Compare commits
328 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 999a5ad562 | |||
| 2ea39a3d41 | |||
| 8fb6f2154d | |||
| c938148619 | |||
| 2512d686a1 | |||
| f44abcc526 | |||
| a99932b427 | |||
| 6d5801bb1f | |||
| 8aba4845bf | |||
| 2ec92ee8bf | |||
| 7c77a378c1 | |||
| 672eabc134 | |||
| a1a2fa3704 | |||
| 22a4978459 | |||
| 1456336652 | |||
| b975716759 | |||
| 4b1edb0617 | |||
| 944e553669 | |||
| cc32c2c4ab | |||
| a1e97c94ac | |||
| c7f59e48f4 | |||
| 4666057066 | |||
| 7138086c3f | |||
| 83e168f326 | |||
| a4abcdefa3 | |||
| 68a3c85186 | |||
| 88c086482e | |||
| feabf9f350 | |||
| 50c6637c1b | |||
| ee9d55ca95 | |||
| a886217223 | |||
| de9884e063 | |||
| bbefda66e2 | |||
| a37c4138a1 | |||
| d6f391430f | |||
| 68b2aa9137 | |||
| f8fa0d1b44 | |||
| 9a333b23d7 | |||
| 663b5c47b9 | |||
| 45c521e1a6 | |||
| e34669a52e | |||
| d434f83c2c | |||
| c310115fd2 | |||
| 3024f76e5f | |||
| 6bc71553ab | |||
| ed1730431c | |||
| 01e80fce4a | |||
| e69f1bd0cf | |||
| f55bedee2e | |||
| e470435cf1 | |||
| 00f9239ef9 | |||
| 3513e508b7 | |||
| c15c2b7bd2 | |||
| b6eaa704a2 | |||
| 2597a7b34a | |||
| 7203cd56fd | |||
| ab3e818bb9 | |||
| b5500a5be8 | |||
| 9095ac847d | |||
| 4b5f6adbae | |||
| ecb8ba72eb | |||
| 4fdecf9a25 | |||
| 2bbd8edbf6 | |||
| beb093aebb | |||
| b1b326018f | |||
| 08889cad88 | |||
| a4630b9314 | |||
| 39d44bb384 | |||
| 65ee0f9c61 | |||
| 76938e206d | |||
| 0b3d81ecbf | |||
| 4be6852b94 | |||
| f7b76c572f | |||
| 05ddc5c92e | |||
| b55e68f98d | |||
| beaa24754c | |||
| aed8cac439 | |||
| af4eeceb6a | |||
| 7b507dec94 | |||
| 2c0334c4fe | |||
| 92cbdbfdd3 | |||
| e78b2d8992 | |||
| 9d58922462 | |||
| b5ac48c126 | |||
| 69d0f5ee78 | |||
| 661b5c1099 | |||
| ff70637a0d | |||
| 06c1cf247e | |||
| 400653810e | |||
| b3936348f5 | |||
| c61b0b3968 | |||
| 0a5211b038 | |||
| 38be702188 | |||
| d42372e996 | |||
| 45231ba69e | |||
| 42c7b8b927 | |||
| e5a1db995d | |||
| d32eae8aac | |||
| 63b645b405 | |||
| 0e82cb442f | |||
| d94ed2e630 | |||
| c8f74c39d6 | |||
| 44b8793e2f | |||
| a4b4733767 | |||
| 8f168ab811 | |||
| eb129c2fad | |||
| 0d5bd0a9f0 | |||
| 4d97280d74 | |||
| e5ec4abe04 | |||
| 7688dfde66 | |||
| e1f84a3474 | |||
| 7852aad60f | |||
| 034d4b4359 | |||
| 799cf5587d | |||
| c1b781fac0 | |||
| 7b2b9d479a | |||
| 92de4ae496 | |||
| a0293bac85 | |||
| c1d9a4547b | |||
| 6499f6365e | |||
| 97e1a44c1a | |||
| 1b3af05d0a | |||
| e7ecce2859 | |||
| 1f8e9f21ce | |||
| e7537d032e | |||
| 2b3e34c7e8 | |||
| dde556a3d3 | |||
| b86172a98d | |||
| 22edc3cdfb | |||
| 4f6dec0cf2 | |||
| 23ad5c0247 | |||
| 0445693a16 | |||
| c7d22858ba | |||
| 0b994ff1c3 | |||
| 12ecc30c57 | |||
| 190cf0c794 | |||
| 6b3749f5a2 | |||
| d156be3442 | |||
| f29bc107d4 | |||
| 10975eff07 | |||
| cc48309c7c | |||
| 4534101d10 | |||
| 5b8707e21e | |||
| 76d123edf3 | |||
| 62675e8fe4 | |||
| 46acf3cba0 | |||
| 373229ab7a | |||
| 2dbf476c45 | |||
| 13cb1903a9 | |||
| 8d20efcfbb | |||
| c661f7bd1a | |||
| e5158d8828 | |||
| 07f7550931 | |||
| 8c1e457150 | |||
| 6923a983aa | |||
| 1d10c9535c | |||
| 3b3660da9a | |||
| dd699b706f | |||
| 0b1efe4911 | |||
| 580959f856 | |||
| bf2587c7fa | |||
| 26ff646ace | |||
| 9e1958e7b0 | |||
| e6923490fd | |||
| d7a43afd90 | |||
| fabc3bc274 | |||
| b6eed20af2 | |||
| 936c6d71db | |||
| 72aa97dae8 | |||
| 1c0a1d0db0 | |||
| 37feee1eb3 | |||
| 94c273780a | |||
| 93c08f9de1 | |||
| 4f96bbd6ec | |||
| 7dba1b7935 | |||
| 8102c73f83 | |||
| 8c36e7ef84 | |||
| 95cbf82e38 | |||
| 5bca435146 | |||
| 69270f4cfb | |||
| 01230bf16b | |||
| ebce90b984 | |||
| 04584fb2da | |||
| 5447f08c06 | |||
| 650363ce67 | |||
| 85456d3833 | |||
| 901354002e | |||
| f4a021d3da | |||
| 316fb197a8 | |||
| 67decc42f0 | |||
| 201fe03d20 | |||
| fec572c997 | |||
| 5187f3bd14 | |||
| 1b5d093148 | |||
| 502327678f | |||
| 5d2fd91c06 | |||
| 33c2d782a9 | |||
| e8ece874b1 | |||
| 1fa14e95a4 | |||
| dd6da78aeb | |||
| d5d4166710 | |||
| 6ec4220668 | |||
| 59cc882265 | |||
| be18649953 | |||
| 41d3a4a903 | |||
| 188d9fc02f | |||
| 5a85d37fa5 | |||
| d70cb7e9ab | |||
| c0aee1558f | |||
| 0d49745a17 | |||
| 2063f8e770 | |||
| 173531be8c | |||
| 01c78ef369 | |||
| bac8673f05 | |||
| 5cc51c5b6e | |||
| be869c6a48 | |||
| 8559f1f450 | |||
| b908c39e45 | |||
| 8c774abe5b | |||
| e2777177b0 | |||
| b8250a8711 | |||
| 02ce730cb2 | |||
| aaf1f0236b | |||
| e488ee2285 | |||
| b6680398c3 | |||
| 0feb8d3dbd | |||
| 0886662360 | |||
| 439ceb5d8e | |||
| ecaf3407fa | |||
| b60264701c | |||
| 60540fa934 | |||
| db8cbdc20a | |||
| 91f6ea84a0 | |||
| b726658692 | |||
| 5f5f14eba7 | |||
| 59b98d5c4d | |||
| 59210cf07d | |||
| 828e034c96 | |||
| c699c139b4 | |||
| b705a786ef | |||
| 20fe909f76 | |||
| ceba69c4bb | |||
| 95eeef13dd | |||
| cfbef45feb | |||
| 3bb82a90db | |||
| abbf0fe60d | |||
| b46bab99f7 | |||
| b9ee858421 | |||
| 594bfc2bc3 | |||
| c600b426f3 | |||
| b95566aa98 | |||
| 795ecf67a5 | |||
| cb3b507ed5 | |||
| 7262310fce | |||
| 69eda3ceee | |||
| 43dc487113 | |||
| 22a8eed1c3 | |||
| 1e35a10f33 | |||
| 69a6eb0fb9 | |||
| 4f7ad7d99a | |||
| 01b47e3864 | |||
| 12c2ae1d17 | |||
| d457c97355 | |||
| 4761c20ad6 | |||
| ed0331c774 | |||
| 968477ea59 | |||
| 82d0384020 | |||
| 1b6d51dc71 | |||
| 9ed259660d | |||
| c8a5b5416e | |||
| 40152e3688 | |||
| 7f411656c2 | |||
| e4f0508a2f | |||
| 5fede2acb7 | |||
| 9ea178be99 | |||
| b49755302c | |||
| 9ef6f286a9 | |||
| c0b99828f9 | |||
| 7414ef4c39 | |||
| 231a4e00f6 | |||
| 52548abe02 | |||
| 70b32af8a7 | |||
| 521c315b30 | |||
| 2acfeb4453 | |||
| 1c20df70f8 | |||
| fffd0cb5fa | |||
| 77a7c994d7 | |||
| 63812af920 | |||
| 869580c913 | |||
| 31deb7d565 | |||
| 1338ec6e2a | |||
| 7843728174 | |||
| a3ad9b5040 | |||
| cb0a3a4f20 | |||
| 6abd2768e8 | |||
| 6e6f73da35 | |||
| 1a64c30427 | |||
| 5753f90752 | |||
| 4d94277836 | |||
| 530c3ff395 | |||
| e031f8f5f5 | |||
| 6c24e19b83 | |||
| 934a28d67c | |||
| cf28f6fdf0 | |||
| eec3d9bed2 | |||
| a5b245dbf5 | |||
| 3e6a427e85 | |||
| 5ac7347c38 | |||
| 5417692566 | |||
| b56e0e6248 | |||
| 0558dfed0f | |||
| 13a5ef0100 | |||
| ac78f83406 | |||
| 40c59aa275 | |||
| 84a75274bf | |||
| da2d11dab6 | |||
| de3f2b5fc2 | |||
| e8f4baf407 | |||
| 92eb6cf6e1 | |||
| 6759ff6003 | |||
| 39284cd851 | |||
| ea0eb167fd | |||
| b6305f1b6e | |||
| 5bd1406c7a | |||
| d988154063 | |||
| 1b76fa8205 | |||
| e87088afb8 | |||
| 1b8d2c60d3 |
@@ -70,3 +70,5 @@ coverage.out
|
||||
|
||||
# root .env — MAVEN_AMBIENT_TOKEN and friends, same class as deploy/telegram.env
|
||||
.env
|
||||
# silero-vad, downloaded (see AGENTS.md)
|
||||
/models/vad/
|
||||
|
||||
@@ -95,6 +95,22 @@ model: the code puts `query: ` in front of a question and `passage: ` in front
|
||||
of a stored note, which is how e5 was trained. The quantized file is the one
|
||||
that is downloaded, deployed and measured.
|
||||
|
||||
## Voice activity model for mavwaked
|
||||
|
||||
`mavwaked` decides an utterance has started with silero-vad when `-vad-model`
|
||||
points at it, and with an energy threshold when it does not. The model is 2.3MB
|
||||
and is not committed:
|
||||
|
||||
```sh
|
||||
mkdir -p models/vad
|
||||
curl -sL -o models/vad/silero_vad.onnx \
|
||||
https://github.com/snakers4/silero-vad/raw/master/src/silero_vad/data/silero_vad.onnx
|
||||
```
|
||||
|
||||
It needs the same `libonnxruntime.so` the embedder needs, passed as `-onnx-lib`
|
||||
or read from `MAVEN_ONNX_LIB`. The measurement is
|
||||
`docs/evals/2026-08-09-silero-vad.md`, and the tests skip without the file.
|
||||
|
||||
**Also need ONNX Runtime** (`libonnxruntime.so`):
|
||||
|
||||
```sh
|
||||
|
||||
@@ -47,27 +47,63 @@ free — `worldGap` in `cmd/mavend/worldmodel.go`, which the owner hears instead
|
||||
answer. A box with no `workstation` block behaves exactly as it did before the seam: naming
|
||||
a gap requires a gap. The offload table in `docs/offload.md` says which caller is which.
|
||||
|
||||
**Speech-to-text moved on 2026-08-09** (V-486). `sttSeam` in `cmd/mavend/voicewire.go`
|
||||
builds an `stt.Pair` beside `modelSeam`, preferring CrisperWhisper 2.0 turbo on workpc
|
||||
with mavsttd as the floor. It takes only the silent half of the rule. A worse
|
||||
transcript is still a turn, so `stt.Pair` has no `TranscribeRemote`. The fallback is
|
||||
never spoken. CW2 turbo scores **10.4% WER in Russian against 27.5%** for the `ggml-small.bin`
|
||||
mavsttd loads, over 200 Golos clips
|
||||
(`docs/evals/2026-08-09-crisperwhisper2-russian-wer.md`). It runs in Intended mode, not
|
||||
Verbatim, though that corpus cannot separate the two.
|
||||
**whisper.cpp cannot load CW2 at all.** It reads its language count off the vocabulary
|
||||
size, and CW2's 51897 tokens shift seven special token ids. So it is not a second
|
||||
endpoint on mavgpud. It is its own transformers service on port 8081
|
||||
(`deploy/cw2/serve.py`), which Maven reaches directly. `stt.HTTPTranscriber`
|
||||
posts raw PCM to it with a bearer token, because audio is the most sensitive thing that
|
||||
crosses this seam. The switch is `workstation.stt` in
|
||||
`deploy/mavend.json`, and deleting the block sends every utterance to mavsttd.
|
||||
**mavgpud runs that service as a second child.** That is not an optimisation. CW2 is a
|
||||
ROCm process on the same card, so it registers on the KFD like any contender. Under its own
|
||||
systemd unit it made mavgpud evict llama-server every few seconds. That took the
|
||||
gemma-4-12b arm down for eight minutes on 2026-08-09 before anyone noticed. The card needs
|
||||
one owner. Any GPU service added beside this daemon has the same defect, so add it to
|
||||
`cmd/mavgpud` and not to systemd. CW2 is on the yield clock and not the idle one. At 1.6GB
|
||||
it denies the card to nobody, and unloading it would only send the next voice turn to the
|
||||
homesrv floor.
|
||||
Text-to-speech has not moved and piper on homesrv is still the only synthesizer.
|
||||
|
||||
## Build & test
|
||||
|
||||
CGO daemons (`mavend`, `mavsttd`, `mavttsd`, `mavenclient`) need the vendored toolchain
|
||||
and libs wired through the Makefile — **do not** call `go build` on them bare, use `make`:
|
||||
|
||||
```sh
|
||||
make build # all 9 binaries
|
||||
make build # all 11 binaries
|
||||
make build-web # single daemon (pure-Go ones: web/waked/poll/caldav build without CGO)
|
||||
make test # go test -race across ./internal/... ./cmd/... with CGO env set
|
||||
```
|
||||
|
||||
Run a single test (must carry the CGO env for packages that touch STT/TTS/voice):
|
||||
Run one package or one test with `make t`. **Do not hand-write the CGO preamble.**
|
||||
Past sessions pasted it about 390 times. That is where the shell-quoting failures
|
||||
came from. This box runs zsh, so an unquoted `-run Test*` or `--include=*.go`
|
||||
dies on "no matches found" before `go` is ever reached.
|
||||
|
||||
```sh
|
||||
CGO_CFLAGS="-I$(pwd)/deps/include -I$(pwd)/deps/whisper.cpp/ggml/include" \
|
||||
CGO_LDFLAGS="-L$(pwd)/deps/lib -Wl,-rpath,$(pwd)/deps/lib" \
|
||||
LD_LIBRARY_PATH="$(pwd)/deps/lib" \
|
||||
deps/go/go/bin/go test -run TestName ./internal/router/
|
||||
make t PKG=./internal/router/
|
||||
make t PKG=./cmd/mavend/ RUN=TestSimulator
|
||||
make t PKG=./internal/router/eval/ RUN='TestONNX' V=1 # V=1 for -v, RACE=0 to drop -race
|
||||
```
|
||||
|
||||
Pure-Go packages (`router`, `memory`, `mavweb`, …) run under a plain `go test ./pkg/`.
|
||||
`t` carries `-race`, so a green `make t` cannot turn red under `make test`. It carries
|
||||
`-count=1`, so a cached PASS from before your edit is never mistaken for a result.
|
||||
|
||||
It also sets `MAVEN_ONNX_LIB`, which the hand-written recipe did not. The four
|
||||
`TestONNX*` measurements self-skip when that variable is unset. The run still prints
|
||||
`ok`. So every targeted eval done the old way reported the hash ratchet while reading
|
||||
as a real embedder score.
|
||||
|
||||
Pure-Go packages (`router`, `memory`, `mavweb`, …) also run under a plain `go test ./pkg/`,
|
||||
but `make t` works everywhere and is one thing to remember.
|
||||
|
||||
## The daemons (`cmd/`)
|
||||
|
||||
@@ -79,22 +115,53 @@ Pure-Go packages (`router`, `memory`, `mavweb`, …) run under a plain `go test
|
||||
| `mavttsd` | Text-to-speech (piper subprocess). |
|
||||
| `mavwaked` | Wake-word / VAD gate. **Not on homesrv** — see below. |
|
||||
| `mavenclient` | Voice loop client (mic → stt → core → tts). **Not on homesrv** — see below. |
|
||||
| `mavpoll` | Telegram long-poll reach. |
|
||||
| `mavpoll` | Environment poller: netdata alarms, uptime-kuma, zenmoney, wireguard presence. Writes facts, sends nothing. Telegram is `internal/delivery/telegramsink`, not this. |
|
||||
| `mavcaldav` | CalDAV calendar sync. |
|
||||
| `mavmaild` | Mail reader (IMAP, read-only). Holds the IMAP password; core never sees it. |
|
||||
| `mavgpud` | GPU supervisor. **Runs on workpc, not homesrv** — own unit, `deploy/mavgpud.service`. Keeps llama-server loaded while the card is free (V-488). Maven never asks it for anything, it reads `/health` through `llm.Pair`. |
|
||||
| `mavupdate` | Not a daemon. Operator CLI a human runs on the box to deploy a new build. |
|
||||
|
||||
Two more binaries have no Makefile target and are built with `go run` or `go build` when
|
||||
they are needed. Neither is deployed.
|
||||
|
||||
| Binary | Role |
|
||||
|---|---|
|
||||
| `mavseal` | Recovery tool. Encrypts a live tmpfs working copy back to the ciphertext file when mavend was killed before `defer st.Close()` sealed it. |
|
||||
| `labelgen` | Runs the stage 0 grammars over utterances and prints JSONL, the training data for the routing heads (V-546). |
|
||||
|
||||
Daemons are wired socket-to-socket, not linked. `internal/ipc` is the client/server wire
|
||||
protocol; the config in `deploy/mavend.json` (with `${VAR}` env expansion from gitignored
|
||||
`deploy/telegram.env`) sets socket paths, model paths, and the phraser/embedder blocks.
|
||||
|
||||
**Seven of the nine run on homesrv. `mavwaked` and `mavenclient` do not, and that is the
|
||||
decision, not an oversight** (Vikunja #463, `docs/plans/17-where-the-voice-loop-runs.md`).
|
||||
**`docker-compose.yml` runs five: `mavend`, `mavsttd`, `mavttsd`, `mavweb`, `mavpoll`.**
|
||||
Count against compose, not against the table. Four of the nine daemons are absent, and each
|
||||
absence has a different reason.
|
||||
|
||||
`mavmaild` and `mavcaldav` are commented out in compose, each with the reason written
|
||||
beside it: the first needs a mail account, the second a CalDAV account, and this box has
|
||||
neither. `mavcaldav` used to appear nowhere at all, which was an oversight; it became a
|
||||
recorded decision on 07-08-2026 (V-644). Two things ride on that absence and the block
|
||||
names them. Agenda questions route to `IntentQuery` at stage 0 (V-498) and the `calendar`
|
||||
query source then reads a table nobody writes. And `loop.State.CalendarBusy` is fed by the
|
||||
same facts, so the gate's "do not nag mid-meeting" is permanently false. Its password is
|
||||
read from a file (`-pass-file`, and `-render-pass-file` for the render collection), never
|
||||
taken as a flag value, which is the rule `mavpoll` and `mavmaild` follow too.
|
||||
|
||||
**`mavwaked` and `mavenclient` are absent by decision, not oversight** (Vikunja #463,
|
||||
`docs/plans/17-where-the-voice-loop-runs.md`).
|
||||
homesrv has a microphone — it is a laptop — but it is in the wrong room, so a wake-word
|
||||
daemon there listens to nobody. They belong on a client machine where the owner is standing.
|
||||
`ipc.Dial` already takes `tcp://host:port?token=...` through the netaddr seam, so nothing
|
||||
needs building to allow it, but no such machine exists yet. **The consequence: the wake
|
||||
word and the VAD gate are covered by unit tests and by nothing else, and no amount of
|
||||
sitting at the box changes that.** Push-to-talk through `/dash` is what QA actually covers.
|
||||
|
||||
**That machine is workpc** (owner's correction, 2026-08-05). This section used to say no
|
||||
such machine existed, which was written when the workstation was only a model host. It is
|
||||
where he sits most of the day and it has the microphone. `ipc.Dial` already takes
|
||||
`tcp://host:port?token=...` through the netaddr seam, so the two daemons need deploying,
|
||||
not building. V-515 is that deployment.
|
||||
|
||||
Until they are deployed, **the wake word and the VAD gate are covered by unit tests and by
|
||||
nothing else**, and push-to-talk through `/dash` is what QA actually covers. Note that
|
||||
deploying them does not by itself prove a wake word: `mavwaked` gates on energy and has no
|
||||
keyword model (V-487), so the loop runs open until that lands.
|
||||
|
||||
## The ecosystem: Nexus, Praxis, Hexis
|
||||
|
||||
@@ -155,6 +222,19 @@ on in deploy** — this section used to say it was wired `nil`, which stopped be
|
||||
Cascade order: `stage0.go` exact-match fast-path → LLM router (when non-nil) → classifier
|
||||
fallback. Any LLM error falls through to the classifier so a turn never breaks on the model.
|
||||
|
||||
**A stage-0 decision is slot-extracted too, since 06-08-2026** (V-572). `fillMatchedSlots`
|
||||
in `router.go` runs the stage-2 extractor over whatever a grammar built and fills only the
|
||||
slots it left empty — a matched value always wins, because the rule read a literal pattern
|
||||
and the extractor guesses. It did not run before, so `ReminderGrammar` handed the daemon
|
||||
`HasTime: false` for "напомни в 11:00 позвонить маме" and `missingFor` read the silence as
|
||||
absence and asked "Когда?". It applies to every grammar and is inert for all but the
|
||||
reminder: `Extract` fills Time, Fn and Key and nothing else, and the query, clock, agenda,
|
||||
feed, list, task and narrative rules all emit intents with no such slot. Benchmarked at
|
||||
20000x, a stage-0 query costs 3.7µs against 3.9µs before. **`Slots.Text` is deliberately not
|
||||
filled** — a grammar that left it empty meant it, and `agendaQueryBuild` hands the query
|
||||
chain the utterance itself. Fixture unchanged at 64/91, with "slots deferred to daemon"
|
||||
6 → 0.
|
||||
|
||||
Measured on the 77-case RU fixture. **Re-measured 2026-08-02: the classifier scores 68.8%
|
||||
full accuracy at p50 16.6µs**, not the 36.8% at p50 31ms that stood here from
|
||||
`docs/evals/2026-07-31-model-bakeoff.md`. That older figure predates the stage 0 rules and the
|
||||
@@ -175,11 +255,21 @@ re-run it, start a **second** llama-server on a fixed host port — the resident
|
||||
`--port 0` inside the container and no host process can reach it.
|
||||
|
||||
**The numbers above are the homesrv floor, not the ceiling.** With the workstation up, routing
|
||||
completes through `llm.Pair` against gemma-4-12b and scores **84.4% full / 93.5% intent-only at
|
||||
p50 329ms** — better than the resident model and about 2.5× faster (`docs/evals/2026-08-02-workstation-gemma4-12b.md`,
|
||||
Vikunja #485). The workstation is never assumed up, so both sets of numbers are live. Judge a
|
||||
completes through `llm.Pair` against the model mavgpud holds, which is better than the resident
|
||||
model and about 2.5× faster. gemma-4-12b scored **84.4% full / 93.5% intent-only at p50 329ms**
|
||||
(`docs/evals/2026-08-02-workstation-gemma4-12b.md`, Vikunja #485). The workstation is never
|
||||
assumed up, so both sets of numbers are live. Judge a
|
||||
routing change against the classifier and the resident model, since those are what always answer.
|
||||
|
||||
**The workstation runs gemma-4-E4B since 2026-08-09** (owner's call), and it is a
|
||||
step down measured the same day (`docs/evals/2026-08-09-e4b-vs-12b-routing.md`).
|
||||
Against a same-session 12B control it scores **83.3% full / 89.6% intent-only,
|
||||
destination 19/33 against 23/33, at p50 294ms against 344ms**. So it costs four
|
||||
destination cases and buys 50ms. Read destination as the finding: it names nothing
|
||||
where the 12B names `recall` or `calendar`, which is safe but walks the whole chain.
|
||||
It also has no MTP and cannot be given any here. The only `gemma4-assistant`
|
||||
draft on disk is trained against the 12B's hidden states.
|
||||
|
||||
**The intended third engine is not a generative model** (owner's call, 05-08-2026, V-546,
|
||||
`docs/plans/18-routing-heads-on-e5-small.md`). Routing has a bounded output space, so it is
|
||||
classification, and the 118M multilingual-e5-small is already resident. Three heads on one
|
||||
@@ -191,6 +281,99 @@ was a hardcode. **Fine-tune a copy of the weights.** The resident embedder backs
|
||||
recall. Training it in place couples routing accuracy to recall@1, with nothing in the
|
||||
suite to name the trade.
|
||||
|
||||
**Two of those heads are trained as of 08-08-2026, and they are not the three
|
||||
above** (V-661, `docs/evals/2026-08-08-routing-heads-two-head.md`). Intent and
|
||||
destination share one masked mean pool. Destination scores a mean **80.8%** over
|
||||
three seeds, best **29/33 (87.9%)**. The classifier cascade scores 12/33 and the
|
||||
cascade with gemma-4-12b scores 24/33, so a 118M encoder beats the 12B teacher it
|
||||
was distilled from. Read the best run as one seed and not a headline, because one
|
||||
case is 3 points on a fixture this small.
|
||||
Recall is 15/15 and world is 5/5. Intent is 93.6% mean over three seeds. That is
|
||||
**not** comparable to the 76.0% and 84.4% those two arms scored: a softmax has no
|
||||
clarify class, so the head's fixture is the 88 cases carrying an intent.
|
||||
|
||||
**A fourth head asks instead of guessing, same day** (V-661,
|
||||
`docs/evals/2026-08-08-clarify-head-four-head.md`). Clarify is not a value
|
||||
of intent, so a softmax cannot emit it. It is a second question over the
|
||||
same pooled vector: can Maven act on this at all. That is why the head's
|
||||
fixture was 88 cases and not 96. Over three seeds it catches **7.0 of the 8
|
||||
`want_clarify` cases and produces 2.3 false clarifies of 88**. The cascade
|
||||
today misses 1 and produces 2, so this is parity with no rules in front of
|
||||
it. Accuracy is the wrong number here and a head that never asks scores
|
||||
91.7%. Confidence is the other half. Max softmax over the intent head reads
|
||||
**0.851 where it is right against 0.604 where it is wrong**, ranking right
|
||||
above wrong in 83.4% of pairs. `Confidence: 1.0` was a hardcode, and this
|
||||
replaces it with a signal. The two are not the same signal: one says which
|
||||
intent is unclear, the other says the utterance carries too little to act
|
||||
on. **The fourth head is not free the way the third was.** Intent,
|
||||
destination and slot F1 each move down one to four points, inside the seed
|
||||
spread. `поужинал` is a false clarify on every seed, which is the same
|
||||
defect `thinSingleToken` was narrowed for on 2026-08-01.
|
||||
|
||||
The corpus for it is generated, because every existing row is answerable by
|
||||
construction. **The router-prompt agreement filter cannot work here**, since
|
||||
`routeGrammar` has no clarify value and a generated line always agrees with
|
||||
itself. A gemma judge replaces it. The first judge called 24 of 40
|
||||
answerable rows underspecified, because it judged against a generic
|
||||
assistant rather than against Maven's contract.
|
||||
|
||||
**Mood is cut, not deferred.** The enum describes her own reply state, not the
|
||||
speaker's emotion, and no dataset maps onto it.
|
||||
|
||||
**A third head landed the same day** (`docs/evals/2026-08-08-slot-head-three-head.md`).
|
||||
BIO slot tags had no Maven-domain corpus, which was true of found corpora and
|
||||
false of made ones. `label_slots.py` distils spans out of gemma-4-12b under a
|
||||
GBNF closed over Maven's own five slots. A span survives only when it is a
|
||||
literal substring of the utterance, so the agreement filter costs no second
|
||||
call. 2178 spans over 1702 rows, 37 dropped, nothing unparsed. Three heads score
|
||||
intent **92.8%**, destination **82.8%** and slot span F1 **72.4%** over three
|
||||
seeds. The slot head is free: both other numbers move less than their own seed
|
||||
spread. Epoch selection reads the intent dev slice alone. Slot F1 is still
|
||||
climbing when it stops, which costs about 4 points.
|
||||
|
||||
The MASSIVE warm-start of step 2 is worth nothing here. Stock e5-small ties it on
|
||||
intent and leads by a third of a case on destination. Nothing argues for keeping
|
||||
that step.
|
||||
|
||||
The floor was a corpus defect and it is fixed. The first 120 floor rows carried
|
||||
one sentence shape, so the head named a destination where the fixture says walk
|
||||
the chain. Rotating six shapes took the floor 3/7 to 6/7 and destination 75.8% to
|
||||
80.8%. What is left is calendar at 3/6 on every seed, which training cannot move:
|
||||
the possessive agenda rules claim those cases at stage 0 and name nothing, so no
|
||||
label reaches the head. That is the same trade V-660 flagged and it wants the
|
||||
owner's call.
|
||||
|
||||
**The heads run in Go and route every turn, since 08-08-2026** (V-664,
|
||||
`docs/evals/2026-08-08-routing-heads-in-go.md`). This section used to say
|
||||
nothing of it ran. `RouterHeads` in `internal/router/heads.go` loads
|
||||
`router_heads.onnx` and reads intent, destination and clarify off one forward
|
||||
pass. It is stage 0b: after the grammars, **before** the resident model, and the
|
||||
classifier is still behind both. Through the cascade it scores intent **96.9%**
|
||||
and destination **75.8%** at p50 27.9ms. That beats the gemma-4-12b cascade,
|
||||
84.4% and 72.7%, at a twelfth of its 329ms. The workstation stays the better
|
||||
phraser and is no longer the better router.
|
||||
|
||||
Three rules around it. The **clarify head decides first**, before the intent
|
||||
threshold. It answers a different question. A thin utterance scores low
|
||||
intent by construction, so gating it cost 6 of 8 ambiguous cases. The
|
||||
**destination head is read on `IntentQuery` only**, since no other intent
|
||||
reaches `queryWalk`. And `headsThreshold` is 0.6, the measured knee: every value
|
||||
to 0.85 drops right answers and keeps the same two wrong ones.
|
||||
|
||||
`voice.embedder.heads_path` is the whole switch. Empty, missing or unloadable
|
||||
means the heads are nil and the cascade is byte-for-byte what shipped before
|
||||
them. **It must never be pointed at `model_path`.** The resident e5-small must
|
||||
not be replaced by the fine-tuned copy. Recall depends on that file scoring
|
||||
what it scored.
|
||||
|
||||
**The hand-written tokenizer read every long word backwards** until this task
|
||||
(`encodeWord`, `onnxembedder.go`). It cost recall@1 7.4 points and recall@3 11.1.
|
||||
Nothing caught it because seeds and queries were mangled the same way, so cosine
|
||||
survived. The heads found it. They are trained through transformers and read
|
||||
through this. The embedder id now carries a tokenizer revision
|
||||
(`@384/tok2`), so fixing the tokenizer triggers `ReembedAll` the way swapping the
|
||||
model file does. Bump `tokenizerRev` on any change to what it emits.
|
||||
|
||||
`Confidence: 1.0` used to be hardcoded in `llmrouter.go`, so the LLM
|
||||
path could never ask for clarification (6/6 refusal cases missed on the fixture) — Vikunja
|
||||
#359. Fixed 31-07-2026 with structural signal (single-token utterance, keyless fact, act with
|
||||
@@ -254,11 +437,183 @@ of the house. A demonstrative ("отметь это как сделанное")
|
||||
`h.surfacedItems` only when exactly one item was spoken. Otherwise the turn goes back to
|
||||
the cascade rather than transitioning the wrong item.
|
||||
|
||||
**Who claimed a turn is now recorded, and so is who did not** (V-564, umbrella
|
||||
V-558). Arbitration between the claimants on the utterance stream is order,
|
||||
hardcoded in the pre-route resolver ladder, in `buildRouter` and in
|
||||
`querySources`. `internal/decision` records one `Record` per turn: every
|
||||
claimant, what it would have made the turn, the score it reported, and whether
|
||||
it won, declined, lost on score, was thinned by a gate or was **never asked**.
|
||||
The record rides the context, the same seam `querysource.go` uses, so a claim
|
||||
site cannot change a route and a context with no record costs nothing. It is
|
||||
installed in `runTurn`, so the mic, telegram and the web all leave the same
|
||||
trail. Storage is a 25-turn in-memory ring on the handler (`decision.Ring`),
|
||||
read over `ipc.TurnDecisions` and rendered as the second table on `/trace`.
|
||||
**It also persists, since 06-08-2026, and that reverses what this section used to
|
||||
say** (V-629, `docs/plans/21-persisting-the-routing-trace.md`). The old rule was
|
||||
that nothing persists, because a turn record is read minutes later or never. The
|
||||
owner reversed it: the routing heads (V-546) cannot be fitted or calibrated
|
||||
without real utterances, and 9 of the 31 modes in `internal/modes` have no seed
|
||||
example at all. The ring did not move. It is still what `/trace` reads and still
|
||||
what a test with no store gets. `cmd/mavend/routingtrace.go` is a second sink
|
||||
beside it, writing `routing_traces` (migration #23). The utterance is stored in
|
||||
clear, because a 384-dimension vector of a short sentence is substantially
|
||||
recoverable and storing vectors instead would be a privacy claim we cannot
|
||||
support. What makes it safe is the same thing that makes the fact store safe.
|
||||
Retention is 14 days, enforced on write and again on start, so a box that goes
|
||||
quiet does not keep every row. Nothing reads it outward, and the rule
|
||||
that his notes and facts are never search input covers this table. `Store.Wipe`
|
||||
deletes it with everything else. A correction (V-630) is promoted out into a
|
||||
seed-shaped row in `routing_labels` (migration #24) and kept, because a label is
|
||||
not a transcript. The transcript still expires. The gesture that writes one is
|
||||
two buttons beside the reply on `/chat`, reached over `ipc.CorrectTurn` and the
|
||||
trace id that now rides back on `ipc.ChatReply`. A turn marked wrong with no
|
||||
target is a usable negative, so naming the intent is never required. The target
|
||||
is one of the seven intents and never free text. **All three reaches offer it as
|
||||
of 06-08-2026**, and this section used to say only `/chat` did. Voice is the
|
||||
`repair` rung, which has read spoken corrections since V-455 and now writes the
|
||||
durable label beside the classifier seed it always wrote; a spoken negative with
|
||||
no target is its own rung, `repair-negative` (V-636, `docs/plans/22-correcting-a-turn.md`).
|
||||
Telegram is an inline keyboard under the reply, and it needed the chat to become
|
||||
readable first — **telegram is no longer outbound only** (V-637,
|
||||
`docs/plans/23-inbound-telegram.md`). The poller is dark unless the `telegram`
|
||||
block says `intake`, it long-polls because the box takes no inbound connections,
|
||||
it accepts `chat_id` and no other sender, and it drops whatever queued while the
|
||||
daemon was down. It reaches the daemon through `ipc.CoreAPI` alone, so a chat
|
||||
turn takes the path `POST /api/chat` takes. Note that the turn source is still
|
||||
`tap:text` for both, so provenance cannot tell a chat turn from a typed one.
|
||||
Adding a rung to the ladder
|
||||
in `runTurn` means adding its name to `preRouteLadder` in
|
||||
`cmd/mavend/decisiontrace.go`, or that rung is silently missing from the record.
|
||||
|
||||
**A route now says where the answer lives, not only that the turn is a question**
|
||||
(V-655, 07-08-2026). `query` was a shrug. The cascade sorted an utterance into one of
|
||||
seven intents, with stage 0, the resident model and the classifier behind it. Then
|
||||
`IntentQuery` handed the turn to `querySources` in the daemon. That is twenty-two branches
|
||||
deciding by seed similarity in a fixed order. It has no fixture and no accuracy
|
||||
number, no model arm and no floor. `Decision.Source` (`internal/router/source.go`) is
|
||||
the second half of the route. Twelve destinations, not twenty-two. The three recall
|
||||
passes plus `fact-by-key` are one destination from outside. So are search, Kiwix and
|
||||
the URL reader.
|
||||
|
||||
**`SourceUnknown` is a real value and it is the floor.** Nothing named a destination,
|
||||
so the daemon walks the whole chain. That is byte-for-byte what shipped before the
|
||||
field existed. The classifier arm names nothing, so a box whose model is down routes
|
||||
queries exactly as it did.
|
||||
|
||||
`queryWalk` in `cmd/mavend/actions_query.go` takes sources **out** and moves none.
|
||||
That is the safety argument and it is not negotiable. The table's order is
|
||||
load-bearing. Every comment on it argues a reason between two sources, and above all
|
||||
it carries "the owner's data first, then the world". Naming `SourceWorld` does not
|
||||
send the turn outside on its own. His notes and his facts still run first, because
|
||||
they look rather than guess.
|
||||
|
||||
**The personal boundary is the one exception and it is deliberate.** It guesses,
|
||||
so naming `SourceWorld` drops it. That is what stops it answering "кто такой
|
||||
Линус Торвальдс?" with "не нашла у тебя такой записи", which it did on
|
||||
2026-08-07. `TestNamingRecallKeepsTheBoundary` pins the other half: naming
|
||||
`SourceRecall` keeps the boundary in front of the world.
|
||||
|
||||
**Only a stage 0 grammar may drop it** (owner's call, 09-08-2026, V-666). The
|
||||
question of who is allowed to was open until then. Three deciders name a
|
||||
destination and two of them infer it: the routing heads and the resident model.
|
||||
An inferred `SourceWorld` on a question about him would reach SearXNG, and that
|
||||
widens what is asked rather than costing a local answer. So `Decision.SourceAnchored`
|
||||
carries the provenance. It is a field and not `Stage == 0`. Stage 0 also means
|
||||
confidence 1.0 and an anchored claim band, and one of those could stop implying
|
||||
the others. `queryWalk` reads it for the source marked `boundary: true` and for
|
||||
no other. So every other guesser still comes off the turn, whoever named the
|
||||
destination. `TestOnlyAGrammarMayDropTheBoundary` pins both directions.
|
||||
`definitionQueryPattern` claims "кто такой X", so the 2026-08-07 case is still
|
||||
anchored and still answered.
|
||||
|
||||
What comes out is only the sources that **guess**. Those decide a turn is theirs by
|
||||
cosine against frozen seeds, then answer whatever they claimed. They hold no table
|
||||
that could come back empty. Weather is the pure case and has no local data at
|
||||
all. It was measured on the box on 2026-08-07
|
||||
(`docs/evals/2026-08-07-week-of-usage.md` section 4). It answered both "что такое
|
||||
TCP?" and "сколько будет 17 на 23?" with "для какого города?". The feed answered "какой у меня любимый язык?" with kernel headlines.
|
||||
The personal boundary answered "кто такой Линус Торвальдс?" with "не нашла у тебя
|
||||
такой записи". A source that guesses is marked `guesses: true` in the table. One that
|
||||
looks is not, and it is always asked.
|
||||
|
||||
Stage 0 fills the destination where a rule already knows it. `WorldQueryGrammars()`
|
||||
(`internal/router/worldquery.go`) claims "что такое X" and "сколько будет 17 на 23".
|
||||
It is wired after the agenda rules and **before** the feed and list rules.
|
||||
"что такое лента" is a definition question, and the feed rule would take it on the
|
||||
noun alone.
|
||||
`calendar-query` and `event-time-query` name the calendar. The possessive agenda rules
|
||||
deliberately do not. "что у меня в списке покупок" matches `agenda-query`, and naming
|
||||
the calendar there would take the list source off the turn.
|
||||
|
||||
Fixture unchanged at **69/91 classifier+ONNX**, measured both sides. That is the
|
||||
expected result, because it scores intent and no case here changes intent.
|
||||
|
||||
**The destination has its own fixture and its own number as of 08-08-2026**
|
||||
(V-659, `docs/evals/2026-08-08-destination-fixture.md`). This section used to say
|
||||
it had neither. `want_source` on `eval.Case` is a pointer, because the destination
|
||||
has three states and a bare string has two. Absent is every intent but query,
|
||||
which never reaches `queryWalk`. Present and empty is the `SourceUnknown`
|
||||
contract: name nothing and walk the chain. Present and named is a destination the
|
||||
route must produce. Thirty-three of ninety-six cases carry one.
|
||||
|
||||
A destination miss does **not** fail the case. It lands in `Outcome.SourceReason`
|
||||
and never in `Reasons`, so `Accuracy` and `IntentAccuracy` mean what they meant
|
||||
and `SourceAccuracy` is a second number over the labelled cases only. Intent and
|
||||
destination are two decisions, and one number hides which one moved. A route that
|
||||
lost its intent scores no destination hit, or a clarify would satisfy an empty
|
||||
label for free.
|
||||
|
||||
Measured classifier+ONNX: intent **73/96 (76.0%)**, destination **12/33 (36.4%)**.
|
||||
The split is the finding. World is 5/5, because a stage 0 rule names it. The
|
||||
`SourceUnknown` floor is 5/7. Calendar is 2/6, because the possessive agenda
|
||||
rules deliberately do not name it. And **recall is 0/15, because nothing
|
||||
anywhere names it**. Those turns are still answered, since the chain walks
|
||||
recall early. Recall is the number the fourth head has to move.
|
||||
|
||||
Seven cases assert the floor and five of them are homelab operations. They
|
||||
cluster because `SourceRecall`, `SourceNetwork` and `SourceAttention` overlap on
|
||||
every question about the box. The other two are `ru-query-005` and
|
||||
`ru-query-014`. No query source reads the reminder store, and a deadline could
|
||||
sit in tasks, the calendar or Praxis. `mavpoll` writes its netdata and uptime-kuma
|
||||
observations into the fact store recall reads. That is a finding about the enum,
|
||||
not a gap in the labelling. The owner confirmed all seven floor labels on
|
||||
08-08-2026, so they are a decision rather than an agent's guess.
|
||||
|
||||
`baselineGrammars` in `eval_test.go` mirrors `buildRouter` and had drifted:
|
||||
`WorldQueryGrammars` was wired into the daemon by V-655 and not into the mirror,
|
||||
so the fixture scored a grammar set nobody runs. Fixed by V-659, worth 3 points of
|
||||
destination and nothing else. Check that function when adding a grammar.
|
||||
|
||||
**The model arm landed the same day** (V-660,
|
||||
`docs/evals/2026-08-08-destination-model-arm.md`). `routeGrammar` carries a
|
||||
`source` rule closed over `router.Sources` plus the empty floor, so the model
|
||||
cannot emit a destination that does not exist. The prompt lists the twelve in
|
||||
Russian and says `""` is a normal answer to give often. `LLMRouter.Route` reads it
|
||||
back through `ValidSource` and on `IntentQuery` alone. Against gemma-4-12b on the
|
||||
workstation the cascade scores destination **24/33 (72.7%)** with intent unmoved
|
||||
at 84.4%, and **recall goes 0/15 to 14/15**. The resident Qwen3-1.7B is
|
||||
unmeasured, because it binds `--port 0` inside the container.
|
||||
|
||||
**Stage 0 now costs four destination points.** It did not before. The four cases
|
||||
the cascade loses and the model alone wins are all calendar. The possessive
|
||||
agenda rules claim them first and name nothing on purpose. That caution was free
|
||||
while nothing downstream could name anything either. It is not free now, and the
|
||||
fix is the owner's call rather than a quiet edit.
|
||||
|
||||
The last arm is V-546. Intent, mood and BIO slot tags were already three heads on
|
||||
one forward pass of the resident e5-small. Destination is a fourth head on the
|
||||
same pass, and 72.7% from a 12B teacher is the label source for training it.
|
||||
|
||||
## LLM output contract
|
||||
|
||||
All phrasing paths emit `{"response":"...","mood":"..."}` (parsed in `replier_llm.go` and
|
||||
`internal/phraser/llmphraser.go`), with fallback to plain text and the legacy
|
||||
`{"body","summary"}`. Mood is a fixed enum. Router prompt is a separate contract:
|
||||
All phrasing paths emit `{"response":"...","mood":"..."}`, with fallback to plain text when
|
||||
the model skips the JSON. **One parser, `parseResponseMood` in
|
||||
`internal/phraser/parse.go`**, and every path reaches it: the six `LLMPhraser` methods,
|
||||
`PhraseWorld`, and `Replier.PhraseReply`, which `cmd/mavend/replier_llm.go` wraps — that file
|
||||
holds the stub fallback and no parsing of its own. The legacy `{"body","summary"}` fallback
|
||||
was deleted on 2026-08-06 (V-397): it was the contract before `{"response","mood"}` replaced
|
||||
it, no prompt asks for that shape, the GBNF cannot emit it, and no test covered it.
|
||||
Mood is a fixed enum. Router prompt is a separate contract:
|
||||
`[{"intent":<enum>, key?, value?, text?, verb?}, ...]`, 7 intents (`fact, reminder,
|
||||
note, query, act, chat, system`). `llm/check_prompt_parity.py` in the training
|
||||
workspace enforces that the Go and relabelling prompts remain identical.
|
||||
@@ -320,11 +675,25 @@ world questions, so she needs to read external sources. What replaces it:
|
||||
`wikipedia_ru_all_maxi_2026-02` verbatim** through `kiwix.book_ru`. The RU→EN rewriter
|
||||
is the workaround for an English book and is skipped there. Kiwix catalog names come
|
||||
from the filename, not the `<name>` field.
|
||||
**That verbatim path sent the whole sentence to a keyword engine until 09-08-2026**
|
||||
(V-668, `docs/evals/2026-08-09-kiwix-topic-retrieval.md`). Kiwix ranks by keyword
|
||||
overlap, so the question words outrank the one word naming the article. "что такое TCP"
|
||||
returned "Перехват TCP-соединения". "кто написал Войну и мир" returned an episode of
|
||||
Doctor Who. `kiwix.Topic` drops the narrative request, the interrogative and a verb
|
||||
behind one. `kiwix.TitlePath` tries the exact article first, since a ZIM is addressable
|
||||
by title and a wrong title is a 404. Four of eight questions reach the right article
|
||||
where they did not, two were already right, and nothing regressed. Both apply on the
|
||||
verbatim path alone. The rewriter already reduces a question, and reducing twice takes
|
||||
the topic off its input.
|
||||
`Response.Empty()` is the whole gate and there is no quality threshold in front of it:
|
||||
the three signals one could read were measured on 2026-08-05 and none of them separate a
|
||||
real question from an invented one. Token overlap would cost "столица Франции" its
|
||||
answer, because the answer is Париж and that word is not in the question. See
|
||||
`docs/evals/2026-08-05-search-quality-signals.md` (V-539). **Which query source claimed
|
||||
`docs/evals/2026-08-05-search-quality-signals.md` (V-539). **The embedder is not a
|
||||
fourth signal**, measured 2026-08-09 (V-668). Query-to-passage cosine scores 0.79 to
|
||||
0.91 on answerable questions and 0.75 to 0.84 on unanswerable ones, and the sets
|
||||
overlap. The wrong TCP article scored 0.8653, above five of six unanswerable rows. It
|
||||
measures topic and not whether the passage answers, so no threshold splits them. **Which query source claimed
|
||||
a turn is readable on `/chat`** as a badge beside the reply, carried on
|
||||
`ipc.ChatReply.Source` and noted by `noteQuerySource` in `cmd/mavend/querysource.go`. It
|
||||
rides the context, so `handleText` keeps the one string signature the mic, telegram and
|
||||
@@ -363,8 +732,11 @@ start of a session rather than one lookup per first use:
|
||||
ToolSearch("select:mcp__vikunja__list_tasks,mcp__vikunja__get_task_details,mcp__vikunja__create_task,mcp__vikunja__update_task")
|
||||
```
|
||||
|
||||
`update_task` carrying a `description` resets `done` to false, so closing a task with a
|
||||
write-up takes two calls: the description, then `done: true`.
|
||||
**Close a finished task with `done: true` and nothing else** (owner's call, 07-08-2026).
|
||||
Do not write a completion summary into the description on the way out. It is lost anyway,
|
||||
and the durable record is the commit messages and the merged PR. Note that `update_task`
|
||||
carrying a `description` resets `done` to false, which is why a write-up ever took two
|
||||
calls.
|
||||
|
||||
## Session workflow
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ PIPER_BIN := $(shell pwd)/deps/piper/piper
|
||||
PIPER_MODEL := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
|
||||
PIPER_ESPEAK := $(shell pwd)/deps/piper/espeak-ng-data
|
||||
|
||||
.PHONY: simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go deps-sentinel tidy eval-router eval-reach eval-recall eval-phrasing eval-models build-gpud
|
||||
.PHONY: t audit simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go deps-sentinel tidy eval-router eval-reach eval-recall eval-phrasing eval-models build-gpud
|
||||
|
||||
all: build
|
||||
|
||||
@@ -128,6 +128,35 @@ test: fmt-check vet
|
||||
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
||||
$(GO) test -race -coverprofile=coverage.out ./internal/... ./cmd/...
|
||||
|
||||
# t — run ONE package or ONE test with the toolchain env already wired. This is
|
||||
# the iteration target; `test` is the gate. Reach for it instead of pasting the
|
||||
# CGO_CFLAGS/CGO_LDFLAGS/LD_LIBRARY_PATH preamble by hand, which is how it was
|
||||
# done ~390 times across past sessions and is where the shell-quoting failures
|
||||
# came from -- the interactive shell here is zsh, and an unquoted `-run Test*`
|
||||
# or `--include=*.go` dies on "no matches found" before go ever starts.
|
||||
#
|
||||
# make t # whole tree (same scope as `test`)
|
||||
# make t PKG=./internal/router/
|
||||
# make t PKG=./cmd/mavend/ RUN=TestSimulator
|
||||
# make t PKG=./internal/router/eval/ RUN='TestONNX' V=1
|
||||
# make t PKG=./internal/store/ RACE=0 # drop -race when iterating hot
|
||||
#
|
||||
# -race is on by default so a green `make t` cannot turn red under `make test`.
|
||||
# -count=1 because a cached PASS from before your edit is worse than no answer.
|
||||
# MAVEN_ONNX_LIB is set for the same reason: the four TestONNX* measurements
|
||||
# self-skip when it is unset, so a targeted eval run would otherwise report the
|
||||
# deterministic hash ratchet and look like it scored the real embedder.
|
||||
PKG ?= ./internal/... ./cmd/...
|
||||
RUN ?=
|
||||
V ?=
|
||||
RACE ?= 1
|
||||
|
||||
t:
|
||||
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
||||
MAVEN_ONNX_LIB="$(MAVEN_ONNX_LIB)" \
|
||||
$(GO) test $(if $(V),-v,) $(if $(filter-out 0,$(RACE)),-race,) -count=1 \
|
||||
$(if $(RUN),-run '$(RUN)',) $(PKG)
|
||||
|
||||
# eval-router — score the held-out RU routing fixture (internal/router/eval).
|
||||
# Verbose so the report tables land in the terminal. MAVEN_ONNX_LIB points the
|
||||
# prod-representative baseline at the vendored runtime; override it or set it
|
||||
@@ -189,6 +218,16 @@ eval-models:
|
||||
# scores the fixtures against ggml-small and self-skips when the model is
|
||||
# absent, and TestGoldenFixturesAreCanonical, which checks the committed audio
|
||||
# and the manifest with no model at all.
|
||||
# audit — the repo inventory: LOC per package, open TODOs, real stubs, living-doc
|
||||
# staleness, test shape, packages with no test. Read-only, prints, writes nothing.
|
||||
# Run it instead of rebuilding the same greps by hand; past sessions spent 93 of
|
||||
# them on this before their first edit. SECTION=loc|todo|stubs|docs|tests|gaps
|
||||
# narrows it.
|
||||
SECTION ?= all
|
||||
|
||||
audit:
|
||||
@SECTION="$(SECTION)" ./scripts/audit.sh
|
||||
|
||||
stt-fixtures:
|
||||
./scripts/gen-stt-fixtures.sh
|
||||
|
||||
|
||||
@@ -0,0 +1,113 @@
|
||||
// Command labelgen labels utterances with the stage 0 grammars and prints JSONL.
|
||||
//
|
||||
// docs/plans/18-routing-heads-on-e5-small.md calls the labeled set the whole
|
||||
// project, and it names the stage 0 grammars as the high-precision label
|
||||
// functions to start from. This runs them — the real ones, in the real
|
||||
// buildRouter order — rather than a reimplementation, so a rule change moves
|
||||
// the training data with it.
|
||||
//
|
||||
// A grammar that declines leaves the line unlabeled. Those go to the model, and
|
||||
// keeping them is the point: a set labeled only by the rules teaches only the
|
||||
// rules.
|
||||
//
|
||||
// go run ./cmd/labelgen < utterances.txt > labeled.jsonl
|
||||
//
|
||||
// The wakeword-act grammar is absent, because its allowlist is the deployment's
|
||||
// enabled tool names and this tool has no deployment. Every other rule is here.
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// label is one output row. The grammar name rides along so a reviewer can see
|
||||
// which rule made the claim, and so a rule that turns out to be wrong can have
|
||||
// its rows pulled without re-running everything.
|
||||
type label struct {
|
||||
Utterance string `json:"utterance"`
|
||||
Intent string `json:"intent,omitempty"`
|
||||
Grammar string `json:"grammar,omitempty"`
|
||||
Key string `json:"key,omitempty"`
|
||||
Value string `json:"value,omitempty"`
|
||||
Fn string `json:"fn,omitempty"`
|
||||
Text string `json:"text,omitempty"`
|
||||
Labeled bool `json:"labeled"`
|
||||
}
|
||||
|
||||
// grammars mirrors buildRouter's order in cmd/mavend/voicewire.go. Order is
|
||||
// load-bearing there and so it is here: the agenda rules must sit after the
|
||||
// clock rules, Praxis before the capture marker, the narrative rules last.
|
||||
func grammars() []router.Grammar {
|
||||
var g []router.Grammar
|
||||
g = append(g, router.SystemTimeDateGrammars()...)
|
||||
g = append(g, router.AgendaQueryGrammars()...)
|
||||
g = append(g, router.FeedQueryGrammar())
|
||||
g = append(g, router.TaskListGrammar())
|
||||
g = append(g, router.ListGrammars()...)
|
||||
g = append(g, router.ReminderGrammar())
|
||||
g = append(g, router.PraxisGrammars()...)
|
||||
g = append(g, router.TaskCaptureGrammar())
|
||||
g = append(g, router.NarrativeQueryGrammars()...)
|
||||
return g
|
||||
}
|
||||
|
||||
func match(gs []router.Grammar, utterance string) label {
|
||||
out := label{Utterance: utterance}
|
||||
for _, g := range gs {
|
||||
m := g.Pattern.FindStringSubmatch(utterance)
|
||||
if m == nil {
|
||||
continue
|
||||
}
|
||||
d, ok := g.Build(m)
|
||||
if !ok {
|
||||
continue // the rule saw its shape and declined it
|
||||
}
|
||||
out.Intent = string(d.Intent)
|
||||
out.Grammar = g.Name
|
||||
out.Key = d.Slots.Key
|
||||
out.Value = d.Slots.Value
|
||||
out.Fn = d.Slots.Fn
|
||||
out.Text = d.Slots.Text
|
||||
out.Labeled = true
|
||||
return out
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func main() {
|
||||
gs := grammars()
|
||||
in := bufio.NewScanner(os.Stdin)
|
||||
in.Buffer(make([]byte, 0, 64*1024), 1024*1024)
|
||||
out := bufio.NewWriter(os.Stdout)
|
||||
defer out.Flush()
|
||||
|
||||
enc := json.NewEncoder(out)
|
||||
var seen, labeled int
|
||||
for in.Scan() {
|
||||
line := strings.TrimSpace(in.Text())
|
||||
if line == "" || strings.HasPrefix(line, "#") {
|
||||
continue
|
||||
}
|
||||
seen++
|
||||
l := match(gs, line)
|
||||
if l.Labeled {
|
||||
labeled++
|
||||
}
|
||||
if err := enc.Encode(l); err != nil {
|
||||
fmt.Fprintln(os.Stderr, "labelgen:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
}
|
||||
if err := in.Err(); err != nil {
|
||||
fmt.Fprintln(os.Stderr, "labelgen:", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
// Coverage on stderr, so the count is visible without polluting the JSONL.
|
||||
fmt.Fprintf(os.Stderr, "labelgen: %d/%d labeled by %d grammars\n", labeled, seen, len(gs))
|
||||
}
|
||||
+41
-9
@@ -50,10 +50,10 @@ func run(args []string) error {
|
||||
socket := fs.String("socket", "", "core IPC socket path (required)")
|
||||
url := fs.String("url", "", "CalDAV calendar URL, e.g. http://localhost:5232/kami/personal (required)")
|
||||
user := fs.String("user", "", "CalDAV basic-auth username (required)")
|
||||
pass := fs.String("pass", "", "CalDAV basic-auth password (required)")
|
||||
passFile := fs.String("pass-file", "", "file holding the CalDAV basic-auth password (required — never passed as a flag value)")
|
||||
renderURL := fs.String("render-url", "", "CalDAV collection maven publishes her own reminders to; empty disables rendering")
|
||||
renderUser := fs.String("render-user", "", "basic-auth username for -render-url (defaults to -user)")
|
||||
renderPass := fs.String("render-pass", "", "basic-auth password for -render-url (defaults to -pass)")
|
||||
renderPassFile := fs.String("render-pass-file", "", "file holding the password for -render-url (defaults to -pass-file)")
|
||||
renderDur := fs.Duration("render-duration", calendar.DefaultReminderDuration, "how long a rendered reminder occupies")
|
||||
interval := fs.Duration("interval", 5*time.Minute, "poll cadence")
|
||||
timeout := fs.Duration("timeout", 10*time.Second, "per-request HTTP timeout")
|
||||
@@ -63,13 +63,22 @@ func run(args []string) error {
|
||||
if *socket == "" {
|
||||
return fmt.Errorf("-socket is required")
|
||||
}
|
||||
if *url == "" || *user == "" || *pass == "" {
|
||||
return fmt.Errorf("-url, -user, -pass are required")
|
||||
if *url == "" || *user == "" || *passFile == "" {
|
||||
return fmt.Errorf("-url, -user, -pass-file are required")
|
||||
}
|
||||
if err := checkRenderTarget([]string{*url}, *renderURL); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// The password is read from a file, never taken as a flag value: an argv
|
||||
// secret is visible in `ps` to every user on the box and lands in the compose
|
||||
// file and the shell history. Same rule mavmaild and mavpoll follow. Read
|
||||
// once at start, so a rotated password means a restart.
|
||||
pass, err := readSecret(*passFile)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
|
||||
defer stop()
|
||||
|
||||
@@ -85,17 +94,20 @@ func run(args []string) error {
|
||||
http: hc,
|
||||
url: strings.TrimRight(*url, "/"),
|
||||
user: *user,
|
||||
pass: *pass,
|
||||
pass: pass,
|
||||
}
|
||||
|
||||
var rend *renderer
|
||||
if *renderURL != "" {
|
||||
ru, rp := *renderUser, *renderPass
|
||||
ru, rp := *renderUser, pass
|
||||
if ru == "" {
|
||||
ru = *user
|
||||
}
|
||||
if rp == "" {
|
||||
rp = *pass
|
||||
if *renderPassFile != "" {
|
||||
rp, err = readSecret(*renderPassFile)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
rend = newRenderer(core, hc, *renderURL, ru, rp, *renderDur)
|
||||
log.Printf("mavcaldav: rendering reminders to %s", *renderURL)
|
||||
@@ -131,6 +143,21 @@ func run(args []string) error {
|
||||
// It takes the whole read set, not one URL. The guarantee in the package
|
||||
// comment is about every calendar maven reads, and a second read target added
|
||||
// later must not quietly fall outside the check.
|
||||
// readSecret reads one credential from a file and refuses an empty one. An
|
||||
// empty file is a deployment mistake, not a password, and CalDAV basic auth
|
||||
// would send it and get a 401 every poll.
|
||||
func readSecret(path string) (string, error) {
|
||||
raw, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("read password file: %w", err)
|
||||
}
|
||||
secret := strings.TrimSpace(string(raw))
|
||||
if secret == "" {
|
||||
return "", fmt.Errorf("password file %s is empty", path)
|
||||
}
|
||||
return secret, nil
|
||||
}
|
||||
|
||||
func checkRenderTarget(readURLs []string, renderURL string) error {
|
||||
if renderURL == "" {
|
||||
return nil
|
||||
@@ -188,6 +215,11 @@ func (p *poller) pollOnce(ctx context.Context) {
|
||||
}
|
||||
}
|
||||
|
||||
// maxResponseBody bounds every CalDAV response this daemon reads (the poller's
|
||||
// GET and the renderer's PROPFIND) — a misbehaving or malicious server gets a
|
||||
// truncated read, not an unbounded one.
|
||||
const maxResponseBody = 4 << 20
|
||||
|
||||
// fetchEvents GETs the calendar URL and parses VEVENTs from the iCal response.
|
||||
func (p *poller) fetchEvents(ctx context.Context, now time.Time) ([]calendar.Event, error) {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, p.url, nil)
|
||||
@@ -203,7 +235,7 @@ func (p *poller) fetchEvents(ctx context.Context, now time.Time) ([]calendar.Eve
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
body, err := io.ReadAll(io.LimitReader(resp.Body, 4<<20))
|
||||
body, err := io.ReadAll(io.LimitReader(resp.Body, maxResponseBody))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
@@ -5,12 +5,38 @@ import (
|
||||
"fmt"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
// The password comes from a file so it never reaches argv. An empty or missing
|
||||
// file must fail at start rather than authenticate as "" against his calendar.
|
||||
func TestReadSecret(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
good := filepath.Join(dir, "ok")
|
||||
if err := os.WriteFile(good, []byte(" hunter2\n"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, err := readSecret(good); err != nil || got != "hunter2" {
|
||||
t.Fatalf("readSecret(good) = %q, %v; want \"hunter2\", nil", got, err)
|
||||
}
|
||||
|
||||
empty := filepath.Join(dir, "empty")
|
||||
if err := os.WriteFile(empty, []byte("\n \n"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := readSecret(empty); err == nil {
|
||||
t.Fatal("readSecret(empty) = nil error, want refusal")
|
||||
}
|
||||
if _, err := readSecret(filepath.Join(dir, "absent")); err == nil {
|
||||
t.Fatal("readSecret(absent) = nil error, want refusal")
|
||||
}
|
||||
}
|
||||
|
||||
type fakeCore struct {
|
||||
ipc.UnimplementedCoreAPI
|
||||
facts map[string]ipc.Fact // composite key "key|source" → Fact
|
||||
|
||||
@@ -142,7 +142,7 @@ func (r *renderer) listPublished(ctx context.Context) ([]int64, error) {
|
||||
return nil, err
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
raw, err := io.ReadAll(io.LimitReader(resp.Body, 4<<20))
|
||||
raw, err := io.ReadAll(io.LimitReader(resp.Body, maxResponseBody))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
@@ -31,15 +31,11 @@ import (
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
"net"
|
||||
"os"
|
||||
"os/signal"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
@@ -155,9 +151,3 @@ func writeWAV(path string, a audio.Audio) error {
|
||||
// jsonUnmarshal — kept local rather than pulling encoding/json into main.go
|
||||
// top-level space.
|
||||
func jsonUnmarshal(b []byte, v any) error { return json.Unmarshal(b, v) }
|
||||
|
||||
// keep strconv + io + net + time alive for future duration/size helpers.
|
||||
var _ = strconv.Atoi
|
||||
var _ io.Reader = (io.Reader)(nil)
|
||||
var _ = net.IPv4
|
||||
var _ = time.Second
|
||||
|
||||
@@ -60,6 +60,17 @@ func (h *reactiveHandler) actionAct(ctx context.Context, dec router.Decision) st
|
||||
phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
|
||||
h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
|
||||
return phraser.A(phraser.ActConfirm, map[string]string{"name": phrase})
|
||||
case errors.Is(err, tool.ErrUnknownTarget):
|
||||
// The verb reached a tool and the tail did not reach a target, so
|
||||
// nothing ran. Saying which word she could not place is the whole
|
||||
// answer: he either renames it or gives the row an alias that
|
||||
// carries the target, and both are one turn away (V-634).
|
||||
word := ""
|
||||
var unknown *tool.UnknownTargetError
|
||||
if errors.As(err, &unknown) {
|
||||
word = unknown.Target
|
||||
}
|
||||
return phraser.A(phraser.ActUnknownTarget, map[string]string{"name": word})
|
||||
case errors.Is(err, tool.ErrNeedsAuthedSurface):
|
||||
// Irreversible (internal/tool/risk.go). A confirm turn would not
|
||||
// help: everything that proposed this act — the STT, the router,
|
||||
|
||||
@@ -9,9 +9,24 @@ import (
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// nothingToCorrectReply — what she says to a correction that points at
|
||||
// nothing. Filing it would put a sentence in his memory that reads as a fact.
|
||||
const nothingToCorrectReply = "не поняла, что поправить. скажи целиком, и я запишу."
|
||||
|
||||
// actionNote handles router.IntentNote: embed the note, persist it, and
|
||||
// index it for recall.
|
||||
//
|
||||
// The stored body is dec.Utterance and nothing else (V-576). It is not
|
||||
// Slots.Text, not phraser output and not any other model string: a note is
|
||||
// durable, the embedder indexes it, and it comes back later as recall in his
|
||||
// own words. Phrasing belongs in the spoken confirmation.
|
||||
func (h *reactiveHandler) actionNote(ctx context.Context, dec router.Decision) string {
|
||||
// A correction with no referent. Everything that could own one has already
|
||||
// run by here: clarify, confirm and repair are all resolved before routing,
|
||||
// so a fragment reaching the note path has nothing behind it (V-576).
|
||||
if correctionFragment(dec.Utterance) {
|
||||
return nothingToCorrectReply
|
||||
}
|
||||
// An utterance that explicitly files a task is work, not recall, and
|
||||
// belongs in the task store (Vikunja #130). Checked before the embedding
|
||||
// is paid for. Everything else is a note, exactly as before.
|
||||
|
||||
+253
-55
@@ -11,7 +11,9 @@ import (
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/crawl"
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/kiwix"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/morning"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
@@ -58,6 +60,35 @@ type querySource struct {
|
||||
// sources search text with no notion of a day. When one of them grows a
|
||||
// date parameter, flip its flag here.
|
||||
dateAware bool
|
||||
|
||||
// dest — the destination this source serves, when the cascade named one
|
||||
// (V-655). Several sources share a destination: the three recall passes and
|
||||
// the fact-by-key lookup are all SourceRecall, because which of them lands
|
||||
// the hit is an ordering detail no utterance can name. A source with no
|
||||
// dest is reachable only by walking the chain.
|
||||
dest router.Source
|
||||
|
||||
// guesses — this source decides whether the turn is its own by scoring the
|
||||
// utterance against frozen seeds, rather than by looking something up and
|
||||
// coming back empty.
|
||||
//
|
||||
// The distinction is the whole point of the field. A source that looks can
|
||||
// be wrong about relevance and still harmless, because the miss shows up as
|
||||
// no rows. A source that guesses answers whatever it claims: weather has no
|
||||
// local table to miss against, so "что такое TCP?" became "для какого
|
||||
// города?". So when the cascade names a destination, the guessers that were
|
||||
// not named do not get to try. The lookups still run, because a named
|
||||
// destination is evidence and not a promise.
|
||||
guesses bool
|
||||
|
||||
// boundary — dropping this source widens what leaves the box, so only a
|
||||
// literal pattern may do it (V-666, owner's call of 2026-08-09).
|
||||
//
|
||||
// Every other guesser costs an answer when it is wrongly taken off a turn.
|
||||
// This one costs the rule that a question about him never reaches an
|
||||
// upstream engine. A grammar read the words to name a destination. A model
|
||||
// and a softmax both inferred one, and neither may spend that.
|
||||
boundary bool
|
||||
}
|
||||
|
||||
// querySources is the ordered chain actionQuery walks; first source to claim
|
||||
@@ -66,85 +97,85 @@ type querySource struct {
|
||||
// gate was never the bug. Adding a source (Kiwix, RSS, crawler, email) is one
|
||||
// line here plus its method; where you put the line is the whole decision.
|
||||
var querySources = []querySource{
|
||||
{name: "fact-by-key", answer: (*reactiveHandler).queryFactByKey},
|
||||
{name: "fact-by-key", answer: (*reactiveHandler).queryFactByKey, dest: router.SourceRecall},
|
||||
// Before "calendar" on purpose: both match "…на сегодня", and the plan is
|
||||
// the more specific ask (its matcher requires a plan word), so the calendar
|
||||
// listing would otherwise swallow it.
|
||||
{name: "day-plan", answer: (*reactiveHandler).queryDayPlan},
|
||||
{name: "day-plan", answer: (*reactiveHandler).queryDayPlan, dest: router.SourceCalendar},
|
||||
// Also before "calendar": "что я обычно делаю по средам?" names a weekday,
|
||||
// and the habit question is the more specific one. Its matcher requires a
|
||||
// habit marker ("обычно", "каждый", …), so a question about this coming
|
||||
// Wednesday still reaches the calendar.
|
||||
{name: "habits", answer: (*reactiveHandler).queryHabits},
|
||||
{name: "habits", answer: (*reactiveHandler).queryHabits, dest: router.SourceCalendar},
|
||||
// Before "calendar" and before the recall sources: "что мне нужно
|
||||
// сделать?" is a question about the task list, and the notes pass would
|
||||
// otherwise answer it with whatever note happens to be nearest. Its
|
||||
// matcher requires a task noun or an explicit "что … сделать", so a
|
||||
// date-bearing question still reaches the calendar.
|
||||
{name: "tasks", answer: (*reactiveHandler).queryTasks},
|
||||
{name: "tasks", answer: (*reactiveHandler).queryTasks, dest: router.SourceTasks},
|
||||
// Next to "tasks" and for the same reason: "что требует внимания?" is a
|
||||
// question about the operational state Praxis holds, and it used to fall
|
||||
// through every source to the web search (Vikunja #475). Its matcher needs
|
||||
// an attention marker, and it falls through when Praxis is not configured.
|
||||
{name: "attention", answer: (*reactiveHandler).queryAttention},
|
||||
// Before the recall sources too: "сколько я потратил?" is a question about
|
||||
// the money facts the poller wrote, and the notes pass would otherwise
|
||||
// answer it from whatever he once said about spending. Its matcher needs a
|
||||
// money noun plus an actual ask, so "я потратил весь день" is untouched.
|
||||
{name: "attention", answer: (*reactiveHandler).queryAttention, dest: router.SourceAttention, guesses: true},
|
||||
// Next to "tasks" and for the same reason: "что мне купить?" is a question
|
||||
// about the shopping list, and the recall pass would otherwise answer it
|
||||
// from an old note about the shop. Its matcher needs an explicit list
|
||||
// marker, so "надо бы съездить в магазин" is untouched.
|
||||
{name: "list", answer: (*reactiveHandler).queryList},
|
||||
{name: "money", answer: (*reactiveHandler).queryMoney},
|
||||
{name: "list", answer: (*reactiveHandler).queryList, dest: router.SourceList, guesses: true},
|
||||
// Before the recall sources too: "сколько я потратил?" is a question about
|
||||
// the money facts the poller wrote, and the notes pass would otherwise
|
||||
// answer it from whatever he once said about spending. Its matcher needs a
|
||||
// money noun plus an actual ask, so "я потратил весь день" is untouched.
|
||||
{name: "money", answer: (*reactiveHandler).queryMoney, dest: router.SourceMoney},
|
||||
// Also above the recall sources: "что я тебе говорил?" is a question about
|
||||
// the facts he tapped in, and the notes pass would answer it with whatever
|
||||
// note is nearest (Vikunja #456). Its matcher needs both halves of a
|
||||
// history phrase and bails out when he names a topic, so "что я говорил
|
||||
// про сервер" is still recall.
|
||||
{name: "history", answer: (*reactiveHandler).queryHistory},
|
||||
{name: "history", answer: (*reactiveHandler).queryHistory, dest: router.SourceRecall},
|
||||
// Before the recall sources and before general knowledge: "что нового?" is
|
||||
// a question about the feeds she reads, and general knowledge would answer
|
||||
// it by inventing news. Its matcher needs a feed noun plus an ask, so
|
||||
// "у меня новая лента в инстаграме" is untouched.
|
||||
{name: "feeds", answer: (*reactiveHandler).queryFeeds},
|
||||
{name: "feeds", answer: (*reactiveHandler).queryFeeds, dest: router.SourceFeeds, guesses: true},
|
||||
// Before "calendar" and before the recall sources: "что включено дома?" is
|
||||
// a question about the house, and the notes pass would otherwise answer it
|
||||
// from whatever he once said about the lights. Its matcher needs a house
|
||||
// marker plus an ask plus a device word, and it bails out on weather
|
||||
// wording, so "какая температура на улице?" still reaches the weather
|
||||
// source.
|
||||
{name: "home", answer: (*reactiveHandler).queryHome},
|
||||
{name: "home", answer: (*reactiveHandler).queryHome, dest: router.SourceHome, guesses: true},
|
||||
// Next to "home" and for the same reason: "какие устройства в сети?" is a
|
||||
// question about the LAN, and the recall pass would otherwise answer it
|
||||
// from an old note about the router. Its matcher needs a network word plus
|
||||
// an ask plus a device noun, so "интернет не работает" is untouched.
|
||||
{name: "network", answer: (*reactiveHandler).queryNetwork},
|
||||
{name: "calendar", answer: (*reactiveHandler).queryCalendar, dateAware: true},
|
||||
{name: "weather", answer: (*reactiveHandler).queryWeather},
|
||||
{name: "network", answer: (*reactiveHandler).queryNetwork, dest: router.SourceNetwork, guesses: true},
|
||||
{name: "calendar", answer: (*reactiveHandler).queryCalendar, dateAware: true, dest: router.SourceCalendar},
|
||||
{name: "weather", answer: (*reactiveHandler).queryWeather, dest: router.SourceWeather, guesses: true},
|
||||
// A question about her, above the three sources that search his own data
|
||||
// (Vikunja #555). It has no answer anywhere else: below the boundary
|
||||
// SearXNG answers about somebody else's assistant, and above it his notes
|
||||
// answer by proximity — "кто ты" came back from a note of his, measured on
|
||||
// the box, because the recall index has no idea the subject is her.
|
||||
{name: "self", answer: (*reactiveHandler).querySelf},
|
||||
{name: "embed", answer: (*reactiveHandler).queryEmbed},
|
||||
{name: "memory", answer: (*reactiveHandler).queryMemory},
|
||||
{name: "notes", answer: (*reactiveHandler).queryNotes},
|
||||
{name: "self", answer: (*reactiveHandler).querySelf, dest: router.SourceSelf, guesses: true},
|
||||
{name: "embed", answer: (*reactiveHandler).queryEmbed, dest: router.SourceRecall},
|
||||
{name: "memory", answer: (*reactiveHandler).queryMemory, dest: router.SourceRecall},
|
||||
{name: "notes", answer: (*reactiveHandler).queryNotes, dest: router.SourceRecall},
|
||||
// THE BOUNDARY. Everything above answers from his own data; everything
|
||||
// below answers from the world's. A question about him that got this far
|
||||
// has no answer in his data, and no outside source can supply one, so this
|
||||
// stops the walk rather than let the encyclopedia and the model guess.
|
||||
{name: "personal", answer: (*reactiveHandler).queryPersonal},
|
||||
{name: "personal", answer: (*reactiveHandler).queryPersonal, dest: router.SourceRecall, guesses: true, boundary: true},
|
||||
// The world, read live. Owner's ruling of 2026-08-02: a metasearch hit beats
|
||||
// a frozen ZIM, so SearXNG asks before Kiwix does. Nothing of his is at
|
||||
// stake by this point — the boundary above already stopped every question
|
||||
// about him, and only the query string leaves the box.
|
||||
{name: "search", answer: (*reactiveHandler).querySearch},
|
||||
{name: "search", answer: (*reactiveHandler).querySearch, dest: router.SourceWorld},
|
||||
// The offline encyclopedia, now the fallback for when the line is down or
|
||||
// the search comes back empty. It reads the way it always did; what changed
|
||||
// is that it no longer gets first refusal on a world question.
|
||||
{name: "kiwix", answer: (*reactiveHandler).queryKiwix},
|
||||
{name: "kiwix", answer: (*reactiveHandler).queryKiwix, dest: router.SourceWorld},
|
||||
// LAST before the model answers from memory, and that position is the whole
|
||||
// design (Vikunja #259): everything of his, then the search, then the ZIMs,
|
||||
// and only then a page he named. The model does NOT come first: it
|
||||
@@ -152,14 +183,70 @@ var querySources = []querySource{
|
||||
// a 1.7B guessing at a page it cannot read is how contents get invented.
|
||||
// This source only claims a turn where he named a URL, so it never competes
|
||||
// with a local answer.
|
||||
{name: "web", answer: (*reactiveHandler).queryWeb},
|
||||
{name: "general-knowledge", answer: (*reactiveHandler).queryGeneral},
|
||||
{name: "web", answer: (*reactiveHandler).queryWeb, dest: router.SourceWorld},
|
||||
{name: "general-knowledge", answer: (*reactiveHandler).queryGeneral, dest: router.SourceWorld},
|
||||
}
|
||||
|
||||
// queryWalk narrows the chain for one turn against the destination the cascade
|
||||
// named, and says which sources were left out (V-655).
|
||||
//
|
||||
// It takes sources OUT and never moves one, which is the whole safety argument.
|
||||
// The table's order is load-bearing and every comment on it argues a reason
|
||||
// between two sources; none of those reasons is about this. Above all, the
|
||||
// order carries "his data first, then the world", and a destination named by a
|
||||
// model must not be able to reverse that. Naming SourceWorld does not send the
|
||||
// turn outside — it stops the guessers from claiming it on the way.
|
||||
//
|
||||
// What comes out is exactly the sources that guess. Those decide whether a turn
|
||||
// is theirs by scoring it against frozen seeds, and then answer whatever they
|
||||
// claimed, because they have no lookup that can come back empty. That is the
|
||||
// whole of the 2026-08-07 defect: weather claiming "что такое TCP?", the feed
|
||||
// claiming "какой у меня любимый язык?", the personal boundary claiming "кто
|
||||
// такой Линус Торвальдс?". The sources that look are all still asked, so a
|
||||
// wrong destination costs nothing but the guess it prevented.
|
||||
//
|
||||
// No destination named ⇒ the table exactly as written, which is what shipped
|
||||
// before the field existed. That is the floor. The classifier arm names
|
||||
// nothing, so a box whose model is down routes queries the way it always did.
|
||||
// The personal boundary is the one exception, and anchored is what buys it
|
||||
// (V-666). A grammar matched a literal pattern to name the destination. The
|
||||
// routing heads and the resident model inferred one, and an inferred SourceWorld
|
||||
// takes the boundary off a question about him. That widens what is asked
|
||||
// upstream rather than costing a local answer, so those two keep it.
|
||||
func queryWalk(dest router.Source, anchored bool) (walk, skipped []querySource) {
|
||||
if dest == router.SourceUnknown {
|
||||
return querySources, nil
|
||||
}
|
||||
for _, s := range querySources {
|
||||
if s.guesses && s.dest != dest && (anchored || !s.boundary) {
|
||||
skipped = append(skipped, s)
|
||||
continue
|
||||
}
|
||||
walk = append(walk, s)
|
||||
}
|
||||
return walk, skipped
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision) string {
|
||||
t := &queryTurn{dec: dec}
|
||||
for _, src := range querySources {
|
||||
// The roster, so the record can say which sources were never reached rather
|
||||
// than leaving them out and letting a reader assume they looked and passed
|
||||
// (V-564). Finish names everyone below the winner.
|
||||
decision.Expect(ctx, decision.StageQuery, querySourceNames())
|
||||
rec := decision.From(ctx)
|
||||
walk, skipped := queryWalk(dec.Source, dec.SourceAnchored)
|
||||
for _, src := range skipped {
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageQuery, Claimant: src.name, Outcome: decision.NeverAsked,
|
||||
Reason: "it decides by similarity and the cascade named " + string(dec.Source),
|
||||
})
|
||||
}
|
||||
for _, src := range walk {
|
||||
if dec.Continued && !src.dateAware {
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageQuery, Claimant: src.name, Outcome: decision.NeverAsked,
|
||||
Reason: "a continuation turn only asks the date-aware sources",
|
||||
})
|
||||
continue
|
||||
}
|
||||
if reply, ok := src.answer(h, ctx, t); ok {
|
||||
@@ -172,8 +259,16 @@ func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision)
|
||||
// caller asked for one, so /chat can show it (V-539).
|
||||
log.Printf("voice: query claimed by source %q", src.name)
|
||||
noteQuerySource(ctx, src.name)
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageQuery, Claimant: src.name,
|
||||
Intent: string(dec.Intent), Outcome: decision.Won,
|
||||
})
|
||||
return reply
|
||||
}
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageQuery, Claimant: src.name, Outcome: decision.Declined,
|
||||
Reason: "it had no answer for this turn",
|
||||
})
|
||||
}
|
||||
if dec.Continued {
|
||||
// The previous question cannot be re-asked for another day. Saying so
|
||||
@@ -217,7 +312,13 @@ func (h *reactiveHandler) queryFactByKey(ctx context.Context, t *queryTurn) (str
|
||||
//
|
||||
// Read-only by construction — the plan is assembled and rendered core-side and
|
||||
// nothing here schedules or announces. "что дальше?" asks for the rest of the
|
||||
// day, so that phrasing trims what has already passed.
|
||||
// day, so that phrasing trims what has already passed and reads only the next
|
||||
// morning.NextSpoken entries. Trimming alone was not enough: asked early it cuts
|
||||
// nothing, and she read 43 entries aloud in one sentence (V-618).
|
||||
//
|
||||
// "что у меня сегодня?" is a different question and is not narrowed here — it
|
||||
// carries no plan word, so IsDayPlanQuery declines it and the calendar source
|
||||
// answers the whole day.
|
||||
//
|
||||
// What surface this belongs on is still open, tracked as Vikunja #431 ("Board
|
||||
// surface: Maven holds the work board, runs the intake form, never argues").
|
||||
@@ -236,16 +337,23 @@ func (h *reactiveHandler) queryDayPlan(ctx context.Context, t *queryTurn) (strin
|
||||
}
|
||||
// Rebuild the pure plan so the rest-of-day rendering is the same code that
|
||||
// rendered the whole day — one formatter, one persona.
|
||||
p := morning.Plan{Date: plan.Date}
|
||||
//
|
||||
// The instants are put back in the asking clock's zone on the way in. They
|
||||
// arrive carrying whatever zone the core read them in — a calendar fact's Ts
|
||||
// and a reminder's FireTs are UTC out of the store — and FormatRU reads the
|
||||
// hours in the plan's own frame, so setting that frame here is what makes
|
||||
// the recital name his clock rather than the store's (V-614).
|
||||
zone := h.now().Location()
|
||||
p := morning.Plan{Date: plan.Date.In(zone)}
|
||||
for _, it := range plan.Items {
|
||||
p.Items = append(p.Items, morning.PlanEntry{
|
||||
At: it.At,
|
||||
At: it.At.In(zone),
|
||||
Text: it.Text,
|
||||
Kind: morning.PlanKind(it.Kind),
|
||||
Uncertain: it.Uncertain,
|
||||
})
|
||||
}
|
||||
return p.After(h.now()).FormatRU(), true
|
||||
return p.Next(h.now(), morning.NextSpoken).FormatRU(), true
|
||||
}
|
||||
|
||||
// habitFactWindow — how many recent SELF facts the behaviour profile is counted
|
||||
@@ -410,6 +518,10 @@ func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (stri
|
||||
return f.FormatEntries(entries, date), true
|
||||
}
|
||||
|
||||
// homeTimeout — the whole house read. Longer than the weather call because the
|
||||
// hub is polled over the LAN and answers for every device at once.
|
||||
const homeTimeout = 10 * time.Second
|
||||
|
||||
// queryHome answers a question about the house. Read-only by construction: it
|
||||
// calls States and nothing else, so there is no confirm turn here — the only
|
||||
// way to CHANGE something is an enabled allowlist row through tool.Executor.
|
||||
@@ -426,7 +538,7 @@ func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string,
|
||||
// unreachable case is different and homeSummary covers it.
|
||||
return "", false
|
||||
}
|
||||
ctxH, cancel := context.WithTimeout(ctx, 10*time.Second)
|
||||
ctxH, cancel := context.WithTimeout(ctx, homeTimeout)
|
||||
defer cancel()
|
||||
return h.home.homeSummary(ctxH)
|
||||
}
|
||||
@@ -450,6 +562,10 @@ func (h *reactiveHandler) queryNetwork(ctx context.Context, t *queryTurn) (strin
|
||||
return h.netscan.scanSummary(ctx)
|
||||
}
|
||||
|
||||
// weatherTimeout — one geocode plus one forecast read. He asked a question with
|
||||
// a one-line answer, so a provider that is slower than this is a failure.
|
||||
const weatherTimeout = 5 * time.Second
|
||||
|
||||
func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !h.turnIsAbout(ctx, t, topicWeather, isWeatherQuery) {
|
||||
return "", false
|
||||
@@ -460,7 +576,7 @@ func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (strin
|
||||
// so is the only honest answer; picking a city would be inventing one.
|
||||
return phraser.Q(phraser.QueryWeatherWhere, nil), true
|
||||
}
|
||||
ctxWT, cancel := context.WithTimeout(ctx, 5*time.Second)
|
||||
ctxWT, cancel := context.WithTimeout(ctx, weatherTimeout)
|
||||
defer cancel()
|
||||
w, err := h.weatherProvider.CurrentWeather(ctxWT, loc)
|
||||
if errors.Is(err, weather.ErrNotConfigured) {
|
||||
@@ -485,7 +601,15 @@ func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (strin
|
||||
|
||||
// queryEmbed isn't an answer source — it's the shared cost the two recall
|
||||
// sources below both need, run once, in the position it always ran in. It
|
||||
// only claims the turn when the embedder fails.
|
||||
// never claims the turn.
|
||||
//
|
||||
// It used to claim on an embedder error, and that made a RAG hint a hard gate
|
||||
// over everything below it (V-568): one failing EmbedQuery and the memory, the
|
||||
// notes, the boundary, the search, the ZIMs, the named page and the model all
|
||||
// answered "не смогла ответить", including the questions search and Kiwix
|
||||
// would have answered without ever touching the embedder. A failed embed means
|
||||
// this source cannot claim, not that the turn is over — same shape as
|
||||
// turnVector in topics.go, which had it right.
|
||||
func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
// A topic source above already paid for this one; see turnVector.
|
||||
if len(t.vec) > 0 {
|
||||
@@ -493,13 +617,37 @@ func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string,
|
||||
}
|
||||
vec, err := router.EmbedQuery(ctx, h.recall.embedder, t.dec.Utterance)
|
||||
if err != nil {
|
||||
// Logged once, here, and the chain walks on. The two recall sources
|
||||
// below read the empty vector and pass; the boundary drops to its
|
||||
// offline floor.
|
||||
log.Printf("voice: embed query: %v", err)
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
return "", false
|
||||
}
|
||||
t.vec = vec
|
||||
return "", false
|
||||
}
|
||||
|
||||
// memoryRecallWidth and noteRecallWidth — how many candidates each recall pass
|
||||
// pulls before the gate reads them. Both are small on purpose: the gate wants a
|
||||
// best hit and its runner-up, and every further row is a margin the top match
|
||||
// has to beat.
|
||||
const (
|
||||
memoryRecallWidth = 3
|
||||
noteRecallWidth = 5
|
||||
)
|
||||
|
||||
// recallOnTopic — the topic veto both recall sources apply after the score gate
|
||||
// (#470). A memory about his slow network scored high enough to answer "почему
|
||||
// небо синее?", because the right-note and must-be-silent score ranges overlap
|
||||
// and no threshold sits between them.
|
||||
func recallOnTopic(utterance, text string) bool {
|
||||
if memory.RecallAllowed(utterance, text) {
|
||||
return true
|
||||
}
|
||||
log.Printf("voice: recall %q rejected for %q: a world question and no shared topic word", text, utterance)
|
||||
return false
|
||||
}
|
||||
|
||||
// queryMemory — long-term memory first: ONE search over everything Maven
|
||||
// remembers (notes and facts share this index) and ONE confidence gate, so
|
||||
// the memory that is clearly the best match answers — a note just as much as
|
||||
@@ -514,7 +662,13 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
if h.recall.memStore == nil {
|
||||
return "", false
|
||||
}
|
||||
hits, herr := h.recall.memStore.Search(ctx, t.vec, 3)
|
||||
if len(t.vec) == 0 {
|
||||
// No query vector: the embed above failed or there is no embedder.
|
||||
// Searching on an empty vector is not a search, and its scores are not
|
||||
// a "there is nothing" answer — pass rather than gate the chain.
|
||||
return "", false
|
||||
}
|
||||
hits, herr := h.recall.memStore.Search(ctx, t.vec, memoryRecallWidth)
|
||||
if herr != nil {
|
||||
log.Printf("voice: memory search: %v", herr)
|
||||
return "", false
|
||||
@@ -524,12 +678,8 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
return "", false
|
||||
}
|
||||
text := hit.Meta["text"]
|
||||
// The score cleared the gate and the topic still has to match (#470). A
|
||||
// note about his slow network scored high enough to answer "почему небо
|
||||
// синее?", because the right-note and must-be-silent score ranges overlap
|
||||
// and no threshold sits between them.
|
||||
if !memory.RecallAllowed(t.dec.Utterance, text) {
|
||||
log.Printf("voice: recall %q rejected for %q: a world question and no shared topic word", text, t.dec.Utterance)
|
||||
// The score cleared the gate and the topic still has to match.
|
||||
if !recallOnTopic(t.dec.Utterance, text) {
|
||||
return "", false
|
||||
}
|
||||
// A note is phrased in Maven's voice; a fact is read back as it was
|
||||
@@ -560,10 +710,18 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
// band. See memory.Confident. Failing the gate passes the turn on to general
|
||||
// knowledge, which is what "don't read back the runner-up" means here.
|
||||
func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
notes, err := h.api.QueryNotes(ctx, t.vec, 5)
|
||||
if len(t.vec) == 0 {
|
||||
// Same reason as queryMemory above (V-568): with no query vector this
|
||||
// source could not look, and could-not-look passes.
|
||||
return "", false
|
||||
}
|
||||
notes, err := h.api.QueryNotes(ctx, t.vec, noteRecallWidth)
|
||||
if err != nil {
|
||||
// The store failed, so this source could not look either. It used to
|
||||
// claim here, which stopped the search, the ZIMs and the model from
|
||||
// answering a question that never needed a note (V-568).
|
||||
log.Printf("voice: query notes: %v", err)
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
return "", false
|
||||
}
|
||||
t.notes = notes
|
||||
noteScores := make([]float64, len(notes))
|
||||
@@ -573,10 +731,9 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
if !memory.ConfidentScores(noteScores, h.recall.minScore, h.recall.minMargin) {
|
||||
return "", false
|
||||
}
|
||||
// Same topic veto as queryMemory above: the best note must be about what
|
||||
// he asked, not merely the nearest vector in the index.
|
||||
if !memory.RecallAllowed(t.dec.Utterance, notes[0].Text) {
|
||||
log.Printf("voice: note %q rejected for %q: a world question and no shared topic word", notes[0].Text, t.dec.Utterance)
|
||||
// The best note must be about what he asked, not merely the nearest vector
|
||||
// in the index.
|
||||
if !recallOnTopic(t.dec.Utterance, notes[0].Text) {
|
||||
return "", false
|
||||
}
|
||||
texts := make([]string, len(notes))
|
||||
@@ -598,6 +755,23 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
// prompt, the persona block and the reply.
|
||||
const webPageContextRunes = 1500
|
||||
|
||||
// webFetchTimeout — the whole named-page source. Longer than the other outside
|
||||
// sources because he named this page himself, so waiting for it is what he asked
|
||||
// for, and there is nothing below that can answer instead.
|
||||
const webFetchTimeout = 30 * time.Second
|
||||
|
||||
// readBackRunes — how much of the evidence is read out when the phraser gave
|
||||
// nothing back. It is spoken aloud, so it is a couple of sentences and not a
|
||||
// page.
|
||||
const readBackRunes = 300
|
||||
|
||||
// readBack — what an outside source says when the phraser gave nothing back.
|
||||
// The evidence is read out plainly rather than dropped, because the fetch did
|
||||
// happen and its result is a better answer than silence.
|
||||
func readBack(evidence string) string {
|
||||
return phraser.Q(phraser.QueryFound, map[string]string{"text": crawl.TrimRunes(evidence, readBackRunes)})
|
||||
}
|
||||
|
||||
// queryWeb — "посмотри https://example.org/x — что там?" (Vikunja #259).
|
||||
//
|
||||
// It claims a turn ONLY when he named a URL, which is what keeps a fallback from
|
||||
@@ -616,7 +790,7 @@ func (h *reactiveHandler) queryWeb(ctx context.Context, t *queryTurn) (string, b
|
||||
// guess dressed as an answer (Vikunja #479).
|
||||
return phraser.Q(phraser.QueryPageOff, nil), true
|
||||
}
|
||||
ctxFetch, cancel := context.WithTimeout(ctx, 30*time.Second)
|
||||
ctxFetch, cancel := context.WithTimeout(ctx, webFetchTimeout)
|
||||
defer cancel()
|
||||
page, err := h.crawler.Page(ctxFetch, link)
|
||||
if err != nil {
|
||||
@@ -637,7 +811,7 @@ func (h *reactiveHandler) queryWeb(ctx context.Context, t *queryTurn) (string, b
|
||||
if reply == "" {
|
||||
// No phraser (or it failed): read back the top of the page rather than
|
||||
// pretend the fetch did not happen.
|
||||
return phraser.Q(phraser.QueryPageText, map[string]string{"text": crawl.TrimRunes(page.Text, 300)}), true
|
||||
return phraser.Q(phraser.QueryPageText, map[string]string{"text": crawl.TrimRunes(page.Text, readBackRunes)}), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -703,7 +877,7 @@ func (h *reactiveHandler) querySearch(ctx context.Context, t *queryTurn) (string
|
||||
if reply == "" {
|
||||
// No phraser, or it failed. Read back the best evidence rather than
|
||||
// pretend the search did not happen.
|
||||
return phraser.Q(phraser.QueryFound, map[string]string{"text": crawl.TrimRunes(resp.Snippets()[0], 300)}), true
|
||||
return readBack(resp.Snippets()[0]), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -753,6 +927,26 @@ func (h *reactiveHandler) queryKiwix(ctx context.Context, t *queryTurn) (string,
|
||||
}
|
||||
}
|
||||
|
||||
// The topic, not the sentence (V-668). Kiwix ranks by keyword overlap, so
|
||||
// the question words outrank the one word that names the article: measured
|
||||
// on 2026-08-09, "что такое TCP" returns "Перехват TCP-соединения" and
|
||||
// "TCP" returns TCP. Only the verbatim path needs this. The rewriter
|
||||
// already reduces a question to English keywords, and reducing twice would
|
||||
// take the topic off the input it reads.
|
||||
if verbatim {
|
||||
if topic := kiwix.Topic(pattern); topic != "" {
|
||||
// The article named exactly, before any ranking runs. A ZIM is
|
||||
// addressable by title and a wrong title is a 404, so this either
|
||||
// answers or costs one request that says nothing.
|
||||
page, err := h.kiwix.client.Article(ctxK, kiwix.TitlePath(book, topic), h.kiwix.runes)
|
||||
if err == nil && page.Text != "" {
|
||||
log.Printf("voice: kiwix: %q in %q → title hit %q", topic, book, page.Title)
|
||||
return h.kiwixReply(ctx, t, page.Title, page.Text)
|
||||
}
|
||||
pattern = topic
|
||||
}
|
||||
}
|
||||
|
||||
hits, err := h.kiwix.client.Search(ctxK, pattern, book, h.kiwix.max)
|
||||
if err != nil {
|
||||
log.Printf("voice: kiwix: search %q: %v", pattern, err)
|
||||
@@ -785,14 +979,18 @@ func (h *reactiveHandler) queryKiwix(ctx context.Context, t *queryTurn) (string,
|
||||
}
|
||||
page = crawl.Page{Title: top.Title, Text: top.Snippet}
|
||||
}
|
||||
// Handed over the same way a note or a page is: context for the question he
|
||||
// asked, not something to recite.
|
||||
snippet := top.Title + "\n" + crawl.TrimRunes(page.Text, h.kiwix.runes)
|
||||
return h.kiwixReply(ctx, t, top.Title, page.Text)
|
||||
}
|
||||
|
||||
// kiwixReply hands one article over the same way a note or a page is handed
|
||||
// over: context for the question he asked, not something to recite.
|
||||
func (h *reactiveHandler) kiwixReply(ctx context.Context, t *queryTurn, title, text string) (string, bool) {
|
||||
snippet := title + "\n" + crawl.TrimRunes(text, h.kiwix.runes)
|
||||
reply := h.phraseSource(ctx, "kiwix", t.dec.Utterance, []string{snippet})
|
||||
if reply == "" {
|
||||
// No phraser, or it failed. Read back the best hit rather than pretend
|
||||
// the search did not happen.
|
||||
return phraser.Q(phraser.QueryFound, map[string]string{"text": crawl.TrimRunes(top.Title+" — "+page.Text, 300)}), true
|
||||
return readBack(title + " — " + text), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
@@ -19,7 +19,10 @@ func (h *reactiveHandler) actionReminder(ctx context.Context, dec router.Decisio
|
||||
// time wasn't parsed. Run the parser as a fallback.
|
||||
if dec.Stage == 0 && h.timeParser != nil {
|
||||
t, ok, err := h.timeParser.Parse(ctx, dec.Utterance, h.now())
|
||||
if err == nil && ok {
|
||||
// Same gate as the extractor (V-577, V-579, V-610): a request whose
|
||||
// hour was not spoken, or was spoken and not read, gets asked about
|
||||
// and is never completed from the clock.
|
||||
if err == nil && ok && router.ResolvedTheHour(dec.Utterance, t) {
|
||||
dec.Slots.Time = t
|
||||
dec.Slots.HasTime = true
|
||||
}
|
||||
|
||||
@@ -0,0 +1,120 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log"
|
||||
"net"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/event"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// The two boot paths meet here. run() wires the daemon twice: once at boot
|
||||
// when a key is in the environment, and once inside UnlockFn after a passkey
|
||||
// assertion, minutes or days later. Listing the same wiring in both places is
|
||||
// what let them drift — seven workers started untracked on the unlock path and
|
||||
// two daemonAPI fields were never set there, silently, for as long as anyone
|
||||
// had been cold-starting (V-639).
|
||||
//
|
||||
// So both paths call newDaemonAPI and startBackground and nothing else. A
|
||||
// field or a worker added later reaches both paths or neither.
|
||||
|
||||
// bootDeps is everything the two constructors below read. It is filled from
|
||||
// the same variables on both paths, by depsNow in run().
|
||||
type bootDeps struct {
|
||||
coreFor func() ipc.CoreAPI
|
||||
tl *tickLoop
|
||||
evBus *event.Bus
|
||||
voiceW *voiceWiring
|
||||
st *store.Store
|
||||
factWorker *factEnrichmentWorker
|
||||
evalWorker *memoryEvalWorker // nil ⇒ memory evaluation off (the default)
|
||||
feedWkr *feedWorker // nil ⇒ no feed is read (the default)
|
||||
crawlWkr *crawlWorker // nil ⇒ no page is watched (the default)
|
||||
}
|
||||
|
||||
// newDaemonAPI builds the real CoreAPI, with every field set. The unlock path
|
||||
// used to leave nexus and getMCPServers nil, so after a cold start
|
||||
// ResolveEntity refused with a nexus block configured and /tools rendered
|
||||
// "not configured" with an mcp block configured. Empty is a wrong answer
|
||||
// there, not a degraded one.
|
||||
func newDaemonAPI(d bootDeps) *daemonAPI {
|
||||
api := &daemonAPI{
|
||||
CoreAPI: d.coreFor(),
|
||||
getTrace: d.tl.trace,
|
||||
getMorningStatus: func(ctx context.Context) []ipc.MorningRoutineStatus { return d.tl.morningStatus(ctx, time.Now()) },
|
||||
getDayPlan: func(ctx context.Context) ipc.DayPlan { return d.tl.dayPlan(ctx, time.Now()) },
|
||||
getEvents: intakeEventsFn(d.evBus),
|
||||
getDecisions: turnDecisionsFn(d.voiceW),
|
||||
seedStore: seedStoreIfAllowed(d.st),
|
||||
nexus: nexusOf(d.voiceW),
|
||||
}
|
||||
if d.voiceW != nil && d.voiceW.handler != nil {
|
||||
api.chatFn = d.voiceW.handler.handleText
|
||||
// And the reverse: the handler was wired with the bare store adapter,
|
||||
// which cannot serve the day plan. See upgradeAPI.
|
||||
d.voiceW.handler.upgradeAPI(api)
|
||||
}
|
||||
if d.voiceW != nil && d.voiceW.mcp != nil {
|
||||
api.getMCPServers = d.voiceW.mcp.status
|
||||
}
|
||||
return api
|
||||
}
|
||||
|
||||
// namedWorker is one long-running goroutine. The name exists so the set is
|
||||
// assertable from a test and readable in a log; nothing dispatches on it.
|
||||
type namedWorker struct {
|
||||
name string
|
||||
run func(ctx context.Context)
|
||||
}
|
||||
|
||||
// backgroundWorkers lists what this deployment runs. It is pure — it starts
|
||||
// nothing — so a test can compare the set the two paths would start without
|
||||
// standing a daemon up.
|
||||
func backgroundWorkers(d bootDeps) []namedWorker {
|
||||
var ws []namedWorker
|
||||
if d.voiceW != nil && d.voiceW.server != nil {
|
||||
ws = append(ws, namedWorker{"voice", func(context.Context) {
|
||||
if err := d.voiceW.server.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("voice serve: %v", err)
|
||||
}
|
||||
}})
|
||||
}
|
||||
ws = append(ws,
|
||||
namedWorker{"tick", d.tl.run},
|
||||
namedWorker{"fact-enrichment", d.factWorker.run},
|
||||
)
|
||||
if d.evalWorker != nil {
|
||||
ws = append(ws, namedWorker{"memory-eval", d.evalWorker.run})
|
||||
}
|
||||
if d.feedWkr != nil {
|
||||
ws = append(ws, namedWorker{"feed", d.feedWkr.run})
|
||||
}
|
||||
if d.crawlWkr != nil {
|
||||
ws = append(ws, namedWorker{"crawl", d.crawlWkr.run})
|
||||
}
|
||||
if d.voiceW != nil && d.voiceW.mcp != nil {
|
||||
ws = append(ws, namedWorker{"mcp", d.voiceW.mcp.run})
|
||||
}
|
||||
if d.voiceW != nil && d.voiceW.home != nil {
|
||||
ws = append(ws, namedWorker{"home", d.voiceW.home.run})
|
||||
}
|
||||
return ws
|
||||
}
|
||||
|
||||
// startBackground starts every worker through goWorker, so waitWorkers can
|
||||
// wait for it at shutdown. A worker started as a bare `go func()` is the
|
||||
// shutdown bug documented at the end of run(): run() never returns, the
|
||||
// deferred Close never seals the database, and the ciphertext goes stale.
|
||||
func startBackground(ctx context.Context, wg *sync.WaitGroup, d bootDeps) {
|
||||
for _, w := range backgroundWorkers(d) {
|
||||
goWorker(wg, func() { w.run(ctx) })
|
||||
}
|
||||
if d.voiceW != nil && d.voiceW.server != nil {
|
||||
log.Printf("mavend: voice listening on %s", d.voiceW.server.Addr())
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,96 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/event"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
// fullDeps — a deployment with every optional piece present. Nothing here is
|
||||
// run: newDaemonAPI takes method values and backgroundWorkers is pure, so
|
||||
// zero-value wirings are enough to say what WOULD be started.
|
||||
func fullDeps() bootDeps {
|
||||
h := &reactiveHandler{
|
||||
ecosystem: &ecosystemWiring{nexus: &nexusClient{}},
|
||||
decisions: decision.NewRing(),
|
||||
}
|
||||
return bootDeps{
|
||||
coreFor: func() ipc.CoreAPI { return ipc.UnimplementedCoreAPI{} },
|
||||
tl: &tickLoop{},
|
||||
evBus: event.NewBus(4),
|
||||
st: &store.Store{},
|
||||
factWorker: &factEnrichmentWorker{},
|
||||
evalWorker: &memoryEvalWorker{},
|
||||
feedWkr: &feedWorker{},
|
||||
crawlWkr: &crawlWorker{},
|
||||
voiceW: &voiceWiring{
|
||||
server: &voice.Server{},
|
||||
handler: h,
|
||||
mcp: &mcpWiring{},
|
||||
home: &homeWiring{},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// The unlock path used to build its own daemonAPI literal and leave nexus and
|
||||
// getMCPServers nil (V-639). Both paths call newDaemonAPI now, so the drift
|
||||
// that can still happen is a field added to the struct and not to the
|
||||
// constructor. This catches that one, by name.
|
||||
func TestNewDaemonAPISetsEveryField(t *testing.T) {
|
||||
prev := allowSeedOnStart
|
||||
allowSeedOnStart = true
|
||||
defer func() { allowSeedOnStart = prev }()
|
||||
|
||||
api := newDaemonAPI(fullDeps())
|
||||
v := reflect.ValueOf(*api)
|
||||
for i := range v.NumField() {
|
||||
if v.Field(i).IsZero() {
|
||||
t.Errorf("newDaemonAPI left %s unset — a fully wired deployment must fill every field", v.Type().Field(i).Name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The handler is wired with the bare store adapter and cannot serve the day
|
||||
// plan until upgradeAPI hands it the real one. The unlocked path did that and
|
||||
// the unlock path did it too; keep it a property of the constructor.
|
||||
func TestNewDaemonAPIUpgradesTheHandler(t *testing.T) {
|
||||
d := fullDeps()
|
||||
api := newDaemonAPI(d)
|
||||
if d.voiceW.handler.api != ipc.CoreAPI(api) {
|
||||
t.Fatal("newDaemonAPI did not hand the handler the API it built")
|
||||
}
|
||||
}
|
||||
|
||||
// Every worker the daemon runs goes through startBackground, so shutdown can
|
||||
// wait for it. The unlock path used to start seven of these as bare
|
||||
// `go func()` under a shadowed WaitGroup.
|
||||
func TestBackgroundWorkersFullSet(t *testing.T) {
|
||||
want := []string{"voice", "tick", "fact-enrichment", "memory-eval", "feed", "crawl", "mcp", "home"}
|
||||
var got []string
|
||||
for _, w := range backgroundWorkers(fullDeps()) {
|
||||
got = append(got, w.name)
|
||||
}
|
||||
if !reflect.DeepEqual(got, want) {
|
||||
t.Errorf("workers = %v, want %v", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
// A default box configures none of the optional blocks. Two workers always run
|
||||
// and the rest stay dark, rather than a nil run being scheduled.
|
||||
func TestBackgroundWorkersFloor(t *testing.T) {
|
||||
d := fullDeps()
|
||||
d.evalWorker, d.feedWkr, d.crawlWkr, d.voiceW = nil, nil, nil, nil
|
||||
want := []string{"tick", "fact-enrichment"}
|
||||
var got []string
|
||||
for _, w := range backgroundWorkers(d) {
|
||||
got = append(got, w.name)
|
||||
}
|
||||
if !reflect.DeepEqual(got, want) {
|
||||
t.Errorf("workers = %v, want %v", got, want)
|
||||
}
|
||||
}
|
||||
@@ -19,7 +19,7 @@ func TestChatAnswersWithNoLlamaServer(t *testing.T) {
|
||||
dead := llm.New("http://127.0.0.1:1", 500*time.Millisecond)
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
h.recall.embedder = emb
|
||||
h.router = buildRouter(emb, h.matcher, 0.55, pickLLMRouter(true, dead))
|
||||
h.router = buildRouter(emb, h.matcher, 0.55, pickLLMRouter(true, dead), nil)
|
||||
h.replier = newLLMReplier(dead, nil)
|
||||
|
||||
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
|
||||
+334
-73
@@ -6,6 +6,7 @@ import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
@@ -65,8 +66,28 @@ var clarifyExpiredVariants = []string{
|
||||
"Столько времени прошло, что я отпустила прошлую просьбу. Скажи заново, если она в силе.",
|
||||
}
|
||||
|
||||
// clarifyExpiredLine picks one of them at random.
|
||||
func clarifyExpiredLine() string {
|
||||
// clarifyExpiredPluralVariants — the same notice when TWO parked requests died
|
||||
// together (Vikunja #561). Since a side query suspends the flow instead of
|
||||
// dropping it, the stack can hold both the flow and the thing he interrupted it
|
||||
// with, and TakeExpired drops the whole stack when the top times out. "Прошлую
|
||||
// просьбу" would then be a lie about the count: he loses two and hears about
|
||||
// one.
|
||||
//
|
||||
// Two phrasings only, against five for the singular. This fires when he walks
|
||||
// off in the middle of an interrupted exchange, which is rarer than walking off
|
||||
// in the middle of a plain one, so it repeats less and needs less variety.
|
||||
var clarifyExpiredPluralVariants = []string{
|
||||
"Прости, я слишком долго ждала и отпустила обе прошлые просьбы. Если они ещё нужны, скажи заново.",
|
||||
"Я не дождалась ответа и убрала обе прошлые просьбы. Повтори, если они всё ещё нужны.",
|
||||
}
|
||||
|
||||
// clarifyExpiredLine picks one of them at random. n is how many requests died;
|
||||
// anything above one gets the plural wording, because the bound is two today and
|
||||
// a third would still be "обе" short of the truth only if MaxStackDepth grew.
|
||||
func clarifyExpiredLine(n int) string {
|
||||
if n > 1 {
|
||||
return clarifyExpiredPluralVariants[rand.Intn(len(clarifyExpiredPluralVariants))]
|
||||
}
|
||||
return clarifyExpiredVariants[rand.Intn(len(clarifyExpiredVariants))]
|
||||
}
|
||||
|
||||
@@ -74,23 +95,34 @@ func clarifyExpiredLine() string {
|
||||
// notice is glued in front of this turn's reply (see withNotice), so a caller
|
||||
// checking for it has to match a prefix, not the whole string.
|
||||
func isClarifyExpired(s string) bool {
|
||||
for _, v := range clarifyExpiredVariants {
|
||||
if strings.HasPrefix(s, v) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
_, ok := cutClarifyExpired(s)
|
||||
return ok
|
||||
}
|
||||
|
||||
// trimClarifyExpired strips a leading expiry notice, leaving this turn's actual
|
||||
// reply. "" ⇒ the notice was the whole thing.
|
||||
func trimClarifyExpired(s string) string {
|
||||
for _, v := range clarifyExpiredVariants {
|
||||
if strings.HasPrefix(s, v) {
|
||||
return strings.TrimSpace(strings.TrimPrefix(s, v))
|
||||
rest, ok := cutClarifyExpired(s)
|
||||
if !ok {
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
return rest
|
||||
}
|
||||
|
||||
// cutClarifyExpired matches either expiry deck as a prefix and returns what
|
||||
// follows it. Both decks, since V-561 added the plural line: a caller asking
|
||||
// "did she say a request timed out" means the fact, not which wording carried
|
||||
// it, and a helper that knew only the singular would read the two-request
|
||||
// notice as ordinary reply text.
|
||||
func cutClarifyExpired(s string) (string, bool) {
|
||||
for _, deck := range [][]string{clarifyExpiredVariants, clarifyExpiredPluralVariants} {
|
||||
for _, v := range deck {
|
||||
if strings.HasPrefix(s, v) {
|
||||
return strings.TrimSpace(strings.TrimPrefix(s, v)), true
|
||||
}
|
||||
}
|
||||
}
|
||||
return strings.TrimSpace(s)
|
||||
return "", false
|
||||
}
|
||||
|
||||
// clarifyExpiredNotice returns that line when a parked question had just timed
|
||||
@@ -101,11 +133,12 @@ func (h *reactiveHandler) clarifyExpiredNotice(ctx context.Context) string {
|
||||
if h.clarifyStore == nil {
|
||||
return ""
|
||||
}
|
||||
if !h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now()) {
|
||||
n := h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now())
|
||||
if n == 0 {
|
||||
return ""
|
||||
}
|
||||
log.Printf("voice: clarify — parked question expired, telling him and routing the words fresh")
|
||||
return clarifyExpiredLine()
|
||||
log.Printf("voice: clarify — %d parked question(s) expired, telling him and routing the words fresh", n)
|
||||
return clarifyExpiredLine(n)
|
||||
}
|
||||
|
||||
// withNotice glues the expiry notice in front of this turn's reply. One turn
|
||||
@@ -121,10 +154,47 @@ func withNotice(notice, reply string) string {
|
||||
return notice + " " + reply
|
||||
}
|
||||
|
||||
// withResumed puts the resumed question on the END of this turn's reply, where
|
||||
// withNotice puts the expiry notice on the front (Vikunja #561).
|
||||
//
|
||||
// The order is the owner's: "в Риме сейчас ..., на какое время поставить
|
||||
// напоминание?" — answer first, then the open question. A question in front of
|
||||
// its own answer would read as ignoring what he asked.
|
||||
//
|
||||
// Two sentences, not one (V-654). This used to fold the answer's full stop into
|
||||
// a comma, on the strength of the owner having written it that way once. Spliced
|
||||
// onto a real answer it reads as one run-on thought — "вот что я нашла: вайфай
|
||||
// пароль лежит в ящике стола, на какое время поставить напоминание?" — and the
|
||||
// question disappears into the tail of a sentence about something else. A reply
|
||||
// with no terminator of its own is given one, so the join never depends on how
|
||||
// the phraser chose to end.
|
||||
//
|
||||
// A resume with no answer in front of it is just the question.
|
||||
func withResumed(reply, resumed string) string {
|
||||
if resumed == "" {
|
||||
return reply
|
||||
}
|
||||
reply = strings.TrimSpace(reply)
|
||||
if reply == "" {
|
||||
return resumed
|
||||
}
|
||||
if !endsSentence(reply) {
|
||||
reply += "."
|
||||
}
|
||||
return reply + " " + resumed
|
||||
}
|
||||
|
||||
// endsSentence reports whether s already closes itself. The ellipsis counts: a
|
||||
// trailing "…" is a deliberate end, and a full stop after it reads as a typo.
|
||||
func endsSentence(s string) bool {
|
||||
r, _ := utf8.DecodeLastRuneInString(s)
|
||||
return strings.ContainsRune(".!?…", r)
|
||||
}
|
||||
|
||||
// missingFor returns the slots a decision still needs, most important first.
|
||||
// Empty ⇒ there is nothing identifiable to ask about.
|
||||
func missingFor(dec router.Decision) []dialogue.Slot {
|
||||
return dialogue.StillMissing(wantedSlots[dec.Intent], toDialogueSlots(dec.Slots))
|
||||
return stillMissingFor(dec.Intent, dec.Utterance, toDialogueSlots(dec.Slots))
|
||||
}
|
||||
|
||||
// clarifyQuestion picks the one question to ask for a clarify decision. Returns
|
||||
@@ -133,18 +203,32 @@ func missingFor(dec router.Decision) []dialogue.Slot {
|
||||
// One question about one thing: if two slots are missing she asks about the
|
||||
// first only. Two questions in one breath is an interrogation. The second gap
|
||||
// is picked up on the turn after the first one is answered (askRemainingGap).
|
||||
func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
|
||||
func (h *reactiveHandler) clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
|
||||
missing := missingFor(dec)
|
||||
if len(missing) == 0 {
|
||||
return "", "", false
|
||||
}
|
||||
q, ok := clarifyQuestionFor(missing[0], 1)
|
||||
q, ok := h.questionFor(missing[0], 1, dec.Utterance, toDialogueSlots(dec.Slots), "")
|
||||
if !ok {
|
||||
return "", "", false
|
||||
}
|
||||
return missing[0], q, true
|
||||
}
|
||||
|
||||
// questionFor picks the wording for one gap. Every slot but the reminder's time
|
||||
// reads its deck by attempt; the time asks about whichever of the hour, the half
|
||||
// of the day and the day he has not said, and states the clock while it does
|
||||
// (V-579).
|
||||
//
|
||||
// taken is the acknowledgement of what his last turn added, empty when it added
|
||||
// nothing and empty for a first ask, which has no turn behind it (V-593).
|
||||
func (h *reactiveHandler) questionFor(slot dialogue.Slot, attempt int, utterance string, s dialogue.Slots, taken string) (string, bool) {
|
||||
if slot != dialogue.SlotTime {
|
||||
return clarifyQuestionFor(slot, attempt)
|
||||
}
|
||||
return whenQuestion(whenGapOf(utterance, s.HasTime), attempt, h.now(), taken)
|
||||
}
|
||||
|
||||
// askClarify parks the request and returns the question to ask instead of the
|
||||
// canned "не поняла". Returns ("", false) when there is nothing to ask about, so
|
||||
// the caller falls back to the canned reply.
|
||||
@@ -152,11 +236,16 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
|
||||
if h.clarifyStore == nil {
|
||||
return "", false
|
||||
}
|
||||
slot, question, ok := clarifyQuestion(dec)
|
||||
slot, question, ok := h.clarifyQuestion(dec)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
|
||||
// An act she could not resolve is a refusal, not a question (Vikunja #556).
|
||||
if slot == dialogue.SlotFn {
|
||||
log.Printf("voice: clarify — act %q matched no capability; saying so instead of asking", dec.Utterance)
|
||||
return actNotRecognized, true
|
||||
}
|
||||
q := &dialogue.PendingQuestion{
|
||||
Intent: dialogue.Intent(dec.Intent),
|
||||
Slots: toDialogueSlots(dec.Slots),
|
||||
Missing: []dialogue.Slot{slot},
|
||||
@@ -165,70 +254,170 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
|
||||
TTL: clarifyTTL,
|
||||
Attempts: 1, // this ask
|
||||
MaxAttempts: h.clarifyMaxAttempts,
|
||||
})
|
||||
}
|
||||
// Push, not Put, when this turn suspended a flow (Vikunja #561): the side
|
||||
// query needs clarifying of ITS own, and Put would replace the top of the
|
||||
// stack — which is the very question the side query was allowed to interrupt
|
||||
// rather than kill. Push keeps both.
|
||||
//
|
||||
// Push returns whatever the depth bound forced out, and that one has to be
|
||||
// spoken: MaxStackDepth is a promise that every level she keeps is a level
|
||||
// she can name when it dies. It is glued in front, like every other notice
|
||||
// about something let go.
|
||||
rt := turnRouteFrom(ctx)
|
||||
if rt != nil && rt.suspended {
|
||||
if evicted := h.clarifyStore.Push(dialogueIDOf(ctx), q); evicted != nil {
|
||||
log.Printf("voice: clarify — stack full at %d, letting go of the request behind %q", dialogue.MaxStackDepth, evicted.Utterance)
|
||||
rt.dropped = withNotice(rt.dropped, clarifyDropped)
|
||||
}
|
||||
// One question per breath still holds. The side query turned out to need
|
||||
// a question of its own, so THAT is the one she asks; resuming as well
|
||||
// would put two questions in one reply, which is the interrogation
|
||||
// askRemainingGap already refuses to run. The suspended flow keeps its
|
||||
// place underneath and is not lost — if it is never reached it dies on
|
||||
// the TTL, and the expiry notice (now plural-aware) says so.
|
||||
rt.resume = ""
|
||||
log.Printf("voice: clarify — asked about %s for intent=%s, stacked on a suspended flow", slot, dec.Intent)
|
||||
return question, true
|
||||
}
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), q)
|
||||
log.Printf("voice: clarify — asked about %s for intent=%s", slot, dec.Intent)
|
||||
return question, true
|
||||
}
|
||||
|
||||
// resolveClarifyAnswer reads an utterance as the answer to a parked question.
|
||||
// Returns ("", false) when no live question is parked (or it expired), so the
|
||||
// caller routes the utterance normally as a fresh request. Sibling of
|
||||
// resolveConfirm and checked in the same place.
|
||||
//
|
||||
// The answer is parsed with the same extractor the router uses, for the intent
|
||||
// she parked — no second parser. If it still does not fill the gap she asks
|
||||
// again, up to MaxAttempts; after that she says out loud that she did not
|
||||
// understand. She never drops the request in silence.
|
||||
// isOwnRequest reports whether an utterance asks for something in its own
|
||||
// right, which is what a clarify answer never does. Two offline tests over
|
||||
// tokens, both already written for other callers: a question shape, and a
|
||||
// capture verb. Cheap on purpose — this runs on the answer to every parked
|
||||
// question, and it must not cost a model call.
|
||||
//
|
||||
// It is not a general relevance test. A bare noun that answers nothing ("синий"
|
||||
// after "Что сделать?") is still treated as an answer and still re-asked, and
|
||||
// that is the intended shape: only an utterance that carries its own request
|
||||
// wins over the question in front of it.
|
||||
func isOwnRequest(text string) bool {
|
||||
return router.IsQuestionShaped(text) || router.CarriesCaptureVerb(text)
|
||||
}
|
||||
// clarifyCancelled — he called the half-built request off. Said out loud, like
|
||||
// every other way it can end: a silent drop reads as "done". Feminine
|
||||
// self-reference ("отменила"), as everywhere.
|
||||
const clarifyCancelled = "Хорошо, отменила."
|
||||
|
||||
// clarifyDropped — he asked for something ELSE instead, so the parked request
|
||||
// is gone. Glued in front of the answer to what he actually asked, because
|
||||
// nothing may be dropped in silence.
|
||||
//
|
||||
// Only new_request and cancel reach this since V-561. A side query used to as
|
||||
// well, and the owner rejected it on sight: he asks about the weather in the
|
||||
// middle of setting a reminder, and hearing "прошлую просьбу отпускаю" tells him
|
||||
// a thing he did not ask to lose has been lost. It had not been — there was
|
||||
// simply nowhere to put it. Now there is (ClarifyStore's stack), so a side query
|
||||
// suspends and resumes, and apologising for a drop that did not happen is worse
|
||||
// than saying nothing.
|
||||
const clarifyDropped = "Прошлую просьбу отпускаю."
|
||||
|
||||
// resolveClarifyAnswer reads an utterance against the parked question and
|
||||
// decides what it IS before deciding what to do with it. Returns ("", false)
|
||||
// when the turn is not this resolver's — nothing parked, or the utterance turned
|
||||
// out to be a request of its own — so the caller dispatches it normally.
|
||||
//
|
||||
// The order is the point (Vikunja #560). The utterance is ROUTED first, and the
|
||||
// role is read off that decision: a routed decision that stands on its own is
|
||||
// not an answer, whatever the extractor found inside it. Before this the
|
||||
// extractor decided, so "какая сейчас погода в Риме?" became the time of a
|
||||
// reminder on the strength of the word "сейчас".
|
||||
//
|
||||
// The answer itself is parsed with the same extractor the router uses, for the
|
||||
// intent she parked — no second parser. If it still does not fill the gap she
|
||||
// asks again, up to MaxAttempts; after that she says out loud that she did not
|
||||
// understand. She never drops the request in silence.
|
||||
func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string) (string, bool) {
|
||||
if h.clarifyStore == nil {
|
||||
return "", false
|
||||
}
|
||||
q := h.clarifyStore.Get(dialogueIDOf(ctx), h.now())
|
||||
if q == nil {
|
||||
return "", false
|
||||
return "", false // not_applicable: nothing is pending
|
||||
}
|
||||
|
||||
intent := router.Intent(q.Intent)
|
||||
answer := h.extractor.Extract(ctx, intent, text, h.now())
|
||||
merged := q.Answer(text, toDialogueSlots(answer))
|
||||
// He moved on. A parked question used to swallow whatever came next, so one
|
||||
// act she could not fulfil ate the following three turns: "выключи свет в
|
||||
// спальне" asked "Что сделать?", and "кто изобрёл телефон" was scored as an
|
||||
// answer to it, then "как дела" after that (Vikunja #554). Nothing checked
|
||||
// whether the words could be an answer at all.
|
||||
//
|
||||
// Deliberately narrow. It only fires where the answer filled nothing, so a
|
||||
// turn that closes the gap is still an answer whatever shape it has, and
|
||||
// the retry budget is untouched — the count was never the problem. Dropping
|
||||
// the question and routing the utterance as itself is what he meant either
|
||||
// way: if he really was answering, he can say it again, and if he was not,
|
||||
// he gets the thing he asked for instead of being asked a third time.
|
||||
if len(dialogue.StillMissing(q.Missing, merged)) > 0 && isOwnRequest(text) {
|
||||
|
||||
var (
|
||||
routed router.Decision
|
||||
routedOK bool
|
||||
)
|
||||
if needsRoute(text) {
|
||||
routed, routedOK = h.routeForRole(ctx, text)
|
||||
}
|
||||
role := classifyTurnRole(q, text, toDialogueSlots(answer), routed, routedOK)
|
||||
log.Printf("voice: clarify — %q is a %s against %s (routed=%v)", text, role, dialogue.CapabilityFor(q.Intent), routedOK)
|
||||
|
||||
switch role {
|
||||
case roleCancel:
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
log.Printf("voice: clarify — %q is its own request, not an answer to %v; dropping the question", text, q.Missing)
|
||||
return clarifyCancelled, true
|
||||
case roleSideQuery:
|
||||
// He asked something of his own WITHOUT leaving the flow. The question
|
||||
// stays exactly where it is — same slot, same attempt, same parked
|
||||
// utterance — and these words go on to be answered as themselves. The
|
||||
// resumed question is then glued onto the back of that answer, so one
|
||||
// reply carries both acts (Vikunja #561).
|
||||
//
|
||||
// No attempt is spent. He answered the side query, not the parked
|
||||
// question, and charging a retry for a turn that was never an answer is
|
||||
// the V-554 shape.
|
||||
h.noteSuspended(ctx, q)
|
||||
return "", false
|
||||
case roleAside:
|
||||
// He stated something in the middle of the flow. Same machinery as a
|
||||
// side query and for the same reason: the words are answered as
|
||||
// themselves, so the note or the fact is stored, and the question comes
|
||||
// back on the end of the same reply (V-577 shape 2). Storing it in
|
||||
// silence and dropping it in silence are both wrong, and dropping it is
|
||||
// what she did.
|
||||
h.noteSuspended(ctx, q)
|
||||
return "", false
|
||||
case roleNewRequest:
|
||||
// He moved on. A parked question used to swallow whatever came next, so
|
||||
// one act she could not fulfil ate the following three turns (Vikunja
|
||||
// #554) and a world question set a reminder for a time nobody asked for
|
||||
// (#558). Drop the question, say so, and let these words be themselves.
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
h.noteDropped(ctx)
|
||||
return "", false
|
||||
}
|
||||
|
||||
// He is answering, so the run of step-asides is over (V-654). Reset here
|
||||
// rather than where a gap is FILLED: "позвонить маме" against a question
|
||||
// about the time gives her nothing she asked for and still means he is in
|
||||
// the exchange, and the retry it costs is bound enough on its own. The
|
||||
// counter is for the case the bounds miss — he asked for other things and
|
||||
// never came back.
|
||||
q.Suspends = 0
|
||||
|
||||
merged := q.Answer(text, toDialogueSlots(answer))
|
||||
// Fold a newly answered subject into the raw utterance. Downstream actions
|
||||
// phrase from Utterance, not from the text slot — actionReminder stores it
|
||||
// as the reminder payload — so a reminder clarified out of a bare "напомни"
|
||||
// would fire at 11:00 saying "напомни" and nothing else.
|
||||
q.Utterance = foldAnswerIntoUtterance(q.Utterance, merged.Text)
|
||||
if len(dialogue.StillMissing(q.Missing, merged)) > 0 {
|
||||
return h.reaskOrGiveUp(ctx, q, merged, text), true
|
||||
// A fact answers with a key and a value and fills no Text slot at all, so
|
||||
// the fold above leaves the utterance at the bare "запиши" — and that is
|
||||
// what the confirmation now reads back to him (V-592). His raw words are the
|
||||
// only record of what he said, so they are what is folded. Never for a time
|
||||
// question: what he says about when is kept apart in WhenText on purpose,
|
||||
// or the reminder would read the day back at him when it fires.
|
||||
if merged.Text == "" && !asksAboutTime(q.Missing) {
|
||||
q.Utterance = foldAnswerIntoUtterance(q.Utterance, text)
|
||||
}
|
||||
// An answer about the time joins everything else he has said about the time,
|
||||
// and the whole of it is re-read as one request (V-579). "завтра" names the
|
||||
// day of an hour she is already holding, and read alone it names no hour at
|
||||
// all, so the parser would have nothing and she would ask for ever.
|
||||
// What he had already said about the time, read BEFORE this answer joins it.
|
||||
// A re-ask that cannot tell the two apart is the one that repeats itself
|
||||
// byte for byte (V-593).
|
||||
var taken string
|
||||
if asksAboutTime(q.Missing) {
|
||||
before := whenKnownOf(whenTextOf(q), q.Slots.HasTime)
|
||||
q.WhenText = strings.TrimSpace(q.WhenText + " " + text)
|
||||
if t, ok := h.readWhen(ctx, intent, q, text); ok {
|
||||
merged.Time, merged.HasTime = t, true
|
||||
}
|
||||
if before.movedForward(whenKnownOf(whenTextOf(q), merged.HasTime)) {
|
||||
taken = whenTakenLine(text)
|
||||
}
|
||||
}
|
||||
if stillOpen(q.Missing, whenTextOf(q), merged) {
|
||||
return h.reaskOrGiveUp(ctx, q, merged, text, taken), true
|
||||
}
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
|
||||
@@ -257,6 +446,64 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
|
||||
return h.finishClarified(ctx, dec), true
|
||||
}
|
||||
|
||||
// noteDropped records that the parked request was let go this turn, so runTurn
|
||||
// can say it in front of whatever these words are answered with. Nothing to
|
||||
// record outside runTurn — a unit test calling one resolver has no turn to glue
|
||||
// a notice onto.
|
||||
func (h *reactiveHandler) noteDropped(ctx context.Context) {
|
||||
if rt := turnRouteFrom(ctx); rt != nil {
|
||||
rt.dropped = clarifyDropped
|
||||
}
|
||||
}
|
||||
|
||||
// noteSuspended keeps the parked question alive across a side query and records
|
||||
// the words that bring it back, so runTurn can put them after this turn's answer
|
||||
// (Vikunja #561).
|
||||
//
|
||||
// Two things happen to the question and neither is an attempt. Its clock is
|
||||
// restarted, because she is about to ask it again and the 90s TTL measures the
|
||||
// pause since she last spoke it — leaving Asked at the original ask would let a
|
||||
// flow he is actively working through die of a wait he did not take. And the
|
||||
// stack is left exactly as it is: the question is already on top, so suspending
|
||||
// it is not a write.
|
||||
//
|
||||
// A slot with no resumed wording (clarifyResumedFor says so) resumes nothing and
|
||||
// says nothing. She must not claim to be holding a question she cannot re-ask.
|
||||
//
|
||||
// Suspension is bounded, since V-654. Neither of the two things above is a
|
||||
// limit: no attempt is spent, and restarting the clock means the TTL cannot
|
||||
// arrive while he keeps talking. So the count is the only thing that ends it,
|
||||
// and past MaxSuspends she lets the request go and says so with the same line
|
||||
// every other drop uses. The rule is unchanged — a question ends by being
|
||||
// answered or by being let go out loud — this only recognises three unrelated
|
||||
// requests in a row as the second of those.
|
||||
func (h *reactiveHandler) noteSuspended(ctx context.Context, q *dialogue.PendingQuestion) {
|
||||
rt := turnRouteFrom(ctx)
|
||||
if rt == nil || len(q.Missing) == 0 {
|
||||
return
|
||||
}
|
||||
question, ok := clarifyResumedFor(q.Missing[0])
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
if !q.CanResume() {
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
h.noteDropped(ctx)
|
||||
log.Printf("voice: clarify — letting the question about %s go: %d asides in a row, %d rides in all", q.Missing[0], q.Suspends, q.Rides)
|
||||
return
|
||||
}
|
||||
q.Suspends++
|
||||
// Rides is the same event counted without the reset (V-663). Incremented
|
||||
// beside Suspends and never anywhere else, so the two cannot disagree about
|
||||
// what happened, only about how much of it they remember.
|
||||
q.Rides++
|
||||
q.Asked = h.now()
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), q)
|
||||
rt.resume = question
|
||||
rt.suspended = true
|
||||
log.Printf("voice: clarify — is its own request; suspending the question about %s and resuming it in the same reply (suspend %d of %d, ride %d of %d)", q.Missing[0], q.Suspends, dialogue.MaxSuspends, q.Rides, dialogue.MaxRides)
|
||||
}
|
||||
|
||||
// foldAnswerIntoUtterance appends an answered subject to the original words,
|
||||
// unless they already carry it. "напомни" + "позвонить маме" reads as the
|
||||
// request he would have made in one breath. Nothing is appended when the
|
||||
@@ -284,25 +531,35 @@ func foldAnswerIntoUtterance(utterance, subject string) string {
|
||||
// costs a question exactly like a second try at the first one does, so the cap
|
||||
// still bounds how many times she can speak before acting or letting go.
|
||||
func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.PendingQuestion, intent router.Intent, merged dialogue.Slots) (string, bool) {
|
||||
remaining := dialogue.StillMissing(wantedSlots[intent], merged)
|
||||
remaining := stillMissingFor(intent, whenTextOf(q), merged)
|
||||
if len(remaining) == 0 {
|
||||
return "", false
|
||||
}
|
||||
// Attempts+1 is the question she is about to ask, and the budget is shared
|
||||
// with the re-ask path, so the second gap is worded like a second try.
|
||||
question, ok := clarifyQuestionFor(remaining[0], q.Attempts+1)
|
||||
question, ok := h.questionFor(remaining[0], q.Attempts+1, whenTextOf(q), merged, "")
|
||||
if !ok || !q.CanAsk() {
|
||||
return "", false
|
||||
}
|
||||
// Suspends is not carried, and by this point it is already zero: the answer
|
||||
// path resets it (V-654). Left off the literal so the zero is stated where
|
||||
// the struct is built, rather than inherited from a field nobody names.
|
||||
//
|
||||
// Rides IS carried, and that is the whole point of it (V-663). This is the
|
||||
// same request under a second question, not a new one, so the turns it has
|
||||
// already ridden still count against it. Dropping the field here is exactly
|
||||
// the re-basing that let one question ride twenty-six replies.
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
|
||||
Intent: q.Intent,
|
||||
Slots: merged,
|
||||
Missing: []dialogue.Slot{remaining[0]},
|
||||
Utterance: q.Utterance,
|
||||
WhenText: q.WhenText,
|
||||
Asked: h.now(),
|
||||
TTL: clarifyTTL,
|
||||
Attempts: q.Attempts + 1,
|
||||
MaxAttempts: q.MaxAttempts,
|
||||
Rides: q.Rides,
|
||||
})
|
||||
log.Printf("voice: clarify — one gap filled, still missing %s for intent=%s, asking again (attempt %d)", remaining[0], intent, q.Attempts+1)
|
||||
return question, true
|
||||
@@ -311,10 +568,12 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
|
||||
// reaskOrGiveUp handles an answer that left the gap open: ask the same question
|
||||
// again while she has attempts left, otherwise say she did not understand and
|
||||
// let the request go. Never returns "" — a mute give-up reads as "done".
|
||||
func (h *reactiveHandler) reaskOrGiveUp(ctx context.Context, q *dialogue.PendingQuestion, merged dialogue.Slots, text string) string {
|
||||
// taken is the acknowledgement of what this answer DID give, empty when it gave
|
||||
// nothing (V-593). The give-up line never carries it: it is not another ask.
|
||||
func (h *reactiveHandler) reaskOrGiveUp(ctx context.Context, q *dialogue.PendingQuestion, merged dialogue.Slots, text, taken string) string {
|
||||
question := ""
|
||||
if len(q.Missing) > 0 {
|
||||
question, _ = clarifyQuestionFor(q.Missing[0], q.Attempts+1)
|
||||
question, _ = h.questionFor(q.Missing[0], q.Attempts+1, whenTextOf(q), merged, taken)
|
||||
}
|
||||
if question == "" || !q.CanAsk() {
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
@@ -342,7 +601,7 @@ func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decisi
|
||||
}
|
||||
reply := h.applyAction(ctx, dec)
|
||||
if reply == "" {
|
||||
reply = h.replier.Reply(dec)
|
||||
reply = h.replier.Reply(ctx, dec)
|
||||
}
|
||||
if reply == "" {
|
||||
// Belt: an empty reply here would be a silent drop.
|
||||
@@ -351,20 +610,22 @@ func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decisi
|
||||
return reply
|
||||
}
|
||||
|
||||
// maxCarriedHistory — how many turns of PRIOR history (beyond the immediate
|
||||
// last turn) rememberTurn carries forward. The session ends up holding this
|
||||
// many plus the one just-finished turn, so callers describing the total
|
||||
// depth (chatHistory's doc comment, this one) say "up to 4".
|
||||
const maxCarriedHistory = 3
|
||||
|
||||
// rememberTurn stores this turn as the dialogue session the next follow-up
|
||||
// inherits from, carrying up to 4 prior turns of history for anaphora. Capped so
|
||||
// one long conversation can't grow the session unboundedly.
|
||||
func (h *reactiveHandler) rememberTurn(ctx context.Context, prev *dialogue.Session, dec router.Decision, now time.Time) {
|
||||
var history []dialogue.Turn
|
||||
if prev != nil {
|
||||
history = append(history, dialogue.Turn{
|
||||
Intent: prev.Intent,
|
||||
Slots: prev.Slots,
|
||||
Text: prev.Slots.Text,
|
||||
})
|
||||
history = append(history, sessionAsTurn(prev))
|
||||
maxHist := len(prev.History)
|
||||
if maxHist > 3 {
|
||||
maxHist = 3
|
||||
if maxHist > maxCarriedHistory {
|
||||
maxHist = maxCarriedHistory
|
||||
}
|
||||
history = append(history, prev.History[:maxHist]...)
|
||||
}
|
||||
|
||||
+214
-44
@@ -10,6 +10,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/phraser/eval"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
@@ -57,18 +58,26 @@ func TestClarifyQuestionForMissingSlot(t *testing.T) {
|
||||
want string
|
||||
asked bool
|
||||
}{
|
||||
{"reminder without a time", clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"), "Когда?", true},
|
||||
{"reminder without a time", clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"), "Сейчас 09:00. Когда?", true},
|
||||
{"fact without a key", clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши"), "Что записать?", true},
|
||||
{"act without a fn", clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это"), "Что сделать?", true},
|
||||
// A time with nothing to say at that time is still half a reminder, so
|
||||
// the subject is what she asks about — not silence.
|
||||
{"reminder that has a time but no subject", clarifyDec(router.IntentReminder, router.Slots{HasTime: true}, "напомни в 11"), "О чём напомнить?", true},
|
||||
{"reminder that has both", clarifyDec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}, "напомни в 11 позвонить маме"), "", false},
|
||||
// A bare hour is half of a day away from being an answer, and she asks
|
||||
// which half rather than picking one (V-579).
|
||||
{"reminder whose hour could be either half of the day", clarifyDec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}, "напомни в 11 позвонить маме"), "Сейчас 09:00. Это утра или вечера?", true},
|
||||
{"reminder that has all three", clarifyDec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}, "напомни завтра в 15:00 позвонить маме"), "", false},
|
||||
// The owner's own two, confirmed 2026-08-06: an unambiguous time and a
|
||||
// relative one are both complete and are never asked about.
|
||||
{"an interval names the instant by itself", clarifyDec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}, "напомни через час позвонить маме"), "", false},
|
||||
{"half an hour is an interval too", clarifyDec(router.IntentReminder, router.Slots{Text: "выключить духовку", HasTime: true}, "напомни через полчаса выключить духовку"), "", false},
|
||||
{"chat is never worth a question", clarifyDec(router.IntentChat, router.Slots{Text: "мгм"}, "мгм"), "", false},
|
||||
{"query is never worth a question", clarifyDec(router.IntentQuery, router.Slots{Text: "а"}, "а"), "", false},
|
||||
}
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
for _, tc := range cases {
|
||||
_, got, asked := clarifyQuestion(tc.dec)
|
||||
_, got, asked := h.clarifyQuestion(tc.dec)
|
||||
if asked != tc.asked || got != tc.want {
|
||||
t.Errorf("%s: got (%q, %v), want (%q, %v)", tc.name, got, asked, tc.want, tc.asked)
|
||||
}
|
||||
@@ -82,11 +91,13 @@ func TestClarifyReminderCompletesOnAnswer(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
|
||||
if !asked || question != "Когда?" {
|
||||
if !asked || question != "Сейчас 09:00. Когда?" {
|
||||
t.Fatalf("expected the time question, got %q asked=%v", question, asked)
|
||||
}
|
||||
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00")
|
||||
// The answer names the day as well as the hour. A reminder commits on what,
|
||||
// what time and what day, and a dayless hour is asked about (V-579).
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "сегодня в 11:00")
|
||||
if !handled {
|
||||
t.Fatal("the answer to an open question must be consumed as an answer")
|
||||
}
|
||||
@@ -158,11 +169,11 @@ func TestClarifyAsksThreeTimesThenSaysSo(t *testing.T) {
|
||||
}
|
||||
// The wording changes with the attempt (Vikunja #457): repeating a
|
||||
// question he already failed to answer is the worst way to ask it.
|
||||
want, _ := clarifyQuestionFor(dialogue.SlotTime, i)
|
||||
want, _ := whenQuestion(whenNoHour, i, h.now(), "")
|
||||
if reply != want {
|
||||
t.Fatalf("attempt %d should ask again as %q, got %q", i, want, reply)
|
||||
}
|
||||
if first, _ := clarifyQuestionFor(dialogue.SlotTime, 1); reply == first {
|
||||
if first, _ := whenQuestion(whenNoHour, 1, h.now(), ""); reply == first {
|
||||
t.Fatalf("attempt %d repeated the first wording: %q", i, reply)
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) == nil {
|
||||
@@ -215,10 +226,11 @@ func TestClarifyRestatedAnswerWins(t *testing.T) {
|
||||
if q == nil {
|
||||
t.Fatal("expected an armed question")
|
||||
}
|
||||
first := h.extractor.Extract(ctx, router.IntentReminder, "в 11:00", h.now())
|
||||
q.Slots = q.Answer("в 11:00", toDialogueSlots(first))
|
||||
first := h.extractor.Extract(ctx, router.IntentReminder, "сегодня в 11:00", h.now())
|
||||
q.Slots = q.Answer("сегодня в 11:00", toDialogueSlots(first))
|
||||
q.WhenText = "сегодня в 11:00"
|
||||
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "нет, в 15:00"); !handled || reply == clarifyGaveUp {
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "нет, сегодня в 15:00"); !handled || reply == clarifyGaveUp {
|
||||
t.Fatalf("the restated answer should complete the request, handled=%v reply=%q", handled, reply)
|
||||
}
|
||||
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
|
||||
@@ -231,34 +243,35 @@ func TestClarifyRestatedAnswerWins(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestClarifiedActOffAllowlistIsStillRefused — clarification fills in an
|
||||
// argument, it never grants authority.
|
||||
func TestClarifiedActOffAllowlistIsStillRefused(t *testing.T) {
|
||||
// TestActOffAllowlistIsStillRefused — naming a capability is not being granted
|
||||
// one. Since Vikunja #556 an unresolved act no longer parks a question, so this
|
||||
// goes through applyAction, which is the only way an act runs.
|
||||
func TestActOffAllowlistIsStillRefused(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
marker := filepath.Join(t.TempDir(), "not-allowed-ran")
|
||||
if err := st.EnableTool(ctx, "uptime", []string{"true"}, false, "test", h.now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
|
||||
t.Fatal("an act with no fn should be asked about")
|
||||
}
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "rm "+marker)
|
||||
if !handled {
|
||||
t.Fatal("the answer should be consumed")
|
||||
}
|
||||
reply := h.applyAction(ctx, router.Decision{
|
||||
Utterance: "rm " + marker,
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Fn: "rm " + marker, HasFn: true},
|
||||
})
|
||||
if strings.Contains(reply, "готово") {
|
||||
t.Fatalf("an act that is not on the allowlist must not report success: %q", reply)
|
||||
}
|
||||
if _, err := os.Stat(marker); !os.IsNotExist(err) {
|
||||
t.Fatalf("a clarified act off the allowlist ran anyway: %v", err)
|
||||
}
|
||||
if tools, err := st.ListTools(ctx, "enabled"); err != nil || len(tools) != 0 {
|
||||
t.Fatalf("clarify must not enable a tool: tools=%+v err=%v", tools, err)
|
||||
if tools, err := st.ListTools(ctx, "enabled"); err != nil || len(tools) != 1 {
|
||||
t.Fatalf("an act must not enable a tool: tools=%+v err=%v", tools, err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestClarifiedDestructiveActStillNeedsConfirm — the confirm gate survives the
|
||||
// clarify path.
|
||||
func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
|
||||
// TestDestructiveActStillNeedsConfirm — the confirm gate stands on the act path.
|
||||
func TestDestructiveActStillNeedsConfirm(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
marker := filepath.Join(t.TempDir(), "destructive-ran")
|
||||
@@ -266,18 +279,16 @@ func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "delete_backups")
|
||||
if !handled {
|
||||
t.Fatal("the answer should be consumed")
|
||||
}
|
||||
reply := h.applyAction(ctx, router.Decision{
|
||||
Utterance: "delete_backups",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Fn: "delete_backups", HasFn: true},
|
||||
})
|
||||
if !strings.Contains(reply, "да") || h.pending == nil {
|
||||
t.Fatalf("a clarified destructive act must still park a confirm: reply=%q pending=%+v", reply, h.pending)
|
||||
t.Fatalf("a destructive act must park a confirm: reply=%q pending=%+v", reply, h.pending)
|
||||
}
|
||||
if _, err := os.Stat(marker); !os.IsNotExist(err) {
|
||||
t.Fatalf("a clarified destructive act ran before confirmation: %v", err)
|
||||
t.Fatalf("a destructive act ran before confirmation: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -306,7 +317,7 @@ func TestClarifyExpiryIsAnnouncedAndWordsStillRoute(t *testing.T) {
|
||||
h, _, now := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
h.recall.embedder = emb
|
||||
h.router = buildRouter(emb, h.matcher, 0.55, nil)
|
||||
h.router = buildRouter(emb, h.matcher, 0.55, nil, nil)
|
||||
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
@@ -357,7 +368,7 @@ func TestClarifyAsksAboutTheSecondGapToo(t *testing.T) {
|
||||
}
|
||||
// Second gap, second attempt, so it is the second wording of the time
|
||||
// question — the attempt budget is shared between the two paths.
|
||||
want, _ := clarifyQuestionFor(dialogue.SlotTime, 2)
|
||||
want, _ := whenQuestion(whenNoHour, 2, h.now(), "")
|
||||
if reply != want {
|
||||
t.Fatalf("a filled subject with no time must ask about the time as %q, got %q", want, reply)
|
||||
}
|
||||
@@ -369,7 +380,7 @@ func TestClarifyAsksAboutTheSecondGapToo(t *testing.T) {
|
||||
t.Fatalf("the re-parked question lost the answered subject: %+v", q.Slots)
|
||||
}
|
||||
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00"); !handled || reply == clarifyGaveUp {
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "сегодня в 11:00"); !handled || reply == clarifyGaveUp {
|
||||
t.Fatalf("the time answer must complete the reminder, handled=%v reply=%q", handled, reply)
|
||||
}
|
||||
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
|
||||
@@ -419,7 +430,7 @@ func TestClarifyProseHoldsThePersona(t *testing.T) {
|
||||
eval.CheckAddress: true,
|
||||
eval.CheckCringe: true,
|
||||
}
|
||||
lines := append([]string{clarifyGaveUp}, clarifyExpiredVariants...)
|
||||
lines := append([]string{clarifyGaveUp, clarifyCancelled, clarifyDropped}, clarifyExpiredVariants...)
|
||||
lines = append(lines, clarifyMissedVariants...)
|
||||
for _, variants := range clarifyQuestionVariants {
|
||||
lines = append(lines, variants...)
|
||||
@@ -487,7 +498,7 @@ func TestClarifySubjectAnswerFillsRatherThanClobbers(t *testing.T) {
|
||||
at := h.now().Add(2 * time.Hour)
|
||||
|
||||
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder,
|
||||
router.Slots{Time: at, HasTime: true}, "напомни в 11"))
|
||||
router.Slots{Time: at, HasTime: true}, "напомни сегодня в 11 утра"))
|
||||
if !asked || question != "О чём напомнить?" {
|
||||
t.Fatalf("expected the subject question, got %q asked=%v", question, asked)
|
||||
}
|
||||
@@ -573,14 +584,24 @@ func TestClarifyStepsAsideForItsOwnRequest(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "выключи свет в спальне"}, "выключи свет в спальне")); !asked {
|
||||
t.Fatal("an act with no fn should be asked about")
|
||||
// A reminder, not the act this bug was found on: since Vikunja #556 an act
|
||||
// no longer parks anything, so it can no longer eat the turn after it.
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
|
||||
t.Fatal("a reminder with no time should be asked about")
|
||||
}
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "кто изобрёл телефон"); handled {
|
||||
t.Fatalf("a world question must route as itself, got %q", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
|
||||
t.Error("the parked question must be dropped, not left to eat the turn after this one")
|
||||
// Not eating the turn is `handled == false` above, and that is the whole of
|
||||
// #554. Since V-561 the question also SURVIVES it: a side query suspends the
|
||||
// flow rather than ending it, so the reminder is still there and still on the
|
||||
// attempt it was parked with.
|
||||
q := h.clarifyStore.Get(voiceDialogueID, h.now())
|
||||
if q == nil {
|
||||
t.Fatal("a side query must suspend the parked question, not drop it")
|
||||
}
|
||||
if q.Attempts != 1 {
|
||||
t.Errorf("a turn that was never an answer spent an attempt: %d, want 1", q.Attempts)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -613,10 +634,159 @@ func TestClarifyQuestionShapedAnswerThatFillsTheGapStillLands(t *testing.T) {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
|
||||
t.Fatal("expected the time question")
|
||||
}
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "а что если в 11:00"); !handled || reply == clarifyGaveUp {
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "а что если сегодня в 11:00"); !handled || reply == clarifyGaveUp {
|
||||
t.Fatalf("an answer that fills the gap must land, handled=%v reply=%q", handled, reply)
|
||||
}
|
||||
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 1 {
|
||||
t.Fatalf("reminder was not created: reminders=%v err=%v", reminders, err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestUnresolvedActSaysItDoesNotKnowTheCommand — Vikunja #556. "Что сделать?"
|
||||
// has no answer he can give, so an act that matched no capability is refused in
|
||||
// one line and nothing is parked. It does not recite what she can do instead.
|
||||
func TestUnresolvedActSaysItDoesNotKnowTheCommand(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
// Enabled tools change nothing here: this act matched none of them.
|
||||
if err := st.EnableTool(ctx, "uptime", []string{"true"}, false, "test", h.now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
reply, spoken := h.askClarify(ctx, clarifyDec(router.IntentAct, router.Slots{Text: "выключи свет"}, "выключи свет"))
|
||||
if !spoken || reply != actNotRecognized {
|
||||
t.Fatalf("reply = %q spoken=%v, want %q", reply, spoken, actNotRecognized)
|
||||
}
|
||||
if strings.Contains(reply, "uptime") {
|
||||
t.Errorf("reply = %q, want no list of capabilities he did not ask about", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
|
||||
t.Error("nothing to ask about, so nothing may be parked")
|
||||
}
|
||||
}
|
||||
|
||||
// newRoutingClarifyHandler wires the real cascade (hash embedder, no model) onto
|
||||
// the clarify handler, so a test can drive handleText end to end and see which
|
||||
// gate claimed the turn.
|
||||
func newRoutingClarifyHandler(t *testing.T) (*reactiveHandler, *store.Store) {
|
||||
t.Helper()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
h.router = buildRouter(router.NewHashEmbedder(1024), h.matcher, 0.55, nil, nil)
|
||||
h.recall = recallWiring{embedder: router.NewHashEmbedder(1024), memStore: memory.NewInMemoryStore()}
|
||||
return h, st
|
||||
}
|
||||
|
||||
// TestIncompleteReminderAsksInsteadOfFailing — Vikunja #557. "напомни позвонить"
|
||||
// is routed confidently and is still half a request. It used to reach applyAction,
|
||||
// fail on the missing time and park nothing, so the "в семь вечера" that followed
|
||||
// was routed as a world question and web-searched.
|
||||
func TestIncompleteReminderAsksInsteadOfFailing(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newRoutingClarifyHandler(t)
|
||||
|
||||
reply := h.handleText(ctx, "web", "напомни позвонить маме")
|
||||
want, _ := whenQuestion(whenNoHour, 1, h.now(), "")
|
||||
if reply != want {
|
||||
t.Fatalf("reply = %q, want the time question %q", reply, want)
|
||||
}
|
||||
if h.clarifyStore.Get(dialogueIDFor(sourceText, "web"), h.now()) == nil {
|
||||
t.Fatal("the request must be parked, or the answer has nowhere to land")
|
||||
}
|
||||
if reply := h.handleText(ctx, "web", "сегодня в семь вечера"); strings.Contains(reply, "нашла") {
|
||||
t.Fatalf("the answer to her own question must not be looked up: %q", reply)
|
||||
}
|
||||
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 1 {
|
||||
t.Fatalf("the answer did not complete the reminder: reminders=%v err=%v", reminders, err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestBareCaptureVerbAsksWhatToRecord — the other half of #557. A bare "запиши"
|
||||
// went to the resident model as chat, which agreed to a wording change nobody
|
||||
// asked for. It is a fact with no key, and that gap has a question.
|
||||
func TestBareCaptureVerbAsksWhatToRecord(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newRoutingClarifyHandler(t)
|
||||
|
||||
reply := h.handleText(ctx, "web", "запиши")
|
||||
want, _ := clarifyQuestionFor(dialogue.SlotKey, 1)
|
||||
if reply != want {
|
||||
t.Fatalf("reply = %q, want %q", reply, want)
|
||||
}
|
||||
if h.clarifyStore.Get(dialogueIDFor(sourceText, "web"), h.now()) == nil {
|
||||
t.Fatal("the request must be parked so the next utterance completes it")
|
||||
}
|
||||
}
|
||||
|
||||
// TestACompleteTurnStillDoesNotAsk — the gate reads a missing slot, not any
|
||||
// slot, so a request she can act on must never turn into a question. Checked on
|
||||
// the decision rather than through the cascade: what is at stake is the gate's
|
||||
// condition, and driving it through the hash embedder would measure routing.
|
||||
func TestACompleteTurnStillDoesNotAsk(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
|
||||
complete := []router.Decision{
|
||||
{Intent: router.IntentReminder, Slots: router.Slots{Text: "позвонить маме", HasTime: true}, Utterance: "напомни завтра в 11 утра позвонить маме"},
|
||||
{Intent: router.IntentFact, Slots: router.Slots{Key: "water", Value: "выпил", HasKey: true}, Utterance: "я выпил воды"},
|
||||
{Intent: router.IntentNote, Slots: router.Slots{Text: "купить хлеб"}, Utterance: "запиши купить хлеб"},
|
||||
{Intent: router.IntentQuery, Slots: router.Slots{Text: "что у меня сегодня"}, Utterance: "что у меня сегодня"},
|
||||
}
|
||||
for _, dec := range complete {
|
||||
if gaps := missingFor(dec); len(gaps) > 0 {
|
||||
t.Errorf("%q reads as incomplete: %v", dec.Utterance, gaps)
|
||||
}
|
||||
if reply, asked := h.askClarify(ctx, dec); asked {
|
||||
t.Errorf("%q was answered with a question: %q", dec.Utterance, reply)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestTheResumedQuestionIsItsOwnSentence — V-654. The re-ask used to be spliced
|
||||
// onto the answer with a comma, so a real answer and an unrelated open question
|
||||
// read as one run-on thought and the question vanished into its tail.
|
||||
func TestTheResumedQuestionIsItsOwnSentence(t *testing.T) {
|
||||
const resumed = "На какое время поставить напоминание?"
|
||||
cases := []struct {
|
||||
name string
|
||||
reply string
|
||||
want string
|
||||
}{
|
||||
{
|
||||
// The measured line, shortened. Two sentences, and the question keeps
|
||||
// its capital.
|
||||
name: "a statement keeps its full stop",
|
||||
reply: "Вайфай пароль лежит в ящике стола.",
|
||||
want: "Вайфай пароль лежит в ящике стола. " + resumed,
|
||||
},
|
||||
{
|
||||
name: "a reply with no terminator is given one",
|
||||
reply: "Вайфай пароль лежит в ящике стола",
|
||||
want: "Вайфай пароль лежит в ящике стола. " + resumed,
|
||||
},
|
||||
{
|
||||
// She sometimes answers a side query by asking him to say it again.
|
||||
// Two questions, and neither may swallow the other.
|
||||
name: "a question keeps its mark",
|
||||
reply: "Можешь переформулировать?",
|
||||
want: "Можешь переформулировать? " + resumed,
|
||||
},
|
||||
{
|
||||
name: "an ellipsis is already an ending",
|
||||
reply: "Не уверена…",
|
||||
want: "Не уверена… " + resumed,
|
||||
},
|
||||
{
|
||||
name: "a resume with no answer in front of it is just the question",
|
||||
reply: "",
|
||||
want: resumed,
|
||||
},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
if got := withResumed(tc.reply, resumed); got != tc.want {
|
||||
t.Errorf("%s: withResumed(%q) = %q, want %q", tc.name, tc.reply, got, tc.want)
|
||||
}
|
||||
}
|
||||
if got := withResumed("Готово.", ""); got != "Готово." {
|
||||
t.Errorf("nothing to resume must leave the reply alone, got %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -40,6 +40,9 @@ var clarifyQuestionVariants = map[dialogue.Slot][]string{
|
||||
"Что именно отметить?",
|
||||
"Назови, что записать — например, «выпил воды».",
|
||||
},
|
||||
// Not spoken since Vikunja #556: askClarify answers actNotRecognized for a
|
||||
// missing capability rather than asking. Kept because clarifyQuestion still
|
||||
// reports the gap, and a re-ask deck with a hole in it is harder to read.
|
||||
dialogue.SlotFn: {
|
||||
"Что сделать?",
|
||||
"Какое действие выполнить?",
|
||||
@@ -47,6 +50,49 @@ var clarifyQuestionVariants = map[dialogue.Slot][]string{
|
||||
},
|
||||
}
|
||||
|
||||
// clarifyResumedVariants — the wording for a question coming BACK after a side
|
||||
// query took the turn away from it (Vikunja #561).
|
||||
//
|
||||
// It is not the first question again. "Когда?" works in the same breath as
|
||||
// "напомни позвонить маме", because the thing it is about was just said. After
|
||||
// a turn about the weather in Rome it does not: he has been thinking about
|
||||
// something else, and a bare "Когда?" asks him to remember what she is holding.
|
||||
// So the resumed form names the request — "напоминание", "заметка" — and the
|
||||
// first form stays short.
|
||||
//
|
||||
// One wording per slot, not a rotation and not an attempt ladder. A resume does
|
||||
// not spend an attempt (that is the point of suspending rather than re-asking),
|
||||
// so there is no attempt number to vary on, and this line is heard once per
|
||||
// interruption rather than repeatedly.
|
||||
//
|
||||
// Persona holds: infinitive, so no gender agreement, "ты" nowhere needed, no pet
|
||||
// names.
|
||||
var clarifyResumedVariants = map[dialogue.Slot]string{
|
||||
dialogue.SlotTime: "На какое время поставить напоминание?",
|
||||
dialogue.SlotText: "Так о чём напомнить?",
|
||||
dialogue.SlotKey: "Так что записать?",
|
||||
dialogue.SlotFn: "Так какое действие выполнить?",
|
||||
}
|
||||
|
||||
// clarifyResumedFor gives the resumed wording for a slot. ("", false) when the
|
||||
// slot has none, and the caller then resumes nothing rather than inventing a
|
||||
// question — a flow it cannot re-ask is one it must not claim to be holding.
|
||||
func clarifyResumedFor(slot dialogue.Slot) (string, bool) {
|
||||
q, ok := clarifyResumedVariants[slot]
|
||||
return q, ok
|
||||
}
|
||||
|
||||
// actNotRecognized is what an act she cannot run gets (Vikunja #556).
|
||||
//
|
||||
// The deck used to ask "Что сделать?" instead. That question has no answer he
|
||||
// can give: he already said what he wanted, and nothing he repeats will match a
|
||||
// capability that is not there. So she asked, failed, asked again and gave up —
|
||||
// three turns spent on one refusal. She says it once now, and parks nothing.
|
||||
//
|
||||
// It does not recite the allowlist. A list of names he did not ask about is not
|
||||
// an answer to the thing he did ask about.
|
||||
const actNotRecognized = "Такую команду я не знаю."
|
||||
|
||||
// clarifyQuestionFor picks the wording for this attempt. attempt is 1-based, as
|
||||
// PendingQuestion.Attempts counts it; anything past the list uses the last and
|
||||
// most explicit phrasing rather than wrapping round to the short one, because
|
||||
|
||||
+111
-22
@@ -3,9 +3,13 @@ package main
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
@@ -20,6 +24,14 @@ type pendingHexisExec struct {
|
||||
entityID string
|
||||
displayName string
|
||||
expiry time.Time
|
||||
|
||||
// correlationID — the id the proposing turn minted for this action. A
|
||||
// confirm arrives on a later turn with a context of its own, so without
|
||||
// carrying it here the execution recorded a fresh id and no causation at
|
||||
// all, and the resolve, the discovery and the thing they authorised sat in
|
||||
// the trace as unrelated calls. The contract mints one id per action, and
|
||||
// the action began when she asked.
|
||||
correlationID string
|
||||
}
|
||||
|
||||
// pendingRoutineConfirm — a proposed routine awaiting a spoken y/n to become
|
||||
@@ -57,10 +69,18 @@ func (h *reactiveHandler) park(fn string, args []string, phrase string) {
|
||||
// resolveConfirm interprets an utterance as the answer to a parked destructive
|
||||
// act OR a parked routine proposal. Returns (reply, true) when it consumed the
|
||||
// utterance as a y/n answer; ("", false) when there's nothing pending (or the
|
||||
// parked act expired), so the caller routes the utterance normally. An
|
||||
// unrecognised answer cancels the pending and routes normally — a confirm that
|
||||
// can't be answered clearly is safer abandoned than left armed.
|
||||
// parked act expired), so the caller routes the utterance normally.
|
||||
//
|
||||
// An utterance that is not clearly yes or no is not an answer at all, so it is
|
||||
// handed straight back and the pending stays parked until it expires (V-567).
|
||||
// This resolver runs before routing and holds the most dangerous trigger on the
|
||||
// box; it may only claim a turn it is certain about.
|
||||
func (h *reactiveHandler) resolveConfirm(ctx context.Context, text string) (string, bool) {
|
||||
verdict := classifyConfirm(text)
|
||||
if verdict == confirmUnknown {
|
||||
return "", false
|
||||
}
|
||||
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
|
||||
@@ -68,16 +88,12 @@ func (h *reactiveHandler) resolveConfirm(ctx context.Context, text string) (stri
|
||||
if !r.claim() {
|
||||
continue
|
||||
}
|
||||
// The slot is already cleared by claim(): every branch below drops the
|
||||
// pending, including the unclear one — a confirm that can't be
|
||||
// answered clearly is safer abandoned than left armed.
|
||||
switch classifyConfirm(text) {
|
||||
// The slot is already cleared by claim().
|
||||
switch verdict {
|
||||
case confirmYes:
|
||||
return r.yes(), true
|
||||
case confirmNo:
|
||||
return r.no(), true
|
||||
default:
|
||||
return "", false
|
||||
return r.no(), true
|
||||
}
|
||||
}
|
||||
return "", false
|
||||
@@ -136,7 +152,11 @@ func (h *reactiveHandler) confirmResolvers(ctx context.Context) []confirmResolve
|
||||
return hx != nil && !h.now().After(hx.expiry)
|
||||
},
|
||||
yes: func() string {
|
||||
return h.execHexis(ctx, hx.capabilityID, hx.capName, hx.entityID, hx.displayName)
|
||||
execCtx := ctx
|
||||
if hx.correlationID != "" {
|
||||
execCtx = withCorrelationID(execCtx, hx.correlationID)
|
||||
}
|
||||
return h.execHexis(execCtx, hx.capabilityID, hx.capName, hx.entityID, hx.displayName)
|
||||
},
|
||||
no: func() string { return phraser.C(phraser.ConfirmCancelled, nil) },
|
||||
},
|
||||
@@ -194,23 +214,92 @@ const (
|
||||
confirmNo
|
||||
)
|
||||
|
||||
// classifyConfirm reads a short ru/en yes-or-no answer. Substring match on the
|
||||
// stems so inflections/fillers ("да, давай", "нет, отмени") still land.
|
||||
// confirmWords are the two closed sets, tokenized once and ordered
|
||||
// longest-first so "не надо" is read before "нет" could claim any of it.
|
||||
var (
|
||||
confirmYesPhrases = confirmPhrases(lexicon.ConfirmYes())
|
||||
confirmNoPhrases = confirmPhrases(lexicon.ConfirmNo())
|
||||
)
|
||||
|
||||
// confirmPhrases splits each lexicon member into tokens and sorts the result
|
||||
// longest-first, so a walk that tries them in order matches the longest member
|
||||
// that fits.
|
||||
func confirmPhrases(words []string) [][]string {
|
||||
out := make([][]string, 0, len(words))
|
||||
for _, w := range words {
|
||||
if toks := confirmTokens(w); len(toks) > 0 {
|
||||
out = append(out, toks)
|
||||
}
|
||||
}
|
||||
sort.SliceStable(out, func(i, j int) bool { return len(out[i]) > len(out[j]) })
|
||||
return out
|
||||
}
|
||||
|
||||
// confirmTokens splits an utterance into lowercase word tokens. Punctuation and
|
||||
// spacing are separators; an apostrophe is not, because "don't" is one word.
|
||||
func confirmTokens(text string) []string {
|
||||
return strings.FieldsFunc(strings.ToLower(text), func(r rune) bool {
|
||||
if r == '\'' || r == '’' {
|
||||
return false
|
||||
}
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
})
|
||||
}
|
||||
|
||||
// classifyConfirm reads a short ru/en yes-or-no answer to a parked confirm.
|
||||
//
|
||||
// The whole utterance must consist of confirmation words and filler, matched as
|
||||
// whole tokens against the closed lexicon sets. Anything else is
|
||||
// confirmUnknown, which leaves the confirm parked and routes the turn — see
|
||||
// resolveConfirm. Both halves of that are the fix for V-567: this used to be a
|
||||
// substring test over bare stems, so "погода", "дальше", "надо" and "давление"
|
||||
// all read as "да", and "покажи" and "около" read as "ок". A parked destructive
|
||||
// act fired on a question about the weather.
|
||||
//
|
||||
// Requiring the WHOLE utterance is the second half. A leading confirm word does
|
||||
// not make a sentence an answer: "давай посмотрим погоду" opens a request, and
|
||||
// the only safe reading of a sentence that carries its own subject is that he
|
||||
// moved on. Guessing wrong here executes something; guessing wrong the other way
|
||||
// asks again.
|
||||
func classifyConfirm(text string) confirmVerdict {
|
||||
t := strings.ToLower(strings.TrimSpace(text))
|
||||
// negatives first — "не надо" contains no "да", but check no-stems before
|
||||
// yes so a leading "нет" isn't shadowed.
|
||||
for _, no := range []string{"нет", "не надо", "отмен", "стоп", "no", "cancel", "stop", "don't"} {
|
||||
if strings.Contains(t, no) {
|
||||
tokens := confirmTokens(text)
|
||||
if len(tokens) == 0 {
|
||||
return confirmUnknown
|
||||
}
|
||||
verdict := confirmUnknown
|
||||
for i := 0; i < len(tokens); {
|
||||
// Negatives first: "не надо" and "не хочу" open with a token that is
|
||||
// not itself an answer, and a yes hit must never shadow them.
|
||||
if n := matchConfirm(confirmNoPhrases, tokens[i:]); n > 0 {
|
||||
return confirmNo
|
||||
}
|
||||
if n := matchConfirm(confirmYesPhrases, tokens[i:]); n > 0 {
|
||||
verdict, i = confirmYes, i+n
|
||||
continue
|
||||
}
|
||||
if lexicon.IsFillerParticle(tokens[i]) {
|
||||
i++
|
||||
continue
|
||||
}
|
||||
// A word that is neither an answer nor filler carries a subject of its
|
||||
// own, so this utterance is not an answer to her question.
|
||||
return confirmUnknown
|
||||
}
|
||||
for _, yes := range []string{"да", "ага", "давай", "подтвер", "конечно", "yes", "yeah", "yep", "confirm", "ок", "okay", "ok"} {
|
||||
if strings.Contains(t, yes) {
|
||||
return confirmYes
|
||||
return verdict
|
||||
}
|
||||
|
||||
// matchConfirm reports the length of the longest phrase matching at the head of
|
||||
// tokens, or 0.
|
||||
func matchConfirm(phrases [][]string, tokens []string) int {
|
||||
for _, p := range phrases {
|
||||
if len(p) > len(tokens) {
|
||||
continue
|
||||
}
|
||||
if slices.Equal(p, tokens[:len(p)]) {
|
||||
return len(p)
|
||||
}
|
||||
}
|
||||
return confirmUnknown
|
||||
return 0
|
||||
}
|
||||
|
||||
// actPhrase renders "fn arg1 arg2" for the confirm prompt.
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
)
|
||||
|
||||
// TestClassifyConfirmRejectsSubstrings — V-567. The old matcher tested bare
|
||||
// stems with strings.Contains, so every word below answered a question she had
|
||||
// asked about something else: "погода", "дальше", "надо" and "давление" carry
|
||||
// "да"; "покажи", "около" and "окно" carry "ок". A parked destructive act fired
|
||||
// on a question about the weather.
|
||||
func TestClassifyConfirmRejectsSubstrings(t *testing.T) {
|
||||
for _, text := range []string{
|
||||
"погода",
|
||||
"какая погода",
|
||||
"что дальше",
|
||||
"надо ещё",
|
||||
"покажи заметки",
|
||||
"около окна",
|
||||
"давление",
|
||||
"давай посмотрим погоду",
|
||||
"не забудь купить хлеб",
|
||||
"окно открыто",
|
||||
"стоит ли брать зонт",
|
||||
"",
|
||||
} {
|
||||
if got := classifyConfirm(text); got != confirmUnknown {
|
||||
t.Errorf("classifyConfirm(%q) = %v, want confirmUnknown", text, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestClassifyConfirmAcceptsAnswers keeps every genuine answer the substring
|
||||
// matcher accepted, and pins the pair the fix could most easily get wrong:
|
||||
// "надо" is not an answer and "не надо" is the opposite of one.
|
||||
func TestClassifyConfirmAcceptsAnswers(t *testing.T) {
|
||||
yes := []string{"да", "Да!", "ага", "давай", "да, давай", "конечно", "подтверждаю", "ну да", "yes", "yeah", "ok", "okay", "confirm"}
|
||||
no := []string{"нет", "Нет.", "не надо", "не нужно", "не сейчас", "отмена", "отмени", "стоп", "нет, отмени", "no", "nope", "cancel", "stop", "don't"}
|
||||
|
||||
for _, text := range yes {
|
||||
if got := classifyConfirm(text); got != confirmYes {
|
||||
t.Errorf("classifyConfirm(%q) = %v, want confirmYes", text, got)
|
||||
}
|
||||
}
|
||||
for _, text := range no {
|
||||
if got := classifyConfirm(text); got != confirmNo {
|
||||
t.Errorf("classifyConfirm(%q) = %v, want confirmNo", text, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestUnrelatedTurnLeavesConfirmParked — the whole point of V-567. An utterance
|
||||
// that is not an answer must not execute the parked act, must not consume the
|
||||
// turn, and must not disarm the confirm either: the answer he has not given yet
|
||||
// is still answerable until it expires.
|
||||
func TestUnrelatedTurnLeavesConfirmParked(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
st := newTestStore(t)
|
||||
api := ipc.NewStoreAPI(st)
|
||||
now := time.Date(2026, 8, 6, 9, 0, 0, 0, time.UTC)
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
dataStore: st,
|
||||
now: func() time.Time { return now },
|
||||
tools: tool.NewExecutor(api, time.Second),
|
||||
}
|
||||
|
||||
marker := filepath.Join(t.TempDir(), "destructive-tool-ran")
|
||||
if err := st.EnableTool(ctx, "delete_backups", []string{"touch", marker}, true, "test", h.now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h.park("delete_backups", nil, "delete_backups")
|
||||
|
||||
if reply, handled := h.resolveConfirm(ctx, "какая погода"); handled {
|
||||
t.Fatalf("the weather question was consumed as a confirm: %q", reply)
|
||||
}
|
||||
if _, err := os.Stat(marker); !os.IsNotExist(err) {
|
||||
t.Fatalf("the parked destructive command ran on an unrelated turn: %v", err)
|
||||
}
|
||||
if h.pending == nil {
|
||||
t.Fatal("the confirm was disarmed by a turn that did not answer it")
|
||||
}
|
||||
|
||||
// It is still answerable, and answering it still runs the act.
|
||||
reply, handled := h.resolveConfirm(ctx, "да")
|
||||
if !handled || !strings.Contains(reply, "готово") {
|
||||
t.Fatalf("the still-parked confirm did not resolve: handled=%v reply=%q", handled, reply)
|
||||
}
|
||||
if _, err := os.Stat(marker); err != nil {
|
||||
t.Fatalf("confirmed destructive command did not run: %v", err)
|
||||
}
|
||||
if h.pending != nil {
|
||||
t.Fatal("the confirm stayed parked after being answered")
|
||||
}
|
||||
}
|
||||
@@ -173,6 +173,13 @@ func (a *crawlFetcher) Get(ctx context.Context, u string) (*crawl.Response, erro
|
||||
case errors.Is(err, webfetch.ErrBlocked), errors.Is(err, webfetch.ErrPrivate), errors.Is(err, webfetch.ErrScheme):
|
||||
return nil, fmt.Errorf("%w: %v", crawl.ErrFetchRefused, err)
|
||||
case errors.Is(err, webfetch.ErrStatus):
|
||||
// Carry the code across the seam. The crawler needs to tell a 5xx
|
||||
// from a 404 to decide what a failed robots.txt means, and it must
|
||||
// not learn that by reading this sentence.
|
||||
var se *webfetch.StatusError
|
||||
if errors.As(err, &se) {
|
||||
return nil, &crawl.StatusError{Code: se.Code}
|
||||
}
|
||||
return nil, fmt.Errorf("%w: %v", crawl.ErrFetchStatus, err)
|
||||
}
|
||||
return nil, err
|
||||
|
||||
@@ -4,12 +4,14 @@ import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/calendar"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/morning"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
@@ -111,6 +113,88 @@ func TestQueryDayPlanRestOfDayWhenNothingIsLeft(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// "что дальше?" rebuilds the plan off the wire and renders it here, and the
|
||||
// instants on it carry the zone the core read them in — a calendar fact's Ts
|
||||
// and a reminder's FireTs are UTC out of the store. Read raw, the recital named
|
||||
// the store's clock instead of his (V-614). The asking clock is three hours off
|
||||
// whatever this machine runs in, so the assertion holds under TZ=UTC too.
|
||||
func TestQueryDayPlanRestOfDayReadsHisClock(t *testing.T) {
|
||||
_, off := time.Now().Zone()
|
||||
away := time.FixedZone("away", off+3*60*60)
|
||||
stored := time.Date(2026, 8, 3, 8, 0, 0, 0, time.UTC)
|
||||
|
||||
h := &reactiveHandler{
|
||||
api: &planAPI{plan: ipc.DayPlan{
|
||||
Date: time.Date(2026, 8, 3, 0, 0, 0, 0, time.UTC),
|
||||
Items: []ipc.DayPlanItem{{At: stored, Text: "позвонить маме", Kind: "reminder"}},
|
||||
}},
|
||||
now: func() time.Time { return time.Date(2026, 8, 3, 9, 0, 0, 0, away) },
|
||||
}
|
||||
reply, ok := h.queryDayPlan(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что дальше?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("expected the plan source to claim it")
|
||||
}
|
||||
if want := stored.In(away).Format("15:04"); !strings.Contains(reply, want) {
|
||||
t.Errorf("the reminder is not read in his clock (%s): %q", want, reply)
|
||||
}
|
||||
if bad := stored.Format("15:04"); strings.Contains(reply, bad) {
|
||||
t.Errorf("the reminder is read in the store's zone (%s): %q", bad, reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The defect V-618 fixes, at the handler: asked at 04:45 the trim removes
|
||||
// nothing, because the whole day is still ahead. She read 43 entries aloud as
|
||||
// one sentence. The zone is three hours off UTC so the test also fails under
|
||||
// TZ=UTC if the rendering ever slips zones.
|
||||
func TestQueryDayPlanCapsWhatItReadsAloud(t *testing.T) {
|
||||
zone := time.FixedZone("MSK", 3*60*60)
|
||||
mid := time.Date(2026, 8, 3, 0, 0, 0, 0, zone)
|
||||
plan := ipc.DayPlan{Date: mid, Spoken: "план на 03.08.2026: …"}
|
||||
for i := 0; i < 43; i++ {
|
||||
plan.Items = append(plan.Items, ipc.DayPlanItem{
|
||||
At: mid.Add(time.Duration(345+i*20) * time.Minute), // 05:45 onward
|
||||
Text: fmt.Sprintf("пункт %d", i),
|
||||
Kind: "event",
|
||||
})
|
||||
}
|
||||
h := &reactiveHandler{api: &planAPI{plan: plan}, now: func() time.Time {
|
||||
return time.Date(2026, 8, 3, 4, 45, 0, 0, zone)
|
||||
}}
|
||||
reply, ok := h.queryDayPlan(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что дальше?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("expected the plan source to claim it")
|
||||
}
|
||||
if n := strings.Count(reply, "пункт "); n != morning.NextSpoken {
|
||||
t.Errorf("read %d entries aloud, want %d: %q", n, morning.NextSpoken, reply)
|
||||
}
|
||||
if !strings.HasPrefix(reply, "дальше: 05:45 — пункт 0;") {
|
||||
t.Errorf("the next thing is not first: %q", reply)
|
||||
}
|
||||
// The rest is counted, not silently dropped.
|
||||
if !strings.Contains(reply, "и ещё 40 дел до конца дня.") {
|
||||
t.Errorf("the sentence hides that the day goes on: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// "что у меня сегодня?" is the whole day and is not narrowed. It carries no
|
||||
// plan word, so the plan source declines it and the calendar listing answers —
|
||||
// asserted here beside the cap so the two questions cannot drift together.
|
||||
func TestWholeDayQuestionIsNotTheRestOfTheDay(t *testing.T) {
|
||||
if router.IsDayPlanQuery("что у меня сегодня?") {
|
||||
t.Error("the plan source claims the whole-day question")
|
||||
}
|
||||
if !router.IsDayPlanQuery("что дальше?") {
|
||||
t.Error("the plan source stopped claiming the rest-of-day question")
|
||||
}
|
||||
if router.IsRestOfDayQuery("какие планы на сегодня?") {
|
||||
t.Error("the whole-day plan question got narrowed to the rest of the day")
|
||||
}
|
||||
}
|
||||
|
||||
// A question that is not about the plan must fall through, or the plan buries
|
||||
// the calendar listing and the weather behind it.
|
||||
func TestQueryDayPlanPassesOnEverythingElse(t *testing.T) {
|
||||
|
||||
@@ -0,0 +1,133 @@
|
||||
// mavend/decisiontrace.go — the daemon's half of the per-turn decision record.
|
||||
//
|
||||
// V-564. The router says what the cascade did (internal/router/decisiontrace.go);
|
||||
// this file covers the two claimant sets that live in the daemon: the stateful
|
||||
// resolvers that run BEFORE routing and pre-empt it unconditionally, and the
|
||||
// query source chain that runs after. Those two are where the arbitration is
|
||||
// least visible, because both are a hardcoded order of functions that each
|
||||
// answer "is this mine?" alone and none of which answers "is this more mine
|
||||
// than yours?" (V-558).
|
||||
//
|
||||
// Recording changes no route. Every helper here is a no-op on a context with no
|
||||
// record, which is what every test that does not ask for one gets.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// preRouteLadder — the resolvers runTurn offers the utterance to before the
|
||||
// router sees it, in the order they get their say. Kept here as a roster rather
|
||||
// than derived from the code, so a resolver that returns early and skips the
|
||||
// rest still leaves the rest NAMED in the record: a claimant that never looked
|
||||
// and one that looked and passed are the distinction the ordering hides, and
|
||||
// they are the difference between a bug in the ladder and a bug in a resolver.
|
||||
//
|
||||
// Adding a step to runTurn means adding its name here. Nothing enforces that,
|
||||
// and nothing should: a missing name costs one line of the record, while a
|
||||
// check that walks the ladder would have to run the ladder.
|
||||
var preRouteLadder = []string{
|
||||
"confirm", "clarify-answer", "quiet-toggle", "snooze", "ack", "repair",
|
||||
"repair-negative", "ordinal",
|
||||
}
|
||||
|
||||
// notePreRoute records one rung of that ladder and passes its verdict through
|
||||
// unchanged, so the call site stays the single `if handled` it already was.
|
||||
func notePreRoute(ctx context.Context, name string, handled bool) bool {
|
||||
rec := decision.From(ctx)
|
||||
if rec == nil {
|
||||
return handled
|
||||
}
|
||||
if handled {
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StagePreRoute, Claimant: name, Outcome: decision.Won,
|
||||
Reason: "it pre-empted routing, so the router never saw this turn",
|
||||
})
|
||||
return handled
|
||||
}
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StagePreRoute, Claimant: name, Outcome: decision.Declined,
|
||||
Reason: "nothing of its own was pending",
|
||||
})
|
||||
return handled
|
||||
}
|
||||
|
||||
// noteTerminal records whoever actually produced the reply, but only if the
|
||||
// turn is still unclaimed. A route decides the intent; it does not answer, and
|
||||
// on a thinned route or a plain act nothing downstream keeps a scoreboard. So
|
||||
// the record would otherwise close with an empty winner, which reads as a lost
|
||||
// turn instead of an asked question.
|
||||
func noteTerminal(ctx context.Context, claimant string, intent router.Intent, reason string) {
|
||||
decision.From(ctx).NoteIfUnclaimed(decision.Claim{
|
||||
Stage: decision.StageAction, Claimant: claimant,
|
||||
Intent: string(intent), Reason: reason,
|
||||
})
|
||||
}
|
||||
|
||||
// noteMerge records the follow-up merge, which is the one claimant that edits
|
||||
// the winning decision instead of taking the turn from it. It is compared on
|
||||
// the four slots the merge can fill, because a Decision holds a slice and is
|
||||
// not comparable.
|
||||
func noteMerge(ctx context.Context, before, after router.Decision) {
|
||||
rec := decision.From(ctx)
|
||||
if rec == nil {
|
||||
return
|
||||
}
|
||||
changed := before.Slots.HasTime != after.Slots.HasTime ||
|
||||
before.Slots.HasKey != after.Slots.HasKey ||
|
||||
before.Slots.HasFn != after.Slots.HasFn ||
|
||||
before.Slots.Text != after.Slots.Text ||
|
||||
before.Intent != after.Intent
|
||||
if !changed {
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageMerge, Claimant: "follow-up-merge", Outcome: decision.Declined,
|
||||
Reason: "no slot of this turn was left for a previous one to fill",
|
||||
})
|
||||
return
|
||||
}
|
||||
rec.Note(decision.Claim{
|
||||
Stage: decision.StageMerge, Claimant: "follow-up-merge", Intent: string(after.Intent),
|
||||
Outcome: decision.Merged, Reason: "filled this turn's gaps from the previous turn",
|
||||
})
|
||||
}
|
||||
|
||||
// turnDecisionsFn — the reader mavweb gets, or nil when voice was never wired.
|
||||
// Same shape as intakeEventsFn: the daemon holds the ring, the IPC layer only
|
||||
// converts it.
|
||||
func turnDecisionsFn(w *voiceWiring) func(int) []ipc.TurnDecision {
|
||||
if w == nil || w.handler == nil || w.handler.decisions == nil {
|
||||
return nil
|
||||
}
|
||||
ring := w.handler.decisions
|
||||
return func(n int) []ipc.TurnDecision {
|
||||
recs := ring.Recent(n)
|
||||
out := make([]ipc.TurnDecision, 0, len(recs))
|
||||
for _, rec := range recs {
|
||||
claims := make([]ipc.TurnClaim, 0, len(rec.Claims))
|
||||
for _, c := range rec.Claims {
|
||||
claims = append(claims, ipc.TurnClaim{
|
||||
Stage: c.Stage, Claimant: c.Claimant, Intent: c.Intent,
|
||||
Score: c.Score, HasScore: c.HasScore,
|
||||
Outcome: c.Outcome, Reason: c.Reason,
|
||||
})
|
||||
}
|
||||
out = append(out, ipc.TurnDecision{
|
||||
Ts: rec.Ts, Utterance: rec.Utterance, Winner: rec.Winner, Claims: claims,
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
}
|
||||
|
||||
// querySourceNames — the query chain's roster, in chain order.
|
||||
func querySourceNames() []string {
|
||||
names := make([]string, len(querySources))
|
||||
for i, src := range querySources {
|
||||
names[i] = src.name
|
||||
}
|
||||
return names
|
||||
}
|
||||
@@ -0,0 +1,163 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
// traceHandler — a handler with the decision ring wired, the same shape the
|
||||
// daemon builds in wireVoice.
|
||||
func traceHandler(t *testing.T, ring *decision.Ring) *reactiveHandler {
|
||||
t.Helper()
|
||||
st := newTestStore(t)
|
||||
api := ipc.NewStoreAPI(st)
|
||||
now := time.Now()
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
return &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, tool.NewMatcher(api), 0.55, nil, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
decisions: ring,
|
||||
}
|
||||
}
|
||||
|
||||
// findClaim — the first claim for a claimant, or nil.
|
||||
func findClaim(rec *decision.Record, claimant string) *decision.Claim {
|
||||
for i := range rec.Claims {
|
||||
if rec.Claims[i].Claimant == claimant {
|
||||
return &rec.Claims[i]
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// TestTurnRecordNamesWinnerAndLosers — the point of V-564. A turn a stage-0
|
||||
// grammar claims must leave a record naming that grammar as the winner, naming
|
||||
// a pre-route resolver that declined, and naming the routing engines that were
|
||||
// never reached at all. The last of those is the fact the hardcoded ordering
|
||||
// hides: "classifier" absent from the record and "classifier" never asked read
|
||||
// the same to a human, and only one of them is the truth.
|
||||
func TestTurnRecordNamesWinnerAndLosers(t *testing.T) {
|
||||
ring := decision.NewRing()
|
||||
h := traceHandler(t, ring)
|
||||
|
||||
reply := h.handleText(context.Background(), "web", "сколько сейчас времени")
|
||||
if reply == "" {
|
||||
t.Fatal("turn produced no reply")
|
||||
}
|
||||
|
||||
recs := ring.Recent(5)
|
||||
if len(recs) != 1 {
|
||||
t.Fatalf("want 1 record, got %d", len(recs))
|
||||
}
|
||||
rec := recs[0]
|
||||
if rec.Utterance != "сколько сейчас времени" {
|
||||
t.Errorf("utterance = %q", rec.Utterance)
|
||||
}
|
||||
if !strings.HasPrefix(rec.Winner, "stage0:") {
|
||||
t.Errorf("want a stage-0 grammar as the winner, got %q", rec.Winner)
|
||||
}
|
||||
|
||||
// A loser that examined the turn: the confirm resolver ran first and had
|
||||
// nothing pending.
|
||||
confirm := findClaim(rec, "confirm")
|
||||
if confirm == nil || confirm.Outcome != decision.Declined {
|
||||
t.Errorf("confirm claim = %+v, want a decline", confirm)
|
||||
}
|
||||
|
||||
// A loser that never looked: stage 0 answered, so neither routing engine
|
||||
// was reached.
|
||||
for _, name := range []string{"llm-router", "classifier"} {
|
||||
c := findClaim(rec, name)
|
||||
if c != nil && c.Outcome == decision.Won {
|
||||
t.Errorf("%s cannot have won a stage-0 turn: %+v", name, c)
|
||||
}
|
||||
}
|
||||
|
||||
// And every rung of the ladder below the winner is named, not omitted.
|
||||
for _, name := range preRouteLadder {
|
||||
if findClaim(rec, name) == nil {
|
||||
t.Errorf("ladder rung %q is missing from the record", name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecordingDoesNotChangeTheReply — instrumentation, so a turn with the ring
|
||||
// wired and the same turn without it must answer identically. If this ever
|
||||
// fails, a claim site is doing more than noting.
|
||||
func TestRecordingDoesNotChangeTheReply(t *testing.T) {
|
||||
for _, utt := range []string{
|
||||
"сколько сейчас времени",
|
||||
"запиши что я пил воду",
|
||||
"что у меня сегодня",
|
||||
} {
|
||||
withRing := traceHandler(t, decision.NewRing()).handleText(context.Background(), "web", utt)
|
||||
without := traceHandler(t, nil).handleText(context.Background(), "web", utt)
|
||||
if withRing != without {
|
||||
t.Errorf("%q: recorded reply %q != unrecorded %q", utt, withRing, without)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestQueryChainRecordsWhoWasNeverAsked — a query source below the claimant is
|
||||
// never consulted, and the record must say so rather than leave it out. This is
|
||||
// the arm that would have explained the Rome misroute in one read.
|
||||
func TestQueryChainRecordsWhoWasNeverAsked(t *testing.T) {
|
||||
ring := decision.NewRing()
|
||||
h := traceHandler(t, ring)
|
||||
h.handleText(context.Background(), "web", "что у меня сегодня")
|
||||
|
||||
rec := ring.Recent(1)[0]
|
||||
var asked, never int
|
||||
for _, c := range rec.Claims {
|
||||
if c.Stage != decision.StageQuery {
|
||||
continue
|
||||
}
|
||||
if c.Outcome == decision.NeverAsked {
|
||||
never++
|
||||
} else {
|
||||
asked++
|
||||
}
|
||||
}
|
||||
if asked == 0 {
|
||||
t.Fatal("no query source reported at all")
|
||||
}
|
||||
if never == 0 {
|
||||
t.Fatal("no query source was recorded as never asked; the chain cannot have run to the end")
|
||||
}
|
||||
if got := len(querySourceNames()); asked+never != got {
|
||||
t.Errorf("record covers %d of %d query sources", asked+never, got)
|
||||
}
|
||||
}
|
||||
|
||||
// TestTurnDecisionsFnConvertsTheRing — the IPC read path. Nil when voice was
|
||||
// never wired, because a box with no turns is an empty page and not an error.
|
||||
func TestTurnDecisionsFnConvertsTheRing(t *testing.T) {
|
||||
if fn := turnDecisionsFn(nil); fn != nil {
|
||||
t.Error("no wiring should mean no reader")
|
||||
}
|
||||
ring := decision.NewRing()
|
||||
h := traceHandler(t, ring)
|
||||
h.handleText(context.Background(), "web", "сколько сейчас времени")
|
||||
|
||||
fn := turnDecisionsFn(&voiceWiring{handler: h})
|
||||
if fn == nil {
|
||||
t.Fatal("wired handler produced no reader")
|
||||
}
|
||||
out := fn(10)
|
||||
if len(out) != 1 || out[0].Winner == "" || len(out[0].Claims) == 0 {
|
||||
t.Fatalf("conversion lost the record: %+v", out)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,807 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"log"
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// Dialogue contract tests (V-563, child of V-558).
|
||||
//
|
||||
// Every other clarify test is single-shot: one ask, one answer, one assertion.
|
||||
// Three bugs of the same family shipped in two days that way — V-554 (a parked
|
||||
// question ate the three turns after it), V-557 (a confidently routed but
|
||||
// incomplete reminder parked nothing, so the answer was web-searched) and the
|
||||
// Rome case in V-558 (a side question was eaten as the time answer). None of
|
||||
// them is visible in one turn. The dialogue path is a state machine, so it can
|
||||
// be enumerated instead: whole traces, each with a per-turn expectation and an
|
||||
// expected END state — what was written to the store, and what is still parked.
|
||||
//
|
||||
// Two rules for the rows below.
|
||||
//
|
||||
// Where today's behaviour is correct, it is asserted. Where it is WRONG, the row
|
||||
// carries the CORRECT expectation and is skipped with the Vikunja id that will
|
||||
// unskip it. A weakened expectation would be worse than no row: it would pin the
|
||||
// bug as the contract.
|
||||
//
|
||||
// Everything runs on the offline floor — hash embedder, no llama-server, no
|
||||
// ONNX, StubDateTimeParser. That has one consequence worth knowing before
|
||||
// reading a fire time here: the stub reads "в 11:00" and "через час" and does
|
||||
// not read "на 9" or "на завтра", so a trace that needs those is noted where it
|
||||
// sits.
|
||||
|
||||
// claim — which claimant consumed an utterance. Not asserted: it is derived from
|
||||
// the log lines the daemon already emits and printed on every failure, because
|
||||
// "the reply differed" does not distinguish a wrong claimant from wrong copy,
|
||||
// and that distinction is the whole point of V-558.
|
||||
type claim struct {
|
||||
utterance string
|
||||
steps []string
|
||||
}
|
||||
|
||||
func (c claim) String() string { return c.utterance + " ⇒ " + strings.Join(c.steps, " → ") }
|
||||
|
||||
// claimMarkers — log fragment to claimant name, in the order runTurn checks
|
||||
// them. The fragments are the daemon's own words (clarify.go, repair.go,
|
||||
// voice.go); a rename there shows up here as an "unclaimed" step rather than a
|
||||
// silent mislabel.
|
||||
var claimMarkers = []struct{ fragment, name string }{
|
||||
{"parked question expired", "clarify:expired"},
|
||||
{"is its own request", "clarify:stepped-aside"},
|
||||
{"gave up on", "clarify:gave-up"},
|
||||
{"did not fill", "clarify:re-ask"},
|
||||
{"one gap filled", "clarify:ask-second-gap"},
|
||||
{"asked about", "clarify:ask"},
|
||||
{"repair —", "repair"},
|
||||
{"route result: intent=", "route"},
|
||||
}
|
||||
|
||||
// claimsOf reads the turn's log output and names the claimants that touched it.
|
||||
func claimsOf(utterance, logged string) claim {
|
||||
c := claim{utterance: utterance}
|
||||
for _, line := range strings.Split(logged, "\n") {
|
||||
for _, m := range claimMarkers {
|
||||
if strings.Contains(line, m.fragment) {
|
||||
name := m.name
|
||||
if m.name == "route" {
|
||||
name = "route:" + intentInLine(line)
|
||||
}
|
||||
c.steps = append(c.steps, name)
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(c.steps) == 0 {
|
||||
c.steps = []string{"unclaimed"}
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
func intentInLine(line string) string {
|
||||
_, rest, ok := strings.Cut(line, "intent=")
|
||||
if !ok {
|
||||
return "?"
|
||||
}
|
||||
intent, _, _ := strings.Cut(rest, " ")
|
||||
return intent
|
||||
}
|
||||
|
||||
// parkedWant — the question that must be armed after a turn. Attempt matters:
|
||||
// a claimant that spends a retry on an utterance that was never an answer is
|
||||
// exactly the V-554 shape, and the count is the only place it shows.
|
||||
type parkedWant struct {
|
||||
slot dialogue.Slot
|
||||
attempt int
|
||||
// carries — a substring the parked utterance must still hold, so a re-park
|
||||
// that lost the answered subject fails here rather than three turns later.
|
||||
carries string
|
||||
}
|
||||
|
||||
// turn — one utterance and everything that must be true right after it.
|
||||
type turn struct {
|
||||
say string
|
||||
// wait — the clock moves this far BEFORE the utterance. The only way to
|
||||
// reach the TTL without sleeping.
|
||||
wait time.Duration
|
||||
// question — the reply must be exactly this clarify question, worded for
|
||||
// this attempt. Zero slot ⇒ not checked.
|
||||
question dialogue.Slot
|
||||
attempt int
|
||||
// gap — which part of the time she is asking about, for a SlotTime question
|
||||
// (V-579). Zero value is the missing hour, which is what she asks first.
|
||||
gap whenGap
|
||||
// took — the words of the PREVIOUS turn that this ask must acknowledge
|
||||
// before asking again (V-593). Empty ⇒ the ask carries no acknowledgement,
|
||||
// which is right for a first ask and for an answer that moved nothing.
|
||||
took string
|
||||
// differs — this reply must not be byte-identical to the one before it. Set
|
||||
// on a re-ask whose turn moved the request forward (V-593).
|
||||
differs bool
|
||||
contains []string
|
||||
notContain []string
|
||||
// noQuestion — the reply must not be any clarify question. Used where the
|
||||
// correct behaviour is known but her wording for it is not written yet: a
|
||||
// cancel must not be answered with another question, whatever it does say.
|
||||
noQuestion bool
|
||||
expired bool // the reply must open with the TTL notice
|
||||
// parked — what is armed after the turn. nil ⇒ nothing may be armed.
|
||||
parked *parkedWant
|
||||
}
|
||||
|
||||
// endState — what the store holds once the trace is over. Counts and
|
||||
// substrings, not rows: a trace is about who claimed what, and a payload
|
||||
// substring is enough to catch a request landing under the wrong words.
|
||||
type endState struct {
|
||||
reminders []reminderWant
|
||||
factKeys []string
|
||||
notes int
|
||||
tasks []string
|
||||
}
|
||||
|
||||
type reminderWant struct {
|
||||
payload string // substring of the stored payload
|
||||
fireAt string // "2006-01-02 15:04" in UTC, "" ⇒ not checked
|
||||
}
|
||||
|
||||
// trace — a named conversation, its turns, and the end state.
|
||||
type trace struct {
|
||||
name string
|
||||
skip string // non-empty ⇒ t.Skip: today's behaviour is wrong, this names the fix
|
||||
turns []turn
|
||||
end endState
|
||||
}
|
||||
|
||||
// newDialogueHandler — the offline floor with the real cascade and a movable
|
||||
// clock: newClarifyHandler's wiring (stub date parser, real fact parser, tool
|
||||
// matcher) plus the router newRoutingClarifyHandler builds, and the `now`
|
||||
// pointer so a turn can carry a wait.
|
||||
func newDialogueHandler(t *testing.T) (*reactiveHandler, *store.Store, *time.Time) {
|
||||
t.Helper()
|
||||
h, st, now := newClarifyHandler(t)
|
||||
// A minute no trace ever says, so "fires at the current clock" is a defect
|
||||
// and never a coincidence (V-577, V-579). checkEnd refuses any reminder
|
||||
// landing on it, and at 09:00 the row that answers "на 9" would trip that.
|
||||
*now = time.Date(2026, 7, 31, 9, 17, 0, 0, time.UTC)
|
||||
h.router = buildRouter(router.NewHashEmbedder(1024), h.matcher, 0.55, nil, nil)
|
||||
h.recall = recallWiring{embedder: router.NewHashEmbedder(1024), memStore: memory.NewInMemoryStore()}
|
||||
return h, st, now
|
||||
}
|
||||
|
||||
// wantedQuestion builds the question a turn must be answered with, from the
|
||||
// same code the daemon asks through. A time question is built from the gap,
|
||||
// because she names the clock and asks about the part he left out (V-579).
|
||||
func wantedQuestion(tn turn, now time.Time) (string, bool) {
|
||||
if tn.question == dialogue.SlotTime {
|
||||
gap := tn.gap
|
||||
if gap == whenComplete {
|
||||
gap = whenNoHour
|
||||
}
|
||||
return whenQuestion(gap, tn.attempt, now, whenTakenLine(tn.took))
|
||||
}
|
||||
return clarifyQuestionFor(tn.question, tn.attempt)
|
||||
}
|
||||
|
||||
// runTrace drives one trace through handleText and checks every turn, then the
|
||||
// end state. Every failure carries the decision trace so far, so a wrong
|
||||
// claimant reads differently from wrong copy.
|
||||
func runTrace(t *testing.T, tr trace) {
|
||||
t.Helper()
|
||||
// MAVEN_DIALOGUE_NO_SKIP=1 runs the rows that fail today. That is how
|
||||
// whoever lands V-560, V-561 or V-562 sees their row go green before
|
||||
// deleting its skip, and it is also the check that a skip is still earned:
|
||||
// a row that passes with the skip in place is a fix nobody noticed.
|
||||
if tr.skip != "" && os.Getenv("MAVEN_DIALOGUE_NO_SKIP") == "" {
|
||||
t.Skip(tr.skip)
|
||||
}
|
||||
ctx := context.Background()
|
||||
h, st, now := newDialogueHandler(t)
|
||||
const conversation = "web"
|
||||
id := dialogueIDFor(sourceText, conversation)
|
||||
|
||||
var claims []claim
|
||||
var previous string
|
||||
fail := func(turnIdx int, format string, args ...any) {
|
||||
t.Helper()
|
||||
lines := make([]string, 0, len(claims))
|
||||
for _, c := range claims {
|
||||
lines = append(lines, " "+c.String())
|
||||
}
|
||||
t.Fatalf("turn %d: "+format+"\n who claimed what:\n%s",
|
||||
append([]any{turnIdx}, append(args, strings.Join(lines, "\n"))...)...)
|
||||
}
|
||||
|
||||
for i, tn := range tr.turns {
|
||||
if tn.wait > 0 {
|
||||
*now = now.Add(tn.wait)
|
||||
}
|
||||
var logged bytes.Buffer
|
||||
prev := log.Writer()
|
||||
log.SetOutput(&logged)
|
||||
reply := h.handleText(ctx, conversation, tn.say)
|
||||
log.SetOutput(prev)
|
||||
claims = append(claims, claimsOf(tn.say, logged.String()))
|
||||
|
||||
body := reply
|
||||
if tn.expired {
|
||||
if !isClarifyExpired(reply) {
|
||||
fail(i, "reply %q must open with the expiry notice", reply)
|
||||
}
|
||||
body = trimClarifyExpired(reply)
|
||||
// The notice is glued in front of this turn's reply, and both halves
|
||||
// have to survive: the words he just said are routed fresh, and
|
||||
// answering only "I let the old one go" drops them.
|
||||
if body == "" {
|
||||
fail(i, "the notice was the whole reply; the fresh words were never answered")
|
||||
}
|
||||
} else if isClarifyExpired(reply) {
|
||||
fail(i, "reply %q announced an expiry nothing asked for", reply)
|
||||
}
|
||||
if tn.question != "" {
|
||||
want, ok := wantedQuestion(tn, h.now())
|
||||
if !ok {
|
||||
fail(i, "no question exists for slot %s attempt %d", tn.question, tn.attempt)
|
||||
}
|
||||
if body != want {
|
||||
fail(i, "reply %q, want the %s question worded for attempt %d, %q", body, tn.question, tn.attempt, want)
|
||||
}
|
||||
}
|
||||
if tn.noQuestion && isAnyClarifyQuestion(body) {
|
||||
fail(i, "reply %q is another question; this turn is not something to ask about", body)
|
||||
}
|
||||
for _, want := range tn.contains {
|
||||
if !strings.Contains(body, want) {
|
||||
fail(i, "reply %q does not carry %q", body, want)
|
||||
}
|
||||
}
|
||||
for _, unwanted := range tn.notContain {
|
||||
if strings.Contains(body, unwanted) {
|
||||
fail(i, "reply %q carries %q and must not", body, unwanted)
|
||||
}
|
||||
}
|
||||
if tn.differs && reply == previous {
|
||||
fail(i, "reply %q is byte-identical to the one before it, and his turn between them answered part of the gap", reply)
|
||||
}
|
||||
previous = reply
|
||||
checkParked(t, fail, i, h.clarifyStore.Get(id, h.now()), tn.parked)
|
||||
}
|
||||
checkEnd(t, ctx, st, h, tr.end, claims)
|
||||
}
|
||||
|
||||
// isAnyClarifyQuestion — is this reply one of her clarify questions, at any
|
||||
// attempt wording? Reads the templates rather than a list of its own.
|
||||
func isAnyClarifyQuestion(reply string) bool {
|
||||
for _, variants := range clarifyQuestionVariants {
|
||||
for _, v := range variants {
|
||||
// HasSuffix, not equality: a question about the time opens with the
|
||||
// clock she is reasoning from (V-579).
|
||||
if strings.HasSuffix(reply, v) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
// The two questions with no deck behind them, asked when the hour is said
|
||||
// and its half of the day or its day is not.
|
||||
return strings.HasSuffix(reply, "утра или вечера?") || strings.HasSuffix(reply, "В какой день?")
|
||||
}
|
||||
|
||||
func checkParked(t *testing.T, fail func(int, string, ...any), i int, got *dialogue.PendingQuestion, want *parkedWant) {
|
||||
t.Helper()
|
||||
if want == nil {
|
||||
if got != nil {
|
||||
fail(i, "a question about %v is still armed and nothing should be: %+v", got.Missing, got.Slots)
|
||||
}
|
||||
return
|
||||
}
|
||||
if got == nil {
|
||||
fail(i, "nothing is armed, want a question about %s (attempt %d)", want.slot, want.attempt)
|
||||
return
|
||||
}
|
||||
if len(got.Missing) != 1 || got.Missing[0] != want.slot {
|
||||
fail(i, "armed question is about %v, want %s", got.Missing, want.slot)
|
||||
}
|
||||
if got.Attempts != want.attempt {
|
||||
fail(i, "armed question is on attempt %d, want %d — a retry spent on something that was never an answer is the V-554 shape", got.Attempts, want.attempt)
|
||||
}
|
||||
if want.carries != "" && !strings.Contains(got.Utterance, want.carries) {
|
||||
fail(i, "the parked request no longer carries %q: %q", want.carries, got.Utterance)
|
||||
}
|
||||
}
|
||||
|
||||
func checkEnd(t *testing.T, ctx context.Context, st *store.Store, h *reactiveHandler, want endState, claims []claim) {
|
||||
t.Helper()
|
||||
lines := make([]string, 0, len(claims))
|
||||
for _, c := range claims {
|
||||
lines = append(lines, " "+c.String())
|
||||
}
|
||||
trace := "\n who claimed what:\n" + strings.Join(lines, "\n")
|
||||
|
||||
reminders, err := st.DueReminders(ctx, h.now().Add(14*24*time.Hour))
|
||||
if err != nil {
|
||||
t.Fatalf("DueReminders: %v", err)
|
||||
}
|
||||
if len(reminders) != len(want.reminders) {
|
||||
t.Fatalf("end state: %d reminder(s), want %d: %+v%s", len(reminders), len(want.reminders), reminders, trace)
|
||||
}
|
||||
// No trace may leave a reminder at the current clock, whatever else it
|
||||
// asserts (V-577, V-579). Twice on the box a sentence naming a day and no
|
||||
// hour was completed from time.Now(): "что у меня сегодня?" became 01:28 and
|
||||
// "на завтра" became 01:38. Neither minute was ever spoken, and a row that
|
||||
// only checked the payload would have passed both.
|
||||
for _, r := range reminders {
|
||||
if r.FireTs.In(h.now().Location()).Format("15:04") == h.now().Format("15:04") {
|
||||
t.Fatalf("end state: reminder %q fires at %s, which is the clock — a time slot naming no hour is asked about, never filled from now()%s",
|
||||
r.Payload, r.FireTs.Format("15:04"), trace)
|
||||
}
|
||||
}
|
||||
for i, w := range want.reminders {
|
||||
if !strings.Contains(reminders[i].Payload, w.payload) {
|
||||
t.Fatalf("end state: reminder %d payload %q does not carry %q%s", i, reminders[i].Payload, w.payload, trace)
|
||||
}
|
||||
if w.fireAt != "" {
|
||||
if got := reminders[i].FireTs.UTC().Format("2006-01-02 15:04"); got != w.fireAt {
|
||||
t.Fatalf("end state: reminder %d fires at %s, want %s%s", i, got, w.fireAt, trace)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
facts, err := st.RecentFacts(ctx, 20)
|
||||
if err != nil {
|
||||
t.Fatalf("RecentFacts: %v", err)
|
||||
}
|
||||
if len(facts) != len(want.factKeys) {
|
||||
t.Fatalf("end state: %d fact(s), want %d: %+v%s", len(facts), len(want.factKeys), facts, trace)
|
||||
}
|
||||
for i, key := range want.factKeys {
|
||||
if facts[i].Key != key {
|
||||
t.Fatalf("end state: fact %d is %q, want %q%s", i, facts[i].Key, key, trace)
|
||||
}
|
||||
}
|
||||
|
||||
notes, err := st.RecentNotes(ctx, 20)
|
||||
if err != nil {
|
||||
t.Fatalf("RecentNotes: %v", err)
|
||||
}
|
||||
if len(notes) != want.notes {
|
||||
t.Fatalf("end state: %d note(s), want %d%s", len(notes), want.notes, trace)
|
||||
}
|
||||
|
||||
tasks, err := st.ListTasks(ctx, store.TaskOpen)
|
||||
if err != nil {
|
||||
t.Fatalf("ListTasks: %v", err)
|
||||
}
|
||||
if len(tasks) != len(want.tasks) {
|
||||
t.Fatalf("end state: %d open task(s), want %d: %+v%s", len(tasks), len(want.tasks), tasks, trace)
|
||||
}
|
||||
for i, text := range want.tasks {
|
||||
if !strings.Contains(tasks[i].Text, text) {
|
||||
t.Fatalf("end state: task %d is %q, want it to carry %q%s", i, tasks[i].Text, text, trace)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestDialogueTraces(t *testing.T) {
|
||||
for _, tr := range dialogueTraces() {
|
||||
tr := tr
|
||||
t.Run(tr.name, func(t *testing.T) { runTrace(t, tr) })
|
||||
}
|
||||
}
|
||||
|
||||
// dialogueTraces — the fixture. Order is the order the shapes were found, not a
|
||||
// dependency: each trace builds its own handler and store.
|
||||
func dialogueTraces() []trace {
|
||||
return []trace{
|
||||
// The plain two-turn shape, and the one every other row is a deviation
|
||||
// from: she asks for the time, he gives it, the reminder lands with the
|
||||
// subject he said in the FIRST turn.
|
||||
{
|
||||
// Three turns since V-579, not two. An hour with no day named is
|
||||
// not an answer she can act on: 11:00 today has passed as often as
|
||||
// not, and picking one for him is the invention the whole rule is
|
||||
// against. So she says the clock she is reasoning from and asks
|
||||
// which day.
|
||||
name: "reminder completed over three turns",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "маме"}},
|
||||
{say: "в 11:00", question: dialogue.SlotTime, attempt: 2, gap: whenNoDay, took: "в 11:00",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2, carries: "маме"}},
|
||||
{say: "сегодня", contains: []string{"11:00"}, notContain: []string{"?"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "позвонить маме", fireAt: "2026-07-31 11:00"}}},
|
||||
},
|
||||
// The same shape on the fact path, where the answer carries both halves
|
||||
// of what was missing — the key and the value — in one breath.
|
||||
{
|
||||
name: "fact completed over two turns",
|
||||
turns: []turn{
|
||||
{say: "запиши", question: dialogue.SlotKey, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotKey, attempt: 1}},
|
||||
// His words back, not the key the parser filed them under
|
||||
// (V-592). "water" is machine vocabulary and he never said it.
|
||||
{say: "пил воду", contains: []string{"пил воду"}},
|
||||
},
|
||||
end: endState{factKeys: []string{"water"}},
|
||||
},
|
||||
// An answer past the TTL is a new request, not an answer (V-385). She
|
||||
// says the old one is gone and routes the words fresh. A bare time on
|
||||
// its own carries no request, so the fresh routing lands on the canned
|
||||
// reply — the point of the row is that NOTHING is created: a reminder
|
||||
// here would fire with the subject of a request she had already let go.
|
||||
{
|
||||
name: "answer arrives after the TTL",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "в 11:00", wait: clarifyTTL + time.Second, expired: true},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// Three questions is the budget, and running out is SPOKEN: a mute
|
||||
// give-up reads as "done" and he would wait for a reminder that was
|
||||
// never set. The wording changes with the attempt (V-457).
|
||||
{
|
||||
name: "three unclear answers then the give-up line",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "ну не знаю", question: dialogue.SlotTime, attempt: 2,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2}},
|
||||
{say: "ну не знаю", question: dialogue.SlotTime, attempt: 3,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 3}},
|
||||
{say: "ну не знаю", contains: []string{clarifyGaveUp}, noQuestion: true},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// A correction points at the previous ACTED turn (repair.go): she redoes
|
||||
// it under the intent he names and says so out loud, because a
|
||||
// correction he cannot see is indistinguishable from one that was
|
||||
// dropped. The task she filed first stays filed — repair redoes, it does
|
||||
// not retract, and V-455 decided that deliberately.
|
||||
//
|
||||
// The corrected-to intent has to differ from the one she used, or repair
|
||||
// declines: teaching the classifier the label it already produced is
|
||||
// worse than doing nothing.
|
||||
{
|
||||
name: "correction of the previous turn",
|
||||
turns: []turn{
|
||||
{say: "добавь в задачи купить молоко", contains: []string{"купить молоко"}},
|
||||
{say: "нет, это был вопрос", contains: []string{"поняла, это вопрос"}},
|
||||
},
|
||||
end: endState{tasks: []string{"купить молоко"}},
|
||||
},
|
||||
// He walks away from his own request: a question is parked, the next
|
||||
// utterance is an unrelated request of its own, and nothing follows.
|
||||
// V-554's fix is what makes this row pass — the question steps aside
|
||||
// rather than scoring "добавь в задачи" as the time. The reminder is
|
||||
// dropped in silence and that is the decision: if he meant it he says it
|
||||
// again, and a question left armed eats the turn after next.
|
||||
{
|
||||
name: "abandoned flow: parked, then an unrelated request",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "добавь в задачи купить молоко", contains: []string{"купить молоко"}},
|
||||
{say: "спасибо"},
|
||||
},
|
||||
end: endState{tasks: []string{"купить молоко"}},
|
||||
},
|
||||
|
||||
// V-577 shape 1, the worst of the nine claimants measured on 2026-08-06.
|
||||
// Every token of "что у меня сегодня?" is frame — an interrogative, a
|
||||
// preposition, a particle and a day word — so the role classifier never
|
||||
// looked at the route, the parked reminder read "сегодня" as its time,
|
||||
// and the hour came from the clock. He got a reminder he never asked for
|
||||
// at a minute he never said, and his question was answered nowhere.
|
||||
//
|
||||
// Two claims: the calendar answers, and nothing is written. The flow
|
||||
// survives underneath, because a question of his own is not a request to
|
||||
// abandon the one he was making.
|
||||
{
|
||||
name: "an agenda question mid-flow is answered, not eaten",
|
||||
turns: []turn{
|
||||
{say: "напомни забрать посылку", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "посылку"}},
|
||||
{say: "что у меня сегодня?", contains: []string{"31.07.2026"},
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "посылку"}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// V-577 shape 2. He states something in the middle of the flow. It is
|
||||
// neither a slot value nor a cancel, and it was scored as a failed
|
||||
// answer and dropped in silence: alone the same sentence is stored.
|
||||
// Silence is the one option that is wrong, so it is stored, no retry is
|
||||
// spent, and the question comes back on the end of the same reply.
|
||||
//
|
||||
// The words are a fact and not the owner's note, because the fact parser
|
||||
// is deterministic and the offline floor marks every classifier route
|
||||
// Clarify. The row below carries his own sentence and needs the model.
|
||||
//
|
||||
// What this floor can prove is the arbitration: no retry is spent, the
|
||||
// flow survives on the same attempt, and the words are answered as
|
||||
// themselves with the question coming back after them. Whether the fact
|
||||
// is then WRITTEN is the routing engine's business — the hash embedder
|
||||
// is unsure of every sentence it sees, and an unsure fact has never been
|
||||
// stored.
|
||||
{
|
||||
name: "a fact stated mid-flow steps aside without spending a retry",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить врачу", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "врачу"}},
|
||||
// Nothing she says about it may be a word he did not say
|
||||
// (V-592). On the box this sentence came back as "Проверила, что
|
||||
// ты выпел стакан воды": a non-word for the verb, a glass copied
|
||||
// out of the example in ReplySystemPrompt, and a claim to have
|
||||
// checked something. The store held key=water value="drank"
|
||||
// throughout, so all of it was generated from two tokens.
|
||||
//
|
||||
// The positive half of the contract — the confirmation IS his
|
||||
// sentence — is asserted by "fact completed over two turns"
|
||||
// above. It cannot be asserted here: the hash embedder marks
|
||||
// this route Clarify, and an unsure fact is answered with the
|
||||
// canned line rather than a confirmation of anything.
|
||||
{say: "я выпил воды", contains: []string{"напоминание?"},
|
||||
notContain: []string{"стакан", "выпел", "Проверила", "water"},
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "врачу"}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// V-593: two asks about the same half of the day, with a turn between
|
||||
// them that answered the DAY. Asking again is right and asking in the
|
||||
// same bytes is not — from his side it is indistinguishable from not
|
||||
// having been heard, which is what the whole V-558 family is about.
|
||||
//
|
||||
// The clock still opens every ask (the owner's rule, V-579); the
|
||||
// acknowledgement goes after it and before the question.
|
||||
{
|
||||
name: "a re-ask names what the answer before it gave her",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "на 9", question: dialogue.SlotTime, attempt: 2, gap: whenAmbiguousHour, took: "на 9",
|
||||
contains: []string{"Сейчас "},
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2}},
|
||||
{say: "на завтра", question: dialogue.SlotTime, attempt: 3, gap: whenAmbiguousHour, took: "на завтра",
|
||||
contains: []string{"Сейчас ", "завтра"}, differs: true,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 3}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// V-579 turn 3: the preposition decided whether the hour was read. "в 9"
|
||||
// set the reminder and "на 9" was not read at all, on the same build and
|
||||
// with the same cardinal.
|
||||
{
|
||||
// It is read, and being read is not the same as being enough: nine is
|
||||
// either half of the day, so she asks which and then which day
|
||||
// (V-579). Both answers are frame words and neither carries an hour
|
||||
// of its own, so this row is also the proof that an answer is read
|
||||
// against the whole request rather than alone.
|
||||
name: "на 9 answers the time question like в 9",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "на 9", question: dialogue.SlotTime, attempt: 2, gap: whenAmbiguousHour, took: "на 9",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2}},
|
||||
{say: "утра", question: dialogue.SlotTime, attempt: 3, gap: whenNoDay, took: "утра",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 3}},
|
||||
{say: "завтра", contains: []string{"09:00"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "позвонить маме", fireAt: "2026-08-01 09:00"}}},
|
||||
},
|
||||
// The owner's own four, ruled 2026-08-06 (V-579). A reminder commits
|
||||
// when what, what time and what day are all answered, and every ask
|
||||
// states the clock she is reasoning from.
|
||||
{
|
||||
name: "his first example: a bare 3 is asked about",
|
||||
turns: []turn{
|
||||
{say: "напомни завтра в 3 заказать цветы",
|
||||
question: dialogue.SlotTime, attempt: 1, gap: whenAmbiguousHour,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "цветы"}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
{
|
||||
// The hour is unambiguous and the day is still missing, so she asks.
|
||||
// Today being a valid reading is not the same as him saying it.
|
||||
name: "his second example: nine in the evening of which day",
|
||||
turns: []turn{
|
||||
{say: "напомни в 9 вечера разгрузить стиралку",
|
||||
question: dialogue.SlotTime, attempt: 1, gap: whenNoDay,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "стиралку"}},
|
||||
{say: "завтра", contains: []string{"21:00"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "стиралку", fireAt: "2026-08-01 21:00"}}},
|
||||
},
|
||||
{
|
||||
// All three answered in one breath, so she does not ask at all.
|
||||
name: "his third example: a full time commits",
|
||||
turns: []turn{
|
||||
{say: "напомни завтра в 15:00 заказать цветы", notContain: []string{"?"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "цветы", fireAt: "2026-08-01 15:00"}}},
|
||||
},
|
||||
{
|
||||
// An interval is one instant, so it answers the hour and the day
|
||||
// together. Confirmed by the owner: "через час is fine as is".
|
||||
name: "an interval commits without a question",
|
||||
turns: []turn{
|
||||
{say: "напомни через час позвонить маме", notContain: []string{"?"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "маме", fireAt: "2026-07-31 10:17"}}},
|
||||
},
|
||||
// V-579 turn 4: he named a day and no hour, and got the day at the
|
||||
// current minute. She has to ask instead, and the global check in
|
||||
// checkEnd refuses the invented minute for every row at once.
|
||||
{
|
||||
name: "a day with no hour is asked about, not taken from the clock",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "на завтра", question: dialogue.SlotTime, attempt: 2,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
|
||||
// ---- rows below carry the CORRECT expectation and fail today ----
|
||||
|
||||
// The owner's own sentence from V-577 shape 2, in his words. It needs
|
||||
// an engine that can route it: the hash embedder marks it note with
|
||||
// Clarify set, and a route she is not sure of is not evidence that he
|
||||
// stated anything. The row above is the same contract in words the
|
||||
// floor's deterministic fact parser reads.
|
||||
{
|
||||
name: "a note stated mid-flow is stored, not dropped",
|
||||
skip: "the offline floor cannot route «у меня новый ноутбук» confidently; needs the resident model",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить врачу", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "врачу"}},
|
||||
{say: "у меня новый ноутбук",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "врачу"}},
|
||||
},
|
||||
end: endState{notes: 1},
|
||||
},
|
||||
|
||||
// The owner's target transcript, V-561. He asks for a reminder, she asks
|
||||
// when, he asks something else entirely, and then comes back to her
|
||||
// question. On the box this created a reminder at 00:12 and never
|
||||
// answered Rome; on the offline floor the side question is recognised as
|
||||
// its own request and the flow is dropped instead, so the wrong reminder
|
||||
// is not made and the right one is not either.
|
||||
//
|
||||
// Both are the same defect: there is no suspend and resume. The correct
|
||||
// shape is the middle turn answered on its own and the parked question
|
||||
// still standing, on the same attempt — a side query is not a failed
|
||||
// answer and must not spend a retry.
|
||||
//
|
||||
// The skip came off with V-579. What held it was the parser, not the
|
||||
// arbitration: neither the stub nor the production one read "на 9",
|
||||
// because only "в" framed a spoken hour, and "на завтра" was completed
|
||||
// from the clock.
|
||||
//
|
||||
// Turn 3 now closes the flow, where the transcript has one more exchange
|
||||
// in it. That is the 12-hour question — the owner's turn 4 answers "на
|
||||
// 9" with "сейчас 15:23, на 9 сегодня вечером?" — and it is a decision of
|
||||
// its own, not one to invent here. Nine o'clock is read as nine and, at
|
||||
// 09:17, as tomorrow's, which is where the transcript ends up anyway.
|
||||
// Turn 4 then has nothing to answer and must not write anything.
|
||||
{
|
||||
name: "the owner's transcript from V-561",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "какая сейчас погода в Риме?",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "маме"}},
|
||||
// His words, unchanged. What changed under V-579 is that "на 9"
|
||||
// is a question and not a commit: nine could be either half of
|
||||
// the day, so she says the clock she is reading from and asks.
|
||||
// "на завтра." then answers the day and leaves the half open, so
|
||||
// she asks that one again.
|
||||
// Each ask names what the turn before it gave her (V-593). The
|
||||
// two asks about the half of the day are the same question and
|
||||
// must not be the same sentence: he answered between them, and a
|
||||
// reply with no trace of that reads as not having been heard.
|
||||
{say: "а, да, прости - на 9.", question: dialogue.SlotTime, attempt: 2, gap: whenAmbiguousHour, took: "а, да, прости - на 9.",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2}},
|
||||
{say: "на завтра.", question: dialogue.SlotTime, attempt: 3, gap: whenAmbiguousHour, took: "на завтра.",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 3}},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// The same shape said in words StubDateTimeParser reads. GREEN since
|
||||
// V-561. Same three claims: Rome is answered, the question survives the
|
||||
// side query on the same attempt, and the answer after it completes the
|
||||
// reminder he actually asked for.
|
||||
//
|
||||
// It sits under the "fail today" header because the row above it still
|
||||
// does. Do not re-skip it to tidy that up: this is the owner's
|
||||
// acceptance test in the only words the offline floor can read.
|
||||
{
|
||||
name: "nested question: a parked question, then one of his own",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "какая сейчас погода в Риме?",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "маме"}},
|
||||
{say: "в 11:00", question: dialogue.SlotTime, attempt: 2, gap: whenNoDay, took: "в 11:00",
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 2, carries: "маме"}},
|
||||
{say: "сегодня", contains: []string{"11:00"}},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "позвонить маме", fireAt: "2026-07-31 11:00"}}},
|
||||
},
|
||||
// A cancel is one of the five turn roles V-560 names, and today it is
|
||||
// none of them: "неважно" fills no slot and carries no request of its
|
||||
// own, so it reads as a failed answer and spends a retry. Two turns
|
||||
// later she is still asking about a reminder he called off.
|
||||
//
|
||||
// The row asserts what is knowable — nothing armed, nothing written, and
|
||||
// not another question — rather than her wording for it, which is not
|
||||
// written yet and is not this task's to invent.
|
||||
{
|
||||
name: "cancel: a parked question, then never mind",
|
||||
skip: "V-560: a cancel is scored as a failed answer, not as a cancel",
|
||||
turns: []turn{
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "неважно", noQuestion: true},
|
||||
},
|
||||
end: endState{},
|
||||
},
|
||||
// Order in runTurn is the whole arbitration (V-558), and this is what it
|
||||
// costs: the clarify answer is checked at step 3 and the repair marker at
|
||||
// step 4d, so while a question is parked no correction can be made. She
|
||||
// scores "нет, это была заметка" as a bad time answer and asks again.
|
||||
{
|
||||
name: "correction while a question is parked",
|
||||
skip: "V-560: clarify pre-empts the repair marker, so a correction cannot be spoken mid-flow",
|
||||
turns: []turn{
|
||||
{say: "добавь в задачи купить молоко", contains: []string{"купить молоко"}},
|
||||
{say: "напомни позвонить маме", question: dialogue.SlotTime, attempt: 1,
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
{say: "нет, это был вопрос", contains: []string{"поняла, это вопрос"},
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1, carries: "маме"}},
|
||||
},
|
||||
end: endState{tasks: []string{"купить молоко"}},
|
||||
},
|
||||
// A reminder said whole, in one breath, with the hour in it — and she
|
||||
// asks when. ReminderGrammar (stage0.go) builds its slots by hand and
|
||||
// never runs the extractor, so a stage-0 reminder carries no time
|
||||
// whatever the sentence says, and the clarify gate reads the gap as
|
||||
// real. It costs a turn on the commonest reminder shape there is.
|
||||
//
|
||||
// Hermetic despite the date parser: stage 0 calls no parser at all, so
|
||||
// this fails the same way with or without python dateparser installed.
|
||||
{
|
||||
name: "a reminder said whole is not asked about",
|
||||
skip: "V-562: a stage-0 decision never meets the extractor, so its slots are never validated",
|
||||
turns: []turn{
|
||||
{say: "напомни в 11:00 позвонить маме", contains: []string{"11:00"}, noQuestion: true},
|
||||
},
|
||||
end: endState{reminders: []reminderWant{{payload: "позвонить маме", fireAt: "2026-07-31 11:00"}}},
|
||||
},
|
||||
// The same gap on the repair path. A correction redoes the request
|
||||
// through finishClarified, which goes straight to applyAction — it never
|
||||
// passes the clarify gate — so a redo that lands short answers with the
|
||||
// parse error V-557 removed from the routing path: "не поняла, на когда
|
||||
// напомнить." She should ask, exactly as she does for a fresh reminder
|
||||
// with no time.
|
||||
{
|
||||
name: "a correction that lands short asks rather than failing",
|
||||
skip: "V-562: finishClarified skips the clarify gate, so a repaired decision is never checked for gaps",
|
||||
turns: []turn{
|
||||
{say: "добавь в задачи купить молоко", contains: []string{"купить молоко"}},
|
||||
{say: "нет, это было напоминание", contains: []string{"поняла, это напоминание"},
|
||||
parked: &parkedWant{slot: dialogue.SlotTime, attempt: 1}},
|
||||
},
|
||||
end: endState{tasks: []string{"купить молоко"}},
|
||||
},
|
||||
}
|
||||
}
|
||||
+151
-108
@@ -12,6 +12,7 @@ import (
|
||||
"log"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
hexisclient "github.com/kami/hexis/pkg/client"
|
||||
@@ -42,28 +43,100 @@ const ecosystemAPIVersion = "v1"
|
||||
// anonymous HTTP client.
|
||||
const mavenRequester = "maven"
|
||||
|
||||
// setEcosystemHeaders stamps the version, requester, auth and correlation
|
||||
// headers common to every outgoing ecosystem request. token may be empty,
|
||||
// which means the transport itself is trusted (loopback or unix socket).
|
||||
// ecosystemHTTP is the JSON transport every ecosystem client shares: one base
|
||||
// URL, one bearer token, and the header set the contract requires on each
|
||||
// request. Nexus and Praxis differ only in the service name and the version
|
||||
// header, so both embed this rather than repeating build, send and classify.
|
||||
type ecosystemHTTP struct {
|
||||
service string // "nexus", "praxis" — the name errors and traces carry
|
||||
versionHeader string
|
||||
baseURL string
|
||||
token string
|
||||
httpClient *http.Client
|
||||
}
|
||||
|
||||
func newEcosystemHTTP(service, versionHeader, baseURL string) ecosystemHTTP {
|
||||
return ecosystemHTTP{
|
||||
service: service,
|
||||
versionHeader: versionHeader,
|
||||
baseURL: baseURL,
|
||||
httpClient: &http.Client{Timeout: 10 * time.Second},
|
||||
}
|
||||
}
|
||||
|
||||
// setHeaders stamps the version, requester, auth and correlation headers common
|
||||
// to every outgoing ecosystem request. The token may be empty, which means the
|
||||
// transport itself is trusted (loopback or unix socket).
|
||||
//
|
||||
// The correlation ID is read from the context and never minted here. Minting
|
||||
// one per request sent the far side an ID that existed nowhere on this side,
|
||||
// and gave a single multi-hop action as many unrelated IDs as it made calls.
|
||||
// Callers that start an action assign the ID once (handleHexisAct,
|
||||
// The correlation ID is read from the request's own context and never minted
|
||||
// here. Minting one per request sent the far side an ID that existed nowhere on
|
||||
// this side, and gave a single multi-hop action as many unrelated IDs as it
|
||||
// made calls. Callers that start an action assign the ID once (handleHexisAct,
|
||||
// handlePraxisAct, resolveEntityReference) and every hop inherits it.
|
||||
func setEcosystemHeaders(req *http.Request, ctx context.Context, versionHeader, token string) {
|
||||
func (t *ecosystemHTTP) setHeaders(req *http.Request) {
|
||||
req.Header.Set("Content-Type", "application/json")
|
||||
req.Header.Set(versionHeader, ecosystemAPIVersion)
|
||||
req.Header.Set(t.versionHeader, ecosystemAPIVersion)
|
||||
req.Header.Set("Accept", "application/json")
|
||||
req.Header.Set("X-Requested-By", mavenRequester)
|
||||
if token != "" {
|
||||
req.Header.Set("Authorization", "Bearer "+token)
|
||||
if t.token != "" {
|
||||
req.Header.Set("Authorization", "Bearer "+t.token)
|
||||
}
|
||||
if id := correlationIDFromCtx(ctx); id != "" {
|
||||
if id := correlationIDFromCtx(req.Context()); id != "" {
|
||||
req.Header.Set("X-Correlation-ID", id)
|
||||
}
|
||||
}
|
||||
|
||||
// call sends one request and decodes the JSON answer into out, which may be nil
|
||||
// when the body carries nothing worth reading. op is the logical operation name
|
||||
// for errors and traces: the path carries the query string, and after entity
|
||||
// scoping that means an entity id in every log line built from the error, next
|
||||
// to a trace that redacts far less than that.
|
||||
//
|
||||
// Every failure is an *ecosystemError, including the transport and decode ones.
|
||||
// Some of these paths mutate remote state, and the question worth answering
|
||||
// afterwards is whether the call never left or was refused.
|
||||
func (t *ecosystemHTTP) call(ctx context.Context, method, op, path string, payload, out any) error {
|
||||
var body io.Reader
|
||||
if payload != nil {
|
||||
data, err := json.Marshal(payload)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: t.service, Op: op, Err: err}
|
||||
}
|
||||
body = bytes.NewReader(data)
|
||||
}
|
||||
req, err := http.NewRequestWithContext(ctx, method, t.baseURL+path, body)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: t.service, Op: op, Err: err}
|
||||
}
|
||||
t.setHeaders(req)
|
||||
|
||||
resp, err := t.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: t.service, Op: op, Err: err}
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
if resp.StatusCode != 200 {
|
||||
return httpError(t.service, op, resp.StatusCode)
|
||||
}
|
||||
if out == nil {
|
||||
return nil
|
||||
}
|
||||
if err := json.NewDecoder(resp.Body).Decode(out); err != nil {
|
||||
return &ecosystemError{Service: t.service, Op: op, Status: resp.StatusCode, Err: err}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// getJSON performs a GET and decodes the JSON body into out.
|
||||
func (t *ecosystemHTTP) getJSON(ctx context.Context, op, path string, out any) error {
|
||||
return t.call(ctx, http.MethodGet, op, path, nil, out)
|
||||
}
|
||||
|
||||
// postJSON posts a JSON payload and decodes the JSON answer into out.
|
||||
func (t *ecosystemHTTP) postJSON(ctx context.Context, op, path string, payload, out any) error {
|
||||
return t.call(ctx, http.MethodPost, op, path, payload, out)
|
||||
}
|
||||
|
||||
// ecosystemError is the typed failure every ecosystem client returns, so
|
||||
// callers can tell a transport failure from a refusal from a contract
|
||||
// mismatch without matching on message text. The distinction matters:
|
||||
@@ -107,17 +180,60 @@ func httpError(service, op string, status int) *ecosystemError {
|
||||
}
|
||||
}
|
||||
|
||||
// hexisStatusTexts maps the http.StatusText spelling back to its code, for the
|
||||
// failure statuses a Hexis call can plausibly answer with. It is the inverse of
|
||||
// what the vendored client threw away.
|
||||
var hexisStatusTexts = func() map[string]int {
|
||||
codes := []int{
|
||||
http.StatusBadRequest, http.StatusUnauthorized, http.StatusForbidden,
|
||||
http.StatusNotFound, http.StatusMethodNotAllowed, http.StatusNotAcceptable,
|
||||
http.StatusRequestTimeout, http.StatusConflict, http.StatusGone,
|
||||
http.StatusUnprocessableEntity, http.StatusUpgradeRequired,
|
||||
http.StatusTooManyRequests, http.StatusInternalServerError,
|
||||
http.StatusNotImplemented, http.StatusBadGateway,
|
||||
http.StatusServiceUnavailable, http.StatusGatewayTimeout,
|
||||
}
|
||||
m := make(map[string]int, len(codes))
|
||||
for _, c := range codes {
|
||||
m[http.StatusText(c)] = c
|
||||
}
|
||||
return m
|
||||
}()
|
||||
|
||||
// hexisError re-wraps an error from the vendored Hexis client as an
|
||||
// *ecosystemError, so a Hexis failure classifies the same way a Nexus or Praxis
|
||||
// one does and ecosystemGap can tell a refused credential from an outage.
|
||||
//
|
||||
// This is a boundary adapter and it is not the fix anyone would choose. The
|
||||
// Hexis client lives in another repository and returns
|
||||
// fmt.Errorf("%s: %s", http.StatusText(status), body) for every status at or
|
||||
// above 400, so the status text is the only signal that survives — the correct
|
||||
// fix is a typed error carrying the code, and Maven cannot land it unilaterally
|
||||
// (Vikunja #587, docs/plans/20-two-artifacts-and-neither-is-spring.md). Parsing
|
||||
// here is bounded: the message's first colon-delimited segment is the status
|
||||
// text verbatim, no status text contains a colon, and anything unrecognised —
|
||||
// "do request: ...", "create request: ..." — is a transport failure and is left
|
||||
// at status 0, which is exactly what Unreachable() means.
|
||||
func hexisError(op string, err error) error {
|
||||
if err == nil {
|
||||
return nil
|
||||
}
|
||||
var ee *ecosystemError
|
||||
if errors.As(err, &ee) {
|
||||
return err
|
||||
}
|
||||
head, _, _ := strings.Cut(err.Error(), ": ")
|
||||
return &ecosystemError{
|
||||
Service: "hexis", Op: op, Status: hexisStatusTexts[head], Err: err,
|
||||
}
|
||||
}
|
||||
|
||||
type nexusClient struct {
|
||||
baseURL string
|
||||
token string
|
||||
httpClient *http.Client
|
||||
ecosystemHTTP
|
||||
}
|
||||
|
||||
func newNexusClient(url string) *nexusClient {
|
||||
return &nexusClient{
|
||||
baseURL: url,
|
||||
httpClient: &http.Client{Timeout: 10 * time.Second},
|
||||
}
|
||||
return &nexusClient{newEcosystemHTTP("nexus", "X-Nexus-Version", url)}
|
||||
}
|
||||
|
||||
// withToken sets the bearer token sent on every request. Returns the client so
|
||||
@@ -176,62 +292,26 @@ func (c *nexusClient) Resolve(ctx context.Context, query string, types []string)
|
||||
body["types"] = types
|
||||
}
|
||||
|
||||
data, _ := json.Marshal(body)
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.baseURL+"/api/v1/resolve", bytes.NewReader(data))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("create request: %w", err)
|
||||
}
|
||||
setEcosystemHeaders(req, ctx, "X-Nexus-Version", c.token)
|
||||
|
||||
resp, err := c.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return nil, &ecosystemError{Service: "nexus", Op: "resolve", Err: err}
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
bodyBytes, _ := io.ReadAll(resp.Body)
|
||||
if resp.StatusCode != 200 {
|
||||
return nil, httpError("nexus", "resolve", resp.StatusCode)
|
||||
}
|
||||
|
||||
var result nexusResolveResult
|
||||
if err := json.Unmarshal(bodyBytes, &result); err != nil {
|
||||
return nil, &ecosystemError{Service: "nexus", Op: "resolve", Status: resp.StatusCode, Err: err}
|
||||
if err := c.postJSON(ctx, "resolve", "/api/v1/resolve", body, &result); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &result, nil
|
||||
}
|
||||
|
||||
func (c *nexusClient) Health(ctx context.Context) error {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+"/health", nil)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: "nexus", Op: "health", Err: err}
|
||||
}
|
||||
setEcosystemHeaders(req, ctx, "X-Nexus-Version", c.token)
|
||||
resp, err := c.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: "nexus", Op: "health", Err: err}
|
||||
}
|
||||
resp.Body.Close()
|
||||
if resp.StatusCode != 200 {
|
||||
return httpError("nexus", "health", resp.StatusCode)
|
||||
}
|
||||
return nil
|
||||
return c.getJSON(ctx, "health", "/health", nil)
|
||||
}
|
||||
|
||||
// praxisClient talks to the Praxis HTTP tools API. Maven must not open Praxis's
|
||||
// SQLite store directly (ecosystem invariant: no component reads another's DB),
|
||||
// so attention/changes/lifecycle all go over this HTTP contract against praxisd.
|
||||
type praxisClient struct {
|
||||
baseURL string
|
||||
token string
|
||||
httpClient *http.Client
|
||||
ecosystemHTTP
|
||||
}
|
||||
|
||||
func newPraxisClient(url string) *praxisClient {
|
||||
return &praxisClient{
|
||||
baseURL: url,
|
||||
httpClient: &http.Client{Timeout: 10 * time.Second},
|
||||
}
|
||||
return &praxisClient{newEcosystemHTTP("praxis", "X-Praxis-Version", url)}
|
||||
}
|
||||
|
||||
func (c *praxisClient) withToken(token string) *praxisClient {
|
||||
@@ -239,30 +319,6 @@ func (c *praxisClient) withToken(token string) *praxisClient {
|
||||
return c
|
||||
}
|
||||
|
||||
// getJSON performs a GET and decodes the JSON body into out. op is the logical
|
||||
// operation name for errors and traces: the path carries the query string, and
|
||||
// after entity scoping that means an entity id in every log line built from the
|
||||
// error, next to a trace that redacts far less than that.
|
||||
func (c *praxisClient) getJSON(ctx context.Context, op, path string, out any) error {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+path, nil)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
setEcosystemHeaders(req, ctx, "X-Praxis-Version", c.token)
|
||||
resp, err := c.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return &ecosystemError{Service: "praxis", Op: op, Err: err}
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
if resp.StatusCode != 200 {
|
||||
return httpError("praxis", op, resp.StatusCode)
|
||||
}
|
||||
if err := json.NewDecoder(resp.Body).Decode(out); err != nil {
|
||||
return &ecosystemError{Service: "praxis", Op: op, Status: resp.StatusCode, Err: err}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// praxisAttention — an attention response in either of the two shapes Praxis
|
||||
// may send (Vikunja #540).
|
||||
//
|
||||
@@ -376,31 +432,14 @@ type praxisItem struct {
|
||||
// postItemAction posts {"item_id": id} to a Praxis tools lifecycle endpoint
|
||||
// and decodes the resulting item. Shared by Surface/Acknowledge/Resolve/Ignore.
|
||||
func (c *praxisClient) postItemAction(ctx context.Context, op, path, itemID string) (*praxisItem, error) {
|
||||
return c.postJSON(ctx, op, path, map[string]any{"item_id": itemID})
|
||||
return c.postItem(ctx, op, path, map[string]any{"item_id": itemID})
|
||||
}
|
||||
|
||||
// postJSON posts a body to a Praxis lifecycle endpoint and decodes the item.
|
||||
// Every failure is a *ecosystemError, including the transport and decode ones:
|
||||
// these are the paths that mutate remote state, and the question worth
|
||||
// answering afterwards is whether the call never left or was refused.
|
||||
func (c *praxisClient) postJSON(ctx context.Context, op, path string, payload map[string]any) (*praxisItem, error) {
|
||||
body, _ := json.Marshal(payload)
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.baseURL+path, bytes.NewReader(body))
|
||||
if err != nil {
|
||||
return nil, &ecosystemError{Service: "praxis", Op: op, Err: err}
|
||||
}
|
||||
setEcosystemHeaders(req, ctx, "X-Praxis-Version", c.token)
|
||||
resp, err := c.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return nil, &ecosystemError{Service: "praxis", Op: op, Err: err}
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
if resp.StatusCode != 200 {
|
||||
return nil, httpError("praxis", op, resp.StatusCode)
|
||||
}
|
||||
// postItem posts a body to a Praxis lifecycle endpoint and decodes the item.
|
||||
func (c *praxisClient) postItem(ctx context.Context, op, path string, payload map[string]any) (*praxisItem, error) {
|
||||
var out praxisItem
|
||||
if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
|
||||
return nil, &ecosystemError{Service: "praxis", Op: op, Status: resp.StatusCode, Err: err}
|
||||
if err := c.postJSON(ctx, op, path, payload, &out); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &out, nil
|
||||
}
|
||||
@@ -425,7 +464,7 @@ func (c *praxisClient) Ignore(ctx context.Context, itemID string) (*praxisItem,
|
||||
}
|
||||
|
||||
func (c *praxisClient) Pin(ctx context.Context, itemID string, pinned bool) (*praxisItem, error) {
|
||||
return c.postJSON(ctx, "pin", "/api/v1/tools/pin", map[string]any{"item_id": itemID, "pinned": pinned})
|
||||
return c.postItem(ctx, "pin", "/api/v1/tools/pin", map[string]any{"item_id": itemID, "pinned": pinned})
|
||||
}
|
||||
|
||||
func (c *praxisClient) GetItem(ctx context.Context, itemID string) (*praxisItem, error) {
|
||||
@@ -540,6 +579,7 @@ func (w *ecosystemWiring) discoverCapabilities(ctx context.Context, entityID str
|
||||
}
|
||||
caps, err := w.hexis.Capabilities(ctx, entityID)
|
||||
if err != nil {
|
||||
err = hexisError("capabilities", err)
|
||||
log.Printf("ecosystem: hexis capabilities error: %v", err)
|
||||
return nil, err
|
||||
}
|
||||
@@ -567,7 +607,10 @@ func (w *ecosystemWiring) executeCapability(ctx context.Context, capabilityID, t
|
||||
|
||||
exec, err := w.hexis.Execute(ctx, req)
|
||||
if err != nil {
|
||||
return correlationID, fmt.Errorf("execute: %w", err)
|
||||
// A classified dependency failure. The two returns below are NOT: an
|
||||
// execution that ran and failed is the command failing, not Hexis
|
||||
// degrading, and it keeps its plain error so the caller says so.
|
||||
return correlationID, hexisError("execute", err)
|
||||
}
|
||||
if exec.Status == "succeeded" {
|
||||
return correlationID, nil
|
||||
|
||||
@@ -22,13 +22,25 @@ import (
|
||||
// already knows which one it was talking to — it records the same name in the
|
||||
// trace (Vikunja #521).
|
||||
const (
|
||||
serviceNexus = "Nexus"
|
||||
serviceHexis = "Hexis"
|
||||
serviceNexus = "Nexus"
|
||||
servicePraxis = "Praxis"
|
||||
serviceHexis = "Hexis"
|
||||
)
|
||||
|
||||
// serviceVars — the one-key map the eco_down and eco_denied lines take.
|
||||
func serviceVars(name string) map[string]string { return map[string]string{"name": name} }
|
||||
|
||||
// ecosystemGap names the service that failed. A rejected credential gets its
|
||||
// own line, because a wrong token looks exactly like an outage to him and
|
||||
// "try again" is advice that will never work. Every degrade path reads through
|
||||
// here, so all of them name the service and none of them guesses instead.
|
||||
func ecosystemGap(service string, err error) string {
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(service))
|
||||
}
|
||||
return phraser.A(phraser.EcoDown, serviceVars(service))
|
||||
}
|
||||
|
||||
// praxisCapability is one arm of the Praxis act dispatch. This is an interface
|
||||
// rather than a map[string]func because each arm carries its own state: the
|
||||
// verb aliases it answers to, the trace name it records, and its own reply
|
||||
@@ -127,10 +139,16 @@ func (h *reactiveHandler) handlePraxisAct(ctx context.Context, dec router.Decisi
|
||||
// praxisItemAction is the shared shape of the item-lifecycle capabilities: take
|
||||
// an item id from the value slot, call one Praxis endpoint, trace the result.
|
||||
type praxisItemAction struct {
|
||||
verbs []string
|
||||
ask string // reply when no item id was given
|
||||
op string // trace + log name of the operation
|
||||
failure string // reply when the Praxis call errors
|
||||
verbs []string
|
||||
ask string // reply when no item id was given
|
||||
op string // trace + log name of the operation
|
||||
// failure is the first half of the reply when the Praxis call errors: which
|
||||
// operation did not happen. ecosystemGap supplies the second half, which
|
||||
// names Praxis and splits a refused token from an outage — those two used to
|
||||
// produce the identical sentence and neither said "Praxis" (Vikunja #588).
|
||||
// The verb is kept alongside the service name because the trace is the only
|
||||
// other place it exists, and he is not reading the trace.
|
||||
failure string
|
||||
success string
|
||||
call func(ctx context.Context, px *praxisClient, id string) error
|
||||
}
|
||||
@@ -147,7 +165,7 @@ func (a praxisItemAction) handle(ctx context.Context, h *reactiveHandler, px *pr
|
||||
log.Printf("ecosystem: praxis %s %s: %v", a.op, id, err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", a.op, traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"item_id": id}))
|
||||
return a.failure
|
||||
return a.failure + " " + ecosystemGap(servicePraxis, err)
|
||||
}
|
||||
h.recordPraxisTrace(ctx, a.op, started, map[string]any{"item_id": id})
|
||||
return a.success
|
||||
@@ -199,16 +217,10 @@ func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, p
|
||||
}
|
||||
parts = append(parts, s)
|
||||
|
||||
// Speaking an item surfaces it, it does not acknowledge it
|
||||
// (ECOSYSTEM-SPEC.md §2.3: surfaced != acknowledged). Best-effort:
|
||||
// a failed surface call must not block delivering the digest.
|
||||
if id, ok := item["id"].(string); ok && id != "" {
|
||||
// Recorded in the order she says them, and only for items she could
|
||||
// say: an item skipped above has no position in what he heard (#516).
|
||||
// Recorded in the order she says them, and only for items she could
|
||||
// say: an item skipped above has no position in what he heard (#516).
|
||||
if id := surfaceSpoken(ctx, px, item); id != "" {
|
||||
spoken = append(spoken, id)
|
||||
if _, err := px.Surface(ctx, id); err != nil {
|
||||
log.Printf("ecosystem: praxis surface %s: %v", id, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
h.rememberSurfaced(spoken)
|
||||
@@ -298,12 +310,7 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
// trace gets. A trace that stores a rune count next to a log line
|
||||
// storing the runes is not redacted at all.
|
||||
log.Printf("ecosystem: entity attention resolve %s: %v", redactSubject(subject), err)
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceNexus))
|
||||
}
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
return h.nexusResolveFailed(ctx, subject, started, err)
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
return phraser.A(phraser.EcoAmbiguous, map[string]string{"items": strings.Join(ambiguous, ", ")})
|
||||
@@ -339,19 +346,24 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
})
|
||||
|
||||
var parts []string
|
||||
var spoken []string
|
||||
for _, item := range items {
|
||||
title, _ := item["title"].(string)
|
||||
if title == "" {
|
||||
continue
|
||||
}
|
||||
parts = append(parts, title)
|
||||
// Same surfaced != acknowledged rule as the unscoped digest.
|
||||
if id, ok := item["id"].(string); ok && id != "" {
|
||||
if _, err := px.Surface(ctx, id); err != nil {
|
||||
log.Printf("ecosystem: praxis surface %s: %v", id, err)
|
||||
}
|
||||
if id := surfaceSpoken(ctx, px, item); id != "" {
|
||||
spoken = append(spoken, id)
|
||||
}
|
||||
}
|
||||
// The scoped digest is a list she read out, so it replaces the positional
|
||||
// memory exactly as the unscoped one does. It used to surface these items
|
||||
// and remember none of them, which left the previous digest live: "отметь
|
||||
// второй как сделанное" then indexed into a list he had not just heard and
|
||||
// transitioned somebody else's item (docs/ecosystem.md — a wrong guess here
|
||||
// transitions the wrong item).
|
||||
h.rememberSurfaced(spoken)
|
||||
if known := h.localFactsForEntity(ctx, entityID); known != "" {
|
||||
parts = append(parts, known)
|
||||
}
|
||||
@@ -366,6 +378,22 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
return phraser.A(phraser.AttentionListEntity, map[string]string{"name": displayName, "items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// surfaceSpoken marks an item she just read out as surfaced. Speaking an item
|
||||
// surfaces it, it does not acknowledge it (ECOSYSTEM-SPEC.md §2.3: surfaced !=
|
||||
// acknowledged), so this calls Surface and nothing else. Best effort: a failed
|
||||
// surface call must not block delivering the digest. Returns the item id, or ""
|
||||
// when the item carried none.
|
||||
func surfaceSpoken(ctx context.Context, px *praxisClient, item map[string]any) string {
|
||||
id, _ := item["id"].(string)
|
||||
if id == "" {
|
||||
return ""
|
||||
}
|
||||
if _, err := px.Surface(ctx, id); err != nil {
|
||||
log.Printf("ecosystem: praxis surface %s: %v", id, err)
|
||||
}
|
||||
return id
|
||||
}
|
||||
|
||||
// scopedToEntity drops items that carry an entity_id other than the one asked
|
||||
// about, and reports whether the response can be trusted as scoped at all. An
|
||||
// item without an entity_id is kept only when at least one sibling carries the
|
||||
@@ -474,6 +502,14 @@ func traceStatusForError(err error) string {
|
||||
return traceFailed
|
||||
}
|
||||
|
||||
// nexusResolveFailed records a resolve that failed and returns the named gap.
|
||||
// The subject is his words, so the trace keeps a rune count and not the runes.
|
||||
func (h *reactiveHandler) nexusResolveFailed(ctx context.Context, subject string, started time.Time, err error) string {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
return ecosystemGap(serviceNexus, err)
|
||||
}
|
||||
|
||||
// redactSubject reduces a user utterance to something safe to persist in a
|
||||
// trace: its length only. Traces are diagnostics, and his words are not
|
||||
// diagnostics — the correlation ID is what ties a trace to the turn.
|
||||
@@ -532,26 +568,31 @@ func unauthorizedEcosystemError(err error) bool {
|
||||
return errors.As(err, &ee) && ee.Unauthorized()
|
||||
}
|
||||
|
||||
// isEcosystemError reports a failure that belongs to the service rather than to
|
||||
// what was asked of it: a call that never landed, or one the far side refused.
|
||||
// It separates "Hexis is down" from "the restart failed".
|
||||
func isEcosystemError(err error) bool {
|
||||
var ee *ecosystemError
|
||||
return errors.As(err, &ee)
|
||||
}
|
||||
|
||||
// traceErrorFields describes an ecosystemError for a trace without leaking the
|
||||
// payload: the HTTP status and the failure class, nothing else.
|
||||
func traceErrorFields(err error) map[string]any {
|
||||
fields := map[string]any{}
|
||||
fields := map[string]any{"class": "error"}
|
||||
var ee *ecosystemError
|
||||
if errors.As(err, &ee) {
|
||||
fields["http_status"] = ee.Status
|
||||
switch {
|
||||
case ee.Unauthorized():
|
||||
fields["class"] = "unauthorized"
|
||||
case ee.ContractMismatch():
|
||||
fields["class"] = "contract_mismatch"
|
||||
case ee.Unreachable():
|
||||
fields["class"] = "unreachable"
|
||||
default:
|
||||
fields["class"] = "error"
|
||||
}
|
||||
if !errors.As(err, &ee) {
|
||||
return fields
|
||||
}
|
||||
fields["class"] = "error"
|
||||
fields["http_status"] = ee.Status
|
||||
switch {
|
||||
case ee.Unauthorized():
|
||||
fields["class"] = "unauthorized"
|
||||
case ee.ContractMismatch():
|
||||
fields["class"] = "contract_mismatch"
|
||||
case ee.Unreachable():
|
||||
fields["class"] = "unreachable"
|
||||
}
|
||||
return fields
|
||||
}
|
||||
|
||||
@@ -636,16 +677,11 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
res := h.resolveEntityCandidates(ctx, entityReferences(dec))
|
||||
subject, entityID, displayName, ambiguous, err := res.subject, res.entityID, res.displayName, res.ambiguous, res.err
|
||||
if err != nil {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceNexus))
|
||||
}
|
||||
// A genuine Nexus dependency failure, not "no such entity" — stop here
|
||||
// and report degradation rather than silently falling through to the
|
||||
// local command executor (ECOSYSTEM-SPEC.md: services degrade
|
||||
// independently, never a silent all-clear).
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
return h.nexusResolveFailed(ctx, subject, started, err)
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceAmbig, started,
|
||||
@@ -668,10 +704,7 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
if err != nil {
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceStatusForError(err), discovered,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceHexis))
|
||||
}
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceHexis))
|
||||
return ecosystemGap(serviceHexis, err)
|
||||
}
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceOK, discovered,
|
||||
map[string]any{"entity_id": entityID, "count": len(caps)})
|
||||
@@ -745,6 +778,9 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
entityID: entityID,
|
||||
displayName: displayName,
|
||||
expiry: h.now().Add(confirmTTL),
|
||||
// This action's id, so the execution the confirm authorises is
|
||||
// joined to the resolve and the discovery that proposed it.
|
||||
correlationID: correlationIDFromCtx(ctx),
|
||||
}
|
||||
h.mu.Unlock()
|
||||
h.recordEcosystemTrace(ctx, "hexis", "confirmation", tracePending, started,
|
||||
@@ -769,6 +805,14 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
|
||||
mergeFields(traceErrorFields(err), map[string]any{
|
||||
"entity_id": entityID, "capability": capName, "causation_id": causationID,
|
||||
}))
|
||||
// Hexis never answering, or answering "no", is a gap in Hexis and is
|
||||
// named as one — a refused token said "не получилось выполнить команду"
|
||||
// here and sent him to debug a capability that was never reached
|
||||
// (Vikunja #587). An execution that genuinely ran and failed is not an
|
||||
// ecosystemError and keeps the command-level line.
|
||||
if isEcosystemError(err) {
|
||||
return ecosystemGap(serviceHexis, err)
|
||||
}
|
||||
return phraser.A(phraser.ActFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
// One record per hop: the second write this used to make said the same
|
||||
|
||||
@@ -0,0 +1,159 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// A refused credential and an outage are different answers, and on the Hexis
|
||||
// path only one of them used to be said. These tests pin the difference at both
|
||||
// Hexis sites: the discovery hop and the execute hop (Vikunja #587). The Praxis
|
||||
// half of the same defect is in praxis_gap_test.go.
|
||||
//
|
||||
// unreachableURL is a port nothing listens on, which is what "the service is
|
||||
// down" looks like from inside a call: the connection is refused, no HTTP
|
||||
// answer is ever produced, and ecosystemError.Unreachable() is true.
|
||||
const unreachableURL = "http://127.0.0.1:1"
|
||||
|
||||
func denied(service, reply string) bool {
|
||||
return phraser.IsA(phraser.EcoDenied, serviceVars(service), reply)
|
||||
}
|
||||
|
||||
func down(service, reply string) bool {
|
||||
return phraser.IsA(phraser.EcoDown, serviceVars(service), reply)
|
||||
}
|
||||
|
||||
// hexisGapHandler wires a handler whose Nexus resolves cleanly and whose Hexis
|
||||
// is the caller's to break. hexisURL is taken separately so a test can point it
|
||||
// at a dead port.
|
||||
func hexisGapHandler(t *testing.T, nexusURL, hexisURL string) *reactiveHandler {
|
||||
t.Helper()
|
||||
st := newTestStore(t)
|
||||
now := time.Now()
|
||||
return &reactiveHandler{
|
||||
api: ipc.NewStoreAPI(st),
|
||||
dataStore: st,
|
||||
now: func() time.Time { return now },
|
||||
ecosystem: stubEcosystem(nexusURL, hexisURL),
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisDiscovery401IsDeniedNotDown — the discovery hop.
|
||||
//
|
||||
// The vendored Hexis client returns a plain fmt.Errorf for every status at or
|
||||
// above 400, so errors.As for *ecosystemError never matched and every failure
|
||||
// fell through to the outage line. "Hexis is down" for a rejected token sends
|
||||
// him to inspect a service that is running fine.
|
||||
func TestHexisDiscovery401IsDeniedNotDown(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", muzickIndexer, "service"))
|
||||
caps := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": true})
|
||||
hexis := newFakeHexis(t, caps, fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := hexisGapHandler(t, nexus.URL, hexis.URL)
|
||||
|
||||
hexis.SetFault(401)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !denied(serviceHexis, reply) {
|
||||
t.Fatalf("401 from hexis discovery: got %q, want the denied line naming Hexis", reply)
|
||||
}
|
||||
if !strings.Contains(reply, serviceHexis) {
|
||||
t.Errorf("reply does not name Hexis: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisDiscoveryOutageIsDownNotDenied — the other half of the same fork.
|
||||
// Without this the fix could pass by calling everything a refused credential.
|
||||
func TestHexisDiscoveryOutageIsDownNotDenied(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", muzickIndexer, "service"))
|
||||
h := hexisGapHandler(t, nexus.URL, unreachableURL)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !down(serviceHexis, reply) {
|
||||
t.Fatalf("connection refused from hexis: got %q, want the outage line naming Hexis", reply)
|
||||
}
|
||||
if denied(serviceHexis, reply) {
|
||||
t.Error("an outage must not be reported as a refused credential")
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisExecute401IsDeniedNotCommandFailure — the execute hop, which did not
|
||||
// consult ecosystemGap at all and named neither the service nor the cause.
|
||||
func TestHexisExecute401IsDeniedNotCommandFailure(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", muzickIndexer, "service"))
|
||||
caps := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": true})
|
||||
hexis := newFakeHexis(t, caps, fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := hexisGapHandler(t, nexus.URL, hexis.URL)
|
||||
|
||||
// Discovery stays healthy; only the execute endpoint refuses. A blanket
|
||||
// fault would never reach the site under test.
|
||||
hexis.SetRouteFault("/api/v1/execute", 401)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !denied(serviceHexis, reply) {
|
||||
t.Fatalf("401 from hexis execute: got %q, want the denied line naming Hexis", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisExecuteOutageIsDown — same site, the other classification.
|
||||
//
|
||||
// Discovery and execution share one base URL, so the outage has to be scoped to
|
||||
// the execute endpoint rather than to the server: it answers capabilities
|
||||
// normally and drops the connection on execute, which is what the client sees
|
||||
// when the far side dies mid-call. That produces no HTTP status at all, which is
|
||||
// what Unreachable() means.
|
||||
func TestHexisExecuteOutageIsDown(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", muzickIndexer, "service"))
|
||||
caps := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": true})
|
||||
hexis := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path == "/api/v1/execute" {
|
||||
conn, _, err := w.(http.Hijacker).Hijack()
|
||||
if err != nil {
|
||||
t.Errorf("hijack: %v", err)
|
||||
return
|
||||
}
|
||||
conn.Close()
|
||||
return
|
||||
}
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
_, _ = w.Write([]byte(caps))
|
||||
}))
|
||||
t.Cleanup(hexis.Close)
|
||||
h := hexisGapHandler(t, nexus.URL, hexis.URL)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !down(serviceHexis, reply) {
|
||||
t.Fatalf("dropped connection on hexis execute: got %q, want the outage line", reply)
|
||||
}
|
||||
if denied(serviceHexis, reply) {
|
||||
t.Error("an outage must not be reported as a refused credential")
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisExecutionFailedStaysCommandFailure — the boundary of the fix. Hexis
|
||||
// answering 200 with a failed execution is the command failing, not Hexis
|
||||
// degrading, and it must keep the command-level line rather than accusing a
|
||||
// healthy service of being down.
|
||||
func TestHexisExecutionFailedStaysCommandFailure(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", muzickIndexer, "service"))
|
||||
caps := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": true})
|
||||
hexis := newFakeHexis(t, caps, fixtureHexisExecutionFailed("exec_1", "unit refused to start"))
|
||||
h := hexisGapHandler(t, nexus.URL, hexis.URL)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if down(serviceHexis, reply) || denied(serviceHexis, reply) {
|
||||
t.Fatalf("a failed execution must not be reported as an ecosystem gap, got %q", reply)
|
||||
}
|
||||
if !phraser.IsA(phraser.ActFailEntity, map[string]string{"name": muzickIndexer}, reply) {
|
||||
t.Fatalf("want the command-failure line, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -115,3 +115,83 @@ func TestFakeNexus_FaultInjectionThenRecovery(t *testing.T) {
|
||||
t.Fatalf("expected success once nexus recovers, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// TestPraxisEntityAttention_RemembersWhatItReadOut: the scoped digest is a list
|
||||
// she read out, so a positional follow-up must land on one of ITS items. It
|
||||
// surfaced them and remembered none, which left the previous digest live and
|
||||
// sent "отметь второй" at somebody else's item.
|
||||
func TestPraxisEntityAttention_RemembersWhatItReadOut(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
|
||||
scoped := fixturePraxisAttentionScoped("ent_muzick",
|
||||
map[string]any{"id": "item_scoped_1", "title": "indexer wedged"})
|
||||
praxis := newFakePraxis(t, scoped)
|
||||
h := ecoHandler(t, nexus, praxis, nil)
|
||||
|
||||
// A digest from an earlier turn, still the positional memory.
|
||||
h.rememberSurfaced([]string{"item_stale"})
|
||||
|
||||
reply := h.handlePraxisAct(ctx, router.Decision{
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Fn: "entity_attention", HasFn: true, Value: "muzick indexer"},
|
||||
})
|
||||
if !strings.Contains(reply, "indexer wedged") {
|
||||
t.Fatalf("expected the scoped item to be read out, got %q", reply)
|
||||
}
|
||||
|
||||
h.mu.Lock()
|
||||
surfaced := append([]string(nil), h.surfacedItems...)
|
||||
h.mu.Unlock()
|
||||
if len(surfaced) != 1 || surfaced[0] != "item_scoped_1" {
|
||||
t.Fatalf("scoped digest must replace the positional memory, got %v", surfaced)
|
||||
}
|
||||
|
||||
// The follow-up resolves against what he just heard, not the stale list.
|
||||
if reply := h.handlePraxisAct(ctx, praxisItemDec("resolve_item", "last")); reply == "" {
|
||||
t.Fatal("positional follow-up should have been claimed by praxis")
|
||||
}
|
||||
var body string
|
||||
for _, r := range praxis.Requests() {
|
||||
if r.Method == "POST" && r.Path == "/api/v1/tools/resolve" {
|
||||
body = string(r.Body)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(body, "item_scoped_1") {
|
||||
t.Fatalf("resolve must transition the item she read out, posted %q", body)
|
||||
}
|
||||
if strings.Contains(body, "item_stale") {
|
||||
t.Fatal("resolve transitioned an item from a previous digest")
|
||||
}
|
||||
}
|
||||
|
||||
// TestHexisConfirm_KeepsOneCorrelationIDPerAction: the confirm arrives on a
|
||||
// later turn with a context of its own. The contract mints one id per action,
|
||||
// so the execution it authorises must still be joinable to the resolve and the
|
||||
// discovery that proposed it — it recorded a fresh id and no causation at all.
|
||||
func TestHexisConfirm_KeepsOneCorrelationIDPerAction(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
|
||||
caps := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": false})
|
||||
hexis := newFakeHexis(t, caps, fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("restart")); !strings.Contains(reply, "да") {
|
||||
t.Fatalf("mutating capability must ask for confirmation, got %q", reply)
|
||||
}
|
||||
resolve := findTrace(t, h, "nexus", "resolve")
|
||||
if resolve == nil || resolve.CorrelationID == "" {
|
||||
t.Fatalf("expected a nexus resolve trace carrying a correlation id, got %+v", resolve)
|
||||
}
|
||||
|
||||
if _, handled := h.resolveConfirm(ctx, "да"); !handled {
|
||||
t.Fatal("confirm should have been claimed")
|
||||
}
|
||||
exec := findTrace(t, h, "hexis", "execute")
|
||||
if exec == nil {
|
||||
t.Fatal("expected a hexis execute trace")
|
||||
}
|
||||
if exec.CausationID != resolve.CorrelationID {
|
||||
t.Fatalf("confirmed execution must cite the action that proposed it: causation %q, action %q",
|
||||
exec.CausationID, resolve.CorrelationID)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -24,7 +24,7 @@ func TestApplyAction_FactCapture_QueuesEntityResolution(t *testing.T) {
|
||||
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
matcher := tool.NewMatcher(api)
|
||||
rtr := buildRouter(emb, matcher, 0.55, nil)
|
||||
rtr := buildRouter(emb, matcher, 0.55, nil, nil)
|
||||
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
|
||||
@@ -37,8 +37,8 @@ type factEnrichmentWorker struct {
|
||||
nextTry map[int64]time.Time // fact id → earliest retry
|
||||
}
|
||||
|
||||
// enrichmentScanLimit bounds how deep a single tick (or status report) walks
|
||||
// the pending queue looking for facts whose backoff has elapsed. The queue is
|
||||
// enrichmentScanLimit bounds how deep a single tick walks the pending queue
|
||||
// looking for facts whose backoff has elapsed. The queue is
|
||||
// ordered by id, so without a scan the oldest facts hold every batch slot
|
||||
// whether or not they are eligible, and one permanently failing fact stalls
|
||||
// every younger one behind it.
|
||||
@@ -75,8 +75,8 @@ func newFactEnrichmentWorker(st *store.Store, eco *ecosystemWiring, interval tim
|
||||
// has been down all day must be visible as a backlog, not as facts that
|
||||
// silently never got tagged.
|
||||
//
|
||||
// All three numbers describe the same set of rows, the first
|
||||
// enrichmentScanLimit pending facts. Counting Pending over a thousand rows
|
||||
// All three numbers describe the same set of rows, whatever is still pending
|
||||
// out of the first enrichmentScanLimit facts. Counting Pending over a thousand rows
|
||||
// while counting InBackoff over the twenty that reached the head of a batch
|
||||
// described two different populations under one struct.
|
||||
type enrichmentStatus struct {
|
||||
@@ -86,13 +86,22 @@ type enrichmentStatus struct {
|
||||
Scanned int // rows the other three counts were taken over
|
||||
}
|
||||
|
||||
// status reads the queue and counts over it. For a caller with no batch in
|
||||
// hand — anything asking the worker how it is doing from outside the tick.
|
||||
func (w *factEnrichmentWorker) status(ctx context.Context) enrichmentStatus {
|
||||
var st enrichmentStatus
|
||||
pending, err := w.store.PendingFactResolutions(ctx, enrichmentScanLimit)
|
||||
if err != nil {
|
||||
log.Printf("factenrichment: status: %v", err)
|
||||
return st
|
||||
return enrichmentStatus{}
|
||||
}
|
||||
return w.statusOf(pending)
|
||||
}
|
||||
|
||||
// statusOf counts over a batch the caller already has. The batch is the query
|
||||
// the tick already ran, so reporting the backlog costs no second read of the
|
||||
// scan limit — up to a thousand rows, on a database that serialises them.
|
||||
func (w *factEnrichmentWorker) statusOf(pending []store.Fact) enrichmentStatus {
|
||||
var st enrichmentStatus
|
||||
st.Pending = len(pending)
|
||||
st.Scanned = len(pending)
|
||||
w.mu.Lock()
|
||||
@@ -144,17 +153,24 @@ func (w *factEnrichmentWorker) tick(ctx context.Context) {
|
||||
}
|
||||
w.forgetDeparted(pending)
|
||||
skipped, failed, attempted := 0, 0, 0
|
||||
// A resolved fact leaves the pending queue, so the batch in hand overstates
|
||||
// the backlog by however many succeeded. Drop them here rather than
|
||||
// re-reading the queue to find out.
|
||||
remaining := make([]store.Fact, 0, len(pending))
|
||||
for _, f := range pending {
|
||||
if attempted >= w.batch {
|
||||
break
|
||||
remaining = append(remaining, f)
|
||||
continue
|
||||
}
|
||||
if !w.due(f.ID) {
|
||||
skipped++
|
||||
remaining = append(remaining, f)
|
||||
continue
|
||||
}
|
||||
attempted++
|
||||
if !w.resolveOne(ctx, f) {
|
||||
failed++
|
||||
remaining = append(remaining, f)
|
||||
}
|
||||
}
|
||||
if failed > 0 {
|
||||
@@ -164,7 +180,7 @@ func (w *factEnrichmentWorker) tick(ctx context.Context) {
|
||||
// Report the backlog every tick, not only when something failed: the
|
||||
// stalled state worth seeing is the one where nothing failed because
|
||||
// nothing was attempted.
|
||||
if st := w.status(ctx); st.Pending > 0 {
|
||||
if st := w.statusOf(remaining); st.Pending > 0 {
|
||||
log.Printf("factenrichment: %d facts pending entity resolution, %d in backoff, worst attempt %d (scanned %d)",
|
||||
st.Pending, st.InBackoff, st.MaxAttempts, st.Scanned)
|
||||
}
|
||||
|
||||
@@ -20,7 +20,7 @@ func newFactGateHandler(t *testing.T, now time.Time) (*reactiveHandler, ipc.Core
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, tool.NewMatcher(api), 0.55, nil),
|
||||
router: buildRouter(emb, tool.NewMatcher(api), 0.55, nil, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
|
||||
+173
-286
@@ -68,6 +68,11 @@ import (
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
// stepUpTTL is how long one passkey assertion keeps the session stepped up.
|
||||
// Long enough for the unlock call that follows it, short enough that a walked
|
||||
// away laptop does not stay authorized.
|
||||
const stepUpTTL = 5 * time.Minute
|
||||
|
||||
var errLocked = errors.New("mavend: daemon locked — complete passkey assertion first")
|
||||
|
||||
// daemonLock tracks whether the daemon is in locked (pre-unlock) mode, and
|
||||
@@ -247,44 +252,31 @@ func run(args []string) error {
|
||||
// envelope per successful intake write.
|
||||
coreFor := func() ipc.CoreAPI { return newIntakeAPI(ipc.NewStoreAPI(st), evBus, time.Now) }
|
||||
|
||||
// depsNow reads whatever the current path has wired. Both boot paths build
|
||||
// the CoreAPI and start the workers from this one value, so neither can
|
||||
// hold a field the other misses. See cmd/mavend/boot.go.
|
||||
depsNow := func() bootDeps {
|
||||
return bootDeps{
|
||||
coreFor: coreFor,
|
||||
tl: tl,
|
||||
evBus: evBus,
|
||||
voiceW: voiceW,
|
||||
st: st,
|
||||
factWorker: factWorker,
|
||||
evalWorker: evalWorker,
|
||||
feedWkr: feedWkr,
|
||||
crawlWkr: crawlWkr,
|
||||
}
|
||||
}
|
||||
|
||||
if !locked {
|
||||
rules = wireRules(cfg)
|
||||
gatherer = loop.NewGatherer(st, rules)
|
||||
if cfg.QuietHours != nil {
|
||||
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
|
||||
}
|
||||
gatherer = wireGatherer(st, cfg, rules)
|
||||
|
||||
// phraser
|
||||
phr = phraser.NewStub()
|
||||
if cfg.Phraser != nil {
|
||||
pc := phraser.Config{
|
||||
ModelPath: cfg.Phraser.ModelPath,
|
||||
BinPath: cfg.Phraser.BinPath,
|
||||
Listen: cfg.Phraser.Listen,
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
CacheRAMMiB: cacheRAMMiB(cfg.Phraser.CacheRAMMiB),
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
LLMNudges: cfg.Phraser.LLMNudges,
|
||||
ContextBlock: contextBlockFn(cfg, time.Now),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = "llama-server"
|
||||
}
|
||||
if pc.Listen == "" {
|
||||
pc.Listen = "127.0.0.1:0"
|
||||
}
|
||||
if pc.NCtx <= 0 {
|
||||
pc.NCtx = 2048
|
||||
}
|
||||
if pc.Timeout <= 0 {
|
||||
pc.Timeout = 30 * time.Second
|
||||
}
|
||||
var err error
|
||||
phr, err = phraser.NewLLMPhraser(ctx, pc)
|
||||
if err != nil {
|
||||
return fmt.Errorf("phraser: %w", err)
|
||||
}
|
||||
phr, err = wirePhraser(ctx, cfg)
|
||||
if err != nil {
|
||||
return fmt.Errorf("phraser: %w", err)
|
||||
}
|
||||
|
||||
// ecosystem — nexus + hexis + praxis (all over HTTP; no direct DB access)
|
||||
@@ -297,72 +289,19 @@ func run(args []string) error {
|
||||
}
|
||||
|
||||
// delivery
|
||||
var ntfy delivery.Sink
|
||||
if cfg.Ntfy != nil {
|
||||
s, err := ntfysink.New(*cfg.Ntfy)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire ntfy sink: %w", err)
|
||||
}
|
||||
ntfy = s
|
||||
dispatcher, err = wireDispatcher(st, cfg, voiceW)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var telegram delivery.Sink
|
||||
if cfg.Telegram != nil {
|
||||
s, err := telegramsink.New(*cfg.Telegram)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire telegram sink: %w", err)
|
||||
}
|
||||
telegram = s
|
||||
}
|
||||
var voiceSink delivery.Sink
|
||||
if voiceW != nil {
|
||||
voiceSink = voiceW.voiceSink
|
||||
}
|
||||
// A crashed prior run may have left "pending" delivery attempts (send
|
||||
// may have landed externally, then the process died before recording
|
||||
// it) — reconcile them to "unknown" before the tick loop resumes
|
||||
// sending, so nothing auto-resends into that ambiguity.
|
||||
if _, err := st.ReconcileStaleDeliveryAttempts(context.Background(), time.Now()); err != nil {
|
||||
log.Printf("delivery outbox reconcile: %v", err)
|
||||
}
|
||||
dispatcher = delivery.NewDispatcher(delivery.Config{
|
||||
Ntfy: ntfy,
|
||||
Telegram: telegram,
|
||||
Voice: voiceSink,
|
||||
Ack: st,
|
||||
Nudges: st,
|
||||
Reminders: st,
|
||||
Outbox: st,
|
||||
})
|
||||
|
||||
// tick loop
|
||||
tickInterval := time.Duration(cfg.TickInterval)
|
||||
repeatInterval := time.Duration(cfg.RepeatInterval)
|
||||
autotuneInterval := time.Duration(cfg.AutotuneInterval)
|
||||
tl = newTickLoop(st, gatherer, dispatcher, phr, rules, tickInterval, repeatInterval, autotuneInterval, cfg.Digest, routinesFromConfig(cfg.Routines), config.MorningRoutinesFromConfig(cfg.MorningRoutines), cfg.PatternProposals)
|
||||
tl = wireTickLoop(st, gatherer, dispatcher, phr, rules, cfg)
|
||||
factWorker = newFactEnrichmentWorker(st, eco, time.Duration(cfg.FactEnrichmentInterval))
|
||||
evalWorker = newMemoryEvalWorker(st, phr, cfg)
|
||||
feedWkr = newFeedWorker(coreFor(), embedderOf(voiceW), cfg)
|
||||
crawlWkr = newCrawlWorker(newCrawler(cfg), coreFor(), embedderOf(voiceW), cfg)
|
||||
|
||||
coreAPI = &daemonAPI{
|
||||
CoreAPI: coreFor(),
|
||||
getTrace: tl.trace,
|
||||
getMorningStatus: func(ctx context.Context) []ipc.MorningRoutineStatus { return tl.morningStatus(ctx, time.Now()) },
|
||||
getDayPlan: func(ctx context.Context) ipc.DayPlan { return tl.dayPlan(ctx, time.Now()) },
|
||||
getEvents: intakeEventsFn(evBus),
|
||||
seedStore: seedStoreIfAllowed(st),
|
||||
nexus: nexusOf(voiceW),
|
||||
}
|
||||
if voiceW != nil && voiceW.handler != nil {
|
||||
api := coreAPI.(*daemonAPI)
|
||||
api.chatFn = voiceW.handler.handleText
|
||||
// And the reverse: the handler was wired with the bare store
|
||||
// adapter, which cannot serve the day plan. See upgradeAPI.
|
||||
voiceW.handler.upgradeAPI(api)
|
||||
}
|
||||
if voiceW != nil && voiceW.mcp != nil {
|
||||
coreAPI.(*daemonAPI).getMCPServers = voiceW.mcp.status
|
||||
}
|
||||
coreAPI = newDaemonAPI(depsNow())
|
||||
} else {
|
||||
// locked mode: no real store yet, so there's no meaningful CoreAPI to
|
||||
// serve. srv.Check below is the actual guard — every CoreAPI call is
|
||||
@@ -379,7 +318,7 @@ func run(args []string) error {
|
||||
return fmt.Errorf("ipc listen: %w", err)
|
||||
}
|
||||
|
||||
passkeySess := webauthn.NewPasskeySession(5 * time.Minute)
|
||||
passkeySess := webauthn.NewPasskeySession(stepUpTTL)
|
||||
|
||||
// Set Server.Check — the single authorization guard, run once by
|
||||
// Server.dispatch before any CoreAPI method is called (see
|
||||
@@ -423,6 +362,9 @@ func run(args []string) error {
|
||||
if !locked {
|
||||
wireMailIntake(srv, st, phr, cfg, evBus)
|
||||
wireModelSwap(srv, phr, cfg)
|
||||
// Inbound telegram (V-637). Dark unless the telegram block says intake,
|
||||
// and it reads one chat.
|
||||
wireTelegramIntake(ctx, &wg, coreAPI, cfg)
|
||||
// Vision + the media blob store (Vikunja #252). Both stay dark without a
|
||||
// media block; MethodDescribeImage answers ErrUnknownMethod then.
|
||||
keeper := wireVision(ctx, &wg, srv, st, embedderOf(voiceW), cfg)
|
||||
@@ -527,40 +469,11 @@ func run(args []string) error {
|
||||
|
||||
// Wire everything.
|
||||
rules = wireRules(cfg)
|
||||
gatherer = loop.NewGatherer(st, rules)
|
||||
if cfg.QuietHours != nil {
|
||||
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
|
||||
}
|
||||
gatherer = wireGatherer(st, cfg, rules)
|
||||
|
||||
phr = phraser.NewStub()
|
||||
if cfg.Phraser != nil {
|
||||
pc := phraser.Config{
|
||||
ModelPath: cfg.Phraser.ModelPath,
|
||||
BinPath: cfg.Phraser.BinPath,
|
||||
Listen: cfg.Phraser.Listen,
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
CacheRAMMiB: cacheRAMMiB(cfg.Phraser.CacheRAMMiB),
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
LLMNudges: cfg.Phraser.LLMNudges,
|
||||
ContextBlock: contextBlockFn(cfg, time.Now),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = "llama-server"
|
||||
}
|
||||
if pc.Listen == "" {
|
||||
pc.Listen = "127.0.0.1:0"
|
||||
}
|
||||
if pc.NCtx <= 0 {
|
||||
pc.NCtx = 2048
|
||||
}
|
||||
if pc.Timeout <= 0 {
|
||||
pc.Timeout = 30 * time.Second
|
||||
}
|
||||
phr, err = phraser.NewLLMPhraser(ctx, pc)
|
||||
if err != nil {
|
||||
return fmt.Errorf("phraser: %w", err)
|
||||
}
|
||||
phr, err = wirePhraser(ctx, cfg)
|
||||
if err != nil {
|
||||
return fmt.Errorf("phraser: %w", err)
|
||||
}
|
||||
|
||||
eco = wireEcosystem(cfg)
|
||||
@@ -570,65 +483,26 @@ func run(args []string) error {
|
||||
return fmt.Errorf("wire voice: %w", err)
|
||||
}
|
||||
|
||||
var ntfy delivery.Sink
|
||||
if cfg.Ntfy != nil {
|
||||
s, err := ntfysink.New(*cfg.Ntfy)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire ntfy sink: %w", err)
|
||||
}
|
||||
ntfy = s
|
||||
dispatcher, err = wireDispatcher(st, cfg, voiceW)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var telegram delivery.Sink
|
||||
if cfg.Telegram != nil {
|
||||
s, err := telegramsink.New(*cfg.Telegram)
|
||||
if err != nil {
|
||||
return fmt.Errorf("wire telegram sink: %w", err)
|
||||
}
|
||||
telegram = s
|
||||
}
|
||||
var voiceSink delivery.Sink
|
||||
if voiceW != nil {
|
||||
voiceSink = voiceW.voiceSink
|
||||
}
|
||||
if _, err := st.ReconcileStaleDeliveryAttempts(context.Background(), time.Now()); err != nil {
|
||||
log.Printf("delivery outbox reconcile: %v", err)
|
||||
}
|
||||
dispatcher = delivery.NewDispatcher(delivery.Config{
|
||||
Ntfy: ntfy,
|
||||
Telegram: telegram,
|
||||
Voice: voiceSink,
|
||||
Ack: st,
|
||||
Nudges: st,
|
||||
Reminders: st,
|
||||
Outbox: st,
|
||||
})
|
||||
|
||||
tickInterval := time.Duration(cfg.TickInterval)
|
||||
repeatInterval := time.Duration(cfg.RepeatInterval)
|
||||
autotuneInterval := time.Duration(cfg.AutotuneInterval)
|
||||
tl = newTickLoop(st, gatherer, dispatcher, phr, rules, tickInterval, repeatInterval, autotuneInterval, cfg.Digest, routinesFromConfig(cfg.Routines), config.MorningRoutinesFromConfig(cfg.MorningRoutines), cfg.PatternProposals)
|
||||
tl = wireTickLoop(st, gatherer, dispatcher, phr, rules, cfg)
|
||||
factWorker = newFactEnrichmentWorker(st, eco, time.Duration(cfg.FactEnrichmentInterval))
|
||||
evalWorker = newMemoryEvalWorker(st, phr, cfg)
|
||||
feedWkr = newFeedWorker(coreFor(), embedderOf(voiceW), cfg)
|
||||
crawlWkr = newCrawlWorker(newCrawler(cfg), coreFor(), embedderOf(voiceW), cfg)
|
||||
|
||||
// Swap the CoreAPI from the locked placeholder to the real store adapter.
|
||||
newAPI := &daemonAPI{
|
||||
CoreAPI: coreFor(),
|
||||
getTrace: tl.trace,
|
||||
getMorningStatus: func(ctx context.Context) []ipc.MorningRoutineStatus { return tl.morningStatus(ctx, time.Now()) },
|
||||
getDayPlan: func(ctx context.Context) ipc.DayPlan { return tl.dayPlan(ctx, time.Now()) },
|
||||
getEvents: intakeEventsFn(evBus),
|
||||
seedStore: seedStoreIfAllowed(st),
|
||||
}
|
||||
if voiceW != nil && voiceW.handler != nil {
|
||||
newAPI.chatFn = voiceW.handler.handleText
|
||||
voiceW.handler.upgradeAPI(newAPI)
|
||||
}
|
||||
newAPI := newDaemonAPI(depsNow())
|
||||
srv.SetAPI(newAPI)
|
||||
srv.Check = (&auth.Gate{Enrollment: auth.NewFloorEnrollment(), Session: passkeySess}).Check
|
||||
wireMailIntake(srv, st, phr, cfg, evBus)
|
||||
wireModelSwap(srv, phr, cfg)
|
||||
// Same on the unlock path, with the API that has just replaced the
|
||||
// locked placeholder (V-637).
|
||||
wireTelegramIntake(ctx, &wg, newAPI, cfg)
|
||||
keeper := wireVision(ctx, &wg, srv, st, embedderOf(voiceW), cfg)
|
||||
wireCapture(ctx, &wg, srv, keeper, st, voiceW, phr, cfg)
|
||||
// Voice identification (Vikunja #255). Enrolment plumbing only until a
|
||||
@@ -636,59 +510,10 @@ func run(args []string) error {
|
||||
// block, so no wire path takes a voiceprint on a default box.
|
||||
wireSpeaker(srv, st, cfg)
|
||||
|
||||
// Start voice server.
|
||||
if voiceW != nil {
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
if err := voiceW.server.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("voice serve: %v", err)
|
||||
}
|
||||
}()
|
||||
log.Printf("mavend: voice listening on %s", voiceW.server.Addr())
|
||||
}
|
||||
|
||||
// Start tick loop.
|
||||
go func() {
|
||||
tl.run(ctx)
|
||||
}()
|
||||
|
||||
// Start fact-entity enrichment worker.
|
||||
go func() {
|
||||
factWorker.run(ctx)
|
||||
}()
|
||||
|
||||
// Start background memory evaluation (nil unless configured).
|
||||
if evalWorker != nil {
|
||||
go func() {
|
||||
evalWorker.run(ctx)
|
||||
}()
|
||||
}
|
||||
|
||||
// Start feed reading (nil unless configured).
|
||||
if feedWkr != nil {
|
||||
go func() {
|
||||
feedWkr.run(ctx)
|
||||
}()
|
||||
}
|
||||
|
||||
// Start the watched-page crawls (nil unless configured).
|
||||
if crawlWkr != nil {
|
||||
go func() {
|
||||
crawlWkr.run(ctx)
|
||||
}()
|
||||
}
|
||||
|
||||
// Keep MCP connections alive (nil unless configured).
|
||||
if voiceW != nil && voiceW.mcp != nil {
|
||||
go voiceW.mcp.run(ctx)
|
||||
}
|
||||
|
||||
// Re-enumerate the house for new devices (nil unless configured).
|
||||
if voiceW != nil && voiceW.home != nil {
|
||||
go voiceW.home.run(ctx)
|
||||
}
|
||||
// The voice server and every background worker, on the outer wg
|
||||
// so shutdown waits for them. This used to be nine bare
|
||||
// `go func()` calls and a shadowed WaitGroup (V-639).
|
||||
startBackground(ctx, &wg, depsNow())
|
||||
|
||||
dl.unlock(st)
|
||||
log.Printf("mavend: unlocked via passkey assertion")
|
||||
@@ -696,72 +521,15 @@ func run(args []string) error {
|
||||
}
|
||||
}
|
||||
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
goWorker(&wg, func() {
|
||||
if err := srv.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("ipc serve: %v", err)
|
||||
}
|
||||
}()
|
||||
})
|
||||
log.Printf("mavend: ipc listening on %s", srv.Path())
|
||||
|
||||
if !locked && voiceW != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
if err := voiceW.server.Serve(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||
log.Printf("voice serve: %v", err)
|
||||
}
|
||||
}()
|
||||
log.Printf("mavend: voice listening on %s", voiceW.server.Addr())
|
||||
}
|
||||
|
||||
if !locked {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
tl.run(ctx)
|
||||
}()
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
factWorker.run(ctx)
|
||||
}()
|
||||
if evalWorker != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
evalWorker.run(ctx)
|
||||
}()
|
||||
}
|
||||
if feedWkr != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
feedWkr.run(ctx)
|
||||
}()
|
||||
}
|
||||
if crawlWkr != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
crawlWkr.run(ctx)
|
||||
}()
|
||||
}
|
||||
if voiceW != nil && voiceW.mcp != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
voiceW.mcp.run(ctx)
|
||||
}()
|
||||
}
|
||||
if voiceW != nil && voiceW.home != nil {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
voiceW.home.run(ctx)
|
||||
}()
|
||||
}
|
||||
startBackground(ctx, &wg, depsNow())
|
||||
}
|
||||
|
||||
<-ctx.Done()
|
||||
@@ -848,6 +616,125 @@ func waitWorkers(wg *sync.WaitGroup, d time.Duration) bool {
|
||||
}
|
||||
}
|
||||
|
||||
// Phraser defaults, applied when the config block leaves a field unset. They
|
||||
// are the daemon's, not the library's: phraser.Config carries no defaults of
|
||||
// its own, so an empty field here would reach llama-server as an empty flag.
|
||||
const (
|
||||
defaultLlamaBin = "llama-server"
|
||||
defaultPhraserListen = "127.0.0.1:0"
|
||||
defaultPhraserNCtx = 2048
|
||||
defaultPhraserTimeout = 30 * time.Second
|
||||
)
|
||||
|
||||
// wirePhraser builds the phrasing seam. No phraser block means the
|
||||
// deterministic stub, which is the floor and not an error: the daemon answers
|
||||
// without a model, in fixed words.
|
||||
func wirePhraser(ctx context.Context, cfg *config.Config) (phraser.Phraser, error) {
|
||||
if cfg.Phraser == nil {
|
||||
return phraser.NewStub(), nil
|
||||
}
|
||||
pc := phraser.Config{
|
||||
ModelPath: cfg.Phraser.ModelPath,
|
||||
BinPath: cfg.Phraser.BinPath,
|
||||
Listen: cfg.Phraser.Listen,
|
||||
NGpuLayers: cfg.Phraser.NGpuLayers,
|
||||
NCtx: cfg.Phraser.NCtx,
|
||||
CacheRAMMiB: cacheRAMMiB(cfg.Phraser.CacheRAMMiB),
|
||||
Timeout: time.Duration(cfg.Phraser.Timeout),
|
||||
LLMNudges: cfg.Phraser.LLMNudges,
|
||||
ContextBlock: contextBlockFn(cfg, time.Now),
|
||||
}
|
||||
if pc.BinPath == "" {
|
||||
pc.BinPath = defaultLlamaBin
|
||||
}
|
||||
if pc.Listen == "" {
|
||||
pc.Listen = defaultPhraserListen
|
||||
}
|
||||
if pc.NCtx <= 0 {
|
||||
pc.NCtx = defaultPhraserNCtx
|
||||
}
|
||||
if pc.Timeout <= 0 {
|
||||
pc.Timeout = defaultPhraserTimeout
|
||||
}
|
||||
return phraser.NewLLMPhraser(ctx, pc)
|
||||
}
|
||||
|
||||
// wireGatherer builds the nudge gatherer over the given rule set and applies
|
||||
// the configured quiet hours.
|
||||
func wireGatherer(st *store.Store, cfg *config.Config, rules []loop.Rule) *loop.Gatherer {
|
||||
g := loop.NewGatherer(st, rules)
|
||||
if cfg.QuietHours != nil {
|
||||
g.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
|
||||
}
|
||||
return g
|
||||
}
|
||||
|
||||
// wireDispatcher builds the delivery fan-out. Each sink stays nil unless its
|
||||
// config block is present, and a sink that fails to build fails the boot
|
||||
// rather than going quiet.
|
||||
//
|
||||
// A crashed prior run may have left "pending" delivery attempts (send may have
|
||||
// landed externally, then the process died before recording it). They are
|
||||
// reconciled to "unknown" here, before the tick loop resumes sending, so
|
||||
// nothing auto-resends into that ambiguity.
|
||||
func wireDispatcher(st *store.Store, cfg *config.Config, voiceW *voiceWiring) (*delivery.Dispatcher, error) {
|
||||
var ntfy delivery.Sink
|
||||
if cfg.Ntfy != nil {
|
||||
s, err := ntfysink.New(*cfg.Ntfy)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("wire ntfy sink: %w", err)
|
||||
}
|
||||
ntfy = s
|
||||
}
|
||||
var telegram delivery.Sink
|
||||
if cfg.Telegram != nil {
|
||||
s, err := telegramsink.New(*cfg.Telegram)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("wire telegram sink: %w", err)
|
||||
}
|
||||
telegram = s
|
||||
}
|
||||
var voiceSink delivery.Sink
|
||||
if voiceW != nil {
|
||||
voiceSink = voiceW.voiceSink
|
||||
}
|
||||
if _, err := st.ReconcileStaleDeliveryAttempts(context.Background(), time.Now()); err != nil {
|
||||
log.Printf("delivery outbox reconcile: %v", err)
|
||||
}
|
||||
return delivery.NewDispatcher(delivery.Config{
|
||||
Ntfy: ntfy,
|
||||
Telegram: telegram,
|
||||
Voice: voiceSink,
|
||||
Ack: st,
|
||||
Nudges: st,
|
||||
Reminders: st,
|
||||
Outbox: st,
|
||||
}), nil
|
||||
}
|
||||
|
||||
// wireTickLoop reads the loop's three intervals and its schedules out of the
|
||||
// config, so the two boot paths cannot disagree about them.
|
||||
func wireTickLoop(st *store.Store, gatherer *loop.Gatherer, dispatcher *delivery.Dispatcher, phr phraser.Phraser, rules []loop.Rule, cfg *config.Config) *tickLoop {
|
||||
return newTickLoop(st, gatherer, dispatcher, phr, rules,
|
||||
time.Duration(cfg.TickInterval),
|
||||
time.Duration(cfg.RepeatInterval),
|
||||
time.Duration(cfg.AutotuneInterval),
|
||||
cfg.Digest,
|
||||
routinesFromConfig(cfg.Routines),
|
||||
config.MorningRoutinesFromConfig(cfg.MorningRoutines),
|
||||
cfg.PatternProposals)
|
||||
}
|
||||
|
||||
// goWorker starts run on its own goroutine and registers it with wg, so
|
||||
// shutdown can wait for it inside workerGrace.
|
||||
func goWorker(wg *sync.WaitGroup, run func()) {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
run()
|
||||
}()
|
||||
}
|
||||
|
||||
// wireRules builds the nudge rule set, minus anything config turned off. The
|
||||
// drop is logged because a rule vanishing silently is indistinguishable from a
|
||||
// rule that is broken, and the next person to wonder why she stopped nudging
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
)
|
||||
|
||||
// correctionFragment reports that an utterance replaces a referent and states
|
||||
// nothing of its own: "нет, не маме, а папе" (V-576).
|
||||
//
|
||||
// Measured on the box 2026-08-06, that fragment routed to note and was filed.
|
||||
// It is not a repair either, because it names no intent, so parseRepair
|
||||
// declines it and repair.go is the wrong place to catch it. This is the note
|
||||
// path saying it has nothing to store.
|
||||
//
|
||||
// Three offline tests, all of them narrow on purpose. The sentence opens with a
|
||||
// refusal word from the lexicon, it carries the contrastive "а" that names the
|
||||
// replacement, and no token in it is a verb form. The verb test is what keeps
|
||||
// the rule off real notes: "нет, я не поеду, а останусь" says something, and a
|
||||
// Russian verb carries its own subject and tense.
|
||||
func correctionFragment(utterance string) bool {
|
||||
toks := repairTokens(strings.ToLower(strings.TrimSpace(utterance)))
|
||||
if len(toks) < 3 {
|
||||
return false
|
||||
}
|
||||
if !refusalWord(toks[0]) {
|
||||
return false
|
||||
}
|
||||
var negated, contrasted bool
|
||||
for _, tok := range toks[1:] {
|
||||
switch tok {
|
||||
case "не", "not":
|
||||
negated = true
|
||||
case "а", "but":
|
||||
contrasted = true
|
||||
}
|
||||
if morph.IsVerbForm(tok) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return negated && contrasted
|
||||
}
|
||||
|
||||
// refusalWord reports that a token is a one-word refusal. The lexicon set holds
|
||||
// phrases too ("не надо"), and those are not what opens a correction.
|
||||
func refusalWord(tok string) bool {
|
||||
for _, w := range lexicon.ConfirmNo() {
|
||||
if strings.ContainsRune(w, ' ') {
|
||||
continue
|
||||
}
|
||||
if w == tok {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
@@ -0,0 +1,117 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
func TestCorrectionFragment(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want bool
|
||||
}{
|
||||
{"нет, не маме, а папе", true},
|
||||
{"Нет, не маме — а папе", true},
|
||||
{"no, not mom, but dad", true},
|
||||
// States something of its own, so it is his to keep.
|
||||
{"нет, я не поеду, а останусь дома", false},
|
||||
{"нет", false},
|
||||
{"не маме, а папе", false}, // no refusal word opening it
|
||||
{"нет, маме и папе", false}, // nothing negated
|
||||
{"нет, не маме", false}, // nothing put in its place
|
||||
{"запомни что кофе закончился", false},
|
||||
}
|
||||
for _, c := range cases {
|
||||
if got := correctionFragment(c.utterance); got != c.want {
|
||||
t.Errorf("correctionFragment(%q) = %v, want %v", c.utterance, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func newNoteHandler(t *testing.T) (*reactiveHandler, *store.Store) {
|
||||
t.Helper()
|
||||
st := newTestStore(t)
|
||||
api := ipc.NewStoreAPI(st)
|
||||
now := time.Now()
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, tool.NewMatcher(api), 0.55, nil, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
}
|
||||
return h, st
|
||||
}
|
||||
|
||||
// TestNoteBodyIsTheUtterance — the stored body comes from the utterance, never
|
||||
// from Slots.Text, which the LLM router is free to write anything into (V-576).
|
||||
func TestNoteBodyIsTheUtterance(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newNoteHandler(t)
|
||||
|
||||
dec := router.Decision{
|
||||
Intent: router.IntentNote,
|
||||
Utterance: "купил хлеб и молоко",
|
||||
Slots: router.Slots{Text: "ты поедешь на дачу"},
|
||||
}
|
||||
if reply := h.applyAction(ctx, dec); reply != "" {
|
||||
t.Fatalf("applyAction = %q, want empty", reply)
|
||||
}
|
||||
notes, err := st.RecentNotes(ctx, 10)
|
||||
if err != nil {
|
||||
t.Fatalf("RecentNotes: %v", err)
|
||||
}
|
||||
if len(notes) != 1 || notes[0].Text != dec.Utterance {
|
||||
t.Fatalf("stored note = %+v, want body %q", notes, dec.Utterance)
|
||||
}
|
||||
}
|
||||
|
||||
// TestNoteBodyIsStable — the same utterance twice stores the same text.
|
||||
func TestNoteBodyIsStable(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newNoteHandler(t)
|
||||
|
||||
dec := router.Decision{Intent: router.IntentNote, Utterance: "кофе закончился"}
|
||||
h.applyAction(ctx, dec)
|
||||
h.applyAction(ctx, dec)
|
||||
|
||||
notes, err := st.RecentNotes(ctx, 10)
|
||||
if err != nil {
|
||||
t.Fatalf("RecentNotes: %v", err)
|
||||
}
|
||||
if len(notes) != 2 {
|
||||
t.Fatalf("notes = %d, want 2", len(notes))
|
||||
}
|
||||
if notes[0].Text != notes[1].Text || notes[0].Text != dec.Utterance {
|
||||
t.Fatalf("bodies differ: %q vs %q", notes[0].Text, notes[1].Text)
|
||||
}
|
||||
}
|
||||
|
||||
// TestCorrectionFragmentWritesNoNote — a correction with nothing behind it is
|
||||
// not a note, and she says so instead of filing it (V-576).
|
||||
func TestCorrectionFragmentWritesNoNote(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newNoteHandler(t)
|
||||
|
||||
dec := router.Decision{Intent: router.IntentNote, Utterance: "нет, не маме, а папе"}
|
||||
if reply := h.applyAction(ctx, dec); reply != nothingToCorrectReply {
|
||||
t.Fatalf("reply = %q, want %q", reply, nothingToCorrectReply)
|
||||
}
|
||||
notes, err := st.RecentNotes(ctx, 10)
|
||||
if err != nil {
|
||||
t.Fatalf("RecentNotes: %v", err)
|
||||
}
|
||||
if len(notes) != 0 {
|
||||
t.Fatalf("notes = %+v, want none", notes)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// A Praxis lifecycle failure used to return a hardcoded constant that named the
|
||||
// verb and never the service, so an outage, a refused token and a contract
|
||||
// mismatch all produced the identical sentence (Vikunja #588). The helpers and
|
||||
// the Hexis half of the same defect are in ecosystem_gap_test.go.
|
||||
|
||||
func TestPraxisLifecycle401NamesPraxis(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
praxis := newFakePraxis(t, fixturePraxisAttentionItems())
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
praxis.SetFault(401)
|
||||
reply := h.handlePraxisAct(ctx, praxisItemDec("resolve_item", "item_1"))
|
||||
if !strings.Contains(reply, servicePraxis) {
|
||||
t.Fatalf("praxis failure does not name Praxis: %q", reply)
|
||||
}
|
||||
if !strings.Contains(reply, phraser.A(phraser.EcoDenied, serviceVars(servicePraxis))) {
|
||||
t.Fatalf("401 from praxis: got %q, want the denied line", reply)
|
||||
}
|
||||
// The verb that did not happen is still said: the trace is the only other
|
||||
// place it exists and he is not reading the trace.
|
||||
if !strings.Contains(reply, "не получилось отметить сделанным.") {
|
||||
t.Errorf("reply dropped the operation that failed: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// TestPraxisLifecycleOutageDiffersFrom401 — the identity that was the bug.
|
||||
func TestPraxisLifecycleOutageDiffersFrom401(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
praxis := newFakePraxis(t, fixturePraxisAttentionItems())
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
praxis.SetFault(401)
|
||||
refused := h.handlePraxisAct(ctx, praxisItemDec("acknowledge_item", "item_1"))
|
||||
|
||||
h.ecosystem = &ecosystemWiring{praxis: newPraxisClient(unreachableURL)}
|
||||
outage := h.handlePraxisAct(ctx, praxisItemDec("acknowledge_item", "item_1"))
|
||||
|
||||
if refused == outage {
|
||||
t.Fatalf("a refused token and an outage still say the same thing: %q", refused)
|
||||
}
|
||||
if !strings.Contains(outage, phraser.A(phraser.EcoDown, serviceVars(servicePraxis))) {
|
||||
t.Fatalf("praxis outage: got %q, want the outage line naming Praxis", outage)
|
||||
}
|
||||
}
|
||||
@@ -2,8 +2,11 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"math"
|
||||
"net/http"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -31,6 +34,57 @@ func (f *fixedEmbedder) Embed(_ context.Context, text string) ([]float32, error)
|
||||
return v, nil
|
||||
}
|
||||
|
||||
// brokenEmbedder fails every call, which is what an ONNX session error looks
|
||||
// like from the query chain's side.
|
||||
type brokenEmbedder struct{}
|
||||
|
||||
func (brokenEmbedder) Dim() int { return 4 }
|
||||
func (brokenEmbedder) Close() error { return nil }
|
||||
func (brokenEmbedder) Embed(context.Context, string) ([]float32, error) {
|
||||
return nil, errors.New("onnx: session failed")
|
||||
}
|
||||
|
||||
// TestQueryEmbedFailureDoesNotStopTheChain — V-568. The embed source used to
|
||||
// claim the turn on an embedder error, so one failing EmbedQuery answered every
|
||||
// question below it with "не смогла ответить", including the ones the search
|
||||
// answers without an embedder at all. A source that could not look must pass.
|
||||
func TestQueryEmbedFailureDoesNotStopTheChain(t *testing.T) {
|
||||
const q = "почему небо голубое"
|
||||
|
||||
h, _ := searchHandler(t, searchBody, http.StatusOK)
|
||||
h.api = ipc.NewStoreAPI(newTestStore(t))
|
||||
h.recall = recallWiring{embedder: brokenEmbedder{}, minScore: 0.55, minMargin: 0.008}
|
||||
h.now = time.Now
|
||||
|
||||
// The embed source itself passes rather than claiming.
|
||||
turn := &queryTurn{dec: router.Decision{Intent: router.IntentQuery, Utterance: q}}
|
||||
if reply, ok := h.queryEmbed(context.Background(), turn); ok {
|
||||
t.Fatalf("queryEmbed claimed the turn on an embedder error: %q", reply)
|
||||
}
|
||||
|
||||
// And the whole chain still reaches the search below it.
|
||||
reply := askQuery(t, h, q)
|
||||
if !strings.Contains(reply, "рэлеевского рассеяния") {
|
||||
t.Fatalf("reply = %q, want the search answer", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The recall sources read the empty vector the failed embed left behind, and
|
||||
// neither of them may turn that into an answer: no vector means they could not
|
||||
// look, which is not the same as looking and finding nothing.
|
||||
func TestQueryRecallPassesWithoutAVector(t *testing.T) {
|
||||
h, _ := buildRecallHandler(t, "где молоко", []recallCase{
|
||||
{text: "молоко стоит в холодильнике", score: 0.90, kind: "note"},
|
||||
})
|
||||
turn := &queryTurn{dec: router.Decision{Intent: router.IntentQuery, Utterance: "где молоко"}}
|
||||
if reply, ok := h.queryMemory(context.Background(), turn); ok {
|
||||
t.Errorf("queryMemory claimed with no vector: %q", reply)
|
||||
}
|
||||
if reply, ok := h.queryNotes(context.Background(), turn); ok {
|
||||
t.Errorf("queryNotes claimed with no vector: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// scoreVec builds a unit vector whose cosine against the query vector
|
||||
// (1,0,0,0) is exactly score.
|
||||
func scoreVec(score float64) []float32 {
|
||||
|
||||
@@ -0,0 +1,137 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The floor, and it is the reason a destination is safe to add at all: a box
|
||||
// whose model is down names nothing, and naming nothing has to walk the chain
|
||||
// the way it walked before the field existed.
|
||||
func TestNoDestinationWalksTheWholeChain(t *testing.T) {
|
||||
walk, skipped := queryWalk(router.SourceUnknown, false)
|
||||
if len(skipped) != 0 {
|
||||
t.Errorf("skipped %d sources with no destination named, want none", len(skipped))
|
||||
}
|
||||
if len(walk) != len(querySources) {
|
||||
t.Fatalf("walk has %d sources, want the whole table of %d", len(walk), len(querySources))
|
||||
}
|
||||
for i := range walk {
|
||||
if walk[i].name != querySources[i].name {
|
||||
t.Fatalf("position %d is %q, want %q", i, walk[i].name, querySources[i].name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The 2026-08-07 defects, one per line. Each is a source that decides by seed
|
||||
// similarity claiming a turn that was never its own, and then answering it
|
||||
// because it has no lookup that could come back empty.
|
||||
func TestANamedDestinationSilencesTheOtherGuessers(t *testing.T) {
|
||||
cases := []struct {
|
||||
dest router.Source
|
||||
utterance string
|
||||
silenced string
|
||||
anchored bool // a stage 0 grammar named the destination
|
||||
}{
|
||||
{router.SourceWorld, "что такое TCP?", "weather", true},
|
||||
{router.SourceWorld, "сколько будет 17 на 23?", "weather", true},
|
||||
{router.SourceWorld, "кто такой Линус Торвальдс?", "personal", true},
|
||||
{router.SourceRecall, "какой у меня любимый язык?", "feeds", false},
|
||||
{router.SourceCalendar, "что в календаре на завтра?", "weather", true},
|
||||
}
|
||||
for _, c := range cases {
|
||||
walk, skipped := queryWalk(c.dest, c.anchored)
|
||||
if inWalk(walk, c.silenced) {
|
||||
t.Errorf("%q named %q: %q is still asked", c.utterance, c.dest, c.silenced)
|
||||
}
|
||||
if !inWalk(skipped, c.silenced) {
|
||||
t.Errorf("%q named %q: %q is missing from the record of who was skipped",
|
||||
c.utterance, c.dest, c.silenced)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Naming the world must not send the turn outside. His notes, his facts and the
|
||||
// boundary in front of them are the invariant CLAUDE.md states as "the owner's
|
||||
// data first, then the world", and a destination a model wrote must not be able
|
||||
// to reverse it.
|
||||
func TestNamingTheWorldStillReadsHisDataFirst(t *testing.T) {
|
||||
walk, _ := queryWalk(router.SourceWorld, true)
|
||||
for _, look := range []string{"fact-by-key", "embed", "memory", "notes"} {
|
||||
if !inWalk(walk, look) {
|
||||
t.Errorf("%q was dropped; only the sources that guess may be dropped", look)
|
||||
}
|
||||
}
|
||||
if posOf(walk, "notes") > posOf(walk, "search") {
|
||||
t.Error("search is asked before his notes are")
|
||||
}
|
||||
if posOf(walk, "search") < 0 {
|
||||
t.Fatal("search is not in the walk at all")
|
||||
}
|
||||
}
|
||||
|
||||
// The boundary belongs to his data, so naming recall keeps it. That is what
|
||||
// makes "какой у меня любимый язык?" answer "не нашла у тебя такой записи"
|
||||
// rather than reaching SearXNG once nothing local had it.
|
||||
func TestNamingRecallKeepsTheBoundary(t *testing.T) {
|
||||
walk, _ := queryWalk(router.SourceRecall, true)
|
||||
if !inWalk(walk, "personal") {
|
||||
t.Fatal("the personal boundary was skipped on a turn named for his own data")
|
||||
}
|
||||
if posOf(walk, "personal") > posOf(walk, "search") {
|
||||
t.Error("the boundary no longer sits in front of the world")
|
||||
}
|
||||
}
|
||||
|
||||
// The owner's call of 2026-08-09 (V-666): only a stage 0 grammar may take the
|
||||
// personal boundary off a turn. The routing heads and the resident model both
|
||||
// name a destination by inference, and an inferred SourceWorld would send a
|
||||
// question about him upstream. Every other guesser still goes.
|
||||
func TestOnlyAGrammarMayDropTheBoundary(t *testing.T) {
|
||||
walk, skipped := queryWalk(router.SourceWorld, false)
|
||||
if !inWalk(walk, "personal") {
|
||||
t.Error("an inferred destination took the boundary off the turn")
|
||||
}
|
||||
if !inWalk(skipped, "weather") {
|
||||
t.Error("weather is still asked; the rule covers the boundary alone")
|
||||
}
|
||||
if posOf(walk, "personal") > posOf(walk, "search") {
|
||||
t.Error("the boundary no longer sits in front of the world")
|
||||
}
|
||||
if anchored, _ := queryWalk(router.SourceWorld, true); inWalk(anchored, "personal") {
|
||||
t.Error(`a grammar named the world and the boundary stayed: ` +
|
||||
`"кто такой Линус Торвальдс?" is answered "не нашла у тебя такой записи" again`)
|
||||
}
|
||||
}
|
||||
|
||||
// Whatever the destination, the walk is a subsequence of the table. Every
|
||||
// comment on that table argues an order between two sources, and none of those
|
||||
// reasons is about this field.
|
||||
func TestTheWalkNeverReordersTheTable(t *testing.T) {
|
||||
for _, dest := range append([]router.Source{router.SourceUnknown}, router.Sources...) {
|
||||
walk, skipped := queryWalk(dest, true)
|
||||
if len(walk)+len(skipped) != len(querySources) {
|
||||
t.Errorf("%q: %d walked + %d skipped, want %d", dest, len(walk), len(skipped), len(querySources))
|
||||
}
|
||||
last := -1
|
||||
for _, s := range walk {
|
||||
at := posOf(querySources, s.name)
|
||||
if at <= last {
|
||||
t.Errorf("%q: %q is out of table order", dest, s.name)
|
||||
}
|
||||
last = at
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func inWalk(list []querySource, name string) bool { return posOf(list, name) >= 0 }
|
||||
|
||||
func posOf(list []querySource, name string) int {
|
||||
for i, s := range list {
|
||||
if s.name == name {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
@@ -22,7 +22,7 @@ func TestReactiveNotesReminders(t *testing.T) {
|
||||
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
matcher := tool.NewMatcher(api)
|
||||
rtr := buildRouter(emb, matcher, 0.55, nil)
|
||||
rtr := buildRouter(emb, matcher, 0.55, nil, nil)
|
||||
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
@@ -104,7 +104,7 @@ func TestSpokenTaskCaptureFilesATask(t *testing.T) {
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, matcher, 0.55, nil),
|
||||
router: buildRouter(emb, matcher, 0.55, nil, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
|
||||
@@ -0,0 +1,209 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// A reminder commits only when three things are answered: what to say, what
|
||||
// time to say it, and what day (owner's rule, 2026-08-06, V-579). Anything
|
||||
// missing is asked about, and nothing missing is filled from the clock.
|
||||
//
|
||||
// "напомни завтра в 3 заказать цветы" has the what and the day and an hour that
|
||||
// could be either half of the day, so she asks which 3. "напомни в 9 вечера
|
||||
// разгрузить стиралку" has the what and an unambiguous hour and no day, so she
|
||||
// asks which day. Today being a valid reading is not the same as him saying it.
|
||||
//
|
||||
// Two things are already whole and are not asked about. A time that admits one
|
||||
// reading is not queried for its half of the day, so "завтра в 15:00" commits.
|
||||
// And an interval is an instant, so "через час" carries all three by itself.
|
||||
type whenGap string
|
||||
|
||||
const (
|
||||
whenComplete whenGap = ""
|
||||
whenNoHour whenGap = "hour"
|
||||
whenAmbiguousHour whenGap = "part_of_day"
|
||||
whenNoDay whenGap = "day"
|
||||
)
|
||||
|
||||
// whenGapOf reads the request and names the first thing about its time that he
|
||||
// has not said. hasTime is whether a parser could read an instant out of it,
|
||||
// which is necessary and not sufficient: the parser answers a dayless "в 9"
|
||||
// with a day it picked.
|
||||
func whenGapOf(text string, hasTime bool) whenGap {
|
||||
if !router.NamesAnHour(text) {
|
||||
return whenNoHour
|
||||
}
|
||||
if router.NamesAnInterval(text) {
|
||||
return whenComplete
|
||||
}
|
||||
if !hasTime {
|
||||
return whenNoHour
|
||||
}
|
||||
if router.HourIsAmbiguous(text) {
|
||||
return whenAmbiguousHour
|
||||
}
|
||||
if !router.NamesADay(text) {
|
||||
return whenNoDay
|
||||
}
|
||||
return whenComplete
|
||||
}
|
||||
|
||||
// whenQuestion is what she asks for each gap. Every one of them opens with the
|
||||
// current time, because she is reasoning from it and he cannot check that
|
||||
// reasoning unless he hears it. The hour deck varies with the attempt, like
|
||||
// every other slot; the other two say one thing and there is only one way to
|
||||
// say it.
|
||||
//
|
||||
// taken is what his last turn added, in his own words, and it goes between the
|
||||
// clock and the question (V-593). It is empty whenever his turn moved nothing
|
||||
// forward, which is the case where repeating the question verbatim is honest.
|
||||
func whenQuestion(gap whenGap, attempt int, now time.Time, taken string) (string, bool) {
|
||||
clock := fmt.Sprintf("Сейчас %s.", now.Format("15:04"))
|
||||
if taken != "" {
|
||||
clock += " " + taken
|
||||
}
|
||||
switch gap {
|
||||
case whenNoHour:
|
||||
q, ok := clarifyQuestionFor(dialogue.SlotTime, attempt)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
return clock + " " + q, true
|
||||
case whenAmbiguousHour:
|
||||
return clock + " Это утра или вечера?", true
|
||||
case whenNoDay:
|
||||
return clock + " В какой день?", true
|
||||
}
|
||||
return "", false
|
||||
}
|
||||
|
||||
// whenKnown — the three things he has to say about the time, and whether the
|
||||
// words so far say them. Read off the same predicates whenGapOf reads, so the
|
||||
// two cannot disagree about what is still open.
|
||||
type whenKnown struct{ hour, part, day bool }
|
||||
|
||||
func whenKnownOf(text string, hasTime bool) whenKnown {
|
||||
if !router.NamesAnHour(text) {
|
||||
return whenKnown{}
|
||||
}
|
||||
if router.NamesAnInterval(text) {
|
||||
return whenKnown{hour: true, part: true, day: true}
|
||||
}
|
||||
if !hasTime {
|
||||
return whenKnown{}
|
||||
}
|
||||
return whenKnown{
|
||||
hour: true,
|
||||
part: !router.HourIsAmbiguous(text),
|
||||
day: router.NamesADay(text),
|
||||
}
|
||||
}
|
||||
|
||||
// movedForward reports whether b says something a did not.
|
||||
func (a whenKnown) movedForward(b whenKnown) bool {
|
||||
return (!a.hour && b.hour) || (!a.part && b.part) || (!a.day && b.day)
|
||||
}
|
||||
|
||||
// whenTakenLine — the acknowledgement in front of a re-ask, in the words he
|
||||
// just used (V-593).
|
||||
//
|
||||
// It is an echo and never a restatement, for the same reason the fact
|
||||
// confirmation is (V-592): a 1.7B asked to say a Russian sentence back invents.
|
||||
// Its only job is evidence that the turn between two asks was heard, so after
|
||||
// "на 9" and then "на завтра" she does not ask "утра или вечера?" twice
|
||||
// byte-identically while he wonders whether the microphone is on.
|
||||
func whenTakenLine(text string) string {
|
||||
text = strings.TrimSpace(text)
|
||||
text = strings.TrimRight(text, " \t.,!?;:")
|
||||
if text == "" {
|
||||
return ""
|
||||
}
|
||||
return "Поняла: " + text + "."
|
||||
}
|
||||
|
||||
// whenTextOf is everything he has said about when, the original request plus
|
||||
// every answer he has given to a question about it.
|
||||
//
|
||||
// The answers are kept apart from the utterance on purpose. The utterance is
|
||||
// the reminder's payload, so folding "завтра" into it would have her read the
|
||||
// day back to him at the time she says it. And a time answer has to be read
|
||||
// against the request rather than alone: "завтра" names no hour, and the hour
|
||||
// it belongs to is the one she is already holding.
|
||||
func whenTextOf(q *dialogue.PendingQuestion) string {
|
||||
if q.WhenText == "" {
|
||||
return q.Utterance
|
||||
}
|
||||
return strings.TrimSpace(q.Utterance + " " + q.WhenText)
|
||||
}
|
||||
|
||||
// slotStillMissing reports whether a slot is still open. Every slot but the
|
||||
// reminder's time is open when it is empty; the time is open until all three of
|
||||
// what he must say about it are said.
|
||||
func slotStillMissing(slot dialogue.Slot, utterance string, s dialogue.Slots) bool {
|
||||
if len(dialogue.StillMissing([]dialogue.Slot{slot}, s)) > 0 {
|
||||
return true
|
||||
}
|
||||
return slot == dialogue.SlotTime && whenGapOf(utterance, s.HasTime) != whenComplete
|
||||
}
|
||||
|
||||
// readWhen reads the instant out of what he has said about the time, newest
|
||||
// statement first.
|
||||
//
|
||||
// The request plus his latest answer is tried before the whole history, and
|
||||
// that order is what makes a correction win: "нет, сегодня в 15:00" after "в
|
||||
// 11:00" must land on 15:00, and a parser reading left to right off the joined
|
||||
// history would find the 11 he just took back. The history is the fallback,
|
||||
// because an answer often completes an earlier one rather than replacing it -
|
||||
// "вечера" says which 9, and alone it names no hour at all.
|
||||
func (h *reactiveHandler) readWhen(ctx context.Context, intent router.Intent, q *dialogue.PendingQuestion, text string) (time.Time, bool) {
|
||||
latest := strings.TrimSpace(q.Utterance + " " + text)
|
||||
if router.NamesAnHour(text) {
|
||||
if w := h.extractor.Extract(ctx, intent, latest, h.now()); w.HasTime {
|
||||
return w.Time, true
|
||||
}
|
||||
}
|
||||
if w := h.extractor.Extract(ctx, intent, whenTextOf(q), h.now()); w.HasTime {
|
||||
return w.Time, true
|
||||
}
|
||||
return time.Time{}, false
|
||||
}
|
||||
|
||||
// asksAboutTime reports whether the parked question is one about when.
|
||||
func asksAboutTime(missing []dialogue.Slot) bool {
|
||||
for _, s := range missing {
|
||||
if s == dialogue.SlotTime {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// stillOpen reports whether any of the slots she asked about is still unsaid.
|
||||
func stillOpen(missing []dialogue.Slot, utterance string, s dialogue.Slots) bool {
|
||||
for _, slot := range missing {
|
||||
if slotStillMissing(slot, utterance, s) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// stillMissingFor is missingFor's engine, in wantedSlots order. It reads the
|
||||
// utterance as well as the slots, which plain StillMissing cannot: whether an
|
||||
// hour is ambiguous is a fact about the words, not about the instant they
|
||||
// parsed to.
|
||||
func stillMissingFor(intent router.Intent, utterance string, s dialogue.Slots) []dialogue.Slot {
|
||||
var out []dialogue.Slot
|
||||
for _, want := range wantedSlots[intent] {
|
||||
if slotStillMissing(want, utterance, s) {
|
||||
out = append(out, want)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
@@ -9,6 +9,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -35,6 +36,11 @@ type routedTurn struct {
|
||||
utterance string
|
||||
intent router.Intent
|
||||
at time.Time
|
||||
// traceID — the persisted trace of this turn, stamped after the fact by
|
||||
// stampLastTurn. 0 when nothing persisted, and then a spoken correction
|
||||
// still teaches the classifier: the durable label is the half that needs a
|
||||
// row to point at (V-636).
|
||||
traceID int64
|
||||
}
|
||||
|
||||
// repairWindow — how long a turn stays correctable. Long enough that he can
|
||||
@@ -54,6 +60,13 @@ const repairWindow = 5 * time.Minute
|
||||
// said. The set's note in lexicon_ru_v1.json carries the same reasoning.
|
||||
var repairMarkers = lexicon.RepairMarkers()
|
||||
|
||||
// repairNegatives — "she got it wrong" with no target. Matched against the whole
|
||||
// utterance, because these are complete sentences and the markers above are
|
||||
// fragments: "это не" needs an intent word after it, "не так поняла" does not.
|
||||
// Substring matching here would claim "не так" out of any sentence containing it
|
||||
// (V-636).
|
||||
var repairNegatives = lexicon.RepairNegatives()
|
||||
|
||||
// repairIntents — the words he uses for each intent, as dictionary forms. They
|
||||
// used to be prefixes ("заметк"), which is what a prefix list costs: "команд"
|
||||
// also matched "командировка", and "факт" matched "фактически". morph.SameWord
|
||||
@@ -147,6 +160,18 @@ func (h *reactiveHandler) recordTurn(utterance string, intent router.Intent) {
|
||||
h.lastRouted = &routedTurn{utterance: utterance, intent: intent, at: h.now()}
|
||||
}
|
||||
|
||||
// stampLastTurn attaches the trace id to the turn a correction would point at.
|
||||
// It cannot be done in recordTurn: the trace is written when the turn ends, and
|
||||
// recordTurn runs in the middle of it.
|
||||
func (h *reactiveHandler) stampLastTurn(utterance string, traceID int64) {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
if h.lastRouted == nil || h.lastRouted.utterance != utterance {
|
||||
return
|
||||
}
|
||||
h.lastRouted.traceID = traceID
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) takeLastTurn() *routedTurn {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
@@ -157,6 +182,56 @@ func (h *reactiveHandler) takeLastTurn() *routedTurn {
|
||||
return last
|
||||
}
|
||||
|
||||
// resolveUntargetedRepair handles the cheap half of a spoken correction: he says
|
||||
// she got it wrong and does not say what it should have been (V-636).
|
||||
//
|
||||
// It is worth having on its own. V-630 made the target optional on the web for
|
||||
// the same reason: a turn marked wrong with no target is a usable negative, and
|
||||
// requiring the target would cost the correction he was willing to give. Voice
|
||||
// needs it more than the web does — naming an intent aloud means saying
|
||||
// "заметка" or "факт", which is Maven's vocabulary and not his.
|
||||
//
|
||||
// Nothing is redone and the classifier is not taught. There is no target, so
|
||||
// there is nothing to redo it as and nothing to teach. Only the label is written,
|
||||
// and she says so, because a correction he cannot see reads as one that was
|
||||
// dropped.
|
||||
func (h *reactiveHandler) resolveUntargetedRepair(ctx context.Context, text string) (string, bool) {
|
||||
if !isRepairNegative(text) {
|
||||
return "", false
|
||||
}
|
||||
last := h.takeLastTurn()
|
||||
if last == nil || h.now().Sub(last.at) > repairWindow {
|
||||
return "", false
|
||||
}
|
||||
if last.traceID == 0 {
|
||||
// No row to point at, so there is no label to write and nothing this
|
||||
// resolver can do. Routing the words normally is the honest outcome.
|
||||
return "", false
|
||||
}
|
||||
h.labelCorrection(ctx, last, "")
|
||||
log.Printf("voice: repair — %q marked wrong, no target given", last.utterance)
|
||||
return phraser.A(phraser.RepairNoted, nil), true
|
||||
}
|
||||
|
||||
// isRepairNegative matches the whole utterance, minus a leading "нет" and any
|
||||
// trailing punctuation. "нет, не так" is the shortest one he says.
|
||||
func isRepairNegative(utterance string) bool {
|
||||
s := strings.ToLower(strings.TrimSpace(utterance))
|
||||
s = strings.TrimRight(s, " .!?")
|
||||
for _, p := range []string{"нет,", "нет", "no,", "no"} {
|
||||
if rest := strings.TrimSpace(strings.TrimPrefix(s, p)); rest != s && rest != "" {
|
||||
s = rest
|
||||
break
|
||||
}
|
||||
}
|
||||
for _, n := range repairNegatives {
|
||||
if s == n {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// resolveRepair handles a spoken correction of the previous turn: teach the
|
||||
// classifier, redo the request under the corrected intent, and say so.
|
||||
func (h *reactiveHandler) resolveRepair(ctx context.Context, text string) (string, bool) {
|
||||
@@ -182,6 +257,7 @@ func (h *reactiveHandler) resolveRepair(ctx context.Context, text string) (strin
|
||||
learned = false
|
||||
}
|
||||
log.Printf("voice: repair — %q was %s, corrected to %s (learned=%v)", last.utterance, last.intent, corrected, learned)
|
||||
h.labelCorrection(ctx, last, string(corrected))
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: last.utterance,
|
||||
@@ -207,3 +283,24 @@ func repairLine(say string, learned bool) string {
|
||||
}
|
||||
return "поняла, это " + say + " — запомнила."
|
||||
}
|
||||
|
||||
// labelCorrection promotes a spoken correction into routing_labels, the same
|
||||
// table the /chat gesture writes (V-630, V-636).
|
||||
//
|
||||
// Two sinks and not one, because they keep different things. CorrectMisroute
|
||||
// appends a classifier seed, which is what makes the NEXT turn better today.
|
||||
// The label is what a fitted head trains on later, it survives the 14-day
|
||||
// transcript, and until now only the web produced any. A sample that only ever
|
||||
// held typed turns would skew to whatever he happens to be at a keyboard for,
|
||||
// and voice is where the hard cases are.
|
||||
//
|
||||
// Best-effort and silent. He has already been told the correction landed, and a
|
||||
// second sink failing is not his problem to hear about.
|
||||
func (h *reactiveHandler) labelCorrection(ctx context.Context, last *routedTurn, shouldBe string) {
|
||||
if h.api == nil || last == nil || last.traceID == 0 {
|
||||
return
|
||||
}
|
||||
if err := h.api.CorrectTurn(ctx, last.traceID, shouldBe); err != nil {
|
||||
log.Printf("voice: repair: could not label trace %d: %v", last.traceID, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func TestParseRepairReadsTheCorrectedIntent(t *testing.T) {
|
||||
@@ -149,3 +150,95 @@ func TestRepairIntentWordCollisions(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// V-636. A spoken correction lands in the same table the /chat gesture writes,
|
||||
// so the sample is not limited to the turns he happened to type.
|
||||
func TestSpokenCorrectionWritesTheLabel(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(256)
|
||||
h.recall.embedder = emb
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(emb), Extractor: h.extractor})
|
||||
ctx := context.Background()
|
||||
|
||||
id, err := st.WriteRoutingTrace(ctx, store.RoutingTrace{
|
||||
Ts: h.now(), Utterance: "купить хлеб", Intent: "fact", Source: "tap:voice",
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
h.stampLastTurn("купить хлеб", id)
|
||||
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); !handled {
|
||||
t.Fatal("the correction was not handled")
|
||||
}
|
||||
labels, err := st.RoutingLabels(ctx, 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(labels) != 1 || labels[0].Was != "fact" || labels[0].ShouldBe != "note" {
|
||||
t.Fatalf("labels %+v: the spoken correction did not land as a pair", labels)
|
||||
}
|
||||
}
|
||||
|
||||
// The cheap half, which voice needs more than the web does: naming an intent
|
||||
// aloud means saying "заметка", which is her vocabulary and not his.
|
||||
func TestUntargetedSpokenCorrection(t *testing.T) {
|
||||
h, st, now := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
seed := func(utterance string) int64 {
|
||||
id, err := st.WriteRoutingTrace(ctx, store.RoutingTrace{
|
||||
Ts: h.now(), Utterance: utterance, Intent: "query", Source: "tap:voice",
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h.recordTurn(utterance, router.IntentQuery)
|
||||
h.stampLastTurn(utterance, id)
|
||||
return id
|
||||
}
|
||||
|
||||
seed("поужинал")
|
||||
reply, handled := h.resolveUntargetedRepair(ctx, "нет, не так")
|
||||
if !handled {
|
||||
t.Fatal("«нет, не так» was not read as a correction")
|
||||
}
|
||||
if reply == "" {
|
||||
t.Error("a correction he cannot hear reads as one that was dropped")
|
||||
}
|
||||
labels, err := st.RoutingLabels(ctx, 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(labels) != 1 || labels[0].ShouldBe != "" || labels[0].Was != "query" {
|
||||
t.Fatalf("labels %+v: want one untargeted negative naming what she chose", labels)
|
||||
}
|
||||
|
||||
// Outside the window it is a fresh sentence, not a verdict.
|
||||
seed("поужинал ещё раз")
|
||||
*now = now.Add(repairWindow + time.Minute)
|
||||
if _, handled := h.resolveUntargetedRepair(ctx, "не так"); handled {
|
||||
t.Error("a correction outside the window was handled")
|
||||
}
|
||||
}
|
||||
|
||||
// Whole-utterance, never a substring. This is the difference between the
|
||||
// negatives and the markers, and getting it wrong would claim any sentence with
|
||||
// "не так" in it.
|
||||
func TestRepairNegativeIsTheWholeUtterance(t *testing.T) {
|
||||
for _, s := range []string{
|
||||
"не так поняла", "нет, не так", "ты ошиблась", "неправильно", "wrong", "no, that was wrong",
|
||||
} {
|
||||
if !isRepairNegative(s) {
|
||||
t.Errorf("%q is not read as a correction", s)
|
||||
}
|
||||
}
|
||||
for _, s := range []string{
|
||||
"это не важно", "напомни не так поздно", "а не завтра", "не так, а вот так — это заметка",
|
||||
"", "нет",
|
||||
} {
|
||||
if isRepairNegative(s) {
|
||||
t.Errorf("%q was read as a correction", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -22,7 +22,7 @@ func newLLMReplier(c phraser.Completer, block func() string) *llmReplier {
|
||||
|
||||
// Reply never fails: a clarify, a model error and an unusable generation all
|
||||
// answer from the stub, which is what keeps a turn from breaking on the model.
|
||||
func (r *llmReplier) Reply(d router.Decision) string {
|
||||
func (r *llmReplier) Reply(ctx context.Context, d router.Decision) string {
|
||||
if d.Clarify {
|
||||
// The deck, not the stub's single sentence: a clarify she cannot turn
|
||||
// into a question is the line he hears most often when she misses him,
|
||||
@@ -31,14 +31,22 @@ func (r *llmReplier) Reply(d router.Decision) string {
|
||||
// a generation to say something this small.
|
||||
return clarifyMissedLine(d)
|
||||
}
|
||||
out, err := r.p.PhraseReply(context.Background(), d)
|
||||
if d.Intent == router.IntentFact {
|
||||
// A captured fact is confirmed by echoing him, and the model is not
|
||||
// asked (V-592). It has nothing to phrase FROM: replyContext hands it
|
||||
// "записала факт: water \"drank\"", so every Russian word in the reply
|
||||
// was the model's own invention, and on 2026-08-06 that was "Проверила,
|
||||
// что ты выпел стакан воды" for "я выпил воды".
|
||||
return phraser.FactAck(d.Utterance)
|
||||
}
|
||||
out, err := r.p.PhraseReply(ctx, d)
|
||||
if err != nil || out == "" {
|
||||
return r.stub.Reply(d)
|
||||
return r.stub.Reply(ctx, d)
|
||||
}
|
||||
// The persona checks, on the live path (personaguard.go). A reply that
|
||||
// leaks reasoning or calls him "вы" is worse than a flat one.
|
||||
if _, ok := guardSpoken("reply", out); !ok {
|
||||
return r.stub.Reply(d)
|
||||
return r.stub.Reply(ctx, d)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -22,7 +22,7 @@ func (s stubCompleter) Complete(_ context.Context, _ llm.Req) (string, error) {
|
||||
|
||||
func TestLLMReplierPassesTheModelReplyThrough(t *testing.T) {
|
||||
r := newLLMReplier(stubCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
|
||||
got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
|
||||
got := r.Reply(context.Background(), router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
|
||||
if got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, want %q", got, "записала, кофе закончился")
|
||||
}
|
||||
@@ -42,7 +42,7 @@ func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
|
||||
// the clarify deck rather than the stub's single sentence.
|
||||
func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
|
||||
r := newLLMReplier(stubCompleter{out: "я всё поняла"}, nil)
|
||||
got := r.Reply(router.Decision{Clarify: true, Utterance: "мгм"})
|
||||
got := r.Reply(context.Background(), router.Decision{Clarify: true, Utterance: "мгм"})
|
||||
if got == "я всё поняла" {
|
||||
t.Fatal("a clarify must not be phrased by the model")
|
||||
}
|
||||
@@ -50,7 +50,7 @@ func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
|
||||
t.Errorf("on clarify: got %q, want %q", got, want)
|
||||
}
|
||||
// Two different misses do not sound identical.
|
||||
if same := r.Reply(router.Decision{Clarify: true, Utterance: "а"}); same == got {
|
||||
if same := r.Reply(context.Background(), router.Decision{Clarify: true, Utterance: "а"}); same == got {
|
||||
t.Log("two utterances hashed to the same line, which is allowed but should be rare")
|
||||
}
|
||||
}
|
||||
@@ -60,14 +60,14 @@ func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
|
||||
// produce, which is the same claim without pinning one wording.
|
||||
func assertAck(t *testing.T, r *llmReplier, d router.Decision, key, what string) {
|
||||
t.Helper()
|
||||
if got := r.Reply(d); !phraser.IsAck(key, nil, got) {
|
||||
if got := r.Reply(context.Background(), d); !phraser.IsAck(key, nil, got) {
|
||||
t.Errorf("on %s: got %q, want a %q line", what, got, key)
|
||||
}
|
||||
}
|
||||
|
||||
func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
|
||||
t.Helper()
|
||||
got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
|
||||
got, want := r.Reply(context.Background(), d), voice.NewStubReplier().Reply(context.Background(), d)
|
||||
if got != want {
|
||||
t.Errorf("on %s: got %q, want stub %q", what, got, want)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,178 @@
|
||||
// mavend/routingtrace.go — persisting the per-turn decision record (V-629).
|
||||
//
|
||||
// internal/decision keeps a 25-turn in-memory ring and persisted nothing, on the
|
||||
// argument that a turn record is read minutes later or never. The owner reversed
|
||||
// that on 06-08-2026, because the routing heads (V-546) cannot be fitted or
|
||||
// calibrated without real utterances and there is no other source of them. The
|
||||
// reversal is written down in docs/plans/21-persisting-the-routing-trace.md.
|
||||
//
|
||||
// The ring stays. It is what /trace reads, it is fast, and it is what a test that
|
||||
// wired no store still gets. This file is the second sink beside it, and it is
|
||||
// nil unless the daemon has a database — no store, no trace, no error.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"log"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// traceWriter is the seam the handler persists through. store.Store satisfies
|
||||
// it. nil ⇒ the ring is the only sink, which is the pre-V-629 behaviour exactly.
|
||||
type traceWriter interface {
|
||||
WriteRoutingTrace(ctx context.Context, tr store.RoutingTrace) (int64, error)
|
||||
}
|
||||
|
||||
// traceSink wraps the store, or returns nil when there is none. A typed nil
|
||||
// pointer assigned straight into the interface would be non-nil and would panic
|
||||
// on the first turn, which is the classic shape of this bug.
|
||||
func traceSink(s *store.Store) traceWriter {
|
||||
if s == nil {
|
||||
return nil
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// The trace id rides the context, the same seam querysource.go uses and for the
|
||||
// same reason: handleText answers every reach through one string, and threading
|
||||
// a second value through the whole action dispatch would change a signature the
|
||||
// mic, telegram and the web all share. A caller that wants the id asks for a
|
||||
// sink; the mic path does not, and pays nothing.
|
||||
type traceIDKey struct{}
|
||||
|
||||
type traceIDSink struct {
|
||||
mu sync.Mutex
|
||||
id int64
|
||||
}
|
||||
|
||||
func (s *traceIDSink) note(id int64) {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
s.id = id
|
||||
}
|
||||
|
||||
// ID is the persisted trace for the turn, or 0 when nothing was persisted.
|
||||
func (s *traceIDSink) ID() int64 {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
return s.id
|
||||
}
|
||||
|
||||
// withTraceIDSink returns a context that collects the persisted trace id, and
|
||||
// the sink to read after the turn has answered.
|
||||
func withTraceIDSink(ctx context.Context) (context.Context, *traceIDSink) {
|
||||
sink := &traceIDSink{}
|
||||
return context.WithValue(ctx, traceIDKey{}, sink), sink
|
||||
}
|
||||
|
||||
func noteTraceID(ctx context.Context, id int64) {
|
||||
if sink, ok := ctx.Value(traceIDKey{}).(*traceIDSink); ok {
|
||||
sink.note(id)
|
||||
}
|
||||
}
|
||||
|
||||
// pruneTracesOnStart enforces retention once at wiring time. Pruning on write
|
||||
// alone is not enough: a box that goes quiet for a month keeps every row until
|
||||
// the next sixty-fourth turn, and "kept for fourteen days" would then be true
|
||||
// only of a box in daily use. Called for its effect and never blocks a start.
|
||||
func pruneTracesOnStart(s *store.Store, now time.Time) {
|
||||
if s == nil {
|
||||
return
|
||||
}
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
defer cancel()
|
||||
if err := s.PruneRoutingTraces(ctx, now.Add(-store.RoutingTraceRetention)); err != nil {
|
||||
log.Printf("routing trace: prune on start: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// persistDecision writes one finished record. It takes the same *decision.Record
|
||||
// the ring takes, so the two sinks cannot disagree about what the turn did.
|
||||
//
|
||||
// Errors are logged and swallowed. A trace is diagnostic and training data, and
|
||||
// a failed insert must never change what the owner hears.
|
||||
func (h *reactiveHandler) persistDecision(turnCtx context.Context, rec *decision.Record, src turnSource) {
|
||||
ctx := turnCtx
|
||||
if h.traces == nil || rec == nil || strings.TrimSpace(rec.Utterance) == "" {
|
||||
return
|
||||
}
|
||||
// Detached from the turn's context, and bounded on its own. Two reasons, and
|
||||
// the first is the one that matters: the turn is over by the time this runs,
|
||||
// so a caller that hung up or timed out would cancel the insert, and the turn
|
||||
// he abandoned halfway is exactly the one worth having. The second is that a
|
||||
// write must not hold the reply, so it gets a second and no more.
|
||||
ctx, cancel := context.WithTimeout(context.WithoutCancel(ctx), time.Second)
|
||||
defer cancel()
|
||||
claims, err := json.Marshal(rec.Claims)
|
||||
if err != nil {
|
||||
log.Printf("routing trace: marshal claims: %v", err)
|
||||
return
|
||||
}
|
||||
tr := store.RoutingTrace{
|
||||
Ts: rec.Ts,
|
||||
Utterance: rec.Utterance,
|
||||
Source: string(src),
|
||||
Winner: rec.Winner,
|
||||
Intent: wonIntent(rec),
|
||||
ClaimedBeforeHead: claimedBeforeHead(rec),
|
||||
EncoderID: h.encoderID,
|
||||
Outcome: wonAt(rec, decision.StageAction),
|
||||
Claims: claims,
|
||||
}
|
||||
id, err := h.traces.WriteRoutingTrace(ctx, tr)
|
||||
if err != nil {
|
||||
log.Printf("routing trace: write: %v", err)
|
||||
return
|
||||
}
|
||||
// The id goes back to whoever asked for it, so /chat can offer a correction
|
||||
// on the turn it is already showing (V-630). Noted on the ORIGINAL context,
|
||||
// not the detached one above: the sink belongs to the caller's turn.
|
||||
noteTraceID(turnCtx, id)
|
||||
// And the spoken path, which has no reply to hang a badge on: a correction
|
||||
// said out loud points at the previous turn, so it needs that turn's row
|
||||
// (V-636, repair.go).
|
||||
h.stampLastTurn(rec.Utterance, id)
|
||||
}
|
||||
|
||||
// wonIntent — what the winning claimant made the turn. Read from the claim
|
||||
// rather than from the route, because a pre-route resolver wins without routing
|
||||
// and its intent is the honest answer to "what was this turn".
|
||||
func wonIntent(rec *decision.Record) string {
|
||||
for _, c := range rec.Claims {
|
||||
if c.Outcome == decision.Won && c.Intent != "" {
|
||||
return c.Intent
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// wonAt — the claimant that won at one stage. The action stage is what actually
|
||||
// produced the reply, which is a different question from what was routed: a
|
||||
// route that reached a gap and a route that ran are not the same turn.
|
||||
func wonAt(rec *decision.Record, stage string) string {
|
||||
for _, c := range rec.Claims {
|
||||
if c.Stage == stage && c.Outcome == decision.Won {
|
||||
return c.Claimant
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// claimedBeforeHead — a pre-route resolver or a stage-0 grammar answered, so the
|
||||
// turn teaches nothing about the classifier. Those are a large share of real
|
||||
// traffic, and fitting a head on them would fit it to the grammars rather than
|
||||
// to him. Recorded per turn rather than filtered on write, because which share
|
||||
// that is happens to be the number V-632 needs to know.
|
||||
func claimedBeforeHead(rec *decision.Record) bool {
|
||||
stage, _, ok := strings.Cut(rec.Winner, ":")
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
return stage == decision.StagePreRoute || stage == decision.StageZero
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// A real turn leaves a persisted trace, not only a ring entry. This is the whole
|
||||
// of V-629: without one there is nothing to fit the routing heads from.
|
||||
func TestTurnPersistsTrace(t *testing.T) {
|
||||
ring := decision.NewRing()
|
||||
h := traceHandler(t, ring)
|
||||
h.traces = traceSink(h.dataStore)
|
||||
h.encoderID = "hash-1024"
|
||||
|
||||
if reply := h.handleText(context.Background(), "web", "сколько сейчас времени"); reply == "" {
|
||||
t.Fatal("turn produced no reply")
|
||||
}
|
||||
got, err := h.dataStore.RecentRoutingTraces(context.Background(), 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("persisted %d traces, want 1", len(got))
|
||||
}
|
||||
tr := got[0]
|
||||
if tr.Utterance != "сколько сейчас времени" {
|
||||
t.Errorf("utterance %q", tr.Utterance)
|
||||
}
|
||||
if tr.Source != string(sourceText) {
|
||||
t.Errorf("source %q, want %q", tr.Source, sourceText)
|
||||
}
|
||||
// A stage-0 clock rule answers this one, so the turn teaches the classifier
|
||||
// nothing and the trace has to say so.
|
||||
if !tr.ClaimedBeforeHead {
|
||||
t.Errorf("claimed_before_head false on winner %q", tr.Winner)
|
||||
}
|
||||
if tr.EncoderID != "hash-1024" {
|
||||
t.Errorf("encoder_id %q", tr.EncoderID)
|
||||
}
|
||||
if len(tr.Claims) < 3 {
|
||||
t.Errorf("claims %s: the losers and the never-asked are the point", tr.Claims)
|
||||
}
|
||||
}
|
||||
|
||||
// No store, no trace, and no panic. A typed nil pointer in the interface would
|
||||
// pass the nil check and die on the first turn.
|
||||
func TestNoStoreNoTrace(t *testing.T) {
|
||||
ring := decision.NewRing()
|
||||
h := traceHandler(t, ring)
|
||||
h.traces = traceSink(nil)
|
||||
|
||||
if reply := h.handleText(context.Background(), "web", "сколько сейчас времени"); reply == "" {
|
||||
t.Fatal("turn produced no reply")
|
||||
}
|
||||
if len(ring.Recent(5)) != 1 {
|
||||
t.Error("the ring is still the first sink and must still hold the turn")
|
||||
}
|
||||
}
|
||||
|
||||
// An empty utterance writes nothing. A blank row carries no label and no
|
||||
// diagnosis, and it is his words the retention bound exists for.
|
||||
func TestEmptyUtteranceIsNotPersisted(t *testing.T) {
|
||||
h := traceHandler(t, decision.NewRing())
|
||||
h.traces = traceSink(h.dataStore)
|
||||
h.persistDecision(context.Background(), &decision.Record{Utterance: " "}, sourceText)
|
||||
got, err := h.dataStore.RecentRoutingTraces(context.Background(), 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(got) != 0 {
|
||||
t.Fatalf("persisted %d traces for a blank utterance", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
var _ traceWriter = (*store.Store)(nil)
|
||||
|
||||
// The trace id rides back to the caller, which is what makes a correction one
|
||||
// gesture: /chat already has the id, so saying "that was wrong" costs a button
|
||||
// and no lookup (V-630).
|
||||
func TestTurnHandsBackItsTraceID(t *testing.T) {
|
||||
h := traceHandler(t, decision.NewRing())
|
||||
h.traces = traceSink(h.dataStore)
|
||||
|
||||
ctx, sink := withTraceIDSink(context.Background())
|
||||
if reply := h.handleText(ctx, "web", "сколько сейчас времени"); reply == "" {
|
||||
t.Fatal("turn produced no reply")
|
||||
}
|
||||
id := sink.ID()
|
||||
if id == 0 {
|
||||
t.Fatal("no trace id came back, so /chat can offer no correction")
|
||||
}
|
||||
// And it names the turn that just ran, so the correction lands on the right
|
||||
// utterance.
|
||||
if err := h.dataStore.CorrectTurn(context.Background(), id, "query", h.now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
labels, err := h.dataStore.RoutingLabels(context.Background(), 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(labels) != 1 || labels[0].Utterance != "сколько сейчас времени" {
|
||||
t.Fatalf("labels %+v, want the turn that just ran", labels)
|
||||
}
|
||||
}
|
||||
|
||||
// A turn nobody asked the id of costs nothing, which is the mic path.
|
||||
func TestTurnWithNoSinkStillPersists(t *testing.T) {
|
||||
h := traceHandler(t, decision.NewRing())
|
||||
h.traces = traceSink(h.dataStore)
|
||||
|
||||
if reply := h.handleText(context.Background(), "web", "сколько сейчас времени"); reply == "" {
|
||||
t.Fatal("turn produced no reply")
|
||||
}
|
||||
got, err := h.dataStore.RecentRoutingTraces(context.Background(), 5)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("persisted %d traces, want 1", len(got))
|
||||
}
|
||||
}
|
||||
+19
-9
@@ -17,6 +17,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
@@ -73,22 +74,26 @@ func mentionsUnknownPlace(u string) bool {
|
||||
// date for a day she did not understand.
|
||||
const onlyNearDaysReply = "я считаю только сегодня, завтра, послезавтра и вчера — про другие дни пока не скажу."
|
||||
|
||||
// dayWords — day references the calendar parser cannot resolve. A weekday name
|
||||
// or a "через …" phrase means he asked about a specific other day.
|
||||
var dayWords = []string{
|
||||
"понедельник", "вторник", "сред", "четверг", "пятниц", "суббот", "воскресен",
|
||||
"через", "monday", "tuesday", "wednesday", "thursday", "friday", "saturday", "sunday",
|
||||
}
|
||||
|
||||
// mentionsUnknownDay reports whether the question names a day the calendar
|
||||
// parser could not resolve. Mirror of mentionsUnknownPlace: it exists only to
|
||||
// pick an honest reply over a confidently wrong one.
|
||||
//
|
||||
// Only called after ParseCalendarDate has already failed, so "завтра" and the
|
||||
// other words it does know never reach here.
|
||||
//
|
||||
// The weekday half was a list of STEMS matched with strings.Contains until
|
||||
// V-581 — "сред", "пятниц", "суббот". That is the hand-written Russian pattern
|
||||
// the sweep of 2026-08-04 took out, and it was wrong in the way such a pattern
|
||||
// always is: "среди", "средство" and "средний" all contain "сред", so a question
|
||||
// carrying any of them was answered with onlyNearDaysReply instead of the date.
|
||||
// Whole tokens now, and the weekday itself is router.WeekdayIndex, which reads
|
||||
// the lexicon and asks the dictionary about the case.
|
||||
func mentionsUnknownDay(u string) bool {
|
||||
for _, w := range dayWords {
|
||||
if strings.Contains(u, w) {
|
||||
for _, tok := range quietTokens(u) {
|
||||
if tok == "через" {
|
||||
return true
|
||||
}
|
||||
if _, ok := router.WeekdayIndex(tok); ok {
|
||||
return true
|
||||
}
|
||||
}
|
||||
@@ -149,6 +154,11 @@ func hasDurationWords(u string) bool {
|
||||
// Used by the query handler when answering "когда я это сделал?"-style questions.
|
||||
func formatTime(t time.Time) string {
|
||||
now := time.Now()
|
||||
// The argument is a fact's Ts, which the store hands back as UTC. Only the
|
||||
// last branch names a wall clock, and it named the store's until V-614: an
|
||||
// answer to "когда я это сделал?" read hours off, in the same sentence
|
||||
// shape the plan reads a day in.
|
||||
t = t.Local()
|
||||
if t.After(now.Add(-2*time.Minute)) && t.Before(now.Add(2*time.Minute)) {
|
||||
return "только что"
|
||||
}
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// "когда я это сделал?" answers off a fact's Ts, which the store hands back as
|
||||
// UTC, and the branch that names a wall clock printed it in whatever zone it
|
||||
// arrived in (V-614). The instant here is built three hours off this machine's
|
||||
// zone, so the assertion holds under TZ=UTC as well.
|
||||
func TestFormatTimeReadsHisClock(t *testing.T) {
|
||||
_, off := time.Now().Zone()
|
||||
away := time.FixedZone("away", off+3*60*60)
|
||||
stored := time.Now().Add(-72 * time.Hour).In(away)
|
||||
|
||||
got := formatTime(stored)
|
||||
if want := stored.Local().Format("15:04"); !strings.Contains(got, want) {
|
||||
t.Errorf("formatTime = %q, want the hour on his clock (%s)", got, want)
|
||||
}
|
||||
if bad := stored.Format("15:04"); strings.Contains(got, bad) {
|
||||
t.Errorf("formatTime = %q reads the zone the fact arrived in (%s)", got, bad)
|
||||
}
|
||||
}
|
||||
|
||||
// TestMentionsUnknownDayReadsWordsNotStems — the defect V-581 found. The
|
||||
// weekday half of this guard was a list of stems matched with strings.Contains,
|
||||
// so "среди", "средство" and "средний" all read as Wednesday and the question
|
||||
// was answered with onlyNearDaysReply instead of a date.
|
||||
//
|
||||
// The other half of the fix is coverage: a stem list stops at the forms whoever
|
||||
// wrote it thought of, and "воскресеньях" was not one of them.
|
||||
func TestMentionsUnknownDayReadsWordsNotStems(t *testing.T) {
|
||||
for _, u := range []string{
|
||||
"какое число в понедельник",
|
||||
"какое число в среду",
|
||||
"какое число в среде",
|
||||
"что там по воскресеньям",
|
||||
"what is the date on friday",
|
||||
"какое число через неделю",
|
||||
} {
|
||||
if !mentionsUnknownDay(u) {
|
||||
t.Errorf("mentionsUnknownDay(%q) = false, want true", u)
|
||||
}
|
||||
}
|
||||
for _, u := range []string{
|
||||
"какое число в среднем",
|
||||
"сколько это в среднем",
|
||||
"какое сегодня средство",
|
||||
"какое число",
|
||||
} {
|
||||
if mentionsUnknownDay(u) {
|
||||
t.Errorf("mentionsUnknownDay(%q) = true; it names no day", u)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -474,7 +474,7 @@ func newSimWorld(t *testing.T, sc scenario) *simWorld {
|
||||
// used to be built on a nil API, which meant any scenario that produced an
|
||||
// act panicked the moment the matcher was consulted.
|
||||
matcher := tool.NewMatcher(api)
|
||||
rtr := buildRouter(emb, matcher, config.DefaultRouterThreshold, router.NewLLMRouter(scripted))
|
||||
rtr := buildRouter(emb, matcher, config.DefaultRouterThreshold, router.NewLLMRouter(scripted), nil)
|
||||
|
||||
w.handler = &reactiveHandler{
|
||||
stt: simTranscriber{},
|
||||
|
||||
@@ -0,0 +1,43 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/stt"
|
||||
)
|
||||
|
||||
// A box with no workstation.stt block transcribes exactly as it did before the
|
||||
// seam existed: the floor is handed back untouched, and nothing probes.
|
||||
func TestSttSeamWithNoBlockIsTheFloor(t *testing.T) {
|
||||
floor := stt.NewStub()
|
||||
got, pair := sttSeam(&config.Config{}, floor)
|
||||
if pair != nil {
|
||||
t.Fatal("no block must build no pair")
|
||||
}
|
||||
if got != stt.Transcriber(floor) {
|
||||
t.Fatal("no block must hand back the floor itself")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSttSeamPrefersTheWorkstation(t *testing.T) {
|
||||
cfg := &config.Config{Workstation: &config.WorkstationConfig{
|
||||
URL: "http://127.0.0.1:1",
|
||||
Stt: &config.WorkstationSttConfig{
|
||||
URL: "http://127.0.0.1:2/transcribe",
|
||||
Health: "http://127.0.0.1:2/health",
|
||||
},
|
||||
}}
|
||||
got, pair := sttSeam(cfg, stt.NewStub())
|
||||
if pair == nil {
|
||||
t.Fatal("a configured block must build a pair")
|
||||
}
|
||||
defer pair.Stop()
|
||||
if got != stt.Transcriber(pair) {
|
||||
t.Fatal("the pair is what callers must transcribe through")
|
||||
}
|
||||
// Nothing answers on port 2, so the seam is the floor until it does.
|
||||
if pair.Available() {
|
||||
t.Fatal("an unreachable workstation must not be available")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
// mavend/telegramintake.go — wiring the inbound telegram poller (V-637).
|
||||
//
|
||||
// The poller reaches the daemon through ipc.CoreAPI and nothing else, so a
|
||||
// telegram turn takes exactly the path the web's POST /api/chat takes: Chat
|
||||
// returns the reply and the persisted trace id, and CorrectTurn writes the
|
||||
// label. Nothing in internal/delivery knows what a handler is.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/delivery/telegramsink"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
// wireTelegramIntake starts the poller, or returns having done nothing. It is
|
||||
// nil-safe in every argument, because it is called from both boot paths — the
|
||||
// unlocked start and the passkey unlock — and telegram must behave the same on
|
||||
// either.
|
||||
//
|
||||
// A sink that will not build is logged rather than fatal here. The push half
|
||||
// already failed the boot in wireDispatcher for the same config, so a second
|
||||
// hard failure would only lose that message.
|
||||
func wireTelegramIntake(ctx context.Context, wg *sync.WaitGroup, api ipc.CoreAPI, cfg *config.Config) {
|
||||
if cfg == nil || cfg.Telegram == nil || !cfg.Telegram.Intake || api == nil {
|
||||
return
|
||||
}
|
||||
sink, err := telegramsink.New(*cfg.Telegram)
|
||||
if err != nil {
|
||||
log.Printf("telegram intake: %v", err)
|
||||
return
|
||||
}
|
||||
poller, err := telegramsink.NewPoller(sink, chatTurnFn(api), api.CorrectTurn)
|
||||
if err != nil {
|
||||
log.Printf("telegram intake: %v", err)
|
||||
return
|
||||
}
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
poller.Run(ctx)
|
||||
}()
|
||||
}
|
||||
|
||||
// chatTurnFn adapts ipc.Chat to the poller's Turn. The trace id comes back on
|
||||
// the reply because the daemon's Chat collects it off the context (V-630), so
|
||||
// the chat can offer the same correction the web does without a second op.
|
||||
func chatTurnFn(api ipc.CoreAPI) telegramsink.Turn {
|
||||
return func(ctx context.Context, conversation, text string) (string, int64, error) {
|
||||
reply, err := api.Chat(ctx, conversation, text)
|
||||
if err != nil {
|
||||
return "", 0, err
|
||||
}
|
||||
return reply.Reply, reply.TraceID, nil
|
||||
}
|
||||
}
|
||||
+2
-2
@@ -24,8 +24,8 @@
|
||||
"at": "21:00",
|
||||
"note": "he speaks. The whole voice path runs: push-to-talk, the STT seam parked with the golden transcript, the real router, the real store write, the phrasing contract.",
|
||||
"audio": "ru_fact",
|
||||
"expect_reply_contains": ["записала"],
|
||||
"expect_reply_lacks": ["записал ", "записал,", "записал.", "милый", "ваш"],
|
||||
"expect_reply_contains": ["записала", "выпил воды"],
|
||||
"expect_reply_lacks": ["записал ", "записал,", "записал.", "милый", "ваш", "стакан"],
|
||||
"expect_events": ["water"]
|
||||
},
|
||||
{
|
||||
|
||||
+3
-3
@@ -81,10 +81,10 @@
|
||||
},
|
||||
{
|
||||
"at": "08:55",
|
||||
"note": "stating a fact writes it and says so, in the feminine. This reply comes back through the replier from the scripted model, so the persona check is against generated text rather than a constant. The masculine forms are listed with their following character — \"записал \" and \"записал,\" — because \"записала\" contains \"записал\", and the earlier check on the comma alone passed on \"записал что ты выпил воды\".",
|
||||
"note": "stating a fact writes it and says so, in the feminine, and in his own words. The reply no longer comes from the model at all (V-592): a 1.7B asked to restate «я выпил воды» answered «Проверила, что ты выпел стакан воды», so the confirmation is now a deck frame with his sentence in it. The masculine forms are listed with their following character — \"записал \" and \"записал,\" — because \"записала\" contains \"записал\".",
|
||||
"say": "я выпил воды",
|
||||
"expect_reply_contains": ["записала"],
|
||||
"expect_reply_lacks": ["записал ", "записал,", "записал.", "милый"],
|
||||
"expect_reply_contains": ["записала", "я выпил воды"],
|
||||
"expect_reply_lacks": ["записал ", "записал,", "записал.", "милый", "стакан"],
|
||||
"expect_events": ["water"]
|
||||
},
|
||||
{
|
||||
|
||||
+14
-9
@@ -319,10 +319,7 @@ func (t *tickLoop) stopFinishedAlarms(ctx context.Context, keys []string, state
|
||||
if len(keys) == 0 {
|
||||
return nil
|
||||
}
|
||||
byName := make(map[string]loop.Rule, len(t.rules))
|
||||
for _, r := range t.rules {
|
||||
byName[r.Name] = r
|
||||
}
|
||||
byName := t.rulesByName()
|
||||
live := keys[:0:0]
|
||||
for _, key := range keys {
|
||||
outcome := ""
|
||||
@@ -381,19 +378,27 @@ func (t *tickLoop) repeatableRules(keys []string) []string {
|
||||
if len(keys) == 0 {
|
||||
return nil
|
||||
}
|
||||
wired := make(map[string]bool, len(t.rules))
|
||||
for _, r := range t.rules {
|
||||
wired[r.Name] = true
|
||||
}
|
||||
wired := t.rulesByName()
|
||||
out := keys[:0:0]
|
||||
for _, k := range keys {
|
||||
if wired[k] {
|
||||
if _, ok := wired[k]; ok {
|
||||
out = append(out, k)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// rulesByName indexes the wired rule set by name, for the two lookups above
|
||||
// that only care whether a key is still wired (repeatableRules) or need the
|
||||
// rule itself (stopFinishedAlarms).
|
||||
func (t *tickLoop) rulesByName() map[string]loop.Rule {
|
||||
byName := make(map[string]loop.Rule, len(t.rules))
|
||||
for _, r := range t.rules {
|
||||
byName[r.Name] = r
|
||||
}
|
||||
return byName
|
||||
}
|
||||
|
||||
// cachePhrase keeps the latest phrased nudge per rule for the sev4-repeat
|
||||
// path. writing under a mutex; the repeat path reads under the same. the
|
||||
// cache is bounded by the rule count (≤ ~30 per spec) so eviction is not a
|
||||
|
||||
+22
-1
@@ -23,6 +23,7 @@ type daemonAPI struct {
|
||||
chatFn func(ctx context.Context, conversation, text string) string
|
||||
getMCPServers func() []ipc.MCPServerStatus
|
||||
getEvents func(n int) []ipc.IntakeEvent
|
||||
getDecisions func(n int) []ipc.TurnDecision
|
||||
// nexus — the identity client, nil when no nexus block is configured. It
|
||||
// is what makes ResolveEntity answerable at all; without it the store
|
||||
// adapter's refusal stands, and a surface that wanted an entity id says so
|
||||
@@ -96,10 +97,19 @@ func (d *daemonAPI) Chat(ctx context.Context, conversation, text string) (ipc.Ch
|
||||
return ipc.ChatReply{}, errors.New("mavend: chat not available")
|
||||
}
|
||||
ctx, sink := withQuerySourceSink(ctx)
|
||||
// The trace id rides back the same way (V-630), so /chat can offer a
|
||||
// correction on the turn it is already showing. 0 when nothing persisted.
|
||||
ctx, traces := withTraceIDSink(ctx)
|
||||
reply := d.chatFn(ctx, conversation, text)
|
||||
return ipc.ChatReply{Reply: reply, Source: sink.Name()}, nil
|
||||
return ipc.ChatReply{Reply: reply, Source: sink.Name(), TraceID: traces.ID()}, nil
|
||||
}
|
||||
|
||||
// CorrectTurn is NOT overridden here, and that is deliberate (V-630). Every other
|
||||
// diagnostic on this type exists because the daemon holds something the store
|
||||
// cannot answer from a table. A correction is a table, so the embedded store
|
||||
// adapter is already the right answer and a second implementation here would be
|
||||
// a second place for it to drift.
|
||||
|
||||
// MCPServers — the configured MCP servers and their health (Vikunja #251).
|
||||
// Empty, not an error, when the mcp block is absent: "not configured" is the
|
||||
// default state and the web surface renders it as such.
|
||||
@@ -118,6 +128,17 @@ func (d *daemonAPI) TickTrace(ctx context.Context) (ipc.TickTrace, error) {
|
||||
return toIPCTickTrace(*trace), nil
|
||||
}
|
||||
|
||||
// TurnDecisions — the arbitration records of the last few turns (V-564). Nil
|
||||
// getter means voice was never wired, and that is an empty list rather than an
|
||||
// error: a box with no voice path has had no turns to arbitrate, which is not a
|
||||
// fault and renders as an empty table.
|
||||
func (d *daemonAPI) TurnDecisions(ctx context.Context, n int) ([]ipc.TurnDecision, error) {
|
||||
if d.getDecisions == nil {
|
||||
return nil, nil
|
||||
}
|
||||
return d.getDecisions(n), nil
|
||||
}
|
||||
|
||||
func (d *daemonAPI) MorningStatus(ctx context.Context) ([]ipc.MorningRoutineStatus, error) {
|
||||
if d.getMorningStatus == nil {
|
||||
return nil, errors.New("mavend: morning status not available")
|
||||
|
||||
@@ -0,0 +1,354 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// turnRole — what this utterance IS, relative to the action Maven is in the
|
||||
// middle of assembling. The five roles are the owner's vocabulary (Vikunja
|
||||
// #558), plus the sixth answer a resolver is allowed to give: not_applicable,
|
||||
// which hands the turn back to generic dispatch.
|
||||
//
|
||||
// It exists because the arbitration used to be ordering. The clarify resolver,
|
||||
// the confirm gate, the follow-up merge and the repair marker all ran BEFORE
|
||||
// the router, so the claimant holding conversational state decided what an
|
||||
// utterance was without asking the one component whose job that is — and on
|
||||
// 2026-08-05 "какая сейчас погода в Риме?" became the time of a reminder,
|
||||
// because the extractor found "сейчас" in it and nothing looked at the rest.
|
||||
//
|
||||
// The rule that fixes that: a routed decision which stands on its own — its own
|
||||
// intent, its own slots filled from its own words — is not an answer, whatever
|
||||
// the extractor found inside it.
|
||||
type turnRole string
|
||||
|
||||
const (
|
||||
roleAnswer turnRole = "answer" // it fills the slot she asked about
|
||||
roleCorrection turnRole = "correction" // it replaces a value she already had
|
||||
roleSideQuery turnRole = "side_query" // a question of its own, asked mid-flow
|
||||
roleNewRequest turnRole = "new_request" // a different request entirely
|
||||
roleAside turnRole = "aside" // something he stated, not an answer
|
||||
roleCancel turnRole = "cancel" // call the pending action off
|
||||
roleNotApplicable turnRole = "not_applicable" // nothing is pending; not our turn
|
||||
)
|
||||
|
||||
// frameWords — the words that can stand around a bare slot value without adding
|
||||
// a request. Every member is a closed class from internal/lexicon: the frame
|
||||
// itself, the interrogatives, the parts of a spoken clock, the days and the
|
||||
// months. Assembled once; the sets are copies, so this cannot edit them.
|
||||
var frameWords = buildFrameWords()
|
||||
|
||||
func buildFrameWords() map[string]bool {
|
||||
out := make(map[string]bool)
|
||||
add := func(list []string) {
|
||||
for _, w := range list {
|
||||
out[strings.ToLower(w)] = true
|
||||
}
|
||||
}
|
||||
add(lexicon.SlotValueFrame())
|
||||
add(lexicon.Interrogatives())
|
||||
add(lexicon.PartsOfDay())
|
||||
add(lexicon.HalfHourWords())
|
||||
add(lexicon.DayOffsetWords())
|
||||
for i := 0; i < 7; i++ {
|
||||
out[lexicon.Weekday(i)] = true
|
||||
}
|
||||
for m := 1; m <= 12; m++ {
|
||||
out[lexicon.MonthGenitive(m)] = true
|
||||
}
|
||||
for hh := 0; hh <= 23; hh++ {
|
||||
add(strings.Fields(lexicon.HourSpoken(hh)))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// cancelWords — the same, for the words that call the pending action off.
|
||||
var cancelWords = buildCancelWords()
|
||||
|
||||
func buildCancelWords() map[string]bool {
|
||||
out := make(map[string]bool)
|
||||
for _, w := range lexicon.DialogueCancel() {
|
||||
out[strings.ToLower(w)] = true
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// turnTokens splits an utterance the way the router's own predicates do: over
|
||||
// letters and digits, lowercased, so punctuation and a clock's colon fall out.
|
||||
func turnTokens(text string) []string {
|
||||
return strings.FieldsFunc(strings.ToLower(text), func(r rune) bool {
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
})
|
||||
}
|
||||
|
||||
// ownContent lists the tokens of an utterance that are neither frame nor value:
|
||||
// what it is about, over and above the thing she asked for. Numbers go out
|
||||
// because a number is the commonest slot value there is, and the closed number
|
||||
// and day lexicons go out with them.
|
||||
//
|
||||
// Empty ⇒ the utterance is a slot value and nothing else, however it is dressed
|
||||
// up. That is the whole test, and it is what separates "а что если в 11:00" —
|
||||
// which is a time, hedged — from "какая сейчас погода в Риме?", which leaves
|
||||
// "погода" and "риме" behind and is therefore about something.
|
||||
func ownContent(text string) []string {
|
||||
var out []string
|
||||
for _, tok := range turnTokens(text) {
|
||||
if frameWords[tok] || lexicon.IsFillerParticle(tok) {
|
||||
continue
|
||||
}
|
||||
if _, ok := lexicon.Cardinal(tok); ok {
|
||||
continue
|
||||
}
|
||||
if _, ok := lexicon.Ordinal(tok); ok {
|
||||
continue
|
||||
}
|
||||
if isNumeric(tok) {
|
||||
continue
|
||||
}
|
||||
out = append(out, tok)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func isNumeric(tok string) bool {
|
||||
for _, r := range tok {
|
||||
if !unicode.IsDigit(r) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return tok != ""
|
||||
}
|
||||
|
||||
// isCancel reports whether the utterance is nothing but a call-off. Every
|
||||
// content token has to be a cancel word, so "забудь" ends the exchange and
|
||||
// "забудь купить молоко" does not.
|
||||
func isCancel(text string) bool {
|
||||
content := ownContent(text)
|
||||
if len(content) == 0 {
|
||||
return false
|
||||
}
|
||||
for _, tok := range content {
|
||||
if !cancelWords[tok] {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// carriesOwnRequest reads the ROUTED decision for the thing that decides this:
|
||||
// does the utterance ask for something in its own right? Each intent is asked
|
||||
// the question in its own terms, because "its own slots filled from its own
|
||||
// words" means a different field for each of them.
|
||||
//
|
||||
// A query or a system question needs no further evidence — the router already
|
||||
// read a question in these words. The write intents need the verb or the slot
|
||||
// that names the request, so a bare value the router guessed a home for does
|
||||
// not count as one.
|
||||
func carriesOwnRequest(dec router.Decision, text string) bool {
|
||||
if dec.Clarify {
|
||||
// The router itself was unsure. An utterance she could not route is
|
||||
// not an utterance that outranks the question in front of it.
|
||||
return false
|
||||
}
|
||||
switch dec.Intent {
|
||||
case router.IntentQuery, router.IntentSystem:
|
||||
return true
|
||||
case router.IntentReminder:
|
||||
return carriesReminderVerb(text)
|
||||
case router.IntentFact, router.IntentNote:
|
||||
return router.CarriesCaptureVerb(text)
|
||||
case router.IntentAct:
|
||||
// An act that resolved to a capability is a command. One that did not
|
||||
// is words she cannot execute anyway, so it stays an answer and gets
|
||||
// re-asked — the same thing that happens to it today.
|
||||
return dec.Slots.HasFn
|
||||
default: // chat
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// carriesReminderVerb — "напомни" and its forms, matched over tokens. The
|
||||
// reminder verbs are a closed lexicon and are not capture verbs, so
|
||||
// CarriesCaptureVerb never sees them.
|
||||
func carriesReminderVerb(text string) bool {
|
||||
toks := turnTokens(text)
|
||||
for _, v := range lexicon.ReminderVerbs() {
|
||||
for _, t := range toks {
|
||||
if t == strings.ToLower(v) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// isPleasantry matches the WHOLE utterance against lexicon.Pleasantries, after
|
||||
// lowercasing and dropping the punctuation a greeting carries.
|
||||
//
|
||||
// Whole utterance and not tokens. Every token rule tried here was wrong on
|
||||
// something: "вечер" answers "это утра или вечера?", "нет" answers a confirm,
|
||||
// and "спокойной" alone is not an utterance at all. A greeting is a fixed
|
||||
// phrase, so matching it as one costs nothing and claims nothing else.
|
||||
func isPleasantry(text string) bool {
|
||||
t := strings.ToLower(strings.TrimSpace(text))
|
||||
t = strings.Trim(t, " .,!?…")
|
||||
t = strings.Join(strings.Fields(t), " ")
|
||||
if t == "" {
|
||||
return false
|
||||
}
|
||||
for _, p := range lexicon.Pleasantries() {
|
||||
if t == p {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// offlineOwnRequest is the shape half of the evidence: the offline token tests,
|
||||
// which cost nothing and never depend on the model that produced the routing.
|
||||
// It is also the whole answer when there is no route to read — the classifier
|
||||
// is the failure floor and a turn must never break on the model.
|
||||
func offlineOwnRequest(text string) bool {
|
||||
return router.IsQuestionShaped(text) || router.CarriesCaptureVerb(text) || carriesReminderVerb(text)
|
||||
}
|
||||
|
||||
// classifyTurnRole decides what this utterance is against the pending action.
|
||||
//
|
||||
// The fast path is the first line and it is a fast path to the SAME answer, not
|
||||
// a second decision procedure: an utterance with no content of its own can
|
||||
// never be a request of its own, so it can never be anything but an answer, and
|
||||
// the route below would spend a second on the resident model to say so. Every
|
||||
// other utterance is routed first, and the role is read off the decision.
|
||||
//
|
||||
// `routed` is the turn's routing, already computed; ok is false when there was
|
||||
// none to compute (no router wired, or the route failed). A failed route falls
|
||||
// to the offline shape tests rather than breaking the turn.
|
||||
func classifyTurnRole(q *dialogue.PendingQuestion, text string, answer dialogue.Slots, routed router.Decision, ok bool) turnRole {
|
||||
if isCancel(text) {
|
||||
return roleCancel
|
||||
}
|
||||
// Two pieces of evidence, and the content gate in front of both. The shape
|
||||
// tests are the floor and answer for free; the route is what sees a request
|
||||
// with no shape to it — "погода в риме" asks a question and carries neither
|
||||
// a question mark nor an interrogative, and only the router knows that.
|
||||
//
|
||||
// An utterance of pure frame gets one more chance, and V-577 is why. Every
|
||||
// token of "что у меня сегодня?" is frame, so the content gate called it an
|
||||
// answer, the parked reminder took "сегодня" for its time, and the question
|
||||
// he asked was answered nowhere. A routed intent beats a frame match,
|
||||
// because the frame is a hint and the route is a decision.
|
||||
//
|
||||
// The condition is that it fills nothing she asked about. That keeps the
|
||||
// hedged "а что если в 11:00" an answer, which is what it is: it carries the
|
||||
// hour, and no route saying "question" changes that. It works because the
|
||||
// extractor no longer reads a day word as the current clock, so a sentence
|
||||
// that names no hour now fills nothing to weigh.
|
||||
// A pleasantry is neither (V-663). "спасибо" and "привет" fell through to
|
||||
// roleAnswer, so a question about a reminder's DAY was re-asked at a man
|
||||
// saying thank you, and the retry it spent was one of the three bounds
|
||||
// meant to end the ride. It is an aside: answered as itself, the question
|
||||
// resumed on the tail, no attempt spent, one ride counted. Placed above the
|
||||
// content gate because "доброе утро" has content and states nothing, so
|
||||
// neither half of the evidence below can reach it.
|
||||
if q != nil && isPleasantry(text) {
|
||||
return roleAside
|
||||
}
|
||||
own := false
|
||||
if len(ownContent(text)) > 0 {
|
||||
own = offlineOwnRequest(text) || (ok && carriesOwnRequest(routed, text))
|
||||
} else if ok && fillsNothingAsked(q, answer) {
|
||||
own = carriesOwnRequest(routed, text)
|
||||
}
|
||||
if !own {
|
||||
if isAside(q, text, answer, routed, ok) {
|
||||
return roleAside
|
||||
}
|
||||
if replacesFilledSlot(q, answer) {
|
||||
return roleCorrection
|
||||
}
|
||||
return roleAnswer
|
||||
}
|
||||
if router.IsQuestionShaped(text) || (ok && (routed.Intent == router.IntentQuery || routed.Intent == router.IntentSystem)) {
|
||||
return roleSideQuery
|
||||
}
|
||||
return roleNewRequest
|
||||
}
|
||||
|
||||
// isAside reports whether the utterance is something he STATED while she was
|
||||
// waiting on a question (V-577 shape 2).
|
||||
//
|
||||
// "у меня новый ноутбук" said into a parked reminder was dropped in silence: it
|
||||
// carries no capture verb, so it is not a request of its own, and it fills no
|
||||
// slot, so it is not an answer either. Neither storing it nor saying it was
|
||||
// ignored is the one behaviour that is wrong, and it was the behaviour.
|
||||
//
|
||||
// Three conditions, and all three are needed. The route has to call it a
|
||||
// statement AND stand behind that, so a bare time is never an aside. It has to
|
||||
// fill none of what she asked about, so an answer she can use stays an answer.
|
||||
// And it has to say something, so a shrug is still a failed answer and still
|
||||
// spends a retry.
|
||||
func isAside(q *dialogue.PendingQuestion, text string, answer dialogue.Slots, routed router.Decision, ok bool) bool {
|
||||
if !ok || q == nil {
|
||||
return false
|
||||
}
|
||||
if !statesSomething(routed) {
|
||||
return false
|
||||
}
|
||||
if len(ownContent(text)) == 0 {
|
||||
return false
|
||||
}
|
||||
return fillsNothingAsked(q, answer)
|
||||
}
|
||||
|
||||
// statesSomething reports whether the route is evidence that these words state
|
||||
// a thing, rather than a guess she has to interrupt a flow over.
|
||||
//
|
||||
// Two kinds of evidence, and the second one exists because the classifier floor
|
||||
// marks nearly everything Clarify. A parsed fact key comes from the
|
||||
// deterministic fact parser and not from a similarity score, so "я выпил воды"
|
||||
// is a statement on any engine. A confident note or fact is the other kind, and
|
||||
// that is the one the resident model gives for "у меня новый ноутбук".
|
||||
func statesSomething(routed router.Decision) bool {
|
||||
switch routed.Intent {
|
||||
case router.IntentFact:
|
||||
return routed.Slots.HasKey || !routed.Clarify
|
||||
case router.IntentNote:
|
||||
return !routed.Clarify
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// fillsNothingAsked reports whether the utterance gave her none of what she
|
||||
// asked for. Nothing is pending counts as nothing filled.
|
||||
func fillsNothingAsked(q *dialogue.PendingQuestion, answer dialogue.Slots) bool {
|
||||
if q == nil {
|
||||
return true
|
||||
}
|
||||
return len(dialogue.StillMissing(q.Missing, answer)) == len(q.Missing)
|
||||
}
|
||||
|
||||
// replacesFilledSlot reports whether the utterance overwrites something the
|
||||
// pending action already had, rather than filling the gap she asked about —
|
||||
// "нет, на девять" while she is waiting for the subject. Both are handled the
|
||||
// same way (dialogue.Answer already prefers the newer value), so this only
|
||||
// names the turn honestly for the log and for the decision trace V-564 adds.
|
||||
func replacesFilledSlot(q *dialogue.PendingQuestion, answer dialogue.Slots) bool {
|
||||
if q == nil {
|
||||
return false
|
||||
}
|
||||
asked := make(map[dialogue.Slot]bool, len(q.Missing))
|
||||
for _, s := range q.Missing {
|
||||
asked[s] = true
|
||||
}
|
||||
if answer.HasTime && q.Slots.HasTime && !asked[dialogue.SlotTime] && !answer.Time.Equal(q.Slots.Time) {
|
||||
return true
|
||||
}
|
||||
if answer.HasKey && q.Slots.HasKey && !asked[dialogue.SlotKey] && answer.Key != q.Slots.Key {
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
@@ -0,0 +1,440 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// TestOwnContentSeparatesAValueFromAQuestion pins the test the whole role
|
||||
// classifier rests on: after the frame, the numbers and the closed time sets
|
||||
// come out, does anything of his own remain? A hedged time leaves nothing. A
|
||||
// question about the weather leaves the weather.
|
||||
func TestOwnContentSeparatesAValueFromAQuestion(t *testing.T) {
|
||||
cases := []struct {
|
||||
text string
|
||||
own bool
|
||||
}{
|
||||
{"в 11:00", false},
|
||||
{"в семь вечера", false},
|
||||
{"нет, в 15:00", false},
|
||||
{"а что если в 11:00", false},
|
||||
{"на 9", false},
|
||||
{"а, да, прости — на 9", false},
|
||||
{"завтра", false},
|
||||
{"в половине восьмого", false},
|
||||
{"какая сейчас погода в Риме?", true},
|
||||
{"кто изобрёл телефон", true},
|
||||
{"напомни в 11:00", true},
|
||||
{"позвонить маме", true},
|
||||
{"запиши что я пил воду", true},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
if got := len(ownContent(tc.text)) > 0; got != tc.own {
|
||||
t.Errorf("ownContent(%q) = %v, want own content = %v", tc.text, ownContent(tc.text), tc.own)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestCancelIsTheWholeUtterance — a call-off calls the request off, and a
|
||||
// sentence that merely contains the word does not.
|
||||
func TestCancelIsTheWholeUtterance(t *testing.T) {
|
||||
for _, yes := range []string{"отмена", "забудь", "неважно", "проехали", "cancel", "ой, отмена"} {
|
||||
if !isCancel(yes) {
|
||||
t.Errorf("isCancel(%q) = false, want true", yes)
|
||||
}
|
||||
}
|
||||
for _, no := range []string{"забудь купить молоко", "в 11:00", "позвонить маме", ""} {
|
||||
if isCancel(no) {
|
||||
t.Errorf("isCancel(%q) = true, want false", no)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestTurnRoleReadsTheRoutedDecision — the inversion itself. The same utterance
|
||||
// gets a different role depending on what the router made of it, which is the
|
||||
// evidence the old guard never had.
|
||||
func TestTurnRoleReadsTheRoutedDecision(t *testing.T) {
|
||||
q := &dialogue.PendingQuestion{
|
||||
Intent: dialogue.Intent(router.IntentReminder),
|
||||
Missing: []dialogue.Slot{dialogue.SlotTime},
|
||||
}
|
||||
dec := func(in router.Intent, s router.Slots) router.Decision {
|
||||
return router.Decision{Intent: in, Slots: s}
|
||||
}
|
||||
cases := []struct {
|
||||
name string
|
||||
text string
|
||||
routed router.Decision
|
||||
ok bool
|
||||
answer dialogue.Slots
|
||||
want turnRole
|
||||
}{
|
||||
{
|
||||
// The measured defect. The extractor finds "сейчас" and would have
|
||||
// closed the gap with it; the route says this is a question of its
|
||||
// own, and the question wins.
|
||||
name: "a world question mid-flow is a side query",
|
||||
text: "какая сейчас погода в Риме?",
|
||||
routed: dec(router.IntentQuery, router.Slots{Text: "какая сейчас погода в Риме?"}),
|
||||
ok: true,
|
||||
answer: dialogue.Slots{HasTime: true, Time: time.Now()},
|
||||
want: roleSideQuery,
|
||||
},
|
||||
{
|
||||
name: "a hedged time is an answer even routed as a query",
|
||||
text: "а что если в 11:00",
|
||||
routed: dec(router.IntentQuery, router.Slots{Text: "а что если в 11:00"}),
|
||||
ok: true,
|
||||
answer: dialogue.Slots{HasTime: true, Time: time.Now()},
|
||||
want: roleAnswer,
|
||||
},
|
||||
{
|
||||
name: "a fresh reminder is a new request",
|
||||
text: "напомни завтра позвонить маме",
|
||||
routed: dec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}),
|
||||
ok: true,
|
||||
want: roleNewRequest,
|
||||
},
|
||||
{
|
||||
name: "a capture is a new request",
|
||||
text: "запиши что я пил воду",
|
||||
routed: dec(router.IntentFact, router.Slots{Key: "water", HasKey: true}),
|
||||
ok: true,
|
||||
want: roleNewRequest,
|
||||
},
|
||||
{
|
||||
name: "an act that resolved to a capability is a new request",
|
||||
text: "выключи свет в спальне",
|
||||
routed: dec(router.IntentAct, router.Slots{Fn: "light_off", HasFn: true}),
|
||||
ok: true,
|
||||
want: roleNewRequest,
|
||||
},
|
||||
{
|
||||
// She could not route it. An utterance she did not understand does
|
||||
// not outrank the question in front of it.
|
||||
name: "a clarify decision is not a request of its own",
|
||||
text: "выключи свет",
|
||||
routed: router.Decision{Intent: router.IntentAct, Slots: router.Slots{Fn: "light_off", HasFn: true}, Clarify: true},
|
||||
ok: true,
|
||||
want: roleAnswer,
|
||||
},
|
||||
{
|
||||
// V-577 shape 1. Every token is frame, so the content gate called
|
||||
// this an answer and the reminder took "сегодня" for its time. It
|
||||
// fills nothing she asked about, so the route decides, and the route
|
||||
// says the calendar answers it.
|
||||
name: "an agenda question of pure frame words is a side query",
|
||||
text: "что у меня сегодня?",
|
||||
routed: dec(router.IntentQuery, router.Slots{}),
|
||||
ok: true,
|
||||
want: roleSideQuery,
|
||||
},
|
||||
{
|
||||
// V-577 shape 2. Neither a slot value nor a request nor a cancel.
|
||||
// It was dropped in silence; it is an aside, and an aside is stored
|
||||
// and re-asked.
|
||||
name: "a fact stated mid-flow is an aside",
|
||||
text: "у меня новый ноутбук",
|
||||
routed: dec(router.IntentNote, router.Slots{Text: "у меня новый ноутбук"}),
|
||||
ok: true,
|
||||
want: roleAside,
|
||||
},
|
||||
{
|
||||
// A route she is not sure of is not evidence that he stated
|
||||
// anything, and "позвонить маме" is the answer to the other half of
|
||||
// a reminder.
|
||||
name: "an unsure note is not an aside",
|
||||
text: "позвонить маме",
|
||||
routed: router.Decision{Intent: router.IntentNote, Clarify: true},
|
||||
ok: true,
|
||||
want: roleAnswer,
|
||||
},
|
||||
{
|
||||
name: "a bare noun that answers nothing is still an answer",
|
||||
text: "ага",
|
||||
ok: false,
|
||||
want: roleAnswer,
|
||||
},
|
||||
{
|
||||
name: "no route to read falls back to the shape",
|
||||
text: "кто изобрёл телефон",
|
||||
ok: false,
|
||||
want: roleSideQuery,
|
||||
},
|
||||
{
|
||||
name: "a call-off needs no route at all",
|
||||
text: "отмена",
|
||||
ok: false,
|
||||
want: roleCancel,
|
||||
},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
if got := classifyTurnRole(q, tc.text, tc.answer, tc.routed, tc.ok); got != tc.want {
|
||||
t.Errorf("%s: classifyTurnRole(%q) = %s, want %s", tc.name, tc.text, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestTurnRoleNamesACorrection — the answer overwrites a slot she was not
|
||||
// asking about. Handled like an answer, named as what it is.
|
||||
func TestTurnRoleNamesACorrection(t *testing.T) {
|
||||
nine := time.Date(2026, 8, 6, 9, 0, 0, 0, time.UTC)
|
||||
q := &dialogue.PendingQuestion{
|
||||
Intent: dialogue.Intent(router.IntentReminder),
|
||||
Missing: []dialogue.Slot{dialogue.SlotText},
|
||||
Slots: dialogue.Slots{HasTime: true, Time: nine.Add(2 * time.Hour)},
|
||||
}
|
||||
got := classifyTurnRole(q, "нет, на 9", dialogue.Slots{HasTime: true, Time: nine}, router.Decision{}, false)
|
||||
if got != roleCorrection {
|
||||
t.Fatalf("role = %s, want %s", got, roleCorrection)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRomeIsAnsweredAndTheReminderIsNotInvented — the measured failure of
|
||||
// 2026-08-05, end to end through the real cascade. "напомни позвонить маме"
|
||||
// parks the time question; the weather question that follows must not become
|
||||
// its answer and must not create a reminder for a time nobody asked for.
|
||||
//
|
||||
// V-560 got that far by DROPPING the parked request and saying so, and the
|
||||
// owner rejected the notice on sight: he did not ask to lose the reminder. So
|
||||
// the contract here is V-561's — the flow is suspended, this turn's reply ends
|
||||
// with the question coming back, and nothing says anything was let go.
|
||||
func TestRomeIsAnsweredAndTheReminderIsNotInvented(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newRoutingClarifyHandler(t)
|
||||
|
||||
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected the time question, got %q", reply)
|
||||
}
|
||||
reply := h.handleText(ctx, "web", "какая сейчас погода в Риме?")
|
||||
if strings.Contains(reply, "напомню") {
|
||||
t.Fatalf("the question was eaten as the reminder's time again: %q", reply)
|
||||
}
|
||||
if strings.Contains(reply, clarifyDropped) {
|
||||
t.Fatalf("a side query suspends the flow; nothing was dropped, so nothing may say so: %q", reply)
|
||||
}
|
||||
resumed, _ := clarifyResumedFor(dialogue.SlotTime)
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("the reply must end with the resumed question %q, got %q", resumed, reply)
|
||||
}
|
||||
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
|
||||
t.Fatalf("a reminder was invented for a time nobody asked for: %v err=%v", reminders, err)
|
||||
}
|
||||
// Still parked, and still on its first attempt: he answered the side query,
|
||||
// not this question, so no retry may have been spent on it.
|
||||
q := h.clarifyStore.Get(dialogueIDFor(sourceText, "web"), h.now())
|
||||
if q == nil {
|
||||
t.Fatal("the parked question was dropped instead of suspended")
|
||||
}
|
||||
if q.Attempts != 1 {
|
||||
t.Fatalf("the side query spent a clarify attempt: attempts = %d, want 1", q.Attempts)
|
||||
}
|
||||
if !strings.Contains(q.Utterance, "маме") {
|
||||
t.Fatalf("the suspended request lost what it was about: %q", q.Utterance)
|
||||
}
|
||||
}
|
||||
|
||||
// TestClarifyCancelEndsTheExchange — "отмена" while she is waiting calls the
|
||||
// half-built request off, out loud, and creates nothing.
|
||||
func TestClarifyCancelEndsTheExchange(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newRoutingClarifyHandler(t)
|
||||
|
||||
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected the time question, got %q", reply)
|
||||
}
|
||||
if reply := h.handleText(ctx, "web", "отмена"); reply != clarifyCancelled {
|
||||
t.Fatalf("reply = %q, want %q", reply, clarifyCancelled)
|
||||
}
|
||||
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
|
||||
t.Fatalf("a cancelled request still landed: %v err=%v", reminders, err)
|
||||
}
|
||||
if h.clarifyStore.Get(dialogueIDFor(sourceText, "web"), h.now()) != nil {
|
||||
t.Fatal("a cancelled exchange must leave nothing parked")
|
||||
}
|
||||
}
|
||||
|
||||
// TestTheTurnIsRoutedOnce — the cost bound. A turn with a question parked pays
|
||||
// for one extra route and not two: the clarify resolver and the pipeline read
|
||||
// the same memo.
|
||||
func TestTheTurnIsRoutedOnce(t *testing.T) {
|
||||
h, _ := newRoutingClarifyHandler(t)
|
||||
rt := h.newTurnRoute("какая сейчас погода в Риме?", h.now())
|
||||
ctx := withTurnRoute(withDialogueID(context.Background(), voiceDialogueID), rt)
|
||||
|
||||
first, ok := h.routeForRole(ctx, rt.text)
|
||||
if !ok {
|
||||
t.Fatal("the cascade must produce a decision to classify against")
|
||||
}
|
||||
second, _, _, err := rt.resolve(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("resolve: %v", err)
|
||||
}
|
||||
if second.Intent != first.Intent || second.Utterance != first.Utterance {
|
||||
t.Fatalf("the pipeline routed again and got something else: %+v vs %+v", second, first)
|
||||
}
|
||||
}
|
||||
|
||||
// TestASuspendedQuestionDoesNotRideForever — V-654, the measured failure of
|
||||
// 2026-08-07 (docs/evals/2026-08-07-week-of-usage-transcript.md, t=51 to t=58).
|
||||
//
|
||||
// A side query suspends the parked question, spends no attempt and restarts the
|
||||
// TTL. Nothing else bounded it, so one unfilled time slot came back on the end
|
||||
// of six consecutive unrelated replies and stopped only when a seventh turn
|
||||
// happened to read as a failed answer. Three step-asides, then she lets it go
|
||||
// and says so.
|
||||
func TestASuspendedQuestionDoesNotRideForever(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st := newRoutingClarifyHandler(t)
|
||||
id := dialogueIDFor(sourceText, "web")
|
||||
resumed, _ := clarifyResumedFor(dialogue.SlotTime)
|
||||
|
||||
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected the time question, got %q", reply)
|
||||
}
|
||||
|
||||
// Three questions of his own. Each one is answered as itself and each one
|
||||
// brings the open question back, exactly as V-561 asks.
|
||||
asides := []string{
|
||||
"о чём мы вчера говорили?",
|
||||
"какие у меня напоминания?",
|
||||
"сколько времени?",
|
||||
}
|
||||
for i, text := range asides {
|
||||
reply := h.handleText(ctx, "web", text)
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("side query %d: the question must come back, got %q", i+1, reply)
|
||||
}
|
||||
if strings.Contains(reply, clarifyDropped) {
|
||||
t.Fatalf("side query %d: nothing was let go yet, so nothing may say so: %q", i+1, reply)
|
||||
}
|
||||
q := h.clarifyStore.Get(id, h.now())
|
||||
if q == nil {
|
||||
t.Fatalf("side query %d: the question was dropped early", i+1)
|
||||
}
|
||||
if q.Attempts != 1 {
|
||||
t.Fatalf("side query %d: a step-aside spent an attempt: %d", i+1, q.Attempts)
|
||||
}
|
||||
if q.Suspends != i+1 {
|
||||
t.Fatalf("side query %d: suspends = %d, want %d", i+1, q.Suspends, i+1)
|
||||
}
|
||||
}
|
||||
|
||||
// The fourth. She has stepped aside as often as she is willing to, so the
|
||||
// request goes — out loud, and without the question on the tail.
|
||||
reply := h.handleText(ctx, "web", "что у меня сегодня?")
|
||||
if !strings.Contains(reply, clarifyDropped) {
|
||||
t.Fatalf("the request was let go in silence: %q", reply)
|
||||
}
|
||||
if strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("a question she has let go must not be asked again: %q", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(id, h.now()) != nil {
|
||||
t.Fatal("the question must be gone once she has said she let it go")
|
||||
}
|
||||
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
|
||||
t.Fatalf("a reminder was invented for a time nobody gave: %v err=%v", reminders, err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestAnAnsweredGapResetsTheSuspendBudget — the counter measures CONSECUTIVE
|
||||
// step-asides. He filled a gap, so the run is broken and the next question
|
||||
// starts with its full allowance: a long exchange he is engaged with must not
|
||||
// run out of patience on his behalf.
|
||||
func TestAnAnsweredGapResetsTheSuspendBudget(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newRoutingClarifyHandler(t)
|
||||
id := dialogueIDFor(sourceText, "web")
|
||||
|
||||
// A bare "напомни" is missing both halves, so answering the subject re-parks
|
||||
// the request with a question about the time.
|
||||
if reply := h.handleText(ctx, "web", "напомни"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected a question, got %q", reply)
|
||||
}
|
||||
if reply := h.handleText(ctx, "web", "какие у меня напоминания?"); reply == "" {
|
||||
t.Fatal("the side query must be answered as itself")
|
||||
}
|
||||
if q := h.clarifyStore.Get(id, h.now()); q == nil || q.Suspends != 1 {
|
||||
t.Fatalf("the side query was not counted: %+v", q)
|
||||
}
|
||||
if reply := h.handleText(ctx, "web", "позвонить маме"); reply == "" {
|
||||
t.Fatal("the answer must be consumed")
|
||||
}
|
||||
q := h.clarifyStore.Get(id, h.now())
|
||||
if q == nil {
|
||||
t.Fatal("a reminder still needs its time, so a question must be parked")
|
||||
}
|
||||
if q.Suspends != 0 {
|
||||
t.Fatalf("answering a gap must reset the suspend budget: suspends = %d", q.Suspends)
|
||||
}
|
||||
// The ride it already took is carried across the re-park (V-663). Resetting
|
||||
// both counters here is what let one question ride twenty-six replies.
|
||||
if q.Rides != 1 {
|
||||
t.Fatalf("the aside it already took was forgotten: rides = %d", q.Rides)
|
||||
}
|
||||
}
|
||||
|
||||
// TestTwoBoundsCannotRearmEachOther — V-663.
|
||||
//
|
||||
// MaxSuspends landed and the measurement did not move: twenty-six of 140 turns
|
||||
// carried a tail before it and twenty-six after. This is the shape it misses,
|
||||
// taken from the 2026-08-08 run, where one question rode turns 7 to 13.
|
||||
//
|
||||
// An aside spends no attempt, so MaxAttempts never reaches it. A turn that
|
||||
// reads as a failed answer zeroes Suspends, so MaxSuspends never reaches the
|
||||
// asides either. Alternating the two rearms each bound with the other's
|
||||
// traffic. Rides counts both kinds and is never reset, so it is what ends this.
|
||||
func TestTwoBoundsCannotRearmEachOther(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newRoutingClarifyHandler(t)
|
||||
id := dialogueIDFor(sourceText, "web")
|
||||
resumed, _ := clarifyResumedFor(dialogue.SlotTime)
|
||||
|
||||
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
|
||||
t.Fatalf("expected the time question, got %q", reply)
|
||||
}
|
||||
|
||||
// Two asides. Each one rides and neither spends an attempt.
|
||||
for i := 0; i < 2; i++ {
|
||||
reply := h.handleText(ctx, "web", "какие у меня напоминания?")
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("aside %d: the question must come back, got %q", i+1, reply)
|
||||
}
|
||||
}
|
||||
q := h.clarifyStore.Get(id, h.now())
|
||||
if q == nil || q.Rides != 2 || q.Suspends != 2 {
|
||||
t.Fatalf("after two asides: %+v", q)
|
||||
}
|
||||
|
||||
// A pleasantry. It used to read as a failed answer, so she re-asked the
|
||||
// question at a man saying thank you and spent an attempt doing it. Now it
|
||||
// is an aside: answered as itself, question on the tail, one more ride.
|
||||
reply := h.handleText(ctx, "web", "спасибо")
|
||||
if !strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("a pleasantry lost the parked question: %q", reply)
|
||||
}
|
||||
q = h.clarifyStore.Get(id, h.now())
|
||||
if q == nil || q.Attempts != 1 {
|
||||
t.Fatalf("a pleasantry spent an attempt: %+v", q)
|
||||
}
|
||||
if q.Rides != 3 {
|
||||
t.Fatalf("a pleasantry rode free: %+v", q)
|
||||
}
|
||||
|
||||
// One more ride of any kind and the request goes, out loud.
|
||||
reply = h.handleText(ctx, "web", "какие у меня напоминания?")
|
||||
if !strings.Contains(reply, clarifyDropped) {
|
||||
t.Fatalf("the question rode four asides and was let go in silence: %q", reply)
|
||||
}
|
||||
if strings.HasSuffix(reply, resumed) {
|
||||
t.Fatalf("a question she has let go must not be asked again: %q", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(id, h.now()) != nil {
|
||||
t.Fatal("the question must be gone once she has said she let it go")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// turnRoute is this turn's routing, computed at most once.
|
||||
//
|
||||
// It exists because the arbitration was inverted (Vikunja #560): the clarify
|
||||
// resolver now reads the routed decision before deciding what the utterance is,
|
||||
// and the pipeline then acts on that same decision. Routing twice would cost a
|
||||
// second on the resident model and — worse — could disagree with itself, which
|
||||
// is exactly the class of bug this task is about.
|
||||
type turnRoute struct {
|
||||
h *reactiveHandler
|
||||
text string
|
||||
now time.Time
|
||||
|
||||
once sync.Once
|
||||
dec router.Decision
|
||||
cont bool
|
||||
prev *dialogue.Session
|
||||
err error
|
||||
|
||||
// dropped — what she let go of this turn and must say out loud. A parked
|
||||
// request that dies without a word leaves him thinking it landed.
|
||||
dropped string
|
||||
|
||||
// resume — the parked question, re-worded, to put AFTER this turn's answer
|
||||
// (Vikunja #561). A side query does not end the flow it interrupted, so the
|
||||
// reply carries two acts: the answer he asked for, then the question he
|
||||
// still owes her. Empty ⇒ nothing was suspended.
|
||||
resume string
|
||||
// suspended — a flow is parked underneath this turn. askClarify reads it to
|
||||
// decide between Put (replace the top) and Push (keep the flow and stack the
|
||||
// new question on it), because a side query that needs clarifying of its own
|
||||
// must not overwrite the thing it interrupted.
|
||||
suspended bool
|
||||
}
|
||||
|
||||
type turnRouteKey struct{}
|
||||
|
||||
func (h *reactiveHandler) newTurnRoute(text string, now time.Time) *turnRoute {
|
||||
return &turnRoute{h: h, text: text, now: now}
|
||||
}
|
||||
|
||||
func withTurnRoute(ctx context.Context, rt *turnRoute) context.Context {
|
||||
return context.WithValue(ctx, turnRouteKey{}, rt)
|
||||
}
|
||||
|
||||
// turnRouteFrom returns the turn's memo, or nil when the caller is not inside
|
||||
// runTurn — a unit test calling one resolver directly, most often.
|
||||
func turnRouteFrom(ctx context.Context) *turnRoute {
|
||||
rt, _ := ctx.Value(turnRouteKey{}).(*turnRoute)
|
||||
return rt
|
||||
}
|
||||
|
||||
// resolve does the routing exactly as step 5 of runTurn does it: an elliptical
|
||||
// follow-up is answered from the previous turn, everything else goes to the
|
||||
// router. One copy of that, so the pre-route the clarify resolver reads and the
|
||||
// decision the pipeline acts on cannot drift apart.
|
||||
func (r *turnRoute) resolve(ctx context.Context) (router.Decision, bool, *dialogue.Session, error) {
|
||||
r.once.Do(func() {
|
||||
if r.h.dialogueSessions != nil {
|
||||
r.prev = r.h.dialogueSessions.Get(dialogueIDOf(ctx), r.now)
|
||||
}
|
||||
if dec, cont := continuationDecision(r.prev, r.text, r.now); cont {
|
||||
log.Printf("voice: continuation of %s from the previous turn", dec.Intent)
|
||||
r.dec, r.cont = dec, true
|
||||
return
|
||||
}
|
||||
if r.h.router == nil {
|
||||
r.err = router.ErrNoIntents
|
||||
return
|
||||
}
|
||||
r.dec, r.err = r.h.router.Route(ctx, r.text, r.now)
|
||||
})
|
||||
return r.dec, r.cont, r.prev, r.err
|
||||
}
|
||||
|
||||
// routeForRole gives the role classifier the turn's routed decision. The second
|
||||
// return is false when there is no usable decision — no router wired, or the
|
||||
// route failed — and the classifier falls back to its offline tests then. A
|
||||
// turn must never break on the model, so the error is logged and swallowed
|
||||
// here; step 5 reads the same memo and reports it the way it always has.
|
||||
func (h *reactiveHandler) routeForRole(ctx context.Context, text string) (router.Decision, bool) {
|
||||
rt := turnRouteFrom(ctx)
|
||||
if rt == nil {
|
||||
rt = h.newTurnRoute(text, h.now())
|
||||
}
|
||||
dec, _, _, err := rt.resolve(ctx)
|
||||
if err != nil {
|
||||
log.Printf("voice: role — no route to classify against (%v), falling back to the offline tests", err)
|
||||
return router.Decision{}, false
|
||||
}
|
||||
return dec, true
|
||||
}
|
||||
|
||||
// needsRoute reports whether classifying this utterance's role is worth a
|
||||
// route. It is not: an utterance with no content of its own carries no request
|
||||
// of its own, so the classifier reaches the same answer without the model. A
|
||||
// call-off is the same — it is read off a closed lexicon and nothing else.
|
||||
//
|
||||
// This is a fast path to the SAME answer and must stay one. If it ever needs a
|
||||
// rule the classifier does not have, it has become a second decision procedure
|
||||
// and it is the thing V-560 deleted.
|
||||
//
|
||||
// A question shape is the exception and V-577 is why (measured 2026-08-06).
|
||||
// "что у меня сегодня?" is an interrogative, a preposition, a particle and a day
|
||||
// word, so every token of it is frame and it left no content of its own. The
|
||||
// fast path called it an answer, the parked reminder read "сегодня" as its time,
|
||||
// and the question he asked was never answered. Asked alone the same sentence
|
||||
// routes to query at stage 0, so the route knew and was never consulted.
|
||||
func needsRoute(text string) bool {
|
||||
if isCancel(text) {
|
||||
return false
|
||||
}
|
||||
return len(ownContent(text)) > 0 || router.IsQuestionShaped(text)
|
||||
}
|
||||
+104
-36
@@ -53,6 +53,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/audio"
|
||||
"github.com/kami/maven/internal/crawl"
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
@@ -137,6 +138,24 @@ type reactiveHandler struct {
|
||||
// slot per reach, not one for the box. nil ⇒ no carry-over.
|
||||
dialogueSessions *dialogue.SessionStore
|
||||
|
||||
// decisions holds the last few turns' arbitration records (V-564): who
|
||||
// claimed the turn, who lost it and who was never asked. In memory and
|
||||
// bounded, because a turn record is read minutes later or never, and none
|
||||
// of his words belong in a table that outlives the diagnosis. nil ⇒ nothing
|
||||
// is recorded, which is what a test that did not ask for one gets.
|
||||
decisions *decision.Ring
|
||||
|
||||
// traces persists those same records (V-629, routingtrace.go). The ring is
|
||||
// still what /trace reads; this is the second sink, and it exists because the
|
||||
// routing heads cannot be fitted without real utterances. nil ⇒ the ring
|
||||
// alone, which is the behaviour every box had before 06-08-2026.
|
||||
traces traceWriter
|
||||
|
||||
// encoderID names the encoder body live on this box, stored beside each
|
||||
// trace: a fitted distance means nothing under another body. Empty ⇒ no
|
||||
// embedder, so the classifier was the keyword floor.
|
||||
encoderID string
|
||||
|
||||
// clarifyStore parks the request behind an open question she asked (see
|
||||
// clarify.go). nil ⇒ she falls back to the canned "не поняла" reply.
|
||||
clarifyStore *dialogue.ClarifyStore
|
||||
@@ -247,7 +266,31 @@ const (
|
||||
// path wraps it in stt/tts, the text path returns it as-is.
|
||||
//
|
||||
// The ordering is load-bearing — see the step comments.
|
||||
func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSource) string {
|
||||
func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSource) (reply string) {
|
||||
// 0. the decision record (V-564). Installed here rather than in the IPC
|
||||
// entry point, so the mic, telegram and the web all leave the same trail —
|
||||
// a record only the web produced would be missing exactly the turns that
|
||||
// are hardest to reproduce. It rides the context, costs a few dozen structs
|
||||
// on a human-rate path, and no claim site can change a route with it.
|
||||
if h.decisions != nil {
|
||||
var rec *decision.Record
|
||||
ctx, rec = decision.With(ctx, text)
|
||||
decision.Expect(ctx, decision.StagePreRoute, preRouteLadder)
|
||||
defer func() {
|
||||
done := rec.Finish(h.now())
|
||||
h.decisions.Push(done)
|
||||
h.persistDecision(ctx, done, src)
|
||||
}()
|
||||
}
|
||||
|
||||
// 0b. the turn's routing, computed at most once and shared (Vikunja #560).
|
||||
// The clarify resolver reads it to decide what this utterance IS before
|
||||
// claiming it, and step 5 acts on the same decision — routing twice would
|
||||
// cost a second on the resident model and could disagree with itself.
|
||||
now := h.now()
|
||||
rt := h.newTurnRoute(text, now)
|
||||
ctx = withTurnRoute(ctx, rt)
|
||||
|
||||
// 1. expired clarify — a question was parked but its TTL ran out, so the
|
||||
// request behind it is gone. Say that out loud (see clarify.go) and carry
|
||||
// on: these words are still routed as a fresh utterance below, with the
|
||||
@@ -263,7 +306,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// 2. confirm turn — if a destructive act is parked, this utterance is its
|
||||
// y/n answer, not a fresh command. Handled before routing so "да" doesn't
|
||||
// get classified as some other intent.
|
||||
if reply, handled := h.resolveConfirm(ctx, text); handled {
|
||||
if reply, handled := h.resolveConfirm(ctx, text); notePreRoute(ctx, "confirm", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
@@ -275,15 +318,27 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// so the notice is empty here in practice. withNotice anyway: every exit
|
||||
// from runTurn carries it, and that is what stops the next one from
|
||||
// forgetting.
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, text); handled {
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, text); notePreRoute(ctx, "clarify-answer", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
// It did not claim the turn. If it let a parked request go to get out of the
|
||||
// way, that has to be said in front of whatever these words are answered
|
||||
// with — carried on the same notice, so every exit below keeps it.
|
||||
expiredNotice = withNotice(expiredNotice, rt.dropped)
|
||||
|
||||
// 3b. and if it SUSPENDED a request instead of letting it go, the question
|
||||
// comes back on the end of whatever these words are answered with (Vikunja
|
||||
// #561). A deferred append rather than a call at each exit: there are eight
|
||||
// returns between here and the replier, and the flow has to survive all of
|
||||
// them — one that forgot would be a request parked for ever, waiting for an
|
||||
// answer to a question he never heard asked.
|
||||
defer func() { reply = withResumed(reply, rt.resume) }()
|
||||
|
||||
// 4. quiet-hours toggle — keyword match, not classifier-dependent.
|
||||
// "тихий режим" / "quiet on" would route through the classifier
|
||||
// unreliably (it's a command, not a free-form query), so we match it
|
||||
// before routing. Same pattern as the confirm turn above.
|
||||
if reply, handled := h.resolveQuietToggle(ctx, text, src); handled {
|
||||
if reply, handled := h.resolveQuietToggle(ctx, text, src); notePreRoute(ctx, "quiet-toggle", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
@@ -291,14 +346,14 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// sent. Only handled when a pending nudge is actually inside the window
|
||||
// (snooze.go); otherwise the words route normally, because "потом" is an
|
||||
// ordinary word and eating every one of them would break real sentences.
|
||||
if reply, handled := h.resolveSnooze(ctx, text, src); handled {
|
||||
if reply, handled := h.resolveSnooze(ctx, text, src); notePreRoute(ctx, "snooze", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
// 4c. spoken ack — "готово" closes that same nudge as `acted`. Only the
|
||||
// contentless form is intercepted here; "выпил воды" keeps routing and
|
||||
// closes the nudge after its fact lands (ackFromFact, step 8b).
|
||||
if reply, handled := h.resolveAck(ctx, text, src); handled {
|
||||
if reply, handled := h.resolveAck(ctx, text, src); notePreRoute(ctx, "ack", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
@@ -306,7 +361,15 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// turn and names what it should have been (repair.go). Before routing,
|
||||
// like the confirm and clarify turns: routing the correction as a fresh
|
||||
// utterance files the correction itself instead of fixing anything.
|
||||
if reply, handled := h.resolveRepair(ctx, text); handled {
|
||||
if reply, handled := h.resolveRepair(ctx, text); notePreRoute(ctx, "repair", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
// 4d-ii. and the same correction without a target — "нет, не так" (V-636).
|
||||
// After the targeted one, which is the narrower claim: an utterance that
|
||||
// names an intent is answered by redoing the request, and this rung only
|
||||
// gets the ones that name nothing.
|
||||
if reply, handled := h.resolveUntargetedRepair(ctx, text); notePreRoute(ctx, "repair-negative", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
@@ -314,7 +377,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// just read (ordinal.go). Before routing, and only when a list is actually
|
||||
// bound to the session: with nothing offered, "второй" is an ordinary word
|
||||
// and keeps routing.
|
||||
if reply, handled := h.resolveCandidate(ctx, text, src); handled {
|
||||
if reply, handled := h.resolveCandidate(ctx, text, src); notePreRoute(ctx, "ordinal", handled) {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
|
||||
@@ -323,22 +386,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// missing, so no amount of routing recovers it, and the model's guess
|
||||
// costs seconds to obtain and is close to a coin flip. Everything else
|
||||
// goes to the router.
|
||||
var (
|
||||
dec router.Decision
|
||||
err error
|
||||
prev *dialogue.Session
|
||||
)
|
||||
now := h.now()
|
||||
if h.dialogueSessions != nil {
|
||||
prev = h.dialogueSessions.Get(dialogueIDOf(ctx), now)
|
||||
}
|
||||
cont := false
|
||||
if dec, cont = continuationDecision(prev, text, now); cont {
|
||||
log.Printf("voice: continuation of %s from the previous turn", dec.Intent)
|
||||
}
|
||||
if !cont {
|
||||
dec, err = h.router.Route(ctx, text, now)
|
||||
}
|
||||
dec, cont, prev, err := rt.resolve(ctx)
|
||||
if err != nil {
|
||||
// ErrNoIntents ⇒ classifier unseeded (cold boot). reply with a
|
||||
// "still warming up" rather than a wire error.
|
||||
@@ -359,21 +407,31 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// ("а завтра?" … "а послезавтра?") keeps working.
|
||||
if h.dialogueSessions != nil {
|
||||
if !cont {
|
||||
dec = followUpMerge(prev, dec, now)
|
||||
merged := followUpMerge(prev, dec, now)
|
||||
noteMerge(ctx, dec, merged)
|
||||
dec = merged
|
||||
}
|
||||
if !dec.Clarify {
|
||||
h.rememberTurn(ctx, prev, dec, now)
|
||||
}
|
||||
}
|
||||
|
||||
// 7. clarify — she is not sure. If one named thing is missing, ask about it
|
||||
// and park the request (clarify.go); otherwise the replier's canned reply
|
||||
// stands.
|
||||
if dec.Clarify {
|
||||
// 7. clarify — something she needs is missing. If one named thing is missing,
|
||||
// ask about it and park the request (clarify.go); otherwise the replier's
|
||||
// canned reply stands.
|
||||
//
|
||||
// Not gated on dec.Clarify alone (Vikunja #557). A turn the cascade routed
|
||||
// confidently but incompletely skipped this entirely: "напомни позвонить"
|
||||
// reached applyAction, failed on the missing time, parked nothing, and the
|
||||
// "в семь вечера" that followed was web-searched as a world question. A
|
||||
// required slot that missingFor names is a gap whatever the confidence.
|
||||
if dec.Clarify || len(missingFor(dec)) > 0 {
|
||||
if reply := h.hexisBeforeClarify(ctx, dec); reply != "" {
|
||||
return withNotice(expiredNotice, reply)
|
||||
}
|
||||
if question, asked := h.askClarify(ctx, dec); asked {
|
||||
noteTerminal(ctx, "clarify-ask", dec.Intent,
|
||||
"the route was below the threshold, so she asked instead of acting")
|
||||
return withNotice(expiredNotice, question)
|
||||
}
|
||||
}
|
||||
@@ -390,6 +448,9 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
// the round-trip stays alive.
|
||||
replyText := h.applyAction(ctx, dec)
|
||||
log.Printf("voice: applyAction returned: %q", replyText)
|
||||
// A query turn was already claimed by a source inside the chain; every other
|
||||
// intent has no chain and no scoreboard, so the handler is the winner.
|
||||
noteTerminal(ctx, "action-handler", dec.Intent, "")
|
||||
|
||||
// 8b. a fact that answers a live nudge closes it as `acted` (ack.go).
|
||||
// Silent: the fact reply stands, she does not congratulate him for it.
|
||||
@@ -397,7 +458,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
|
||||
|
||||
// 9. replier — phrase the reply across the router decision.
|
||||
if replyText == "" {
|
||||
replyText = h.replier.Reply(dec)
|
||||
replyText = h.replier.Reply(ctx, dec)
|
||||
}
|
||||
return withNotice(expiredNotice, replyText)
|
||||
}
|
||||
@@ -490,6 +551,17 @@ func (h *reactiveHandler) replySystem(ctx context.Context, dec router.Decision)
|
||||
}
|
||||
}
|
||||
|
||||
// sessionAsTurn projects a stored session onto the dialogue.Turn shape used in
|
||||
// history lists. Shared by chatHistory and rememberTurn (clarify.go) so the
|
||||
// same session is described the same way in both places.
|
||||
func sessionAsTurn(s *dialogue.Session) dialogue.Turn {
|
||||
return dialogue.Turn{
|
||||
Intent: s.Intent,
|
||||
Slots: s.Slots,
|
||||
Text: s.Slots.Text,
|
||||
}
|
||||
}
|
||||
|
||||
// chatHistory collects dialogue turns from the session store for the current
|
||||
// conversation. Returns prior user utterances (newest last) up to a depth of
|
||||
// 4 turns. Returns nil when there's no session or no history.
|
||||
@@ -503,13 +575,9 @@ func (h *reactiveHandler) chatHistory(ctx context.Context) []dialogue.Turn {
|
||||
return nil
|
||||
}
|
||||
// History already includes the immediate prior turn (set by the dialogue
|
||||
// merge at lines 373-395), plus up to 3 more from deeper history.
|
||||
// merge in runTurn's step 6, above), plus up to 3 more from deeper history.
|
||||
out := make([]dialogue.Turn, 0, 1+len(prev.History))
|
||||
out = append(out, dialogue.Turn{
|
||||
Intent: prev.Intent,
|
||||
Slots: prev.Slots,
|
||||
Text: prev.Slots.Text,
|
||||
})
|
||||
out = append(out, sessionAsTurn(prev))
|
||||
out = append(out, prev.History...)
|
||||
return out
|
||||
}
|
||||
|
||||
+125
-15
@@ -11,6 +11,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/decision"
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/delivery/voicesink"
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
@@ -35,7 +36,9 @@ type voiceWiring struct {
|
||||
sessions *voice.Sessions
|
||||
voiceSink delivery.Sink
|
||||
embedder router.Embedder
|
||||
handler *reactiveHandler // the reactive handler for IPC Chat
|
||||
// heads — the routing heads, nil unless embedder.heads_path is set.
|
||||
heads *router.RouterHeads
|
||||
handler *reactiveHandler // the reactive handler for IPC Chat
|
||||
// worker clients (set when configured as Remote): closed on shutdown so
|
||||
// mavsttd / mavttsd don't keep a stale conn into a restarting daemon.
|
||||
sttClient *worker.Client
|
||||
@@ -52,7 +55,11 @@ type voiceWiring struct {
|
||||
// unless a `workstation` block names an address. Held here only so the
|
||||
// prober is stopped on shutdown; callers were handed it at build time.
|
||||
pair *llm.Pair
|
||||
mcp *mcpWiring
|
||||
// sttPair — CrisperWhisper 2.0 on the workstation with mavsttd as the
|
||||
// floor, nil unless the `workstation.stt` block names an address. Held for
|
||||
// the same reason as pair: to stop its prober on shutdown.
|
||||
sttPair *stt.Pair
|
||||
mcp *mcpWiring
|
||||
// home — the Home Assistant client, nil unless the `smarthome` block is
|
||||
// enabled (Vikunja #256). Its devices land in the same allowlist as every
|
||||
// other act, so nothing else here has to know about it.
|
||||
@@ -71,6 +78,9 @@ func (w *voiceWiring) close() {
|
||||
if w.embedder != nil {
|
||||
_ = w.embedder.Close()
|
||||
}
|
||||
if w.heads != nil {
|
||||
_ = w.heads.Close()
|
||||
}
|
||||
if w.server != nil {
|
||||
_ = w.server.Close()
|
||||
}
|
||||
@@ -83,6 +93,9 @@ func (w *voiceWiring) close() {
|
||||
if w.pair != nil {
|
||||
w.pair.Stop()
|
||||
}
|
||||
if w.sttPair != nil {
|
||||
w.sttPair.Stop()
|
||||
}
|
||||
w.mcp.close()
|
||||
}
|
||||
|
||||
@@ -111,6 +124,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
} else {
|
||||
transcriber = stt.NewStub()
|
||||
}
|
||||
transcriber, w.sttPair = sttSeam(cfg, transcriber)
|
||||
w.transcriber = transcriber
|
||||
|
||||
// ----- tts (Stub in-process OR Remote) -----
|
||||
@@ -146,8 +160,29 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
emb = router.NewHashEmbedder(1024)
|
||||
}
|
||||
w.embedder = emb
|
||||
|
||||
// ----- router: routing heads (only when configured, and never fatal) -----
|
||||
// A missing or broken weights file logs and leaves w.heads nil, which is
|
||||
// byte-for-byte the cascade that shipped before V-664. Refusing to start
|
||||
// over a routing accelerator would trade a working box for a better one.
|
||||
if cfg.Voice.Embedder != nil && cfg.Voice.Embedder.HeadsPath != "" {
|
||||
h, err := router.NewRouterHeads(
|
||||
cfg.Voice.Embedder.HeadsPath,
|
||||
cfg.Voice.Embedder.TokenizerPath,
|
||||
)
|
||||
if err != nil {
|
||||
log.Printf("voice: routing heads unavailable, cascade unchanged: %v", err)
|
||||
} else {
|
||||
log.Printf("voice: routing heads loaded from %s", cfg.Voice.Embedder.HeadsPath)
|
||||
w.heads = h
|
||||
}
|
||||
}
|
||||
|
||||
repairFactVectors(dataStore, emb)
|
||||
checkStoredEmbedder(dataStore, emb)
|
||||
// Retention is enforced on write, which is not enough on its own: a box that
|
||||
// goes quiet keeps every trace until the next sixty-fourth turn (V-629).
|
||||
pruneTracesOnStart(dataStore, time.Now())
|
||||
|
||||
// ----- tool executor (the enabled act allowlist, store-backed) -----
|
||||
// Config tools are the declarative bootstrap: seed them into the store as
|
||||
@@ -175,7 +210,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
// The LAN scanner (Vikunja #257): a read, bounded to the configured
|
||||
// subnets and rate-limited. Off unless the `netscan` block is enabled.
|
||||
w.netscan = wireNetScan(cfg, coreAPI)
|
||||
matcher := tool.NewMatcher(coreAPI)
|
||||
matcher := tool.NewMatcher(coreAPI).WithAliases(toolAliases(cfg.Voice.Tools))
|
||||
|
||||
// ----- weather provider (Open-Meteo when configured, Stub otherwise) -----
|
||||
var weatherProvider weather.Provider
|
||||
@@ -219,7 +254,8 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
// against the classifier's 50.0%, at about 1s a turn instead of 30ms (see
|
||||
// config.VoiceConfig.LLMRouter). The classifier always stays wired as the
|
||||
// fallback, so a model error never breaks a turn.
|
||||
rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.UseLLMRouter(), hot))
|
||||
rtr := buildRouter(emb, matcher, threshold,
|
||||
pickLLMRouter(cfg.Voice.UseLLMRouter(), hot), w.heads)
|
||||
|
||||
// ----- sessions registry (shared with voicesink) -----
|
||||
sessions := voice.NewSessions()
|
||||
@@ -235,21 +271,22 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
memStore = memory.NewInMemoryStore()
|
||||
}
|
||||
|
||||
// ----- dialogue (multi-turn slot carry-over; 2-min follow-up window) -----
|
||||
// ----- dialogue (multi-turn slot carry-over; dialogueSessionTTL follow-up window) -----
|
||||
// Store-backed when the daemon passes a store, so a restart mid-conversation
|
||||
// keeps the thread (Vikunja #363). Sessions past their TTL are dropped on
|
||||
// load, never revived. Clarify's parked question stays in memory only, and
|
||||
// that is a decision rather than an omission (Vikunja #385, docs/design.md):
|
||||
// a restart expires it, so the thread comes back and the open question does
|
||||
// not.
|
||||
const dialogueSessionTTL = 2 * time.Minute
|
||||
var dialogueSessions *dialogue.SessionStore
|
||||
if dataStore != nil {
|
||||
dialogueSessions = dialogue.NewPersistentSessionStore(2*time.Minute, dataStore)
|
||||
dialogueSessions = dialogue.NewPersistentSessionStore(dialogueSessionTTL, dataStore)
|
||||
if err := dialogueSessions.Load(context.Background(), time.Now()); err != nil {
|
||||
log.Printf("dialogue: load saved sessions: %v", err)
|
||||
}
|
||||
} else {
|
||||
dialogueSessions = dialogue.NewSessionStore(2 * time.Minute)
|
||||
dialogueSessions = dialogue.NewSessionStore(dialogueSessionTTL)
|
||||
}
|
||||
clarifyStore := dialogue.NewClarifyStore(clarifyTTL)
|
||||
timeParser := router.NewPythonDateParser()
|
||||
@@ -293,7 +330,17 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
},
|
||||
dataStore: dataStore,
|
||||
dialogueSessions: dialogueSessions,
|
||||
clarifyStore: clarifyStore,
|
||||
// Always on (V-564). The record is the instrument the rest of V-558 is
|
||||
// measured with, and one that only runs when a flag is set is not there
|
||||
// on the night the misroute happens.
|
||||
decisions: decision.NewRing(),
|
||||
// The second sink (V-629). Same records, persisted, because the routing
|
||||
// heads cannot be fitted from a 25-turn ring. Nil store ⇒ ring only, and
|
||||
// EmbedderID is the same string the vector marker uses, so a trace and a
|
||||
// stored vector name their body the same way.
|
||||
traces: traceSink(dataStore),
|
||||
encoderID: router.EmbedderID(emb),
|
||||
clarifyStore: clarifyStore,
|
||||
// 0 here (unset config) ⇒ the dialogue default.
|
||||
clarifyMaxAttempts: cfg.Voice.ClarifyMaxAttempts,
|
||||
extractor: router.Extractor{Time: timeParser, Acts: matcher, Facts: router.DefaultFactParser{}},
|
||||
@@ -351,6 +398,44 @@ func modelSeam(cfg *config.Config, resident *llm.Client) (router.Completer, *llm
|
||||
return pair, pair
|
||||
}
|
||||
|
||||
// sttSeam builds the transcription seam the voice path and the meeting
|
||||
// recorder share. It is modelSeam for audio and follows the same rule.
|
||||
//
|
||||
// With no `workstation.stt` block it hands back the floor untouched, which is
|
||||
// today's deploy exactly. With one, it is an stt.Pair preferring CrisperWhisper
|
||||
// 2.0 on workpc, which scores 10.4% WER in Russian against the floor's 27.5%
|
||||
// (docs/evals/2026-08-09-crisperwhisper2-russian-wer.md).
|
||||
//
|
||||
// Only the silent half of the degradation rule applies here. A worse transcript
|
||||
// is still a turn, so there is nothing to name a gap about and the fallback is
|
||||
// never spoken. That is why stt.Pair has no TranscribeRemote.
|
||||
func sttSeam(cfg *config.Config, floor stt.Transcriber) (stt.Transcriber, *stt.Pair) {
|
||||
if cfg.Workstation == nil || cfg.Workstation.Stt == nil {
|
||||
return floor, nil
|
||||
}
|
||||
s := cfg.Workstation.Stt
|
||||
lang := ""
|
||||
if cfg.Voice != nil {
|
||||
lang = cfg.Voice.Lang
|
||||
if cfg.Voice.Stt != nil && cfg.Voice.Stt.Lang != "" {
|
||||
lang = cfg.Voice.Stt.Lang
|
||||
}
|
||||
}
|
||||
pair := stt.NewPair(
|
||||
stt.NewHTTPTranscriber(s.URL, s.Token, lang, time.Duration(s.Timeout)),
|
||||
floor,
|
||||
s.Health,
|
||||
time.Duration(s.Probe),
|
||||
)
|
||||
pair.Start(context.Background())
|
||||
if s.Token == "" {
|
||||
log.Print("voice: the workstation transcriber has no token, so anything on the LAN can post audio to it")
|
||||
}
|
||||
log.Printf("voice: workstation transcriber at %s, probed every %s, mavsttd as the floor",
|
||||
s.URL, time.Duration(s.Probe))
|
||||
return pair, pair
|
||||
}
|
||||
|
||||
func pickLLMRouter(enabled bool, c router.Completer) *router.LLMRouter {
|
||||
if !enabled {
|
||||
return nil
|
||||
@@ -371,11 +456,12 @@ func pickLLMRouter(enabled bool, c router.Completer) *router.LLMRouter {
|
||||
// - The embedder is provided by wireVoice: HashEmbedder (floor) when no
|
||||
// embedder config is present, or the ONNX multilingual model when
|
||||
// configured — same interface, one constructor change.
|
||||
// - 6 bootstrap examples covering the 5 intents + one compound-capture
|
||||
// placeholder. Spec calls for ~10 per intent at production; this is the
|
||||
// bootstrapping floor swapped by tuning the seed set later.
|
||||
// - The classifier is floored by seedClassifier, which loads one file per
|
||||
// intent from seedDir (models/seeds/<intent>.txt) — see seedClassifier
|
||||
// below for the current intent list and file names.
|
||||
// - Threshold is from voice.router_threshold config (default 0.55).
|
||||
func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64, llmR *router.LLMRouter) *router.Router {
|
||||
func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
llmR *router.LLMRouter, heads *router.RouterHeads) *router.Router {
|
||||
cls := router.NewClassifier(emb)
|
||||
seedClassifier(cls)
|
||||
grammars := router.DefaultGrammars(acts)
|
||||
@@ -386,6 +472,10 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
grammars = append(grammars, router.AgendaQueryGrammars()...)
|
||||
// Same reason as the agenda rules, for the feeds: "что нового в лентах?"
|
||||
// routed system and answered "пока не умею" (Vikunja #474).
|
||||
// After the agenda rules, which are the narrower claim, and BEFORE the feed
|
||||
// and list rules, which are not: "что такое лента" is a definition question
|
||||
// and the feed rule would take it on the noun alone (V-655).
|
||||
grammars = append(grammars, router.WorldQueryGrammars()...)
|
||||
grammars = append(grammars, router.FeedQueryGrammar())
|
||||
// The list side of the same exposure: a phrasing with no possessive in it
|
||||
// ("список дел") routed system and never reached queryTasks (Vikunja #467).
|
||||
@@ -404,6 +494,10 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
// board noun), and before the capture marker, which would otherwise read
|
||||
// "убери из задач купить молоко" as a new task (Vikunja #512).
|
||||
grammars = append(grammars, router.TaskStatusGrammar())
|
||||
// Before the capture markers, which all need an object. A capture verb
|
||||
// alone is a fact with no key, and the clarify path asks for it rather than
|
||||
// letting the model invent an answer (Vikunja #557).
|
||||
grammars = append(grammars, router.BareCaptureGrammar()...)
|
||||
grammars = append(grammars, router.TaskCaptureGrammar())
|
||||
// After the capture marker, so "запиши" still wins over "расскажи", and
|
||||
// last overall because it matches on the first word alone: "расскажи про
|
||||
@@ -419,6 +513,7 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
},
|
||||
Threshold: threshold,
|
||||
LLM: llmR,
|
||||
Heads: heads,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -452,9 +547,10 @@ func seedPath() string {
|
||||
|
||||
// seedClassifier floors the embedded examples so the cold-boot path
|
||||
// doesn't return ErrNoIntents. Loads examples from seedDir — one file per
|
||||
// intent (act.txt, reminder.txt, fact.txt, note.txt, query.txt). When the
|
||||
// classifier can't decide it falls through to Clarify — the last-resort
|
||||
// path asks the user to rephrase rather than guessing wrong.
|
||||
// intent (act.txt, reminder.txt, fact.txt, note.txt, query.txt, chat.txt,
|
||||
// system.txt). When the classifier can't decide it falls through to
|
||||
// Clarify — the last-resort path asks the user to rephrase rather than
|
||||
// guessing wrong.
|
||||
func seedClassifier(c *router.Classifier) {
|
||||
intents := []router.Intent{
|
||||
router.IntentAct,
|
||||
@@ -504,6 +600,20 @@ func loadSeedFile(c *router.Classifier, intent router.Intent) (int, error) {
|
||||
return count, nil
|
||||
}
|
||||
|
||||
// toolAliases collects the spoken phrases per tool name. Without them the act
|
||||
// matcher only ever matched the English tool name, so no Russian utterance could
|
||||
// reach a tool and every homelab act fell to proposeGap (V-633).
|
||||
func toolAliases(tools []config.ToolConfig) map[string][]string {
|
||||
out := make(map[string][]string, len(tools))
|
||||
for _, tc := range tools {
|
||||
if tc.Name == "" || len(tc.Aliases) == 0 {
|
||||
continue
|
||||
}
|
||||
out[tc.Name] = tc.Aliases
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// seedTools upserts the config-declared tools into the store as enabled. Editing
|
||||
// mavend.json is a human act, so a config tool is enabled by definition; this
|
||||
// makes the declarative config the reproducible bootstrap while the store stays
|
||||
|
||||
+39
-9
@@ -7,6 +7,10 @@ package main
|
||||
import (
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// isWeatherQuery returns true if the utterance is about weather.
|
||||
@@ -27,16 +31,42 @@ func isWeatherQuery(u string) bool {
|
||||
// come through whole and "в 5 утра" does not.
|
||||
var weatherPlace = regexp.MustCompile(`(?i)(?:^|\s)(?:в|во|in)\s+([\p{L}-]+(?:\s+[\p{L}-]+)?)`)
|
||||
|
||||
// weatherNonPlaces — words that follow "в" in a weather question and are not
|
||||
// cities. "какая погода в доме" is the smart-home sensor, not Open-Meteo, and
|
||||
// "тепло в комнате" is the same question about the same room.
|
||||
var weatherNonPlaces = map[string]bool{
|
||||
// weatherRooms — the rooms of the house, which are the only words in this
|
||||
// guard that belong to it. "какая погода в доме" is the smart-home sensor, not
|
||||
// Open-Meteo, and "тепло в комнате" is the same question about the same room.
|
||||
//
|
||||
// The rest of the guard used to be a third copy of three closed sets that
|
||||
// already exist in the lexicon: the weekdays, the parts of the day, and the
|
||||
// words that follow "в" without naming a place (V-581). Each copy was short in
|
||||
// its own direction — "среду" but not "среде", "утром" but not "утра", "целом"
|
||||
// but not "общем" — so the same question phrased one word differently reached
|
||||
// the geocoder as a city.
|
||||
var weatherRooms = map[string]bool{
|
||||
"доме": true, "квартире": true, "комнате": true, "спальне": true,
|
||||
"гостиной": true, "кухне": true, "гараже": true, "офисе": true,
|
||||
"выходные": true, "субботу": true, "воскресенье": true, "понедельник": true,
|
||||
"вторник": true, "среду": true, "четверг": true, "пятницу": true,
|
||||
"обед": true, "обеде": true, "утро": true, "утром": true, "вечер": true,
|
||||
"вечером": true, "ночь": true, "ночью": true, "целом": true, "принципе": true,
|
||||
"обед": true, "обеде": true, "выходные": true, "выходных": true,
|
||||
}
|
||||
|
||||
// isWeatherNonPlace reports whether the word after "в" names something other
|
||||
// than a place he could ask the weather for.
|
||||
func isWeatherNonPlace(word string) bool {
|
||||
if weatherRooms[word] {
|
||||
return true
|
||||
}
|
||||
if _, ok := router.WeekdayIndex(word); ok {
|
||||
return true
|
||||
}
|
||||
for _, w := range lexicon.PartsOfDay() {
|
||||
if word == w || morph.SameWord(word, w) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
for _, w := range lexicon.NotPlaceAfterV() {
|
||||
if word == w {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// extractWeatherLocation returns the place he named, or the configured default
|
||||
@@ -63,7 +93,7 @@ func extractWeatherLocation(u, defaultLoc string) string {
|
||||
}
|
||||
place := strings.TrimSpace(m[1])
|
||||
first := strings.ToLower(strings.Fields(place)[0])
|
||||
if weatherNonPlaces[first] {
|
||||
if isWeatherNonPlace(first) {
|
||||
return defaultLoc
|
||||
}
|
||||
return place
|
||||
|
||||
@@ -29,6 +29,13 @@ func TestExtractWeatherLocation(t *testing.T) {
|
||||
// the house sensors and the day words answer elsewhere.
|
||||
{"тепло в комнате?", "Berlin", "Berlin"},
|
||||
{"какая погода в выходные", "Berlin", "Berlin"},
|
||||
// The cases the three private copies of the lexicon were short by
|
||||
// (V-581): a weekday in a case the old map did not list, a part of the
|
||||
// day in one it did not list, and "в общем".
|
||||
{"какая погода в среде", "Berlin", "Berlin"},
|
||||
{"какая погода в воскресеньях", "Berlin", "Berlin"},
|
||||
{"какая погода в понедельникам", "Berlin", "Berlin"},
|
||||
{"какая погода в общем", "Berlin", "Berlin"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
if got := extractWeatherLocation(c.utterance, c.def); got != c.want {
|
||||
|
||||
+13
-4
@@ -34,22 +34,31 @@ type probe struct {
|
||||
drmDev string
|
||||
}
|
||||
|
||||
// foreign lists every ROCm process that is not ours. selfPID is the supervisor's
|
||||
// llama-server child, or 0 when it is not running.
|
||||
// foreign lists every ROCm process that is not ours. self holds the pids of the
|
||||
// supervisor's own children, and a child that is not running contributes 0.
|
||||
//
|
||||
// There is more than one child since 09-08-2026. CW2 registers on the KFD like
|
||||
// any ROCm job, so a supervisor that excluded only llama-server would read its
|
||||
// own transcriber as a contender, yield the card to it, and never keep a model
|
||||
// loaded again.
|
||||
//
|
||||
// An unreadable kfd tree returns no processes and no error. That is deliberate
|
||||
// and it is the safe direction only because startVRAM also has to agree before
|
||||
// anything launches: a supervisor that cannot see the KFD never sees free VRAM
|
||||
// either, because the CPT run holding the card shows up in the drm totals.
|
||||
func (p probe) foreign(selfPID int) []gpuProc {
|
||||
func (p probe) foreign(self ...int) []gpuProc {
|
||||
entries, err := os.ReadDir(p.kfdRoot)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
mine := make(map[int]bool, len(self))
|
||||
for _, pid := range self {
|
||||
mine[pid] = true
|
||||
}
|
||||
var out []gpuProc
|
||||
for _, e := range entries {
|
||||
pid, err := strconv.Atoi(e.Name())
|
||||
if err != nil || pid == selfPID {
|
||||
if err != nil || mine[pid] {
|
||||
continue
|
||||
}
|
||||
out = append(out, gpuProc{
|
||||
|
||||
+46
-1
@@ -1,6 +1,7 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"net/url"
|
||||
@@ -8,6 +9,7 @@ import (
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// fakeKFD builds the sysfs shape the workstation actually has: one directory
|
||||
@@ -47,6 +49,24 @@ func TestForeignExcludesOurChild(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The transcriber is a ROCm process on the same card, so it registers on the
|
||||
// KFD exactly like a contender does. Reading it as one is what happened on
|
||||
// 2026-08-09 while CW2 ran under its own systemd unit: mavgpud yielded, waited
|
||||
// five polls, loaded the model, yielded again, and never held it for a whole
|
||||
// minute. Excluding every child is the fix and this is the test of it.
|
||||
func TestForeignExcludesEveryChild(t *testing.T) {
|
||||
p := probe{kfdRoot: fakeKFD(t, map[int]int64{478104: 12791693312, 999: 4096, 1001: 1717986918})}
|
||||
|
||||
ours := p.foreign(999, 1001)
|
||||
if len(ours) != 1 || ours[0].PID != 478104 {
|
||||
t.Fatalf("only the CPT run is a contender, got %+v", ours)
|
||||
}
|
||||
// A child that is not running reports pid 0, which must exclude nothing.
|
||||
if got := p.foreign(999, 0); len(got) != 2 {
|
||||
t.Errorf("a stopped child excludes nobody: got %d contenders, want 2", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
// An empty KFD tree is the state that permits a start, so it must read as empty
|
||||
// rather than as an error the caller has to interpret.
|
||||
func TestForeignEmptyAndMissing(t *testing.T) {
|
||||
@@ -81,7 +101,7 @@ func TestFreeVRAM(t *testing.T) {
|
||||
// rather than hanging or proxying into a closed port. Maven reads this endpoint
|
||||
// on a timer forever, including while the workstation is busy.
|
||||
func TestHealthAndProxyRefuseWhenNotReady(t *testing.T) {
|
||||
s := &supervisor{run: newRunner("/bin/true", nil, "")}
|
||||
s := &supervisor{run: newRunner("fake", "/bin/true", nil, "")}
|
||||
h := s.handler(mustURL(t, "http://127.0.0.1:1"))
|
||||
|
||||
for _, path := range []string{"/health", "/v1/chat/completions"} {
|
||||
@@ -101,3 +121,28 @@ func mustURL(t *testing.T, s string) *url.URL {
|
||||
}
|
||||
return u
|
||||
}
|
||||
|
||||
// Yielding is all or nothing. A CPT run wants the whole card, so handing back
|
||||
// the language model while the transcriber keeps 1.6GB mapped would leave the
|
||||
// other job failing its allocation, which is the outcome yielding exists to
|
||||
// prevent.
|
||||
func TestYieldStopsEveryChild(t *testing.T) {
|
||||
idle := "while : ; do sleep 1 ; done"
|
||||
s := &supervisor{
|
||||
cfg: config{EvictAfter: 1, StopGrace: duration(2 * time.Second)},
|
||||
probe: probe{kfdRoot: fakeKFD(t, map[int]int64{478104: 12791693312})},
|
||||
run: newRunner("llama-server", fakeServer(t, idle), nil, ""),
|
||||
stt: newRunner("cw2", fakeServer(t, idle), nil, ""),
|
||||
}
|
||||
for _, r := range s.children() {
|
||||
if err := r.start(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
s.tick(context.Background())
|
||||
for _, r := range s.children() {
|
||||
if r.running() {
|
||||
t.Errorf("%s outlived the yield", r.name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
+90
-17
@@ -10,6 +10,11 @@
|
||||
// the card. Not on demand, because a 7-14B takes tens of seconds to load and a
|
||||
// world question would be answered by a gap every time the card had been quiet.
|
||||
// Not always on, because that holds 16GB against the owner's own jobs.
|
||||
//
|
||||
// It supervises a second child since 09-08-2026, the CW2 transcriber, and for
|
||||
// one reason only: it is a ROCm process on the same card. Any GPU service the
|
||||
// owner leaves running beside this daemon reads as a contender and evicts the
|
||||
// model, so the card needs one owner rather than two neighbours.
|
||||
package main
|
||||
|
||||
import (
|
||||
@@ -36,6 +41,10 @@ type config struct {
|
||||
// owner's business and not this daemon's schema.
|
||||
LlamaArgs []string `json:"llama_args"`
|
||||
|
||||
// Stt is optional. Without it mavgpud supervises llama-server alone, which
|
||||
// is everything it did before 09-08-2026.
|
||||
Stt *sttConfig `json:"stt,omitempty"`
|
||||
|
||||
KFDRoot string `json:"kfd_root"`
|
||||
DRMDevice string `json:"drm_device"`
|
||||
|
||||
@@ -51,6 +60,22 @@ type config struct {
|
||||
StartAfter int `json:"start_after_polls"`
|
||||
}
|
||||
|
||||
// sttConfig is the CW2 transcriber, which mavgpud runs for one reason: it is a
|
||||
// ROCm process on this card. Left to its own systemd unit it registers on the
|
||||
// KFD, the supervisor reads it as a contender, and llama-server is evicted
|
||||
// within two polls and restarted five polls later, forever. That thrash was
|
||||
// observed on 2026-08-09 and it is what folded the service in here.
|
||||
//
|
||||
// Maven talks to it directly, not through this daemon. There is no proxy and no
|
||||
// idle timer: at 1.6GB it denies the card to nobody, and unloading it would only
|
||||
// send the next voice turn to the homesrv floor for no gain.
|
||||
type sttConfig struct {
|
||||
// Addr is where the service binds, and it is read only to probe /health.
|
||||
Addr string `json:"addr"`
|
||||
Bin string `json:"bin"`
|
||||
Args []string `json:"args"`
|
||||
}
|
||||
|
||||
func defaults() config {
|
||||
return config{
|
||||
Listen: ":8080",
|
||||
@@ -99,12 +124,18 @@ func main() {
|
||||
}
|
||||
|
||||
base := "http://" + cfg.LlamaAddr
|
||||
run := newRunner(cfg.LlamaBin, cfg.LlamaArgs, base+"/health")
|
||||
run := newRunner("llama-server", cfg.LlamaBin, cfg.LlamaArgs, base+"/health")
|
||||
sup := &supervisor{
|
||||
cfg: cfg,
|
||||
probe: probe{kfdRoot: cfg.KFDRoot, drmDev: cfg.DRMDevice},
|
||||
run: run,
|
||||
}
|
||||
if s := cfg.Stt; s != nil {
|
||||
if s.Bin == "" || s.Addr == "" {
|
||||
log.Fatal("mavgpud: stt needs both bin and addr")
|
||||
}
|
||||
sup.stt = newRunner("cw2", s.Bin, s.Args, "http://"+s.Addr+"/health")
|
||||
}
|
||||
sup.touch()
|
||||
|
||||
ctx, cancel := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
|
||||
@@ -129,13 +160,17 @@ func main() {
|
||||
shut, done := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
defer done()
|
||||
_ = srv.Shutdown(shut)
|
||||
run.stop(time.Duration(cfg.StopGrace))
|
||||
for _, r := range sup.children() {
|
||||
r.stop(time.Duration(cfg.StopGrace))
|
||||
}
|
||||
}
|
||||
|
||||
type supervisor struct {
|
||||
cfg config
|
||||
probe probe
|
||||
run *runner
|
||||
// stt is the CW2 transcriber, or nil when the config names none.
|
||||
stt *runner
|
||||
|
||||
lastReq atomic.Int64 // unix nanos of the last request Maven sent
|
||||
|
||||
@@ -198,7 +233,11 @@ func (s *supervisor) loop(ctx context.Context) {
|
||||
// allocates, so we see a contender during its startup rather than after it has
|
||||
// already failed to get the memory it wanted.
|
||||
func (s *supervisor) tick(ctx context.Context) {
|
||||
others := s.probe.foreign(s.run.pid())
|
||||
var pids []int
|
||||
for _, r := range s.children() {
|
||||
pids = append(pids, r.pid())
|
||||
}
|
||||
others := s.probe.foreign(pids...)
|
||||
if len(others) > 0 {
|
||||
s.foreignStreak++
|
||||
s.clearStreak = 0
|
||||
@@ -207,31 +246,65 @@ func (s *supervisor) tick(ctx context.Context) {
|
||||
s.clearStreak++
|
||||
}
|
||||
|
||||
if s.run.running() {
|
||||
s.run.refreshReady(ctx)
|
||||
switch {
|
||||
case s.foreignStreak >= s.cfg.EvictAfter:
|
||||
log.Printf("mavgpud: yielding the card to %s", describe(others))
|
||||
s.run.stop(time.Duration(s.cfg.StopGrace))
|
||||
case s.idle() > time.Duration(s.cfg.IdleTimeout):
|
||||
log.Printf("mavgpud: idle for %s, unloading", s.idle().Round(time.Second))
|
||||
s.run.stop(time.Duration(s.cfg.StopGrace))
|
||||
// Yielding is all or nothing. A CPT run wants the whole card, and handing
|
||||
// back 8GB while holding 1.6GB is the shape of a failed allocation.
|
||||
if s.foreignStreak >= s.cfg.EvictAfter && s.anyRunning() {
|
||||
log.Printf("mavgpud: yielding the card to %s", describe(others))
|
||||
for _, r := range s.children() {
|
||||
r.stop(time.Duration(s.cfg.StopGrace))
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
if s.clearStreak < s.cfg.StartAfter {
|
||||
clear := s.clearStreak >= s.cfg.StartAfter
|
||||
|
||||
if s.run.running() {
|
||||
s.run.refreshReady(ctx)
|
||||
if s.idle() > time.Duration(s.cfg.IdleTimeout) {
|
||||
log.Printf("mavgpud: idle for %s, unloading", s.idle().Round(time.Second))
|
||||
s.run.stop(time.Duration(s.cfg.StopGrace))
|
||||
}
|
||||
} else if clear && s.probe.freeVRAM() >= s.cfg.MinFreeVRAM {
|
||||
s.touch() // the idle clock starts at load, not at the last request before it
|
||||
if err := s.run.start(); err != nil {
|
||||
log.Printf("mavgpud: start llama-server: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
if s.stt == nil {
|
||||
return
|
||||
}
|
||||
if free := s.probe.freeVRAM(); free < s.cfg.MinFreeVRAM {
|
||||
if s.stt.running() {
|
||||
s.stt.refreshReady(ctx)
|
||||
return
|
||||
}
|
||||
s.touch() // the idle clock starts at load, not at the last request before it
|
||||
if err := s.run.start(); err != nil {
|
||||
log.Printf("mavgpud: start llama-server: %v", err)
|
||||
// No VRAM precondition here, unlike llama-server. That check exists because
|
||||
// a 12B refuses to load when the card is short, and 1.6GB fits wherever the
|
||||
// KFD is clear. Reading free VRAM would also block the transcriber for good
|
||||
// once the language model was resident, since it holds more than the floor.
|
||||
if clear {
|
||||
if err := s.stt.start(); err != nil {
|
||||
log.Printf("mavgpud: start cw2: %v", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (s *supervisor) children() []*runner {
|
||||
if s.stt == nil {
|
||||
return []*runner{s.run}
|
||||
}
|
||||
return []*runner{s.run, s.stt}
|
||||
}
|
||||
|
||||
func (s *supervisor) anyRunning() bool {
|
||||
for _, r := range s.children() {
|
||||
if r.running() {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// describe names the contenders in the log. This log is the instrument for the
|
||||
// open question in #488: whether polling the KFD misses a job that wants the
|
||||
// card without registering there.
|
||||
|
||||
+17
-13
@@ -10,14 +10,18 @@ import (
|
||||
"time"
|
||||
)
|
||||
|
||||
// runner owns one llama-server process. Owning it is the point of the daemon:
|
||||
// the workstation cannot keep a 7-14B resident, because that holds 16GB against
|
||||
// runner owns one GPU process. Owning it is the point of the daemon: the
|
||||
// workstation cannot keep a 7-14B resident, because that holds 16GB against
|
||||
// the owner's CPT runs, Correx and the manga-recap pipeline. So the thing that
|
||||
// stays up is this, which costs no VRAM, and the model comes and goes under it.
|
||||
//
|
||||
// There are two of them since 09-08-2026: llama-server and the CW2 transcriber.
|
||||
// name is what the log calls this one.
|
||||
type runner struct {
|
||||
name string
|
||||
bin string
|
||||
args []string
|
||||
// ready is llama-server's own /health, which answers "is a model loaded".
|
||||
// ready is the child's own /health, which answers "is a model loaded".
|
||||
// Loading a 7-14B takes tens of seconds, so started is not ready.
|
||||
readyURL string
|
||||
|
||||
@@ -32,9 +36,9 @@ type runner struct {
|
||||
http *http.Client
|
||||
}
|
||||
|
||||
func newRunner(bin string, args []string, readyURL string) *runner {
|
||||
func newRunner(name, bin string, args []string, readyURL string) *runner {
|
||||
return &runner{
|
||||
bin: bin, args: args, readyURL: readyURL,
|
||||
name: name, bin: bin, args: args, readyURL: readyURL,
|
||||
http: &http.Client{Timeout: 2 * time.Second},
|
||||
}
|
||||
}
|
||||
@@ -60,7 +64,7 @@ func (r *runner) isReady() bool {
|
||||
return r.ready
|
||||
}
|
||||
|
||||
// start launches llama-server. It returns as soon as the process exists, not
|
||||
// start launches the child. It returns as soon as the process exists, not
|
||||
// when the model is loaded.
|
||||
func (r *runner) start() error {
|
||||
r.mu.Lock()
|
||||
@@ -76,7 +80,7 @@ func (r *runner) start() error {
|
||||
return err
|
||||
}
|
||||
r.cmd, r.ready, r.yielding = cmd, false, false
|
||||
log.Printf("mavgpud: started llama-server pid=%d", cmd.Process.Pid)
|
||||
log.Printf("mavgpud: started %s pid=%d", r.name, cmd.Process.Pid)
|
||||
go func() {
|
||||
err := cmd.Wait()
|
||||
r.mu.Lock()
|
||||
@@ -84,15 +88,15 @@ func (r *runner) start() error {
|
||||
r.cmd, r.ready, r.yielding = nil, false, false
|
||||
r.mu.Unlock()
|
||||
if yielded {
|
||||
log.Printf("mavgpud: llama-server stopped, card yielded (%v)", err)
|
||||
log.Printf("mavgpud: %s stopped, card yielded (%v)", r.name, err)
|
||||
return
|
||||
}
|
||||
log.Printf("mavgpud: llama-server exited: %v", err)
|
||||
log.Printf("mavgpud: %s exited: %v", r.name, err)
|
||||
}()
|
||||
return nil
|
||||
}
|
||||
|
||||
// stop ends llama-server and waits for the VRAM to come back. SIGTERM first so
|
||||
// stop ends the child and waits for the VRAM to come back. SIGTERM first so
|
||||
// it unmaps cleanly, SIGKILL after the grace window. Returning before the
|
||||
// process is gone would let the supervisor report a free card while 14GB is
|
||||
// still mapped, which is the one lie that would make yielding useless.
|
||||
@@ -117,11 +121,11 @@ func (r *runner) stop(grace time.Duration) {
|
||||
}
|
||||
time.Sleep(100 * time.Millisecond)
|
||||
}
|
||||
log.Printf("mavgpud: llama-server did not exit in %s, killing", grace)
|
||||
log.Printf("mavgpud: %s did not exit in %s, killing", r.name, grace)
|
||||
_ = syscall.Kill(pgid, syscall.SIGKILL)
|
||||
}
|
||||
|
||||
// refreshReady asks llama-server whether the model is loaded. Called once per
|
||||
// refreshReady asks the child whether the model is loaded. Called once per
|
||||
// supervisor tick, never per request.
|
||||
func (r *runner) refreshReady(ctx context.Context) {
|
||||
if !r.running() {
|
||||
@@ -141,6 +145,6 @@ func (r *runner) refreshReady(ctx context.Context) {
|
||||
r.ready = ok
|
||||
r.mu.Unlock()
|
||||
if ok && !was {
|
||||
log.Printf("mavgpud: model ready")
|
||||
log.Printf("mavgpud: %s ready", r.name)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -25,7 +25,7 @@ func fakeServer(t *testing.T, body string) string {
|
||||
// status of a routine yield is identical to that of a real crash. Reading the
|
||||
// mavgpud log, the two were indistinguishable (Vikunja #491).
|
||||
func TestStopMarksTheExitAsAYield(t *testing.T) {
|
||||
r := newRunner(fakeServer(t, "while : ; do sleep 1 ; done"), nil, "")
|
||||
r := newRunner("fake", fakeServer(t, "while : ; do sleep 1 ; done"), nil, "")
|
||||
if err := r.start(); err != nil {
|
||||
t.Fatalf("start: %v", err)
|
||||
}
|
||||
@@ -49,7 +49,7 @@ func TestStopMarksTheExitAsAYield(t *testing.T) {
|
||||
// Stopping when nothing is running must not arm the flag for the next child.
|
||||
// The next exit after that would be a real crash logged as a yield.
|
||||
func TestStopWithNoChildDoesNotArmTheFlag(t *testing.T) {
|
||||
r := newRunner("/nonexistent", nil, "")
|
||||
r := newRunner("fake", "/nonexistent", nil, "")
|
||||
r.stop(10 * time.Millisecond)
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
|
||||
+139
-58
@@ -6,10 +6,11 @@
|
||||
// restart-free, fail-independent — a crashing poller can't touch the store key
|
||||
// (it never had it), worst case a stale env fact until the next tick.
|
||||
//
|
||||
// Two sources, each its own provenance (the loop's rules trust source):
|
||||
// Four sources, each its own provenance (the loop's rules trust source):
|
||||
// - netdata → poll:netdata resource alarms (disk/mem/cert/temp)
|
||||
// - kuma → poll:uptimekuma service up/down (the source of truth for it)
|
||||
// - zenmoney → poll:zenmoney spending/income totals (Vikunja #125)
|
||||
// - wireguard → infer:wg latest handshake, the presence signal
|
||||
//
|
||||
// The zenmoney source is why the token lives HERE and not in core: the poller
|
||||
// already owns every other third-party credential, it holds no store key, and
|
||||
@@ -76,27 +77,31 @@ func run(args []string) error {
|
||||
if *netdataURL == "" && *kumaURL == "" && *wgIface == "" && *zenTokenFile == "" {
|
||||
return fmt.Errorf("nothing to poll: set -netdata, -kuma, -wg and/or -zenmoney-token-file")
|
||||
}
|
||||
// A bad duration or an empty -wg-cmd used to get past start and kill the
|
||||
// poller on the first tick — time.NewTicker panics on a non-positive
|
||||
// interval, and pollWg indexed field 0 of an empty command. A zero -timeout
|
||||
// is worse than a crash: http.Client reads it as "no deadline", so one
|
||||
// wedged source stalls every other source behind it forever. Refuse all
|
||||
// three here, where the operator sees the message.
|
||||
if *interval <= 0 {
|
||||
return fmt.Errorf("-interval must be positive, got %s", *interval)
|
||||
}
|
||||
if *timeout <= 0 {
|
||||
return fmt.Errorf("-timeout must be positive, got %s", *timeout)
|
||||
}
|
||||
if *wgIface != "" && strings.TrimSpace(*wgCmd) == "" {
|
||||
return fmt.Errorf("-wg-cmd is empty but -wg is set")
|
||||
}
|
||||
|
||||
// The token is read from a file, never taken as a flag value: an argv token
|
||||
// is visible in `ps` to every user on the box and lands in the compose file
|
||||
// and the shell history. Read once at start — a rotated token means a
|
||||
// restart, which is cheaper than re-reading his credential every hour.
|
||||
var zen *zenmoney.Client
|
||||
if *zenTokenFile != "" {
|
||||
raw, err := os.ReadFile(*zenTokenFile)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read zenmoney token: %w", err)
|
||||
}
|
||||
zen, err = zenmoney.New(strings.TrimSpace(string(raw)), *zenURL, *timeout*3)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
zen, err := newZenClient(*zenTokenFile, *zenURL, *timeout)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
|
||||
defer stop()
|
||||
|
||||
core, err := ipc.DialWait(*socket, 60*time.Second)
|
||||
core, err := ipc.DialWait(*socket, coreDialWait)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -117,14 +122,46 @@ func run(args []string) error {
|
||||
// The token is never logged, not even its length.
|
||||
log.Printf("mavpoll: polling every %s (netdata=%q kuma=%q wg=%q zenmoney=%v every %s)",
|
||||
*interval, *netdataURL, *kumaURL, *wgIface, zen != nil, *zenInterval)
|
||||
p.loop(ctx, *interval)
|
||||
return nil
|
||||
}
|
||||
|
||||
// coreDialWait — how long to wait for core's socket at start. The poller and
|
||||
// core come up together under compose, so a cold start is a wait, not a failure.
|
||||
const coreDialWait = 60 * time.Second
|
||||
|
||||
// zenTimeoutFactor — the zenmoney client gets a longer deadline than the other
|
||||
// sources. A diff call walks his whole transaction history, where netdata and
|
||||
// kuma answer from memory.
|
||||
const zenTimeoutFactor = 3
|
||||
|
||||
// newZenClient builds the money client, or nil when no token file was given.
|
||||
//
|
||||
// The token is read from a file, never taken as a flag value: an argv token is
|
||||
// visible in `ps` to every user on the box and lands in the compose file and
|
||||
// the shell history. Read once at start — a rotated token means a restart,
|
||||
// which is cheaper than re-reading his credential every hour.
|
||||
func newZenClient(tokenFile, baseURL string, timeout time.Duration) (*zenmoney.Client, error) {
|
||||
if tokenFile == "" {
|
||||
return nil, nil
|
||||
}
|
||||
raw, err := os.ReadFile(tokenFile)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read zenmoney token: %w", err)
|
||||
}
|
||||
return zenmoney.New(strings.TrimSpace(string(raw)), baseURL, timeout*zenTimeoutFactor)
|
||||
}
|
||||
|
||||
// loop polls until the context is cancelled.
|
||||
func (p *poller) loop(ctx context.Context, interval time.Duration) {
|
||||
p.pollOnce(ctx) // fire immediately; don't idle a full interval on start
|
||||
t := time.NewTicker(*interval)
|
||||
t := time.NewTicker(interval)
|
||||
defer t.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
log.Printf("mavpoll: bye")
|
||||
return nil
|
||||
return
|
||||
case <-t.C:
|
||||
p.pollOnce(ctx)
|
||||
}
|
||||
@@ -151,8 +188,8 @@ type poller struct {
|
||||
zenLast time.Time
|
||||
}
|
||||
|
||||
// pollOnce — one sweep of both sources. A failure in one source logs and does
|
||||
// NOT abort the other: netdata being down shouldn't blind kuma and vice versa.
|
||||
// pollOnce — one sweep of every configured source. A failure in one logs and
|
||||
// does NOT abort the rest: netdata being down shouldn't blind kuma.
|
||||
func (p *poller) pollOnce(ctx context.Context) {
|
||||
now := time.Now()
|
||||
if p.netdataURL != "" {
|
||||
@@ -244,6 +281,14 @@ func (p *poller) pollZenmoney(ctx context.Context, now time.Time) error {
|
||||
|
||||
// ---- wireguard: latest handshake → presence signal -------------------------
|
||||
|
||||
const (
|
||||
// wgFactKey / wgSource — the presence signal, read by the decay in core.
|
||||
// The source says infer because a handshake is evidence he is home, not a
|
||||
// reading of where he is.
|
||||
wgFactKey = "wg_handshake"
|
||||
wgSource = "infer:wg"
|
||||
)
|
||||
|
||||
// pollWg reads `wg show <iface> latest-handshakes` and writes a wg_handshake
|
||||
// fact (source=infer:wg) stamped with the MOST RECENT peer handshake time — not
|
||||
// now(). Presence decays from the real handshake instant, so the fact's ts must
|
||||
@@ -253,9 +298,19 @@ func (p *poller) pollZenmoney(ctx context.Context, now time.Time) error {
|
||||
// `wg show` needs CAP_NET_ADMIN; run mavpoll with the cap or set -wg-cmd "sudo wg".
|
||||
func (p *poller) pollWg(ctx context.Context) error {
|
||||
fields := strings.Fields(p.wgCmd)
|
||||
if len(fields) == 0 {
|
||||
return fmt.Errorf("wg command is empty")
|
||||
}
|
||||
args := append(fields[1:], "show", p.wgIface, "latest-handshakes")
|
||||
out, err := exec.CommandContext(ctx, fields[0], args...).Output()
|
||||
if err != nil {
|
||||
// wg says why it refused on stderr — usually a missing CAP_NET_ADMIN or
|
||||
// an interface that does not exist. Output() drops that, leaving a log
|
||||
// line that reads "exit status 1" and diagnoses nothing.
|
||||
var ee *exec.ExitError
|
||||
if errors.As(err, &ee) && len(ee.Stderr) > 0 {
|
||||
return fmt.Errorf("run %s: %w: %s", p.wgCmd, err, strings.TrimSpace(string(ee.Stderr)))
|
||||
}
|
||||
return fmt.Errorf("run %s: %w", p.wgCmd, err)
|
||||
}
|
||||
maxTs := parseMaxHandshake(string(out))
|
||||
@@ -263,20 +318,19 @@ func (p *poller) pollWg(ctx context.Context) error {
|
||||
return nil // no peer has ever handshaked → drop out of presence
|
||||
}
|
||||
hs := time.Unix(maxTs, 0)
|
||||
prev, err := p.core.LatestFactBySource(ctx, "wg_handshake", "infer:wg")
|
||||
prev, err := p.core.LatestFactBySource(ctx, wgFactKey, wgSource)
|
||||
if err == nil && !hs.After(prev.Ts) {
|
||||
return nil // not newer → no churn
|
||||
}
|
||||
if err != nil && err != ipc.ErrNoFact && !isNoFact(err) {
|
||||
return fmt.Errorf("read wg_handshake: %w", err)
|
||||
if err != nil && !isNoFact(err) {
|
||||
return fmt.Errorf("read %s: %w", wgFactKey, err)
|
||||
}
|
||||
if _, err := p.core.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: hs, Kind: "env", Key: "wg_handshake", Value: `"up"`,
|
||||
Source: "infer:wg", Confidence: 1.0,
|
||||
}); err != nil {
|
||||
return fmt.Errorf("write wg_handshake: %w", err)
|
||||
// The ts is the handshake instant, not now(): presence decays from when he
|
||||
// was last seen.
|
||||
if err := p.writeFact(ctx, wgFactKey, wgSource, `"up"`, hs); err != nil {
|
||||
return err
|
||||
}
|
||||
log.Printf("mavpoll: wg_handshake @ %s (infer:wg)", hs.Format(time.RFC3339))
|
||||
log.Printf("mavpoll: %s @ %s (%s)", wgFactKey, hs.Format(time.RFC3339), wgSource)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -431,29 +485,53 @@ func kumaState(v float64) string {
|
||||
|
||||
// ---- helpers ---------------------------------------------------------------
|
||||
|
||||
// writeIfChanged writes a `facts(kind=env)` row only when val differs from the
|
||||
// latest fact for (key, source). Values are stored JSON-encoded (the store's
|
||||
// convention: `"down"`, `"critical"`), matching how rules compare f.Value.
|
||||
func (p *poller) writeIfChanged(ctx context.Context, key, source, val string, now time.Time) error {
|
||||
jv, _ := json.Marshal(val) // string never fails to marshal
|
||||
// factConfidence — every poll is a direct reading of another service, never an
|
||||
// inference, so the fact goes in at full confidence.
|
||||
const factConfidence = 1.0
|
||||
|
||||
// unchanged reports whether the latest fact for (key, source) already holds
|
||||
// jsonVal. A missing fact is not an error here, it is the first write.
|
||||
func (p *poller) unchanged(ctx context.Context, key, source, jsonVal string) (bool, error) {
|
||||
prev, err := p.core.LatestFactBySource(ctx, key, source)
|
||||
switch {
|
||||
case err == nil && prev.Value == string(jv):
|
||||
return nil // unchanged → no churn
|
||||
case err != nil && err != ipc.ErrNoFact && !isNoFact(err):
|
||||
return fmt.Errorf("read %s: %w", key, err)
|
||||
case err == nil:
|
||||
return prev.Value == jsonVal, nil
|
||||
case isNoFact(err):
|
||||
return false, nil
|
||||
default:
|
||||
return false, fmt.Errorf("read %s: %w", key, err)
|
||||
}
|
||||
_, err = p.core.WriteFact(ctx, ipc.WriteFactReq{
|
||||
}
|
||||
|
||||
// writeFact writes one `facts(kind=env)` row. Every poll in this file lands
|
||||
// here, so the row shape is written once.
|
||||
func (p *poller) writeFact(ctx context.Context, key, source, jsonVal string, now time.Time) error {
|
||||
_, err := p.core.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: now,
|
||||
Kind: "env",
|
||||
Key: key,
|
||||
Value: string(jv),
|
||||
Value: jsonVal,
|
||||
Source: source,
|
||||
Confidence: 1.0, // a direct reading, not an inference
|
||||
Confidence: factConfidence,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("write %s: %w", key, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// writeIfChanged writes only when val differs from the latest fact for
|
||||
// (key, source). Values are stored JSON-encoded (the store's convention:
|
||||
// `"down"`, `"critical"`), matching how rules compare f.Value.
|
||||
func (p *poller) writeIfChanged(ctx context.Context, key, source, val string, now time.Time) error {
|
||||
jv, _ := json.Marshal(val) // a string never fails to marshal
|
||||
same, err := p.unchanged(ctx, key, source, string(jv))
|
||||
if err != nil || same {
|
||||
return err // unchanged → no churn
|
||||
}
|
||||
if err := p.writeFact(ctx, key, source, string(jv), now); err != nil {
|
||||
return err
|
||||
}
|
||||
log.Printf("mavpoll: %s=%s (%s)", key, val, source)
|
||||
return nil
|
||||
}
|
||||
@@ -466,18 +544,12 @@ func (p *poller) writeIfChanged(ctx context.Context, key, source, val string, no
|
||||
// The log line names the key and the source, never the figures: mavpoll's log
|
||||
// is not the place his spending ends up.
|
||||
func (p *poller) writeIfChangedRaw(ctx context.Context, key, source, jsonVal string, now time.Time) error {
|
||||
prev, err := p.core.LatestFactBySource(ctx, key, source)
|
||||
switch {
|
||||
case err == nil && prev.Value == jsonVal:
|
||||
return nil
|
||||
case err != nil && err != ipc.ErrNoFact && !isNoFact(err):
|
||||
return fmt.Errorf("read %s: %w", key, err)
|
||||
same, err := p.unchanged(ctx, key, source, jsonVal)
|
||||
if err != nil || same {
|
||||
return err
|
||||
}
|
||||
if _, err := p.core.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: now, Kind: "env", Key: key, Value: jsonVal,
|
||||
Source: source, Confidence: 1.0,
|
||||
}); err != nil {
|
||||
return fmt.Errorf("write %s: %w", key, err)
|
||||
if err := p.writeFact(ctx, key, source, jsonVal, now); err != nil {
|
||||
return err
|
||||
}
|
||||
log.Printf("mavpoll: %s updated (%s)", key, source)
|
||||
return nil
|
||||
@@ -490,11 +562,8 @@ func (p *poller) writeIfChangedRaw(ctx context.Context, key, source, jsonVal str
|
||||
// The log line names the key only, never the figures: mavpoll's log is not the
|
||||
// place his spending ends up.
|
||||
func (p *poller) writeMoneyFact(ctx context.Context, key, jsonVal string, now time.Time) error {
|
||||
if _, err := p.core.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: now, Kind: "env", Key: key, Value: jsonVal,
|
||||
Source: zenmoney.Source, Confidence: 1.0,
|
||||
}); err != nil {
|
||||
return fmt.Errorf("write %s: %w", key, err)
|
||||
if err := p.writeFact(ctx, key, zenmoney.Source, jsonVal, now); err != nil {
|
||||
return err
|
||||
}
|
||||
log.Printf("mavpoll: %s read (%s)", key, zenmoney.Source)
|
||||
return nil
|
||||
@@ -506,6 +575,15 @@ func isNoFact(err error) bool {
|
||||
return errors.Is(err, ipc.ErrNoFact)
|
||||
}
|
||||
|
||||
// maxBodyBytes caps what a source can make the poller hold. Kuma's whole
|
||||
// metrics page is a few hundred kilobytes, so 4 MiB is slack, not a budget.
|
||||
//
|
||||
// Hitting the cap is an error, not a shorter body. A truncated kuma page parses
|
||||
// cleanly right up to the cut, and every monitor past it reads as deleted — the
|
||||
// poller would write "unknown" over live services and the down-rule would go
|
||||
// quiet. Reading one byte past the cap is how we tell full from truncated.
|
||||
const maxBodyBytes = 4 << 20
|
||||
|
||||
func (p *poller) get(ctx context.Context, url, basicUser string) ([]byte, error) {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
|
||||
if err != nil {
|
||||
@@ -519,12 +597,15 @@ func (p *poller) get(ctx context.Context, url, basicUser string) ([]byte, error)
|
||||
return nil, err
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
body, err := io.ReadAll(io.LimitReader(resp.Body, 4<<20))
|
||||
body, err := io.ReadAll(io.LimitReader(resp.Body, maxBodyBytes+1))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
return nil, fmt.Errorf("GET %s: %s", url, resp.Status)
|
||||
}
|
||||
if len(body) > maxBodyBytes {
|
||||
return nil, fmt.Errorf("GET %s: body over %d bytes", url, maxBodyBytes)
|
||||
}
|
||||
return body, nil
|
||||
}
|
||||
|
||||
@@ -3,6 +3,7 @@ package main
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"os"
|
||||
@@ -212,3 +213,59 @@ func TestRunRequiresSomethingToPoll(t *testing.T) {
|
||||
t.Errorf("err = %v, want a 'nothing to poll' refusal", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A flag value that would kill the poller later is refused at start, before it
|
||||
// dials core: a non-positive interval panics time.NewTicker on the first tick, a
|
||||
// zero timeout means http.Client waits forever, and an empty wg command used to
|
||||
// index field 0 of an empty slice.
|
||||
func TestRunRefusesFlagsThatCrashLater(t *testing.T) {
|
||||
cases := []struct {
|
||||
name string
|
||||
args []string
|
||||
want string
|
||||
}{
|
||||
{"zero interval", []string{"-interval", "0"}, "-interval must be positive"},
|
||||
{"negative interval", []string{"-interval", "-5s"}, "-interval must be positive"},
|
||||
{"zero timeout", []string{"-timeout", "0"}, "-timeout must be positive"},
|
||||
{"empty wg command", []string{"-wg", "wg0", "-wg-cmd", " "}, "-wg-cmd is empty"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
args := append([]string{"-socket", "/tmp/nope.sock"}, c.args...)
|
||||
err := run(args)
|
||||
if err == nil || !strings.Contains(err.Error(), c.want) {
|
||||
t.Errorf("err = %v, want %q", err, c.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// pollWg refuses an empty command rather than panicking on fields[0].
|
||||
func TestPollWgEmptyCommand(t *testing.T) {
|
||||
p := &poller{core: &factCore{}, wgIface: "wg0", wgCmd: ""}
|
||||
if err := p.pollWg(context.Background()); err == nil {
|
||||
t.Error("want an error, got a poll that ran something")
|
||||
}
|
||||
}
|
||||
|
||||
// A body at the cap is a truncated body, and a truncated kuma page reads as
|
||||
// "every monitor past the cut was deleted". Refuse it instead of parsing it.
|
||||
func TestGetRefusesTruncatedBody(t *testing.T) {
|
||||
big := strings.Repeat("x", maxBodyBytes+64)
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
io.WriteString(w, big)
|
||||
}))
|
||||
defer srv.Close()
|
||||
p := &poller{http: srv.Client()}
|
||||
if _, err := p.get(context.Background(), srv.URL, ""); err == nil {
|
||||
t.Error("want an over-size refusal, got a silently truncated body")
|
||||
}
|
||||
small := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
io.WriteString(w, "ok")
|
||||
}))
|
||||
defer small.Close()
|
||||
body, err := p.get(context.Background(), small.URL, "")
|
||||
if err != nil || string(body) != "ok" {
|
||||
t.Errorf("get = %q, %v; want the whole small body", body, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -22,6 +22,18 @@ import (
|
||||
// to it before sending, so it's also the rate the silence gate assumes.
|
||||
const whisperSampleRate = 16000
|
||||
|
||||
// whisperThreads — greedy decode is single-pass and this is a laptop CPU
|
||||
// (homesrv), not a server box; 4 was picked to leave headroom for the rest
|
||||
// of the daemons sharing the machine, not measured against a latency target.
|
||||
const whisperThreads = 4
|
||||
|
||||
// noSpeechFloor — whisper's own no_speech_prob past this point means the
|
||||
// segment it transcribed is not speech (the model still emits token
|
||||
// probabilities for silence/noise, so a high avgLogProb-derived confidence
|
||||
// can coexist with a segment that should be zero). Read as "at least 90%
|
||||
// sure this was not speech."
|
||||
const noSpeechFloor = 0.9
|
||||
|
||||
type whisperHandler struct {
|
||||
ctx *C.struct_whisper_context
|
||||
minMs int // clips shorter than this are dropped (hallucination bait)
|
||||
@@ -101,7 +113,7 @@ func (h *whisperHandler) Transcribe(ctx context.Context, req worker.TranscribeRe
|
||||
params.print_realtime = false
|
||||
params.print_timestamps = false
|
||||
params.print_special = false
|
||||
params.n_threads = C.int(4)
|
||||
params.n_threads = C.int(whisperThreads)
|
||||
params.single_segment = true
|
||||
|
||||
lang := C.CString(req.Lang)
|
||||
@@ -162,7 +174,7 @@ func (h *whisperHandler) Transcribe(ctx context.Context, req worker.TranscribeRe
|
||||
}
|
||||
|
||||
noSpeechProb := float64(C.whisper_full_get_segment_no_speech_prob(h.ctx, 0))
|
||||
if noSpeechProb > 0.9 {
|
||||
if noSpeechProb > noSpeechFloor {
|
||||
confidence = 0
|
||||
}
|
||||
|
||||
|
||||
@@ -116,18 +116,27 @@ func (h *piperHandler) Synthesize(ctx context.Context, req worker.SynthesizeReq)
|
||||
}, nil
|
||||
}
|
||||
|
||||
// resample22050To16000 converts raw 16-bit PCM from 22050 Hz to 16000 Hz
|
||||
// using linear interpolation.
|
||||
// piperSampleRate is the rate piper's onnx voices render at (ru_RU-irina and
|
||||
// the other models this daemon has been pointed at). targetSampleRate is the
|
||||
// canonical maven wire rate (audio.PCM16kMono) that every downstream
|
||||
// consumer — playback, the voice wire, whisper on the way back in — expects.
|
||||
const (
|
||||
piperSampleRate = 22050
|
||||
targetSampleRate = 16000
|
||||
)
|
||||
|
||||
// resample22050To16000 converts raw 16-bit PCM from piperSampleRate to
|
||||
// targetSampleRate using linear interpolation.
|
||||
func resample22050To16000(input []byte) []byte {
|
||||
if len(input) < 2 {
|
||||
return nil
|
||||
}
|
||||
|
||||
nSamples := len(input) / 2
|
||||
outSamples := int(float64(nSamples) * 16000.0 / 22050.0)
|
||||
outSamples := int(float64(nSamples) * float64(targetSampleRate) / float64(piperSampleRate))
|
||||
output := make([]byte, outSamples*2)
|
||||
|
||||
ratio := 22050.0 / 16000.0
|
||||
ratio := float64(piperSampleRate) / float64(targetSampleRate)
|
||||
|
||||
for i := 0; i < outSamples; i++ {
|
||||
srcPos := float64(i) * ratio
|
||||
|
||||
+27
-7
@@ -5,12 +5,17 @@
|
||||
// is detected sends it as a PushToTalk frame to the voice server. The reply
|
||||
// audio is played back through aplay(1).
|
||||
//
|
||||
// No wake-word model yet (MVP uses voice-activity-only trigger). The
|
||||
// SurfaceVoice auth layer caps all commands at L0 (no destructive acts),
|
||||
// making accidental triggers safe by design. A proper wake-word engine
|
||||
// (openWakeWord / Silero VAD ONNX) is the planned upgrade — the VAD shape
|
||||
// (30ms frames, 16kHz PCM) matches silero-vad's input interface exactly, so
|
||||
// swapping energy-threshold for ONNX-inference is a local change in vad.go.
|
||||
// Voice activity is silero-vad when -vad-model points at the graph, and an
|
||||
// energy threshold when it does not. Silero declines noise the threshold
|
||||
// accepts: 0 frames against 68 to 99 on the four fixtures, measured in
|
||||
// docs/evals/2026-08-09-silero-vad.md. Note that the model window is 512
|
||||
// samples and the capture frame is 480, so silero.go re-chunks. This comment
|
||||
// used to say the two matched, which was true of silero v4.
|
||||
//
|
||||
// There is still no wake-word model, so anything spoken near the microphone
|
||||
// becomes a turn (V-487 stage two). The SurfaceVoice auth layer caps all
|
||||
// commands at L0 (no destructive acts), which is what makes an accidental
|
||||
// trigger safe rather than expensive.
|
||||
//
|
||||
// While a reply is playing the capture side is muted (half-duplex): without
|
||||
// it, Maven's own voice comes back in through the mic and she answers
|
||||
@@ -73,6 +78,9 @@ func run(args []string) error {
|
||||
bargeIn := flag.Bool("barge-in", false, "cut Maven off when he talks over her (needs a room-tuned -barge-in-rms)")
|
||||
bargeRMS := flag.Int("barge-in-rms", defaultBargeRMS, "RMS x10000 a frame must clear to count as barge-in")
|
||||
bargeFrames := flag.Int("barge-in-frames", defaultBargeFrames, "consecutive frames over -barge-in-rms before playback is cut")
|
||||
vadModel := flag.String("vad-model", "", "silero-vad onnx file; empty runs the energy threshold instead")
|
||||
vadThreshold := flag.Float64("vad-threshold", defaultSileroThreshold, "speech probability a frame must clear")
|
||||
onnxLib := flag.String("onnx-lib", os.Getenv("MAVEN_ONNX_LIB"), "libonnxruntime.so, needed with -vad-model")
|
||||
flag.CommandLine.Parse(args)
|
||||
|
||||
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
|
||||
@@ -82,8 +90,20 @@ func run(args []string) error {
|
||||
vc := voice.Dial(*addr)
|
||||
defer vc.Close()
|
||||
|
||||
// VAD engine.
|
||||
// VAD engine. A model that will not load is logged and not fatal: the
|
||||
// energy threshold is worse, and it is a great deal better than a
|
||||
// listening client that refuses to start.
|
||||
vad := NewVAD(*minRMS, *speechMs, *silenceMs, *maxMs)
|
||||
if *vadModel != "" {
|
||||
s, err := newSileroVAD(*vadModel, *onnxLib)
|
||||
if err != nil {
|
||||
log.Printf("mavwaked: silero unavailable, energy threshold unchanged: %v", err)
|
||||
} else {
|
||||
defer s.Close()
|
||||
vad.UseSilero(s, *vadThreshold)
|
||||
log.Printf("mavwaked: silero-vad from %s, threshold %.2f", *vadModel, *vadThreshold)
|
||||
}
|
||||
}
|
||||
|
||||
// Audio source.
|
||||
var src io.ReadCloser
|
||||
|
||||
@@ -0,0 +1,171 @@
|
||||
package main
|
||||
|
||||
// silero-vad, the speech detector that replaces the energy threshold (V-487).
|
||||
//
|
||||
// Why an energy threshold is not a voice activity detector. It answers "is
|
||||
// this frame loud", and a fan, a door and a television are all loud. mavwaked
|
||||
// sends every utterance it accepts to speech-to-text and then to the daemon,
|
||||
// so a false trigger is a turn Maven takes on something nobody said to her.
|
||||
// Silero answers "is this frame speech", which is the question.
|
||||
//
|
||||
// It is 2.3MB of ONNX and runs on one CPU core in real time. That is not an
|
||||
// aside: this is the one model in the system that may never be offloaded or
|
||||
// gated on GPU admission, because a wake path that waits on a card is not a
|
||||
// wake path.
|
||||
//
|
||||
// Nil is a working value. Without -vad-model the daemon runs the energy VAD
|
||||
// exactly as it did before this file existed.
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"sync"
|
||||
|
||||
ort "github.com/yalue/onnxruntime_go"
|
||||
)
|
||||
|
||||
const (
|
||||
// sileroWindow — samples per inference at 16kHz. The model is fixed at
|
||||
// 512 and does not accept another size, which is why this file
|
||||
// re-chunks rather than reusing the 480-sample capture frame. main.go
|
||||
// used to claim the two matched; that was true of silero v4.
|
||||
sileroWindow = 512
|
||||
|
||||
// sileroContext — samples of the previous window prepended to each
|
||||
// inference, as the reference implementation does. Without it the first
|
||||
// milliseconds of every window are judged with no history and speech
|
||||
// onsets score low.
|
||||
sileroContext = 64
|
||||
|
||||
// sileroState — the LSTM state carried between windows, [2][1][128].
|
||||
sileroStateDim = 128
|
||||
|
||||
// defaultSileroThreshold — probability above which a window is speech.
|
||||
// 0.5 is the reference default. Raising it costs speech onsets, which
|
||||
// are the quietest part of an utterance.
|
||||
defaultSileroThreshold = 0.5
|
||||
)
|
||||
|
||||
// sileroVAD holds one ONNX session and the streaming state around it. It is
|
||||
// fed 30ms capture frames and answers per frame, buffering across calls
|
||||
// because 480 samples never line up with a 512-sample window.
|
||||
type sileroVAD struct {
|
||||
mu sync.Mutex
|
||||
session *ort.DynamicAdvancedSession
|
||||
|
||||
pending []float32 // samples not yet part of a full window
|
||||
context [sileroContext]float32 // tail of the previous window
|
||||
state []float32 // [2][1][128], carried between windows
|
||||
last float64 // most recent probability, held between windows
|
||||
sr []int64
|
||||
}
|
||||
|
||||
// newSileroVAD loads the graph. The ONNX environment is initialised here when
|
||||
// nothing else has done it, because mavwaked has no embedder to do it first.
|
||||
func newSileroVAD(modelPath, libPath string) (*sileroVAD, error) {
|
||||
if !ort.IsInitialized() {
|
||||
if libPath != "" {
|
||||
ort.SetSharedLibraryPath(libPath)
|
||||
}
|
||||
if err := ort.InitializeEnvironment(); err != nil {
|
||||
return nil, fmt.Errorf("silero: onnx runtime: %w", err)
|
||||
}
|
||||
}
|
||||
s, err := ort.NewDynamicAdvancedSession(modelPath,
|
||||
[]string{"input", "state", "sr"}, []string{"output", "stateN"}, nil)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("silero: load %s: %w", modelPath, err)
|
||||
}
|
||||
return &sileroVAD{
|
||||
session: s,
|
||||
state: make([]float32, 2*sileroStateDim),
|
||||
sr: []int64{16000},
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Speech reports whether the frame carries speech, and the probability behind
|
||||
// that answer. A frame that completes no window inherits the previous
|
||||
// probability, so the caller sees one answer per frame either way.
|
||||
func (s *sileroVAD) Speech(frame []int16, threshold float64) (bool, float64) {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
|
||||
for _, v := range frame {
|
||||
s.pending = append(s.pending, float32(v)/32768.0)
|
||||
}
|
||||
for len(s.pending) >= sileroWindow {
|
||||
p, err := s.infer(s.pending[:sileroWindow])
|
||||
if err != nil {
|
||||
// A failed inference must not silence the microphone. Hold the
|
||||
// last answer and let the next window try again.
|
||||
break
|
||||
}
|
||||
s.last = p
|
||||
s.pending = s.pending[sileroWindow:]
|
||||
}
|
||||
return s.last >= threshold, s.last
|
||||
}
|
||||
|
||||
// infer runs one window and rolls the state and the context forward.
|
||||
func (s *sileroVAD) infer(window []float32) (float64, error) {
|
||||
in := make([]float32, sileroContext+sileroWindow)
|
||||
copy(in, s.context[:])
|
||||
copy(in[sileroContext:], window)
|
||||
|
||||
inT, err := ort.NewTensor(ort.NewShape(1, int64(len(in))), in)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer inT.Destroy()
|
||||
stT, err := ort.NewTensor(ort.NewShape(2, 1, sileroStateDim), s.state)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer stT.Destroy()
|
||||
srT, err := ort.NewTensor(ort.NewShape(1), s.sr)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer srT.Destroy()
|
||||
|
||||
out, err := ort.NewEmptyTensor[float32](ort.NewShape(1, 1))
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer out.Destroy()
|
||||
next, err := ort.NewEmptyTensor[float32](ort.NewShape(2, 1, sileroStateDim))
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
defer next.Destroy()
|
||||
|
||||
if err := s.session.Run(
|
||||
[]ort.Value{inT, stT, srT},
|
||||
[]ort.Value{out, next},
|
||||
); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
copy(s.state, next.GetData())
|
||||
copy(s.context[:], in[len(in)-sileroContext:])
|
||||
return float64(out.GetData()[0]), nil
|
||||
}
|
||||
|
||||
// Reset drops the streaming state. Called at every utterance boundary and
|
||||
// after barge-in, so echo-era history never scores the next sentence.
|
||||
func (s *sileroVAD) Reset() {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
s.pending = s.pending[:0]
|
||||
s.context = [sileroContext]float32{}
|
||||
for i := range s.state {
|
||||
s.state[i] = 0
|
||||
}
|
||||
s.last = 0
|
||||
}
|
||||
|
||||
// Close releases the session.
|
||||
func (s *sileroVAD) Close() error {
|
||||
if s == nil || s.session == nil {
|
||||
return nil
|
||||
}
|
||||
return s.session.Destroy()
|
||||
}
|
||||
@@ -0,0 +1,149 @@
|
||||
package main
|
||||
|
||||
// What this measures. The energy threshold cannot tell a voice from a
|
||||
// television, and every utterance it accepts becomes a turn. So the test that
|
||||
// matters is not "does silero find speech" — it is "does it decline what the
|
||||
// energy threshold accepts".
|
||||
//
|
||||
// Speech is the four piper fixtures mavsttd already scores against. They are
|
||||
// synthesised, so nothing of the owner's voice is committed. Non-speech is
|
||||
// white noise at the same loudness, which is the cheapest thing that fools an
|
||||
// energy floor and the honest floor for this claim.
|
||||
//
|
||||
// Both halves skip without models/vad/silero_vad.onnx and MAVEN_ONNX_LIB,
|
||||
// like the TestONNX measurements in internal/router/eval.
|
||||
|
||||
import (
|
||||
"math"
|
||||
"math/rand"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
const wavHeader = 44 // 16kHz mono s16le, written by piper
|
||||
|
||||
func loadSilero(t *testing.T) *sileroVAD {
|
||||
t.Helper()
|
||||
model := filepath.Join("..", "..", "models", "vad", "silero_vad.onnx")
|
||||
lib := os.Getenv("MAVEN_ONNX_LIB")
|
||||
if _, err := os.Stat(model); err != nil {
|
||||
t.Skipf("missing %s: %v", model, err)
|
||||
}
|
||||
if lib == "" {
|
||||
t.Skip("MAVEN_ONNX_LIB unset")
|
||||
}
|
||||
s, err := newSileroVAD(model, lib)
|
||||
if err != nil {
|
||||
t.Skipf("silero unavailable: %v", err)
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// feedAll runs a whole clip through a VAD and reports how many utterances it
|
||||
// produced and how many frames it called speech.
|
||||
func feedAll(v *VAD, pcm []int16) (utterances, speechFrames int) {
|
||||
for i := 0; i+frameSamples <= len(pcm); i += frameSamples {
|
||||
frame := pcm[i : i+frameSamples]
|
||||
utt, state := v.Feed(frame)
|
||||
if state == StateSpeech {
|
||||
speechFrames++
|
||||
}
|
||||
if utt.Bytes != nil {
|
||||
utterances++
|
||||
}
|
||||
}
|
||||
return utterances, speechFrames
|
||||
}
|
||||
|
||||
func readFixture(t *testing.T, name string) []int16 {
|
||||
t.Helper()
|
||||
raw, err := os.ReadFile(filepath.Join("..", "mavsttd", "testdata", name))
|
||||
if err != nil {
|
||||
t.Skipf("missing fixture %s: %v", name, err)
|
||||
}
|
||||
if len(raw) <= wavHeader {
|
||||
t.Fatalf("%s: %d bytes, no audio", name, len(raw))
|
||||
}
|
||||
return PCMToI16(raw[wavHeader:])
|
||||
}
|
||||
|
||||
// noise returns white noise scaled to the same RMS as ref. Same loudness,
|
||||
// nothing said.
|
||||
func noise(ref []int16, seed int64) []int16 {
|
||||
target := frameRMS(ref)
|
||||
r := rand.New(rand.NewSource(seed))
|
||||
out := make([]int16, len(ref))
|
||||
for i := range out {
|
||||
out[i] = int16(r.NormFloat64() * target * 32768.0)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func TestSileroHearsSpeechAndDeclinesNoise(t *testing.T) {
|
||||
s := loadSilero(t)
|
||||
defer s.Close()
|
||||
|
||||
for _, name := range []string{"ru_fact.wav", "ru_query.wav", "ru_reminder.wav", "en_act.wav"} {
|
||||
pcm := readFixture(t, name)
|
||||
|
||||
v := NewVAD(0, 0, 0, 0)
|
||||
v.UseSilero(s, defaultSileroThreshold)
|
||||
_, spoke := feedAll(v, pcm)
|
||||
if spoke == 0 {
|
||||
t.Errorf("%s: silero heard no speech in a spoken clip", name)
|
||||
}
|
||||
|
||||
s.Reset()
|
||||
v2 := NewVAD(0, 0, 0, 0)
|
||||
v2.UseSilero(s, defaultSileroThreshold)
|
||||
_, heard := feedAll(v2, noise(pcm, 7))
|
||||
|
||||
energy := NewVAD(0, 0, 0, 0)
|
||||
_, energyHeard := feedAll(energy, noise(pcm, 7))
|
||||
|
||||
t.Logf("%s: speech frames — silero on speech %d, silero on noise %d, energy on noise %d",
|
||||
name, spoke, heard, energyHeard)
|
||||
if heard >= energyHeard {
|
||||
t.Errorf("%s: silero called %d noise frames speech, energy called %d — no improvement",
|
||||
name, heard, energyHeard)
|
||||
}
|
||||
s.Reset()
|
||||
}
|
||||
}
|
||||
|
||||
// BenchmarkSileroFrame answers the only performance question that matters
|
||||
// here: one 30ms frame must cost far less than 30ms on one core, or the
|
||||
// detector cannot run always-on beside everything else on that machine.
|
||||
func BenchmarkSileroFrame(b *testing.B) {
|
||||
s := loadSilero(&testing.T{})
|
||||
if s == nil {
|
||||
b.Skip("silero unavailable")
|
||||
}
|
||||
defer s.Close()
|
||||
frame := make([]int16, frameSamples)
|
||||
for i := range frame {
|
||||
frame[i] = int16(i%400 - 200)
|
||||
}
|
||||
for i := 0; i < b.N; i++ {
|
||||
s.Speech(frame, defaultSileroThreshold)
|
||||
}
|
||||
}
|
||||
|
||||
// TestSileroRechunksAcrossFrames pins the reason this file exists. The capture
|
||||
// frame is 480 samples and the model window is 512, so a detector that ran one
|
||||
// inference per frame would be feeding the model a shape it does not accept.
|
||||
func TestSileroRechunksAcrossFrames(t *testing.T) {
|
||||
s := loadSilero(t)
|
||||
defer s.Close()
|
||||
|
||||
silence := make([]int16, frameSamples)
|
||||
for i := 0; i < 20; i++ {
|
||||
if _, p := s.Speech(silence, defaultSileroThreshold); math.IsNaN(p) {
|
||||
t.Fatalf("frame %d: probability is NaN", i)
|
||||
}
|
||||
}
|
||||
if len(s.pending) >= sileroWindow {
|
||||
t.Errorf("pending grew to %d samples, so windows are not being consumed", len(s.pending))
|
||||
}
|
||||
}
|
||||
+35
-1
@@ -68,6 +68,37 @@ type VAD struct {
|
||||
// follows the room's ambient level. Initialised to minRMS; updated
|
||||
// on each silence frame.
|
||||
floorRMS float64
|
||||
|
||||
// speech is silero-vad, or nil. When it is set the energy floor decides
|
||||
// nothing: the question becomes "is this speech" rather than "is this
|
||||
// loud", and the noise floor is not even tracked. Everything after that
|
||||
// answer — the speech hold, the silence hold, the length cap, the
|
||||
// buffer — is the same state machine either way, which is why the
|
||||
// detector goes here and not around this type.
|
||||
speech *sileroVAD
|
||||
speechMin float64
|
||||
}
|
||||
|
||||
// UseSilero swaps the energy threshold for the model. Passing nil is a
|
||||
// no-op, so a caller that could not load the graph keeps a working VAD.
|
||||
func (v *VAD) UseSilero(s *sileroVAD, threshold float64) {
|
||||
if s == nil {
|
||||
return
|
||||
}
|
||||
if threshold <= 0 {
|
||||
threshold = defaultSileroThreshold
|
||||
}
|
||||
v.speech = s
|
||||
v.speechMin = threshold
|
||||
}
|
||||
|
||||
// isSpeech answers the one question the state machine asks of a frame.
|
||||
func (v *VAD) isSpeech(frame []int16, rms float64) bool {
|
||||
if v.speech != nil {
|
||||
ok, _ := v.speech.Speech(frame, v.speechMin)
|
||||
return ok
|
||||
}
|
||||
return rms >= v.floorRMS
|
||||
}
|
||||
|
||||
// NewVAD creates a VAD with the given thresholds. Zero values use defaults.
|
||||
@@ -110,7 +141,7 @@ func (v *VAD) State() SpeechState { return v.state }
|
||||
// should send the audio to the voice server before feeding more frames.
|
||||
func (v *VAD) Feed(frame []int16) (_ audio.Audio, state SpeechState) {
|
||||
rms := frameRMS(frame)
|
||||
isSpeech := rms >= v.floorRMS
|
||||
isSpeech := v.isSpeech(frame, rms)
|
||||
|
||||
switch v.state {
|
||||
case StateSilence:
|
||||
@@ -175,6 +206,9 @@ func (v *VAD) Feed(frame []int16) (_ audio.Audio, state SpeechState) {
|
||||
func (v *VAD) Reset() { v.reset() }
|
||||
|
||||
func (v *VAD) reset() {
|
||||
if v.speech != nil {
|
||||
v.speech.Reset()
|
||||
}
|
||||
v.state = StateSilence
|
||||
v.speechFrames = 0
|
||||
v.silenceFrames = 0
|
||||
|
||||
@@ -0,0 +1,195 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"errors"
|
||||
"log"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
//go:embed chat.html
|
||||
var chatPageHTML string
|
||||
|
||||
// chatTmpl — plain text conversation interface. No JS: form POSTs to /api/chat
|
||||
// and the handler redirects back to /chat with the response.
|
||||
var chatTmpl = parsePage("chat", chatPageHTML, nil)
|
||||
|
||||
// chatMsg — one message in the conversation history.
|
||||
type chatMsg struct {
|
||||
Role string // "user" | "assistant"
|
||||
Text string
|
||||
// Source — the query source that claimed the turn, shown as a badge beside
|
||||
// the reply. Empty for a turn no source claimed (V-539).
|
||||
Source string
|
||||
// TraceID anchors the correction gesture (V-630). Non-zero ⇒ the turn was
|
||||
// persisted and can be corrected in one click. 0 ⇒ no correction is offered,
|
||||
// which is honest: a box with no database has no turn to correct.
|
||||
TraceID int64
|
||||
// Corrected — the owner already corrected this turn, so the page says thank
|
||||
// you instead of offering the buttons again.
|
||||
Corrected string
|
||||
}
|
||||
|
||||
// correctionTargets — the seven public intents, in the order the buttons are
|
||||
// shown. Read from internal/router rather than typed out, so a new intent cannot
|
||||
// exist without a way to correct a turn into it.
|
||||
var correctionTargets = []router.Intent{
|
||||
router.IntentFact, router.IntentNote, router.IntentReminder,
|
||||
router.IntentQuery, router.IntentAct, router.IntentChat, router.IntentSystem,
|
||||
}
|
||||
|
||||
// handleChatPage renders the chat conversation page.
|
||||
func handleChatPage(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "chat") {
|
||||
return
|
||||
}
|
||||
msgs := []chatMsg{}
|
||||
// Read user message + reply from query params (set by /api/chat redirect).
|
||||
if q := r.URL.Query().Get("q"); q != "" {
|
||||
msgs = append(msgs, chatMsg{Role: "user", Text: q})
|
||||
}
|
||||
if reply := r.URL.Query().Get("r"); reply != "" {
|
||||
id, _ := strconv.ParseInt(r.URL.Query().Get("t"), 10, 64)
|
||||
msgs = append(msgs, chatMsg{
|
||||
Role: "assistant", Text: reply, Source: r.URL.Query().Get("s"),
|
||||
TraceID: id, Corrected: r.URL.Query().Get("c"),
|
||||
})
|
||||
}
|
||||
// UserText rides beside the messages so the correction form can hand the
|
||||
// conversation back on the redirect: this page has no session and no JS, so
|
||||
// what is on screen is what the query params carry.
|
||||
renderPage(w, chatTmpl, struct {
|
||||
Error string
|
||||
Messages []chatMsg
|
||||
Targets []router.Intent
|
||||
UserText string
|
||||
}{Messages: msgs, Targets: correctionTargets, UserText: r.URL.Query().Get("q")})
|
||||
}
|
||||
|
||||
// handleChatAPI processes a chat message POST and redirects back to /chat.
|
||||
//
|
||||
// State-changing, and the widest surface on this server: the text reaches the
|
||||
// router, the LLM, and through mavend's applyAction the whole action path
|
||||
// including `act` — so it is gated on the same step-up as POST /tools and
|
||||
// POST /api/revert (Vikunja #317). With WebAuthn unconfigured the gate is
|
||||
// fail-open exactly like the others (see stepUpOK); with -require-stepup it
|
||||
// denies, which is the point of that flag.
|
||||
func handleChatAPI(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) {
|
||||
if r.Method != http.MethodPost {
|
||||
http.Error(w, "POST only", http.StatusMethodNotAllowed)
|
||||
return
|
||||
}
|
||||
if !requireCore(w, core, "chat") {
|
||||
return
|
||||
}
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return
|
||||
}
|
||||
text := strings.TrimSpace(r.FormValue("text"))
|
||||
if text == "" {
|
||||
http.Redirect(w, r, "/chat", http.StatusSeeOther)
|
||||
return
|
||||
}
|
||||
// One conversation id for the whole web chat, and a different one from
|
||||
// telegram or the mic. A parked question belongs to the reach that was
|
||||
// asked; before this, a clarify nobody answered on the web ate the next
|
||||
// utterance spoken at the mic (Vikunja #466). This server has no
|
||||
// per-browser session, so every browser tab is the same conversation —
|
||||
// which is right for a single-owner box.
|
||||
reply, err := core.Chat(r.Context(), "web", text)
|
||||
if err != nil {
|
||||
log.Printf("chat api: %v", err)
|
||||
http.Redirect(w, r, "/chat", http.StatusSeeOther)
|
||||
return
|
||||
}
|
||||
// The claiming query source rides back on the redirect so the page can show
|
||||
// it. Empty for a turn no source claimed, which is most of them.
|
||||
dest := "/chat?q=" + url.QueryEscape(text) + "&r=" + url.QueryEscape(reply.Reply)
|
||||
if reply.Source != "" {
|
||||
dest += "&s=" + url.QueryEscape(reply.Source)
|
||||
}
|
||||
// The trace id rides along so the reply can carry a correction gesture
|
||||
// (V-630). Absent when nothing persisted, and the page then offers none.
|
||||
if reply.TraceID != 0 {
|
||||
dest += "&t=" + strconv.FormatInt(reply.TraceID, 10)
|
||||
}
|
||||
http.Redirect(w, r, dest, http.StatusSeeOther)
|
||||
}
|
||||
|
||||
// handleCorrectAPI records that the last turn was routed wrongly (V-630).
|
||||
//
|
||||
// A correction is the only supervised signal this box gets, and everything else
|
||||
// in the trace accumulates on its own. So the gesture has to cost nothing: one
|
||||
// POST from the reply he is already looking at, carrying the trace id and
|
||||
// optionally the intent it should have been. An unstated target is accepted,
|
||||
// because a turn marked wrong with no target is still a usable negative.
|
||||
//
|
||||
// Step-up gated like POST /api/chat, and that costs the gesture nothing: he
|
||||
// tapped to send the turn he is now correcting, so the session is already up.
|
||||
// It is gated because trace ids are sequential integers and this writes the one
|
||||
// table the routing heads (V-546) will be fitted on. A caller who can guess an
|
||||
// id could otherwise mislabel turns he never corrected.
|
||||
func handleCorrectAPI(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) {
|
||||
if r.Method != http.MethodPost {
|
||||
http.Error(w, "POST only", http.StatusMethodNotAllowed)
|
||||
return
|
||||
}
|
||||
if !requireCore(w, core, "correct") {
|
||||
return
|
||||
}
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return
|
||||
}
|
||||
id, err := strconv.ParseInt(strings.TrimSpace(r.FormValue("trace_id")), 10, 64)
|
||||
if err != nil || id <= 0 {
|
||||
http.Error(w, "trace_id required", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
shouldBe := strings.TrimSpace(r.FormValue("should_be"))
|
||||
// Only one of the seven, or nothing. Free text here would put an unroutable
|
||||
// label in the one table V-632 fits prototypes from.
|
||||
if shouldBe != "" && !isCorrectionTarget(shouldBe) {
|
||||
http.Error(w, "should_be must be one of the seven intents", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
if err := core.CorrectTurn(r.Context(), id, shouldBe); err != nil {
|
||||
log.Printf("correct turn %d: %v", id, err)
|
||||
// A turn past the retention bound is gone, and saying so is different
|
||||
// from saying the write broke.
|
||||
if errors.Is(err, ipc.ErrNoSuchTrace) {
|
||||
http.Error(w, "that turn is no longer stored", http.StatusNotFound)
|
||||
return
|
||||
}
|
||||
http.Error(w, "correction failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
stamp := shouldBe
|
||||
if stamp == "" {
|
||||
stamp = "wrong"
|
||||
}
|
||||
// Back to the conversation he was in, with the turn still on screen. The
|
||||
// query params carry it, so the correction is preserved by re-sending them.
|
||||
dest := "/chat?q=" + url.QueryEscape(r.FormValue("q")) +
|
||||
"&r=" + url.QueryEscape(r.FormValue("rep")) + "&c=" + url.QueryEscape(stamp)
|
||||
if s := r.FormValue("s"); s != "" {
|
||||
dest += "&s=" + url.QueryEscape(s)
|
||||
}
|
||||
http.Redirect(w, r, dest, http.StatusSeeOther)
|
||||
}
|
||||
|
||||
// isCorrectionTarget — one of the seven, and nothing else.
|
||||
func isCorrectionTarget(s string) bool {
|
||||
for _, t := range correctionTargets {
|
||||
if string(t) == s {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
@@ -5,6 +5,21 @@
|
||||
<div class="scroll chat-scroll" id=chatHistory>
|
||||
{{range .Messages}}
|
||||
<div class="chat-msg {{.Role}}"><strong>{{if eq .Role "user"}}you{{else}}maven{{end}}:</strong> {{.Text}}{{if .Source}} <span class="badge badge-accent" title="the query source that claimed this turn">{{.Source}}</span>{{end}}</div>
|
||||
{{if and (eq .Role "assistant") .TraceID}}
|
||||
{{if .Corrected}}
|
||||
<div class=chat-correct><span class="badge badge-ok" title="the label is kept; the transcript still expires in 14 days">corrected: {{.Corrected}}</span></div>
|
||||
{{else}}
|
||||
<form method=post action=/api/correct class=chat-correct>
|
||||
<input type=hidden name=trace_id value="{{.TraceID}}">
|
||||
<input type=hidden name=q value="{{$.UserText}}">
|
||||
<input type=hidden name=rep value="{{.Text}}">
|
||||
<input type=hidden name=s value="{{.Source}}">
|
||||
<button class="btn btn-sm" title="wrong, and I am not saying what it was">wrong</button>
|
||||
<span class=chat-correct-label>should have been:</span>
|
||||
{{range $.Targets}}<button class="btn btn-sm btn-muted" name=should_be value="{{.}}">{{.}}</button>{{end}}
|
||||
</form>
|
||||
{{end}}
|
||||
{{end}}
|
||||
{{else}}
|
||||
<div class=empty>
|
||||
<svg class=icon width="20" height="20"><use href="/ethos-icons.svg#i-message"/></svg>
|
||||
|
||||
@@ -0,0 +1,160 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"net/url"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
// correctCore records the correction the handler sends.
|
||||
type correctCore struct {
|
||||
ipc.UnimplementedCoreAPI
|
||||
traceID int64
|
||||
shouldBe string
|
||||
called bool
|
||||
err error
|
||||
}
|
||||
|
||||
func (c *correctCore) CorrectTurn(_ context.Context, traceID int64, shouldBe string) error {
|
||||
c.called, c.traceID, c.shouldBe = true, traceID, shouldBe
|
||||
return c.err
|
||||
}
|
||||
|
||||
func postCorrect(form url.Values) *http.Request {
|
||||
req := httptest.NewRequest(http.MethodPost, "/api/correct", strings.NewReader(form.Encode()))
|
||||
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
return req
|
||||
}
|
||||
|
||||
// The full gesture: wrong, and it should have been a fact.
|
||||
func TestCorrectAPIWithTarget(t *testing.T) {
|
||||
core := &correctCore{}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{
|
||||
"trace_id": {"42"}, "should_be": {"fact"}, "q": {"поужинал"}, "rep": {"поняла"},
|
||||
}), core, stepUpSession(), false)
|
||||
|
||||
if rr.Code != http.StatusSeeOther {
|
||||
t.Fatalf("status %d, want 303; body=%s", rr.Code, rr.Body.String())
|
||||
}
|
||||
if core.traceID != 42 || core.shouldBe != "fact" {
|
||||
t.Errorf("corrected trace %d to %q", core.traceID, core.shouldBe)
|
||||
}
|
||||
// The turn stays on screen, and the page says it was corrected.
|
||||
loc := rr.Header().Get("Location")
|
||||
if !strings.Contains(loc, "c=fact") || !strings.Contains(loc, "q=") {
|
||||
t.Errorf("redirect %q loses the turn or the correction", loc)
|
||||
}
|
||||
}
|
||||
|
||||
// The cheap half. A turn marked wrong with no target is still a usable negative,
|
||||
// and it must not cost more to give than the full answer.
|
||||
func TestCorrectAPIWithNoTarget(t *testing.T) {
|
||||
core := &correctCore{}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{"trace_id": {"7"}}), core, stepUpSession(), false)
|
||||
|
||||
if rr.Code != http.StatusSeeOther {
|
||||
t.Fatalf("status %d, want 303", rr.Code)
|
||||
}
|
||||
if !core.called || core.shouldBe != "" {
|
||||
t.Errorf("called=%v shouldBe=%q, want an untargeted negative recorded", core.called, core.shouldBe)
|
||||
}
|
||||
if !strings.Contains(rr.Header().Get("Location"), "c=wrong") {
|
||||
t.Errorf("redirect %q does not say the turn was marked wrong", rr.Header().Get("Location"))
|
||||
}
|
||||
}
|
||||
|
||||
// Free text here would put an unroutable label in the one table V-632 fits
|
||||
// prototypes from.
|
||||
func TestCorrectAPIRejectsUnknownTarget(t *testing.T) {
|
||||
core := &correctCore{}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{"trace_id": {"7"}, "should_be": {"погода"}}), core, stepUpSession(), false)
|
||||
|
||||
if rr.Code != http.StatusBadRequest {
|
||||
t.Fatalf("status %d, want 400", rr.Code)
|
||||
}
|
||||
if core.called {
|
||||
t.Error("wrote a label for a target that is not one of the seven")
|
||||
}
|
||||
}
|
||||
|
||||
func TestCorrectAPINeedsTraceID(t *testing.T) {
|
||||
for _, form := range []url.Values{{}, {"trace_id": {"0"}}, {"trace_id": {"nope"}}} {
|
||||
core := &correctCore{}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(form), core, stepUpSession(), false)
|
||||
if rr.Code != http.StatusBadRequest {
|
||||
t.Errorf("form %v: status %d, want 400", form, rr.Code)
|
||||
}
|
||||
if core.called {
|
||||
t.Errorf("form %v: reached the core", form)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A write that broke is not a turn that expired, and the two must not read the
|
||||
// same to the owner deciding whether to correct again.
|
||||
func TestCorrectAPIReportsFailure(t *testing.T) {
|
||||
core := &correctCore{err: errors.New("disk is full")}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{"trace_id": {"9"}, "should_be": {"note"}}), core, stepUpSession(), false)
|
||||
if rr.Code != http.StatusBadGateway {
|
||||
t.Fatalf("status %d, want 502", rr.Code)
|
||||
}
|
||||
}
|
||||
|
||||
// A trace past the retention bound is gone, and the surface says that.
|
||||
func TestCorrectAPIExpiredTurn(t *testing.T) {
|
||||
core := &correctCore{err: ipc.ErrNoSuchTrace}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{"trace_id": {"9"}, "should_be": {"note"}}), core, stepUpSession(), false)
|
||||
if rr.Code != http.StatusNotFound {
|
||||
t.Fatalf("status %d, want 404", rr.Code)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCorrectAPIPostOnly(t *testing.T) {
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, httptest.NewRequest(http.MethodGet, "/api/correct", nil), &correctCore{}, stepUpSession(), false)
|
||||
if rr.Code != http.StatusMethodNotAllowed {
|
||||
t.Fatalf("status %d, want 405", rr.Code)
|
||||
}
|
||||
}
|
||||
|
||||
// Every one of the seven intents has a button, so a new intent cannot exist with
|
||||
// no way to correct a turn into it.
|
||||
func TestCorrectionTargetsAreTheSeven(t *testing.T) {
|
||||
if len(correctionTargets) != 7 {
|
||||
t.Fatalf("%d targets, want the seven public intents", len(correctionTargets))
|
||||
}
|
||||
for _, want := range []string{"fact", "note", "reminder", "query", "act", "chat", "system"} {
|
||||
if !isCorrectionTarget(want) {
|
||||
t.Errorf("%s is not offered", want)
|
||||
}
|
||||
}
|
||||
if isCorrectionTarget("") {
|
||||
t.Error("empty is not a target: it is the absence of one, handled separately")
|
||||
}
|
||||
}
|
||||
|
||||
// Trace ids are sequential, so a caller who cannot assert step-up must not be
|
||||
// able to label a turn the owner never corrected.
|
||||
func TestCorrectAPINeedsStepUp(t *testing.T) {
|
||||
core := &correctCore{}
|
||||
rr := httptest.NewRecorder()
|
||||
handleCorrectAPI(rr, postCorrect(url.Values{"trace_id": {"9"}, "should_be": {"note"}}), core, nil, true)
|
||||
if rr.Code != http.StatusForbidden {
|
||||
t.Fatalf("status %d, want 403", rr.Code)
|
||||
}
|
||||
if core.called {
|
||||
t.Error("wrote a label with no step-up")
|
||||
}
|
||||
}
|
||||
@@ -117,8 +117,5 @@ func handleEcosystem(w http.ResponseWriter, r *http.Request, urls ecoURLs, core
|
||||
d.Calls.Rows = rows
|
||||
}
|
||||
|
||||
w.Header().Set("Content-Type", "text/html; charset=utf-8")
|
||||
if err := ecosystemTmpl.Execute(w, d); err != nil {
|
||||
log.Printf("ecosystem render: %v", err)
|
||||
}
|
||||
renderPage(w, ecosystemTmpl, d)
|
||||
}
|
||||
|
||||
@@ -14,8 +14,13 @@ memory only, so a restart empties this.</div>
|
||||
<div class=scroll><table class=mono>
|
||||
<tr><th>noticed<th>happened<th>source<th>kind<th>pri<th>what<th>detail</tr>
|
||||
{{range .Events}}<tr>
|
||||
<td>{{.NoticedAt.Format "02.01 15:04:05"}}</td>
|
||||
<td class=gray>{{.OccurredAt.Format "02.01 15:04:05"}}</td>
|
||||
<!-- Both columns in his clock (V-469 on /reminders, same rule here). NoticedAt
|
||||
is the bus's local instant, OccurredAt is whatever zone the source used —
|
||||
the store hands back UTC and internal/rss parses a pubDate to UTC — so
|
||||
rendering them raw put two zones side by side in the same row and made a
|
||||
feed item look hours older than it was. -->
|
||||
<td>{{.NoticedAt.Local.Format "02.01 15:04:05"}}</td>
|
||||
<td class=gray>{{.OccurredAt.Local.Format "02.01 15:04:05"}}</td>
|
||||
<td class=gray>{{.Source}}</td>
|
||||
<td class=gray>{{.Kind}}</td>
|
||||
<td class=gray>{{.Priority}}</td>
|
||||
|
||||
@@ -46,7 +46,8 @@ func TestEventsPageRendersTheJournal(t *testing.T) {
|
||||
t.Fatalf("status = %d, want 200", w.Code)
|
||||
}
|
||||
body := w.Body.String()
|
||||
for _, want := range []string{"rss:tech", "Вышло ядро 6.19", "ambient:notif", "10:00-11:00 планёрка", "01.08 10:00:00"} {
|
||||
occurred := time.Date(2026, 8, 1, 10, 0, 0, 0, time.UTC).Local().Format("02.01 15:04:05")
|
||||
for _, want := range []string{"rss:tech", "Вышло ядро 6.19", "ambient:notif", "10:00-11:00 планёрка", occurred} {
|
||||
if !strings.Contains(body, want) {
|
||||
t.Errorf("page does not mention %q", want)
|
||||
}
|
||||
@@ -89,6 +90,38 @@ func TestEventsPageWithoutCore(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// awayFromLocal returns a zone three hours off whatever this machine runs in,
|
||||
// so a test can tell "rendered in his clock" apart from "rendered in whatever
|
||||
// zone the value arrived in" without depending on TZ.
|
||||
func awayFromLocal() *time.Location {
|
||||
_, off := time.Now().Zone()
|
||||
return time.FixedZone("away", off+3*60*60)
|
||||
}
|
||||
|
||||
func TestEventsPageRendersBothTimesInLocalZone(t *testing.T) {
|
||||
// OccurredAt carries the source's zone — the store hands back UTC and
|
||||
// internal/rss parses a pubDate to UTC — while NoticedAt is the bus's local
|
||||
// instant. Rendered raw, the two columns of one row were in two zones and a
|
||||
// feed item read hours older than it was.
|
||||
away := awayFromLocal()
|
||||
occurred := time.Date(2026, 8, 1, 7, 15, 0, 0, time.UTC).In(away)
|
||||
noticed := occurred.Add(2 * time.Minute)
|
||||
core := &eventsCore{events: []ipc.IntakeEvent{{
|
||||
Source: "rss:tech", Kind: "note", Title: "Вышло ядро 6.19", Priority: "low",
|
||||
OccurredAt: occurred, NoticedAt: noticed,
|
||||
}}}
|
||||
body := getEvents(t, core).Body.String()
|
||||
const layout = "02.01 15:04:05"
|
||||
for _, ts := range []time.Time{occurred, noticed} {
|
||||
if !strings.Contains(body, ts.Local().Format(layout)) {
|
||||
t.Errorf("page does not render %s in his clock (%s)", ts, ts.Local().Format(layout))
|
||||
}
|
||||
if strings.Contains(body, ts.In(away).Format(layout)) {
|
||||
t.Errorf("page rendered %s in the source's zone", ts)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestEventsPageEscapesIntakeText(t *testing.T) {
|
||||
// Titles come from outside — a feed headline, a notification. They are shown
|
||||
// on a page and must never be able to inject markup into it.
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"log"
|
||||
"net/http"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
// The two fact-writing API routes: POST /api/signal appends a presence
|
||||
// observation, POST /api/revert voids the latest fact for a key. Neither
|
||||
// renders a page.
|
||||
|
||||
// presenceSignals — the only fact keys /api/signal may write. mavweb is a
|
||||
// network-facing surface inside wg; an allowlist keeps a compromised caller
|
||||
// boxed to forging weak presence signals (reachability, multi-source, never
|
||||
// truth) — it can't write arbitrary facts. ponytail: floor auth (wg-only); a
|
||||
// per-signal token belongs here if the tunnel ever hosts untrusted devices.
|
||||
var presenceSignals = map[string]string{
|
||||
"desk_active": "infer:hyprland",
|
||||
"page_heartbeat": "infer:heartbeat",
|
||||
"wg_handshake": "infer:wg",
|
||||
}
|
||||
|
||||
// handleSignal ingests one presence signal and writes a fresh fact through
|
||||
// CoreAPI. The fact's timestamp (now) is all the presence scorer reads; value
|
||||
// is a marker. Only allowlisted keys are accepted (see presenceSignals).
|
||||
func handleSignal(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if r.Method != http.MethodPost {
|
||||
http.Error(w, "POST only", http.StatusMethodNotAllowed)
|
||||
return
|
||||
}
|
||||
if !requireCore(w, core, "presence ingest") {
|
||||
return
|
||||
}
|
||||
key := r.URL.Query().Get("key")
|
||||
source, ok := presenceSignals[key]
|
||||
if !ok {
|
||||
http.Error(w, "unknown signal key", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
// kind=env: an observation about the device/surface, NOT a self-fact — a
|
||||
// passive signal never writes truth about you (spec), it only feeds
|
||||
// presence. confidence 1.0: the reading ("input happened") is certain;
|
||||
// presence applies its own per-signal weight/decay on top.
|
||||
if _, err := core.WriteFact(r.Context(), ipc.WriteFactReq{
|
||||
Ts: time.Now(),
|
||||
Kind: "env",
|
||||
Key: key,
|
||||
Value: `"active"`,
|
||||
Source: source,
|
||||
Confidence: 1.0,
|
||||
}); err != nil {
|
||||
log.Printf("signal %s: %v", key, err)
|
||||
http.Error(w, "write failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
}
|
||||
|
||||
func handleRevert(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) {
|
||||
if r.Method != http.MethodPost {
|
||||
http.Error(w, "POST only", http.StatusMethodNotAllowed)
|
||||
return
|
||||
}
|
||||
if !requireCore(w, core, "revert") {
|
||||
return
|
||||
}
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return
|
||||
}
|
||||
|
||||
key := strings.TrimSpace(r.FormValue("key"))
|
||||
if key == "" {
|
||||
http.Error(w, "key required", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
newID, err := core.RevertFact(r.Context(), key)
|
||||
if err != nil {
|
||||
log.Printf("revert %q: %v", key, err)
|
||||
if errors.Is(err, ipc.ErrNoFact) {
|
||||
http.Error(w, "no fact to revert", http.StatusNotFound)
|
||||
return
|
||||
}
|
||||
http.Error(w, "revert failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
log.Printf("reverted fact for key=%s, new_id=%d", key, newID)
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
json.NewEncoder(w).Encode(map[string]any{"reverted": true, "new_id": newID})
|
||||
}
|
||||
@@ -65,6 +65,7 @@ type fakeCore struct {
|
||||
// for handleTrace tests
|
||||
tickTrace ipc.TickTrace
|
||||
traceErr error
|
||||
turns []ipc.TurnDecision
|
||||
|
||||
// for handleChatAPI tests
|
||||
chatText string
|
||||
@@ -173,6 +174,10 @@ func (f *fakeCore) RevertFact(_ context.Context, key string) (int64, error) {
|
||||
return f.revertNewID, nil
|
||||
}
|
||||
|
||||
func (f *fakeCore) TurnDecisions(_ context.Context, _ int) ([]ipc.TurnDecision, error) {
|
||||
return f.turns, nil
|
||||
}
|
||||
|
||||
func (f *fakeCore) TickTrace(_ context.Context) (ipc.TickTrace, error) {
|
||||
if f.traceErr != nil {
|
||||
return ipc.TickTrace{}, f.traceErr
|
||||
@@ -825,6 +830,41 @@ func TestHandleTrace(t *testing.T) {
|
||||
t.Error("rendered 'nothing fired' but a winner was set")
|
||||
}
|
||||
})
|
||||
|
||||
// The turn arbitration shares this page (V-564). A reader must see the
|
||||
// winner, a loser and the claimants that were never asked, because the last
|
||||
// of those is what the hardcoded ordering hides.
|
||||
t.Run("renders the turn decision record", func(t *testing.T) {
|
||||
core := &fakeCore{turns: []ipc.TurnDecision{{
|
||||
Ts: time.Date(2025, 6, 1, 12, 0, 0, 0, time.UTC),
|
||||
Utterance: "какая погода в риме",
|
||||
Winner: "query:weather",
|
||||
Claims: []ipc.TurnClaim{
|
||||
{Stage: "query", Claimant: "weather", Intent: "query", Outcome: "won"},
|
||||
{Stage: "query", Claimant: "calendar", Outcome: "declined", Reason: "no answer"},
|
||||
{Stage: "query", Claimant: "kiwix", Outcome: "never_asked"},
|
||||
},
|
||||
}}}
|
||||
rr := httptest.NewRecorder()
|
||||
handleTrace(rr, httptest.NewRequest(http.MethodGet, "/trace", nil), core)
|
||||
body := rr.Body.String()
|
||||
for _, want := range []string{"какая погода в риме", "query:weather", "calendar", "kiwix", "never_asked"} {
|
||||
if !strings.Contains(body, want) {
|
||||
t.Errorf("rendered page is missing %q", want)
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("no turns renders the empty note, not an error", func(t *testing.T) {
|
||||
rr := httptest.NewRecorder()
|
||||
handleTrace(rr, httptest.NewRequest(http.MethodGet, "/trace", nil), &fakeCore{})
|
||||
if rr.Code != http.StatusOK {
|
||||
t.Fatalf("status = %d, want 200", rr.Code)
|
||||
}
|
||||
if !strings.Contains(rr.Body.String(), "no turn has run") {
|
||||
t.Error("empty ring did not render its note")
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// --- handleRevert ---
|
||||
|
||||
+88
-1672
File diff suppressed because it is too large
Load Diff
+5
-41
@@ -2,8 +2,8 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
_ "embed"
|
||||
"errors"
|
||||
"html/template"
|
||||
"log"
|
||||
"net/http"
|
||||
"strconv"
|
||||
@@ -31,43 +31,10 @@ type modelController interface {
|
||||
SwapModel(ctx context.Context, req ipc.SwapModelReq) (ipc.SwapModelResp, error)
|
||||
}
|
||||
|
||||
var modelsTmpl = template.Must(template.New("models").Funcs(shellFuncs()).Parse(shellHTML + modelsHTML))
|
||||
//go:embed models.html
|
||||
var modelsHTML string
|
||||
|
||||
const modelsHTML = `{{template "shellTop" "models"}}
|
||||
<h1>Resident model</h1>
|
||||
<p class=hint>swapping requires step-up — <a href=/auth/passkey>assert a passkey</a> first. The old model is unloaded before the new one is loaded (one model fits the iGPU at a time), so turns during the load are refused and fall back to the classifier.</p>
|
||||
<p class=hint>a swap is not remembered. Nothing writes it down, so the next restart of the daemon — including the one <code>mavupdate</code> does — comes back on <code>phraser.model_path</code> from the config. Make it stick by editing that.</p>
|
||||
{{if .Msg}}<div class="msg msg-ok">{{.Msg}}</div>{{end}}
|
||||
{{if .Err}}<div class="msg msg-err">{{.Err}}</div>{{end}}
|
||||
{{if .Off}}
|
||||
<section class=card>
|
||||
<h2 class=card-title>swap not configured</h2>
|
||||
<p class=hint>this core has no <code>phraser.swap_models</code> allowlist, so there is nothing to swap to. Add the gguf paths you allow to <code>deploy/mavend.json</code> and restart once.</p>
|
||||
</section>
|
||||
{{else}}
|
||||
<section class=card>
|
||||
<h2 class=card-title>loaded now</h2>
|
||||
<div class=scroll><table>
|
||||
<tr><th>model</th><td><code>{{.Status.Model}}</code></td></tr>
|
||||
<tr><th>file</th><td><code>{{.Status.ModelPath}}</code></td></tr>
|
||||
<tr><th>server</th><td><code>{{.Status.BaseURL}}</code></td></tr>
|
||||
<tr><th>n_ctx</th><td>{{.Status.NCtx}}</td></tr>
|
||||
<tr><th>n_gpu_layers</th><td>{{.Status.NGpuLayers}}</td></tr>
|
||||
</table></div>
|
||||
<p class=hint>the model name is what llama-server reports for itself, not what the config says it should be.</p>
|
||||
</section>
|
||||
<section class=card>
|
||||
<h2 class=card-title>allowed models <span class=badge>{{len .Status.Swappable}}</span></h2>
|
||||
{{if .Status.Swappable}}<div class=scroll><table><tr><th>file</th><th></th></tr>
|
||||
{{range .Status.Swappable}}<tr><td><code>{{.}}</code></td>
|
||||
<td><form method=post action=/models class=inline-form>
|
||||
<input type=hidden name=model_path value="{{.}}">
|
||||
<button class=btn>load this one</button></form></td></tr>{{end}}
|
||||
</table></div>
|
||||
{{else}}<div class=empty><div>no models allowlisted</div></div>{{end}}
|
||||
</section>
|
||||
{{end}}
|
||||
{{template "shellBottom"}}`
|
||||
var modelsTmpl = parsePage("models", modelsHTML, nil)
|
||||
|
||||
type modelsPage struct {
|
||||
Msg string
|
||||
@@ -154,8 +121,5 @@ func handleModels(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, swap
|
||||
}
|
||||
}
|
||||
page.Status = st
|
||||
w.Header().Set("Content-Type", "text/html; charset=utf-8")
|
||||
if err := modelsTmpl.Execute(w, page); err != nil {
|
||||
log.Printf("models render: %v", err)
|
||||
}
|
||||
renderPage(w, modelsTmpl, page)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
{{template "shellTop" "models"}}
|
||||
<h1>Resident model</h1>
|
||||
<p class=hint>swapping requires step-up — <a href=/auth/passkey>assert a passkey</a> first. The old model is unloaded before the new one is loaded (one model fits the iGPU at a time), so turns during the load are refused and fall back to the classifier.</p>
|
||||
<p class=hint>a swap is not remembered. Nothing writes it down, so the next restart of the daemon — including the one <code>mavupdate</code> does — comes back on <code>phraser.model_path</code> from the config. Make it stick by editing that.</p>
|
||||
{{if .Msg}}<div class="msg msg-ok">{{.Msg}}</div>{{end}}
|
||||
{{if .Err}}<div class="msg msg-err">{{.Err}}</div>{{end}}
|
||||
{{if .Off}}
|
||||
<section class=card>
|
||||
<h2 class=card-title>swap not configured</h2>
|
||||
<p class=hint>this core has no <code>phraser.swap_models</code> allowlist, so there is nothing to swap to. Add the gguf paths you allow to <code>deploy/mavend.json</code> and restart once.</p>
|
||||
</section>
|
||||
{{else}}
|
||||
<section class=card>
|
||||
<h2 class=card-title>loaded now</h2>
|
||||
<div class=scroll><table>
|
||||
<tr><th>model</th><td><code>{{.Status.Model}}</code></td></tr>
|
||||
<tr><th>file</th><td><code>{{.Status.ModelPath}}</code></td></tr>
|
||||
<tr><th>server</th><td><code>{{.Status.BaseURL}}</code></td></tr>
|
||||
<tr><th>n_ctx</th><td>{{.Status.NCtx}}</td></tr>
|
||||
<tr><th>n_gpu_layers</th><td>{{.Status.NGpuLayers}}</td></tr>
|
||||
</table></div>
|
||||
<p class=hint>the model name is what llama-server reports for itself, not what the config says it should be.</p>
|
||||
</section>
|
||||
<section class=card>
|
||||
<h2 class=card-title>allowed models <span class=badge>{{len .Status.Swappable}}</span></h2>
|
||||
{{if .Status.Swappable}}<div class=scroll><table><tr><th>file</th><th></th></tr>
|
||||
{{range .Status.Swappable}}<tr><td><code>{{.}}</code></td>
|
||||
<td><form method=post action=/models class=inline-form>
|
||||
<input type=hidden name=model_path value="{{.}}">
|
||||
<button class=btn>load this one</button></form></td></tr>{{end}}
|
||||
</table></div>
|
||||
{{else}}<div class=empty><div>no models allowlisted</div></div>{{end}}
|
||||
</section>
|
||||
{{end}}
|
||||
{{template "shellBottom"}}
|
||||
@@ -8,7 +8,10 @@
|
||||
<div class=scroll><table class=mono>
|
||||
<tr><th>at<th>kind<th>what</tr>
|
||||
{{range .Items}}<tr>
|
||||
<td>{{.At.Format "15:04"}}</td>
|
||||
<!-- In his clock. A plan item's At is a calendar fact's Ts or a reminder's
|
||||
FireTs, and the store hands both back as UTC, so the raw hour printed a
|
||||
reminder here at an hour /reminders did not agree with (V-469). -->
|
||||
<td>{{.At.Local.Format "15:04"}}</td>
|
||||
<td class=gray>{{.Kind}}</td>
|
||||
<td>{{if .Uncertain}}<span class=hint title="relayed notification, not a calendar read">похоже,</span> {{end}}{{.Text}}</td>
|
||||
</tr>{{end}}
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
// morningCore serves a canned checklist and day plan.
|
||||
type morningCore struct {
|
||||
ipc.UnimplementedCoreAPI
|
||||
status []ipc.MorningRoutineStatus
|
||||
plan ipc.DayPlan
|
||||
}
|
||||
|
||||
func (c *morningCore) MorningStatus(context.Context) ([]ipc.MorningRoutineStatus, error) {
|
||||
return c.status, nil
|
||||
}
|
||||
|
||||
func (c *morningCore) DayPlan(context.Context) (ipc.DayPlan, error) { return c.plan, nil }
|
||||
|
||||
func TestMorningRendersPlanTimesInLocalZone(t *testing.T) {
|
||||
// A plan item's At is a calendar fact's Ts or a reminder's FireTs, and the
|
||||
// store hands both back as UTC. Printed raw, /morning named an hour for a
|
||||
// reminder that /reminders — which does call Local — disagreed with.
|
||||
away := awayFromLocal()
|
||||
at := time.Date(2026, 8, 1, 9, 0, 0, 0, time.UTC).In(away)
|
||||
core := &morningCore{plan: ipc.DayPlan{
|
||||
Date: at,
|
||||
Items: []ipc.DayPlanItem{{At: at, Text: "выпить таблетки", Kind: "reminder"}},
|
||||
}}
|
||||
w := httptest.NewRecorder()
|
||||
handleMorning(w, httptest.NewRequest(http.MethodGet, "/morning", nil), core)
|
||||
if w.Code != http.StatusOK {
|
||||
t.Fatalf("status = %d, want 200", w.Code)
|
||||
}
|
||||
body := w.Body.String()
|
||||
if !strings.Contains(body, at.Local().Format("15:04")) {
|
||||
t.Errorf("plan item not rendered in his clock (%s): %s", at.Local().Format("15:04"), body)
|
||||
}
|
||||
if strings.Contains(body, at.In(away).Format("15:04")) {
|
||||
t.Errorf("plan item rendered in the stored zone: %s", body)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,76 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"net/http"
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
//go:embed notifications.html
|
||||
var notificationsHTML string
|
||||
|
||||
var notificationsTmpl = parsePage("notifications", notificationsHTML, nil)
|
||||
|
||||
// deliveryRow is one outbox line, with every timestamp already formatted so
|
||||
// the template holds no date logic — same shape as taskRow.
|
||||
type deliveryRow struct {
|
||||
Kind string
|
||||
Target string
|
||||
Channel string
|
||||
Status string
|
||||
Created string
|
||||
Completed string
|
||||
}
|
||||
|
||||
func deliveryRows(as []ipc.DeliveryAttempt) []deliveryRow {
|
||||
out := make([]deliveryRow, 0, len(as))
|
||||
for _, a := range as {
|
||||
target := a.Rule
|
||||
if target == "" && a.ReminderID != 0 {
|
||||
target = "reminder #" + strconv.FormatInt(a.ReminderID, 10)
|
||||
}
|
||||
row := deliveryRow{
|
||||
Kind: a.Kind,
|
||||
Target: target,
|
||||
Channel: a.Channel,
|
||||
Status: a.Status,
|
||||
Created: a.Created.Format("02.01 15:04"),
|
||||
}
|
||||
if a.Completed != nil {
|
||||
row.Completed = a.Completed.Format("15:04")
|
||||
}
|
||||
out = append(out, row)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func handleNotifications(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "notifications") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
nudges, err := core.RecentNudges(ctx, 50)
|
||||
if err != nil {
|
||||
log.Printf("notifications: %v", err)
|
||||
http.Error(w, "notifications error: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
// The outbox, on the page that already answers "what did she send".
|
||||
// A failed or dropped attempt is why she went quiet, and until now it was
|
||||
// recorded and unreadable (Vikunja #390). Filter with ?status=dropped.
|
||||
status := r.URL.Query().Get("status")
|
||||
attempts, err := core.DeliveryAttempts(ctx, status, 50)
|
||||
if err != nil {
|
||||
// The nudge list is still worth showing, so this is a note on the page
|
||||
// rather than a dead page.
|
||||
log.Printf("notifications: delivery attempts: %v", err)
|
||||
}
|
||||
renderPage(w, notificationsTmpl, map[string]any{
|
||||
"Nudges": nudges,
|
||||
"Attempts": deliveryRows(attempts),
|
||||
"Status": status,
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,205 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"cmp"
|
||||
_ "embed"
|
||||
"html/template"
|
||||
"log"
|
||||
"net/http"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
// The read-only pages: dash, history, trace, morning, events, and the voice
|
||||
// page mounted at "/". Each is GET-only, reads through CoreAPI and renders.
|
||||
// The write surfaces live next to their own handlers (tasks.go, tools.go,
|
||||
// routines.go, chat.go).
|
||||
|
||||
//go:embed dash.html
|
||||
var dashHTML string
|
||||
|
||||
//go:embed history.html
|
||||
var historyHTML string
|
||||
|
||||
//go:embed trace.html
|
||||
var traceHTML string
|
||||
|
||||
//go:embed morning.html
|
||||
var morningHTML string
|
||||
|
||||
//go:embed events.html
|
||||
var eventsHTML string
|
||||
|
||||
//go:embed voice.html
|
||||
var voiceHTML string
|
||||
|
||||
//go:embed ecosystem.html
|
||||
var ecosystemHTML string
|
||||
|
||||
// dashTmpl — the monitoring read surface, server-rendered from dash.html;
|
||||
// a small fetch loop refreshes the tables in place. html/template escapes the
|
||||
// user text in facts/nudges. Read-only: browses the append-only store via
|
||||
// CoreAPI, never writes — the store IS the audit trail, this just shows it.
|
||||
var dashTmpl = parsePage("dash", dashHTML, nil)
|
||||
|
||||
var historyTmpl = parsePage("history", historyHTML, nil)
|
||||
|
||||
var traceTmpl = parsePage("trace", traceHTML, template.FuncMap{
|
||||
"fmtTime": func(t *time.Time) string {
|
||||
if t == nil || t.IsZero() {
|
||||
return "—"
|
||||
}
|
||||
return t.Format("15:04:05")
|
||||
},
|
||||
"join": strings.Join,
|
||||
})
|
||||
|
||||
// morningTmpl — read-only view of today's checklist state per configured
|
||||
// morning routine (internal/morning). Same shape as trace.html: a plain
|
||||
// server-rendered page, refreshed on reload — no live-update loop, since
|
||||
// checklist state changes on the scale of minutes, not seconds.
|
||||
var morningTmpl = parsePage("morning", morningHTML, nil)
|
||||
|
||||
// eventsTmpl — the unified intake journal (Vikunja #283), read-only. Same
|
||||
// shape as trace.html and morning.html: server-rendered, refreshed on reload.
|
||||
var eventsTmpl = parsePage("events", eventsHTML, nil)
|
||||
|
||||
var voiceTmpl = parsePage("voice", voiceHTML, nil)
|
||||
|
||||
// ecosystemTmpl — read-only view of the Nexus/Praxis/Hexis siblings, whose only
|
||||
// human surface is here (they ship no web UI of their own).
|
||||
var ecosystemTmpl = parsePage("ecosystem", ecosystemHTML, nil)
|
||||
|
||||
func handleDash(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "dash") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
pres, err1 := core.Presence(ctx)
|
||||
facts, err2 := core.RecentFacts(ctx, 50)
|
||||
nudges, err3 := core.RecentNudges(ctx, 50)
|
||||
notes, err4 := core.RecentNotes(ctx, 50)
|
||||
if err := cmp.Or(err1, err2, err3, err4); err != nil {
|
||||
log.Printf("dash: %v", err)
|
||||
http.Error(w, "core read failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
renderPage(w, dashTmpl, struct {
|
||||
Presence ipc.Presence
|
||||
Facts []ipc.Fact
|
||||
Nudges []ipc.Nudge
|
||||
Notes []ipc.Note
|
||||
}{pres, facts, nudges, notes})
|
||||
}
|
||||
|
||||
func handleHistory(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "history") {
|
||||
return
|
||||
}
|
||||
facts, err := core.RecentFacts(r.Context(), 200)
|
||||
if err != nil {
|
||||
log.Printf("history: %v", err)
|
||||
http.Error(w, "core read failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
renderPage(w, historyTmpl, struct {
|
||||
Facts []ipc.Fact
|
||||
}{facts})
|
||||
}
|
||||
|
||||
func handleTrace(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "trace") {
|
||||
return
|
||||
}
|
||||
trace, err := core.TickTrace(r.Context())
|
||||
if err != nil {
|
||||
log.Printf("trace: %v", err)
|
||||
http.Error(w, "core read failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
// The turn records share this page rather than getting one of their own
|
||||
// (V-564). Both answer the same question, who won and who lost and why, and
|
||||
// one is about nudges while the other is about utterances. A read failure
|
||||
// here is not fatal to the page. The rule trace above it still renders, and
|
||||
// a daemon too old to know the method is the ordinary case during a rolling
|
||||
// deploy.
|
||||
turns, err := core.TurnDecisions(r.Context(), 25)
|
||||
if err != nil {
|
||||
log.Printf("trace: turn decisions: %v", err)
|
||||
}
|
||||
renderPage(w, traceTmpl, traceData{Tick: trace, Turns: turns})
|
||||
}
|
||||
|
||||
// traceData — what trace.html renders: the last tick's rule arbitration and the
|
||||
// last turns' claim arbitration.
|
||||
type traceData struct {
|
||||
Tick ipc.TickTrace
|
||||
Turns []ipc.TurnDecision
|
||||
}
|
||||
|
||||
// morningView — what /morning renders: today's plan on top, the checklist
|
||||
// state under it. PlanErr is set instead of Plan when the core could not build
|
||||
// a plan, so the page says so rather than showing an empty day.
|
||||
type morningView struct {
|
||||
Plan *ipc.DayPlan
|
||||
PlanErr string
|
||||
Routines []ipc.MorningRoutineStatus
|
||||
}
|
||||
|
||||
func handleMorning(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "morning") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
status, err := core.MorningStatus(ctx)
|
||||
if err != nil {
|
||||
log.Printf("morning: %v", err)
|
||||
http.Error(w, "core read failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
view := morningView{Routines: status}
|
||||
// The day plan (#128) shows on this page because it is the same question at
|
||||
// a different scale. A plan read that fails must not take the checklist
|
||||
// down with it — the page degrades to what it had before.
|
||||
plan, err := core.DayPlan(ctx)
|
||||
if err != nil {
|
||||
log.Printf("morning: day plan: %v", err)
|
||||
view.PlanErr = err.Error()
|
||||
} else {
|
||||
view.Plan = &plan
|
||||
}
|
||||
renderPage(w, morningTmpl, view)
|
||||
}
|
||||
|
||||
// eventsView — what /events renders. Err is set instead of Events when the
|
||||
// core could not serve the journal, so the page says why rather than showing an
|
||||
// empty intake and implying nothing arrived.
|
||||
type eventsView struct {
|
||||
Events []ipc.IntakeEvent
|
||||
Err string
|
||||
}
|
||||
|
||||
// eventsPageLimit — how many envelopes the page shows. The ring holds more; a
|
||||
// page is for scanning what just happened, not for archaeology.
|
||||
const eventsPageLimit = 200
|
||||
|
||||
func handleEvents(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "intake journal") {
|
||||
return
|
||||
}
|
||||
var view eventsView
|
||||
evs, err := core.RecentEvents(r.Context(), eventsPageLimit)
|
||||
if err != nil {
|
||||
log.Printf("events: %v", err)
|
||||
view.Err = err.Error()
|
||||
} else {
|
||||
view.Events = evs
|
||||
}
|
||||
renderPage(w, eventsTmpl, view)
|
||||
}
|
||||
|
||||
func handleVoice(w http.ResponseWriter, r *http.Request) {
|
||||
renderPage(w, voiceTmpl, nil)
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
{{template "shellTop" "passkey"}}
|
||||
<h1>Passkey</h1>
|
||||
<p class=hint>Enroll a passkey once, then assert it to unlock destructive actions (tool enable) for a few minutes.</p>
|
||||
<div class=flex gap-2>
|
||||
<button class=btn onclick=enroll()>enroll passkey</button>
|
||||
<button class=btn onclick=assert()>assert (step-up)</button>
|
||||
<button class=btn onclick=rewrapKey()>rewrite cold-start key</button>
|
||||
<a href=/tools><button class=btn-primary>→ tools</button></a>
|
||||
</div>
|
||||
<p class=hint>Rewriting the cold-start key points it at the passkey you assert next. Every other enrolled passkey stops being able to unlock a cold-booted daemon.</p>
|
||||
<div id=msg></div>
|
||||
{{template "shellBottom"}}
|
||||
<script>
|
||||
const b64u=b=>btoa(String.fromCharCode(...new Uint8Array(b))).replace(/\+/g,'-').replace(/\//g,'_').replace(/=+$/,'');
|
||||
const ub64=s=>{s=s.replace(/-/g,'+').replace(/_/g,'/');const b=atob(s),a=new Uint8Array(b.length);for(let i=0;i<b.length;i++)a[i]=b.charCodeAt(i);return a;};
|
||||
const say=(t,ok)=>{const m=document.getElementById('msg');m.textContent=t;m.className=ok?'msg msg-ok':'msg msg-err';};
|
||||
async function enroll(){try{
|
||||
const {challenge,options}=await (await fetch('/auth/webauthn/register/begin')).json();
|
||||
options.challenge=ub64(options.challenge);
|
||||
options.user.id=ub64(options.user.id);
|
||||
const c=await navigator.credentials.create({publicKey:options});
|
||||
const r=await fetch('/auth/webauthn/register/finish',{method:'POST',headers:{'content-type':'application/json'},
|
||||
body:JSON.stringify({challenge,credential:{id:c.id,type:c.type,response:{
|
||||
clientDataJSON:b64u(c.response.clientDataJSON),attestationObject:b64u(c.response.attestationObject)}}})});
|
||||
if(!r.ok){say('enroll failed: '+await r.text(),false);return;}
|
||||
// The wrapped key can only be written from an assertion: PRF results are
|
||||
// not produced at create() time on most authenticators. Enrolment reports
|
||||
// whether PRF is available at all so he is not told cold-start works when
|
||||
// it cannot.
|
||||
const ext=c.getClientExtensionResults?c.getClientExtensionResults():{};
|
||||
const prfOK=!!(ext.prf&&ext.prf.enabled);
|
||||
say(prfOK?'enrolled ✓ — now assert once to write the cold-start key':
|
||||
'enrolled ✓ — but this authenticator has no PRF: cold-start unlock unavailable',true);
|
||||
}catch(e){say('enroll error: '+e,false);}}
|
||||
async function assert(explicit){try{
|
||||
const {challenge,options}=await (await fetch('/auth/webauthn/assert/begin')).json();
|
||||
options.challenge=ub64(options.challenge);
|
||||
const c=await navigator.credentials.get({publicKey:options});
|
||||
// The PRF result is the cold-start secret. It never touches localStorage
|
||||
// and is posted once, over the same request as the assertion.
|
||||
const ext=c.getClientExtensionResults?c.getClientExtensionResults():{};
|
||||
const prf=ext.prf&&ext.prf.results&&ext.prf.results.first?b64u(ext.prf.results.first):'';
|
||||
const r=await fetch('/auth/webauthn/assert/finish',{method:'POST',headers:{'content-type':'application/json'},
|
||||
body:JSON.stringify({challenge,prf,explicit:!!explicit,credential:{id:c.id,type:c.type,response:{
|
||||
clientDataJSON:b64u(c.response.clientDataJSON),authenticatorData:b64u(c.response.authenticatorData),
|
||||
signature:b64u(c.response.signature)}}})});
|
||||
if(!r.ok){say('assert failed: '+await r.text(),false);return;}
|
||||
if(!prf){say('stepped up ✓ — no PRF from this authenticator, so cold-start unlock stayed unavailable',true);return;}
|
||||
say(explicit?'stepped up ✓ — cold-start key now points at this passkey':
|
||||
'stepped up ✓ — enable tools now',true);
|
||||
}catch(e){say('assert error: '+e,false);}}
|
||||
// Rewriting the wrapped key is a separate gesture, never a side effect of a
|
||||
// step-up. Only this button sets explicit, and only explicit lets the daemon
|
||||
// replace a blob that already exists.
|
||||
async function rewrapKey(){
|
||||
if(!confirm('Rewrite the cold-start key under the passkey you are about to assert? Every other enrolled passkey stops being able to unlock a cold-booted daemon.'))return;
|
||||
await assert(true);}
|
||||
</script>
|
||||
@@ -0,0 +1,74 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"encoding/json"
|
||||
"log"
|
||||
"net/http"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
//go:embed reminders.html
|
||||
var remindersHTML string
|
||||
|
||||
var remindersTmpl = parsePage("reminders", remindersHTML, nil)
|
||||
|
||||
// reminderRow is one line on /reminders, with the payload unwrapped and both
|
||||
// timestamps already in his clock.
|
||||
//
|
||||
// The page rendered `{{.Payload}}` and the UTC instant, so a reminder read
|
||||
// `{"text":"выпить таблетки"}` and fired an hour off what he was told
|
||||
// (Vikunja #469). Neither is a formatting nicety: the envelope is an internal
|
||||
// shape he never chose, and a time on a page he reads is the time on his wall.
|
||||
type reminderRow struct {
|
||||
Created string
|
||||
Fires string
|
||||
Status string
|
||||
Text string
|
||||
}
|
||||
|
||||
// reminderText unwraps the {"text":...} payload the router writes.
|
||||
//
|
||||
// A copy of store.ReminderText rather than a call to it, because mavweb is one
|
||||
// of the pure-Go daemons and internal/store carries the CGO sqlite driver. The
|
||||
// ipc DTO is decoupled from the store on purpose, so the unwrap belongs to
|
||||
// whoever renders it. Payload that is not that shape is shown as he said it.
|
||||
func reminderText(payload string) string {
|
||||
var m map[string]any
|
||||
if err := json.Unmarshal([]byte(payload), &m); err == nil {
|
||||
if t, ok := m["text"]; ok {
|
||||
if s, isStr := t.(string); isStr && s != "" {
|
||||
return s
|
||||
}
|
||||
}
|
||||
}
|
||||
return strings.TrimSpace(payload)
|
||||
}
|
||||
|
||||
func reminderRows(rs []ipc.Reminder) []reminderRow {
|
||||
out := make([]reminderRow, 0, len(rs))
|
||||
for _, r := range rs {
|
||||
out = append(out, reminderRow{
|
||||
Created: r.CreatedTs.Local().Format("02 Jan 15:04"),
|
||||
Fires: r.FireTs.Local().Format("02 Jan 15:04"),
|
||||
Status: r.Status,
|
||||
Text: reminderText(r.Payload),
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func handleReminders(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "reminders") {
|
||||
return
|
||||
}
|
||||
reminders, err := core.ListReminders(r.Context(), 50)
|
||||
if err != nil {
|
||||
log.Printf("reminders: %v", err)
|
||||
http.Error(w, "reminders error: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
renderPage(w, remindersTmpl, map[string]any{"Reminders": reminderRows(reminders)})
|
||||
}
|
||||
@@ -0,0 +1,200 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
_ "embed"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"net/http"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/pattern"
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
//go:embed routines.html
|
||||
var routinesHTML string
|
||||
|
||||
// routinesTmpl — the proposed-routine review surface. One row per thing maven
|
||||
// noticed, in her words, with at most two actions: accept or dismiss.
|
||||
var routinesTmpl = parsePage("routines", routinesHTML, nil)
|
||||
|
||||
// routineView is one line on the page: what maven noticed, in her words, and
|
||||
// how long ago she noticed it. A view model, not a database row — the template
|
||||
// never formats an interval or a timestamp itself.
|
||||
type routineView struct {
|
||||
ID int64
|
||||
Phrase string
|
||||
Noticed string
|
||||
}
|
||||
|
||||
// handleRoutines serves the routine review surface (GET) and answers a
|
||||
// proposal (POST id + action=accept|dismiss).
|
||||
//
|
||||
// Accept is gated at step-up, the same tier as enabling a tool: saying yes
|
||||
// hands the trigger loop a new standing reason to speak to the human, so it
|
||||
// moves the boundary and only an authed surface may do it. Dismiss is not
|
||||
// gated — it only ever removes a reason to speak, so the worst a weaker caller
|
||||
// can do is make maven quieter.
|
||||
func handleRoutines(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) {
|
||||
if !requireCore(w, core, "routines") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
var msg string
|
||||
if r.Method == http.MethodPost {
|
||||
var ok bool
|
||||
if msg, ok = applyRoutinePost(w, r, core, session, requireStepUp); !ok {
|
||||
return
|
||||
}
|
||||
}
|
||||
proposed, err := core.ListProposedRoutines(ctx)
|
||||
if err != nil {
|
||||
log.Printf("routines: list: %v", err)
|
||||
http.Error(w, "routines error: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
renderPage(w, routinesTmpl, struct {
|
||||
Msg string
|
||||
Proposed []routineView
|
||||
}{msg, toRoutineViews(proposed)})
|
||||
}
|
||||
|
||||
// applyRoutinePost performs one write and returns the message to show. Unlike
|
||||
// the task form, a bad request here is an HTTP status rather than an inline
|
||||
// note, so the second return says whether the response was already written.
|
||||
func applyRoutinePost(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) (string, bool) {
|
||||
ctx := r.Context()
|
||||
action := r.FormValue("action")
|
||||
// "seed" is the one action with no routine to act on — it is what
|
||||
// MAKES a routine (Vikunja #518), so it runs before the id parse. It
|
||||
// lives on this route rather than a page of its own because it is
|
||||
// already the step-up-gated surface for this table, and a second gated
|
||||
// surface is a second thing to get wrong.
|
||||
if action == "seed" {
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return "", false
|
||||
}
|
||||
out, err := seedRoutineEvent(ctx, core, r)
|
||||
if err != nil {
|
||||
log.Printf("routines: seed: %v", err)
|
||||
http.Error(w, "seed failed: "+err.Error(), http.StatusBadGateway)
|
||||
return "", false
|
||||
}
|
||||
return out, true
|
||||
}
|
||||
|
||||
idStr := r.FormValue("id")
|
||||
var rid int64
|
||||
if n, _ := fmt.Sscanf(idStr, "%d", &rid); n != 1 {
|
||||
http.Error(w, "invalid id", http.StatusBadRequest)
|
||||
return "", false
|
||||
}
|
||||
switch action {
|
||||
case "accept":
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return "", false
|
||||
}
|
||||
if err := acceptRoutine(ctx, core, rid); err != nil {
|
||||
log.Printf("routines: accept %d: %v", rid, err)
|
||||
http.Error(w, "accept failed: "+err.Error(), http.StatusBadGateway)
|
||||
return "", false
|
||||
}
|
||||
return "accepted routine — maven will remind you", true
|
||||
case "dismiss":
|
||||
if err := core.DismissProposedRoutine(ctx, rid); err != nil {
|
||||
log.Printf("routines: dismiss %d: %v", rid, err)
|
||||
http.Error(w, "dismiss failed: "+err.Error(), http.StatusBadGateway)
|
||||
return "", false
|
||||
}
|
||||
return "dismissed routine", true
|
||||
default:
|
||||
http.Error(w, "unknown action", http.StatusBadRequest)
|
||||
return "", false
|
||||
}
|
||||
}
|
||||
|
||||
// toRoutineViews turns the wire rows into view models. The phrase comes from
|
||||
// pattern.PhraseRoutine so the page says the same thing maven's voice says.
|
||||
func toRoutineViews(rs []ipc.ProposedRoutine) []routineView {
|
||||
out := make([]routineView, 0, len(rs))
|
||||
for _, r := range rs {
|
||||
p := pattern.ProposedRoutine{Action: r.Action, Object: r.Object, IntervalDays: r.IntervalDays}
|
||||
noticed := "just now"
|
||||
if r.CreatedTs > 0 {
|
||||
noticed = time.Since(time.UnixMilli(r.CreatedTs)).Round(time.Minute).String() + " ago"
|
||||
}
|
||||
out = append(out, routineView{ID: r.ID, Phrase: pattern.PhraseRoutine(&p), Noticed: noticed})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// acceptRoutine marks a proposal accepted. This page is the ONLY surface that
|
||||
// may do it (Vikunja #367): accepting gives the tick loop a standing new
|
||||
// reason to speak, which DESIGN.md puts at layer 3, and the button here is
|
||||
// behind step-up. Voice can park the question and dismiss, never accept.
|
||||
func acceptRoutine(ctx context.Context, core ipc.CoreAPI, id int64) error {
|
||||
proposed, err := core.ListProposedRoutines(ctx)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var found *ipc.ProposedRoutine
|
||||
for i := range proposed {
|
||||
if proposed[i].ID == id {
|
||||
found = &proposed[i]
|
||||
break
|
||||
}
|
||||
}
|
||||
if found == nil {
|
||||
return errors.New("no such proposed routine")
|
||||
}
|
||||
|
||||
// No reminder is created here. Accepting only flips the status; the tick
|
||||
// loop reads accepted routines and nudges on the interval (Vikunja #366).
|
||||
// The old code made a one-shot reminder, so a non-weekly routine fired
|
||||
// once and then went quiet forever.
|
||||
return core.AcceptProposedRoutine(ctx, id)
|
||||
}
|
||||
|
||||
// seedRoutineEvent drives one backdated fact write through core (Vikunja #518),
|
||||
// so the pattern detector can be exercised against a running daemon instead of
|
||||
// over real days. Refused unless mavend was started with -allow-seed; on an
|
||||
// ordinary box the error says so and nothing is written.
|
||||
//
|
||||
// Takes "ago" rather than an absolute timestamp — hours before now, as a float
|
||||
// so a QA sitting can space four seeds three hours apart without doing clock
|
||||
// arithmetic. The detector's floor is two hours, and "0" is a legal answer
|
||||
// meaning now.
|
||||
func seedRoutineEvent(ctx context.Context, core ipc.CoreAPI, r *http.Request) (string, error) {
|
||||
key := strings.TrimSpace(r.FormValue("key"))
|
||||
value := strings.TrimSpace(r.FormValue("value"))
|
||||
if key == "" || value == "" {
|
||||
return "", errors.New("seed needs a key and a value")
|
||||
}
|
||||
agoHours, err := strconv.ParseFloat(strings.TrimSpace(r.FormValue("ago")), 64)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("seed: bad ago (hours before now): %w", err)
|
||||
}
|
||||
if agoHours < 0 {
|
||||
return "", errors.New("seed: ago is hours BEFORE now, so it cannot be negative")
|
||||
}
|
||||
resp, err := core.SeedEvent(ctx, ipc.SeedEventReq{
|
||||
Key: key,
|
||||
Value: value,
|
||||
Ts: time.Now().Add(-time.Duration(agoHours * float64(time.Hour))),
|
||||
})
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if !resp.Extracted {
|
||||
return fmt.Sprintf("wrote fact %d, but %q is not in the action lexicon — no event, no pattern", resp.FactID, value), nil
|
||||
}
|
||||
if !resp.Proposed {
|
||||
return fmt.Sprintf("seeded %s/%s (fact %d, event %d) — not enough yet to propose", resp.Action, resp.Object, resp.FactID, resp.EventID), nil
|
||||
}
|
||||
return fmt.Sprintf("seeded %s/%s and PROPOSED routine %d, every %.1f days", resp.Action, resp.Object, resp.RoutineID, resp.IntervalDays), nil
|
||||
}
|
||||
@@ -0,0 +1,195 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"html/template"
|
||||
"log"
|
||||
"net/http"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
// shellHTML — the shell partial every page is wrapped in: "shellTop", the
|
||||
// "sidebar" it calls, and "shellBottom". It used to be two Go string constants
|
||||
// with the sidebar assembled by a strings.Builder, which is the one piece of
|
||||
// markup that was still concatenated in Go.
|
||||
//
|
||||
// Two template pieces wrap every page:
|
||||
//
|
||||
// {{template "shellTop" "<page-key>"}} ← opens <html>, topbar, sidebar, content
|
||||
// {{template "shellBottom"}} ← closes content, inspector, </html>
|
||||
//
|
||||
// The page-key argument highlights the active sidebar link and sets breadcrumbs.
|
||||
//
|
||||
//go:embed shell.html
|
||||
var shellHTML string
|
||||
|
||||
// sidebarSections maps sidebar section → page entries {label, url, icon}
|
||||
var sidebarSections = []struct {
|
||||
Label string
|
||||
Pages []struct{ Label, URL, Key string }
|
||||
}{
|
||||
{
|
||||
Label: "Workspace",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "Dashboard", URL: "/dash", Key: "dash"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Label: "Infrastructure",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "History", URL: "/history", Key: "history"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Label: "Automation",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "Rule Trace", URL: "/trace", Key: "trace"},
|
||||
{Label: "Notifications", URL: "/notifications", Key: "notifications"},
|
||||
{Label: "Tasks", URL: "/tasks", Key: "tasks"},
|
||||
{Label: "Reminders", URL: "/reminders", Key: "reminders"},
|
||||
{Label: "Routines", URL: "/routines", Key: "routines"},
|
||||
{Label: "Morning", URL: "/morning", Key: "morning"},
|
||||
{Label: "Intake", URL: "/events", Key: "events"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Label: "Ecosystem",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "Siblings", URL: "/ecosystem", Key: "ecosystem"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Label: "AI",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "Chat", URL: "/chat", Key: "chat"},
|
||||
{Label: "Voice", URL: "/", Key: "voice"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Label: "Settings",
|
||||
Pages: []struct{ Label, URL, Key string }{
|
||||
{Label: "Tools", URL: "/tools", Key: "tools"},
|
||||
{Label: "Model", URL: "/models", Key: "models"},
|
||||
{Label: "Passkey", URL: "/auth/passkey", Key: "passkey"},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
// pageChrome is the per-page title and ethos-icons.svg symbol id, keyed by the
|
||||
// page key a page hands to shellTop. One table rather than two parallel
|
||||
// switches, so a new page cannot end up with a title and no icon.
|
||||
var pageChrome = map[string]struct{ Title, Icon string }{
|
||||
"dash": {"Dashboard", "i-grid"},
|
||||
"history": {"History", "i-clock"},
|
||||
"trace": {"Rule Trace", "i-wave"},
|
||||
"notifications": {"Notifications", "i-bell"},
|
||||
"tasks": {"Tasks", "i-grid"},
|
||||
"reminders": {"Reminders", "i-calendar"},
|
||||
"routines": {"Routines", "i-repeat"},
|
||||
"morning": {"Morning Routines", "i-calendar"},
|
||||
"events": {"Intake", "i-download"},
|
||||
"chat": {"Chat", "i-message"},
|
||||
"voice": {"Voice", "i-mic"},
|
||||
"ecosystem": {"Ecosystem", "i-grid"},
|
||||
"tools": {"Tools", "i-settings"},
|
||||
"models": {"Resident Model", "i-wave"},
|
||||
"passkey": {"Passkey", "i-lock"},
|
||||
}
|
||||
|
||||
// pageIcon returns the ethos-icons.svg symbol id for the given page. The
|
||||
// sidebar template wraps it in the <use> reference.
|
||||
func pageIcon(key string) string {
|
||||
if c, ok := pageChrome[key]; ok {
|
||||
return c.Icon
|
||||
}
|
||||
return "i-search"
|
||||
}
|
||||
|
||||
// pageTitle returns the human-readable page title for the given key. An
|
||||
// unknown key renders as itself rather than as a blank crumb.
|
||||
func pageTitle(key string) string {
|
||||
if c, ok := pageChrome[key]; ok {
|
||||
return c.Title
|
||||
}
|
||||
return key
|
||||
}
|
||||
|
||||
// shellFuncs returns the FuncMap shared by every server-rendered page template.
|
||||
func shellFuncs() template.FuncMap {
|
||||
return template.FuncMap{
|
||||
"pageTitle": pageTitle,
|
||||
"pageIcon": pageIcon,
|
||||
"sidebarSections": func() any { return sidebarSections },
|
||||
"ago": func(t time.Time) string {
|
||||
if t.IsZero() {
|
||||
return "never"
|
||||
}
|
||||
return time.Since(t).Round(time.Second).String() + " ago"
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// parsePage parses one server-rendered page: the shell partial plus the page's
|
||||
// own embedded markup, under the shared FuncMap. extra adds page-local
|
||||
// functions (/tools needs capability lookups, /trace a time format) and may be
|
||||
// nil.
|
||||
//
|
||||
// The name is also the page's log label, so a render failure says which page.
|
||||
func parsePage(name, body string, extra template.FuncMap) *template.Template {
|
||||
funcs := shellFuncs()
|
||||
for k, v := range extra {
|
||||
funcs[k] = v
|
||||
}
|
||||
return template.Must(template.New(name).Funcs(funcs).Parse(shellHTML + body))
|
||||
}
|
||||
|
||||
// renderPage writes one page. Every handler sent the same content type and
|
||||
// logged the same way on failure; the header is already written by then, so a
|
||||
// render error can only be logged, never reported.
|
||||
func renderPage(w http.ResponseWriter, t *template.Template, data any) {
|
||||
w.Header().Set("Content-Type", "text/html; charset=utf-8")
|
||||
if err := t.Execute(w, data); err != nil {
|
||||
log.Printf("%s render: %v", t.Name(), err)
|
||||
}
|
||||
}
|
||||
|
||||
// requireCore answers whether the surface has a core to read. mavweb runs
|
||||
// without -core (voice-only), and every page that needs mavend says so with a
|
||||
// 503 naming itself rather than a blank error.
|
||||
func requireCore(w http.ResponseWriter, core ipc.CoreAPI, surface string) bool {
|
||||
if core == nil {
|
||||
http.Error(w, surface+" disabled (no -core)", http.StatusServiceUnavailable)
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// stepUpGate reports whether the caller may proceed through the AuthStepUp
|
||||
// gate, writing the 403 itself when it may not. See stepUpOK for the policy.
|
||||
func stepUpGate(w http.ResponseWriter, session *webauthn.PasskeySession, requireStepUp bool) bool {
|
||||
if stepUpOK(session, requireStepUp) {
|
||||
return true
|
||||
}
|
||||
http.Error(w, "step-up required: assert a passkey first", http.StatusForbidden)
|
||||
return false
|
||||
}
|
||||
|
||||
// stepUpOK is the single decision point for the AuthStepUp gate shared by
|
||||
// POST /tools and POST /api/revert.
|
||||
//
|
||||
// A nil session means WebAuthn is not configured (-webauthn-origin /
|
||||
// -webauthn-rpid unset), so step-up can never be asserted — not merely unmet.
|
||||
// The default is therefore fail-OPEN: gating on an unassertable session would
|
||||
// 403 those surfaces permanently. In that mode the actions rest on the
|
||||
// transport-level auth in front of mavweb (wg+nginx+auth), and main logs a
|
||||
// startup warning naming them. With -require-stepup the same situation fails
|
||||
// CLOSED instead: no assertable step-up ⇒ deny.
|
||||
func stepUpOK(session *webauthn.PasskeySession, requireStepUp bool) bool {
|
||||
if session == nil {
|
||||
return !requireStepUp
|
||||
}
|
||||
return session.IsStepUp()
|
||||
}
|
||||
@@ -702,6 +702,11 @@ details[open] > summary { margin-bottom: var(--space-1); }
|
||||
.chat-form { display: flex; gap: var(--space-2); }
|
||||
.chat-form input { flex: 1; }
|
||||
.chat-scroll { max-height: 60vh; overflow-y: auto; margin-bottom: var(--space-4); }
|
||||
/* The correction gesture (V-630). Wraps on a phone rather than scrolling: it is
|
||||
one row of small buttons, and a gesture that has to be panned to is not one. */
|
||||
.chat-correct { display: flex; flex-wrap: wrap; align-items: center; gap: var(--space-1);
|
||||
padding: 0 var(--space-3) var(--space-2); margin-top: calc(-1 * var(--space-1)); margin-bottom: var(--space-2); }
|
||||
.chat-correct-label { font-size: var(--fs-xs); color: var(--text-machine); margin-left: var(--space-2); }
|
||||
|
||||
/* ── Key-value grid ── */
|
||||
.kv { display: grid; grid-template-columns: auto 1fr; gap: var(--space-1) var(--space-3); font-size: var(--fs-sm); }
|
||||
|
||||
@@ -0,0 +1,412 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
_ "embed"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"net/http"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/tasks"
|
||||
)
|
||||
|
||||
//go:embed tasks.html
|
||||
var tasksHTML string
|
||||
|
||||
var tasksTmpl = parsePage("tasks", tasksHTML, nil)
|
||||
|
||||
// now — the wall clock, indirected so the task page can be rendered at a fixed
|
||||
// instant in a test. internal/tasks is pure and the daemon path already ranks
|
||||
// through a clock it is handed; the page had no reason to be the one surface
|
||||
// that could only be tested at whatever time it happened to run.
|
||||
var now = time.Now
|
||||
|
||||
// resolvedShown — how many finished tasks the page renders. The list is
|
||||
// history, it only grows, and the rows below the first screen are read by
|
||||
// nobody.
|
||||
const resolvedShown = 50
|
||||
|
||||
// taskRow is one line on /tasks, with every timestamp already formatted so the
|
||||
// template holds no date logic.
|
||||
type taskRow struct {
|
||||
ID int64
|
||||
Text string
|
||||
Source string
|
||||
Evidence string
|
||||
Status string
|
||||
Due string
|
||||
Created string
|
||||
Resolved string
|
||||
ResolvedBy string
|
||||
// DueValue and Weight are the raw values the edit form posts back
|
||||
// (Vikunja #509). Due above is for reading and says "—" for no date; a
|
||||
// date input needs "2026-08-07" or the empty string.
|
||||
DueValue string
|
||||
Weight int
|
||||
// Why — the ranker's reason for this row's position (Vikunja #129), in
|
||||
// Russian, empty when nothing distinguished the task. Blank is the honest
|
||||
// rendering: he never said this one mattered more.
|
||||
Why string
|
||||
}
|
||||
|
||||
// rowOf renders one wire task into the shared read-only columns. The two call
|
||||
// sites below add what only they need: the live rows carry the edit form's raw
|
||||
// values and the ranker's reason, the resolved rows carry neither.
|
||||
func rowOf(t ipc.Task) taskRow {
|
||||
return taskRow{
|
||||
ID: t.ID, Text: t.Text, Source: t.Source, Evidence: t.Evidence,
|
||||
Status: t.Status, Created: fmtTaskTime(&t.CreatedTs),
|
||||
Due: fmtTaskDate(t.Due), Resolved: fmtTaskTime(t.Resolved),
|
||||
ResolvedBy: t.ResolvedBy,
|
||||
}
|
||||
}
|
||||
|
||||
// handleTasks serves the task review surface (GET) and the five writes it
|
||||
// offers (POST): add, edit, confirm, done, drop.
|
||||
//
|
||||
// Not step-up gated, unlike /tools and /routines, and the difference is the
|
||||
// point: enabling a tool defines argv Maven will execute, and accepting a
|
||||
// routine hands the tick loop a new standing reason to interrupt him. A task is
|
||||
// neither — nothing in the tick loop reads the tasks table, so the worst a
|
||||
// weaker caller can do here is write a line onto a list he reads himself. It
|
||||
// still sits behind whatever transport auth fronts mavweb, like every other
|
||||
// page.
|
||||
//
|
||||
// "edit" was re-argued on the same terms rather than inheriting the exemption
|
||||
// (Vikunja #509), and it stays ungated. It rewrites a line on a list he reads
|
||||
// himself, the same blast radius "drop" already has on this page, and the store
|
||||
// refuses the two edits that would cost something: a resolved task keeps the
|
||||
// text it was finished under, and a text collision with another live row is
|
||||
// named instead of merged.
|
||||
//
|
||||
// "confirm" is the only interesting move: it promotes a candidate Maven derived
|
||||
// from something she read into work he owns. That review step is why derived
|
||||
// tasks are captured as candidates in the first place.
|
||||
func handleTasks(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
|
||||
if !requireCore(w, core, "tasks") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
var msg, errMsg string
|
||||
if r.Method == http.MethodPost {
|
||||
var err error
|
||||
msg, err = applyTaskPost(ctx, core, r)
|
||||
if err != nil {
|
||||
log.Printf("tasks: %v", err)
|
||||
errMsg = err.Error()
|
||||
}
|
||||
}
|
||||
|
||||
all, err := core.ListTasks(ctx, "")
|
||||
if err != nil {
|
||||
log.Printf("tasks: list: %v", err)
|
||||
http.Error(w, "tasks error: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
// Live rows are ordered by the same ranker the spoken list uses, so the page
|
||||
// and the voice reply can never disagree about what comes first. Resolved
|
||||
// rows keep store order (newest first) — ranking finished work is pointless.
|
||||
var live []tasks.Item
|
||||
var resolved []taskRow
|
||||
resolvedTotal := 0
|
||||
for _, t := range all {
|
||||
switch t.Status {
|
||||
case "candidate", "open":
|
||||
live = append(live, tasks.Item{
|
||||
ID: t.ID, Text: t.Text, Status: t.Status,
|
||||
Created: t.CreatedTs, Due: t.Due, Weight: t.Weight,
|
||||
})
|
||||
default:
|
||||
resolvedTotal++
|
||||
// Finished work is history, and the history only grows. The page
|
||||
// showed every row that ever existed, which is a page that gets
|
||||
// slower every month for a section nobody reads past the top of.
|
||||
if len(resolved) >= resolvedShown {
|
||||
continue
|
||||
}
|
||||
resolved = append(resolved, rowOf(t))
|
||||
}
|
||||
}
|
||||
byID := make(map[int64]ipc.Task, len(all))
|
||||
for _, t := range all {
|
||||
byID[t.ID] = t
|
||||
}
|
||||
var cands, open []taskRow
|
||||
for _, r := range tasks.Rank(live, now()) {
|
||||
t := byID[r.ID]
|
||||
row := rowOf(t)
|
||||
row.DueValue = fmtTaskDateValue(t.Due)
|
||||
row.Weight = t.Weight
|
||||
row.Why = r.Reason
|
||||
if t.Status == "candidate" {
|
||||
// A candidate's due date is Maven's reading of a mail, so its
|
||||
// ranking reason is not shown as if he had set a priority.
|
||||
row.Why = ""
|
||||
cands = append(cands, row)
|
||||
} else {
|
||||
open = append(open, row)
|
||||
}
|
||||
}
|
||||
renderPage(w, tasksTmpl, struct {
|
||||
Msg, Err string
|
||||
Stalls []tasks.Stall
|
||||
Candidates []taskRow
|
||||
Open []taskRow
|
||||
Resolved []taskRow
|
||||
ResolvedMore bool
|
||||
}{msg, errMsg, tasks.Stalls(live, now()), cands, open, resolved, resolvedTotal > len(resolved)})
|
||||
}
|
||||
|
||||
// applyTaskPost performs one write and returns the message to show. A bad
|
||||
// request returns an error, which the page renders inline rather than as a
|
||||
// bare 400 — this is a form surface, not an API.
|
||||
func applyTaskPost(ctx context.Context, core ipc.CoreAPI, r *http.Request) (string, error) {
|
||||
action := r.FormValue("action")
|
||||
if action == "add" {
|
||||
text := strings.TrimSpace(r.FormValue("text"))
|
||||
if text == "" {
|
||||
return "", errors.New("empty task text")
|
||||
}
|
||||
req := ipc.CaptureTaskReq{Text: text, Source: "tap:web", Status: "open", Ts: now()}
|
||||
wgt, err := formWeight(r)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
req.Weight = wgt
|
||||
due, err := formDue(r, now())
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
req.Due = due
|
||||
resp, err := core.CaptureTask(ctx, req)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if resp.Promoted {
|
||||
return "confirmed a candidate maven had found", nil
|
||||
}
|
||||
if !resp.Created {
|
||||
return "already on the list", nil
|
||||
}
|
||||
return "added task", nil
|
||||
}
|
||||
|
||||
id, err := strconv.ParseInt(r.FormValue("id"), 10, 64)
|
||||
if err != nil {
|
||||
return "", errors.New("invalid id")
|
||||
}
|
||||
|
||||
if action == "promote" {
|
||||
msg, err := promoteCandidate(ctx, core, r, id)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return msg, nil
|
||||
}
|
||||
|
||||
if action == "edit" {
|
||||
// The three fields capture set, and only those (Vikunja #509). Status
|
||||
// is not editable here: that ladder is one-way and has its own buttons.
|
||||
text := strings.TrimSpace(r.FormValue("text"))
|
||||
if text == "" {
|
||||
return "", errors.New("empty task text")
|
||||
}
|
||||
wgt, err := formWeight(r)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
due, err := formDue(r, now())
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
switch err := core.EditTask(ctx, id, text, due, wgt); {
|
||||
case err == nil:
|
||||
return "saved task", nil
|
||||
case errors.Is(err, ipc.ErrTaskDuplicate):
|
||||
// Naming the collision instead of merging: two live rows carry two
|
||||
// provenances, and picking one is not the page's call.
|
||||
return "", errors.New("another open task already says this — drop one of the two")
|
||||
case errors.Is(err, ipc.ErrTaskResolved):
|
||||
return "", errors.New("a resolved task keeps the text it was finished under")
|
||||
default:
|
||||
return "", err
|
||||
}
|
||||
}
|
||||
|
||||
var status, msg string
|
||||
switch action {
|
||||
case "confirm":
|
||||
status, msg = "open", "confirmed task"
|
||||
case "done":
|
||||
status, msg = "done", "task done"
|
||||
case "drop":
|
||||
status, msg = "dropped", "dropped task"
|
||||
default:
|
||||
return "", fmt.Errorf("unknown action %q", action)
|
||||
}
|
||||
if err := core.SetTaskStatus(ctx, id, status, now(), "tap:web"); err != nil {
|
||||
return "", statusWriteErr(err)
|
||||
}
|
||||
return msg, nil
|
||||
}
|
||||
|
||||
// errNoDoneWhen — the refusal has to name what is missing, or the button looks
|
||||
// broken. The field it asks for arrives with the intake form (Vikunja #511).
|
||||
var errNoDoneWhen = errors.New("write a definition of done before confirming this candidate")
|
||||
|
||||
// statusWriteErr translates a SetTaskStatus failure into what the page says.
|
||||
func statusWriteErr(err error) error {
|
||||
if errors.Is(err, ipc.ErrTaskNoDoneWhen) {
|
||||
return errNoDoneWhen
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
// promoteCandidate turns a candidate into open work with the three things the
|
||||
// board needs (Vikunja #511): a definition of done, an optional blocker, and an
|
||||
// optional date.
|
||||
//
|
||||
// The definition of done is required, and the refusal is the store's — this
|
||||
// only reaches it in a readable order. The blocker is a NAME here and an entity
|
||||
// id in the row: identity lives in Nexus, so the name is resolved first and a
|
||||
// name Nexus cannot resolve stops the promotion instead of being stored.
|
||||
//
|
||||
// A date set here writes a reminder, which is the one unprompted delivery the
|
||||
// persona allows: he asked to be told, on a day he named.
|
||||
func promoteCandidate(ctx context.Context, core ipc.CoreAPI, r *http.Request, id int64) (string, error) {
|
||||
doneWhen := strings.TrimSpace(r.FormValue("done_when"))
|
||||
if doneWhen == "" {
|
||||
return "", errors.New("write a definition of done — what has to be true for this to be finished")
|
||||
}
|
||||
text := strings.TrimSpace(r.FormValue("text"))
|
||||
if text == "" {
|
||||
return "", errors.New("empty task text")
|
||||
}
|
||||
due, err := formDue(r, now())
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
||||
blockedOn, err := resolveBlocker(ctx, core, r.FormValue("blocked_on"))
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
||||
if err := core.SetTaskFields(ctx, id, doneWhen, blockedOn); err != nil {
|
||||
return "", err
|
||||
}
|
||||
wgt, err := formWeight(r)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
// The importance select is posted whether or not a date is. This ran under
|
||||
// `if due != nil`, so confirming a candidate as "срочно" with no deadline
|
||||
// dropped the word on the floor — the row came back normal and nothing said
|
||||
// why. A promote with neither field set still writes nothing.
|
||||
if due != nil || wgt != 0 {
|
||||
if err := core.EditTask(ctx, id, text, due, wgt); err != nil {
|
||||
return "", err
|
||||
}
|
||||
}
|
||||
if err := core.SetTaskStatus(ctx, id, "open", now(), "tap:web"); err != nil {
|
||||
return "", statusWriteErr(err)
|
||||
}
|
||||
if due == nil {
|
||||
return "confirmed", nil
|
||||
}
|
||||
// A date-only field has no hour. Nine in the morning, because the reminder
|
||||
// is about a day's work and being told at midnight is being told the night
|
||||
// before.
|
||||
fire := time.Date(due.Year(), due.Month(), due.Day(), 9, 0, 0, 0, due.Location())
|
||||
if _, err := core.CreateReminder(ctx, fire, text, ""); err != nil {
|
||||
// The task IS promoted; only the reminder failed. Saying "confirmed"
|
||||
// and nothing else would leave him expecting a nudge that will not come.
|
||||
return "", fmt.Errorf("confirmed, but the reminder did not save: %w", err)
|
||||
}
|
||||
return "confirmed, and maven will remind you that morning", nil
|
||||
}
|
||||
|
||||
// resolveBlocker turns the blocked-on NAME the form posts into the entity id
|
||||
// the row stores. Identity lives in Nexus, so an unresolvable name stops the
|
||||
// promotion instead of being written as free text. An empty field is no
|
||||
// blocker and reaches Nexus not at all.
|
||||
func resolveBlocker(ctx context.Context, core ipc.CoreAPI, field string) (string, error) {
|
||||
name := strings.TrimSpace(field)
|
||||
if name == "" {
|
||||
return "", nil
|
||||
}
|
||||
ref, err := core.ResolveEntity(ctx, name, []string{"person"})
|
||||
switch {
|
||||
case errors.Is(err, ipc.ErrNotImplemented):
|
||||
return "", errors.New("no identity service here, so blocked-on cannot be stored — leave it empty")
|
||||
case errors.Is(err, ipc.ErrNoEntity):
|
||||
return "", fmt.Errorf("nexus does not know %q", name)
|
||||
case err != nil:
|
||||
return "", fmt.Errorf("resolving %q: %w", name, err)
|
||||
case ref.Ambiguous:
|
||||
// Asking, not picking: a task blocked on the wrong person is a
|
||||
// mistake nobody can see afterwards.
|
||||
return "", fmt.Errorf("%q matches %s — say which", name, strings.Join(ref.Candidates, ", "))
|
||||
}
|
||||
return ref.ID, nil
|
||||
}
|
||||
|
||||
// formWeight reads the importance select. Out-of-range clamps rather than
|
||||
// rejects — a bad select is not worth a 400 — but trailing garbage is refused,
|
||||
// because strconv is not Sscanf and "3junk" is not a 3.
|
||||
func formWeight(r *http.Request) (int, error) {
|
||||
v := r.FormValue("weight")
|
||||
if v == "" {
|
||||
return 0, nil
|
||||
}
|
||||
wgt, err := strconv.Atoi(v)
|
||||
if err != nil || wgt < 0 {
|
||||
return 0, fmt.Errorf("bad weight %q", v)
|
||||
}
|
||||
if wgt > tasks.MaxWeight {
|
||||
wgt = tasks.MaxWeight
|
||||
}
|
||||
return wgt, nil
|
||||
}
|
||||
|
||||
// formDue reads the date input. An empty field is nil, which on an edit means
|
||||
// "clear the date" — the form has no other way to say it.
|
||||
func formDue(r *http.Request, now time.Time) (*time.Time, error) {
|
||||
d := r.FormValue("due")
|
||||
if d == "" {
|
||||
return nil, nil
|
||||
}
|
||||
due, err := time.ParseInLocation("2006-01-02", d, now.Location())
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("bad due date %q", d)
|
||||
}
|
||||
return &due, nil
|
||||
}
|
||||
|
||||
// fmtTaskDateValue renders a due date the way <input type=date> requires, or
|
||||
// "" for no date. Separate from fmtTaskDate, which renders it for reading.
|
||||
func fmtTaskDateValue(t *time.Time) string {
|
||||
if t == nil || t.IsZero() {
|
||||
return ""
|
||||
}
|
||||
return t.Local().Format("2006-01-02")
|
||||
}
|
||||
|
||||
func fmtTaskTime(t *time.Time) string {
|
||||
if t == nil || t.IsZero() {
|
||||
return "—"
|
||||
}
|
||||
return t.Local().Format("02 Jan 15:04")
|
||||
}
|
||||
|
||||
func fmtTaskDate(t *time.Time) string {
|
||||
if t == nil || t.IsZero() {
|
||||
return "—"
|
||||
}
|
||||
return t.Local().Format("02 Jan")
|
||||
}
|
||||
@@ -32,6 +32,31 @@ type fakeTaskCore struct {
|
||||
statusErr error
|
||||
|
||||
promoted bool
|
||||
|
||||
// The promote path's two extra writes.
|
||||
fields []any
|
||||
edits []editCall
|
||||
editErr error
|
||||
fieldErr error
|
||||
}
|
||||
|
||||
// editCall records one EditTask, so a test can say what the form actually sent
|
||||
// down rather than only that the promotion succeeded.
|
||||
type editCall struct {
|
||||
ID int64
|
||||
Text string
|
||||
Due *time.Time
|
||||
Weight int
|
||||
}
|
||||
|
||||
func (f *fakeTaskCore) EditTask(_ context.Context, id int64, text string, due *time.Time, weight int) error {
|
||||
f.edits = append(f.edits, editCall{id, text, due, weight})
|
||||
return f.editErr
|
||||
}
|
||||
|
||||
func (f *fakeTaskCore) SetTaskFields(_ context.Context, id int64, doneWhen, blockedOn string) error {
|
||||
f.fields = append(f.fields, []any{id, doneWhen, blockedOn})
|
||||
return f.fieldErr
|
||||
}
|
||||
|
||||
func (f *fakeTaskCore) ListTasks(_ context.Context, status string) ([]ipc.Task, error) {
|
||||
@@ -220,6 +245,49 @@ func TestApplyTaskPostCarriesWeight(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// Confirming a candidate posts the importance select whether or not a date is
|
||||
// set. The weight write hung off `if due != nil`, so "срочно" with no deadline
|
||||
// was read off the form and thrown away, and the row came back normal.
|
||||
func TestPromoteCandidateCarriesWeightWithoutADueDate(t *testing.T) {
|
||||
core := &fakeTaskCore{}
|
||||
form := url.Values{
|
||||
"action": {"promote"}, "id": {"4"}, "text": {"продлить страховку"},
|
||||
"done_when": {"полис на руках"}, "weight": {"3"},
|
||||
}
|
||||
req := httptest.NewRequest(http.MethodPost, "/tasks", strings.NewReader(form.Encode()))
|
||||
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
handleTasks(httptest.NewRecorder(), req, core)
|
||||
|
||||
if len(core.edits) != 1 {
|
||||
t.Fatalf("edits = %+v, want the weight written once", core.edits)
|
||||
}
|
||||
if core.edits[0].Weight != 3 || core.edits[0].ID != 4 {
|
||||
t.Errorf("edit = %+v, want id 4 at weight 3", core.edits[0])
|
||||
}
|
||||
if core.edits[0].Due != nil {
|
||||
t.Errorf("edit invented a due date: %v", core.edits[0].Due)
|
||||
}
|
||||
if core.statusVal != "open" {
|
||||
t.Errorf("status = %q, want the candidate promoted", core.statusVal)
|
||||
}
|
||||
}
|
||||
|
||||
// A promote with neither field set still writes nothing: the row is unchanged
|
||||
// apart from its status, and an EditTask here would be a no-op that can fail.
|
||||
func TestPromoteCandidateWithNoDateAndNoWeightDoesNotEdit(t *testing.T) {
|
||||
core := &fakeTaskCore{}
|
||||
form := url.Values{
|
||||
"action": {"promote"}, "id": {"4"}, "text": {"продлить страховку"},
|
||||
"done_when": {"полис на руках"}, "weight": {"0"},
|
||||
}
|
||||
req := httptest.NewRequest(http.MethodPost, "/tasks", strings.NewReader(form.Encode()))
|
||||
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
handleTasks(httptest.NewRecorder(), req, core)
|
||||
if len(core.edits) != 0 {
|
||||
t.Errorf("edits = %+v, want none", core.edits)
|
||||
}
|
||||
}
|
||||
|
||||
// Out of range clamps rather than 400s; a non-number is a real client error.
|
||||
func TestApplyTaskPostClampsWeight(t *testing.T) {
|
||||
core := &fakeTaskCore{created: true}
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"cmp"
|
||||
_ "embed"
|
||||
"html/template"
|
||||
"log"
|
||||
"net/http"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
"github.com/kami/maven/internal/webauthn"
|
||||
)
|
||||
|
||||
//go:embed tools.html
|
||||
var toolsHTML string
|
||||
|
||||
// toolsTmpl — the enable surface. Server-rendered, no JS: a plain HTML form
|
||||
// POSTs back to /tools to enable a proposal. html/template escapes tool names +
|
||||
// utterances (they came from voice STT — untrusted text).
|
||||
var toolsTmpl = parsePage("tools", toolsHTML, template.FuncMap{
|
||||
"join": strings.Join,
|
||||
"capability": func(t ipc.Tool) string { return tool.CapabilityOf(t).String() },
|
||||
"risk": func(t ipc.Tool) string { return string(tool.RiskOf(t)) },
|
||||
})
|
||||
|
||||
// handleTools serves the enable surface (GET) and applies an enable (POST).
|
||||
// POST fields: name, cmd (space-separated argv), destructive (checkbox). cmd is
|
||||
// whitespace-split — argv with embedded spaces isn't supported (ponytail: no
|
||||
// shell-word parsing; the box owner controls this input, quote a wrapper script
|
||||
// if an arg needs spaces).
|
||||
func handleTools(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, session *webauthn.PasskeySession, requireStepUp bool) {
|
||||
if !requireCore(w, core, "tools") {
|
||||
return
|
||||
}
|
||||
ctx := r.Context()
|
||||
var msg string
|
||||
if r.Method == http.MethodPost {
|
||||
if !stepUpGate(w, session, requireStepUp) {
|
||||
return
|
||||
}
|
||||
action := r.FormValue("action")
|
||||
name := strings.TrimSpace(r.FormValue("name"))
|
||||
switch action {
|
||||
case "enable":
|
||||
scope := r.FormValue("scope")
|
||||
cmd := strings.Fields(r.FormValue("cmd"))
|
||||
destructive := r.FormValue("destructive") != ""
|
||||
if name == "" || len(cmd) == 0 {
|
||||
http.Error(w, "name and cmd required", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
if err := core.EnableTool(ctx, name, cmd, destructive, scope, time.Now()); err != nil {
|
||||
log.Printf("tools: enable %q: %v", name, err)
|
||||
http.Error(w, "enable failed: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
msg = "enabled " + name
|
||||
case "disable":
|
||||
if name == "" {
|
||||
http.Error(w, "name required", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
if err := core.DisableTool(ctx, name); err != nil {
|
||||
log.Printf("tools: disable %q: %v", name, err)
|
||||
http.Error(w, "disable failed: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
msg = "disabled " + name
|
||||
case "dismiss":
|
||||
if name == "" {
|
||||
http.Error(w, "name required", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
if err := core.DeleteTool(ctx, name); err != nil {
|
||||
log.Printf("tools: dismiss %q: %v", name, err)
|
||||
http.Error(w, "dismiss failed: "+err.Error(), http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
msg = "dismissed " + name
|
||||
default:
|
||||
http.Error(w, "unknown action", http.StatusBadRequest)
|
||||
return
|
||||
}
|
||||
}
|
||||
proposed, err1 := core.ListTools(ctx, "proposed")
|
||||
enabled, err2 := core.ListTools(ctx, "enabled")
|
||||
if err := cmp.Or(err1, err2); err != nil {
|
||||
log.Printf("tools: %v", err)
|
||||
http.Error(w, "core read failed", http.StatusBadGateway)
|
||||
return
|
||||
}
|
||||
// MCP is off by default and an older core may not know the method at all,
|
||||
// so a failure here renders an empty section rather than breaking the page.
|
||||
servers, err := core.MCPServers(ctx)
|
||||
if err != nil {
|
||||
log.Printf("tools: mcp servers: %v", err)
|
||||
servers = nil
|
||||
}
|
||||
// Enabled rows are shown grouped by capability domain (Vikunja #452). A
|
||||
// flat list stops answering "what can she do to the house" somewhere
|
||||
// around fifteen rows, and that is the question this page exists for.
|
||||
renderPage(w, toolsTmpl, struct {
|
||||
Msg string
|
||||
Proposed []ipc.Tool
|
||||
Enabled []ipc.Tool
|
||||
Groups []tool.CapabilityGroup
|
||||
MCP []ipc.MCPServerStatus
|
||||
}{msg, proposed, enabled, tool.GroupByDomain(enabled), servers})
|
||||
}
|
||||
+22
-2
@@ -1,9 +1,9 @@
|
||||
{{template "shellTop" "trace"}}
|
||||
<h1>Rule Trace</h1>
|
||||
<div class="hint mb-4">{{.Now | ago}} — winner: <strong>{{if .Winner}}{{.Winner}}{{else}}nothing fired{{end}}</strong></div>
|
||||
<div class="hint mb-4">{{.Tick.Now | ago}} — winner: <strong>{{if .Tick.Winner}}{{.Tick.Winner}}{{else}}nothing fired{{end}}</strong></div>
|
||||
<div class=scroll><table class=mono>
|
||||
<tr><th>rule<th>sev<th>predicate<th>gate<th>blocked by<th>detail<th>selected<th>lost to</tr>
|
||||
{{range .Rules}}<tr>
|
||||
{{range .Tick.Rules}}<tr>
|
||||
<td>{{.RuleName}}</td>
|
||||
<td>{{.Severity}}</td>
|
||||
<td class={{if .PredicateResult}}green{{else}}gray{{end}}>{{.PredicateResult}}</td>
|
||||
@@ -21,5 +21,25 @@
|
||||
<td>{{.LostTo}}</td>
|
||||
</tr>{{end}}
|
||||
</table></div>
|
||||
|
||||
<h1 class=mt-4>Turn Decisions</h1>
|
||||
<div class="hint mb-4">Who claimed each utterance, who lost it, and who was never asked. In memory, newest first, cleared on restart.</div>
|
||||
{{if not .Turns}}<div class=hint>no turn has run since the daemon started</div>{{end}}
|
||||
{{range .Turns}}
|
||||
<details class=mb-4>
|
||||
<summary><span class=mono>{{.Utterance}}</span> — <strong>{{if .Winner}}{{.Winner}}{{else}}nobody{{end}}</strong> <span class=hint>{{.Ts | ago}}</span></summary>
|
||||
<div class=scroll><table class=mono>
|
||||
<tr><th>stage<th>claimant<th>would have been<th>score<th>outcome<th>why</tr>
|
||||
{{range .Claims}}<tr>
|
||||
<td>{{.Stage}}</td>
|
||||
<td>{{.Claimant}}</td>
|
||||
<td>{{if .Intent}}{{.Intent}}{{else}}—{{end}}</td>
|
||||
<td>{{if .HasScore}}{{printf "%.3f" .Score}}{{else}}—{{end}}</td>
|
||||
<td class={{if eq .Outcome "won"}}green{{else if eq .Outcome "never_asked"}}red{{else}}gray{{end}}>{{.Outcome}}</td>
|
||||
<td>{{.Reason}}</td>
|
||||
</tr>{{end}}
|
||||
</table></div>
|
||||
</details>
|
||||
{{end}}
|
||||
{{template "shellBottom"}}
|
||||
</html>
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user