Compare commits
324 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 2b3e34c7e8 | |||
| fa67dd82fe | |||
| 52fd218c70 | |||
| 33032b859a | |||
| 0d8cbaec01 | |||
| 1f38e71d1a | |||
| 2de5a339fb | |||
| 1ee9a930d3 | |||
| f48c2280bd | |||
| 888c1c6768 | |||
| 7cacbc8b21 | |||
| dc3cda666e | |||
| 1b354e9b39 | |||
| c07722266a | |||
| be758d9a59 | |||
| 8bbdcd2727 | |||
| f8947bef5a | |||
| b752ec037e | |||
| 4dbeca5a2e | |||
| 9e15ff36aa | |||
| 7955a41105 | |||
| a93a16d7b3 | |||
| dd63180e44 | |||
| 9d80a39a30 | |||
| b5b599e287 | |||
| bb51c28a19 | |||
| 549d4c8380 | |||
| 4766167c3a | |||
| f6f9e75eac | |||
| 1524991adc | |||
| 9da468810e | |||
| 7b4fb6229a | |||
| cdd81e2ad5 | |||
| 32d5f68710 | |||
| fdc18edd87 | |||
| a98d25ecac | |||
| 113508eaac | |||
| 6dc2622596 | |||
| dd91c6961c | |||
| 0560684b35 | |||
| c4cf06d610 | |||
| acd985323e | |||
| 598f4fc011 | |||
| 69db1cf849 | |||
| f5480e281b | |||
| cc72f69769 | |||
| b954e0cea6 | |||
| c82dbd1e65 | |||
| 69ecea19d5 | |||
| 8a13d189bb | |||
| 8e7aa0d451 | |||
| 00595c2211 | |||
| b54ccccd0a | |||
| 4cfef41541 | |||
| 0793955896 | |||
| 71a9a59403 | |||
| d3c63e6493 | |||
| c586346a60 | |||
| 23d89b2831 | |||
| 06ddf41228 | |||
| 2e64c8ce94 | |||
| 7695620a96 | |||
| 758fb6a3f0 | |||
| 0e75245205 | |||
| 8d816f47e9 | |||
| 4425ba112b | |||
| a4d5155029 | |||
| c62c7034fa | |||
| 58b546a27e | |||
| 997f92f5c4 | |||
| d9ef9ecef2 | |||
| be3e5cea25 | |||
| 1da3aa39e8 | |||
| bee3ef80b4 | |||
| fc9538d07f | |||
| bb8bd608da | |||
| db0752223f | |||
| 97fc786acf | |||
| 54f13466c9 | |||
| 3bbffa4f37 | |||
| 8b76dc50d3 | |||
| a1324e679f | |||
| 82ef1b0110 | |||
| 897dcf847a | |||
| 8b9e8e9f4e | |||
| b338d9bb40 | |||
| 6878e12d37 | |||
| 8d46ee39e0 | |||
| 6eba79b332 | |||
| 3f60ec3994 | |||
| 14ea06712e | |||
| 42d3feadd2 | |||
| 2a2f706b74 | |||
| e082e06868 | |||
| 88dc4e1383 | |||
| 60759a991e | |||
| 9537346441 | |||
| c6be818f13 | |||
| b5575a9402 | |||
| fcda5e3d2c | |||
| b1420acb94 | |||
| 70fb7c030b | |||
| fe489dff6d | |||
| d8da529be0 | |||
| 0258a40b0d | |||
| f6a8752d00 | |||
| 5b7480ddaf | |||
| 8aa790cc48 | |||
| 0ade0ec734 | |||
| d960e211d3 | |||
| 6fba4d6931 | |||
| 12c18dcf65 | |||
| a286865fe5 | |||
| 28c0ff73bd | |||
| bdafc82e35 | |||
| c69023c310 | |||
| 761cf9f3e0 | |||
| 6a9d8a4dd5 | |||
| 4c95b200e4 | |||
| 6ae1312ff1 | |||
| 765ed36340 | |||
| feca776077 | |||
| d79b30a1a6 | |||
| c5e993fc55 | |||
| a2081d8227 | |||
| 82bd160c0d | |||
| 1fe03f7a51 | |||
| d773f1f72b | |||
| 80ac7579fb | |||
| bb6cb6d185 | |||
| a9067a5754 | |||
| 787cc56522 | |||
| 86dcd99de2 | |||
| 554181ccbd | |||
| 58635f1a69 | |||
| fd3d063e02 | |||
| ed491e23fc | |||
| 246db4e609 | |||
| b6abb19090 | |||
| 1f7fd476ec | |||
| 08512ad58b | |||
| ff71d981ef | |||
| 4d83f8c785 | |||
| a439117995 | |||
| 2689715c2d | |||
| 05f47aef4b | |||
| 45a5e37963 | |||
| 6d8a95095a | |||
| 7e21cd06b3 | |||
| 09c648b934 | |||
| 4f516657da | |||
| 8a21478f36 | |||
| 958d2a2fc8 | |||
| 7db139b83e | |||
| 0987dabfc4 | |||
| 947506c7b8 | |||
| 6c67e61962 | |||
| 0990f32808 | |||
| d41878c2b1 | |||
| e023638135 | |||
| 0d52344d27 | |||
| 5bd303788b | |||
| afac8fb670 | |||
| 77206f298e | |||
| a1f811d4c8 | |||
| 7ab38cd7f7 | |||
| 6a85e71077 | |||
| bf6c2bf1a6 | |||
| 1558233665 | |||
| 5afa2dfb38 | |||
| 0f361d2034 | |||
| 19242ef73b | |||
| 26d6d71588 | |||
| df58710141 | |||
| 442d3ec08e | |||
| e481ad4930 | |||
| 3d8224fb04 | |||
| 990a4a99e9 | |||
| 5b622389c5 | |||
| a820a95ebb | |||
| ea9c746852 | |||
| d60a51c9e7 | |||
| 9aabb01e2a | |||
| 2815adee03 | |||
| 9f51596e2f | |||
| 87d176153a | |||
| 7d4b4ad736 | |||
| 569991bb15 | |||
| c915115096 | |||
| 908d92a7e8 | |||
| 43f2c37538 | |||
| 6d3f5b5b01 | |||
| eda1112f3b | |||
| 1c8a32c3fd | |||
| 96b474223d | |||
| 42d7a39c49 | |||
| bad3fa4035 | |||
| d819fc09f0 | |||
| c35979d9f9 | |||
| f3c0540b42 | |||
| 5b4192acb5 | |||
| 16d94894b7 | |||
| ae8d38fc31 | |||
| b2521988e1 | |||
| dae123adac | |||
| 1c9ddbbea2 | |||
| 3f2782f5b7 | |||
| 865623ef3e | |||
| 4fdce3ca2c | |||
| c47881106e | |||
| 9a70f7378b | |||
| b18f608594 | |||
| d1f8a734c5 | |||
| 71041029e2 | |||
| 35018226ef | |||
| 8833a9c76b | |||
| 6c07409452 | |||
| 1c2541f7d6 | |||
| 9e25f18a3e | |||
| 197897516e | |||
| 767748720a | |||
| 58051b5af1 | |||
| f9b2391a8b | |||
| f229795cea | |||
| 6e5364a0ed | |||
| 86817d6d06 | |||
| 0fc2e3a18a | |||
| 453919db20 | |||
| ad60e10e95 | |||
| 1528697287 | |||
| dbdab2d570 | |||
| b9371dcac6 | |||
| 62c2e92ec0 | |||
| aec94eb2e8 | |||
| 4dfe106fe3 | |||
| 2e0e2fd0bb | |||
| f3fa6b353a | |||
| 6645f64c3e | |||
| f10e0068dd | |||
| 9b124d9194 | |||
| 12530c8a95 | |||
| 51256c4c9a | |||
| 76481c2736 | |||
| bcc2305cd0 | |||
| 0ceeac8df4 | |||
| 4fae13af75 | |||
| 774217199e | |||
| 2db59d52a7 | |||
| 92d5fd580c | |||
| edeef19ff0 | |||
| 018f7a6f47 | |||
| eca41798bd | |||
| cc423567e7 | |||
| 8088ef9e00 | |||
| 666b924d29 | |||
| e52c616592 | |||
| 2b97bac51e | |||
| ab42db2b87 | |||
| 94d553570d | |||
| 2e97b905b4 | |||
| fbcca449be | |||
| 2076e4a788 | |||
| 30eb6add1b | |||
| dc266056d1 | |||
| 1c786b7156 | |||
| a3af10a830 | |||
| c0de473382 | |||
| 3e534340bf | |||
| 1a704d704d | |||
| e57adcb001 | |||
| bec7362b7b | |||
| a3ec746a01 | |||
| af0eec250e | |||
| 20aa2d59c9 | |||
| 4bad90dedb | |||
| 2b8d0f74fa | |||
| af9d2133dc | |||
| a1fdfccd61 | |||
| 5c05163266 | |||
| 92d2629001 | |||
| bdcfccce77 | |||
| f4deccacc9 | |||
| 8aaac01de6 | |||
| feb6f2c03d | |||
| 99bb3526db | |||
| bb8cb8d014 | |||
| 5e66aa8f22 | |||
| e332f167b2 | |||
| 322401b9af | |||
| 4f34a232d4 | |||
| 93987f2dfc | |||
| c0d61a71a4 | |||
| 0b89294af7 | |||
| 7079a240f7 | |||
| 587f1e6a07 | |||
| 99193ff1d1 | |||
| 63a389a1f8 | |||
| 2150a18e98 | |||
| 612ca8cf1b | |||
| 14e98334ad | |||
| a103708a08 | |||
| a654b0126f | |||
| b8227295b8 | |||
| b35151418a | |||
| 17964d1162 | |||
| 079cf689aa | |||
| 9397f9e5f6 | |||
| 3f98a99f44 | |||
| 53616836db | |||
| cf40f13573 | |||
| 7d08d27efb | |||
| d0d0021659 | |||
| 79c3b994cf | |||
| ba1d8e3f44 | |||
| 29329b5f0e | |||
| 47dda97226 | |||
| 8fdb9e5cd1 | |||
| f1a809121b | |||
| 79893d646b | |||
| c04c5eca9c | |||
| bfdbe0045e | |||
| d09954d85d | |||
| 7e402b279d | |||
| 6915e6a714 |
@@ -0,0 +1,160 @@
|
||||
# Maven project dictionary for the direct-prose skill.
|
||||
#
|
||||
# These terms override every word preference in the skill's word-choice tables.
|
||||
# Each entry exists because the name drifted in real docs or real answers, not
|
||||
# because the word looked improvable.
|
||||
#
|
||||
# Format and the rule for adding a term: ~/.claude/skills/direct-prose/references/modes.md
|
||||
|
||||
terms:
|
||||
resident_model:
|
||||
name: resident model
|
||||
meaning: the one always-warm Qwen3-1.7B llama-server that both routes and phrases
|
||||
avoid:
|
||||
- the model
|
||||
- the LLM
|
||||
- the 1.7B
|
||||
- the phraser model
|
||||
examples:
|
||||
good: The resident model emits GBNF-constrained JSON.
|
||||
bad: The 1.7B emits GBNF-constrained JSON.
|
||||
|
||||
router:
|
||||
name: router
|
||||
meaning: the stage that turns an utterance into a Decision with one of 7 intents
|
||||
avoid:
|
||||
- orchestrator
|
||||
- intent classifier
|
||||
- dispatcher
|
||||
|
||||
classifier:
|
||||
name: classifier
|
||||
meaning: the embedder nearest-neighbour path that runs when the router is off or errors
|
||||
avoid:
|
||||
- the fallback
|
||||
- the floor
|
||||
- the old router
|
||||
examples:
|
||||
good: A router error falls through to the classifier.
|
||||
bad: A router error falls through to the floor.
|
||||
|
||||
cascade:
|
||||
name: cascade
|
||||
meaning: the ordered path stage 0, then router, then classifier
|
||||
avoid:
|
||||
- the pipeline
|
||||
- the chain
|
||||
- the fallback chain
|
||||
|
||||
stage_0:
|
||||
name: stage 0
|
||||
meaning: the deterministic rules that answer before the resident model is called
|
||||
avoid:
|
||||
- the fast path
|
||||
- bypass
|
||||
- deterministic assist
|
||||
- preemption
|
||||
examples:
|
||||
good: Stage 0 routes agenda questions to IntentQuery.
|
||||
bad: The bypass routes agenda questions to IntentQuery.
|
||||
|
||||
query_source:
|
||||
name: query source
|
||||
meaning: one entry in querySources, which either claims a turn or passes
|
||||
avoid:
|
||||
- arm
|
||||
- handler
|
||||
- branch
|
||||
- answerer
|
||||
examples:
|
||||
good: Kiwix is the last query source before the model answers from memory.
|
||||
bad: Kiwix is the last arm before the model answers from memory.
|
||||
|
||||
personal_boundary:
|
||||
name: personal boundary
|
||||
meaning: the query source that stops a question about him from reaching the world
|
||||
avoid:
|
||||
- the boundary
|
||||
- the privacy gate
|
||||
- the personal filter
|
||||
|
||||
clarify:
|
||||
name: clarify
|
||||
meaning: the turn outcome where Maven asks instead of acting
|
||||
avoid:
|
||||
- refusal
|
||||
- rejection
|
||||
- punt
|
||||
examples:
|
||||
good: The gate produced two false clarifies.
|
||||
bad: The gate produced two false refusals.
|
||||
|
||||
fact:
|
||||
name: fact
|
||||
meaning: a keyed, supersedable row in the fact store
|
||||
avoid:
|
||||
- memory entry
|
||||
- datum
|
||||
- record
|
||||
|
||||
note:
|
||||
name: note
|
||||
meaning: free text he captured, indexed for recall
|
||||
avoid:
|
||||
- memo
|
||||
- entry
|
||||
|
||||
memory:
|
||||
name: memory
|
||||
meaning: the embedded index over notes and facts that backs recall
|
||||
avoid:
|
||||
- RAG store
|
||||
- vector db
|
||||
- long-term memory
|
||||
|
||||
nudge:
|
||||
name: nudge
|
||||
meaning: one proactive message the digestion worker proposes and the dispatcher sends
|
||||
avoid:
|
||||
- suggestion
|
||||
- proposal
|
||||
- proactive prompt
|
||||
- reminder
|
||||
examples:
|
||||
good: A fact can close the nudge that asked for it.
|
||||
bad: A fact can close the suggestion that asked for it.
|
||||
|
||||
digestion_worker:
|
||||
name: digestion worker
|
||||
meaning: the background engine that consolidates memory and proposes nudges
|
||||
avoid:
|
||||
- digestion tick
|
||||
- background engine
|
||||
- reflection loop
|
||||
|
||||
reach:
|
||||
name: reach
|
||||
meaning: an outbound channel Maven speaks through, such as telegram, ntfy or voice
|
||||
avoid:
|
||||
- sink
|
||||
- delivery channel
|
||||
- notification backend
|
||||
|
||||
ecosystem:
|
||||
name: ecosystem
|
||||
meaning: Nexus, Praxis and Hexis together
|
||||
avoid:
|
||||
- the services
|
||||
- the integrations
|
||||
- upstream
|
||||
|
||||
act:
|
||||
name: act
|
||||
meaning: the intent that runs a capability through Hexis
|
||||
avoid:
|
||||
- action
|
||||
- command
|
||||
- execution
|
||||
examples:
|
||||
good: An act with no allowlisted fn is gated to a clarify.
|
||||
bad: An action with no allowlisted fn is gated to a clarify.
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"hooks": {
|
||||
"SessionStart": [
|
||||
{
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "f=.claude/prose-dictionary.yaml; [ -f \"$f\" ] && jq -Rs '{hookSpecificOutput:{hookEventName:\"SessionStart\",additionalContext:(\"Project prose dictionary. These terms override every word preference in the direct-prose output style. Use the name, never the avoid list.\\n\\n\"+.)}}' \"$f\" 2>/dev/null || true",
|
||||
"statusMessage": "Loading prose dictionary"
|
||||
},
|
||||
{
|
||||
"type": "command",
|
||||
"command": "f=HANDOFF.md; [ -f \"$f\" ] && jq -Rs '{hookSpecificOutput:{hookEventName:\"SessionStart\",additionalContext:(\"An unconsumed HANDOFF.md is present. Run the pickup skill before anything else: read it, read the Vikunja task it names, restate the assumption set in at most five bullets, and wait for the user to confirm before writing code. It is a claim from the previous session, not truth. Delete it once consumed.\\n\\n\"+.)}}' \"$f\" 2>/dev/null || true",
|
||||
"statusMessage": "Loading handoff"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,78 @@
|
||||
---
|
||||
name: pickup
|
||||
description: Start a work session on a Maven task. Runs task start, reads the brief and the disposable handoff, restates the assumption set, and waits for correction before touching code. Use at the start of any session that continues earlier work, when the user says "pickup", "continue", "resume", or names a Vikunja task id.
|
||||
---
|
||||
|
||||
# Pickup
|
||||
|
||||
The point of this skill is the pause in step 5. Every wasted session in this repo
|
||||
started with an agent that inferred the goal instead of stating it back.
|
||||
|
||||
## 0. Get on the branch
|
||||
|
||||
```sh
|
||||
task start <vikunja-id>
|
||||
```
|
||||
|
||||
`~/.local/bin/task` owns the branch, the identity and the PR. It cuts
|
||||
`task/<id>-<slug>` off `origin/master` and sets the commit author to the `claude`
|
||||
gitea user. It writes `TASK.md` from the Vikunja task, and pulls any waiting
|
||||
review comments into `.task/review-comments.md`. Do not hand-roll any of that.
|
||||
|
||||
`TASK.md` is the brief and it is immutable. If it says a PR already exists, this
|
||||
is a review-fix session and not new work. Read the comments first.
|
||||
|
||||
## 1. Read the handoff
|
||||
|
||||
`HANDOFF.md` at the repo root, if it exists. It is gitignored, it belongs to one
|
||||
session, and it holds only what is needed to resume. Treat it as a claim from the
|
||||
previous agent, not as truth. It can be stale or wrong.
|
||||
|
||||
If there is no handoff, that is normal. It means the last session closed clean.
|
||||
|
||||
## 2. Read the durable state
|
||||
|
||||
In this order, and stop as soon as you have enough:
|
||||
|
||||
- The Vikunja task, by id. Project Maven is ID 2, MCP at `http://localhost:9100/mcp`.
|
||||
The task description and its comments hold the goal, the constraints, and the
|
||||
assumption ledger. This outranks the handoff on every conflict.
|
||||
- `CLAUDE.md`, the section that covers the area you are about to touch.
|
||||
- The one file under `docs/` that owns the area. Check its `Last verified` line.
|
||||
If the sha is behind the code you are reading, say so in step 4 and trust the code.
|
||||
|
||||
Do not read the dated files under `docs/evals/`. They are measurements from one day,
|
||||
never updated. Read one only when you need the number it recorded.
|
||||
|
||||
If no task id is known, ask for one before doing anything else. Work without a task
|
||||
is work nobody can resume.
|
||||
|
||||
## 3. Look at the ground
|
||||
|
||||
`git status`, `git log --oneline -5`, and the diff on the current branch. What the
|
||||
repo says beats what any document says.
|
||||
|
||||
## 4. Restate, then stop
|
||||
|
||||
Write at most five bullets and stop. Do not write code, do not open files to "check
|
||||
one thing first", do not start with a small safe change.
|
||||
|
||||
```
|
||||
Task: V-359, one line.
|
||||
Done: what is already on the branch.
|
||||
Next: the one thing this session does.
|
||||
Constraints: what would make this wrong.
|
||||
Assuming: the beliefs that, if false, waste the session.
|
||||
```
|
||||
|
||||
Then ask: is this right? Wait for the answer.
|
||||
|
||||
A corrected assumption goes into the Vikunja task as a comment, not into the handoff.
|
||||
The handoff dies tonight. The task does not.
|
||||
|
||||
## 5. Then begin
|
||||
|
||||
- Delete `HANDOFF.md`. It has been consumed and must not outlive this step.
|
||||
- On master, cut the branch: `scripts/task-branch.sh <id> <slug>`.
|
||||
- One task per session. When context passes roughly half, run `/wrap` rather than
|
||||
pushing on. A compacted session is a session that forgot why it made a choice.
|
||||
@@ -0,0 +1,94 @@
|
||||
---
|
||||
name: wrap
|
||||
description: Close a Maven work session cleanly. Runs the tests, updates the durable docs, commits in reviewable slices with the Vikunja ref, pushes so the PR opens, records state in Vikunja, and leaves a disposable handoff only if work remains. Use when the user says "wrap", "wrap up", "done for now", or when context passes roughly half.
|
||||
---
|
||||
|
||||
# Wrap
|
||||
|
||||
Run every step. A partial wrap is worse than none, because the next session trusts
|
||||
the parts that did run.
|
||||
|
||||
## 1. Prove it works
|
||||
|
||||
`make test`. If something fails, fix it or say plainly in the handoff and in Vikunja
|
||||
that it fails, with the output. Never wrap on an untested claim.
|
||||
|
||||
## 2. Update the durable docs
|
||||
|
||||
Ask what a future agent would have to learn the hard way, and write that down.
|
||||
|
||||
- `CLAUDE.md` when a fact an agent needs before touching code has changed: routing
|
||||
behaviour, a measured number, a flag default, a constraint. A commit that changed
|
||||
routing or phrasing without touching the matching CLAUDE.md section is a bug.
|
||||
Correct stale text in place. Do not append a new paragraph next to the wrong one.
|
||||
- `AGENTS.md` when the recipe to build, run or preview changed.
|
||||
- The one file under `docs/` that owns the area, plus its `Last verified: <date> @ <sha>`
|
||||
line. Only a doc directly under `docs/` carries that line.
|
||||
- A new dated file under `docs/evals/` when you measured something. Never edit an
|
||||
existing dated file. A newer measurement is a new file, and the living doc points
|
||||
at it.
|
||||
|
||||
Nothing that must survive tonight goes anywhere else. Not into the handoff, not into
|
||||
a commit message, not into a comment in the code.
|
||||
|
||||
## 3. Commit in slices
|
||||
|
||||
Under 300 changed lines per commit in non-markdown files, enforced by `.githooks/pre-commit`.
|
||||
Markdown is exempt and may land as one batch.
|
||||
|
||||
Each commit is one idea, subject in the repo's voice, lowercase area prefix, and it
|
||||
ends with the Vikunja ref:
|
||||
|
||||
```
|
||||
router: narrow the single-token rule (V-359)
|
||||
```
|
||||
|
||||
If a change genuinely cannot split under 300 lines, say why in the commit body before
|
||||
reaching for `--no-verify`.
|
||||
|
||||
## 4. Land it
|
||||
|
||||
```sh
|
||||
task pr
|
||||
```
|
||||
|
||||
It refuses a dirty tree, pushes, opens or refreshes the PR against the repo default
|
||||
branch, labels the Vikunja task in-review, comments the PR url on it, and pushes an
|
||||
ntfy. Do not push by hand and do not call `tea` yourself.
|
||||
|
||||
## 5. Record what `task pr` cannot know
|
||||
|
||||
Comment on the Vikunja task: what you measured, what is still open. List every
|
||||
assumption that turned out to be wrong. If the session found new work, create a task
|
||||
for it now rather than describing it in prose.
|
||||
|
||||
This step is what makes the handoff disposable.
|
||||
|
||||
## 6. Leave the handoff, or leave none
|
||||
|
||||
If the task is finished, delete `HANDOFF.md` and stop. An empty root is the correct
|
||||
end state.
|
||||
|
||||
If work remains, write `HANDOFF.md` with nothing but what the next agent needs to
|
||||
resume, and no history:
|
||||
|
||||
```markdown
|
||||
# Handoff — <date>
|
||||
|
||||
Task: V-359 <one line>
|
||||
Branch: task/359-<slug>, cut from master
|
||||
|
||||
## Where I stopped
|
||||
<two sentences, mid-thought detail that is nowhere else>
|
||||
|
||||
## Next action
|
||||
<the single concrete next step>
|
||||
|
||||
## Do not
|
||||
<the trap I nearly fell into, or the approach already ruled out>
|
||||
```
|
||||
|
||||
Nothing else goes in it. No summary of what landed, that is in git and Vikunja. No
|
||||
design rationale, that is in `docs/`. No fact an agent needs on any task, that is in
|
||||
`CLAUDE.md`. If a line in the handoff would still matter next week, it is in the wrong
|
||||
file.
|
||||
Executable
+30
@@ -0,0 +1,30 @@
|
||||
#!/bin/sh
|
||||
# Every commit names the Vikunja task it belongs to.
|
||||
#
|
||||
# router: narrow the single-token rule (V-359)
|
||||
#
|
||||
# V- and not #, because Gitea autolinks #359 to a Gitea issue, which is a
|
||||
# different tracker and a wrong link.
|
||||
#
|
||||
# Exempt: merges, reverts, fixup/squash, and the initial commit.
|
||||
|
||||
msg_file=$1
|
||||
subject=$(sed -n '1p' "$msg_file")
|
||||
|
||||
case "$subject" in
|
||||
Merge\ *|Revert\ *|fixup!\ *|squash!\ *|amend!\ *) exit 0 ;;
|
||||
esac
|
||||
|
||||
if [ -f "$(git rev-parse --git-dir)/MERGE_HEAD" ]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if printf '%s' "$subject" | grep -qE '\(V-[0-9]+\)$'; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "commit-msg: subject must end with a Vikunja task ref." >&2
|
||||
echo " got: $subject" >&2
|
||||
echo " want: router: narrow the single-token rule (V-359)" >&2
|
||||
echo " No task yet? Create one. Work without a task is work nobody can resume." >&2
|
||||
exit 1
|
||||
Executable
+30
@@ -0,0 +1,30 @@
|
||||
#!/bin/sh
|
||||
# Two guards, both bypassable with --no-verify when you mean it.
|
||||
# 1. master is not a working branch.
|
||||
# 2. a code commit stays under 300 changed lines.
|
||||
# Markdown is exempt from the size cap on purpose: docs land as one batch.
|
||||
|
||||
branch=$(git symbolic-ref --short HEAD 2>/dev/null)
|
||||
|
||||
case "$branch" in
|
||||
master|main)
|
||||
echo "pre-commit: refusing to commit on $branch." >&2
|
||||
echo " task start <vikunja-id> # branch off origin/master, write TASK.md" >&2
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
# Added + deleted lines across staged files that are not markdown.
|
||||
# numstat prints "-\t-\t<path>" for binaries; those count 0 and that is fine,
|
||||
# a binary blob is not the kind of diff this cap exists to stop.
|
||||
loc=$(git diff --cached --numstat -- . ':(exclude)*.md' |
|
||||
awk '$1 ~ /^[0-9]+$/ { a += $1 } $2 ~ /^[0-9]+$/ { d += $2 } END { print a + d + 0 }')
|
||||
|
||||
if [ "$loc" -gt 300 ]; then
|
||||
echo "pre-commit: $loc changed lines in non-markdown files, cap is 300." >&2
|
||||
echo " Split it. Each commit should be one reviewable idea." >&2
|
||||
echo " git reset <path> to unstage, or --no-verify if this genuinely cannot split." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
exit 0
|
||||
+18
-2
@@ -9,6 +9,7 @@
|
||||
/mavwaked
|
||||
/mavmaild
|
||||
/mavupdate
|
||||
/mavgpud
|
||||
|
||||
# Certs (private keys, don't commit)
|
||||
certs/
|
||||
@@ -40,6 +41,9 @@ deploy/telegram.env
|
||||
deploy/zenmoney.token
|
||||
# IMAP password, read by mavmaild (never in argv, never committed)
|
||||
deploy/imap.password
|
||||
# Compose interpolation secrets — MAVEN_AMBIENT_TOKEN today. docker compose
|
||||
# reads this file itself; it is not an env_file on any service.
|
||||
/.env
|
||||
|
||||
# Temp files
|
||||
/tmp/
|
||||
@@ -50,7 +54,19 @@ opencode.json
|
||||
# Test coverage output
|
||||
coverage.out
|
||||
|
||||
# Agent worktrees and local agent state
|
||||
.claude/
|
||||
# Agent worktrees and local agent state. The workflow itself is tracked: the
|
||||
# hooks, the skills and the prose dictionary are how a session behaves, so they
|
||||
# get reviewed like code. Everything else under .claude/ is scratch.
|
||||
/.claude/*
|
||||
!/.claude/settings.json
|
||||
!/.claude/prose-dictionary.yaml
|
||||
!/.claude/skills/
|
||||
|
||||
# The disposable handoff. One session, then deleted. Never committed:
|
||||
# anything worth keeping belongs in Vikunja, CLAUDE.md or docs/.
|
||||
/HANDOFF.md
|
||||
/models/stt
|
||||
/models/tts
|
||||
|
||||
# root .env — MAVEN_AMBIENT_TOKEN and friends, same class as deploy/telegram.env
|
||||
.env
|
||||
|
||||
@@ -1,396 +0,0 @@
|
||||
beyond the model and tts work, the useful additions are mostly around **reliability, context, and reach**, not more intelligence.
|
||||
|
||||
## highest-value additions
|
||||
|
||||
### 1. unified event intake
|
||||
|
||||
maven should receive normalized events from:
|
||||
|
||||
* praxis
|
||||
* calendar
|
||||
* telegram
|
||||
* local notifications
|
||||
* system/service health
|
||||
* manual checklists
|
||||
* eventually email bridges
|
||||
|
||||
one internal envelope:
|
||||
|
||||
```go
|
||||
type Event struct {
|
||||
Source string
|
||||
Kind string
|
||||
EntityIDs []string
|
||||
Title string
|
||||
Body string
|
||||
Priority string
|
||||
OccurredAt time.Time
|
||||
Payload json.RawMessage
|
||||
}
|
||||
```
|
||||
|
||||
this gives digestion one stable input instead of source-specific logic.
|
||||
|
||||
---
|
||||
|
||||
### 2. explicit morning routine engine — **core engine done (2026-07-20)**
|
||||
|
||||
`internal/morning` — pure checklist engine, mirrors `internal/loop`/
|
||||
`internal/routine`'s no-I/O contract. `Evaluate(routine, facts, now)` answers
|
||||
"what's still missing" any time (order-independent — checks facts, not
|
||||
sequence); `Due(routines, facts, last, now)` fires the once-per-day nag only
|
||||
at `NudgeAt` (defaults to window end) and only when something's unevidenced,
|
||||
with a `last`-map dedupe identical in shape to `routine.Due`'s cold-start/
|
||||
last-fire tracking. Evidence is just a fact timestamped inside today's
|
||||
window — manual (voice-tapped) and inferred (another daemon writing the same
|
||||
key) are indistinguishable, satisfying the manual/inferred requirement for
|
||||
free. Weekday/weekend variants are two `Routine`s with different `Weekdays`
|
||||
sets under different names. Wired into `config.MorningRoutineConfig` +
|
||||
`cmd/mavend/tick.go`'s `fireMorningRoutines` (reads only the fact keys the
|
||||
configured items reference, dispatches through the normal severity/presence
|
||||
routing table, body is literal joined item labels — not LLM-phrased, same
|
||||
no-hallucination rationale as cron routines). 13 unit tests in
|
||||
`internal/morning/morning_test.go`.
|
||||
|
||||
Added since (2026-07-20, same day): a read-only `/morning` page in mavweb —
|
||||
`ipc.CoreAPI.MorningStatus` (new wire method, mirrors `TickTrace`'s
|
||||
daemon-cache-only shape: the store adapter errors, `daemonAPI` serves it from
|
||||
a `tickLoop.morningStatus` closure) returns each routine's active/window/
|
||||
per-item done state, server-rendered same as `/trace` (no live-update loop —
|
||||
checklist state moves on minutes, not seconds).
|
||||
|
||||
Not yet done: no config wired in `deploy/mavend.json` (no morning routines
|
||||
configured on homesrv yet — add items there when the medicine/water/pets
|
||||
fact keys the phone/desktop write are settled), no voice query path for
|
||||
"what did I miss this morning" (Evaluate supports it; nothing calls it yet),
|
||||
no way to create/edit routines from the web UI — construction still means
|
||||
hand-editing config, deliberately deferred: routines are operator-declared
|
||||
config (like cron routines), and a CRUD editor would mean moving them to a
|
||||
DB table + hot-reload, a bigger change than this pass.
|
||||
|
||||
not ordinary reminders.
|
||||
|
||||
support:
|
||||
|
||||
* required morning items
|
||||
* order-independent completion
|
||||
* soft time windows
|
||||
* skipped-step detection
|
||||
* one nudge, not repeated spam
|
||||
* manual and inferred completion evidence
|
||||
* weekend/weekday variants
|
||||
|
||||
example:
|
||||
|
||||
```text
|
||||
08:00–11:00
|
||||
- medicine
|
||||
- water
|
||||
- pets
|
||||
- check praxis attention
|
||||
```
|
||||
|
||||
maven should know what is still missing, not merely fire four timers.
|
||||
|
||||
---
|
||||
|
||||
### 3. cross-device presence
|
||||
|
||||
**status (2026-07-20):** the hysteresis engine and 3 of the listed signals are
|
||||
already built and wired live: `internal/store/presence.go` (noisy-OR combiner
|
||||
+ Schmitt-trigger bucket resolve), fed by `desk_active` (workstation, via
|
||||
`scripts/desk-active.sh` posting to `/api/signal`), `page_heartbeat` (mavweb
|
||||
tab, `app.js`), and `wg_handshake` (`mavpoll` polling `wg show`) — threaded
|
||||
into the tick loop via `internal/loop/gather.go`. Not done: phone-reachable,
|
||||
homesrv-available, audio-output, and active-maven-client signals from the
|
||||
list below are still missing.
|
||||
|
||||
a small presence daemon on each trusted device:
|
||||
|
||||
* workstation active/idle
|
||||
* phone reachable
|
||||
* homesrv available
|
||||
* last keyboard/mouse activity
|
||||
* wireguard presence
|
||||
* current audio output
|
||||
* active maven client
|
||||
|
||||
mavend receives only compact state, not raw activity logs.
|
||||
|
||||
useful for:
|
||||
|
||||
* choosing delivery channel
|
||||
* suppressing voice while away
|
||||
* surfacing reminders when you return
|
||||
* knowing whether an agent result should be spoken or sent as text
|
||||
|
||||
---
|
||||
|
||||
### 4. interruption policy — **done (2026-07-20), turned out to already be built**
|
||||
|
||||
audited the existing code before writing anything new: `internal/loop.Gate`
|
||||
already answers deliver_now vs. drop (quiet-hours/cooldown/snooze/presence/
|
||||
calendar-busy), and `cmd/mavend/tick.go`'s `digestQ` + `config.DigestConfig`
|
||||
already implement queue/digest (low-severity nudges batch into one
|
||||
notification, flushed on window elapsed or max-items reached). The four
|
||||
outcomes below were already covered by these two mechanisms; nothing new to
|
||||
build for the core policy.
|
||||
|
||||
Gap that *was* real: `deploy/mavend.json` had no `digest` block, so batching
|
||||
was disabled in prod despite being fully implemented. Fixed — see the config
|
||||
change alongside this note.
|
||||
|
||||
before delivering anything, evaluate:
|
||||
|
||||
```text
|
||||
urgency
|
||||
current activity
|
||||
quiet hours
|
||||
recent nudges
|
||||
available channels
|
||||
whether already surfaced
|
||||
```
|
||||
|
||||
result:
|
||||
|
||||
```text
|
||||
deliver_now
|
||||
queue
|
||||
digest
|
||||
drop
|
||||
```
|
||||
|
||||
this prevents maven from becoming annoying once praxis and other sources start producing more data.
|
||||
|
||||
---
|
||||
|
||||
### 5. entity-aware memory — **done (2026-07-20)**
|
||||
|
||||
`03fa52d`/`9876187` (Vikunja #279): facts gain `Subject`/`EntityID`/
|
||||
`ResolutionState`; an async enrichment worker resolves free-text subjects to
|
||||
canonical Nexus entity_ids (mirrors Praxis's enrichment pattern). Ambiguous
|
||||
or unreachable Nexus never guesses — the fact stays `pending` or terminal
|
||||
`ambiguous`. Voice-tapped facts (`IntentFact`) now flow into the enrichment
|
||||
queue automatically via an optional `Subject` field on `WriteFactReq` (old
|
||||
callers unaffected).
|
||||
|
||||
Landed alongside this in the same session (not originally on this list, but
|
||||
closes the plumbing gaps the last brief flagged for Nexus/Praxis maturity):
|
||||
a typed Praxis lifecycle client (`398997f` — surface/acknowledge/resolve/
|
||||
ignore/pin; fixes the surfaced≠acknowledged gap where reading an item aloud
|
||||
left no trace), correlation-ID/version headers on the Nexus/Praxis clients
|
||||
(`b743860`), entity-scoped Praxis attention queries (`0579ef9`), a durable
|
||||
delivery outbox with begin-before-send/complete-after semantics
|
||||
(`29f23e3`+`9ff726e` — closes a duplicate-send-on-crash bug), fail-closed
|
||||
handling on ambiguous IPC mutation outcomes and Nexus/Hexis dependency
|
||||
errors (`838fde1`+`d9fa4d6`), and a reusable fake-ecosystem test harness
|
||||
with fault injection (`c932cd8`).
|
||||
|
||||
connect maven memory to nexus ids.
|
||||
|
||||
instead of:
|
||||
|
||||
```text
|
||||
key = "кошачий фонтан"
|
||||
```
|
||||
|
||||
store:
|
||||
|
||||
```text
|
||||
entity_id = ent_pet_water_fountain
|
||||
predicate = refilled_at
|
||||
value = 2026-07-19T...
|
||||
```
|
||||
|
||||
benefits:
|
||||
|
||||
* stable russian/english aliases
|
||||
* fewer duplicate facts
|
||||
* better “when did i last…” queries
|
||||
* easier routine detection
|
||||
* cleaner praxis correlation
|
||||
|
||||
---
|
||||
|
||||
### 6. bounded follow-up state
|
||||
|
||||
for short continuations:
|
||||
|
||||
* “yes”
|
||||
* “tomorrow”
|
||||
* “the second one”
|
||||
* “not that project”
|
||||
* “do it later”
|
||||
|
||||
store explicit pending state instead of relying on chat history:
|
||||
|
||||
```go
|
||||
type PendingInteraction struct {
|
||||
Kind string
|
||||
Candidates []string
|
||||
Args json.RawMessage
|
||||
ExpiresAt time.Time
|
||||
}
|
||||
```
|
||||
|
||||
this matters a lot for a 1.7b model.
|
||||
|
||||
---
|
||||
|
||||
### 7. evaluation lab — **skipped for now (2026-07-20)**
|
||||
|
||||
runs on a different machine (GPU box), and CPT is currently in progress
|
||||
there — deprioritized until the training pipeline has a checkpoint to gate.
|
||||
Not abandoned, just off the immediate list.
|
||||
|
||||
before every new checkpoint or lora deploy:
|
||||
|
||||
* routing accuracy
|
||||
* slot accuracy
|
||||
* malformed json rate
|
||||
* russian/english mixed input
|
||||
* ambiguous entity handling
|
||||
* reminder vs note vs fact
|
||||
* direct answer vs tool call
|
||||
* confirmation safety
|
||||
* phrasing quality
|
||||
* latency and ram
|
||||
|
||||
also replay real anonymized traces against old and new checkpoints.
|
||||
|
||||
this should be a hard deployment gate.
|
||||
|
||||
---
|
||||
|
||||
### 8. replayable full-system simulator
|
||||
|
||||
fake:
|
||||
|
||||
* clock
|
||||
* presence
|
||||
* caldav
|
||||
* telegram
|
||||
* praxis
|
||||
* nexus
|
||||
* hexis
|
||||
* stt
|
||||
* tts
|
||||
* llama-server
|
||||
|
||||
scenario:
|
||||
|
||||
```text
|
||||
08:30 user appears
|
||||
08:35 medicine not completed
|
||||
08:40 correx agent waits
|
||||
08:45 calendar sync stale
|
||||
08:50 user says “what did i miss?”
|
||||
```
|
||||
|
||||
assert:
|
||||
|
||||
* what tools were called
|
||||
* what was surfaced
|
||||
* what stayed unresolved
|
||||
* what maven said
|
||||
* what was not executed
|
||||
|
||||
this will save more time than another feature daemon.
|
||||
|
||||
---
|
||||
|
||||
## useful second-wave additions
|
||||
|
||||
### voice session quality
|
||||
|
||||
* barge-in
|
||||
* interrupt tts on wake word
|
||||
* partial stt display
|
||||
* confidence-aware clarification
|
||||
* retry only failed stt segment
|
||||
* per-room microphone profiles
|
||||
* noise-floor calibration
|
||||
* short response mode when speaking
|
||||
|
||||
### notification bridge framework
|
||||
|
||||
small adapters for:
|
||||
|
||||
* ntfy
|
||||
* telegram
|
||||
* matrix
|
||||
* web push
|
||||
* android notification forwarding
|
||||
* local dbus notifications
|
||||
|
||||
normalize into maven/praxis events instead of treating each as a separate feature.
|
||||
|
||||
### local knowledge ingestion
|
||||
|
||||
* markdown/docs ingestion
|
||||
* git repo summaries
|
||||
* project decision records
|
||||
* conversation exports
|
||||
* provenance and source links
|
||||
* incremental reindexing
|
||||
|
||||
keep this read-only and separate from personal fact memory.
|
||||
|
||||
### service self-diagnostics
|
||||
|
||||
`maven doctor`:
|
||||
|
||||
* socket reachability
|
||||
* model health
|
||||
* stt/tts readiness
|
||||
* embedder availability
|
||||
* caldav freshness
|
||||
* telegram poll state
|
||||
* praxis/nexus/hexis reachability
|
||||
* db integrity
|
||||
* disk usage
|
||||
* recent failures
|
||||
|
||||
### config and secret management
|
||||
|
||||
* schema-validated config
|
||||
* config migration
|
||||
* secret references instead of inline values
|
||||
* dry-run validation
|
||||
* redacted config dump
|
||||
* per-daemon health config
|
||||
* startup dependency report
|
||||
|
||||
---
|
||||
|
||||
## things i would not build yet
|
||||
|
||||
* autonomous multi-step planning
|
||||
* large external reasoner
|
||||
* generic workflow engine
|
||||
* self-editing memory
|
||||
* automatic hexis actions from praxis
|
||||
* emotion simulation beyond phrasing
|
||||
* full home-assistant replacement
|
||||
* more model layers before routing is stable
|
||||
|
||||
## recommended order
|
||||
|
||||
**status as of 2026-07-20:**
|
||||
|
||||
1. ~~evaluation lab~~ — **skipped, GPU-box work, deprioritized while CPT is in progress**
|
||||
2. ~~entity-aware memory~~ — **done** (`03fa52d`/`9876187`, plus adjacent
|
||||
Nexus/Praxis plumbing hardening — see item 5 above)
|
||||
3. ~~morning routine engine~~ — **core engine done** (`internal/morning` +
|
||||
`cmd/mavend` wiring — see item 2 above; not yet configured on homesrv,
|
||||
no voice query, no web UI)
|
||||
4. interruption/delivery policy
|
||||
5. presence agents
|
||||
6. unified event intake
|
||||
7. full-system simulator
|
||||
8. notification bridges
|
||||
9. knowledge ingestion
|
||||
10. voice-session polish
|
||||
|
||||
the main goal should be: **maven reliably knows what is happening, knows what you meant, and chooses the least annoying correct response**. everything else can wait.
|
||||
|
||||
@@ -5,6 +5,46 @@ This repo maps to **Maven** (project ID: 2) in Vikunja.
|
||||
Feature work, bugs, deployment tasks all go here.
|
||||
MCP endpoint: `http://localhost:9100/mcp` (or `http://192.168.1.104:9100/mcp` from workpc)
|
||||
|
||||
## The sibling services (Nexus, Praxis, Hexis)
|
||||
|
||||
Maven is the conversational front end of a four-service ecosystem. The other three
|
||||
live in sibling repos next to this one.
|
||||
|
||||
| Service | Repo | Port | Answers |
|
||||
|---|---|---|---|
|
||||
| Nexus | `../nexus` | 9740 | who or what is this name |
|
||||
| Praxis | `../praxis` | 8989 | what needs attention |
|
||||
| Hexis | `../hexis` | 9741 | what can be run, and running it |
|
||||
|
||||
Division of labour: Nexus identifies, Praxis observes, Hexis acts, Maven understands
|
||||
and coordinates. Maven is not the source of truth for any of the three. The full
|
||||
contract is `docs/ecosystem.md`, and the constraints that bite during
|
||||
implementation are summarised in `CLAUDE.md`.
|
||||
|
||||
Where things are in this repo:
|
||||
|
||||
- `cmd/mavend/ecosystem.go` holds `nexusClient` and `praxisClient`. The Hexis client
|
||||
is vendored from `github.com/kami/hexis/pkg/client`.
|
||||
- `cmd/mavend/ecosystem_acts.go` routes an act through capability discovery.
|
||||
- `cmd/mavend/factenrichment.go` resolves each stored fact's `Subject` against Nexus
|
||||
on a background poll loop, with backoff and no give-up.
|
||||
- `internal/store/entityfacts.go` holds the entity-tagged fact rows.
|
||||
- Config blocks are `nexus`, `praxis` and `hexis` in `deploy/mavend.json`. Each is
|
||||
optional. Absent means that integration is dark, not broken.
|
||||
|
||||
Bring the whole ecosystem up locally:
|
||||
|
||||
```sh
|
||||
docker compose -f deploy/ecosystem/docker-compose.yml up -d
|
||||
```
|
||||
|
||||
That builds all three from the sibling working trees, so commit or stash there first.
|
||||
Each publishes on loopback at the port above. Maven reaches them by service name on
|
||||
the shared compose network.
|
||||
|
||||
Testing without them running: `cmd/mavend/fakeecosystem_test.go` provides stubs, and
|
||||
`cmd/mavend/ecosystem_degraded_test.go` covers each service being unreachable.
|
||||
|
||||
## Rendering / previewing the web UI locally
|
||||
|
||||
To see mavweb pages with real data without touching the production stack:
|
||||
|
||||
@@ -10,7 +10,7 @@ compose passes `/dev/dri` + the render gid) — the resident model stays ≤1.7B
|
||||
**Resident model:** currently **Qwen3-1.7B** (`UD-Q4_K_XL`), stock — not yet the CPT'd one.
|
||||
It replaced Qwen3.5-0.8B on 2026-07-31 because it measured better on both fixtures we have:
|
||||
67.5% vs 59.7% intent-only on the 77-case RU routing fixture, and 20/27 vs 11-17/27 on the
|
||||
talk fixture. See `MODEL-BAKEOFF-31-07-2026.md`. It is a Thinking variant, so `n_ctx` is 4096
|
||||
talk fixture. See `docs/evals/2026-07-31-model-bakeoff.md`. It is a Thinking variant, so `n_ctx` is 4096
|
||||
— reasoning tokens need the room, and 4096 is what the scores above were measured at.
|
||||
|
||||
The **target** is still the locally CPT'd **Qwen3-1.7B** (Vikunja #122, training in flight).
|
||||
@@ -25,9 +25,28 @@ Spanish. Their strong published IFEval/BFCL numbers are English-only. Model file
|
||||
`models/llm/`, so the LFM2.5 gguf sitting there is not loaded by anything. Swapping the resident
|
||||
model is a one-line change to `phraser.model_path` in `deploy/mavend.json`.
|
||||
|
||||
See `REARCH.md` for the target architecture, `DESIGN.md` for the folded design spec, and
|
||||
See `docs/rearchitecture.md` for the target architecture, `docs/design.md` for the folded design spec, and
|
||||
`AGENTS.md` for local-preview + model-download recipes.
|
||||
|
||||
**Model work is moving to the workstation** (owner's call, 2026-08-02). homesrv cannot grow a
|
||||
GPU and the workstation has 16GB of VRAM. So the resident model, STT and TTS become preferred
|
||||
remotes with a floor on homesrv. The workstation is never assumed up. Fall back silently when
|
||||
it would only do the job better. Name the gap when the 1.7B cannot do it at all. The embedder
|
||||
stays on homesrv permanently, because it backs that floor. It is multilingual-e5-small,
|
||||
quantized and asymmetric — `EmbedQuery` and `EmbedPassage` apply the `query:`/`passage:`
|
||||
prefixes it was trained with, and calling plain `Embed` on a note is a bug. It replaced
|
||||
MiniLM and bought ten points of recall@1 and 2.5× the speed; see
|
||||
`docs/evals/2026-08-04-recall-e5-small.md`. Read `docs/offload.md` before
|
||||
touching a daemon seam or adding a model caller. Vikunja #483 is the umbrella, #484 to #487
|
||||
are the work.
|
||||
|
||||
Both halves are wired as of 2026-08-03. Routing and replies prefer the workstation silently
|
||||
through `modelSeam`; nudge and reminder phrasing prefer it silently inside the phraser. A
|
||||
world question goes through `LLMPhraser.PhraseWorld` and names the gap when the card is not
|
||||
free — `worldGap` in `cmd/mavend/worldmodel.go`, which he hears instead of an invented
|
||||
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.
|
||||
|
||||
## Build & test
|
||||
|
||||
CGO daemons (`mavend`, `mavsttd`, `mavttsd`, `mavenclient`) need the vendored toolchain
|
||||
@@ -58,8 +77,8 @@ Pure-Go packages (`router`, `memory`, `mavweb`, …) run under a plain `go test
|
||||
| `mavweb` | HTTP UI + PWA (`/dash`, `/history`, `/trace`, `/notifications`, `/tools`); WebAuthn auth. Connects to mavend's socket. |
|
||||
| `mavsttd` | Speech-to-text (whisper.cpp, CGO). |
|
||||
| `mavttsd` | Text-to-speech (piper subprocess). |
|
||||
| `mavwaked` | Wake-word / VAD gate. |
|
||||
| `mavenclient` | Voice loop client (mic → stt → core → tts). |
|
||||
| `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. |
|
||||
| `mavcaldav` | CalDAV calendar sync. |
|
||||
| `mavmaild` | Mail reader (IMAP, read-only). Holds the IMAP password; core never sees it. |
|
||||
@@ -68,13 +87,61 @@ Daemons are wired socket-to-socket, not linked. `internal/ipc` is the client/ser
|
||||
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`).
|
||||
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 he 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.
|
||||
|
||||
## The ecosystem: Nexus, Praxis, Hexis
|
||||
|
||||
Maven is one of four services. It owns conversation and personal memory. It does not
|
||||
own identity, operational state, or execution. Full contract in
|
||||
`docs/ecosystem.md`.
|
||||
|
||||
```text
|
||||
Nexus identifies. Praxis observes. Hexis acts. Maven understands and coordinates.
|
||||
```
|
||||
|
||||
| Service | Owns | Maven's client | Configured at |
|
||||
|---|---|---|---|
|
||||
| **Nexus** | Canonical entity ids, names, aliases, relationships. Projects, services, devices, people, pets, places. | `nexusClient` in `cmd/mavend/ecosystem.go`, `POST /api/v1/resolve` | `nexus.url` (`http://nexus:9740`) |
|
||||
| **Praxis** | Operational attention and item lifecycle. What needs looking at, what changed, what is still unresolved. | `praxisClient`, the HTTP tools API under `/api/v1/tools/` | `praxis.url` (`http://praxis:8989`) |
|
||||
| **Hexis** | The capability registry and the only path to executing anything. | vendored `github.com/kami/hexis/pkg/client` | `hexis.url` (`http://hexis:9741`) |
|
||||
|
||||
All three are `nil` unless configured, and every one of them degrades on its own.
|
||||
An outage means a named gap in the answer, never a broken turn and never a guess.
|
||||
|
||||
Rules that are not negotiable:
|
||||
|
||||
- **No component reads another component's database.** Praxis attention comes over
|
||||
HTTP, never from its SQLite file.
|
||||
- **Identity lives in Nexus.** Do not invent a local fact key for something Nexus
|
||||
resolves. `actionFact` already sets `Subject`, and `cmd/mavend/factenrichment.go`
|
||||
resolves it in the background against Nexus.
|
||||
- **Free text never reaches a mutating Hexis call.** Resolve to a canonical entity id
|
||||
first. Ambiguous resolution asks the owner, it does not pick.
|
||||
- **LLM output is not authorization.** Confirmation binds capability id, target
|
||||
entity, arguments, requester and expiry. See `cmd/mavend/confirm.go`.
|
||||
- **Praxis lifecycle words mean different things.** Surfaced is not acknowledged,
|
||||
acknowledged is not resolved, execution success is not recovery. Reading an item
|
||||
aloud calls `Surface`, never `Acknowledge`.
|
||||
- **No automatic attention-to-action path.** Digestion may summarise Praxis. It may
|
||||
not call Hexis.
|
||||
|
||||
Every cross-service call carries a correlation id minted once per action
|
||||
(`withCorrelationID`), a contract version header, and `X-Requested-By: maven`.
|
||||
|
||||
## Routing — read this before touching the router
|
||||
|
||||
`internal/router/` has TWO layered engines. **The LLM router is now the default and it is
|
||||
on in deploy** — this section used to say it was wired `nil`, which stopped being true on
|
||||
2026-07-31.
|
||||
|
||||
- **LLM router (the intended design, REARCH.md):** the resident Qwen3-1.7B (`llmrouter.go`)
|
||||
- **LLM router (the intended design, docs/rearchitecture.md):** the resident Qwen3-1.7B (`llmrouter.go`)
|
||||
emits GBNF-constrained structured JSON, and the SAME model phrases replies. Embedder is
|
||||
demoted from a routing gate to a RAG hint. Wired at `voice.go:214` via
|
||||
`pickLLMRouter(cfg.Voice.UseLLMRouter(), llmClient)`; the flag is `voice.llm_router`
|
||||
@@ -88,10 +155,34 @@ 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.
|
||||
|
||||
Measured on the 77-case RU fixture (`MODEL-BAKEOFF-31-07-2026.md`): the classifier scores
|
||||
36.8% full accuracy at p50 31ms; Qwen3-1.7B scores 67.5% intent-only / 72.7% through the
|
||||
cascade at p50 ≈2.7s. Accuracy roughly doubled, latency is ~90× worse, and that trade was
|
||||
accepted deliberately. `Confidence: 1.0` used to be hardcoded in `llmrouter.go`, so the LLM
|
||||
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
|
||||
seed additions, both of which now score inside the classifier baseline. Qwen3-1.7B scores
|
||||
77.9% intent-only / 72.7% through the cascade. So the router buys about 4 points of accuracy,
|
||||
not a doubling, and the trade is worth re-arguing rather than assuming. **The ≈2.7s figure
|
||||
that stood here until 2026-08-02 was contention, not the model.** See `docs/evals/2026-07-31-routing.md` line 61, which measures the LLM router at
|
||||
p50 825ms / p95 1.2s / max 3.0s and the full cascade at p50 0.80-1.04s. Do not plan latency
|
||||
work off the bakeoff table.
|
||||
|
||||
**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
|
||||
routing change against the classifier and the resident model, since those are what always answer.
|
||||
|
||||
**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
|
||||
forward pass: intent, mood, and BIO slot tags. Roughly 5e15 FLOPs to train, so 10 to 30
|
||||
minutes on the workstation. A 100M decoder from scratch is 10 to 20 GPU hours. Two things
|
||||
it buys that a decoder cannot. No grammar is needed, because a softmax cannot emit a value
|
||||
that does not exist. And max softmax is a calibratable confidence, where `Confidence: 1.0`
|
||||
was a hardcode. **Fine-tune a copy of the weights.** The resident embedder backs memory
|
||||
recall. Training it in place couples routing accuracy to recall@1, with nothing in the
|
||||
suite to name the trade.
|
||||
|
||||
`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
|
||||
no allowlisted fn) feeding the same stage-3 gate the classifier path already had — see
|
||||
@@ -102,8 +193,51 @@ Re-measured on the fixture after the fix: **missed clarify 6/6 → 1**, at the c
|
||||
clarifies and 2.6pt of full accuracy (72.7% → 70.1%, intent-only 67.5% → 74.0%). Two of the
|
||||
three false clarifies are acts the model mis-routed and the gate caught — asking beats wrongly
|
||||
executing, so the fixture and the daemon disagree about what is correct there. The third,
|
||||
`"поужинал"`, is a real defect: **the single-token rule is an English intuition and does not
|
||||
transfer to Russian**, where one word is routinely a whole sentence. Narrow or drop it.
|
||||
`"поужинал"`, was a real defect: the single-token rule was an English intuition and does not
|
||||
transfer to Russian, where one word is routinely a whole sentence.
|
||||
|
||||
Narrowed 01-08-2026. `thinSingleToken` (`internal/router/singletoken.go`) still thins a bare
|
||||
one-word nominal — "вода", "бэкап" — but spares two classes: a closed lexicon of social and
|
||||
control singles ("привет", "спасибо", "стоп", "yes"), and any token carrying a Russian verb
|
||||
ending (past tense, 2nd person, reflexive), because a verb already contains its subject. Both
|
||||
tests are offline and cost nothing. Re-measured: **false clarifies 3 → 2, intent-only 74.0% →
|
||||
75.3%, full accuracy unchanged at 70.1%, missed clarify still 1.** The two remaining false
|
||||
clarifies are the act-with-no-allowlisted-fn arm of the gate, not this rule.
|
||||
|
||||
Agenda questions taken off the model, 01-08-2026. `AgendaQueryGrammars` (`stage0.go`, wired
|
||||
after the clock rules in `buildRouter`) routes "что у меня сегодня", "во сколько у меня
|
||||
встреча" and anything naming a calendar to `IntentQuery` at stage 0. They were going to
|
||||
`IntentSystem`, where `replySystem` has no agenda arm and answered "пока не умею" — the
|
||||
fixture had said `query` since ru-query-019 was written. Measured: **full accuracy 70.1% →
|
||||
72.7%, intent-only 75.3% → 77.9%, calendar 0/2 → 2/2**, clarify counts unchanged. Note that
|
||||
Go's `\b` is ASCII-only and never fires after a Cyrillic letter; the pattern needs an
|
||||
explicit `(\s|[?!.]|$)`.
|
||||
|
||||
Two more shapes taken off the model, 04-08-2026 (V-498). `rest-of-day-query` inside
|
||||
`AgendaQueryGrammars` claims "что дальше?" / "what's next", and `NarrativeQueryGrammar`
|
||||
(`stage0.go`, wired **last** in `buildRouter`, after the capture marker) claims "расскажи про
|
||||
X", "объясни X", "опиши X". Neither carries a question mark or an interrogative, so the model
|
||||
called both `IntentFact`; the write was caught downstream by `IsQuestionShaped`, so this was a
|
||||
latency and fixture defect, not a correctness one. The narrative rule reads the same
|
||||
`narrativeRequests` lexicon `IsQuestionShaped` reads, and declines `chatNarrativeTopics` — a
|
||||
joke, a bedtime story, herself — because the query chain has no source that answers those.
|
||||
New fixture cases ru-query-024 and ru-query-025. Classifier + ONNX baseline **56/80 (70.0%) →
|
||||
58/82 (70.7%)**, no case regressed, no new false clarify. The LLM arm was not measured (no
|
||||
llama-server in that run), so judge it again before quoting a cascade number.
|
||||
|
||||
Praxis taken off the model, 05-08-2026 (V-516). `PraxisGrammars()`
|
||||
(`internal/router/praxis.go`, wired in `buildRouter` before the capture marker because
|
||||
"отметь" is a capture verb) fills `Slots.Fn` with a Praxis capability name. Praxis reach
|
||||
was **0/12 and structurally so**: `handlePraxisAct` compares `Slots.Fn` to a capability
|
||||
alias, and that slot is filled from the deployment's enabled tool names, which no Praxis
|
||||
alias is on. Measured **16/30 → 27/30 overall, praxis 0/12 → 11/12, lifecycle 0/5 → 5/5**
|
||||
(`docs/evals/2026-08-05-praxis-reach.md`). Two rules to know before editing: a **stative**
|
||||
lifecycle word ("готово", "принято") needs an item named beside it, while a bare
|
||||
**imperative** ("закрывай") may ask which one. The bare arm additionally requires that
|
||||
the sentence name no object of its own, or "закрой шторы в комнате" goes to Praxis instead
|
||||
of the house. A demonstrative ("отметь это как сделанное") resolves against
|
||||
`h.surfacedItems` only when exactly one item was spoken. Otherwise the turn goes back to
|
||||
the cascade rather than transitioning the wrong item.
|
||||
|
||||
## LLM output contract
|
||||
|
||||
@@ -114,6 +248,34 @@ All phrasing paths emit `{"response":"...","mood":"..."}` (parsed in `replier_ll
|
||||
note, query, act, chat, system`). `llm/check_prompt_parity.py` in the training
|
||||
workspace enforces that the Go and relabelling prompts remain identical.
|
||||
|
||||
## Russian patterns — three mechanisms, no fourth
|
||||
|
||||
Hand-written Russian stem patterns were swept out on 2026-08-04 (owner's call: not a
|
||||
pattern, and the resident model cannot be asked per turn either). A regex whose output is a
|
||||
fact or a route is the defect; a regex over structured input — HTML, MIME, JSON, a URL, an
|
||||
argv list — is not. Before writing a Russian word list, pick one of these:
|
||||
|
||||
- **`internal/lexicon`** — closed classes, in `lexicon_ru_v1.json`. Interrogatives,
|
||||
capture verbs, reminder verbs, cardinals, day offsets, parts of day, weekdays, months,
|
||||
spoken hours. Editing a word is a data change, and there is exactly one copy: months used
|
||||
to live in three files. Cardinals carry the oblique forms, because a spoken time declines
|
||||
and `в семь` / `к семи` are one hour.
|
||||
- **`internal/morph`** — grammar, from the vendored golem Russian dictionary. `IsVerbForm`
|
||||
and `SameWord`. Note that lemma matching is BROADER than stem-plus-one-ending, so a verb
|
||||
slot that means the imperative must be matched exactly — `говори` and `говорил` are one
|
||||
lemma and only one of them is a command (`cmd/mavend/quiet_toggle.go`).
|
||||
- **`cmd/mavend/topics.go` and the embedder** — open sets, where the question is what a
|
||||
turn is ABOUT. Frozen seeds per subject plus a real `other` class, scored against the
|
||||
turn's own query vector. Same shape as the personal boundary in `personalboundary.go`,
|
||||
with one difference: a topic must clear the runner-up by `topicMargin`, because a false
|
||||
claim here spends a network scan rather than one honest "не знаю". The old keyword tests
|
||||
stay as the offline floor and may remain narrow, since they are no longer the only answer.
|
||||
- **The ecosystem trio** — when the answer is not in the utterance at all. Identity is
|
||||
Nexus's, never a local pattern.
|
||||
|
||||
Seeds are scoring data. Editing one moves a recogniser and must be re-measured against the
|
||||
`TestONNX*` tests, not eyeballed.
|
||||
|
||||
## Non-goals (hard constraints)
|
||||
|
||||
Not a nag, not autonomous. Maven's persona is **feminine** — Russian
|
||||
@@ -129,18 +291,44 @@ world questions, so she needs to read external sources. What replaces it:
|
||||
|
||||
- **No telemetry, no cloud model, no third-party account.** That part never changes. Nothing
|
||||
about Maven is reported to anyone, and inference stays on the box.
|
||||
- **Local sources first.** Kiwix ZIMs on homesrv (Wikipedia, ifixit) before anything on the
|
||||
network. Reading beats recalling for a small model, and a local read costs nothing.
|
||||
- **His data first, then the world.** Every source that reads his facts, notes, calendar,
|
||||
tasks or house runs before anything outside, and the personal boundary sits between them.
|
||||
Reading beats recalling for a small model.
|
||||
- **In the world, live search leads and the ZIMs are the fallback** (owner's call,
|
||||
2026-08-02). A self-hosted SearXNG (`search` block) answers first; the Kiwix ZIMs on
|
||||
homesrv answer when the search is empty, unreachable, or the line is down.
|
||||
**Verified with the line down on 2026-08-05** (V-508,
|
||||
`docs/evals/2026-08-05-kiwix-offline-fallback.md`): a stopped SearXNG costs nothing,
|
||||
the ZIM answers in the same turn budget. A blackholed host cost 8 seconds he waited
|
||||
through. So the connect phase alone is capped at `dialTimeout` (1.5s), while a slow
|
||||
instance that did connect keeps the full 8. **A Russian question reads
|
||||
`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.
|
||||
`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
|
||||
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
|
||||
the web share.
|
||||
- **External search is allowed and off unless configured**, like the weather and telegram
|
||||
capabilities.
|
||||
capabilities. The code default is still off. `deploy/mavend.json` now ships a `search`
|
||||
block (owner's call, 2026-08-02), so it is on for this box and deleting the block turns
|
||||
it off again.
|
||||
- **His notes and facts are never search input.** Looking up why the sky is blue and sending
|
||||
his stored personal notes to an upstream engine are different acts. Only the utterance goes
|
||||
out, never the persona block, history, or matched notes.
|
||||
|
||||
## Web UI conventions
|
||||
|
||||
Server-rendered pages share `cmd/mavweb/static/ui.css` (served at `/ui.css`) and the `nav`
|
||||
partial (`navHTML` in `cmd/mavweb/main.go`, `{{template "nav" "<active-page>"}}`). No
|
||||
Server-rendered pages share `cmd/mavweb/static/ui.css` (served at `/ui.css`) and the shell
|
||||
partial in `cmd/mavweb/shell.html`: a page opens with `{{template "shellTop" "<page-key>"}}`
|
||||
and closes with `{{template "shellBottom"}}`, and the key marks the active sidebar link.
|
||||
Every page is its own embedded `.html` file next to `main.go` — no page markup lives in Go,
|
||||
and the sidebar is data (`sidebarSections`, `pageIcon`) the template renders. No
|
||||
per-page `<style>` beyond true one-offs. Wrap every table in `<div class=scroll>` so wide
|
||||
data pans on a phone. Local preview + headless screenshot recipe is in `AGENTS.md`.
|
||||
|
||||
@@ -148,3 +336,60 @@ data pans on a phone. Local preview + headless screenshot recipe is in `AGENTS.m
|
||||
|
||||
This repo is project **Maven** (ID 2) in Vikunja. MCP: `http://localhost:9100/mcp` (or
|
||||
`http://192.168.1.104:9100/mcp` from workpc). Feature/bug/deploy tasks go there.
|
||||
|
||||
Vikunja is the durable task store. A task holds the goal, the constraints and the
|
||||
assumption ledger. Work without a task id is work nobody can resume, so a session that
|
||||
has no id asks for one before it starts.
|
||||
|
||||
## Session workflow
|
||||
|
||||
`~/.local/bin/task` owns the branch, the commit identity and the PR. One task, one
|
||||
session, one PR.
|
||||
|
||||
```sh
|
||||
task start <vikunja-id> # branch off origin/master, write TASK.md, fetch review comments
|
||||
task pr # push, open or refresh the PR, label Vikunja, notify
|
||||
task comments # re-pull this branch's review comments into .task/
|
||||
```
|
||||
|
||||
Around that, `/pickup` opens a session and `/wrap` closes it. Wrap at roughly half
|
||||
context rather than letting the session compact.
|
||||
|
||||
Five stores, and each one owns something the others must not hold:
|
||||
|
||||
| Store | Holds | Lifetime |
|
||||
|---|---|---|
|
||||
| Vikunja task | goal, constraints, assumption ledger, status | durable |
|
||||
| `CLAUDE.md`, `AGENTS.md` | what an agent must know before touching code | durable |
|
||||
| `docs/` | design, measurements, decisions | durable |
|
||||
| `TASK.md` | the brief for this branch, written by `task start`, immutable | one branch |
|
||||
| `HANDOFF.md` | only what the next agent needs to resume | one session |
|
||||
|
||||
`TASK.md` and `.task/` are excluded through `.git/info/exclude`. `HANDOFF.md` is
|
||||
gitignored and injected at session start. If a line in the handoff would still matter
|
||||
next week, it is in the wrong file.
|
||||
|
||||
Docs are tiered by path, so staleness is visible from the filename. Files directly under
|
||||
`docs/` are living and carry a `Last verified: <date> @ <sha>` line. Files under
|
||||
`docs/evals/` are dated measurements and are never edited after the day, so a newer
|
||||
number is a new file. Files under `docs/archive/` are dead and read by nobody by default.
|
||||
|
||||
## Git guards
|
||||
|
||||
Two hooks in `.githooks/`, tracked, wired with `core.hooksPath`. Fresh clone:
|
||||
|
||||
```sh
|
||||
git config core.hooksPath .githooks
|
||||
```
|
||||
|
||||
- `pre-commit` refuses master, and refuses more than 300 changed lines in non-markdown
|
||||
files. Markdown is exempt and may land as one batch.
|
||||
- `commit-msg` requires the subject to end with `(V-<id>)`. `V-` and not `#`, because
|
||||
Gitea autolinks `#123` to a Gitea issue, which is the wrong tracker.
|
||||
|
||||
Two more guards live outside the repo, in `~/.claude/hooks/`. `diff-budget.sh` blocks
|
||||
further edits past 600 changed lines on a `task/` branch. `prose_lint_hook.py` checks
|
||||
prose on every write. Both measure against `origin/master`, so a local master that is
|
||||
ahead of the remote makes the diff budget read high.
|
||||
|
||||
`--no-verify` exists. Using it means saying why in the commit body.
|
||||
|
||||
+11
@@ -82,11 +82,22 @@ FROM debian:trixie-slim AS runtime
|
||||
# tzdata so the TZ env (set in compose) resolves — otherwise Go can't load the
|
||||
# zone and time.Now() stays UTC, and mavend answers clock/date queries and
|
||||
# evaluates quiet-hours in UTC.
|
||||
#
|
||||
# TZ is a build arg as well as an env because the image was self-inconsistent
|
||||
# without it (V-545): compose set TZ=Europe/Samara and Go read it, but
|
||||
# /etc/localtime still pointed at Etc/UTC, so anything asking the system zone
|
||||
# instead of the environment answered UTC. The reminder path shells out to
|
||||
# python dateparser, which is exactly such a caller. Compose passes the same
|
||||
# zone it already declares, so the zone is written in one place.
|
||||
ARG TZ=Etc/UTC
|
||||
ENV TZ=$TZ
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
ca-certificates libvulkan1 mesa-vulkan-drivers libgomp1 tzdata \
|
||||
python3 python3-pip && \
|
||||
pip3 install --no-cache-dir --break-system-packages 'dateparser==1.4.1' && \
|
||||
apt-get purge -y --auto-remove python3-pip && \
|
||||
ln -snf "/usr/share/zoneinfo/$TZ" /etc/localtime && \
|
||||
echo "$TZ" > /etc/timezone && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# runtime native libs: whisper/ggml (incl. vulkan) are real files in deps/lib.
|
||||
|
||||
@@ -16,11 +16,11 @@ PIPER_BIN := $(shell pwd)/deps/piper/piper
|
||||
PIPER_MODEL := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
|
||||
PIPER_ESPEAK := $(shell pwd)/deps/piper/espeak-ng-data
|
||||
|
||||
.PHONY: simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall eval-phrasing eval-models
|
||||
.PHONY: simulate stt-fixtures test-stt-golden all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go deps-sentinel tidy eval-router eval-reach eval-recall eval-phrasing eval-models build-gpud
|
||||
|
||||
all: build
|
||||
|
||||
build: build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav build-mail build-update
|
||||
build: build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav build-mail build-update build-gpud
|
||||
|
||||
build-stt:
|
||||
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
||||
@@ -59,6 +59,12 @@ build-mail:
|
||||
build-update:
|
||||
$(GO) build $(GOFLAGS) -o mavupdate ./cmd/mavupdate/
|
||||
|
||||
# mavgpud runs on the workstation, not here. It is built with the rest so a
|
||||
# broken supervisor is caught by `make build` on homesrv rather than by the
|
||||
# workstation refusing to serve. Copy the binary over, do not `make deploy` it.
|
||||
build-gpud:
|
||||
$(GO) build $(GOFLAGS) -o mavgpud ./cmd/mavgpud/
|
||||
|
||||
run-web: build-web
|
||||
./mavweb -addr :9200 -voice 127.0.0.1:9100
|
||||
|
||||
@@ -68,7 +74,7 @@ run-web: build-web
|
||||
# base.Tool(), which only stats pkg/tool and exits. So build them in once here.
|
||||
GO_TARBALL := go$(GO_VERSION).linux-amd64.tar.gz
|
||||
GO_SHA256 := 9e9b755d63b36acf30c12a9a3fc379243714c1c6d3dd72861da637f336ebb35b
|
||||
deps-go:
|
||||
deps-go: deps-sentinel
|
||||
@mkdir -p deps/go
|
||||
cd deps/go && curl -fLO 'https://go.dev/dl/$(GO_TARBALL)'
|
||||
cd deps/go && echo '$(GO_SHA256) $(GO_TARBALL)' | sha256sum -c -
|
||||
@@ -78,7 +84,26 @@ deps-go:
|
||||
done
|
||||
$(GO) version
|
||||
|
||||
# fmt-check fails if any file needs gofmt. DESIGN.md has always said `make
|
||||
# deps/go.mod — the sentinel that stops the module walk at deps/ (Vikunja #454).
|
||||
# The vendored toolchain lives inside the module tree, so `go mod tidy` walked
|
||||
# Go's own compiler-error fixtures and died on files that are malformed on
|
||||
# purpose ("unicode//utf8": double slash). A nested module is not part of the
|
||||
# parent, so one three-line file ends the walk. deps/ is gitignored, so it is
|
||||
# generated here rather than committed, and every target that populates deps/
|
||||
# writes it.
|
||||
deps-sentinel:
|
||||
@mkdir -p deps
|
||||
@printf 'module github.com/kami/maven/deps\n\ngo 1.21\n' > deps/go.mod
|
||||
|
||||
# Run the tidy the sentinel makes possible. Not part of `test`: it rewrites
|
||||
# go.mod, and a build target that edits the module file is a surprise.
|
||||
# vendor/ is committed, so a tidy that drops a requirement must be followed by
|
||||
# a re-vendor or the next build fails on "inconsistent vendoring".
|
||||
tidy: deps-sentinel
|
||||
GOTOOLCHAIN=local GOFLAGS=-mod=mod $(GO) mod tidy
|
||||
GOTOOLCHAIN=local GOFLAGS=-mod=mod $(GO) mod vendor
|
||||
|
||||
# fmt-check fails if any file needs gofmt. docs/design.md has always said `make
|
||||
# test` gates on gofmt and vet; it did not, so nine files quietly drifted.
|
||||
# Run `gofmt -w` on whatever this prints.
|
||||
fmt-check:
|
||||
@@ -113,6 +138,14 @@ MAVEN_ONNX_LIB ?= $(shell pwd)/deps/onnxruntime-linux-x64-1.26.0/lib/libonnxrunt
|
||||
eval-router:
|
||||
MAVEN_ONNX_LIB="$(MAVEN_ONNX_LIB)" $(GO) test -v -count=1 ./internal/router/eval/
|
||||
|
||||
# eval-reach — score the held-out ecosystem reach fixture (internal/router/eval,
|
||||
# ru_ecosystem_v1.json). Answers "does a real Russian utterance actually arrive
|
||||
# at Praxis or Hexis", which routing accuracy alone does not say. Same
|
||||
# MAVEN_ONNX_LIB deal as eval-router; without it only the deterministic hash
|
||||
# ratchet runs. Vikunja #405.
|
||||
eval-reach:
|
||||
MAVEN_ONNX_LIB="$(MAVEN_ONNX_LIB)" $(GO) test -v -count=1 -run 'Reach|Praxis' ./internal/router/eval/
|
||||
|
||||
# eval-recall — score the held-out note-recall fixture (internal/memory/recalleval).
|
||||
# Answers "can she find the note again when it matters": recall@1, recall@3,
|
||||
# false recall and the query_min_score sweep. Same MAVEN_ONNX_LIB deal as
|
||||
@@ -172,7 +205,7 @@ run-tts: build-tts
|
||||
./mavttsd -socket /tmp/maven/tts.sock \
|
||||
-piper $(PIPER_BIN) -model $(PIPER_MODEL) -espeak_data $(PIPER_ESPEAK)
|
||||
|
||||
deps: deps-whisper deps-piper
|
||||
deps: deps-sentinel deps-whisper deps-piper
|
||||
|
||||
deps-whisper:
|
||||
cd deps/whisper.cpp && cmake -B build -DCMAKE_BUILD_TYPE=Release \
|
||||
@@ -191,7 +224,7 @@ deps-piper:
|
||||
# multilingual-e5-small: an asymmetric retrieval model. It is trained to match
|
||||
# a short question against a longer passage, which is what note recall is.
|
||||
# The quantized file is the one we download, deploy and measure — see
|
||||
# RECALL-EVAL-31-07-2026.md.
|
||||
# docs/evals/2026-08-04-recall-e5-small.md for what the swap bought.
|
||||
EMBEDDER_DIR := $(shell pwd)/models/embedder/multilingual-e5-small
|
||||
EMBEDDER_MODEL_URL := https://huggingface.co/Xenova/multilingual-e5-small/resolve/main/onnx/model_quantized.onnx
|
||||
EMBEDDER_TOKENIZER_URL := https://huggingface.co/Xenova/multilingual-e5-small/resolve/main/tokenizer.json
|
||||
|
||||
-468
@@ -1,468 +0,0 @@
|
||||
## Maven — current state (updated 2026-07-20)
|
||||
|
||||
### Session 2026-07-20 — ecosystem hardening + entity-aware facts
|
||||
|
||||
Ten commits, focused on closing the Nexus/Praxis integration gaps flagged
|
||||
as "wired but immature" in the prior review, plus the entity-aware-memory
|
||||
backlog item (`20-07-2026-BACKLOG.md` item 5).
|
||||
|
||||
- **Entity-aware fact resolution (Vikunja #279)** — facts gain
|
||||
`Subject`/`EntityID`/`ResolutionState`; an async worker resolves
|
||||
free-text subjects to canonical Nexus entity_ids (mirrors Praxis's own
|
||||
enrichment pattern). Ambiguous/unreachable Nexus never guesses — stays
|
||||
`pending` or terminal `ambiguous`. Voice-tapped facts (`IntentFact`) flow
|
||||
into the queue automatically via an optional `Subject` field on
|
||||
`WriteFactReq` (old callers unaffected, no signature break).
|
||||
- **Typed Praxis lifecycle client (Vikunja #271)** — `GetItem`/`Search`/
|
||||
`Surface`/`Acknowledge`/`Resolve`/`Ignore`/`Pin`, routed through new RU/EN
|
||||
dialogue verbs. Fixes a real lifecycle-invariant bug: reading an
|
||||
attention item aloud now calls `Surface` — previously the digest path
|
||||
read items without recording that they'd been surfaced, so "Maven
|
||||
mentioned it" was indistinguishable from "never came up."
|
||||
- **Durable delivery outbox (Vikunja #270)** — `BeginDeliveryAttempt`
|
||||
before `Send`, `CompleteDeliveryAttempt` after; a stale `pending` row
|
||||
found at startup reconciles to `unknown` (never silently resent or
|
||||
dropped — same rule as Hexis's execution-timeout handling). Closes a
|
||||
crash-window duplicate-send bug. Wired into `DispatchNudge`,
|
||||
`DispatchReminder`, `RepeatUnacked`; reconciliation runs once at boot
|
||||
before the tick loop resumes.
|
||||
- **Fail-closed IPC/dependency handling (Vikunja #269, #272/#273)** —
|
||||
ambiguous mutation outcomes (frame sent, reply lost) no longer blindly
|
||||
retry; Nexus/Hexis dependency errors fail closed instead of guessing.
|
||||
- **Correlation IDs + version headers (Vikunja #273)** — the hand-rolled
|
||||
Nexus/Praxis HTTP clients now send `X-Nexus-Version`/`X-Praxis-Version`
|
||||
and thread the same correlation ID already generated in
|
||||
`executeCapability` through the whole call chain, matching the Hexis
|
||||
client's existing behavior.
|
||||
- **Entity-scoped Praxis attention queries** — callers holding a resolved
|
||||
entity_id can ask "what needs attention for this entity" directly
|
||||
instead of filtering the unscoped list client-side.
|
||||
- **Fake-ecosystem test harness with fault injection** — a reusable
|
||||
`fakeServer` (Nexus/Praxis/Hexis fixtures, runtime-toggleable
|
||||
`SetFault`, fake clock) replacing ad-hoc per-test `httptest` servers;
|
||||
covers a gap that had zero test coverage (`handlePraxisAct`) and adds a
|
||||
fault-then-recovery regression test for the fail-closed fixes above.
|
||||
- **Ops fix** — `deploy/mavend.json`'s phraser was pointed at a 4B model
|
||||
with `n_gpu_layers=99`, which OOM'd under memory pressure and left a
|
||||
zombie `llama-server` child; swapped to the 2B Qwen model matching the
|
||||
intended resident-model size.
|
||||
|
||||
Net effect: the Nexus/Praxis wiring described as "plumbing exists, thin
|
||||
compared to Maven's test depth" in the prior review is now materially
|
||||
hardened — typed clients, fail-closed error handling, durable delivery,
|
||||
and a proper fault-injection test harness are all in place. Evaluation lab
|
||||
(`20-07-2026-BACKLOG.md` item 7) is explicitly skipped for now — it runs
|
||||
on the GPU box, which is occupied by CPT. Morning routine engine (backlog
|
||||
item 3) is next up, not started.
|
||||
|
||||
---
|
||||
|
||||
> **Resolved 2026-07-30 (task #318).** The resident checkpoint is
|
||||
> **Qwen3.5-0.8B** (`Q4_K_M`), set in `deploy/mavend.json`; the **target** is
|
||||
> the locally CPT'd **Qwen3-1.7B**, still training (#122). Older model claims
|
||||
> below — the LFM references, the pipeline line, and the "swapped to the 2B
|
||||
> Qwen model" ops entry above — are historical. Read them as a log of what was
|
||||
> true at the time, not as current fact. Note also that `/mnt/hdd1/llms` is
|
||||
> bind-mounted over `models/llm/`, so the LFM2.5 gguf in the repo tree is
|
||||
> never loaded.
|
||||
|
||||
Architecture decision (as written on 2026-07-20): the target resident
|
||||
router/phraser is the locally trained Qwen3-1.7B model — still the target as
|
||||
of 2026-07-30. Older LFM references below describe the then-deployed
|
||||
historical stack, not the target checkpoint. RU CPT has a successful
|
||||
full-weight checkpoint at step 1000/8077; evaluation and Qwen3 SFT tooling are
|
||||
tracked in `docs/plans/2026-07-18-qwen3-resident-training-eval.md`.
|
||||
|
||||
Consolidated status. The reactive↔proactive core is closed and testable through
|
||||
the web PWA. The former SPEC's open items 1–7 (now `DESIGN.md` § execution ledger) are landed (protocol doc, away-channel
|
||||
fallthrough, CalDAV poller, quiet-hours schedule, tools enable/disable, note RAG,
|
||||
passkey step-up); item 8 (multi-user) is deliberately deferred — see the tail.
|
||||
The two big infra gaps from the jul5 revision are closed on `overnight-jul5`:
|
||||
**at-rest encryption** (AES-256-GCM, tmpfs working copy — not sqlcipher, see
|
||||
`internal/store/crypt.go`) and **Docker deployment** (one image, six daemon
|
||||
containers). The `overnight-jul6` session (now on `master`) closed the biggest
|
||||
*query-surface* gaps — **calendar querying, general-knowledge answers, and
|
||||
weather** — plus a populated homelab act allowlist and two pure scaffolds
|
||||
(dialogue state, long-term-memory vector store). ~15.2k LOC + ~8.5k test, 303
|
||||
tests, `-race` in `make test`.
|
||||
|
||||
### Access model
|
||||
|
||||
- **Phone** → needs the wg tunnel to reach homesrv (no homesrv DNS otherwise;
|
||||
raw IP or a DNS tweak can bypass, not the default).
|
||||
- **PC** → uses homesrv DNS, resolves the domains over local-net, **no wg needed**.
|
||||
- nginx + ufw both scope to `10.42.0.0/24` (wg) + `192.168.1.0/24` (LAN), deny all else.
|
||||
- **Surface in use now: the web PWA (`mavweb`).** Voice PTT + in-app nudges both ride it.
|
||||
|
||||
### Works end-to-end (tested)
|
||||
|
||||
- **Reactive voice:** PWA record → Whisper STT (`mavsttd`) → ONNX classifier →
|
||||
resident phraser (llama-server subprocess; Qwen3.5-0.8B as of 2026-07-30 —
|
||||
this line historically named "LFM 2.5-1.2B") → Piper TTS
|
||||
(`mavttsd`) → reply.
|
||||
HTTP POST path (mobile-Chrome drops WS for the audio).
|
||||
- **Capture:** `fact` (EN **and RU** — root-substring recognizers) + `reminder`
|
||||
persist through CoreAPI (`source=tap:voice`). This is the substrate the care
|
||||
rules read.
|
||||
- **Notes / query (semantic recall, sqlite — no chroma):** `note` → embed (the
|
||||
classifier's ONNX embedder) → `notes` table. `query` → embed → brute-force
|
||||
cosine top-k → confidence-gated (below `queryMinScore` 0.55 ⇒ "no note", not a
|
||||
guess). **Note RAG (SPEC item 6):** the gated top-k feed the phraser
|
||||
(`PhraseQuery`) to compose a natural answer ("вот что я нашла: …") instead of
|
||||
a verbatim dump; raw-notes fallback on any LLM error. Stub is deterministic.
|
||||
- **Monitoring (`/dash`):** mavweb server-renders presence + recent nudges (by
|
||||
outcome) + recent facts from the append-only store via CoreAPI. Read-only,
|
||||
meta-refresh, no JS.
|
||||
- **Proactive loop:** 60s dumb ticker, pure predicates over a State snapshot,
|
||||
universal gate (quiet-hours/presence/cooldown/snooze/calendar), one-nudge-per-
|
||||
tick max-severity, reminders (gate-bypassing), sev4 repeat-til-ack, feedback
|
||||
auto-tuner (outcome ratio → bounded cooldown, persisted as `source=feedback`).
|
||||
- **Rules:** water/meal/break (sev1–2 care), service_down (sev4, `poll:uptimekuma`),
|
||||
netdata_critical (sev3, `poll:netdata`).
|
||||
- **Routines (`internal/routine`):** operator-declared clockwork — the third
|
||||
proactive class beside reminders (user-stated) and care rules (world-state).
|
||||
Config `routines[]` (cron + literal RU body + severity) fire through the normal
|
||||
dispatcher on schedule (an 08:00 briefing, a 22:00 wind-down). Bodies are
|
||||
literal (not LLM-phrased ⇒ can't hallucinate); rule name `routine:<name>` so
|
||||
they don't pollute the care autotuner; cold-start guard seeds on first sight so
|
||||
a restart never replays a missed schedule. Pure `routine.Due`, unit-tested; the
|
||||
tick driver holds the last-fired map.
|
||||
- **Env facts (`mavpoll`):** netdata alarms → `netdata_alarm` (fires immediately
|
||||
on a real CRITICAL); kuma monitor_status → `service_down`. Writes only on
|
||||
value-change (no append-only churn).
|
||||
- **Presence:** noisy-OR decay + Schmitt hysteresis. Live via `page_heartbeat`
|
||||
(PWA auto-pings `/api/signal` every 30s → present when a tab's open).
|
||||
- **Delivery:** ntfy / telegram / voice by `f(severity, presence)`; minimal body
|
||||
on away channels. PWA subscribes to ntfy over **WebSocket** for in-app nudges.
|
||||
- **Away-channel fallthrough (SPEC item 2):** when the router picks voice but no
|
||||
live session exists at push time (presence guess was wrong), the dispatcher
|
||||
reroutes through the AWAY table — sev3→ntfy, sev4→telegram-repeat-til-ack,
|
||||
sev≤2→drop — instead of silently dropping. Covers nudges + reminders.
|
||||
- **Calendar busy (SPEC item 3, `mavcaldav`):** new poller queries a self-hosted
|
||||
**Radicale** CalDAV server on an interval, writes `calendar_busy` + event facts
|
||||
through CoreAPI (value-change only). The loop gate already consumes `calendar_busy`.
|
||||
- **Quiet-hours schedule (SPEC item 4):** the gate reads `quiet_hours`; a config
|
||||
time window (`voice.quiet_hours`, HH:MM, midnight-crossing handled) now sets it
|
||||
on each tick — in addition to the "тихий режим" voice toggle. Both activate quiet.
|
||||
- **Client protocol (SPEC item 1):** the voice wire format (length-prefixed JSON
|
||||
frames) is published in `PROTOCOL.md`, generated from `internal/voice/wire.go`
|
||||
so third-party clients don't need the Go source.
|
||||
- **Passkey step-up (SPEC item 7):** `internal/webauthn` does real WebAuthn —
|
||||
ES256/P-256 register + assert, ecdsa signature verification, rpIdHash + UP/UV
|
||||
flag binding (UV = the gesture), sign-count regression check. `PasskeySession`
|
||||
bumps the auth session L2→L3 for a TTL on assert. mavweb serves `/auth/passkey`
|
||||
(enroll + step-up) + the begin/finish endpoints. Crypto is round-trip tested
|
||||
(incl. tampered-sig / missing-UV / wrong-origin negatives).
|
||||
- **Stability:** llama-server orphan leak fixed (`Pdeathsig` kills the child on
|
||||
any mavend death); `kill-maven.sh` reaps strays (matches the model, not a
|
||||
bogus `llama-server.*maven` pattern); `start-maven.sh` wires `-core` + poller.
|
||||
|
||||
### Wired but needs a deploy action (not code)
|
||||
|
||||
- **`desk_active`** (strongest presence signal) — `scripts/desk-active.sh` runs
|
||||
on the **desk PC** (hypridle-gated systemd timer), posts over wg to mavweb.
|
||||
- **`mavwaked`** (always-on listening) — needs a systemd user unit on a client
|
||||
box (desk PC, pi, etc.) where the mic is attached. Connects to mavend over wg
|
||||
or local net via `-addr`. Deferred until a client box is wired with a mic.
|
||||
|
||||
Caveats / gotchas:
|
||||
- **desk_active is a workstation deploy, not code** — 0 facts ever written; presence
|
||||
runs on page_heartbeat alone (dash reads "away"/"never at desk"). `scripts/desk-active.sh`
|
||||
+ a hypridle-gated `maven-desk` timer must be installed on the desk PC (not homesrv).
|
||||
- **Notes recall needs the ONNX embedder** — under the HashEmbedder floor, cosine is
|
||||
lexical (token overlap), not semantic; scores are low, so most RU commands sit under
|
||||
the 0.35 route threshold and clarify. Configure `voice.embedder` for confident recall+routing.
|
||||
(The floor now at least tokenizes Cyrillic — see below — so it ranks correctly, just weakly.)
|
||||
- **Switching the embedder model silently breaks old notes** — different dim ⇒
|
||||
cosine 0 ⇒ they stop matching; brute-force can't re-embed. Re-embed on a model change.
|
||||
- **`wg_handshake` is OFF and should stay off** — in this topology the phone only
|
||||
runs wg when *outside*, so a fresh handshake means AWAY, not here. The `mavpoll
|
||||
-wg` flag exists (defaults `""`) and could later back the spec's "away override"
|
||||
by flipping the sign; as a presence-*here* signal it's inverted. desk_active +
|
||||
page_heartbeat cover home presence.
|
||||
- **Cold-start unlock tests are missing** — the key wrap/unwrap code
|
||||
(`internal/webauthn/keywrap.go`) and locked-mode IPC gating (`cmd/mavend/main.go`)
|
||||
are correct but have **zero test coverage**. The roadmap (item 2.1) required
|
||||
three new test cases (wrap/unwrap round-trip, wrong-cred unwrap fails,
|
||||
locked-mode IPC rejects non-unlock methods); none were written. `make test`
|
||||
is green by omission. Write these before relying on the cold-start path with
|
||||
real keys.
|
||||
|
||||
### Done since last revision (overnight-jul6, 2026-07-06)
|
||||
|
||||
Seven tasks (session board `SESSION-06-07-2026.md`, deleted 2026-07-30 — see git history), one commit each, merged to `master`.
|
||||
This session was run through **opencode**, not Claude Code (co-author trailer).
|
||||
|
||||
Since then (**2026-07-06, second session**):
|
||||
|
||||
- **Always-on listening (gap 1, MVP)** — `cmd/mavwaked/`: 825 lines, 10 `-race`
|
||||
tests. Energy-based VAD over 30ms windows (same RMS threshold as mavsttd's
|
||||
`gateReason`), adaptive noise floor, speech→silence state machine. Captures
|
||||
PCM from arecord(1) subprocess, sends `PushToTalk` with `Surface=SurfaceVoice`
|
||||
(L0 — no destructive acts). Reply plays through aplay(1). No wake word yet
|
||||
(pure VAD trigger); the 30ms frame shape matches silero-vad ONNX input 1:1,
|
||||
so swapping energy-threshold for ONNX inference is a local change in vad.go.
|
||||
`Makefile` `build-waked` target. Runs on client boxes (not docker/homesrv)
|
||||
via systemd user unit; connects to mavend over wg or local net.
|
||||
|
||||
Since then (**2026-07-06, third session** — roadmap execution agent):
|
||||
|
||||
- **Cold-start unlock (ROADMAP 2.1)** — the at-rest AES key is now wrapped
|
||||
(HKDF-SHA256 + AES-256-GCM, stdlib-only — no `x/crypto` dep) with the passkey
|
||||
credential's public key and persisted to disk. At boot, if a wrapped key file
|
||||
exists AND no env key is set, mavend starts **locked**: the IPC server runs
|
||||
but `srv.Check` rejects everything except `MethodAssertStepUp` +
|
||||
`MethodUnlock`. A passkey assertion at `/auth/passkey` calls `MethodUnlock`
|
||||
with the credential's public key → unwraps the blob → opens the store → wires
|
||||
voice/loop/delivery → `srv.SetAPI` swaps the locked stub for the real
|
||||
CoreAPI. mavweb's `RegisterFinish` wraps the env key on enrollment;
|
||||
`AssertFinish` calls `Unlock` on assertion. Env-key fallback preserved
|
||||
(dev/CI path unchanged). **Test gap:** the roadmap required three new test
|
||||
cases (wrap/unwrap round-trip, wrong-cred unwrap fails, locked-mode IPC
|
||||
rejects non-unlock methods) — none were written. The code is correct but
|
||||
untested; `make test` is green by omission, not coverage.
|
||||
- **Conversation depth (ROADMAP 3.2)** — cross-intent anaphora + fact-by-key
|
||||
lookup. `AnaphoraResolver` in `router/slots.go` detects RU pronouns
|
||||
(это/он/она/оно/тот/мой + inflected forms). `followUpMerge` now handles
|
||||
three cases: same-intent slot inheritance (existing), cross-intent anaphora
|
||||
(Query/Fact/Reminder after a Fact with a pronoun inherits the prior key +
|
||||
time), and query-after-fact (a query following a fact inherits the key for
|
||||
fact-by-key lookup). `Session.History []Turn` added as the multi-turn
|
||||
scaffold (capped at 4). 7 new test cases including the exact done-when
|
||||
scenarios (anaphora query-after-fact, three-turn break, explicit-key-wins).
|
||||
- **Routing quality + persona (ROADMAP 4.1/4.4)** — `QueryMinScore` is now a
|
||||
config knob (`voice.query_min_score`, default 0.55) instead of a hardcoded
|
||||
const. `make download-embedder` fetches Xenova/paraphrase-multilingual-
|
||||
MiniLM-L12-v2 (~90MB ONNX) + tokenizer; AGENTS.md documents the embedder +
|
||||
libonnxruntime setup. `Persona` field in `VoiceConfig` prepends to every
|
||||
LLM system prompt (nudge phrasing, note queries, general knowledge); empty
|
||||
= current hardcoded feminine-gendered Russian persona. Also fixed two
|
||||
pre-existing data races found by `-race`: `voice/server.go` wg.Add vs
|
||||
wg.Wait (accept mutex), `mavweb/server.go` s.api field (atomic.Value).
|
||||
|
||||
- **Calendar querying (task 3)** — "что у меня завтра?" now answers from the
|
||||
CalDAV facts the poller already writes. Added `store.CalendarEvents(from,to)`,
|
||||
a RU date-scope parser («сегодня»/«завтра») in `router/slots.go`, and an
|
||||
IPC `CalendarEvents` RPC (api/client/server/wire) feeding the `IntentQuery`
|
||||
handler. Empty day → «на сегодня ничего нет». Previously calendar only *gated*
|
||||
nudges; it's now queryable.
|
||||
- **General-knowledge routing (task 4)** — when notes-RAG misses `queryMinScore`,
|
||||
the query now falls through to the phraser with an anti-hallucination system
|
||||
prompt (`router.KnowledgePrompt`, single tested source) instead of giving up.
|
||||
Empty/errored/Stub phraser → «не знаю.», never a fabrication.
|
||||
- **Weather (task 5)** — new `internal/weather/`: `Provider` interface, a stub
|
||||
(«погода не настроена»), and a real **keyless Open-Meteo** provider (geocode +
|
||||
current_weather, injectable `*http.Client`, mocked in tests — no live network).
|
||||
Wired into `IntentQuery` (keywords погода/градус/температура) with a ~5s
|
||||
context timeout; selected by `voice.weather.provider` ("open-meteo" | "" → stub).
|
||||
- **Homelab act allowlist (task 2)** — `voice.tools` seeded with read-only acts
|
||||
(`systemctl status`, `docker ps`, `uptime`, `df`, `free`, `journalctl` reads)
|
||||
as `destructive:false` and mutating ones (restart/stop/start/reboot,
|
||||
docker-restart/stop) as `destructive:true`. Guardrail verified: no dangerous
|
||||
verb is `destructive:false`. RU phrasings seeded in `act.txt`.
|
||||
- **Embedder config validation (task 1)** — a partially-filled `voice.embedder`
|
||||
block (some of model/tokenizer/lib paths missing) is now a load error instead
|
||||
of a silent fall-through to the Hash floor; the floor fallback logs explicitly.
|
||||
- **Dialogue state scaffold (task 6)** — `internal/dialogue/`: `Session` +
|
||||
TTL `SessionStore` + pure `InheritSlots`. **Now wired** (post-merge follow-up):
|
||||
the voice handler carries slots across same-intent turns within a 2-min window
|
||||
(`followUpMerge`, unit-tested) — bounded gap-filling, not full multi-turn yet.
|
||||
- **Long-term memory interface (task 7)** — `internal/memory/`: `Store` interface
|
||||
+ `InMemoryStore` (cosine). Wired into `IntentNote` (best-effort insert) and,
|
||||
post-merge, into `IntentFact` (facts indexed) + `IntentQuery` (read-back after
|
||||
notes-RAG misses). In-memory only — no persistent backend yet (gap #8).
|
||||
|
||||
Follow-ups (Claude Code, post-merge): gofmt'd `handlers_test.go` (the jul6
|
||||
verification commit left it misaligned, so `gofmt -l` still flagged it despite the
|
||||
"all gates green" claim); deduped the task-4 knowledge prompt to the single tested
|
||||
`router.KnowledgePrompt()`. Tree is now genuinely green (gofmt/vet/303 tests).
|
||||
|
||||
### Done since the jul5 revision (overnight-jul5, 2026-07-05)
|
||||
|
||||
The overnight session (`SESSION-05-07-2026.md`, deleted 2026-07-30 — see git history; 25 tasks) closed the previous
|
||||
"not built yet" items 1–3 and added feature depth:
|
||||
|
||||
- **At-rest encryption** — the on-disk db is AES-256-GCM ciphertext; the daemon
|
||||
works on a tmpfs (RAM) plaintext copy, sealed back atomically on close. Wrong
|
||||
key / tamper ⇒ fail closed, never a plaintext fallback. Legacy plaintext dbs
|
||||
upgrade on first clean shutdown. Key via config/env (`db_key_env`); no KDF —
|
||||
raw 32-byte key, base64. The passkey cold-start unlock plugs into the same
|
||||
`store.OpenEncrypted` seam later.
|
||||
- **Docker deployment** — single image, one container per daemon
|
||||
(`docker-compose.yml`); only mavend mounts the key + db volume; IPC over a
|
||||
shared socket volume. `ipc.DialWait` (boot-order tolerance) + redial-on-drop
|
||||
(core restarts don't kill modules). `deploy/README.md` has the runbook.
|
||||
- **Tests** — mavcaldav, mavttsd, voicesink, mavweb main/handlers covered;
|
||||
`make test` runs `-race -coverprofile`.
|
||||
- **Recurring reminders** — `cron` + `next_fire_ts` on reminders; recurring ones
|
||||
reschedule (instead of mark-fired) after successful delivery.
|
||||
- **Notification digest/batching** — low-severity nudges queue and flush as one
|
||||
digest per window/max-items (`digest` config block); stale-reminder bursts on
|
||||
boot collapse into a single digest reminder, completed only after delivery.
|
||||
- **Rule trace engine** — `ExplainTick`/`ExplainGate` record per-rule
|
||||
predicate/gate/selection results each tick; served over IPC (`tick_trace`)
|
||||
and rendered at mavweb `/trace` ("why didn't she nudge me").
|
||||
- **Web UI** — new `/history` (facts + revert buttons), `/notifications` (nudge
|
||||
history), `/trace` pages; nav links on `/dash`; RU/EN cheatsheet toggle in the
|
||||
PWA; manifest icons (`icon.svg`). POST `/tools` now requires an in-process
|
||||
passkey step-up when WebAuthn is configured.
|
||||
- **Revert/undo** — `RevertFact` voids the latest fact for a key (append-only
|
||||
void-marker, audit trail intact); exposed at `/api/revert` from `/history`.
|
||||
- **Tool scopes** — `scope` column on tools, threaded through propose/enable/UI.
|
||||
`DisableTool` raised to AuthStepUp alongside Enable.
|
||||
- **Passkey persistence** — mavweb credentials in a JSON file (`-passkey-file`),
|
||||
surviving restarts; rollback-on-persist-failure keeps memory and disk in sync.
|
||||
- **STT silence gate** — min-duration + RMS floor drop non-speech before whisper
|
||||
hallucinates on it (`-min-ms`, `-silence-rms` flags on mavsttd).
|
||||
- **Housekeeping** — `db_key.env` gitignored (+`.env.example`), `build-caldav`
|
||||
target, zero-timestamp "never" fix on /dash.
|
||||
|
||||
### Not built yet (ranked by ROI)
|
||||
|
||||
1. **Multi-user (SPEC item 8)** — deliberately deferred, see the tail.
|
||||
|
||||
Closed (jul6 follow-ups): `/api/revert` now sits behind the same passkey
|
||||
step-up as POST `/tools`; `go.mod` direct deps (`onnxruntime_go`,
|
||||
`coder/websocket`, `robfig/cron`) are labeled correctly — `go mod tidy` can't
|
||||
run here because it walks the vendored `deps/go` toolchain tree.
|
||||
Purge+rotate leaked db key (#12) — investigated and closed: the key was
|
||||
**never committed** to git history (gitignored at introduction, no commit
|
||||
ever tracked `deploy/db_key.env`), so nothing to scrub. File stays on disk
|
||||
and in deploy env by design — at-rest encryption needs it at boot.
|
||||
|
||||
Done earlier (2026-07-03): **act tool executor, store-backed, full flow**
|
||||
(`internal/tool` + `internal/store/tools.go` + `tools` CoreAPI methods).
|
||||
- **Execution:** IntentAct runs the matched fn against the store's ENABLED
|
||||
allowlist. argv, no shell → STT text can't inject. Live store read, so a
|
||||
newly-enabled tool runs without a daemon restart.
|
||||
- **proposed→enabled→disabled (SPEC item 5):** an act whose verb isn't enabled is
|
||||
scaffolded as a `proposed` tool (maven suggests). A human enables it (fills argv
|
||||
+ destructive) on the authed **`mavweb /tools`** page — never voice — and can
|
||||
disable it back to `proposed` (kept in the store, won't run). `EnableTool`/
|
||||
`DisableTool` sit at `AuthStepUp`; the gate is now **live** via `PasskeySession`,
|
||||
so /tools enable requires a passkey assertion at `/auth/passkey` first.
|
||||
- **Confirm turn:** a destructive enabled tool replies "выполнить X? да/нет" and
|
||||
parks; the next utterance (ru/en yes-no) confirms or cancels (90s TTL).
|
||||
- **Config:** `voice.tools` seeds enabled tools at boot (editing mavend.json =
|
||||
the human enable act); mavweb enables ad-hoc ones on top.
|
||||
- **Russian:** fixed grammar in reply strings + seed files; maven's self-
|
||||
reference is feminine ("she") — [[maven-persona-gender]].
|
||||
|
||||
Also fixed:
|
||||
- **HashEmbedder was blind to Cyrillic** (`tokenize` iterated bytes, kept only
|
||||
`a-z0-9`) → every RU utterance embedded to the zero vector → cosine 0 across
|
||||
all intents → misrouted to `act` (alphabetical tie-break). Now rune-based
|
||||
(`unicode.IsLetter`). This was the real cause of "Найди заметку" (a query)
|
||||
landing in `notes`; added note-retrieval query seeds too.
|
||||
- **Notes are now browsable on `/dash`** — `RecentNotes` plumbed through the
|
||||
store + CoreAPI; voice-captured notes were previously only reachable via
|
||||
semantic `query`.
|
||||
Earlier: notes/query recall, `/dash` monitoring, `wg_handshake` poller (NO-OP).
|
||||
|
||||
### Gaps — why "voice assistant" is still aspirational (2026-07-06)
|
||||
|
||||
What separates Maven today from the thing the spec describes. Dealbreakers
|
||||
first — these define the category:
|
||||
|
||||
1. **Always-on listening is code-complete (MVP).** `cmd/mavwaked` captures
|
||||
PCM from arecord → energy-based VAD → PushToTalk with `Surface=SurfaceVoice`
|
||||
(L0). Gap narrowed: no wake word yet (pure voice-activity trigger; every
|
||||
utterance fires). The 30ms frame shape and 16kHz PCM match silero-vad's
|
||||
ONNX input exactly, so a wake-word model swap is a local change in vad.go.
|
||||
Hardware: the mic lives on a client box (desk PC, pi, etc.) — never the
|
||||
homesrv. Deploy action: systemd user unit on whichever box has the mic,
|
||||
connects to mavend over wg or local net.
|
||||
2. **Conversation is deeper now, still not full dialogue.** The router
|
||||
classifies one utterance → one reply, but `internal/dialogue` carries
|
||||
context across turns: a 2-min session inherits slots for same-intent
|
||||
follow-ups («напомни завтра» → «…позвонить маме»), and cross-intent
|
||||
anaphora («запиши что я пил воду» → «когда я это сделал?») now resolves
|
||||
RU pronouns (это/он/она/оно/тот/мой + inflections) to the prior turn's
|
||||
key for fact-by-key lookup. `Session.History []Turn` is the scaffold for
|
||||
real multi-turn. Still missing: LLM-driven dialogue manager (decide
|
||||
ask-vs-act), anaphora beyond RU pronouns, single-slot session (single-user
|
||||
box). The sub-1B phraser only words replies.
|
||||
3. **Latency/shape of a turn.** Clip-based STT (record → upload → whisper →
|
||||
route → phrase → piper → play). No streaming either direction, no barge-in;
|
||||
every exchange is a full round trip.
|
||||
|
||||
Capability-class gaps — built but thin:
|
||||
|
||||
4. **Act surface is a small argv allowlist.** propose→enable works and the
|
||||
allowlist now ships a homelab starter set (jul6 task 2 — status/ps/uptime/
|
||||
df/free/logs read-only, restart/stop/reboot gated). Still bounded to what's
|
||||
seeded; broadening it is config, not code.
|
||||
5. **Query answers now cover notes + calendar + weather + general knowledge**
|
||||
(jul6 tasks 3/4/5). Calendar querying, keyless Open-Meteo weather, and a
|
||||
phraser knowledge-fallback all landed; caveat — general-knowledge quality is
|
||||
only as good as the sub-1B phraser, and weather needs `voice.weather.provider`
|
||||
set. The cheatsheet and router are now roughly aligned.
|
||||
6. **Routing quality depends on the ONNX embedder being configured** — the
|
||||
HashEmbedder floor makes RU recall lexical/weak; many commands fall to
|
||||
"clarify". `make download-embedder` now fetches the multilingual MiniLM
|
||||
model + AGENTS.md documents libonnxruntime setup; `voice.query_min_score`
|
||||
is a config knob (default 0.55) so the floor can be tuned without recompile.
|
||||
7. **Presence is effectively one signal** (page_heartbeat); desk_active is
|
||||
still an undeployed script — "voice when near" routing runs on a guess.
|
||||
8. **Long-term memory is now persistent (store-backed), not the spec's chroma.**
|
||||
`internal/memory` has a `Store` interface; the daemon now wires
|
||||
`store.MemoryStore` (`internal/store/memory.go`) — a **persistent** backend
|
||||
in the **same encrypted sqlite db** (survives restarts; recall text inherits
|
||||
at-rest encryption, so no plaintext sidecar). Vectors are float32 blobs,
|
||||
search is brute-force cosine (fine at single-user scale; ANN is the later
|
||||
swap behind the same interface). Notes **and facts** are indexed on capture;
|
||||
`IntentQuery` reads it back (after notes-RAG misses, before general-knowledge)
|
||||
— fact recall («когда я пил воду?») is its distinct payoff. The in-memory
|
||||
impl remains the test/no-store floor. Remaining: an ANN/external index is
|
||||
optional-scale, not a gap. Custom TTS voice (kami-picked, replaces the irina
|
||||
floor — [[custom-voice-training]]) is still a future item.
|
||||
|
||||
Ops footnote: voice-over-web verified 2026-07-06 — mavend binds 0.0.0.0:9100
|
||||
and mavweb reaches it cross-container at mavend:9100 (nc -z confirmed).
|
||||
mavpoll uses network_mode=host to reach localhost services (netdata, kuma).
|
||||
|
||||
### Future / logged, not now
|
||||
|
||||
Custom TTS voice training (kami-picked voice, replaces irina floor); listening
|
||||
modes 2–3 (meeting-record, ambient-derive).
|
||||
|
||||
### Services & layout
|
||||
|
||||
- `mavend` (core, IPC unix socket) — store + loop + phraser; the only key-holder.
|
||||
- `mavsttd` / `mavttsd` — STT/TTS worker modules (unix sockets).
|
||||
- `mavweb` — PWA bridge (HTTP), `/api/ptt` voice, `/api/signal` presence ingest,
|
||||
`/api/ntfy` WS-subscribe config, `/dash` read-only monitoring.
|
||||
- `mavpoll` — env poller (netdata/kuma → facts via CoreAPI).
|
||||
- `mavcaldav` — CalDAV poller (Radicale → `calendar_busy` + events via CoreAPI).
|
||||
- All behind wg + nginx deny-all; no phone-home. CGo only in `mavsttd`.
|
||||
- Start/stop: `./start-maven.sh [build]`, `./kill-maven.sh`.
|
||||
- Config: `~/.config/maven/mavend.json` (or `mavend.json` in repo root).
|
||||
|
||||
### Key files
|
||||
|
||||
- `cmd/mavend/{main,tick,voice}.go` — daemon wiring, loop driver, voice handler
|
||||
- `internal/loop/{loop,rules,gather,feedback}.go` — proactive engine
|
||||
- `internal/store/` — append-only facts/reminders/nudges/presence/notes
|
||||
- `cmd/mavweb/{main.go,dash.html}` — PWA bridge + `/dash` monitoring
|
||||
- `internal/router/{classifier,slots,stage0}.go` — reactive routing + slot parse
|
||||
- `internal/delivery/` — dispatcher + ntfy/telegram/voice sinks
|
||||
- `internal/auth/` — scope/gate/policy; `FloorEnrollment` (same-uid = device
|
||||
trust) + `webauthn.PasskeySession` (real step-up for L3)
|
||||
- `internal/webauthn/`, `cmd/mavweb/webauthn.go` — passkey register/assert
|
||||
- `cmd/mavcaldav/`, `cmd/mavpoll/`, `scripts/desk-active.sh` — env producers
|
||||
|
||||
### Why multi-user (SPEC item 8) is deferred
|
||||
|
||||
Not neglect — the one item where doing nothing now beats doing something:
|
||||
|
||||
- **No second user exists yet** (the "gf phase"). Building per-user partitioning
|
||||
now means code exercised by zero users and validated by nobody — YAGNI.
|
||||
- **The append-only schema makes it a migration, not a rewrite.** No row is ever
|
||||
mutated, so adding `facts/notes/reminders.user_id` later is add-columns +
|
||||
backfill-to-"kami" — no reshaping, no dual-write window. Deferral is cheap.
|
||||
- **The hard part is speaker attribution, and it needs the second voice.** A
|
||||
voice-print discriminator (kami vs gf vs unknown) can't be trained or tuned
|
||||
with one voice in the house. Plumbing before the model is pipe with no water.
|
||||
- **It's fenced deliberately** (`DO NOT TOUCH THIS PHASE` in `DESIGN.md` § Users) so an
|
||||
autonomous agent doesn't add `user_id` columns while touching the store and
|
||||
commit us to a schema before the constraints that shape it exist.
|
||||
@@ -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))
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
// Package main is mavenclient — maven's reference client.
|
||||
//
|
||||
// Per DESIGN.md § Voice pipeline (STT / TTS): capture lives on the client;
|
||||
// Per docs/design.md § Voice pipeline (STT / TTS): capture lives on the client;
|
||||
// the server transcribes + synthesises on demand. The PC client runs the
|
||||
// wake-word / VAD gate (cmd/mavwaked) and ships ONE clean audio blob per
|
||||
// utterance on activation. The server never owns a mic.
|
||||
|
||||
@@ -0,0 +1,129 @@
|
||||
// Spoken ack — the other half of the snooze wire. "готово" said out loud
|
||||
// resolves a live nudge as `acted`, and a fact that answers the nudge on its
|
||||
// own ("выпил воды" after the water rule fired) closes it without him having
|
||||
// to say anything extra.
|
||||
//
|
||||
// Two entry points rather than one, because the two utterances are different
|
||||
// acts. A bare "готово" carries no content and is intercepted before the
|
||||
// router, exactly like the snooze. "выпил воды" IS content: it has to route
|
||||
// normally and write its fact, and only then close the nudge. Folding the
|
||||
// second into a pre-route intercept would have thrown the fact away, which is
|
||||
// the thing he actually said.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// resolveAck — pre-route keyword check for a contentless acknowledgement,
|
||||
// run after the snooze. Same window and same fall-through rule: the words only
|
||||
// count when a nudge is actually live, so "готово" with nothing pending routes
|
||||
// normally.
|
||||
func (h *reactiveHandler) resolveAck(ctx context.Context, text string, src turnSource) (string, bool) {
|
||||
if !classifyAck(text) {
|
||||
return "", false
|
||||
}
|
||||
now := h.now()
|
||||
target, ok := h.pendingNudge(ctx, now)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeActed, now); err != nil {
|
||||
log.Printf("voice: ack nudge %d (%s, %s): %v", target.ID, target.Rule, src, err)
|
||||
return phraser.Ack(phraser.FailAck, nil), true
|
||||
}
|
||||
log.Printf("voice: acked nudge %d (rule %s) from %s", target.ID, target.Rule, src)
|
||||
return phraser.Ack(phraser.AckNudge, nil), true
|
||||
}
|
||||
|
||||
// ackFromFact — post-action hook, called once the turn's decision has been
|
||||
// applied. A fact whose key is the substrate of a live nudge's rule answers
|
||||
// that nudge, so the nudge is resolved `acted` and the auto-tuner learns the
|
||||
// rule is working.
|
||||
//
|
||||
// Silent by design: it returns nothing and never changes the reply. He said
|
||||
// "выпил воды" and the fact reply is what he is owed; "отлично, отметила" on
|
||||
// top would be her congratulating him for obeying, which is the nag she is
|
||||
// explicitly not.
|
||||
//
|
||||
// Best-effort throughout. A failure here loses one feedback signal and must
|
||||
// never turn a written fact into an error the user hears.
|
||||
func (h *reactiveHandler) ackFromFact(ctx context.Context, dec router.Decision) {
|
||||
if dec.Clarify || dec.Intent != router.IntentFact || !dec.Slots.HasKey {
|
||||
return
|
||||
}
|
||||
rules := ackRulesForKey(dec.Slots.Key)
|
||||
if len(rules) == 0 {
|
||||
return
|
||||
}
|
||||
now := h.now()
|
||||
target, ok := h.pendingNudge(ctx, now)
|
||||
if !ok || !rules[target.Rule] {
|
||||
return
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeActed, now); err != nil {
|
||||
log.Printf("voice: ack nudge %d from fact %q: %v", target.ID, dec.Slots.Key, err)
|
||||
return
|
||||
}
|
||||
log.Printf("voice: nudge %d (rule %s) acked by fact %q", target.ID, target.Rule, dec.Slots.Key)
|
||||
}
|
||||
|
||||
// ackRulesForKey — which rules a fact under this key answers.
|
||||
//
|
||||
// Derived from each rule's InertWhenNoData rather than written out as a map,
|
||||
// so a rule added later is covered the day it lands. That field already names
|
||||
// the substrate the rule reads; a fresh fact under one of those keys is by
|
||||
// definition the thing the rule was complaining about the absence of.
|
||||
//
|
||||
// DefaultRules, not the daemon's wired set: a rule disabled in config cannot
|
||||
// have a pending nudge to close anyway, and reading the canonical set here
|
||||
// keeps this free of the config plumbing.
|
||||
func ackRulesForKey(key string) map[string]bool {
|
||||
if key == "" {
|
||||
return nil
|
||||
}
|
||||
var out map[string]bool
|
||||
for _, r := range loop.DefaultRules() {
|
||||
for _, k := range r.InertWhenNoData {
|
||||
if k != key {
|
||||
continue
|
||||
}
|
||||
if out == nil {
|
||||
out = map[string]bool{}
|
||||
}
|
||||
out[r.Name] = true
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// ackPhrases — the acknowledgement vocabulary, as stem sequences. Matched by
|
||||
// quietPhrase (quiet_toggle.go), so a single-word pattern matches only a
|
||||
// single-word utterance.
|
||||
//
|
||||
// "да" and "ок" are deliberately absent. Both are answers to a question she
|
||||
// asked, and the clarify gate upstream (resolveClarifyAnswer) has the stronger
|
||||
// claim on them; letting them close a nudge as well would mean a stray "да"
|
||||
// silently rewrites the feedback the auto-tuner learns from.
|
||||
var ackPhrases = [][]string{
|
||||
{"готово"}, {"сделал"}, {"сделано"}, {"выполнил"}, {"уже"},
|
||||
{"уже", "сделал"}, {"уже", "готово"}, {"всё", "сделал"},
|
||||
{"done"}, {"already", "did"},
|
||||
}
|
||||
|
||||
// classifyAck reads an utterance as a contentless acknowledgement.
|
||||
func classifyAck(text string) bool {
|
||||
tokens := quietTokens(text)
|
||||
for _, p := range ackPhrases {
|
||||
if quietPhrase(tokens, p) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
@@ -0,0 +1,109 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func TestClassifyAck(t *testing.T) {
|
||||
for _, s := range []string{
|
||||
"готово", "сделал", "сделано", "выполнил", "уже",
|
||||
"уже сделал", "всё сделал", "done",
|
||||
} {
|
||||
if !classifyAck(s) {
|
||||
t.Errorf("classifyAck(%q) = false, want true", s)
|
||||
}
|
||||
}
|
||||
for _, s := range []string{
|
||||
// "да" and "ок" belong to the clarify gate, not to the nudge.
|
||||
"да", "ок", "хорошо",
|
||||
// A single-word pattern must not eat the sentence it appears in.
|
||||
"сделал бэкап базы", "готово ли обновление", "уже поздно",
|
||||
"напомни завтра позвонить маме", "",
|
||||
} {
|
||||
if classifyAck(s) {
|
||||
t.Errorf("classifyAck(%q) = true, want false", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveAckMarksTheNudgeActed(t *testing.T) {
|
||||
h, api := snoozeHandler([]ipc.Nudge{pendingNudgeAt(6, 2*time.Minute)})
|
||||
reply, handled := h.resolveAck(context.Background(), "готово", sourceVoice)
|
||||
if !handled || reply == "" {
|
||||
t.Fatalf("got (%q, %v), want a reply", reply, handled)
|
||||
}
|
||||
if api.gotID != 6 || api.gotOutcome != store.NudgeActed {
|
||||
t.Fatalf("resolved (%d, %q), want (6, %q)", api.gotID, api.gotOutcome, store.NudgeActed)
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveAckFallsThroughWithNothingPending(t *testing.T) {
|
||||
h, api := snoozeHandler(nil)
|
||||
if reply, handled := h.resolveAck(context.Background(), "готово", sourceVoice); handled || reply != "" {
|
||||
t.Fatalf("got (%q, %v), want fall-through", reply, handled)
|
||||
}
|
||||
if api.calls != 0 {
|
||||
t.Fatalf("resolved a nudge with nothing pending")
|
||||
}
|
||||
}
|
||||
|
||||
func TestAckRulesForKey(t *testing.T) {
|
||||
cases := []struct {
|
||||
key string
|
||||
want string // "" means no rule
|
||||
}{
|
||||
{"water", "water"},
|
||||
{"meal", "meal"},
|
||||
{"break", "break"},
|
||||
{"desk_active", "break"},
|
||||
{"weight", ""},
|
||||
{"", ""},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
got := ackRulesForKey(tc.key)
|
||||
if tc.want == "" {
|
||||
if len(got) != 0 {
|
||||
t.Errorf("ackRulesForKey(%q) = %v, want none", tc.key, got)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if !got[tc.want] {
|
||||
t.Errorf("ackRulesForKey(%q) = %v, want %q in it", tc.key, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestAckFromFactClosesTheMatchingNudge(t *testing.T) {
|
||||
h, api := snoozeHandler([]ipc.Nudge{pendingNudgeAt(11, time.Minute)}) // rule "water"
|
||||
h.ackFromFact(context.Background(), router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Slots: router.Slots{Key: "water", HasKey: true},
|
||||
})
|
||||
if api.gotID != 11 || api.gotOutcome != store.NudgeActed {
|
||||
t.Fatalf("resolved (%d, %q), want (11, %q)", api.gotID, api.gotOutcome, store.NudgeActed)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAckFromFactIgnoresAnUnrelatedFact(t *testing.T) {
|
||||
// The live nudge is "water"; a meal fact does not answer it. Closing it
|
||||
// anyway would tell the auto-tuner the water rule works when he ignored it.
|
||||
h, api := snoozeHandler([]ipc.Nudge{pendingNudgeAt(12, time.Minute)})
|
||||
for _, dec := range []router.Decision{
|
||||
{Intent: router.IntentFact, Slots: router.Slots{Key: "meal", HasKey: true}},
|
||||
{Intent: router.IntentFact, Slots: router.Slots{Key: "weight", HasKey: true}},
|
||||
{Intent: router.IntentFact}, // no key
|
||||
{Intent: router.IntentQuery, Slots: router.Slots{Key: "water", HasKey: true}},
|
||||
{Intent: router.IntentFact, Slots: router.Slots{Key: "water", HasKey: true}, Clarify: true},
|
||||
} {
|
||||
h.ackFromFact(context.Background(), dec)
|
||||
}
|
||||
if api.calls != 0 {
|
||||
t.Fatalf("resolved %d nudge(s) on unrelated decisions", api.calls)
|
||||
}
|
||||
}
|
||||
+10
-2
@@ -40,6 +40,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -57,11 +58,18 @@ var actionHandlers = map[router.Intent]func(*reactiveHandler, context.Context, r
|
||||
func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) string {
|
||||
// Conversational: build history from dialogue session (prior user turns)
|
||||
// and let the LLM respond from general knowledge + context.
|
||||
history := h.chatHistory()
|
||||
if h.phraser == nil {
|
||||
return "поговорили."
|
||||
}
|
||||
history := h.chatHistory(ctx)
|
||||
// The phraser hands back its own fallback text alongside the error, so the
|
||||
// turn survives a dead server and the failure still reaches the log.
|
||||
reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
|
||||
if err != nil {
|
||||
log.Printf("voice: chat: %v", err)
|
||||
return "поговорили."
|
||||
}
|
||||
if reply == "" {
|
||||
return phraser.ChatFallback()
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/mcp"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
)
|
||||
@@ -50,31 +51,37 @@ func (h *reactiveHandler) actionAct(ctx context.Context, dec router.Decision) st
|
||||
// destructive: park it and ask. The next utterance answers.
|
||||
phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
|
||||
h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
|
||||
return "выполнить «" + phrase + "»? скажи «да» или «нет»."
|
||||
return phraser.A(phraser.ActConfirm, map[string]string{"name": phrase})
|
||||
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,
|
||||
// the fuzzy allowlist match — is a guess, and a spoken "да" checks
|
||||
// none of it. She names the gap instead.
|
||||
return phraser.A(phraser.ActNeedsAuthedSurface, nil)
|
||||
case errors.Is(err, tool.ErrNotEnabled):
|
||||
return h.proposeGap(ctx, dec)
|
||||
case errors.Is(err, tool.ErrNotConnected), errors.Is(err, mcp.ErrNotConnected), errors.Is(err, mcp.ErrNoServer):
|
||||
// The row is enabled and the backend is gone. Drafting a proposal
|
||||
// for it (the ErrNotEnabled path) would be answering the wrong
|
||||
// question.
|
||||
return "этот инструмент включён, но сервер, который его выполняет, сейчас не подключён."
|
||||
return phraser.A(phraser.ActServerDown, nil)
|
||||
case errors.Is(err, mcp.ErrToolGone):
|
||||
return "сервер больше не предлагает этот инструмент — я сняла его с разрешённых, посмотри на /tools."
|
||||
return phraser.A(phraser.ActWithdrawn, nil)
|
||||
case errors.Is(err, mcp.ErrNeedsArgs):
|
||||
// An MCP tool that wants named arguments a spoken verb cannot
|
||||
// supply. Guessing them would be a wrong act, so she says so
|
||||
// instead — the tool is still runnable from the authed surface,
|
||||
// where a human types them.
|
||||
return "этому инструменту нужны аргументы, которые я из голоса не соберу — я не буду угадывать."
|
||||
return phraser.A(phraser.ActNeedsArgs, nil)
|
||||
}
|
||||
log.Printf("voice: tool %s: %v", dec.Slots.Fn, err)
|
||||
if out != "" {
|
||||
return "не получилось выполнить команду: " + firstLine(out)
|
||||
return phraser.A(phraser.ActFailOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "не получилось выполнить команду."
|
||||
return phraser.A(phraser.ActFail, nil)
|
||||
}
|
||||
if out != "" {
|
||||
return "готово: " + firstLine(out)
|
||||
return phraser.A(phraser.ActDoneOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "готово."
|
||||
return phraser.A(phraser.ActDone, nil)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The act path speaks each tier (Vikunja #449): a safe row runs, a destructive
|
||||
// one costs a confirm turn, an irreversible one is refused with the reason.
|
||||
func TestActPathSpeaksTheTiers(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
now := h.now()
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
cmd []string
|
||||
destructive bool
|
||||
}{
|
||||
{"status", []string{"true"}, false},
|
||||
{"restart", []string{"true"}, true},
|
||||
{"wipe", []string{"rm", "-rf"}, true},
|
||||
} {
|
||||
if _, err := st.ProposeTool(ctx, tc.name, "test", "homelab", now); err != nil {
|
||||
t.Fatalf("propose %s: %v", tc.name, err)
|
||||
}
|
||||
if err := st.EnableTool(ctx, tc.name, tc.cmd, tc.destructive, "homelab", now); err != nil {
|
||||
t.Fatalf("enable %s: %v", tc.name, err)
|
||||
}
|
||||
}
|
||||
|
||||
act := func(fn string) string {
|
||||
return h.actionAct(ctx, router.Decision{
|
||||
Intent: router.IntentAct,
|
||||
Utterance: fn,
|
||||
Slots: router.Slots{Fn: fn, HasFn: true},
|
||||
})
|
||||
}
|
||||
|
||||
if reply := act("status"); !strings.HasPrefix(reply, "готово") {
|
||||
t.Errorf("safe act replied %q; want it to have run", reply)
|
||||
}
|
||||
// PR 112's review cut «скажи «да» или «нет».» — he knows how to answer a
|
||||
// yes/no question — so the confirm turn is recognised by the question.
|
||||
if reply := act("restart"); !strings.Contains(reply, "да или нет") {
|
||||
t.Errorf("destructive act replied %q; want a confirm turn", reply)
|
||||
}
|
||||
// Clear the confirm the destructive act parked, so what is pending after
|
||||
// the irreversible one is only what the irreversible one parked.
|
||||
h.mu.Lock()
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
|
||||
reply := act("wipe")
|
||||
if strings.Contains(reply, "да или нет") {
|
||||
t.Fatalf("irreversible act asked for a confirm: %q", reply)
|
||||
}
|
||||
if !strings.Contains(reply, "не вернуть") {
|
||||
t.Errorf("irreversible act replied %q; want it to name the reason", reply)
|
||||
}
|
||||
// Nothing was parked, so a later "да" cannot pick it up.
|
||||
h.mu.Lock()
|
||||
pending := h.pending
|
||||
h.mu.Unlock()
|
||||
if pending != nil {
|
||||
t.Errorf("an irreversible act parked %+v", pending)
|
||||
}
|
||||
// And it is still an enabled row — refusing to run it from voice is not
|
||||
// the same as taking it off the allowlist.
|
||||
if got, err := st.LookupTool(ctx, "wipe"); err != nil || got.Status != "enabled" {
|
||||
t.Errorf("wipe is %+v, %v; want it still enabled", got, err)
|
||||
}
|
||||
}
|
||||
+105
-18
@@ -6,23 +6,68 @@ import (
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// actionFact handles router.IntentFact: persist a tapped self-fact, index
|
||||
// it for recall, and let pattern detection propose a routine.
|
||||
func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) string {
|
||||
if !dec.Slots.HasKey {
|
||||
return "не разобрала, что записать — попробуй иначе."
|
||||
return phraser.Ack(phraser.FailFactUnparsed, nil)
|
||||
}
|
||||
// A question is never a fact about him (#470). "какая последняя версия
|
||||
// языка Go?" used to land here, and the value stored was whatever the
|
||||
// model invented for it, at confidence 1.00, indexed for recall under the
|
||||
// question's own text. Two such rows then claimed seven unrelated world
|
||||
// questions through recall and silently disabled world answering.
|
||||
//
|
||||
// The routing error itself is not fixed here — the answer is to answer.
|
||||
// Sending the turn down the query chain is what he asked for anyway, and
|
||||
// it costs a mis-routed capture nothing: an explicit "запиши ..." is not
|
||||
// question-shaped, so it never takes this branch.
|
||||
if router.IsQuestionShaped(dec.Utterance) {
|
||||
log.Printf("voice: fact write refused, utterance is a question: %q (key %q) — answering as a query",
|
||||
dec.Utterance, dec.Slots.Key)
|
||||
q := dec
|
||||
q.Intent = router.IntentQuery
|
||||
// The key the model extracted is its guess at what to store, not a
|
||||
// fact he has. Left in place, queryFactByKey would read it back and
|
||||
// claim the turn before any real source ran.
|
||||
q.Slots.Key, q.Slots.HasKey = "", false
|
||||
q.Slots.Value = ""
|
||||
return h.actionQuery(ctx, q)
|
||||
}
|
||||
// A complaint is not a fact either (#481). "сеть какая-то медленная" and
|
||||
// "интернет не работает" were stored as `self` rows at confidence 1.00, and
|
||||
// recall reads a self row back later as if it were still true — the same
|
||||
// class of row that outranked live search in #470. The sentence describes a
|
||||
// moment, so she answers it and stores nothing. An explicit "запомни ..."
|
||||
// and anything about him are both left alone by the test.
|
||||
if router.IsTransientComplaint(dec.Utterance) {
|
||||
log.Printf("voice: fact write refused, utterance is a passing complaint: %q (key %q) — answering as chat",
|
||||
dec.Utterance, dec.Slots.Key)
|
||||
c := dec
|
||||
c.Intent = router.IntentChat
|
||||
c.Slots.Key, c.Slots.HasKey = "", false
|
||||
c.Slots.Value = ""
|
||||
return h.actionChat(ctx, c)
|
||||
}
|
||||
now := h.now()
|
||||
req := ipc.WriteFactReq{
|
||||
Ts: now,
|
||||
Kind: "self",
|
||||
Key: dec.Slots.Key,
|
||||
Value: dec.Slots.Value,
|
||||
Source: "tap:voice",
|
||||
Confidence: 1.0,
|
||||
Ts: now,
|
||||
Kind: "self",
|
||||
Key: dec.Slots.Key,
|
||||
Value: dec.Slots.Value,
|
||||
Source: "tap:voice",
|
||||
// Not 1.00 unconditionally any more (#470). A value he said is
|
||||
// evidence; a value the model supplied for words he never said is a
|
||||
// guess, and writing a guess at full confidence is the same mistake
|
||||
// the act path already refuses under "LLM output is not
|
||||
// authorization".
|
||||
Confidence: factConfidence(dec.Utterance, dec.Slots.Value),
|
||||
// Subject: the key doubles as the entity-resolution candidate —
|
||||
// a voice-tapped fact's key is usually the thing/person it's
|
||||
// about ("espresso_machine", "kate"), so queueing it for Nexus
|
||||
@@ -34,19 +79,35 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
|
||||
factID, err := h.api.WriteFact(ctx, req)
|
||||
if err != nil {
|
||||
log.Printf("voice: write fact: %v", err)
|
||||
return "не получилось сохранить факт."
|
||||
return phraser.Ack(phraser.FailFact, nil)
|
||||
}
|
||||
// Index the fact utterance in long-term memory (best-effort, must not
|
||||
// fail the fact write). Facts aren't in the notes table, so this is the
|
||||
// only recall path for them — "когда я пил воду?" reads back from here.
|
||||
if h.memStore != nil {
|
||||
if vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance); err != nil {
|
||||
// Index the fact in long-term memory (best-effort, must not fail the fact
|
||||
// write). Facts aren't in the notes table, so this is the only recall path
|
||||
// for them — "когда я пил воду?" reads back from here.
|
||||
//
|
||||
// The indexed text is the fact, not the utterance (#493). queryMemory
|
||||
// returns a fact's stored text verbatim, so what goes in here is what he
|
||||
// hears; storing the utterance meant recall answered with his own sentence
|
||||
// rather than the value. The utterance stays alongside as provenance —
|
||||
// readable on /trace, never the answer and never embedded.
|
||||
//
|
||||
// The vector id carries a timestamp, so a second tap of the same key adds a
|
||||
// row rather than replacing one, and recall then scores the superseded
|
||||
// value against the current one. CorrectValue and VoidLatestFact already
|
||||
// drop the key's vectors; an ordinary re-tap is the third way a value is
|
||||
// superseded and it did not (#493). Dropping first keeps exactly one vector
|
||||
// per key, which is what "recall answers with the current value" means.
|
||||
if h.recall.memStore != nil {
|
||||
pruneFactVectors(ctx, h.recall.memStore, dec.Slots.Key)
|
||||
text := store.FactRecallText(dec.Slots.Key, dec.Slots.Value)
|
||||
if vec, err := router.EmbedPassage(ctx, h.recall.embedder, text); err != nil {
|
||||
log.Printf("voice: embed fact for memory: %v", err)
|
||||
} else if err := h.memStore.Insert(ctx, "fact:"+dec.Slots.Key+":"+strconv.FormatInt(now.Unix(), 10), vec, map[string]string{
|
||||
"source": "voice",
|
||||
"type": "fact",
|
||||
"text": dec.Utterance,
|
||||
"ts": strconv.FormatInt(now.Unix(), 10),
|
||||
} else if err := h.recall.memStore.Insert(ctx, "fact:"+dec.Slots.Key+":"+strconv.FormatInt(now.Unix(), 10), vec, map[string]string{
|
||||
"source": "voice",
|
||||
"type": "fact",
|
||||
"text": text,
|
||||
"utterance": dec.Utterance,
|
||||
"ts": strconv.FormatInt(now.Unix(), 10),
|
||||
}); err != nil {
|
||||
log.Printf("voice: memory insert fact: %v", err)
|
||||
}
|
||||
@@ -62,3 +123,29 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
|
||||
}
|
||||
return "" // replier phrases the success reply
|
||||
}
|
||||
|
||||
// vectorPruner — the part of the vector index this file needs and memory.Store
|
||||
// does not carry. store.MemoryStore implements it; the in-memory test double
|
||||
// may not, and a double that cannot prune is not a reason to fail a fact write.
|
||||
type vectorPruner interface {
|
||||
DeletePrefix(ctx context.Context, prefix string) (int64, error)
|
||||
}
|
||||
|
||||
// pruneFactVectors drops every vector for one fact key, so the insert that
|
||||
// follows is the only one left. Best-effort and silent on a store that cannot
|
||||
// prune: the fact row is the truth, and a stale vector costs a wrong recall,
|
||||
// not a lost fact.
|
||||
func pruneFactVectors(ctx context.Context, ms memory.Store, key string) {
|
||||
p, ok := ms.(vectorPruner)
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
n, err := p.DeletePrefix(ctx, "fact:"+key+":")
|
||||
if err != nil {
|
||||
log.Printf("voice: prune memory vectors for %q: %v", key, err)
|
||||
return
|
||||
}
|
||||
if n > 0 {
|
||||
log.Printf("voice: %q superseded, dropped %d stale memory vector(s)", key, n)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,143 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// Standing lists on the voice path (Vikunja #453).
|
||||
//
|
||||
// Three halves, mirroring what task capture already does: an add that runs at
|
||||
// the top of actionNote, a read-back query source, and a crossing-off that runs
|
||||
// on the same note path because "всё купил" is note-shaped.
|
||||
//
|
||||
// These read h.dataStore rather than the CoreAPI. A list is local to the core
|
||||
// and nothing outside it writes one: the web UI has no list page, no reach
|
||||
// files groceries, and the digestion worker does not read the table. When
|
||||
// something outside mavend needs to add to a list, the ipc seam is what it
|
||||
// grows through — the intake rules that CaptureTaskReq documents are about
|
||||
// shared intake, and there is none here yet.
|
||||
//
|
||||
// Nothing here speaks unprompted. A list is answered when asked about.
|
||||
|
||||
// captureListFromNote claims the turn when the utterance adds to, clears, or
|
||||
// crosses one item off a list. ("", false) hands the turn back to the note path.
|
||||
func (h *reactiveHandler) captureListFromNote(ctx context.Context, dec router.Decision) (string, bool) {
|
||||
if h.dataStore == nil {
|
||||
return "", false
|
||||
}
|
||||
// Clearing is read before removing on purpose: "всё купил" and "купил
|
||||
// молоко" start with the same word, and only the second one names an item.
|
||||
if list, ok := router.ParseListClear(dec.Utterance); ok {
|
||||
n, err := h.dataStore.ClearList(ctx, list, h.now())
|
||||
if err != nil {
|
||||
log.Printf("voice: clear list: %v", err)
|
||||
return "не получилось обновить список.", true
|
||||
}
|
||||
if n == 0 {
|
||||
return "в списке и так ничего не было.", true
|
||||
}
|
||||
return "вычеркнула всё, список пустой.", true
|
||||
}
|
||||
if cap, ok := router.ParseListRemove(dec.Utterance); ok {
|
||||
if reply, ok := h.removeListItem(ctx, cap); ok {
|
||||
return reply, true
|
||||
}
|
||||
// Nothing on the list by that name. "купил новый ноутбук" is a note and
|
||||
// must stay one, so the turn goes back rather than claiming a removal
|
||||
// that removed nothing.
|
||||
return "", false
|
||||
}
|
||||
cap, ok := router.ParseListCapture(dec.Utterance)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
res, err := h.dataStore.AddListItem(ctx, store.ListItem{
|
||||
List: cap.List,
|
||||
Item: cap.Item,
|
||||
Source: "tap:voice",
|
||||
CreatedTs: h.now(),
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: add list item: %v", err)
|
||||
return "не получилось добавить в список.", true
|
||||
}
|
||||
if !res.Created {
|
||||
return cap.Item + " уже в списке.", true
|
||||
}
|
||||
return "добавила в список: " + cap.Item + ".", true
|
||||
}
|
||||
|
||||
// removeListItem crosses one named item off. It reports false when the list
|
||||
// holds nothing by that name, which is what keeps the marker words from
|
||||
// swallowing ordinary notes.
|
||||
func (h *reactiveHandler) removeListItem(ctx context.Context, cap router.ListCapture) (string, bool) {
|
||||
items, err := h.dataStore.ListItems(ctx, cap.List, "")
|
||||
if err != nil {
|
||||
log.Printf("voice: list items: %v", err)
|
||||
return "", false
|
||||
}
|
||||
want := store.NormalizeTaskText(cap.Item)
|
||||
for _, li := range items {
|
||||
if store.NormalizeTaskText(li.Item) != want {
|
||||
continue
|
||||
}
|
||||
if err := h.dataStore.SetListItemStatus(ctx, li.ID, store.ListItemDone, h.now()); err != nil {
|
||||
log.Printf("voice: cross off list item: %v", err)
|
||||
return "не получилось обновить список.", true
|
||||
}
|
||||
return "вычеркнула: " + li.Item + ".", true
|
||||
}
|
||||
return "", false
|
||||
}
|
||||
|
||||
// queryList — "что в списке покупок?", "что мне купить?".
|
||||
//
|
||||
// A query source, so it sits in querySources and either claims the turn or
|
||||
// passes it on. It is before the recall sources for the reason every specific
|
||||
// source is: the notes pass would otherwise answer a list question with
|
||||
// whatever note is nearest.
|
||||
func (h *reactiveHandler) queryList(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
list, ok := router.ParseListQuery(t.dec.Utterance)
|
||||
if !ok || h.dataStore == nil {
|
||||
return "", false
|
||||
}
|
||||
items, err := h.dataStore.ListItems(ctx, list, "")
|
||||
if err != nil {
|
||||
log.Printf("voice: list items: %v", err)
|
||||
return "не получилось посмотреть список.", true
|
||||
}
|
||||
return formatListRU(list, items), true
|
||||
}
|
||||
|
||||
// formatListRU reads a list aloud. One sentence, comma-separated, because a
|
||||
// shopping list is heard in a shop and a numbered recital is unusable there.
|
||||
func formatListRU(list string, items []store.ListItem) string {
|
||||
name := "списке " + listGenitive(list)
|
||||
if len(items) == 0 {
|
||||
return "в " + name + " пусто."
|
||||
}
|
||||
names := make([]string, 0, len(items))
|
||||
for _, li := range items {
|
||||
names = append(names, li.Item)
|
||||
}
|
||||
return "в " + name + ": " + strings.Join(names, ", ") + "."
|
||||
}
|
||||
|
||||
// listGenitive puts a list tag into the case "список <…>" needs. Russian
|
||||
// declines the noun and she must not say "в списке покупки".
|
||||
func listGenitive(list string) string {
|
||||
switch list {
|
||||
case "покупки":
|
||||
return "покупок"
|
||||
case "аптека":
|
||||
return "аптеки"
|
||||
case "хозяйство":
|
||||
return "хозяйства"
|
||||
}
|
||||
return list
|
||||
}
|
||||
@@ -0,0 +1,184 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func listNow() time.Time { return time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC) }
|
||||
|
||||
func listHandler(t *testing.T) *reactiveHandler {
|
||||
t.Helper()
|
||||
return &reactiveHandler{dataStore: newTestStore(t), now: listNow}
|
||||
}
|
||||
|
||||
func askList(t *testing.T, h *reactiveHandler, utterance string) (string, bool) {
|
||||
t.Helper()
|
||||
return h.captureListFromNote(context.Background(), router.Decision{
|
||||
Intent: router.IntentNote, Utterance: utterance,
|
||||
})
|
||||
}
|
||||
|
||||
func TestListCaptureAddsAndReadsBack(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{"добавь в список покупок молоко", "добавь в список хлеб"} {
|
||||
if reply, ok := askList(t, h, u); !ok {
|
||||
t.Fatalf("%q was not claimed (reply %q)", u, reply)
|
||||
}
|
||||
}
|
||||
if reply, ok := askList(t, h, "добавь в список покупок молоко"); !ok || !strings.Contains(reply, "уже") {
|
||||
t.Errorf("second молоко replied %q, %v; want an already-there answer", reply, ok)
|
||||
}
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что в списке покупок?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("the list question was not claimed")
|
||||
}
|
||||
if !strings.Contains(answer, "молоко") || !strings.Contains(answer, "хлеб") {
|
||||
t.Errorf("answer %q; want both items", answer)
|
||||
}
|
||||
if strings.Contains(answer, "списке покупки") {
|
||||
t.Errorf("answer %q declines the list name wrong", answer)
|
||||
}
|
||||
}
|
||||
|
||||
// An utterance with no list marker is a note and must stay one, whichever half
|
||||
// of the parser it brushes against.
|
||||
func TestListCapturePassesOrdinaryNotes(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{
|
||||
"молоко закончилось",
|
||||
"надо бы съездить в магазин",
|
||||
"купил новый ноутбук",
|
||||
"добавь в список покупок",
|
||||
} {
|
||||
if reply, ok := askList(t, h, u); ok {
|
||||
t.Errorf("%q was claimed as a list turn: %q", u, reply)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestListCrossOffOneItemAndThenAll(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{
|
||||
"добавь в список покупок молоко",
|
||||
"добавь в список покупок хлеб",
|
||||
"добавь в список аптеки бинт",
|
||||
} {
|
||||
if _, ok := askList(t, h, u); !ok {
|
||||
t.Fatalf("%q was not claimed", u)
|
||||
}
|
||||
}
|
||||
reply, ok := askList(t, h, "вычеркни молоко")
|
||||
if !ok || !strings.Contains(reply, "молоко") {
|
||||
t.Fatalf("cross off replied %q, %v", reply, ok)
|
||||
}
|
||||
open, err := h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(open) != 1 || open[0].Item != "хлеб" {
|
||||
t.Fatalf("open list %+v; want only хлеб", open)
|
||||
}
|
||||
if reply, ok := askList(t, h, "всё купил"); !ok || !strings.Contains(reply, "пустой") {
|
||||
t.Errorf("clear replied %q, %v", reply, ok)
|
||||
}
|
||||
open, err = h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(open) != 0 {
|
||||
t.Errorf("%d items still open after всё купил", len(open))
|
||||
}
|
||||
// The other list is untouched, and it is read back on its own.
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "покажи список аптеки"},
|
||||
})
|
||||
if !ok || !strings.Contains(answer, "бинт") {
|
||||
t.Errorf("аптека answer %q, %v; want бинт", answer, ok)
|
||||
}
|
||||
}
|
||||
|
||||
func TestQueryListSaysWhenItIsEmpty(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что мне купить?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("the list question was not claimed")
|
||||
}
|
||||
if !strings.Contains(answer, "пусто") {
|
||||
t.Errorf("empty answer %q; want it to say so", answer)
|
||||
}
|
||||
if _, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "какие у меня задачи?"},
|
||||
}); ok {
|
||||
t.Error("the list source claimed a task question")
|
||||
}
|
||||
}
|
||||
|
||||
// Stage 0 answers a list turn without the model: the grammars route it, and the
|
||||
// action handlers re-parse what the grammar matched.
|
||||
func TestListGrammarsRouteWithoutTheModel(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want router.Intent
|
||||
}{
|
||||
{"добавь в список покупок молоко", router.IntentNote},
|
||||
{"что в списке покупок?", router.IntentQuery},
|
||||
{"всё купил", router.IntentNote},
|
||||
}
|
||||
for _, c := range cases {
|
||||
var got router.Intent
|
||||
claimed := false
|
||||
for _, g := range router.ListGrammars() {
|
||||
m := g.Pattern.FindStringSubmatch(c.utterance)
|
||||
if m == nil {
|
||||
continue
|
||||
}
|
||||
if dec, ok := g.Build(m); ok {
|
||||
got, claimed = dec.Intent, true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !claimed {
|
||||
t.Errorf("no list grammar claimed %q", c.utterance)
|
||||
continue
|
||||
}
|
||||
if got != c.want {
|
||||
t.Errorf("%q routed to %v; want %v", c.utterance, got, c.want)
|
||||
}
|
||||
}
|
||||
for _, g := range router.ListGrammars() {
|
||||
m := g.Pattern.FindStringSubmatch("напомни купить молоко завтра")
|
||||
if m == nil {
|
||||
continue
|
||||
}
|
||||
if _, ok := g.Build(m); ok {
|
||||
t.Errorf("grammar %s claimed a reminder", g.Name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestListStoreSourceIsVoice(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
if _, ok := askList(t, h, "добавь в список покупок молоко"); !ok {
|
||||
t.Fatal("not claimed")
|
||||
}
|
||||
items, err := h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(items) != 1 || items[0].Source != "tap:voice" {
|
||||
t.Errorf("stored %+v; want one row from tap:voice", items)
|
||||
}
|
||||
if items[0].Status != store.ListItemOpen {
|
||||
t.Errorf("status %q; want open", items[0].Status)
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"log"
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -17,24 +18,30 @@ func (h *reactiveHandler) actionNote(ctx context.Context, dec router.Decision) s
|
||||
if reply, ok := h.captureTaskFromNote(ctx, dec); ok {
|
||||
return reply
|
||||
}
|
||||
// A standing list is neither work nor recall (Vikunja #453). Checked here
|
||||
// for the same reason and at the same cost: before the embedding is paid
|
||||
// for, and it passes the turn straight back when no marker matches.
|
||||
if reply, ok := h.captureListFromNote(ctx, dec); ok {
|
||||
return reply
|
||||
}
|
||||
// embed the note text with the same model the classifier uses, persist
|
||||
// via CoreAPI (source=tap:voice). Semantic recall lives in `notes`, not
|
||||
// facts — no predicate reads it (spec's two-memory split).
|
||||
vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance)
|
||||
vec, err := router.EmbedPassage(ctx, h.recall.embedder, dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
noteTs := h.now()
|
||||
noteID, err := h.api.WriteNote(ctx, noteTs, dec.Utterance, vec, "tap:voice")
|
||||
if err != nil {
|
||||
log.Printf("voice: write note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
// Insert into long-term memory (best-effort, must not fail the note write).
|
||||
// text/ts in the meta make a Search hit self-describing (see bestRecall).
|
||||
if h.memStore != nil {
|
||||
if err := h.memStore.Insert(ctx, "note:"+strconv.FormatInt(noteID, 10), vec, map[string]string{
|
||||
if h.recall.memStore != nil {
|
||||
if err := h.recall.memStore.Insert(ctx, "note:"+strconv.FormatInt(noteID, 10), vec, map[string]string{
|
||||
"source": "voice",
|
||||
"type": "note",
|
||||
"text": dec.Utterance,
|
||||
|
||||
+444
-72
@@ -5,13 +5,16 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"regexp"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/crawl"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/morning"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/rss"
|
||||
"github.com/kami/maven/internal/store"
|
||||
@@ -41,6 +44,20 @@ type queryTurn struct {
|
||||
type querySource struct {
|
||||
name string
|
||||
answer func(*reactiveHandler, context.Context, *queryTurn) (string, bool)
|
||||
// dateAware — this source reads the day out of the turn and answers for
|
||||
// THAT day. Only such a source may claim a continuation ("а завтра?"),
|
||||
// because a continuation is a question about a different day and nothing
|
||||
// else. A date-blind source claiming one would answer with today's data
|
||||
// under tomorrow's question, which is a wrong answer delivered in a
|
||||
// confident voice — the failure mode that took reminder out of
|
||||
// continuableIntents (continuation.go).
|
||||
//
|
||||
// Exactly one source qualifies today, and that is not an oversight in the
|
||||
// table: CalendarEvents is the only CoreAPI call that takes a date at all.
|
||||
// DayPlan is today-only, CurrentWeather is now-only, and the recall
|
||||
// sources search text with no notion of a day. When one of them grows a
|
||||
// date parameter, flip its flag here.
|
||||
dateAware bool
|
||||
}
|
||||
|
||||
// querySources is the ordered chain actionQuery walks; first source to claim
|
||||
@@ -49,69 +66,116 @@ 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{
|
||||
{"fact-by-key", (*reactiveHandler).queryFactByKey},
|
||||
{name: "fact-by-key", answer: (*reactiveHandler).queryFactByKey},
|
||||
// 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.
|
||||
{"day-plan", (*reactiveHandler).queryDayPlan},
|
||||
{name: "day-plan", answer: (*reactiveHandler).queryDayPlan},
|
||||
// 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.
|
||||
{"habits", (*reactiveHandler).queryHabits},
|
||||
{name: "habits", answer: (*reactiveHandler).queryHabits},
|
||||
// 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.
|
||||
{"tasks", (*reactiveHandler).queryTasks},
|
||||
{name: "tasks", answer: (*reactiveHandler).queryTasks},
|
||||
// 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.
|
||||
{"money", (*reactiveHandler).queryMoney},
|
||||
// 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},
|
||||
// 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},
|
||||
// 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.
|
||||
{"feeds", (*reactiveHandler).queryFeeds},
|
||||
{name: "feeds", answer: (*reactiveHandler).queryFeeds},
|
||||
// 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.
|
||||
{"home", (*reactiveHandler).queryHome},
|
||||
{name: "home", answer: (*reactiveHandler).queryHome},
|
||||
// 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.
|
||||
{"network", (*reactiveHandler).queryNetwork},
|
||||
{"calendar", (*reactiveHandler).queryCalendar},
|
||||
{"weather", (*reactiveHandler).queryWeather},
|
||||
{"embed", (*reactiveHandler).queryEmbed},
|
||||
{"memory", (*reactiveHandler).queryMemory},
|
||||
{"notes", (*reactiveHandler).queryNotes},
|
||||
{name: "network", answer: (*reactiveHandler).queryNetwork},
|
||||
{name: "calendar", answer: (*reactiveHandler).queryCalendar, dateAware: true},
|
||||
{name: "weather", answer: (*reactiveHandler).queryWeather},
|
||||
{name: "embed", answer: (*reactiveHandler).queryEmbed},
|
||||
{name: "memory", answer: (*reactiveHandler).queryMemory},
|
||||
{name: "notes", answer: (*reactiveHandler).queryNotes},
|
||||
// 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},
|
||||
// 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},
|
||||
// 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},
|
||||
// LAST before the model answers from memory, and that position is the whole
|
||||
// design (Vikunja #259): local sources first. His memory, his notes and —
|
||||
// once internal/kiwix is wired into this chain — the offline ZIMs all get
|
||||
// their turn before anything touches the network. The model does NOT: it
|
||||
// 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
|
||||
// answers after this, because a URL he said out loud is an instruction and
|
||||
// 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.
|
||||
{"web", (*reactiveHandler).queryWeb},
|
||||
{"general-knowledge", (*reactiveHandler).queryGeneral},
|
||||
{name: "web", answer: (*reactiveHandler).queryWeb},
|
||||
{name: "general-knowledge", answer: (*reactiveHandler).queryGeneral},
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision) string {
|
||||
t := &queryTurn{dec: dec}
|
||||
for _, src := range querySources {
|
||||
if dec.Continued && !src.dateAware {
|
||||
continue
|
||||
}
|
||||
if reply, ok := src.answer(h, ctx, t); ok {
|
||||
// Which source claimed is the one thing about a query turn that was
|
||||
// invisible from outside: /trace is the nudge-rule trace and carries
|
||||
// no query-source field, so a wrong answer could not be told from a
|
||||
// wrongly-ordered chain (Vikunja #474). Only the name is logged —
|
||||
// the utterance and the answer are already on the voice lines above
|
||||
// and below this one. The same name goes to the turn's sink when the
|
||||
// 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)
|
||||
return reply
|
||||
}
|
||||
}
|
||||
return "не знаю."
|
||||
if dec.Continued {
|
||||
// The previous question cannot be re-asked for another day. Saying so
|
||||
// beats "не знаю", which reads as "no data for tomorrow" when the
|
||||
// truth is that she never looked.
|
||||
return phraser.Q(phraser.QueryOtherDay, nil)
|
||||
}
|
||||
return phraser.Q(phraser.QueryUnknown, nil)
|
||||
}
|
||||
|
||||
// queryFactByKey — when the dialogue layer resolved an anaphoric reference to
|
||||
@@ -129,11 +193,11 @@ func (h *reactiveHandler) queryFactByKey(ctx context.Context, t *queryTurn) (str
|
||||
if dec.Slots.HasTime {
|
||||
// The query asks about timing — the fact's own timestamp is the
|
||||
// answer it's looking for. Format as a natural reply.
|
||||
return fmt.Sprintf("я записала это %s", formatTime(f.Ts)), true
|
||||
return phraser.Q(phraser.QueryFactWhen, map[string]string{"when": formatTime(f.Ts)}), true
|
||||
}
|
||||
// General fact reference: describe what we know.
|
||||
if dec.Utterance == "" {
|
||||
return fmt.Sprintf("вот что я знаю: %s — %s", dec.Slots.Key, f.Value), true
|
||||
return phraser.Q(phraser.QueryFactValue, map[string]string{"key": dec.Slots.Key, "value": f.Value}), true
|
||||
}
|
||||
// The utterance still carries the question; fall through to normal RAG
|
||||
// with the resolved key in context.
|
||||
@@ -159,7 +223,7 @@ func (h *reactiveHandler) queryDayPlan(ctx context.Context, t *queryTurn) (strin
|
||||
plan, err := h.api.DayPlan(ctx)
|
||||
if err != nil {
|
||||
log.Printf("voice: day plan: %v", err)
|
||||
return "не получилось собрать план.", true
|
||||
return phraser.Q(phraser.QueryFailPlan, nil), true
|
||||
}
|
||||
if !router.IsRestOfDayQuery(t.dec.Utterance) {
|
||||
return plan.Spoken, true
|
||||
@@ -204,7 +268,7 @@ func (h *reactiveHandler) queryHabits(ctx context.Context, t *queryTurn) (string
|
||||
facts, err := h.api.RecentActiveFactsByKind(ctx, string(store.KindSelf), habitFactWindow)
|
||||
if err != nil {
|
||||
log.Printf("voice: habits: recent facts: %v", err)
|
||||
return "не получилось посмотреть записи.", true
|
||||
return phraser.Q(phraser.QueryFailNotes, nil), true
|
||||
}
|
||||
obs := make([]memory.Observation, 0, len(facts))
|
||||
for _, f := range facts {
|
||||
@@ -240,10 +304,18 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
return "", false
|
||||
}
|
||||
if !h.feedsOn {
|
||||
// Claim the turn rather than fall through: "не читаю ленты" is true, and
|
||||
// letting general knowledge answer "что нового?" would be an invented
|
||||
// news bulletin.
|
||||
return "я пока не читаю ленты — они не настроены.", true
|
||||
// Claim only when nothing below can read the world. The reason this
|
||||
// source used to claim unconditionally was that general knowledge would
|
||||
// answer "что нового?" with an invented news bulletin — true, and it
|
||||
// stopped being the only alternative on 2026-08-02, when live search
|
||||
// took the lead. With SearXNG or the ZIMs configured, "что происходит
|
||||
// в новостях про искусственный интеллект?" has a real answer below,
|
||||
// and a configuration status is the wrong thing to say instead
|
||||
// (Vikunja #474).
|
||||
if h.search != nil || h.kiwix != nil {
|
||||
return "", false
|
||||
}
|
||||
return phraser.Q(phraser.QueryFeedsOff, nil), true
|
||||
}
|
||||
// By source, not the last 200 notes of any kind: a busy day of voice notes
|
||||
// used to push the newest headline out of the window, and she answered "в
|
||||
@@ -251,7 +323,7 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
notes, err := h.api.RecentNotesFromSource(ctx, rss.SourcePrefix, feedNoteWindow)
|
||||
if err != nil {
|
||||
log.Printf("voice: feeds: recent notes: %v", err)
|
||||
return "не получилось посмотреть ленты.", true
|
||||
return phraser.Q(phraser.QueryFailFeeds, nil), true
|
||||
}
|
||||
var picked []string
|
||||
for _, n := range notes {
|
||||
@@ -268,17 +340,26 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
}
|
||||
if len(picked) == 0 {
|
||||
if q.Category != "" {
|
||||
return "по этой теме в лентах пока ничего.", true
|
||||
return phraser.Q(phraser.QueryFeedsTopic, nil), true
|
||||
}
|
||||
return "в лентах пока ничего нового.", true
|
||||
return phraser.Q(phraser.QueryFeedsEmpty, nil), true
|
||||
}
|
||||
return "вот что нового: " + strings.Join(picked, "; "), true
|
||||
return phraser.Q(phraser.QueryFeedsNew, map[string]string{"items": strings.Join(picked, "; ")}), true
|
||||
}
|
||||
|
||||
// queryCalendar — "что у меня сегодня?", "планы на завтра?"
|
||||
// h.now(), not time.Now(): the handler's clock is the injected one, so this
|
||||
// source can be tested at a fixed time like the rest.
|
||||
func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
// A day word is all this source matches on, so any question that merely
|
||||
// names a day reached it first. "какая сегодня погода в Москве?" answered
|
||||
// "на 02.08.2026 ничего нет." (Vikunja #474). Weather is asked about a day
|
||||
// far more often than the calendar is, and the weather source sits right
|
||||
// below, so the calendar steps aside on weather wording — the same bail-out
|
||||
// queryHome already does for the same reason.
|
||||
if isWeatherQuery(t.dec.Utterance) {
|
||||
return "", false
|
||||
}
|
||||
date, ok := router.ParseCalendarDate(t.dec.Utterance, h.now())
|
||||
if !ok {
|
||||
return "", false
|
||||
@@ -286,7 +367,7 @@ func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (stri
|
||||
events, err := h.api.CalendarEvents(ctx, date, date.Add(24*time.Hour))
|
||||
if err != nil {
|
||||
log.Printf("voice: calendar events: %v", err)
|
||||
return "не получилось проверить календарь.", true
|
||||
return phraser.Q(phraser.QueryFailCalendar, nil), true
|
||||
}
|
||||
// Provenance travels with each event. A work meeting relayed off a phone
|
||||
// notification (source ambient:notif, #126) is stored below full confidence
|
||||
@@ -303,7 +384,7 @@ func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (stri
|
||||
// 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.
|
||||
func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isHomeQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicHome, isHomeQuery) {
|
||||
return "", false
|
||||
}
|
||||
if h.home == nil {
|
||||
@@ -325,48 +406,61 @@ func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string,
|
||||
// because Scan takes no target — the utterance selects the question, never the
|
||||
// subnet.
|
||||
func (h *reactiveHandler) queryNetwork(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isNetworkQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicNetwork, isNetworkQuery) {
|
||||
return "", false
|
||||
}
|
||||
if h.netscan == nil {
|
||||
// Fall through, same as queryHome: an unconfigured scanner must not
|
||||
// swallow "сколько устройств в сети?" before recall has looked.
|
||||
return "", false
|
||||
// The recogniser already matched, so this is a question about HIS LAN
|
||||
// and there is no scanner to answer it. Falling through sent it to the
|
||||
// search leg, which answered with a paragraph about routers in general
|
||||
// and put his network question on an upstream engine (Vikunja #479).
|
||||
// A missing capability names itself.
|
||||
return phraser.Q(phraser.QueryNetOff, nil), true
|
||||
}
|
||||
return h.netscan.scanSummary(ctx)
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isWeatherQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicWeather, isWeatherQuery) {
|
||||
return "", false
|
||||
}
|
||||
loc := extractWeatherLocation(t.dec.Utterance, h.weatherLocation)
|
||||
if loc == "" {
|
||||
// He named no city and voice.weather.default_location is unset. Saying
|
||||
// so is the only honest answer; picking a city would be inventing one.
|
||||
return "не знаю, для какого города — задай voice.weather.default_location или назови город.", true
|
||||
return phraser.Q(phraser.QueryWeatherWhere, nil), true
|
||||
}
|
||||
ctxWT, cancel := context.WithTimeout(ctx, 5*time.Second)
|
||||
defer cancel()
|
||||
w, err := h.weatherProvider.CurrentWeather(ctxWT, loc)
|
||||
if errors.Is(err, weather.ErrNotConfigured) {
|
||||
return "погода не настроена.", true
|
||||
return phraser.Q(phraser.QueryWeatherOff, nil), true
|
||||
}
|
||||
if errors.Is(err, weather.ErrLocationUnknown) {
|
||||
// He named a place and the geocoder does not have it. Saying so beats
|
||||
// reading out the default city's temperature (Vikunja #421).
|
||||
return "не знаю такого города — " + loc + ".", true
|
||||
}
|
||||
if err != nil {
|
||||
log.Printf("voice: weather: %v", err)
|
||||
return "не получилось узнать погоду.", true
|
||||
return phraser.Q(phraser.QueryFailWeather, nil), true
|
||||
}
|
||||
return fmt.Sprintf("в %s сейчас %.0f градусов, %s.", w.Location, w.Temperature, w.Condition), true
|
||||
return phraser.Q(phraser.QueryWeatherNow, map[string]string{
|
||||
"location": w.Location,
|
||||
"temp": fmt.Sprintf("%.0f", w.Temperature),
|
||||
"word": phraser.Degrees(w.Temperature),
|
||||
"condition": w.Condition,
|
||||
}), true
|
||||
}
|
||||
|
||||
// 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.
|
||||
func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
vec, err := router.EmbedQuery(ctx, h.embedder, t.dec.Utterance)
|
||||
vec, err := router.EmbedQuery(ctx, h.recall.embedder, t.dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed query: %v", err)
|
||||
return "не получилось найти ответ.", true
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
}
|
||||
t.vec = vec
|
||||
return "", false
|
||||
@@ -383,23 +477,37 @@ func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string,
|
||||
// gate, was the bug — the set of questions Maven answers is unchanged, only
|
||||
// which memory gets to answer them.
|
||||
func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if h.memStore == nil {
|
||||
if h.recall.memStore == nil {
|
||||
return "", false
|
||||
}
|
||||
hits, herr := h.memStore.Search(ctx, t.vec, 3)
|
||||
hits, herr := h.recall.memStore.Search(ctx, t.vec, 3)
|
||||
if herr != nil {
|
||||
log.Printf("voice: memory search: %v", herr)
|
||||
return "", false
|
||||
}
|
||||
hit, ok := bestRecall(hits, h.queryMinScore, h.queryMinMargin)
|
||||
hit, ok := bestRecall(hits, h.recall.minScore, h.recall.minMargin)
|
||||
if !ok {
|
||||
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)
|
||||
return "", false
|
||||
}
|
||||
// A note is phrased in Maven's voice; a fact is read back as it was
|
||||
// stored.
|
||||
if hit.Meta["type"] == "note" {
|
||||
if reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
|
||||
reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text})
|
||||
switch {
|
||||
case perr != nil:
|
||||
// Reading the note back verbatim beats the phraser's own fallback,
|
||||
// which only wraps the same text in "вот что я нашла:".
|
||||
log.Printf("voice: recall phrase: %v", perr)
|
||||
case reply != "":
|
||||
return reply, true
|
||||
}
|
||||
}
|
||||
@@ -421,14 +529,20 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
notes, err := h.api.QueryNotes(ctx, t.vec, 5)
|
||||
if err != nil {
|
||||
log.Printf("voice: query notes: %v", err)
|
||||
return "не получилось найти ответ.", true
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
}
|
||||
t.notes = notes
|
||||
noteScores := make([]float64, len(notes))
|
||||
for i, n := range notes {
|
||||
noteScores[i] = n.Score
|
||||
}
|
||||
if !memory.ConfidentScores(noteScores, h.queryMinScore, h.queryMinMargin) {
|
||||
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)
|
||||
return "", false
|
||||
}
|
||||
texts := make([]string, len(notes))
|
||||
@@ -440,7 +554,7 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
log.Printf("voice: phrase query: %v", err)
|
||||
}
|
||||
if reply == "" {
|
||||
reply = "вот что я нашла: " + texts[0]
|
||||
reply = phraser.Q(phraser.QueryFound, map[string]string{"text": texts[0]})
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -462,49 +576,307 @@ func (h *reactiveHandler) queryWeb(ctx context.Context, t *queryTurn) (string, b
|
||||
return "", false
|
||||
}
|
||||
if h.crawler == nil {
|
||||
// Fall through. Reading pages is off unless configured, and on a daemon
|
||||
// where it was never turned on the older behaviour is right: the model
|
||||
// answers the question as if the URL had not been said. Announcing a
|
||||
// configuration status is for a capability that exists and failed, not
|
||||
// for one he never asked for.
|
||||
return "", false
|
||||
// He named a URL, so the question is about that page and nothing else
|
||||
// can answer it. The older comment here argued for falling through and
|
||||
// letting the model answer as if the URL had not been said; that is a
|
||||
// guess dressed as an answer (Vikunja #479).
|
||||
return phraser.Q(phraser.QueryPageOff, nil), true
|
||||
}
|
||||
ctxFetch, cancel := context.WithTimeout(ctx, 30*time.Second)
|
||||
defer cancel()
|
||||
page, err := h.crawler.Page(ctxFetch, link)
|
||||
if err != nil {
|
||||
if errors.Is(err, crawl.ErrRobots) {
|
||||
return "эта страница закрыта для чтения — robots.txt не разрешает.", true
|
||||
return phraser.Q(phraser.QueryPageBlocked, nil), true
|
||||
}
|
||||
log.Printf("voice: web: %v", err)
|
||||
return "не получилось прочитать страницу.", true
|
||||
return phraser.Q(phraser.QueryFailPage, nil), true
|
||||
}
|
||||
if page.Text == "" {
|
||||
return "страница открылась, но читать там нечего.", true
|
||||
return phraser.Q(phraser.QueryPageEmpty, nil), true
|
||||
}
|
||||
// The page is handed to the phraser the same way a note is: as context for
|
||||
// the question he actually asked. She answers the question, she does not
|
||||
// recite the page.
|
||||
snippet := page.Title + "\n" + crawl.TrimRunes(page.Text, webPageContextRunes)
|
||||
reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{snippet})
|
||||
if perr != nil {
|
||||
log.Printf("voice: web: phrase: %v", perr)
|
||||
}
|
||||
reply := h.phraseSource(ctx, "web", t.dec.Utterance, []string{snippet})
|
||||
if reply == "" {
|
||||
// No phraser (or it failed): read back the top of the page rather than
|
||||
// pretend the fetch did not happen.
|
||||
return "вот что на странице: " + crawl.TrimRunes(page.Text, 300), true
|
||||
return phraser.Q(phraser.QueryPageText, map[string]string{"text": crawl.TrimRunes(page.Text, 300)}), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
// queryGeneral — general knowledge from the phraser, the last source before
|
||||
// giving up. It always claims: either the model answers or Maven says she
|
||||
// doesn't know.
|
||||
func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
reply, err := h.phraser.PhraseQuery(ctx, t.dec.Utterance, nil)
|
||||
if err != nil || reply == "" {
|
||||
return "не знаю.", true
|
||||
// kiwixTimeout — the whole ZIM source, rewrite included. The rewrite is one
|
||||
// short constrained completion and the search is a LAN request; if the pair
|
||||
// takes longer than this something is wrong and he is better served by the
|
||||
// model's own answer than by more waiting.
|
||||
const kiwixTimeout = 20 * time.Second
|
||||
|
||||
// searchTimeout — the whole metasearch source. websearch.Client already holds a
|
||||
// per-request timeout from config; this is the outer bound on the turn, so a
|
||||
// hung dial cannot outlive it either. Shorter than kiwixTimeout because there
|
||||
// is no rewrite call in front of it: the question goes out verbatim.
|
||||
const searchTimeout = 12 * time.Second
|
||||
|
||||
// querySearch — the live web, through a self-hosted SearXNG.
|
||||
//
|
||||
// Ahead of Kiwix by the owner's ruling of 2026-08-02: a search reads what is
|
||||
// true today, a ZIM reads what was true when it was built, and the ZIM is the
|
||||
// fallback for a box with no line out. Everything of his still answers first —
|
||||
// the personal boundary is directly above this source, so a question ABOUT him
|
||||
// never becomes a query.
|
||||
//
|
||||
// What leaves this process is the query string and nothing else. His notes, his
|
||||
// facts, the persona block and the history do not travel with it: the websearch
|
||||
// package cannot read the store. That is the CLAUDE.md rule made mechanical,
|
||||
// not a promise about how the prompt is assembled.
|
||||
//
|
||||
// It claims the turn only when the search returns something. An empty result,
|
||||
// an unreachable instance and a 403 from an instance without the JSON format
|
||||
// all fall through to Kiwix, which is the point of the ordering.
|
||||
func (h *reactiveHandler) querySearch(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if h.search == nil {
|
||||
// Off unless configured, same as the crawler and the ZIMs. Nothing is
|
||||
// said about it: he never asked for a capability he did not enable.
|
||||
return "", false
|
||||
}
|
||||
ctxS, cancel := context.WithTimeout(ctx, searchTimeout)
|
||||
defer cancel()
|
||||
|
||||
// Verbatim. No rewriter: SearXNG ranks by meaning through real engines, and
|
||||
// reducing "почему небо голубое" to English keywords would throw away the
|
||||
// language he asked in along with the ranking that handles it.
|
||||
resp, err := h.search.client.Search(ctxS, t.dec.Utterance, h.search.max)
|
||||
if err != nil {
|
||||
log.Printf("voice: search %q: %v", t.dec.Utterance, err)
|
||||
return "", false
|
||||
}
|
||||
if resp.Empty() {
|
||||
return "", false
|
||||
}
|
||||
// Logged on the way through, not only on failure. Without this there is no
|
||||
// telling from the outside whether an answer came off the web, off a ZIM or
|
||||
// out of the model's weights, and those are the cases worth telling apart.
|
||||
log.Printf("voice: search: %q → %d answers, %d results", t.dec.Utterance, len(resp.Answers), len(resp.Results))
|
||||
|
||||
// Handed over the same way a note, a page or an article is: evidence for the
|
||||
// question he asked, not something to recite. The trim is one budget over the
|
||||
// joined block, so a long first snippet cannot crowd out the rest.
|
||||
evidence := crawl.TrimRunes(strings.Join(resp.Snippets(), "\n"), h.search.runes)
|
||||
reply := h.phraseSource(ctx, "search", t.dec.Utterance, []string{evidence})
|
||||
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 reply, true
|
||||
}
|
||||
|
||||
// queryKiwix — the offline encyclopedia, and the fallback behind querySearch:
|
||||
// everything of his has already had its turn and the live search found nothing
|
||||
// or could not be reached. Reading beats recalling for a 1.7B either way.
|
||||
//
|
||||
// What leaves this process is the search query and nothing else. His notes,
|
||||
// his facts, the persona block and the history do not travel with it — the
|
||||
// kiwix package cannot read the store. That holds even though the server is on
|
||||
// the LAN, because "local sources first" is not a licence to widen what a
|
||||
// lookup is allowed to see.
|
||||
//
|
||||
// It claims the turn only when the search returns something. No results is not
|
||||
// a failure worth announcing: it means the ZIM does not cover this, and the
|
||||
// model answering next is the better outcome than "ничего не нашла".
|
||||
func (h *reactiveHandler) queryKiwix(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if h.kiwix == nil {
|
||||
// Off unless configured, same as the crawler and the weather. Nothing
|
||||
// is said about it: he never asked for a capability he did not enable.
|
||||
return "", false
|
||||
}
|
||||
ctxK, cancel := context.WithTimeout(ctx, kiwixTimeout)
|
||||
defer cancel()
|
||||
|
||||
// A Russian question reads the Russian ZIM verbatim when there is one
|
||||
// (V-508). Kiwix ranks by keyword overlap rather than meaning, so an English
|
||||
// book matches a Russian sentence not at all, and the rewriter exists to
|
||||
// turn the question into English keywords with the resident model. Against a
|
||||
// Russian book that is a translation of his own words back at him: it costs
|
||||
// a model call and drops whatever the keywords do not carry.
|
||||
book, verbatim := h.kiwix.book, false
|
||||
if h.kiwix.bookRU != "" && hasCyrillic(t.dec.Utterance) {
|
||||
book, verbatim = h.kiwix.bookRU, true
|
||||
}
|
||||
|
||||
pattern := t.dec.Utterance
|
||||
if h.kiwix.rewriter != nil && !verbatim {
|
||||
q, err := h.kiwix.rewriter.Rewrite(ctxK, t.dec.Utterance)
|
||||
if err != nil {
|
||||
// Fall through to the verbatim question rather than give up. It
|
||||
// will usually miss, and missing is a fall-through too.
|
||||
log.Printf("voice: kiwix: rewrite: %v", err)
|
||||
} else if q != "" {
|
||||
pattern = q
|
||||
}
|
||||
}
|
||||
|
||||
hits, err := h.kiwix.client.Search(ctxK, pattern, book, h.kiwix.max)
|
||||
if err != nil {
|
||||
log.Printf("voice: kiwix: search %q: %v", pattern, err)
|
||||
return "", false
|
||||
}
|
||||
if len(hits) == 0 {
|
||||
return "", false
|
||||
}
|
||||
top := hits[0]
|
||||
// Logged on the way through, not only on failure. Without this there is no
|
||||
// way to tell from the outside whether an answer came off a ZIM or out of
|
||||
// the model's weights, and those are the two cases worth telling apart.
|
||||
log.Printf("voice: kiwix: %q in %q → %d hits, top %q", pattern, book, len(hits), top.Title)
|
||||
|
||||
// The top hit only, read as an article rather than as a snippet. Kiwix
|
||||
// builds its snippet from wherever the keyword matched, which on Wikipedia
|
||||
// is usually the navigation box at the foot of the page — the first version
|
||||
// of this joined three of those and she recited "Ecological economics
|
||||
// Ecological footprint …" at him. The head of the article is the lead
|
||||
// paragraph, which is the definition the snippet was meant to be.
|
||||
page, aerr := h.kiwix.client.Article(ctxK, top.Path, h.kiwix.runes)
|
||||
if aerr != nil || page.Text == "" {
|
||||
if aerr != nil {
|
||||
log.Printf("voice: kiwix: article %s: %v", top.Path, aerr)
|
||||
}
|
||||
// The search did find something, so fall back to its snippet rather
|
||||
// than throw the hit away.
|
||||
if top.Snippet == "" {
|
||||
return "", false
|
||||
}
|
||||
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)
|
||||
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 reply, true
|
||||
}
|
||||
|
||||
// hasCyrillic reports whether the text carries a Cyrillic letter, which is the
|
||||
// whole test for "he asked this in Russian". A question mixing a Latin proper
|
||||
// noun into a Russian sentence is still Russian, so one letter is enough.
|
||||
func hasCyrillic(s string) bool {
|
||||
for _, r := range s {
|
||||
if unicode.Is(unicode.Cyrillic, r) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// queryPersonal — stop the walk on a question about him that his own data did
|
||||
// not answer.
|
||||
//
|
||||
// Every source above this one reads something of his: his facts, his calendar,
|
||||
// his tasks, his house, his notes. Everything below reads the world: an offline
|
||||
// Wikipedia, a page he named, the model's own weights. The world does not know
|
||||
// when his meeting is, and asked anyway it will produce something.
|
||||
//
|
||||
// It did. "во сколько у меня встреча" reached Kiwix on the deployed daemon,
|
||||
// 01-08-2026; Wikipedia matched an article on the 2015 CPISRA World Games, and
|
||||
// the phraser rendered it as "встреча у тебя в 2015 CPISRA World Games, где
|
||||
// были соревнования по плаванию". Fluent, confident, and about a swimming
|
||||
// competition in Nottingham. Saying "не знаю" is not a worse answer than that
|
||||
// one — it is the only true one.
|
||||
//
|
||||
// Note this is also the privacy edge. The rule in CLAUDE.md is that only the
|
||||
// utterance may leave the box, never his notes; a question that is ABOUT him
|
||||
// carries his life in the utterance itself, so it is the one class that should
|
||||
// not be sent to an upstream engine at all. The guard closes both holes with
|
||||
// the same test.
|
||||
func (h *reactiveHandler) queryPersonal(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !h.isPersonalTurn(ctx, t) {
|
||||
return "", false
|
||||
}
|
||||
log.Printf("voice: %q is about him and his own data did not answer it; not asking the world", t.dec.Utterance)
|
||||
return phraser.Q(phraser.QueryPersonalNone, nil), true
|
||||
}
|
||||
|
||||
// personalMarkers — first-person POSSESSION, not first person generally.
|
||||
//
|
||||
// "у меня" and "мой" attach to a thing that is his, which is what makes the
|
||||
// question unanswerable from outside. A bare "мне" or "я" does not: "как мне
|
||||
// сварить борщ" and "что я могу посмотреть" are ordinary questions about the
|
||||
// world that happen to mention the asker, and refusing those would be the
|
||||
// opposite mistake. The narrow test is the point.
|
||||
// Go's \b is ASCII-only and never fires next to a Cyrillic letter, so the
|
||||
// Russian patterns spell the boundary out as "not a letter or a digit". The
|
||||
// English ones keep \b, where it works.
|
||||
var personalMarkers = []*regexp.Regexp{
|
||||
regexp.MustCompile(`(?i)(^|[^\p{L}\p{N}])у\s+меня([^\p{L}\p{N}]|$)`),
|
||||
regexp.MustCompile(`(?i)(^|[^\p{L}\p{N}])мо(й|я|ё|е|и|его|ей|их|им|ими|ем|ю|ею)([^\p{L}\p{N}]|$)`),
|
||||
regexp.MustCompile(`(?i)\bmy\b`),
|
||||
regexp.MustCompile(`(?i)\bdo\s+i\s+have\b`),
|
||||
regexp.MustCompile(`(?i)\bdid\s+i\b`),
|
||||
}
|
||||
|
||||
// isPersonalQuery — the offline floor under the boundary. Possession only, and
|
||||
// deliberately still narrow: it answers when there is no embedder to ask, and a
|
||||
// broad guess made blind is worse than a narrow one.
|
||||
func isPersonalQuery(utterance string) bool {
|
||||
if utterance == "" {
|
||||
return false
|
||||
}
|
||||
for _, re := range personalMarkers {
|
||||
if re.MatchString(utterance) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// isPersonalTurn — the boundary test. The seeds decide when the embedder is
|
||||
// there, which is every deployed box; the possession markers are the floor
|
||||
// underneath, for a handler with no embedder or a turn whose vector never got
|
||||
// computed. Same shape as the cascade: the better test leads, the offline one
|
||||
// always answers.
|
||||
func (h *reactiveHandler) isPersonalTurn(ctx context.Context, t *queryTurn) bool {
|
||||
h.recall.boundary.load(ctx, h.recall.embedder)
|
||||
if personal, world, ok := h.recall.boundary.score(t.vec); ok {
|
||||
if personal > world {
|
||||
log.Printf("voice: %q scores personal %.4f vs world %.4f", t.dec.Utterance, personal, world)
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
return isPersonalQuery(t.dec.Utterance)
|
||||
}
|
||||
|
||||
// queryGeneral — general knowledge, the last source before giving up. It always
|
||||
// claims: either a model answers, or Maven names the gap, or she says she does
|
||||
// not know.
|
||||
//
|
||||
// This is the sharpest case for the naming half. Nothing has been fetched, so
|
||||
// there is no passage to fall back on and no floor under the answer except the
|
||||
// model's weights — and a 1.7B's weights are where the invented answers come
|
||||
// from. With a workstation configured and asleep he is told that, rather than
|
||||
// told something false in a confident voice. With no workstation configured at
|
||||
// all the resident model answers exactly as it does today: naming a gap requires
|
||||
// a gap, and on that box the 1.7B is the whole product.
|
||||
func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if h.phraser == nil {
|
||||
// No model of any size. That is not the workstation being asleep, so it
|
||||
// is not that gap: it is simply not knowing.
|
||||
return phraser.Q(phraser.QueryUnknown, nil), true
|
||||
}
|
||||
reply, err := h.phraseWorld(ctx, t.dec.Utterance, nil)
|
||||
if errors.Is(err, phraser.ErrNoWorldModel) {
|
||||
log.Printf("voice: %q needs the world model and it is not available", t.dec.Utterance)
|
||||
return worldGap(), true
|
||||
}
|
||||
if err != nil || reply == "" {
|
||||
return phraser.Q(phraser.QueryUnknown, nil), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
@@ -0,0 +1,116 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// contQueryAPI records which core call a continued query reached. DayPlan and
|
||||
// LatestFact are here to be caught, not to be used: a continuation must never
|
||||
// reach them, and the counters are how the test says so.
|
||||
type contQueryAPI struct {
|
||||
ipc.UnimplementedCoreAPI
|
||||
from, to time.Time
|
||||
events int
|
||||
plans int
|
||||
factLooks int
|
||||
}
|
||||
|
||||
func (a *contQueryAPI) CalendarEvents(_ context.Context, from, to time.Time) ([]ipc.Fact, error) {
|
||||
a.events++
|
||||
a.from, a.to = from, to
|
||||
return []ipc.Fact{{Key: "calendar", Value: "Планёрка @ 14:00", Confidence: 1.0, Ts: from.Add(14 * time.Hour)}}, nil
|
||||
}
|
||||
|
||||
func (a *contQueryAPI) DayPlan(context.Context) (ipc.DayPlan, error) {
|
||||
a.plans++
|
||||
return ipc.DayPlan{Spoken: "план на сегодня"}, nil
|
||||
}
|
||||
|
||||
func (a *contQueryAPI) LatestFact(_ context.Context, key string) (ipc.Fact, error) {
|
||||
a.factLooks++
|
||||
return ipc.Fact{Key: key, Value: "2л", Ts: contNow.Add(-time.Hour)}, nil
|
||||
}
|
||||
|
||||
func contQueryHandler() (*reactiveHandler, *contQueryAPI) {
|
||||
api := &contQueryAPI{}
|
||||
return &reactiveHandler{api: api, now: func() time.Time { return contNow }}, api
|
||||
}
|
||||
|
||||
// A continuation is a question about another day, so the one source that can
|
||||
// read a day answers it — for the day the ellipsis named, not for today.
|
||||
func TestContinuedQueryReachesTheCalendar(t *testing.T) {
|
||||
h, api := contQueryHandler()
|
||||
reply := h.actionQuery(context.Background(), router.Decision{
|
||||
Intent: router.IntentQuery,
|
||||
Utterance: "а завтра?",
|
||||
Continued: true,
|
||||
Slots: router.Slots{Text: "что у меня сегодня", Time: contNow.Add(24 * time.Hour), HasTime: true},
|
||||
})
|
||||
if api.events != 1 {
|
||||
t.Fatalf("CalendarEvents called %d times, want 1", api.events)
|
||||
}
|
||||
if got, want := api.from.Format("2006-01-02"), "2026-08-02"; got != want {
|
||||
t.Errorf("asked the calendar for %s, want %s", got, want)
|
||||
}
|
||||
if reply == "" {
|
||||
t.Error("empty reply")
|
||||
}
|
||||
}
|
||||
|
||||
// The regression this gate exists for: every other source is date-blind, so
|
||||
// letting one claim a continuation answers a question about tomorrow with
|
||||
// today's data. queryFactByKey was the live case — HasKey plus HasTime, both
|
||||
// set by the continuation, and it replies with a stored fact's own timestamp.
|
||||
func TestContinuedQuerySkipsDateBlindSources(t *testing.T) {
|
||||
h, api := contQueryHandler()
|
||||
h.actionQuery(context.Background(), router.Decision{
|
||||
Intent: router.IntentQuery,
|
||||
Utterance: "а вчера?",
|
||||
Continued: true,
|
||||
Slots: router.Slots{
|
||||
Key: "water", HasKey: true,
|
||||
Text: "когда я пил воду",
|
||||
Time: contNow.Add(-24 * time.Hour), HasTime: true,
|
||||
},
|
||||
})
|
||||
if api.factLooks != 0 {
|
||||
t.Errorf("fact-by-key claimed a continuation (%d lookups)", api.factLooks)
|
||||
}
|
||||
if api.plans != 0 {
|
||||
t.Errorf("day-plan claimed a continuation (%d calls)", api.plans)
|
||||
}
|
||||
}
|
||||
|
||||
// Nothing date-aware claimed it: say that, rather than "не знаю", which reads
|
||||
// as "no data for that day" when she never looked.
|
||||
func TestContinuedQueryWithNoDateAwareAnswerSaysSo(t *testing.T) {
|
||||
h, _ := contQueryHandler()
|
||||
// No parseable day in the utterance, so even the calendar passes.
|
||||
reply := h.actionQuery(context.Background(), router.Decision{
|
||||
Intent: router.IntentQuery,
|
||||
Utterance: "а?",
|
||||
Continued: true,
|
||||
Slots: router.Slots{Text: "какая погода", HasTime: true},
|
||||
})
|
||||
if reply == "не знаю." || !strings.Contains(reply, "спроси целиком") {
|
||||
t.Fatalf("reply = %q, want the honest continuation refusal", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// An ordinary query is untouched by the gate — every source still runs.
|
||||
func TestOrdinaryQueryStillReachesEverySource(t *testing.T) {
|
||||
h, api := contQueryHandler()
|
||||
h.actionQuery(context.Background(), router.Decision{
|
||||
Intent: router.IntentQuery,
|
||||
Utterance: "какие планы на сегодня?",
|
||||
})
|
||||
if api.plans != 1 {
|
||||
t.Fatalf("day-plan called %d times on an ordinary query, want 1", api.plans)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,117 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestIsPersonalQuery(t *testing.T) {
|
||||
for _, s := range []string{
|
||||
"во сколько у меня встреча",
|
||||
"что у меня сегодня",
|
||||
"когда мой следующий отпуск",
|
||||
"где моя книга",
|
||||
"сколько моих задач висит",
|
||||
"when is my meeting",
|
||||
"do i have anything today",
|
||||
"did i take my vitamins",
|
||||
// Speech, but only the forms possession already covers ("did i").
|
||||
// The verb forms the floor cannot see are the seeds' job, scored in
|
||||
// TestONNXPersonalBoundary.
|
||||
"what did i say about backups",
|
||||
} {
|
||||
if !isPersonalQuery(s) {
|
||||
t.Errorf("isPersonalQuery(%q) = false, want true", s)
|
||||
}
|
||||
}
|
||||
for _, s := range []string{
|
||||
// First person without possession. These are questions about the
|
||||
// world that merely mention the asker, and refusing them would be the
|
||||
// opposite mistake.
|
||||
"как мне сварить борщ",
|
||||
"что я могу посмотреть вечером",
|
||||
"почему небо синее",
|
||||
"столица франции",
|
||||
"how do i boil an egg",
|
||||
// The floor is possession-only by design: a speech verb it cannot see
|
||||
// passes here and is caught by the seeds instead.
|
||||
"что я говорил про бэкапы?",
|
||||
"как я говорил, почему небо синее",
|
||||
"",
|
||||
} {
|
||||
if isPersonalQuery(s) {
|
||||
t.Errorf("isPersonalQuery(%q) = true, want false", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// kiwixTrapAPI stands in for the world. Nothing below the personal boundary
|
||||
// should be consulted for a question about him, so the test asserts on the
|
||||
// reply rather than on a call: reaching Kiwix or general knowledge produces a
|
||||
// phrased answer, and refusing produces the honest one.
|
||||
func personalHandler() *reactiveHandler {
|
||||
return &reactiveHandler{
|
||||
api: ipc.UnimplementedCoreAPI{},
|
||||
now: func() time.Time { return contNow },
|
||||
// No phraser and no kiwix wiring: if the walk gets past the personal
|
||||
// source it reaches queryGeneral, which returns "не знаю." with a nil
|
||||
// phraser — a different string from the one this guard produces, so
|
||||
// the two cases stay distinguishable.
|
||||
}
|
||||
}
|
||||
|
||||
// The regression: "во сколько у меня встреча" reached Kiwix, Wikipedia matched
|
||||
// an article on the 2015 CPISRA World Games, and the phraser reported it back
|
||||
// as his meeting. Seen on the deployed daemon, 01-08-2026.
|
||||
func TestPersonalQuestionIsNotSentToTheWorld(t *testing.T) {
|
||||
h := personalHandler()
|
||||
reply, ok := h.queryPersonal(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "во сколько у меня встреча"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("queryPersonal passed on a question about him")
|
||||
}
|
||||
if reply == "" {
|
||||
t.Fatal("empty reply")
|
||||
}
|
||||
}
|
||||
|
||||
func TestWorldQuestionsPassThroughTheBoundary(t *testing.T) {
|
||||
h := personalHandler()
|
||||
for _, u := range []string{"почему небо синее", "столица франции"} {
|
||||
if _, ok := h.queryPersonal(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: u},
|
||||
}); ok {
|
||||
t.Errorf("queryPersonal claimed %q, want it to pass to the encyclopedia", u)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The boundary must sit above kiwix and general-knowledge and below every
|
||||
// source that reads his own data. Asserted on the table itself: an ordering
|
||||
// bug here is silent, because both arrangements answer, just from the wrong
|
||||
// place.
|
||||
func TestPersonalBoundarySitsBetweenHisDataAndTheWorld(t *testing.T) {
|
||||
idx := map[string]int{}
|
||||
for i, s := range querySources {
|
||||
idx[s.name] = i
|
||||
}
|
||||
boundary, ok := idx["personal"]
|
||||
if !ok {
|
||||
t.Fatal("no personal source in the chain")
|
||||
}
|
||||
for _, his := range []string{"fact-by-key", "day-plan", "tasks", "calendar", "memory", "notes"} {
|
||||
if i, ok := idx[his]; !ok || i > boundary {
|
||||
t.Errorf("%q reads his own data and must run before the personal boundary", his)
|
||||
}
|
||||
}
|
||||
for _, world := range []string{"search", "kiwix", "web", "general-knowledge"} {
|
||||
if i, ok := idx[world]; !ok || i < boundary {
|
||||
t.Errorf("%q reads the world and must run after the personal boundary", world)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,105 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"net/url"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/websearch"
|
||||
)
|
||||
|
||||
func searchHandler(t *testing.T, body string, status int) (*reactiveHandler, *string) {
|
||||
t.Helper()
|
||||
var seen string
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
seen = r.URL.RawQuery
|
||||
if status != http.StatusOK {
|
||||
http.Error(w, "no", status)
|
||||
return
|
||||
}
|
||||
w.Write([]byte(body))
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
return &reactiveHandler{
|
||||
// No phraser: querySearch then reads back the best evidence, which is
|
||||
// what makes the claim visible without a llama-server in the test.
|
||||
search: &searchWiring{client: websearch.New(srv.URL, websearch.Options{}), max: 3, runes: 1500},
|
||||
}, &seen
|
||||
}
|
||||
|
||||
const searchBody = `{"answers":["Небо голубое из-за рэлеевского рассеяния."],
|
||||
"results":[{"title":"Рэлеевское рассеяние","url":"https://ru.wikipedia.org/x","content":"Рассеяние света."}]}`
|
||||
|
||||
func TestQuerySearchClaimsAndReadsBack(t *testing.T) {
|
||||
h, _ := searchHandler(t, searchBody, http.StatusOK)
|
||||
reply, ok := h.querySearch(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо голубое"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("querySearch passed on a search with hits")
|
||||
}
|
||||
if !strings.Contains(reply, "рэлеевского рассеяния") {
|
||||
t.Fatalf("reply = %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// No rewriter in front of this source: SearXNG ranks by meaning, and reducing
|
||||
// the question to English keywords would throw away the language he asked in.
|
||||
func TestQuerySearchSendsTheQuestionVerbatim(t *testing.T) {
|
||||
h, seen := searchHandler(t, searchBody, http.StatusOK)
|
||||
h.querySearch(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо голубое"},
|
||||
})
|
||||
if !strings.Contains(*seen, "q="+url.QueryEscape("почему небо голубое")) {
|
||||
t.Fatalf("query string = %q", *seen)
|
||||
}
|
||||
}
|
||||
|
||||
// The whole reason the ordering is safe: an unreachable or empty instance
|
||||
// passes the turn to Kiwix instead of claiming it with an apology.
|
||||
func TestQuerySearchFallsThroughWhenItFails(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
body string
|
||||
status int
|
||||
}{
|
||||
{"http error", "", http.StatusForbidden},
|
||||
{"no hits", `{"answers":[],"results":[]}`, http.StatusOK},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
h, _ := searchHandler(t, tc.body, tc.status)
|
||||
if _, ok := h.querySearch(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо голубое"},
|
||||
}); ok {
|
||||
t.Fatal("querySearch claimed the turn; Kiwix never got its fallback")
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Off unless configured, and silent about it: he never asked for a capability
|
||||
// he did not enable.
|
||||
func TestQuerySearchOffWithoutConfig(t *testing.T) {
|
||||
h := &reactiveHandler{}
|
||||
if _, ok := h.querySearch(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо голубое"},
|
||||
}); ok {
|
||||
t.Fatal("querySearch claimed a turn with no search block")
|
||||
}
|
||||
}
|
||||
|
||||
// The owner's ruling of 2026-08-02: the live search asks first, the ZIM is the
|
||||
// fallback for a box with no line out.
|
||||
func TestSearchRunsBeforeKiwix(t *testing.T) {
|
||||
idx := map[string]int{}
|
||||
for i, s := range querySources {
|
||||
idx[s.name] = i
|
||||
}
|
||||
if idx["search"] > idx["kiwix"] {
|
||||
t.Fatalf("search at %d, kiwix at %d: the ZIM is the fallback, not the first read", idx["search"], idx["kiwix"])
|
||||
}
|
||||
}
|
||||
@@ -2,8 +2,12 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -21,13 +25,35 @@ func (h *reactiveHandler) actionReminder(ctx context.Context, dec router.Decisio
|
||||
}
|
||||
}
|
||||
if !dec.Slots.HasTime {
|
||||
return "не получилось разобрать время напоминания."
|
||||
return phraser.Ack(phraser.FailReminderTime, nil)
|
||||
}
|
||||
}
|
||||
payload := `{"text":` + jsonString(dec.Utterance) + `}`
|
||||
// The body is what she says at the hour, so the marker and the time come
|
||||
// out of it: the fire time is already a column, and "напомни" is an
|
||||
// instruction that has been carried out (Vikunja #469).
|
||||
payload := `{"text":` + jsonString(reminderBody(dec.Utterance, dec.Slots.Text)) + `}`
|
||||
if _, err := h.api.CreateReminder(ctx, dec.Slots.Time, payload, ""); err != nil {
|
||||
log.Printf("voice: create reminder: %v", err)
|
||||
return "не получилось поставить напоминание."
|
||||
return phraser.Ack(phraser.FailReminder, nil)
|
||||
}
|
||||
return ""
|
||||
// Phrased from the row, never from the utterance (Vikunja #507). The
|
||||
// replier only ever saw Slots.Text, so it named whatever hour the sentence
|
||||
// contained — including one the parser had rejected or read differently.
|
||||
// A confirmation naming an hour no row holds is worse than a clarify,
|
||||
// because he stops thinking about it.
|
||||
return reminderConfirm(dec.Slots.Time, h.now())
|
||||
}
|
||||
|
||||
// reminderConfirm — the confirmation for a reminder that exists, naming the
|
||||
// stored fire time. Deterministic on purpose: the one sentence that must match
|
||||
// a database row is not one to hand to a 1.7B.
|
||||
func reminderConfirm(fire, now time.Time) string {
|
||||
when := dayPrefix(now, fire)
|
||||
if when == "это" {
|
||||
// Further out than the day words reach — say the date instead of a
|
||||
// word that would be wrong.
|
||||
date := fmt.Sprintf("%d %s", fire.Day(), lexicon.MonthGenitive(int(fire.Month())))
|
||||
return "хорошо, напомню " + date + " в " + fire.Format("15:04") + "."
|
||||
}
|
||||
return "хорошо, напомню " + when + " в " + fire.Format("15:04") + "."
|
||||
}
|
||||
|
||||
@@ -4,7 +4,9 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tasks"
|
||||
@@ -40,18 +42,18 @@ func (h *reactiveHandler) captureTaskFromNote(ctx context.Context, dec router.De
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: capture task: %v", err)
|
||||
return "не получилось записать задачу.", true
|
||||
return phraser.Ack(phraser.FailTask, nil), true
|
||||
}
|
||||
if resp.Promoted {
|
||||
// It was a candidate Maven derived from something she read, and he has
|
||||
// now said it himself. Saying "уже в списке" here would be answering a
|
||||
// confirmation with a shrug.
|
||||
return "поняла, беру в работу: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTaskUrgent, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
if !resp.Created {
|
||||
return "это уже в списке.", true
|
||||
return phraser.Ack(phraser.AckTaskDuplicate, nil), true
|
||||
}
|
||||
return "записала: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTask, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
|
||||
// queryTasks — "какие у меня задачи?", "что мне нужно сделать?".
|
||||
@@ -70,7 +72,16 @@ func (h *reactiveHandler) queryTasks(ctx context.Context, t *queryTurn) (string,
|
||||
log.Printf("voice: list tasks: %v", err)
|
||||
return "не получилось посмотреть задачи.", true
|
||||
}
|
||||
return tasks.FormatRU(tasks.Rank(taskItems(live), h.now())), true
|
||||
ranked := tasks.Rank(taskItems(live), h.now())
|
||||
// Bind what she is about to say, in the order she says it, so "второй"
|
||||
// means the second task he heard (ordinal.go).
|
||||
spoken := tasks.Spoken(ranked)
|
||||
cands := make([]dialogue.Candidate, 0, len(spoken))
|
||||
for _, r := range spoken {
|
||||
cands = append(cands, dialogue.Candidate{Kind: "task", Ref: r.ID, Label: r.Text})
|
||||
}
|
||||
h.offerCandidates(ctx, cands)
|
||||
return tasks.FormatRU(ranked), true
|
||||
}
|
||||
|
||||
// taskItems maps wire rows onto the ranker's input. Written here rather than in
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -108,7 +109,7 @@ func TestCaptureTaskFromNoteReportsStoreFailure(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("a failed capture still claims the turn — the note path must not double-write")
|
||||
}
|
||||
if !strings.Contains(reply, "не получилось") {
|
||||
if !phraser.IsAck(phraser.FailTask, nil, reply) {
|
||||
t.Errorf("reply = %q, want an honest failure", reply)
|
||||
}
|
||||
}
|
||||
@@ -137,7 +138,7 @@ func TestQueryTasksRecitesTheLiveList(t *testing.T) {
|
||||
if !(openIdx < candIdx) {
|
||||
t.Errorf("reply = %q, want confirmed work before candidates", reply)
|
||||
}
|
||||
if !strings.Contains(reply, "не подтвердил") {
|
||||
if !strings.Contains(reply, "не подтверждал") {
|
||||
t.Errorf("reply = %q, want the candidate flagged as unconfirmed", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,186 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// The sev4 repeat path had no off switch (Vikunja #535): it re-sent every
|
||||
// pending telegram nudge every repeat_interval, and nothing in the tree could
|
||||
// ever mark one acked. None of what follows can be reproduced by hand without
|
||||
// sitting in front of the box for hours, so it is covered here or nowhere.
|
||||
|
||||
// seedDown writes one kuma monitor fact at ts. value is "down" or "up".
|
||||
func seedDown(t *testing.T, st *store.Store, ctx context.Context, value string, ts time.Time) {
|
||||
t.Helper()
|
||||
if _, err := st.SetValue(ctx, store.KindSelf, "service_down:db", "poll:uptimekuma", value, ts); err != nil {
|
||||
t.Fatalf("seed service_down:db=%s: %v", value, err)
|
||||
}
|
||||
}
|
||||
|
||||
// newAlarmTickLoop — like newTestTickLoop but with the ack tracker wired, which
|
||||
// the shared helper leaves nil. Without it RepeatUnacked returns early and the
|
||||
// repeat these tests are about never happens. The daemon wires it (main.go).
|
||||
func newAlarmTickLoop(t *testing.T, st *store.Store, sink delivery.Sink) *tickLoop {
|
||||
t.Helper()
|
||||
rules := loop.DefaultRules()
|
||||
g := loop.NewGatherer(st, rules)
|
||||
d := delivery.NewDispatcher(delivery.Config{
|
||||
Voice: sink, Ntfy: sink, Telegram: sink,
|
||||
Ack: st, Nudges: st, Reminders: st,
|
||||
})
|
||||
return newTickLoop(st, g, d, phraser.NewStub(), rules, time.Second, 5*time.Minute, 0, nil, nil, nil, nil)
|
||||
}
|
||||
|
||||
// telegramSends counts sends that went out on the telegram reach.
|
||||
func telegramSends(sink *fakeSink, rule string) int {
|
||||
n := 0
|
||||
for _, s := range sink.sends {
|
||||
if s.RuleName == rule {
|
||||
n++
|
||||
}
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// outcomes returns the outcome of every nudge row for a rule, newest first.
|
||||
func outcomes(t *testing.T, st *store.Store, ctx context.Context, rule string) []string {
|
||||
t.Helper()
|
||||
rows, err := st.RecentNudges(ctx, 50)
|
||||
if err != nil {
|
||||
t.Fatalf("recent nudges: %v", err)
|
||||
}
|
||||
var out []string
|
||||
for _, n := range rows {
|
||||
if n.Rule == rule {
|
||||
out = append(out, n.Outcome)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func TestAlarmStopsWhenTheServiceComesBackUp(t *testing.T) {
|
||||
// The condition clearing is the ending that should happen. StillTrue reads
|
||||
// the same DownServices helper the phraser reads, so the repeat stops on
|
||||
// exactly the monitor he was told about.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
|
||||
|
||||
sink := &fakeSink{}
|
||||
tl := newAlarmTickLoop(t, st, sink)
|
||||
tl.tick(ctx, now)
|
||||
if telegramSends(sink, "service_down") == 0 {
|
||||
t.Fatal("the alarm never went out; the rest of this test proves nothing")
|
||||
}
|
||||
|
||||
seedDown(t, st, ctx, "up", now.Add(time.Minute))
|
||||
sink.sends = nil
|
||||
tl.tick(ctx, now.Add(6*time.Minute)) // past repeat_interval
|
||||
|
||||
if n := telegramSends(sink, "service_down"); n != 0 {
|
||||
t.Fatalf("repeated %d time(s) after the service came back up; want 0", n)
|
||||
}
|
||||
for _, o := range outcomes(t, st, ctx, "service_down") {
|
||||
if o != store.NudgeResolved {
|
||||
t.Fatalf("nudge outcome = %q, want %q", o, store.NudgeResolved)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestAlarmStopsAtTheAgeCapWhileStillDown(t *testing.T) {
|
||||
// Still down, still un-acked, and nobody has answered in two hours. That is
|
||||
// not one more repeat away from being answered.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
|
||||
|
||||
sink := &fakeSink{}
|
||||
tl := newAlarmTickLoop(t, st, sink)
|
||||
tl.tick(ctx, now)
|
||||
|
||||
sink.sends = nil
|
||||
tl.tick(ctx, now.Add(6*time.Minute))
|
||||
if n := telegramSends(sink, "service_down"); n == 0 {
|
||||
t.Fatal("no repeat inside the cap; the cap is not what stopped it later")
|
||||
}
|
||||
|
||||
sink.sends = nil
|
||||
tl.tick(ctx, now.Add(maxAlarmAge+time.Minute))
|
||||
if n := telegramSends(sink, "service_down"); n != 0 {
|
||||
t.Fatalf("repeated %d time(s) past the %s cap; want 0", n, maxAlarmAge)
|
||||
}
|
||||
// Ignored, not resolved: nothing says the service got better.
|
||||
for _, o := range outcomes(t, st, ctx, "service_down") {
|
||||
if o != store.NudgeIgnored {
|
||||
t.Fatalf("nudge outcome = %q, want %q", o, store.NudgeIgnored)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestAFlapRaisesAFreshAlarmRatherThanReviveTheClosedOne(t *testing.T) {
|
||||
// Down, up, down again. Closing the first run must not make the second run
|
||||
// unreportable, and must not silently reopen the closed rows either.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
|
||||
|
||||
sink := &fakeSink{}
|
||||
tl := newAlarmTickLoop(t, st, sink)
|
||||
tl.tick(ctx, now)
|
||||
first := len(outcomes(t, st, ctx, "service_down"))
|
||||
|
||||
seedDown(t, st, ctx, "up", now.Add(time.Minute))
|
||||
tl.tick(ctx, now.Add(2*time.Minute))
|
||||
if got := outcomes(t, st, ctx, "service_down"); len(got) != first {
|
||||
t.Fatalf("closing the run changed the row count: %d → %d", first, len(got))
|
||||
}
|
||||
|
||||
seedDown(t, st, ctx, "down", now.Add(25*time.Minute))
|
||||
sink.sends = nil
|
||||
tl.tick(ctx, now.Add(31*time.Minute))
|
||||
|
||||
if n := telegramSends(sink, "service_down"); n == 0 {
|
||||
t.Fatal("the second outage said nothing; the first alarm's ending swallowed it")
|
||||
}
|
||||
got := outcomes(t, st, ctx, "service_down")
|
||||
if len(got) <= first {
|
||||
t.Fatalf("no new nudge row for the second outage (%d rows, was %d)", len(got), first)
|
||||
}
|
||||
}
|
||||
|
||||
func TestARuleThatSaysNothingAboutItsConditionOnlyStopsOnAge(t *testing.T) {
|
||||
// StillTrue == nil means "I cannot tell you", never "it cleared". A rule
|
||||
// that says nothing must keep its alarm until the age cap, or a rule author
|
||||
// silences their own alarm by omission.
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
|
||||
sink := &fakeSink{}
|
||||
tl := newAlarmTickLoop(t, st, sink)
|
||||
tl.rules = []loop.Rule{{Name: "mute", Severity: loop.Sev4}} // no StillTrue
|
||||
|
||||
if _, err := st.RecordNudge(ctx, "mute", string(delivery.ChannelTelegram), "still bad", now); err != nil {
|
||||
t.Fatalf("record nudge: %v", err)
|
||||
}
|
||||
|
||||
live := tl.stopFinishedAlarms(ctx, []string{"mute"}, loop.State{}, now.Add(time.Minute))
|
||||
if len(live) != 1 {
|
||||
t.Fatalf("a nil StillTrue was read as resolved: live = %v", live)
|
||||
}
|
||||
|
||||
live = tl.stopFinishedAlarms(ctx, []string{"mute"}, loop.State{}, now.Add(maxAlarmAge+time.Minute))
|
||||
if len(live) != 0 {
|
||||
t.Fatalf("the age cap did not stop a rule with no StillTrue: live = %v", live)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// An empty attention list used to be answered "ничего не требует внимания"
|
||||
// unconditionally, which is an all-clear Maven had no way to know was true
|
||||
// (ECOSYSTEM-SPEC §2.6, Vikunja #540).
|
||||
func TestAttentionEmptyWithHealthySourcesIsAllClear(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t, `[]`, `[{"source_id":"src_ntfy","health":"ok"}]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
if !strings.Contains(reply, "ничего не требует внимания") {
|
||||
t.Fatalf("healthy and quiet should be an all-clear, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAttentionEmptyWithAFailedSourceHedges(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t, `[]`, `[
|
||||
{"source_id":"src_ntfy","health":"ok"},
|
||||
{"source_id":"src_llamacpp","health":"failed"},
|
||||
{"source_id":"src_imap","health":"stale"}
|
||||
]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
if strings.Contains(reply, "ничего не требует внимания") {
|
||||
t.Fatalf("a failed source must not read as all-clear, got %q", reply)
|
||||
}
|
||||
for _, want := range []string{"src_llamacpp", "src_imap"} {
|
||||
if !strings.Contains(reply, want) {
|
||||
t.Errorf("reply names no %s: %q", want, reply)
|
||||
}
|
||||
}
|
||||
if strings.Contains(reply, "src_ntfy") {
|
||||
t.Errorf("the healthy source is named as a problem: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// A Praxis that polls nothing knows nothing, which is the state the box is in.
|
||||
func TestAttentionEmptyWithNoSourcesHedges(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t, `[]`, `[]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
if strings.Contains(reply, "ничего не требует внимания") {
|
||||
t.Fatalf("a Praxis with no sources must not answer all-clear, got %q", reply)
|
||||
}
|
||||
if !strings.Contains(reply, "источник") {
|
||||
t.Errorf("reply does not say why she cannot tell: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The spec's own mechanism, which the deployed Praxis does not send yet: the
|
||||
// envelope's degraded array is believed without a second call.
|
||||
func TestAttentionDegradedEnvelopeIsReadWithoutASourcesCall(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t,
|
||||
`{"items":[],"degraded":["src_metrics"]}`,
|
||||
`[{"source_id":"src_ntfy","health":"ok"}]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
if !strings.Contains(reply, "src_metrics") {
|
||||
t.Fatalf("the envelope's degraded source is not named: %q", reply)
|
||||
}
|
||||
for _, r := range praxis.Requests() {
|
||||
if r.Path == "/api/v1/sources" {
|
||||
t.Error("sources was read even though the response carried degraded")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A sources endpoint that errors is not evidence of a fault: the attention call
|
||||
// itself succeeded, and hedging on it would make her permanently uncertain.
|
||||
func TestAttentionKeepsAllClearWhenSourcesCannotBeRead(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t, `[]`, `[]`)
|
||||
praxis.SetRouteFault("/api/v1/sources", 500)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
if !strings.Contains(reply, "ничего не требует внимания") {
|
||||
t.Fatalf("an unreadable sources list should leave the answer alone, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// Both response shapes decode, because the spec says one and the box sends the
|
||||
// other.
|
||||
func TestPraxisAttentionDecodesBothShapes(t *testing.T) {
|
||||
var bare praxisAttention
|
||||
if err := json.Unmarshal([]byte(`[{"id":"item_1"}]`), &bare); err != nil {
|
||||
t.Fatalf("bare array: %v", err)
|
||||
}
|
||||
if len(bare.Items) != 1 || len(bare.Degraded) != 0 {
|
||||
t.Errorf("bare array decoded as %+v", bare)
|
||||
}
|
||||
|
||||
var env praxisAttention
|
||||
if err := json.Unmarshal([]byte(`{"items":[{"id":"item_2"}],"degraded":["src_a"]}`), &env); err != nil {
|
||||
t.Fatalf("envelope: %v", err)
|
||||
}
|
||||
if len(env.Items) != 1 || len(env.Degraded) != 1 || env.Degraded[0] != "src_a" {
|
||||
t.Errorf("envelope decoded as %+v", env)
|
||||
}
|
||||
}
|
||||
|
||||
// A source that reports no health at all counts as healthy. A Praxis that never
|
||||
// fills the field would otherwise make every quiet turn a hedge.
|
||||
func TestUnhealthySourcesTreatsAnAbsentHealthFieldAsHealthy(t *testing.T) {
|
||||
praxis := newFakePraxisWithSources(t, `[]`, `[{"source_id":"src_a"},{"id":"src_b","health":"stale"}]`)
|
||||
bad, total, err := newPraxisClient(praxis.URL).UnhealthySources(context.Background())
|
||||
if err != nil {
|
||||
t.Fatalf("UnhealthySources: %v", err)
|
||||
}
|
||||
if total != 2 {
|
||||
t.Errorf("total = %d, want 2", total)
|
||||
}
|
||||
if len(bad) != 1 || bad[0] != "src_b" {
|
||||
t.Errorf("bad = %v, want [src_b]", bad)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,71 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// attentionMarkers — the offline floor under the attention topic (topics.go).
|
||||
// The seeds decide when the embedder is there; this answers when it is not, and
|
||||
// it stays a substring list on purpose for the reason the other floors do: a
|
||||
// narrow test made blind beats a broad guess made blind.
|
||||
//
|
||||
// "что нового" is deliberately absent: the feeds source claims it, and it
|
||||
// still should — a question about news is a question about the feeds she
|
||||
// reads. This list is about the operational state of his things.
|
||||
var attentionMarkers = []string{
|
||||
"внимани", "что требует", "что не так", "что важн", "что срочн",
|
||||
"needs attention", "what needs looking",
|
||||
}
|
||||
|
||||
// isAttentionQuery reports whether the utterance asks what needs looking at.
|
||||
// Called through turnIsAbout, never directly.
|
||||
func isAttentionQuery(u string) bool {
|
||||
s := strings.ToLower(strings.TrimSpace(u))
|
||||
if s == "" {
|
||||
return false
|
||||
}
|
||||
for _, m := range attentionMarkers {
|
||||
if strings.Contains(s, m) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// queryAttention answers "что требует внимания?" from Praxis.
|
||||
//
|
||||
// The capability was already built and already degraded correctly, and no
|
||||
// utterance could reach it (Vikunja #475). Its aliases live on the act
|
||||
// dispatch, and the question routes to IntentQuery, so it fell through every
|
||||
// source to the web search and came back with an encyclopedia article about
|
||||
// the concept of attention — worse than silence, because it reads as an
|
||||
// answer.
|
||||
//
|
||||
// Placed above the recall sources and well above the personal boundary: this
|
||||
// is operational state about his things, and a notes pass would otherwise
|
||||
// answer it from whatever he once wrote about a server. An unconfigured or
|
||||
// absent Praxis falls through rather than claiming the turn, the same
|
||||
// convention queryHome and queryNetwork follow. A Praxis that is configured
|
||||
// and down does claim it, and says it cannot reach the service — that is the
|
||||
// degradation the ecosystem contract asks for, and it comes from the same
|
||||
// handler the act path uses.
|
||||
func (h *reactiveHandler) queryAttention(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !h.turnIsAbout(ctx, t, topicAttend, isAttentionQuery) {
|
||||
return "", false
|
||||
}
|
||||
if h.ecosystem == nil || h.ecosystem.praxis == nil {
|
||||
return "", false
|
||||
}
|
||||
reply := h.handlePraxisAct(ctx, router.Decision{
|
||||
Utterance: t.dec.Utterance,
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Fn: "list_attention", HasFn: true},
|
||||
})
|
||||
if reply == "" {
|
||||
return "", false
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -0,0 +1,77 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestIsAttentionQuery(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
text string
|
||||
want bool
|
||||
}{
|
||||
{"что требует внимания", true},
|
||||
{"на что обратить внимание?", true},
|
||||
{"что не так?", true},
|
||||
{"что важного?", true},
|
||||
// The feeds source owns this one, and should keep owning it.
|
||||
{"что нового?", false},
|
||||
{"какая погода?", false},
|
||||
{"", false},
|
||||
} {
|
||||
if got := isAttentionQuery(tc.text); got != tc.want {
|
||||
t.Errorf("isAttentionQuery(%q) = %v, want %v", tc.text, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestAttentionQuestionReachesPraxis — the defect (Vikunja #475). The question
|
||||
// routes to IntentQuery, and every source used to pass, so a web search about
|
||||
// the concept of attention answered it.
|
||||
func TestAttentionQuestionReachesPraxis(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
praxis := newFakePraxis(t, fixturePraxisAttentionItems(map[string]any{
|
||||
"id": "item_1", "title": "disk almost full", "importance": 3.0,
|
||||
}))
|
||||
h := ecoHandler(t, nil, praxis, nil)
|
||||
|
||||
reply, ok := h.queryAttention(ctx, &queryTurn{dec: router.Decision{
|
||||
Intent: router.IntentQuery, Utterance: "что требует внимания",
|
||||
}})
|
||||
if !ok {
|
||||
t.Fatal("the attention question must be claimed before the world sources")
|
||||
}
|
||||
if !strings.Contains(reply, "disk almost full") {
|
||||
t.Fatalf("reply = %q, want the praxis item", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// A configured Praxis that is down claims the turn and says so. Falling
|
||||
// through here would answer an outage with an encyclopedia article.
|
||||
func TestAttentionQuestionSaysWhenPraxisIsDown(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
praxis := newFakePraxis(t, fixturePraxisAttentionItems())
|
||||
h := ecoHandler(t, nil, praxis, nil)
|
||||
praxis.SetFault(503)
|
||||
|
||||
reply, ok := h.queryAttention(ctx, &queryTurn{dec: router.Decision{
|
||||
Intent: router.IntentQuery, Utterance: "что требует внимания",
|
||||
}})
|
||||
if !ok || !strings.Contains(reply, "не могу") {
|
||||
t.Fatalf("an outage must name the gap, got ok=%v reply=%q", ok, reply)
|
||||
}
|
||||
}
|
||||
|
||||
// No Praxis configured means no claim: the rest of the chain still runs.
|
||||
func TestAttentionQuestionFallsThroughWithoutPraxis(t *testing.T) {
|
||||
h, _ := newFactGateHandler(t, time.Now())
|
||||
if _, ok := h.queryAttention(context.Background(), &queryTurn{dec: router.Decision{
|
||||
Intent: router.IntentQuery, Utterance: "что требует внимания",
|
||||
}}); ok {
|
||||
t.Fatal("an unconfigured praxis must not claim the turn")
|
||||
}
|
||||
}
|
||||
+52
-1
@@ -31,9 +31,11 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -54,16 +56,65 @@ import (
|
||||
// asks Maven to stop recording gets the transcript back in seconds.
|
||||
const captureSummaryTimeout = 20 * time.Minute
|
||||
|
||||
// summaryGrammar — GBNF pinning a summarisation call to one JSON object holding
|
||||
// the summary and nothing else. Same reasoning as responseGrammar and memeval's
|
||||
// evalGrammar: the resident model is a Thinking variant, and a summarisation
|
||||
// prompt is exactly the shape that invites it to answer with its reasoning as
|
||||
// plain text. Demanding JSON leaves the reasoning nowhere to go.
|
||||
//
|
||||
// The bound is 2000 characters, twice the phraser's, because a reduce step over
|
||||
// a two-hour meeting is a paragraph and not a sentence. Newlines are escaped by
|
||||
// the escape rule, so the bullet list the prompt asks for survives the wrapper.
|
||||
const summaryGrammar = `
|
||||
root ::= "{" ws "\"summary\"" ws ":" ws string ws "}"
|
||||
string ::= "\"" ([^"\\] | "\\" ["\\/bfnrt]){0,2000} "\""
|
||||
ws ::= [ \t\n]*
|
||||
`
|
||||
|
||||
// llmCompleter adapts *llm.Client to capture.Completer. The pure package names
|
||||
// the two strings it needs and stays free of the llm request struct; the client
|
||||
// itself is the swap-aware one from llmClientFor, so a model swap re-points it.
|
||||
//
|
||||
// The JSON wrapper lives here, not in internal/capture: that package is
|
||||
// text-in/text-out by design, and the map/reduce steps still see plain prose.
|
||||
type llmCompleter struct {
|
||||
c *llm.Client
|
||||
maxTokens int
|
||||
}
|
||||
|
||||
func (l llmCompleter) Complete(ctx context.Context, system, user string) (string, error) {
|
||||
return l.c.Complete(ctx, llm.Req{System: system, User: user, MaxTokens: l.maxTokens})
|
||||
out, err := l.c.Complete(ctx, llm.Req{
|
||||
System: system,
|
||||
User: user,
|
||||
Grammar: summaryGrammar,
|
||||
MaxTokens: l.maxTokens,
|
||||
})
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return unwrapSummary(out), nil
|
||||
}
|
||||
|
||||
// unwrapSummary takes the summary out of the JSON object the grammar produced.
|
||||
// Anything that does not parse is returned as-is: an operator running without a
|
||||
// grammar, or a llama-server too old to honour one, gets the plain text it used
|
||||
// to get rather than an empty meeting summary.
|
||||
func unwrapSummary(raw string) string {
|
||||
s := phraser.StripThink(strings.TrimSpace(raw))
|
||||
start := strings.Index(s, "{")
|
||||
end := strings.LastIndex(s, "}")
|
||||
if start < 0 || end <= start {
|
||||
return s
|
||||
}
|
||||
var parsed struct {
|
||||
Summary string `json:"summary"`
|
||||
}
|
||||
if err := json.Unmarshal([]byte(s[start:end+1]), &parsed); err != nil {
|
||||
return s
|
||||
}
|
||||
// An empty field is the model saying nothing, so hand back nothing. Returning
|
||||
// the raw object here would write `{"summary":""}` into his notes.
|
||||
return strings.TrimSpace(parsed.Summary)
|
||||
}
|
||||
|
||||
// captureWiring — the recorder plus what it needs to write the result down.
|
||||
|
||||
@@ -116,3 +116,29 @@ func TestStopReturnsTranscriptAndNotesItWithoutASummary(t *testing.T) {
|
||||
t.Fatalf("the meeting left no note behind: %+v", notes)
|
||||
}
|
||||
}
|
||||
|
||||
// The summary path is JSON-wrapped by summaryGrammar, and internal/capture must
|
||||
// keep seeing plain prose. These cover the wrapper and every way it can be
|
||||
// absent or broken, because a meeting summary is written once and not retried.
|
||||
func TestUnwrapSummary(t *testing.T) {
|
||||
cases := []struct {
|
||||
name string
|
||||
in string
|
||||
want string
|
||||
}{
|
||||
{"grammar output", `{"summary": "решили купить насос"}`, "решили купить насос"},
|
||||
{"multiline field", `{"summary": "- насос\n- бюджет"}`, "- насос\n- бюджет"},
|
||||
{"empty marker survives", `{"summary": "пусто"}`, "пусто"},
|
||||
{"empty field says nothing", `{"summary": ""}`, ""},
|
||||
{"thinking prefix", "<think>hm</think>\n{\"summary\": \"итог\"}", "итог"},
|
||||
{"no grammar, plain prose", "решили купить насос", "решили купить насос"},
|
||||
{"broken json falls back", `{"summary": "обрыв`, `{"summary": "обрыв`},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
if got := unwrapSummary(c.in); got != c.want {
|
||||
t.Errorf("unwrapSummary(%q) = %q, want %q", c.in, got, c.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The chat path must answer when llama-server is down (Vikunja #45 step 4).
|
||||
// Both halves of a turn call the model — the router and the replier — and each
|
||||
// has its own floor: the cascade falls to the classifier, the replier falls to
|
||||
// the stub. This wires a client at a closed port so both floors are exercised
|
||||
// by a dial error rather than by a stubbed error value.
|
||||
func TestChatAnswersWithNoLlamaServer(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(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.replier = newLLMReplier(dead, nil)
|
||||
|
||||
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
for _, utt := range []string{
|
||||
"привет",
|
||||
"запиши что кофе закончился",
|
||||
"что у меня сегодня",
|
||||
} {
|
||||
reply := h.handleText(ctx, "web", utt)
|
||||
if reply == "" {
|
||||
t.Errorf("%q answered with nothing; a dead model must degrade to the stub", utt)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// daemonAPI.Chat reports an error only when the voice path was never wired.
|
||||
// A turn that reaches handleText always carries text, which is what keeps
|
||||
// mavweb's /api/chat off its error branch when the model is down.
|
||||
func TestChatAPIErrsOnlyWhenUnwired(t *testing.T) {
|
||||
d := &daemonAPI{}
|
||||
if _, err := d.Chat(context.Background(), "web", "привет"); err == nil {
|
||||
t.Fatal("an unwired daemon must say so")
|
||||
}
|
||||
d.chatFn = func(context.Context, string, string) string { return "" }
|
||||
if _, err := d.Chat(context.Background(), "web", "привет"); err != nil {
|
||||
t.Fatalf("a wired daemon must not error: %v", err)
|
||||
}
|
||||
}
|
||||
+45
-34
@@ -33,19 +33,10 @@ var wantedSlots = map[router.Intent][]dialogue.Slot{
|
||||
router.IntentAct: {dialogue.SlotFn},
|
||||
}
|
||||
|
||||
// clarifyQuestions — one short question per missing slot.
|
||||
//
|
||||
// These are fixed templates, not model output. The resident model is a 0.8B; it
|
||||
// would wander, and a question whose wording changes every time is harder to
|
||||
// answer than a blunt one that always reads the same. They are infinitive
|
||||
// questions, so there is no gender agreement to get wrong; the feminine
|
||||
// self-reference lives in the reply she gives when she drops the request.
|
||||
var clarifyQuestions = map[dialogue.Slot]string{
|
||||
dialogue.SlotTime: "Когда?",
|
||||
dialogue.SlotText: "О чём напомнить?",
|
||||
dialogue.SlotKey: "Что записать?",
|
||||
dialogue.SlotFn: "Что сделать?",
|
||||
}
|
||||
// The questions themselves live in clarifytemplates.go, one list per slot,
|
||||
// picked by attempt (Vikunja #457). The first ask is the short one this map
|
||||
// used to hold; a re-ask says it differently, because a question he already
|
||||
// failed to answer is the worst one to repeat unchanged.
|
||||
|
||||
// clarifyGaveUp — she is out of questions and still does not have the slot. She
|
||||
// says so out loud: dropping the request in silence would leave him thinking it
|
||||
@@ -106,11 +97,11 @@ func trimClarifyExpired(s string) string {
|
||||
// out, and "" when nothing was parked. Call it right after
|
||||
// resolveClarifyAnswer: a live question is answered there, an expired one is
|
||||
// only reported here — the words themselves still go on to be routed fresh.
|
||||
func (h *reactiveHandler) clarifyExpiredNotice() string {
|
||||
func (h *reactiveHandler) clarifyExpiredNotice(ctx context.Context) string {
|
||||
if h.clarifyStore == nil {
|
||||
return ""
|
||||
}
|
||||
if !h.clarifyStore.TakeExpired(voiceDialogueID, h.now()) {
|
||||
if !h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now()) {
|
||||
return ""
|
||||
}
|
||||
log.Printf("voice: clarify — parked question expired, telling him and routing the words fresh")
|
||||
@@ -147,7 +138,7 @@ func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
|
||||
if len(missing) == 0 {
|
||||
return "", "", false
|
||||
}
|
||||
q, ok := clarifyQuestions[missing[0]]
|
||||
q, ok := clarifyQuestionFor(missing[0], 1)
|
||||
if !ok {
|
||||
return "", "", false
|
||||
}
|
||||
@@ -157,7 +148,7 @@ func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
|
||||
// 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.
|
||||
func (h *reactiveHandler) askClarify(dec router.Decision) (string, bool) {
|
||||
func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (string, bool) {
|
||||
if h.clarifyStore == nil {
|
||||
return "", false
|
||||
}
|
||||
@@ -165,7 +156,7 @@ func (h *reactiveHandler) askClarify(dec router.Decision) (string, bool) {
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
|
||||
Intent: dialogue.Intent(dec.Intent),
|
||||
Slots: toDialogueSlots(dec.Slots),
|
||||
Missing: []dialogue.Slot{slot},
|
||||
@@ -192,7 +183,7 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
|
||||
if h.clarifyStore == nil {
|
||||
return "", false
|
||||
}
|
||||
q := h.clarifyStore.Get(voiceDialogueID, h.now())
|
||||
q := h.clarifyStore.Get(dialogueIDOf(ctx), h.now())
|
||||
if q == nil {
|
||||
return "", false
|
||||
}
|
||||
@@ -206,9 +197,9 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
|
||||
// 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(q, merged, text), true
|
||||
return h.reaskOrGiveUp(ctx, q, merged, text), true
|
||||
}
|
||||
h.clarifyStore.Delete(voiceDialogueID)
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
|
||||
// One gap filled is not the same as a complete request. askClarify parks
|
||||
// only the first gap, because one question per turn is the rule, but a
|
||||
@@ -217,7 +208,7 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
|
||||
// a reminder with no time, which answered "не получилось разобрать время
|
||||
// напоминания." — an error for a request she never finished asking about.
|
||||
// Re-enter the loop instead, one question at a time as before.
|
||||
if reply, asked := h.askRemainingGap(q, intent, merged); asked {
|
||||
if reply, asked := h.askRemainingGap(ctx, q, intent, merged); asked {
|
||||
return reply, true
|
||||
}
|
||||
|
||||
@@ -261,16 +252,18 @@ func foldAnswerIntoUtterance(utterance, subject string) string {
|
||||
// The attempt budget is shared with the re-ask path on purpose. A second gap
|
||||
// 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(q *dialogue.PendingQuestion, intent router.Intent, merged dialogue.Slots) (string, bool) {
|
||||
func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.PendingQuestion, intent router.Intent, merged dialogue.Slots) (string, bool) {
|
||||
remaining := dialogue.StillMissing(wantedSlots[intent], merged)
|
||||
if len(remaining) == 0 {
|
||||
return "", false
|
||||
}
|
||||
question, ok := clarifyQuestions[remaining[0]]
|
||||
// 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)
|
||||
if !ok || !q.CanAsk() {
|
||||
return "", false
|
||||
}
|
||||
h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
|
||||
Intent: q.Intent,
|
||||
Slots: merged,
|
||||
Missing: []dialogue.Slot{remaining[0]},
|
||||
@@ -287,13 +280,13 @@ func (h *reactiveHandler) askRemainingGap(q *dialogue.PendingQuestion, intent ro
|
||||
// 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(q *dialogue.PendingQuestion, merged dialogue.Slots, text string) string {
|
||||
func (h *reactiveHandler) reaskOrGiveUp(ctx context.Context, q *dialogue.PendingQuestion, merged dialogue.Slots, text string) string {
|
||||
question := ""
|
||||
if len(q.Missing) > 0 {
|
||||
question = clarifyQuestions[q.Missing[0]]
|
||||
question, _ = clarifyQuestionFor(q.Missing[0], q.Attempts+1)
|
||||
}
|
||||
if question == "" || !q.CanAsk() {
|
||||
h.clarifyStore.Delete(voiceDialogueID)
|
||||
h.clarifyStore.Delete(dialogueIDOf(ctx))
|
||||
log.Printf("voice: clarify — gave up on %v after %d question(s), answer was %q", q.Missing, q.Attempts, text)
|
||||
return clarifyGaveUp
|
||||
}
|
||||
@@ -302,7 +295,7 @@ func (h *reactiveHandler) reaskOrGiveUp(q *dialogue.PendingQuestion, merged dial
|
||||
q.Slots = merged
|
||||
q.Attempts++
|
||||
q.Asked = h.now()
|
||||
h.clarifyStore.Put(voiceDialogueID, q)
|
||||
h.clarifyStore.Put(dialogueIDOf(ctx), q)
|
||||
log.Printf("voice: clarify — answer %q did not fill %v, asking again (attempt %d)", text, q.Missing, q.Attempts)
|
||||
return question
|
||||
}
|
||||
@@ -312,9 +305,9 @@ func (h *reactiveHandler) reaskOrGiveUp(q *dialogue.PendingQuestion, merged dial
|
||||
func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decision) string {
|
||||
if h.dialogueSessions != nil {
|
||||
now := h.now()
|
||||
prev := h.dialogueSessions.Get(voiceDialogueID, now)
|
||||
prev := h.dialogueSessions.Get(dialogueIDOf(ctx), now)
|
||||
dec = followUpMerge(prev, dec, now)
|
||||
h.rememberTurn(prev, dec, now)
|
||||
h.rememberTurn(ctx, prev, dec, now)
|
||||
}
|
||||
reply := h.applyAction(ctx, dec)
|
||||
if reply == "" {
|
||||
@@ -330,7 +323,7 @@ func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decisi
|
||||
// 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(prev *dialogue.Session, dec router.Decision, now time.Time) {
|
||||
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{
|
||||
@@ -348,9 +341,27 @@ func (h *reactiveHandler) rememberTurn(prev *dialogue.Session, dec router.Decisi
|
||||
if dec.Intent == router.IntentChat {
|
||||
ttl = 15 * time.Minute // conversational turns should last longer
|
||||
}
|
||||
h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
|
||||
// A system or query turn often carries no Text slot at all — a stage-0
|
||||
// grammar fills none. The next turn may be an ellipsis ("а завтра?"),
|
||||
// which knows the day but not what was asked ABOUT, so keep the raw
|
||||
// utterance where continuation.go can find it. Only these two intents:
|
||||
// everywhere else Text is a payload and must stay what the router put in.
|
||||
//
|
||||
// Overwritten, not filled: rememberTurn runs AFTER followUpMerge, which
|
||||
// has already inherited a Text from the previous same-intent turn, so a
|
||||
// fill-if-empty rule keeps the OLD topic for ever. Seen on the deployed
|
||||
// daemon 01-08-2026 — "во сколько у меня встреча" then "какие у меня
|
||||
// планы" then "а завтра?" continued the meeting, two turns stale.
|
||||
//
|
||||
// A continuation is the exception and keeps what it inherited: its
|
||||
// utterance is the ellipsis, and the topic it carries is the real one.
|
||||
slots := toDialogueSlots(dec.Slots)
|
||||
if !dec.Continued && (dec.Intent == router.IntentSystem || dec.Intent == router.IntentQuery) {
|
||||
slots.Text = dec.Utterance
|
||||
}
|
||||
h.dialogueSessions.Put(dialogueIDOf(ctx), &dialogue.Session{
|
||||
Intent: dialogue.Intent(dec.Intent),
|
||||
Slots: toDialogueSlots(dec.Slots),
|
||||
Slots: slots,
|
||||
Timestamp: now,
|
||||
TTL: ttl,
|
||||
History: history,
|
||||
|
||||
+126
-27
@@ -81,7 +81,7 @@ func TestClarifyReminderCompletesOnAnswer(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
|
||||
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
|
||||
if !asked || question != "Когда?" {
|
||||
t.Fatalf("expected the time question, got %q asked=%v", question, asked)
|
||||
}
|
||||
@@ -112,7 +112,7 @@ func TestClarifyFactCompletesOnAnswer(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши")); !asked {
|
||||
t.Fatal("a fact with no key should be asked about")
|
||||
}
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "пил воду"); !handled || reply == clarifyGaveUp {
|
||||
@@ -128,7 +128,7 @@ func TestClarifyAnswerAfterTTLIsANewRequest(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, now := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
*now = now.Add(clarifyTTL + time.Second)
|
||||
@@ -147,7 +147,7 @@ func TestClarifyAsksThreeTimesThenSaysSo(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a first question")
|
||||
}
|
||||
// Two more unclear answers ⇒ two more questions (3 asks in total).
|
||||
@@ -156,8 +156,14 @@ func TestClarifyAsksThreeTimesThenSaysSo(t *testing.T) {
|
||||
if !handled {
|
||||
t.Fatalf("answer %d must be consumed as an answer", i)
|
||||
}
|
||||
if reply != "Когда?" {
|
||||
t.Fatalf("attempt %d should ask again, got %q", i, reply)
|
||||
// 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)
|
||||
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 {
|
||||
t.Fatalf("attempt %d repeated the first wording: %q", i, reply)
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) == nil {
|
||||
t.Fatalf("attempt %d must leave the question armed", i)
|
||||
@@ -185,7 +191,7 @@ func TestClarifyMaxAttemptsIsConfigurable(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
h.clarifyMaxAttempts = 1
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
if reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю"); !handled || reply != clarifyGaveUp {
|
||||
@@ -199,7 +205,7 @@ func TestClarifyRestatedAnswerWins(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
// First answer parses, but re-park it by hand as if she had asked again:
|
||||
@@ -232,7 +238,7 @@ func TestClarifiedActOffAllowlistIsStillRefused(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
marker := filepath.Join(t.TempDir(), "not-allowed-ran")
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
|
||||
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)
|
||||
@@ -260,7 +266,7 @@ func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
|
||||
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")
|
||||
@@ -284,7 +290,7 @@ func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
|
||||
clarifyDec(router.IntentQuery, router.Slots{Text: "ммм"}, "ммм"),
|
||||
clarifyDec(router.IntentNote, router.Slots{Text: "..."}, "..."),
|
||||
} {
|
||||
if question, asked := h.askClarify(dec); asked {
|
||||
if question, asked := h.askClarify(context.Background(), dec); asked {
|
||||
t.Fatalf("intent %s should keep the canned reply, got %q", dec.Intent, question)
|
||||
}
|
||||
}
|
||||
@@ -296,29 +302,29 @@ func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
|
||||
// TestClarifyExpiryIsAnnouncedAndWordsStillRoute — his answer lands after the
|
||||
// TTL: she must say the old request is gone AND still answer the new words.
|
||||
func TestClarifyExpiryIsAnnouncedAndWordsStillRoute(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, ""))
|
||||
h, _, now := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
h.embedder = emb
|
||||
h.recall.embedder = emb
|
||||
h.router = buildRouter(emb, h.matcher, 0.55, nil)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
*now = now.Add(clarifyTTL + time.Second)
|
||||
|
||||
reply := h.handleText(ctx, "как дела")
|
||||
reply := h.handleText(ctx, "", "как дела")
|
||||
if !isClarifyExpired(reply) {
|
||||
t.Fatalf("expired question must be announced first, got %q", reply)
|
||||
}
|
||||
if trimClarifyExpired(reply) == "" {
|
||||
t.Fatalf("the new words must still be answered, got only the notice: %q", reply)
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
|
||||
if h.clarifyStore.Get(textDialogueID, h.now()) != nil {
|
||||
t.Fatal("the expired question must be gone")
|
||||
}
|
||||
// The notice is said once, not on every later utterance.
|
||||
if reply := h.handleText(ctx, "как дела"); isClarifyExpired(reply) {
|
||||
if reply := h.handleText(ctx, "", "как дела"); isClarifyExpired(reply) {
|
||||
t.Fatalf("notice repeated on a later turn: %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -340,7 +346,7 @@ func TestClarifyAsksAboutTheSecondGapToo(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
|
||||
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{}, "напомни"))
|
||||
question, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{}, "напомни"))
|
||||
if !asked || question != "О чём напомнить?" {
|
||||
t.Fatalf("expected the subject question, got %q asked=%v", question, asked)
|
||||
}
|
||||
@@ -349,8 +355,11 @@ func TestClarifyAsksAboutTheSecondGapToo(t *testing.T) {
|
||||
if !handled {
|
||||
t.Fatal("the answer must be consumed as an answer")
|
||||
}
|
||||
if reply != "Когда?" {
|
||||
t.Fatalf("a filled subject with no time must ask about the time, got %q", reply)
|
||||
// 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)
|
||||
if reply != want {
|
||||
t.Fatalf("a filled subject with no time must ask about the time as %q, got %q", want, reply)
|
||||
}
|
||||
q := h.clarifyStore.Get(voiceDialogueID, h.now())
|
||||
if q == nil {
|
||||
@@ -380,7 +389,7 @@ func TestClarifySecondGapRespectsTheAttemptCap(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
h.clarifyMaxAttempts = 1
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{}, "напомни")); !asked {
|
||||
t.Fatal("expected the subject question")
|
||||
}
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "позвонить маме")
|
||||
@@ -411,8 +420,9 @@ func TestClarifyProseHoldsThePersona(t *testing.T) {
|
||||
eval.CheckCringe: true,
|
||||
}
|
||||
lines := append([]string{clarifyGaveUp}, clarifyExpiredVariants...)
|
||||
for _, q := range clarifyQuestions {
|
||||
lines = append(lines, q)
|
||||
lines = append(lines, clarifyMissedVariants...)
|
||||
for _, variants := range clarifyQuestionVariants {
|
||||
lines = append(lines, variants...)
|
||||
}
|
||||
for _, line := range lines {
|
||||
for _, r := range eval.RunChecks(eval.Case{}, line, "neutral") {
|
||||
@@ -440,10 +450,10 @@ func TestClarifyProseHoldsThePersona(t *testing.T) {
|
||||
// The confirm turn used to return before the notice was even computed, so he
|
||||
// answered the confirm and never heard that the older request was let go.
|
||||
func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, ""))
|
||||
h, _, now := newClarifyHandler(t)
|
||||
|
||||
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question")
|
||||
}
|
||||
// A confirm parked with a longer life than the question, so only the
|
||||
@@ -451,7 +461,7 @@ func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
|
||||
h.pending = &pendingAct{fn: "delete_backups", phrase: "удалить бэкапы", expiry: now.Add(time.Hour)}
|
||||
*now = now.Add(clarifyTTL + time.Second)
|
||||
|
||||
reply := h.handleText(ctx, "нет")
|
||||
reply := h.handleText(ctx, "", "нет")
|
||||
if !isClarifyExpired(reply) {
|
||||
t.Fatalf("the expired question must be announced on a confirm turn too, got %q", reply)
|
||||
}
|
||||
@@ -461,7 +471,96 @@ func TestExpiryNoticeSurvivesAConfirmTurn(t *testing.T) {
|
||||
if h.pending != nil {
|
||||
t.Fatal("the confirm must still have been consumed")
|
||||
}
|
||||
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
|
||||
if h.clarifyStore.Get(textDialogueID, h.now()) != nil {
|
||||
t.Fatal("the expired question must be gone")
|
||||
}
|
||||
}
|
||||
|
||||
// The other half of the subject question: his answer must fill the empty slot,
|
||||
// not replace the request. Slots.Text used to be the whole raw utterance for
|
||||
// every intent, so the branch that fills a text slot could only ever overwrite
|
||||
// (Vikunja #383). Here the parked request holds the hour and the answer holds
|
||||
// what to say at it, and the reminder that lands has both.
|
||||
func TestClarifySubjectAnswerFillsRatherThanClobbers(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, st, _ := newClarifyHandler(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"))
|
||||
if !asked || question != "О чём напомнить?" {
|
||||
t.Fatalf("expected the subject question, got %q asked=%v", question, asked)
|
||||
}
|
||||
|
||||
reply, handled := h.resolveClarifyAnswer(ctx, "позвонить маме")
|
||||
if !handled {
|
||||
t.Fatal("the answer to an open question must be consumed as an answer")
|
||||
}
|
||||
if reply == clarifyGaveUp {
|
||||
t.Fatalf("a good answer must not drop the request: %q", reply)
|
||||
}
|
||||
|
||||
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
|
||||
if err != nil || len(reminders) != 1 {
|
||||
t.Fatalf("clarified reminder was not created: reminders=%v err=%v", reminders, err)
|
||||
}
|
||||
if !strings.Contains(reminders[0].Payload, "маме") {
|
||||
t.Fatalf("the answer never reached the reminder: %q", reminders[0].Payload)
|
||||
}
|
||||
// The hour is the fire time, not a word in the body: the body is what she
|
||||
// says at the hour, and the time expression is stripped out of it
|
||||
// (Vikunja #469). Clobbering the parked request would show up here as a
|
||||
// reminder that fires at some other time than the one he asked for.
|
||||
if got := reminders[0].FireTs.UTC(); !got.Equal(at.UTC()) {
|
||||
t.Fatalf("the answer clobbered the original request: fires at %v, want %v", got, at.UTC())
|
||||
}
|
||||
}
|
||||
|
||||
// TestClarifyIsPerConversation — the parked question belongs to the reach that
|
||||
// was asked. Before this the clarify store had one global key, so a question
|
||||
// asked in the web chat and never answered captured the next utterance from
|
||||
// telegram, or from the mic, and answered it against a request the speaker had
|
||||
// never made (Vikunja #466).
|
||||
func TestClarifyIsPerConversation(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
web := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
telegram := withDialogueID(context.Background(), dialogueIDFor(sourceText, "telegram:42"))
|
||||
|
||||
if _, asked := h.askClarify(web, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question on the web conversation")
|
||||
}
|
||||
if _, handled := h.resolveClarifyAnswer(telegram, "в 11:00"); handled {
|
||||
t.Fatal("a question asked on the web must not eat a telegram utterance")
|
||||
}
|
||||
if _, handled := h.resolveClarifyAnswer(voiceCtx(), "в 11:00"); handled {
|
||||
t.Fatal("a question asked on the web must not eat what he says at the mic")
|
||||
}
|
||||
if reply, handled := h.resolveClarifyAnswer(web, "в 11:00"); !handled || reply == clarifyGaveUp {
|
||||
t.Fatalf("the asker's own answer must land, handled=%v reply=%q", handled, reply)
|
||||
}
|
||||
}
|
||||
|
||||
// voiceCtx — the mic's conversation, which carries no id of its own.
|
||||
func voiceCtx() context.Context {
|
||||
return withDialogueID(context.Background(), dialogueIDFor(sourceVoice, ""))
|
||||
}
|
||||
|
||||
// TestARestartExpiresTheParkedQuestion pins the Vikunja #385 decision: the
|
||||
// question dies with the process, and she does not claim to have let it go —
|
||||
// the words that follow are routed as a fresh request. Restarting is modelled
|
||||
// the way the daemon does it, by building a second handler over the same store.
|
||||
func TestARestartExpiresTheParkedQuestion(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
ctx := voiceCtx()
|
||||
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
|
||||
t.Fatal("expected a question before the restart")
|
||||
}
|
||||
|
||||
restarted, _, _ := newClarifyHandler(t)
|
||||
if _, handled := restarted.resolveClarifyAnswer(ctx, "в 11:00"); handled {
|
||||
t.Fatal("a question parked before the restart must not eat the next utterance")
|
||||
}
|
||||
if notice := restarted.clarifyExpiredNotice(ctx); notice != "" {
|
||||
t.Fatalf("notice = %q, want silence: nothing survived to expire", notice)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,109 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The clarify copy deck (Vikunja #457).
|
||||
//
|
||||
// Every clarify turn used to say one sentence per gap, and a re-ask repeated
|
||||
// that sentence word for word. A question he already failed to answer is the
|
||||
// worst one to ask again unchanged: the second wording is the one that tells
|
||||
// him which part she missed.
|
||||
//
|
||||
// Fixed templates, not model output, for the reason clarifyQuestions has always
|
||||
// given: the resident model would wander, and a question whose wording changes
|
||||
// at random is harder to answer than a blunt one. What changes here is that the
|
||||
// wording varies with the attempt rather than with a die roll — the first ask is
|
||||
// short, the second names the gap, the third spells it out.
|
||||
//
|
||||
// No schema_version, unlike internal/phraser/nudge_templates.go. These are Go
|
||||
// constants compiled into the daemon, so there is no file that can drift out of
|
||||
// step with the code that reads it.
|
||||
//
|
||||
// Persona holds: infinitive and imperative questions, so there is no gender
|
||||
// agreement to get wrong, "ты" throughout, and no pet names.
|
||||
var clarifyQuestionVariants = map[dialogue.Slot][]string{
|
||||
dialogue.SlotTime: {
|
||||
"Когда?",
|
||||
"Во сколько напомнить?",
|
||||
"Скажи время — например, «в семь вечера» или «через час».",
|
||||
},
|
||||
dialogue.SlotText: {
|
||||
"О чём напомнить?",
|
||||
"Что сказать тебе в это время?",
|
||||
"Скажи одной фразой, о чём напомнить.",
|
||||
},
|
||||
dialogue.SlotKey: {
|
||||
"Что записать?",
|
||||
"Что именно отметить?",
|
||||
"Назови, что записать — например, «выпил воды».",
|
||||
},
|
||||
dialogue.SlotFn: {
|
||||
"Что сделать?",
|
||||
"Какое действие выполнить?",
|
||||
"Назови действие — я умею только то, что ты мне разрешил.",
|
||||
},
|
||||
}
|
||||
|
||||
// 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
|
||||
// wrapping would ask the same short question he has already not answered.
|
||||
//
|
||||
// Deterministic on purpose, unlike clarifyExpiredLine: an expiry notice is the
|
||||
// same statement however it is worded, and a re-ask is not.
|
||||
func clarifyQuestionFor(slot dialogue.Slot, attempt int) (string, bool) {
|
||||
variants, ok := clarifyQuestionVariants[slot]
|
||||
if !ok || len(variants) == 0 {
|
||||
return "", false
|
||||
}
|
||||
i := attempt - 1
|
||||
if i < 0 {
|
||||
i = 0
|
||||
}
|
||||
if i >= len(variants) {
|
||||
i = len(variants) - 1
|
||||
}
|
||||
return variants[i], true
|
||||
}
|
||||
|
||||
// clarifyMissedVariants — she is asking for the whole utterance again, because
|
||||
// the gate fired on an intent with nothing identifiable to ask about (note,
|
||||
// query, chat, system are not in wantedSlots).
|
||||
//
|
||||
// Rotated like the expiry lines and for the same reason: this is the line he
|
||||
// hears whenever she misses him completely, so it is a line that repeats, and
|
||||
// the same sentence every time is what makes a house assistant sound like a
|
||||
// kiosk. All of them say the same two things — she did not catch it, and he
|
||||
// should say it again — because the wording may vary and the meaning may not.
|
||||
var clarifyMissedVariants = []string{
|
||||
"Не совсем поняла — скажи, пожалуйста, ещё раз.",
|
||||
"Я тебя не разобрала. Повтори, пожалуйста.",
|
||||
"Не уловила. Скажи это по-другому?",
|
||||
"Прости, не поняла — попробуй сказать иначе.",
|
||||
}
|
||||
|
||||
// clarifyMissedFor picks a wording by the utterance itself, so the same words
|
||||
// asked twice get the same answer and two different misses sound different.
|
||||
//
|
||||
// A hash, not rand: a test that drives an utterance twice must not depend on a
|
||||
// die roll, and the point of rotating is only that consecutive misses differ.
|
||||
func clarifyMissedFor(utterance string) string {
|
||||
var sum int
|
||||
for _, r := range utterance {
|
||||
sum += int(r)
|
||||
}
|
||||
return clarifyMissedVariants[sum%len(clarifyMissedVariants)]
|
||||
}
|
||||
|
||||
// clarifyMissedLine is the canned reply for a clarify decision she cannot turn
|
||||
// into a question. Returns "" for a decision that is not a clarify, so the
|
||||
// caller keeps its own reply.
|
||||
func clarifyMissedLine(dec router.Decision) string {
|
||||
if !dec.Clarify {
|
||||
return ""
|
||||
}
|
||||
return clarifyMissedFor(dec.Utterance)
|
||||
}
|
||||
@@ -0,0 +1,63 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Every slot she can ask about has a wording for every attempt she is allowed,
|
||||
// and no two attempts on one slot read the same. A deck with a repeated line is
|
||||
// the defect this deck exists to fix (Vikunja #457).
|
||||
func TestClarifyQuestionsVaryByAttempt(t *testing.T) {
|
||||
for slot, variants := range clarifyQuestionVariants {
|
||||
seen := map[string]bool{}
|
||||
for _, v := range variants {
|
||||
if v == "" {
|
||||
t.Errorf("%s: empty wording in the deck", slot)
|
||||
}
|
||||
if seen[v] {
|
||||
t.Errorf("%s: repeated wording %q", slot, v)
|
||||
}
|
||||
seen[v] = true
|
||||
}
|
||||
for attempt := 1; attempt <= len(variants); attempt++ {
|
||||
got, ok := clarifyQuestionFor(slot, attempt)
|
||||
if !ok || got != variants[attempt-1] {
|
||||
t.Errorf("%s attempt %d = %q ok=%v, want %q", slot, attempt, got, ok, variants[attempt-1])
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Past the end she keeps the most explicit wording. Wrapping round would ask
|
||||
// the short question he has already not answered twice.
|
||||
func TestClarifyQuestionPastTheEndKeepsTheLastWording(t *testing.T) {
|
||||
last := clarifyQuestionVariants[dialogue.SlotTime][len(clarifyQuestionVariants[dialogue.SlotTime])-1]
|
||||
for _, attempt := range []int{0, 4, 9} {
|
||||
if got, _ := clarifyQuestionFor(dialogue.SlotTime, attempt); attempt > 1 && got != last {
|
||||
t.Errorf("attempt %d = %q, want the last wording %q", attempt, got, last)
|
||||
}
|
||||
}
|
||||
if _, ok := clarifyQuestionFor("nonesuch", 1); ok {
|
||||
t.Error("an unknown slot must have no question")
|
||||
}
|
||||
}
|
||||
|
||||
// The missed line is stable for one utterance and absent for a decision that is
|
||||
// not a clarify.
|
||||
func TestClarifyMissedLine(t *testing.T) {
|
||||
d := router.Decision{Clarify: true, Utterance: "мгм"}
|
||||
first := clarifyMissedLine(d)
|
||||
if first == "" || first != clarifyMissedLine(d) {
|
||||
t.Fatalf("the missed line must be stable for one utterance, got %q", first)
|
||||
}
|
||||
if got := clarifyMissedLine(router.Decision{Intent: router.IntentNote}); got != "" {
|
||||
t.Errorf("a decision that is not a clarify got %q", got)
|
||||
}
|
||||
// The empty utterance still gets a line: she has to say something.
|
||||
if got := clarifyMissedLine(router.Decision{Clarify: true}); got == "" {
|
||||
t.Error("an empty utterance must still be answered out loud")
|
||||
}
|
||||
}
|
||||
+25
-19
@@ -6,6 +6,7 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -107,20 +108,24 @@ func (h *reactiveHandler) confirmResolvers(ctx context.Context) []confirmResolve
|
||||
return pr != nil && !h.now().After(pr.expiry)
|
||||
},
|
||||
yes: func() string {
|
||||
// Only record the acceptance. The tick loop reads accepted
|
||||
// routines and nudges on their own interval. Building a
|
||||
// reminder here made a routine fire exactly once (Vikunja #366).
|
||||
if err := h.dataStore.AcceptProposedRoutine(ctx, pr.routineID, h.now()); err != nil {
|
||||
log.Printf("voice: accept proposed routine: %v", err)
|
||||
return "не получилось запомнить рутину."
|
||||
}
|
||||
return "буду напоминать."
|
||||
// Voice does NOT accept (Vikunja #367). Accepting hands the
|
||||
// tick loop a standing new reason to speak, which is the same
|
||||
// tier as enabling a tool — and DESIGN.md § "surface caps
|
||||
// authority" says a room mic, reachable by anyone present, is
|
||||
// structurally incapable of layer 3. So a spoken "да" leaves
|
||||
// the row 'proposed' and points at the authed page, where the
|
||||
// accept button is gated at step-up. The convenience of
|
||||
// answering out loud stays; the authority does not move.
|
||||
//
|
||||
// Acceptance itself is recorded by /routines, and the tick
|
||||
// loop nudges on the interval from there (Vikunja #366).
|
||||
return phraser.C(phraser.ConfirmRoutineAuthed, nil)
|
||||
},
|
||||
no: func() string {
|
||||
if err := h.dataStore.DismissProposedRoutine(ctx, pr.routineID); err != nil {
|
||||
log.Printf("voice: dismiss proposed routine: %v", err)
|
||||
}
|
||||
return "хорошо, не буду."
|
||||
return phraser.C(phraser.ConfirmRoutineNo, nil)
|
||||
},
|
||||
},
|
||||
// Hexis execution confirm. Bound to the exact capability + target that
|
||||
@@ -133,7 +138,7 @@ func (h *reactiveHandler) confirmResolvers(ctx context.Context) []confirmResolve
|
||||
yes: func() string {
|
||||
return h.execHexis(ctx, hx.capabilityID, hx.capName, hx.entityID, hx.displayName)
|
||||
},
|
||||
no: func() string { return "отменила." },
|
||||
no: func() string { return phraser.C(phraser.ConfirmCancelled, nil) },
|
||||
},
|
||||
// Tool confirm.
|
||||
{
|
||||
@@ -146,16 +151,16 @@ func (h *reactiveHandler) confirmResolvers(ctx context.Context) []confirmResolve
|
||||
if err != nil {
|
||||
log.Printf("voice: tool %s (confirmed): %v", p.fn, err)
|
||||
if out != "" {
|
||||
return "не получилось выполнить команду: " + firstLine(out)
|
||||
return phraser.A(phraser.ActFailOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "не получилось выполнить команду."
|
||||
return phraser.A(phraser.ActFail, nil)
|
||||
}
|
||||
if out != "" {
|
||||
return "готово: " + firstLine(out)
|
||||
return phraser.A(phraser.ActDoneOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "готово."
|
||||
return phraser.A(phraser.ActDone, nil)
|
||||
},
|
||||
no: func() string { return "отменила." },
|
||||
no: func() string { return phraser.C(phraser.ConfirmCancelled, nil) },
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -166,17 +171,18 @@ func (h *reactiveHandler) confirmResolvers(ctx context.Context) []confirmResolve
|
||||
func (h *reactiveHandler) proposeGap(ctx context.Context, dec router.Decision) string {
|
||||
name := firstWord(stripWake(dec.Utterance))
|
||||
if name == "" {
|
||||
return "не разобрала команду — попробуй иначе."
|
||||
return phraser.C(phraser.ProposeNoVerb, nil)
|
||||
}
|
||||
vars := map[string]string{"name": name}
|
||||
newly, err := h.api.ProposeTool(ctx, name, dec.Utterance, "", h.now())
|
||||
if err != nil {
|
||||
log.Printf("voice: propose tool %q: %v", name, err)
|
||||
return "команды «" + name + "» нет в списке разрешённых."
|
||||
return phraser.C(phraser.ProposeFailed, vars)
|
||||
}
|
||||
if newly {
|
||||
return "команды «" + name + "» нет в списке. Предложила её добавить — включи через клиент."
|
||||
return phraser.C(phraser.ProposeNew, vars)
|
||||
}
|
||||
return "команды «" + name + "» пока нет в списке — она уже предложена, включи через клиент."
|
||||
return phraser.C(phraser.ProposeAlready, vars)
|
||||
}
|
||||
|
||||
// confirmVerdict — the parse of a y/n confirm answer.
|
||||
|
||||
@@ -0,0 +1,125 @@
|
||||
// Elliptical follow-ups — "а завтра?" after "какие напоминания на сегодня".
|
||||
//
|
||||
// These carry no intent of their own. Two words, one of them a particle, and
|
||||
// everything that makes the utterance meaningful lives in the turn before it.
|
||||
// Sent to the router they get whatever the model guesses, which on a 1.7B is
|
||||
// close to a coin flip, and the guess costs ~2.7s to obtain.
|
||||
//
|
||||
// followUpMerge (followup.go) cannot help: it inherits SLOTS once the intent is
|
||||
// known, and here the intent is the missing part. So this runs before the
|
||||
// router and answers from the previous turn directly, which is both correct by
|
||||
// construction and free.
|
||||
package main
|
||||
|
||||
import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// continuationMaxTokens — an ellipsis is short by definition. Past four tokens
|
||||
// the utterance carries enough of its own content to be routed on its merits,
|
||||
// and inheriting an intent for it would be overreach.
|
||||
const continuationMaxTokens = 4
|
||||
|
||||
// continuationParticles — the words that open a follow-up. A leading particle
|
||||
// is one of the two ways in; the other is an utterance that is nothing but a
|
||||
// date ("завтра?").
|
||||
var continuationParticles = map[string]bool{
|
||||
"а": true, "и": true, "ну": true,
|
||||
"what": true, "and": true, "how": true,
|
||||
}
|
||||
|
||||
// continuableIntents — which intents an ellipsis may inherit.
|
||||
//
|
||||
// query and system are questions: asking the same question about a different
|
||||
// day is exactly what "а завтра?" means, and re-aiming the Time slot answers it
|
||||
// completely.
|
||||
//
|
||||
// The rest are excluded on purpose. fact and note would write something he did
|
||||
// not say — "поужинал" then "а вчера?" is a question about yesterday, not a
|
||||
// claim about it. chat has no slot to re-aim. act is the dangerous one: an
|
||||
// allowlisted fn inherited by a two-word utterance is a way to run a
|
||||
// destructive command nobody typed, and no follow-up is worth that.
|
||||
//
|
||||
// reminder was in this list and came out after a live check on 01-08-2026. A
|
||||
// reminder's payload is its Text, and the Text embeds the day word it was
|
||||
// created with: continuing "напомни сегодня о событиях" with "а завтра?" fires
|
||||
// tomorrow with the text still reading "сегодня". Re-aiming Time is not enough
|
||||
// when the day is also written into the payload, and rewriting the payload
|
||||
// needs the date's span in the string, which ParseCalendarDate does not report.
|
||||
var continuableIntents = map[dialogue.Intent]bool{
|
||||
dialogue.IntentQuery: true,
|
||||
dialogue.IntentSystem: true,
|
||||
}
|
||||
|
||||
// continuationDecision reads an utterance as "the previous question, but for
|
||||
// this other day". Returns ok=false whenever anything is uncertain, which
|
||||
// hands the turn back to the ordinary router path.
|
||||
//
|
||||
// The date is what makes this safe. An ellipsis with no parseable day is just
|
||||
// a short utterance, and short utterances are the router's job.
|
||||
func continuationDecision(prev *dialogue.Session, text string, now time.Time) (router.Decision, bool) {
|
||||
if prev == nil || prev.IsExpired(now) || !continuableIntents[prev.Intent] {
|
||||
return router.Decision{}, false
|
||||
}
|
||||
tokens := quietTokens(text)
|
||||
if len(tokens) == 0 || len(tokens) > continuationMaxTokens {
|
||||
return router.Decision{}, false
|
||||
}
|
||||
day, ok := router.ParseCalendarDate(text, now)
|
||||
if !ok {
|
||||
return router.Decision{}, false
|
||||
}
|
||||
// Either it opens with a particle, or the whole utterance is the date.
|
||||
if !continuationParticles[tokens[0]] && !isBareDate(tokens, day, now) {
|
||||
return router.Decision{}, false
|
||||
}
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: text,
|
||||
Intent: router.Intent(prev.Intent),
|
||||
Confidence: 1.0,
|
||||
Stage: 0,
|
||||
Continued: true,
|
||||
Slots: router.Slots{
|
||||
Key: prev.Slots.Key,
|
||||
HasKey: prev.Slots.HasKey,
|
||||
Value: prev.Slots.Value,
|
||||
Text: prev.Slots.Text,
|
||||
// Fn/Args are deliberately not carried: continuableIntents
|
||||
// excludes act, so there is never one to carry.
|
||||
Time: day,
|
||||
HasTime: true,
|
||||
},
|
||||
}
|
||||
return dec, true
|
||||
}
|
||||
|
||||
// isBareDate reports whether the utterance is nothing but its date expression.
|
||||
// "завтра" and "на выходных" qualify; "напомни завтра" does not, because the
|
||||
// verb is content of its own and belongs to the router.
|
||||
//
|
||||
// Implemented by re-parsing each token: if every token that is not part of a
|
||||
// date expression is a preposition or a question mark's leftovers, the
|
||||
// utterance is bare. Cheap enough at four tokens.
|
||||
func isBareDate(tokens []string, day time.Time, now time.Time) bool {
|
||||
for _, t := range tokens {
|
||||
if continuationFillers[t] {
|
||||
continue
|
||||
}
|
||||
if d, ok := router.ParseCalendarDate(t, now); ok && d.Equal(day) {
|
||||
continue
|
||||
}
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// continuationFillers — tokens that carry no content of their own inside a
|
||||
// date expression ("на выходных", "в среду").
|
||||
var continuationFillers = map[string]bool{
|
||||
"на": true, "в": true, "во": true, "за": true, "про": true,
|
||||
"about": true, "on": true, "for": true,
|
||||
}
|
||||
@@ -0,0 +1,171 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
var contNow = time.Date(2026, 8, 1, 12, 0, 0, 0, time.UTC)
|
||||
|
||||
func contSession(intent dialogue.Intent, key string) *dialogue.Session {
|
||||
return &dialogue.Session{
|
||||
Intent: intent,
|
||||
Slots: dialogue.Slots{Key: key, HasKey: key != "", Text: "какие напоминания на сегодня"},
|
||||
Timestamp: contNow.Add(-30 * time.Second),
|
||||
TTL: 2 * time.Minute,
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationInheritsTheQuestion(t *testing.T) {
|
||||
prev := contSession(dialogue.IntentQuery, "water")
|
||||
dec, ok := continuationDecision(prev, "а завтра?", contNow)
|
||||
if !ok {
|
||||
t.Fatal("continuationDecision returned false, want a decision")
|
||||
}
|
||||
if dec.Intent != router.IntentQuery {
|
||||
t.Errorf("intent = %q, want query", dec.Intent)
|
||||
}
|
||||
if dec.Slots.Key != "water" || !dec.Slots.HasKey {
|
||||
t.Errorf("key = %q, want water carried over", dec.Slots.Key)
|
||||
}
|
||||
if !dec.Slots.HasTime {
|
||||
t.Fatal("no time slot; the whole point is re-aiming the day")
|
||||
}
|
||||
if got, want := dec.Slots.Time.Format("2006-01-02"), "2026-08-02"; got != want {
|
||||
t.Errorf("time = %s, want %s", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationAcceptsABareDate(t *testing.T) {
|
||||
prev := contSession(dialogue.IntentQuery, "water")
|
||||
for _, s := range []string{"завтра?", "вчера", "а вчера?", "и завтра"} {
|
||||
if _, ok := continuationDecision(prev, s, contNow); !ok {
|
||||
t.Errorf("continuationDecision(%q) = false, want true", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationDeclinesWhatIsNotAnEllipsis(t *testing.T) {
|
||||
prev := contSession(dialogue.IntentQuery, "water")
|
||||
for _, s := range []string{
|
||||
// No date to re-aim at — an ordinary short utterance, the router's job.
|
||||
"а что там", "а бэкап?", "привет", "",
|
||||
// Content of its own: the verb is not an ellipsis.
|
||||
"напомни завтра позвонить маме",
|
||||
// Too long to be an ellipsis even with a date in it.
|
||||
"а что у меня стоит в календаре на завтра",
|
||||
} {
|
||||
if _, ok := continuationDecision(prev, s, contNow); ok {
|
||||
t.Errorf("continuationDecision(%q) = true, want false", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationDeclinesUncontinuableIntents(t *testing.T) {
|
||||
// act is the one that matters: inheriting an allowlisted fn from a
|
||||
// two-word utterance would be a way to run a destructive command.
|
||||
// reminder is here because its payload is its Text, and the Text embeds
|
||||
// the day word it was created with — see continuableIntents.
|
||||
for _, in := range []dialogue.Intent{
|
||||
dialogue.IntentAct, dialogue.IntentFact, dialogue.IntentNote,
|
||||
dialogue.IntentChat, dialogue.IntentReminder,
|
||||
} {
|
||||
if _, ok := continuationDecision(contSession(in, "water"), "а завтра?", contNow); ok {
|
||||
t.Errorf("continuationDecision inherited intent %q, want refusal", in)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationDeclinesWithoutALiveSession(t *testing.T) {
|
||||
if _, ok := continuationDecision(nil, "а завтра?", contNow); ok {
|
||||
t.Error("continued with no previous turn")
|
||||
}
|
||||
stale := contSession(dialogue.IntentQuery, "water")
|
||||
stale.Timestamp = contNow.Add(-10 * time.Minute)
|
||||
if _, ok := continuationDecision(stale, "а завтра?", contNow); ok {
|
||||
t.Error("continued an expired session")
|
||||
}
|
||||
}
|
||||
|
||||
func TestContinuationNeverCarriesAnFn(t *testing.T) {
|
||||
prev := contSession(dialogue.IntentQuery, "water")
|
||||
prev.Slots.Fn, prev.Slots.HasFn = "restart", true
|
||||
dec, ok := continuationDecision(prev, "а завтра?", contNow)
|
||||
if !ok {
|
||||
t.Fatal("want a decision")
|
||||
}
|
||||
if dec.Slots.HasFn || dec.Slots.Fn != "" {
|
||||
t.Fatalf("carried fn %q into a continuation", dec.Slots.Fn)
|
||||
}
|
||||
}
|
||||
|
||||
// TestContinuationCarriesTheTopic — the ellipsis names the day; what he is
|
||||
// asking ABOUT has to come from the previous turn, or replySystem keyword-
|
||||
// matches "а завтра?" and finds nothing. Caught on the deployed daemon.
|
||||
func TestContinuationCarriesTheTopic(t *testing.T) {
|
||||
prev := contSession(dialogue.IntentSystem, "")
|
||||
prev.Slots.Text = "какой сегодня день"
|
||||
dec, ok := continuationDecision(prev, "а завтра?", contNow)
|
||||
if !ok {
|
||||
t.Fatal("want a decision")
|
||||
}
|
||||
if dec.Slots.Text != "какой сегодня день" {
|
||||
t.Fatalf("Slots.Text = %q, want the previous turn's topic", dec.Slots.Text)
|
||||
}
|
||||
}
|
||||
|
||||
// TestReplySystemIgnoresAnInheritedTopic — the regression the deployed daemon
|
||||
// showed on 01-08-2026: followUpMerge fills an empty Text from the previous
|
||||
// same-intent turn, so a plain "привет" after "какой сегодня день" arrived at
|
||||
// replySystem carrying the old topic and was answered with the date. Only a
|
||||
// continuation may widen the keyword match.
|
||||
func TestReplySystemIgnoresAnInheritedTopic(t *testing.T) {
|
||||
h := &reactiveHandler{now: func() time.Time { return contNow }}
|
||||
inherited := router.Decision{
|
||||
Utterance: "привет",
|
||||
Intent: router.IntentSystem,
|
||||
Slots: router.Slots{Text: "какой сегодня день"},
|
||||
}
|
||||
if got := h.replySystem(nil, inherited); got != "пока не умею отвечать на этот вопрос." {
|
||||
t.Fatalf("replySystem answered %q on an inherited topic", got)
|
||||
}
|
||||
cont := inherited
|
||||
cont.Utterance, cont.Continued = "а завтра?", true
|
||||
if got := h.replySystem(nil, cont); got == "пока не умею отвечать на этот вопрос." {
|
||||
t.Fatalf("replySystem refused a real continuation")
|
||||
}
|
||||
}
|
||||
|
||||
// TestRememberTurnRefreshesTheTopic — rememberTurn runs after followUpMerge,
|
||||
// which has already inherited a Text from the previous same-intent turn. A
|
||||
// fill-if-empty rule therefore pins the FIRST topic of a run of query turns
|
||||
// and never lets go, so a later "а завтра?" continues a question two turns
|
||||
// old. Seen on the deployed daemon, 01-08-2026.
|
||||
func TestRememberTurnRefreshesTheTopic(t *testing.T) {
|
||||
h := &reactiveHandler{
|
||||
now: func() time.Time { return contNow },
|
||||
dialogueSessions: dialogue.NewSessionStore(2 * time.Minute),
|
||||
}
|
||||
ctx := context.Background()
|
||||
h.rememberTurn(ctx, nil, router.Decision{
|
||||
Intent: router.IntentQuery, Utterance: "во сколько у меня встреча",
|
||||
}, contNow)
|
||||
// The second turn arrives with the first turn's Text already merged in.
|
||||
prev := h.dialogueSessions.Get(voiceDialogueID, contNow)
|
||||
h.rememberTurn(ctx, prev, router.Decision{
|
||||
Intent: router.IntentQuery,
|
||||
Utterance: "какие у меня планы",
|
||||
Slots: router.Slots{Text: "во сколько у меня встреча"},
|
||||
}, contNow)
|
||||
got := h.dialogueSessions.Get(voiceDialogueID, contNow)
|
||||
if got == nil {
|
||||
t.Fatal("no session")
|
||||
}
|
||||
if got.Slots.Text != "какие у меня планы" {
|
||||
t.Fatalf("topic = %q, want the latest turn's", got.Slots.Text)
|
||||
}
|
||||
}
|
||||
+16
-11
@@ -125,13 +125,17 @@ func TestQueryWebPassesWithoutAURL(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// A daemon where page reading was never turned on — the default — answers the
|
||||
// question the way it did before the capability existed. Claiming the turn to
|
||||
// report a configuration status is for something that exists and failed.
|
||||
func TestQueryWebPassesWhenNotConfigured(t *testing.T) {
|
||||
// A daemon where page reading was never turned on names the gap. He asked
|
||||
// about one page, nothing else on the box can read it, and the old behaviour
|
||||
// here was to answer as though the URL had not been said (Vikunja #479).
|
||||
func TestQueryWebNamesTheGapWhenNotConfigured(t *testing.T) {
|
||||
h := buildWebHandler(nil)
|
||||
if reply, ok := askWeb(h, "посмотри https://example.org/page"); ok {
|
||||
t.Fatalf("an unconfigured crawler claimed the turn with %q", reply)
|
||||
reply, ok := askWeb(h, "посмотри https://example.org/page")
|
||||
if !ok {
|
||||
t.Fatal("an unconfigured crawler let the page question fall through")
|
||||
}
|
||||
if !phraser.IsQ(phraser.QueryPageOff, nil, reply) {
|
||||
t.Errorf("got %q, want the gap named", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -156,21 +160,22 @@ func TestQueryWebRefusesNonHTML(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("the web source did not claim a question with a URL")
|
||||
}
|
||||
if !strings.Contains(reply, "не получилось") {
|
||||
if !phraser.IsQ(phraser.QueryFailPage, nil, reply) {
|
||||
t.Errorf("reply = %q, want the read-failed answer", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// robots.txt is honoured on the answer path too, and she says so instead of
|
||||
// reporting a generic failure.
|
||||
// robots.txt is honoured on the answer path too, and she says the page is
|
||||
// closed instead of reporting a generic failure.
|
||||
func TestQueryWebObeysRobots(t *testing.T) {
|
||||
h := buildWebHandler(crawl.New(&robotsDenyFetcher{}, crawl.Config{}))
|
||||
reply, ok := askWeb(h, "посмотри https://example.org/private")
|
||||
if !ok {
|
||||
t.Fatal("the web source did not claim a question with a URL")
|
||||
}
|
||||
if !strings.Contains(reply, "robots.txt") {
|
||||
t.Errorf("reply = %q, want the robots answer", reply)
|
||||
// She names the cause without reading a filename out loud.
|
||||
if !strings.Contains(reply, "закрыта для чтения") || strings.Contains(reply, "robots") {
|
||||
t.Errorf("reply = %q, want the closed-page answer with no filename", reply)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -10,6 +10,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/calendar"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -147,8 +148,8 @@ func TestQueryDayPlanCoreFailure(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("a failed plan read must still answer, not fall through to RAG")
|
||||
}
|
||||
if reply != "не получилось собрать план." {
|
||||
t.Errorf("reply = %q", reply)
|
||||
if !phraser.IsQ(phraser.QueryFailPlan, nil, reply) {
|
||||
t.Errorf("reply = %q, want the honest failure", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -351,3 +352,31 @@ func TestTickDayPlanReadsTheStore(t *testing.T) {
|
||||
t.Errorf("a reminder for next year is not today's plan: %q", plan.Spoken)
|
||||
}
|
||||
}
|
||||
|
||||
// TestHandlerUpgradesToTheDaemonAPI — wireVoice runs before the tick loop
|
||||
// exists, so the handler starts with the bare store adapter, and that adapter
|
||||
// refuses DayPlan ("not available via direct store API"). main back-patches
|
||||
// the real one in. Without the patch every "какие у меня планы на сегодня"
|
||||
// answered "не получилось собрать план" on the deployed daemon, 01-08-2026.
|
||||
func TestHandlerUpgradesToTheDaemonAPI(t *testing.T) {
|
||||
h := &reactiveHandler{api: ipc.NewStoreAPI(nil), now: planDay}
|
||||
if _, err := h.api.DayPlan(context.Background()); err == nil {
|
||||
t.Fatal("the bare store adapter served a day plan; this test is measuring nothing")
|
||||
}
|
||||
|
||||
want := samplePlan()
|
||||
h.upgradeAPI(&daemonAPI{
|
||||
CoreAPI: ipc.UnimplementedCoreAPI{},
|
||||
getDayPlan: func(context.Context) ipc.DayPlan { return want },
|
||||
})
|
||||
|
||||
reply, ok := h.queryDayPlan(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "какие у меня планы на сегодня?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("queryDayPlan passed on a plan question")
|
||||
}
|
||||
if reply != want.Spoken {
|
||||
t.Fatalf("reply = %q, want the assembled plan", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The list she read at the mic is not the list a browser is looking at
|
||||
// (Vikunja #45 step 3). The clarify store was keyed per reach in #466; the
|
||||
// dialogue session was still one slot for the box, so "второй" typed on the web
|
||||
// closed the second task she had recited out loud.
|
||||
func TestCandidatesDoNotCrossReaches(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
voiceCtx := withDialogueID(context.Background(), dialogueIDFor(sourceVoice, ""))
|
||||
webCtx := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
|
||||
ids := seedTasks(t, st, "купить хлеб", "позвонить маме")
|
||||
putCandidates(h, voiceCtx, ids, "купить хлеб", "позвонить маме")
|
||||
|
||||
if reply, handled := h.resolveCandidate(webCtx, "первую сделал", sourceText); handled {
|
||||
t.Fatalf("a web turn picked from the list she read aloud: %q", reply)
|
||||
}
|
||||
live, err := st.ListTasks(context.Background(), "live")
|
||||
if err != nil {
|
||||
t.Fatalf("list tasks: %v", err)
|
||||
}
|
||||
if len(live) != 2 {
|
||||
t.Fatalf("%d tasks live, want 2 — the web turn moved one", len(live))
|
||||
}
|
||||
// The reach that was offered the list still owns it.
|
||||
if _, handled := h.resolveCandidate(voiceCtx, "первую сделал", sourceVoice); !handled {
|
||||
t.Fatal("the mic lost its own list")
|
||||
}
|
||||
}
|
||||
|
||||
// A selection writes a fact, so the fact must name the reach the words arrived
|
||||
// on. It said "tap:voice" for a typed turn.
|
||||
func TestCandidateProvenanceFollowsTheReach(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
ids := seedTasks(t, st, "купить хлеб")
|
||||
putCandidates(h, ctx, ids, "купить хлеб")
|
||||
|
||||
if _, handled := h.resolveCandidate(ctx, "первую сделал", sourceText); !handled {
|
||||
t.Fatal("the pick was not acted on")
|
||||
}
|
||||
done, err := st.ListTasks(context.Background(), "done")
|
||||
if err != nil {
|
||||
t.Fatalf("list tasks: %v", err)
|
||||
}
|
||||
if len(done) != 1 {
|
||||
t.Fatalf("%d tasks done, want 1", len(done))
|
||||
}
|
||||
if by := done[0].ResolvedBy; by != string(sourceText) {
|
||||
t.Errorf("resolved_by = %q, want %q", by, sourceText)
|
||||
}
|
||||
}
|
||||
|
||||
// Anaphora is per reach too: an ellipsis typed on the web must not continue the
|
||||
// question he asked at the mic. Both surfaces stay usable at once, which is the
|
||||
// case a single-owner box actually hits — a phone open while he talks.
|
||||
func TestAnaphoraDoesNotCrossReaches(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
voiceCtx := withDialogueID(context.Background(), dialogueIDFor(sourceVoice, ""))
|
||||
webCtx := withDialogueID(context.Background(), dialogueIDFor(sourceText, "web"))
|
||||
now := h.now()
|
||||
|
||||
h.rememberTurn(voiceCtx, nil, router.Decision{
|
||||
Intent: router.IntentQuery, Utterance: "во сколько у меня встреча",
|
||||
}, now)
|
||||
|
||||
if sess := h.dialogueSessions.Get(dialogueIDOf(webCtx), now); sess != nil {
|
||||
t.Fatalf("the web reach inherited the mic's turn: %+v", sess)
|
||||
}
|
||||
sess := h.dialogueSessions.Get(dialogueIDOf(voiceCtx), now)
|
||||
if sess == nil || !strings.Contains(sess.Slots.Text, "встреча") {
|
||||
t.Fatalf("the mic lost its own turn: %+v", sess)
|
||||
}
|
||||
}
|
||||
+71
-4
@@ -263,18 +263,85 @@ func (c *praxisClient) getJSON(ctx context.Context, op, path string, out any) er
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *praxisClient) ListAttention(ctx context.Context, limit int) ([]map[string]any, error) {
|
||||
var out []map[string]any
|
||||
// praxisAttention — an attention response in either of the two shapes Praxis
|
||||
// may send (Vikunja #540).
|
||||
//
|
||||
// ECOSYSTEM-SPEC §2.6 says the response carries `degraded: [source_ids]` when a
|
||||
// source is failed or stale, and that Maven is required to say so rather than
|
||||
// report all-clear. The deployed Praxis answers with a bare JSON array and no
|
||||
// envelope at all, so both are decoded here: an array is the items, an object is
|
||||
// the spec envelope. This lands the Maven half without waiting on the server,
|
||||
// and the sources read below is what makes the hedge work meanwhile.
|
||||
type praxisAttention struct {
|
||||
Items []map[string]any
|
||||
Degraded []string
|
||||
}
|
||||
|
||||
func (a *praxisAttention) UnmarshalJSON(data []byte) error {
|
||||
trimmed := bytes.TrimSpace(data)
|
||||
if len(trimmed) > 0 && trimmed[0] == '[' {
|
||||
return json.Unmarshal(trimmed, &a.Items)
|
||||
}
|
||||
var env struct {
|
||||
Items []map[string]any `json:"items"`
|
||||
Degraded []string `json:"degraded"`
|
||||
}
|
||||
if err := json.Unmarshal(trimmed, &env); err != nil {
|
||||
return err
|
||||
}
|
||||
a.Items, a.Degraded = env.Items, env.Degraded
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *praxisClient) ListAttention(ctx context.Context, limit int) (praxisAttention, error) {
|
||||
var out praxisAttention
|
||||
err := c.getJSON(ctx, "attention", fmt.Sprintf("/api/v1/tools/attention?limit=%d", limit), &out)
|
||||
return out, err
|
||||
}
|
||||
|
||||
// praxisSource — one polled source, as much of it as the hedge needs. The tools
|
||||
// API does not expose sources, so this decodes the plain `/api/v1/sources` rows.
|
||||
type praxisSource struct {
|
||||
ID string `json:"id"`
|
||||
SourceID string `json:"source_id"`
|
||||
Health string `json:"health"`
|
||||
}
|
||||
|
||||
func (s praxisSource) name() string {
|
||||
if s.SourceID != "" {
|
||||
return s.SourceID
|
||||
}
|
||||
return s.ID
|
||||
}
|
||||
|
||||
// UnhealthySources reports which sources cannot be trusted to have reported,
|
||||
// and how many sources Praxis has at all (Vikunja #540).
|
||||
//
|
||||
// Only read when the attention list came back empty, which is the one turn where
|
||||
// an all-clear is at stake. A source whose health field is absent counts as
|
||||
// healthy: a Praxis that never reports health would otherwise make every quiet
|
||||
// turn a hedge, and an unreported field is not evidence of a fault. Everything it
|
||||
// does report other than "ok" — failed, stale, degraded, unknown — counts as
|
||||
// cannot-tell, because none of them mean the source has spoken.
|
||||
func (c *praxisClient) UnhealthySources(ctx context.Context) (bad []string, total int, err error) {
|
||||
var out []praxisSource
|
||||
if err := c.getJSON(ctx, "sources", "/api/v1/sources", &out); err != nil {
|
||||
return nil, 0, err
|
||||
}
|
||||
for _, s := range out {
|
||||
if s.Health != "" && s.Health != "ok" {
|
||||
bad = append(bad, s.name())
|
||||
}
|
||||
}
|
||||
return bad, len(out), nil
|
||||
}
|
||||
|
||||
// ListAttentionForEntity is ListAttention scoped to a single canonical Nexus
|
||||
// entity, so callers already holding a resolved entity_id (e.g. after
|
||||
// resolveEntityReference) can ask "what needs attention for this entity"
|
||||
// instead of filtering the unscoped list client-side.
|
||||
func (c *praxisClient) ListAttentionForEntity(ctx context.Context, entityID string, limit int) ([]map[string]any, error) {
|
||||
var out []map[string]any
|
||||
func (c *praxisClient) ListAttentionForEntity(ctx context.Context, entityID string, limit int) (praxisAttention, error) {
|
||||
var out praxisAttention
|
||||
err := c.getJSON(ctx, "attention_for_entity",
|
||||
fmt.Sprintf("/api/v1/tools/attention?limit=%d&entity_id=%s", limit, url.QueryEscape(entityID)), &out)
|
||||
return out, err
|
||||
|
||||
+310
-35
@@ -5,14 +5,30 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
hexisclient "github.com/kami/hexis/pkg/client"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
)
|
||||
|
||||
// The three services, spelled the way she says them out loud. A service that is
|
||||
// down or refusing has to be named: they degrade independently, so "не
|
||||
// отвечает" on its own tells him nothing he can act on, and each call site
|
||||
// already knows which one it was talking to — it records the same name in the
|
||||
// trace (Vikunja #521).
|
||||
const (
|
||||
serviceNexus = "Nexus"
|
||||
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} }
|
||||
|
||||
// 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
|
||||
@@ -90,6 +106,13 @@ func (h *reactiveHandler) handlePraxisAct(ctx context.Context, dec router.Decisi
|
||||
ctx = withCorrelationID(ctx, newCorrelationID())
|
||||
}
|
||||
px := h.ecosystem.praxis
|
||||
dec, ok := h.resolveSurfacedPosition(dec)
|
||||
if !ok {
|
||||
// A demonstrative with no digest behind it. "я это сделал" is a sentence
|
||||
// about his day, so the rest of the cascade gets it back rather than
|
||||
// hearing "какой пункт?" for something that was never about a пункт.
|
||||
return ""
|
||||
}
|
||||
for _, capability := range praxisCapabilities {
|
||||
for _, alias := range capability.aliases() {
|
||||
if alias == dec.Slots.Fn {
|
||||
@@ -139,24 +162,34 @@ func (listAttentionCapability) aliases() []string {
|
||||
|
||||
func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, px *praxisClient, _ router.Decision) string {
|
||||
started := h.now()
|
||||
items, err := px.ListAttention(ctx, 20)
|
||||
att, err := px.ListAttention(ctx, 20)
|
||||
if err != nil {
|
||||
log.Printf("ecosystem: praxis attention: %v", err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "list_attention", traceStatusForError(err),
|
||||
started, traceErrorFields(err))
|
||||
return "не могу сейчас узнать, что требует внимания."
|
||||
return phraser.A(phraser.AttentionFail, nil)
|
||||
}
|
||||
items := att.Items
|
||||
if len(items) == 0 {
|
||||
return "ничего не требует внимания."
|
||||
if hedge := h.attentionCannotTell(ctx, px, att.Degraded, started); hedge != "" {
|
||||
return hedge
|
||||
}
|
||||
return phraser.A(phraser.AttentionNone, nil)
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "list_attention", started, map[string]any{"count": len(items)})
|
||||
var parts []string
|
||||
var spoken []string
|
||||
for _, item := range items {
|
||||
title, _ := item["title"].(string)
|
||||
// importance arrives as JSON number ⇒ float64 over the HTTP contract.
|
||||
importance, _ := item["importance"].(float64)
|
||||
rule, _ := item["rule"].(string)
|
||||
s := title
|
||||
if s == "" {
|
||||
// An item Praxis returned without a title is not an item she can
|
||||
// read out. Counting it would put an empty slot in the list.
|
||||
continue
|
||||
}
|
||||
if importance > 0 {
|
||||
s += fmt.Sprintf(" (важность %d", int(importance))
|
||||
if rule != "" {
|
||||
@@ -170,12 +203,22 @@ func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, p
|
||||
// (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).
|
||||
spoken = append(spoken, id)
|
||||
if _, err := px.Surface(ctx, id); err != nil {
|
||||
log.Printf("ecosystem: praxis surface %s: %v", id, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
return "требует внимания: " + strings.Join(parts, "; ")
|
||||
h.rememberSurfaced(spoken)
|
||||
if len(parts) == 0 {
|
||||
// Praxis returned items and not one of them could be said. "ничего не
|
||||
// требует внимания" is the honest answer; the list line would render as
|
||||
// its own label and a colon (Vikunja #521).
|
||||
return phraser.A(phraser.AttentionNone, nil)
|
||||
}
|
||||
return phraser.A(phraser.AttentionList, map[string]string{"items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// listChangesCapability reads the recent-changes feed.
|
||||
@@ -192,19 +235,29 @@ func (listChangesCapability) handle(ctx context.Context, h *reactiveHandler, px
|
||||
log.Printf("ecosystem: praxis changes: %v", err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "list_changes", traceStatusForError(err),
|
||||
started, traceErrorFields(err))
|
||||
return "не могу сейчас узнать об изменениях."
|
||||
return phraser.A(phraser.ChangesFail, nil)
|
||||
}
|
||||
if len(changes) == 0 {
|
||||
return "нет изменений."
|
||||
return phraser.A(phraser.ChangesNone, nil)
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "list_changes", started, map[string]any{"count": len(changes)})
|
||||
var parts []string
|
||||
for _, c := range changes {
|
||||
title, _ := c["title"].(string)
|
||||
if title == "" {
|
||||
continue
|
||||
}
|
||||
typ, _ := c["change_type"].(string)
|
||||
if typ == "" {
|
||||
parts = append(parts, title)
|
||||
continue
|
||||
}
|
||||
parts = append(parts, fmt.Sprintf("%s (%s)", title, typ))
|
||||
}
|
||||
return "изменения: " + strings.Join(parts, "; ")
|
||||
if len(parts) == 0 {
|
||||
return phraser.A(phraser.ChangesNone, nil)
|
||||
}
|
||||
return phraser.A(phraser.ChangesList, map[string]string{"items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// entityAttentionCapability answers "what's going on with X" by resolving X to
|
||||
@@ -230,12 +283,12 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
subject = dec.Slots.Text
|
||||
}
|
||||
if subject == "" {
|
||||
return "про что именно спросить?"
|
||||
return phraser.A(phraser.EcoAboutWhat, nil)
|
||||
}
|
||||
if h.ecosystem == nil || h.ecosystem.nexus == nil {
|
||||
// Without Nexus there is no canonical ref to scope by. Say so rather
|
||||
// than quietly answering about something else.
|
||||
return "не могу связать это с сущностью — Nexus не настроен."
|
||||
return phraser.A(phraser.EcoNoNexus, nil)
|
||||
}
|
||||
|
||||
started := h.now()
|
||||
@@ -248,29 +301,29 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceNexus))
|
||||
}
|
||||
return "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
|
||||
return phraser.A(phraser.EcoAmbiguous, map[string]string{"items": strings.Join(ambiguous, ", ")})
|
||||
}
|
||||
if entityID == "" {
|
||||
return "не знаю такой сущности."
|
||||
return phraser.A(phraser.EcoUnknownEntity, nil)
|
||||
}
|
||||
if displayName == "" {
|
||||
displayName = subject
|
||||
}
|
||||
|
||||
queried := h.now()
|
||||
items, err := px.ListAttentionForEntity(ctx, entityID, 20)
|
||||
att, err := px.ListAttentionForEntity(ctx, entityID, 20)
|
||||
if err != nil {
|
||||
log.Printf("ecosystem: praxis attention for %s: %v", entityID, err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "entity_attention", traceStatusForError(err),
|
||||
queried, mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
|
||||
return "не могу сейчас узнать, что требует внимания по «" + displayName + "»."
|
||||
return phraser.A(phraser.AttentionFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
items, scoped := scopedToEntity(items, entityID)
|
||||
items, scoped := scopedToEntity(att.Items, entityID)
|
||||
if !scoped {
|
||||
// A Praxis old enough to ignore an unknown query parameter answers the
|
||||
// scoped question with the unscoped list. Reading that back as "по
|
||||
@@ -279,7 +332,7 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
log.Printf("ecosystem: praxis returned unscoped items for %s, refusing to answer", entityID)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "entity_attention", traceFailed, queried,
|
||||
map[string]any{"entity_id": entityID, "class": "unscoped_response"})
|
||||
return "не могу сейчас узнать, что требует внимания по «" + displayName + "»."
|
||||
return phraser.A(phraser.AttentionFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "entity_attention", queried, map[string]any{
|
||||
"entity_id": entityID, "count": len(items),
|
||||
@@ -303,9 +356,14 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
parts = append(parts, known)
|
||||
}
|
||||
if len(parts) == 0 {
|
||||
return "по «" + displayName + "» ничего нет."
|
||||
// The scoped list is as exposed to a silent source as the unscoped one,
|
||||
// and a per-entity all-clear is the more convincing of the two (#540).
|
||||
if hedge := h.attentionCannotTell(ctx, px, att.Degraded, queried); hedge != "" {
|
||||
return hedge
|
||||
}
|
||||
return phraser.A(phraser.AttentionNoneEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
return "по «" + displayName + "»: " + strings.Join(parts, "; ")
|
||||
return phraser.A(phraser.AttentionListEntity, map[string]string{"name": displayName, "items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// scopedToEntity drops items that carry an entity_id other than the one asked
|
||||
@@ -370,7 +428,7 @@ func (h *reactiveHandler) localFactsForEntity(ctx context.Context, entityID stri
|
||||
if len(parts) == 0 {
|
||||
return ""
|
||||
}
|
||||
out := "я помню: " + strings.Join(parts, ", ")
|
||||
out := phraser.A(phraser.EcoRecall, map[string]string{"items": strings.Join(parts, ", ")})
|
||||
if more {
|
||||
out += ", и это не всё"
|
||||
}
|
||||
@@ -497,6 +555,64 @@ func traceErrorFields(err error) map[string]any {
|
||||
return fields
|
||||
}
|
||||
|
||||
// entityResolution — what asking Nexus about a turn's candidate names came to.
|
||||
// One shape rather than five return values, because the caller needs the
|
||||
// reference that answered as well as the answer: it goes in the trace.
|
||||
type entityResolution struct {
|
||||
subject string // the reference Nexus answered about
|
||||
entityID string // set when exactly one name resolved
|
||||
displayName string // that entity's name as Nexus spells it
|
||||
ambiguous []string // candidate display names to ask between
|
||||
err error // a dependency failure, not a miss
|
||||
}
|
||||
|
||||
// resolveEntityCandidates asks Nexus about each name the turn offered and
|
||||
// reports what it knows, stopping early where the answer is already decided.
|
||||
//
|
||||
// The rules, in the order they apply:
|
||||
//
|
||||
// - A dependency failure ends it. Nexus being down is not "no such entity",
|
||||
// and asking about the next name would report the outage as a miss.
|
||||
// - Nexus calling one name ambiguous ends it. It has the candidates and it is
|
||||
// telling us to ask.
|
||||
// - Two names resolving to different entities is a clarify too, this time ours:
|
||||
// "перезапусти nginx на muzick-indexer" names both a service and its host,
|
||||
// and picking either would be inventing an intent he did not state.
|
||||
// - Nothing resolving returns the first name as the subject, so the trace says
|
||||
// what was actually looked for.
|
||||
func (h *reactiveHandler) resolveEntityCandidates(ctx context.Context, refs []string) entityResolution {
|
||||
var out entityResolution
|
||||
for _, ref := range refs {
|
||||
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, ref, nil)
|
||||
if err != nil {
|
||||
return entityResolution{subject: ref, err: err}
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
return entityResolution{subject: ref, ambiguous: ambiguous}
|
||||
}
|
||||
if entityID == "" {
|
||||
continue
|
||||
}
|
||||
if out.entityID == "" {
|
||||
out = entityResolution{subject: ref, entityID: entityID, displayName: displayName}
|
||||
continue
|
||||
}
|
||||
if entityID == out.entityID {
|
||||
continue
|
||||
}
|
||||
// Both are real and they are not the same thing. Hand back the names
|
||||
// Nexus spells, not the words he happened to say.
|
||||
return entityResolution{
|
||||
subject: out.subject,
|
||||
ambiguous: []string{out.displayName, displayName},
|
||||
}
|
||||
}
|
||||
if out.entityID == "" && len(refs) > 0 {
|
||||
out.subject = refs[0]
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// handleHexisAct — resolves entity references through Nexus and executes
|
||||
// matching capabilities through Hexis. Returns a reply string when handled,
|
||||
// or "" to fall through to the system command executor.
|
||||
@@ -514,28 +630,31 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
|
||||
// Resolve the utterance text as an entity reference through Nexus. An
|
||||
// ambiguous match must stop and clarify — never guess a mutation target.
|
||||
// The names come from entityReferences, not straight from the Text slot: the
|
||||
// model transliterates Latin names as it routes (Vikunja #476, #524).
|
||||
started := h.now()
|
||||
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, dec.Slots.Text, nil)
|
||||
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(dec.Slots.Text)}))
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
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 "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceAmbig, started,
|
||||
map[string]any{"candidates": len(ambiguous)})
|
||||
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
|
||||
return phraser.A(phraser.EcoAmbiguous, map[string]string{"items": strings.Join(ambiguous, ", ")})
|
||||
}
|
||||
if entityID == "" {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceNotFound, started,
|
||||
map[string]any{"subject": redactSubject(dec.Slots.Text)})
|
||||
map[string]any{"subject": redactSubject(subject)})
|
||||
return ""
|
||||
}
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceOK, started,
|
||||
@@ -550,9 +669,9 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceStatusForError(err), discovered,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceHexis))
|
||||
}
|
||||
return "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceHexis))
|
||||
}
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceOK, discovered,
|
||||
map[string]any{"entity_id": entityID, "count": len(caps)})
|
||||
@@ -569,10 +688,21 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
}
|
||||
verbLower := strings.ToLower(verb)
|
||||
|
||||
// With no allowlisted fn the verb is a whole phrase ("restart status muzick
|
||||
// indexer"), which no capability name ever contains. Read it the other way
|
||||
// round then: the phrase is the haystack and the capability name is what we
|
||||
// look for in it (Vikunja #476). Only when the fn slot is empty — a matched
|
||||
// fn is a single verb and containment already means what it says.
|
||||
loose := !dec.Slots.HasFn
|
||||
var matches []*hexisclient.Capability
|
||||
for i, c := range caps {
|
||||
if strings.Contains(strings.ToLower(c.Name), verbLower) ||
|
||||
(c.Description != "" && strings.Contains(strings.ToLower(c.Description), verbLower)) {
|
||||
name := strings.ToLower(c.Name)
|
||||
hit := strings.Contains(name, verbLower) ||
|
||||
(c.Description != "" && strings.Contains(strings.ToLower(c.Description), verbLower))
|
||||
if loose && name != "" && strings.Contains(verbLower, name) {
|
||||
hit = true
|
||||
}
|
||||
if hit {
|
||||
matches = append(matches, &caps[i])
|
||||
}
|
||||
}
|
||||
@@ -584,13 +714,30 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
for _, m := range matches {
|
||||
names = append(names, m.Name)
|
||||
}
|
||||
return "какую команду для " + displayName + ": " + strings.Join(names, ", ") + "?"
|
||||
return phraser.A(phraser.ActWhich, map[string]string{"name": displayName, "items": strings.Join(names, ", ")})
|
||||
}
|
||||
matched := matches[0]
|
||||
|
||||
// Read-only capabilities run immediately; mutating ones are parked for an
|
||||
// explicit spoken confirm bound to this capability + target.
|
||||
if !matched.ReadOnly {
|
||||
// The tier decides, and Hexis owns the tier (Vikunja #523). read_only alone
|
||||
// used to decide it here, which flattened three answers into two: a
|
||||
// capability that wipes the thing it names got the same single spoken "да"
|
||||
// as one that restarts a service, and requires_confirmation — which the
|
||||
// Hexis contract calls server-derived and not settable by a caller — was
|
||||
// read by nobody. docs/ecosystem.md §17.3 says confirmation follows risk.
|
||||
tier := tool.RiskOfCapability(matched.Risk, matched.ReadOnly, matched.RequiresConfirmation)
|
||||
policy := tool.PolicyFor(tier)
|
||||
if !policy.VoiceMayRun {
|
||||
// Irreversible. A confirm turn would not help, for the same reason it
|
||||
// does not help a local row: the STT heard it, the model routed it and
|
||||
// a substring matched the capability, and a spoken "да" checks none of
|
||||
// those. She names the gap and he runs it himself.
|
||||
h.recordEcosystemTrace(ctx, "hexis", "confirmation", traceRefused, started,
|
||||
map[string]any{"entity_id": entityID, "capability": matched.Name, "risk": string(tier)})
|
||||
return phraser.A(phraser.ActNeedsAuthedSurface, nil)
|
||||
}
|
||||
if policy.Confirm {
|
||||
h.mu.Lock()
|
||||
h.pendingHexis = &pendingHexisExec{
|
||||
capabilityID: matched.ID,
|
||||
@@ -602,7 +749,7 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
h.mu.Unlock()
|
||||
h.recordEcosystemTrace(ctx, "hexis", "confirmation", tracePending, started,
|
||||
map[string]any{"entity_id": entityID, "capability": matched.Name})
|
||||
return "выполнить «" + matched.Name + "» для " + displayName + "? скажи «да» или «нет»."
|
||||
return phraser.A(phraser.ActConfirmEntity, map[string]string{"name": matched.Name, "name_entity": displayName})
|
||||
}
|
||||
|
||||
return h.execHexis(ctx, matched.ID, matched.Name, entityID, displayName)
|
||||
@@ -622,7 +769,7 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
|
||||
mergeFields(traceErrorFields(err), map[string]any{
|
||||
"entity_id": entityID, "capability": capName, "causation_id": causationID,
|
||||
}))
|
||||
return "не получилось выполнить команду для " + displayName + "."
|
||||
return phraser.A(phraser.ActFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
// One record per hop: the second write this used to make said the same
|
||||
// thing under a different key, in a different shape.
|
||||
@@ -630,5 +777,133 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
|
||||
"entity_id": entityID, "entity_name": displayName,
|
||||
"capability": capName, "causation_id": causationID,
|
||||
})
|
||||
return "команда выполнена для " + displayName + "."
|
||||
return phraser.A(phraser.ActDoneEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
|
||||
// hexisBeforeClarify gives an entity-shaped act one chance at Hexis before she
|
||||
// asks what to do.
|
||||
//
|
||||
// The stage-3 gate thins an act that never matched an allowlisted fn, so
|
||||
// "перезапусти muzick indexer" was answered with "Что сделать?" and the Hexis
|
||||
// path was never entered — the capability existed and no utterance could reach
|
||||
// it (Vikunja #476). Hexis is exactly where an act with no local fn belongs:
|
||||
// the verb is matched against the capabilities Hexis registers for the entity,
|
||||
// not against the allowlist.
|
||||
//
|
||||
// Narrow on purpose. Only an act, only when the fn slot is still empty, and
|
||||
// only when Hexis is wired — a box with no ecosystem asks the question it
|
||||
// always asked. A "" back means Nexus knew no such entity or Hexis had no
|
||||
// matching capability, and then she asks after all. Authority is unchanged:
|
||||
// resolution stops on ambiguity and a mutating capability still goes through
|
||||
// the spoken confirm in handleHexisAct.
|
||||
func (h *reactiveHandler) hexisBeforeClarify(ctx context.Context, dec router.Decision) string {
|
||||
if h.ecosystem == nil || h.ecosystem.hexis == nil {
|
||||
return ""
|
||||
}
|
||||
if dec.Intent != router.IntentAct || dec.Slots.HasFn || dec.Slots.Text == "" {
|
||||
return ""
|
||||
}
|
||||
return h.handleHexisAct(ctx, dec)
|
||||
}
|
||||
|
||||
// attentionCannotTell returns the hedge to say instead of an all-clear, or ""
|
||||
// when an empty attention list really does mean nothing needs looking at
|
||||
// (ECOSYSTEM-SPEC §2.6, Vikunja #540).
|
||||
//
|
||||
// "Nothing needs attention" and "I cannot currently tell" are different answers
|
||||
// and only one of them was ever said. The spec's mechanism is a `degraded` array
|
||||
// on the attention response, which the deployed Praxis does not send, so the
|
||||
// source health read is the half that works today. It costs one HTTP call and
|
||||
// only on the empty-list turn, which is the only turn where an all-clear is at
|
||||
// stake.
|
||||
//
|
||||
// A failed sources read is deliberately NOT a hedge. The attention call itself
|
||||
// succeeded, and not being able to ask about health is not evidence of a fault —
|
||||
// hedging on it would turn one flaky endpoint into a permanently uncertain
|
||||
// assistant.
|
||||
func (h *reactiveHandler) attentionCannotTell(ctx context.Context, px *praxisClient, degraded []string, started time.Time) string {
|
||||
if len(degraded) > 0 {
|
||||
h.recordPraxisTrace(ctx, "attention_degraded", started, map[string]any{
|
||||
"degraded": strings.Join(degraded, ","), "source": "response",
|
||||
})
|
||||
return phraser.A(phraser.AttentionDegraded, map[string]string{"items": strings.Join(degraded, ", ")})
|
||||
}
|
||||
bad, total, err := px.UnhealthySources(ctx)
|
||||
if err != nil {
|
||||
log.Printf("ecosystem: praxis sources: %v", err)
|
||||
return ""
|
||||
}
|
||||
if total == 0 {
|
||||
// A Praxis that polls nothing knows nothing, so its silence is not an
|
||||
// all-clear either. This is the state the box is in as of 2026-08-05:
|
||||
// /api/v1/sources answers with an empty array.
|
||||
h.recordPraxisTrace(ctx, "attention_no_sources", started, map[string]any{"sources": 0})
|
||||
return phraser.A(phraser.AttentionNoSources, nil)
|
||||
}
|
||||
if len(bad) > 0 {
|
||||
h.recordPraxisTrace(ctx, "attention_degraded", started, map[string]any{
|
||||
"degraded": strings.Join(bad, ","), "sources": total, "source": "health",
|
||||
})
|
||||
return phraser.A(phraser.AttentionDegraded, map[string]string{"items": strings.Join(bad, ", ")})
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// rememberSurfaced records the item ids she just read out, replacing whatever the
|
||||
// previous digest left. Called with the ids in speaking order (Vikunja #516).
|
||||
func (h *reactiveHandler) rememberSurfaced(ids []string) {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
h.surfacedItems = ids
|
||||
}
|
||||
|
||||
// resolveSurfacedPosition turns a positional item reference into a Praxis item
|
||||
// id, using the list she last read out.
|
||||
//
|
||||
// The router names a position and not an id, because only the daemon has the
|
||||
// list: PraxisGrammars fills the value slot with "2", "last" or "this". An id is
|
||||
// left alone, since "item_ab12" is already one.
|
||||
//
|
||||
// The second return says whether the turn is still Praxis's. A position that
|
||||
// names nothing keeps the turn and clears the slot, so the capability answers its
|
||||
// own "какой пункт?" — he said "второй пункт" and deserves to hear that there is
|
||||
// no second one. A demonstrative that resolves to nothing gives the turn BACK,
|
||||
// because "я это сделал" was probably never about a пункт at all. "это" also
|
||||
// needs the list to hold exactly one item: pointing at one of five is a guess,
|
||||
// and a wrong guess here transitions the wrong item.
|
||||
func (h *reactiveHandler) resolveSurfacedPosition(dec router.Decision) (router.Decision, bool) {
|
||||
ref := dec.Slots.Value
|
||||
if ref == "" || strings.HasPrefix(ref, "item") {
|
||||
return dec, true
|
||||
}
|
||||
h.mu.Lock()
|
||||
ids := h.surfacedItems
|
||||
h.mu.Unlock()
|
||||
|
||||
idx := -1
|
||||
switch {
|
||||
case ref == "this":
|
||||
if len(ids) != 1 {
|
||||
log.Printf("ecosystem: praxis \"это\" has no single item (%d surfaced)", len(ids))
|
||||
return dec, false
|
||||
}
|
||||
idx = 0
|
||||
case ref == "last":
|
||||
idx = len(ids) - 1
|
||||
default:
|
||||
n, err := strconv.Atoi(ref)
|
||||
if err != nil || n < 1 {
|
||||
// Neither a position nor an id: leave it for the capability to
|
||||
// reject rather than silently rewriting what he said.
|
||||
return dec, true
|
||||
}
|
||||
idx = n - 1
|
||||
}
|
||||
if idx < 0 || idx >= len(ids) {
|
||||
log.Printf("ecosystem: praxis position %q has no item (%d surfaced)", ref, len(ids))
|
||||
dec.Slots.Value = ""
|
||||
return dec, true
|
||||
}
|
||||
dec.Slots.Value = ids[idx]
|
||||
return dec, true
|
||||
}
|
||||
|
||||
@@ -96,7 +96,7 @@ func TestEcosystem_OutagesLeaveNoSharedFailureState(t *testing.T) {
|
||||
// A Nexus outage during a Hexis act writes a failure trace, and a shared
|
||||
// store is the one thing the Praxis path could inherit it through.
|
||||
nexus.SetFault(503)
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); actRan(reply) {
|
||||
t.Fatalf("nexus outage must not report success, got %q", reply)
|
||||
}
|
||||
if len(tracesFor(t, h, "nexus", "resolve")) == 0 {
|
||||
@@ -117,7 +117,7 @@ func TestEcosystem_OutagesLeaveNoSharedFailureState(t *testing.T) {
|
||||
if reply := h.handlePraxisAct(ctx, praxisActDec("list_attention")); strings.Contains(reply, "disk") {
|
||||
t.Fatalf("praxis outage must not serve content, got %q", reply)
|
||||
}
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("a praxis outage must not block the hexis path, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -154,7 +154,7 @@ func TestEcosystem_ResolvedWithoutEntityFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("a resolve with no entity must degrade, not fall through to local execution")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("a resolve with no entity must not report success, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -212,7 +212,7 @@ func TestEcosystem_MalformedNexusResponseFailsClosed(t *testing.T) {
|
||||
|
||||
nexus.SetBody(`{"status":"resolved","entity":`)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if reply == "" || strings.Contains(reply, "выполнена") {
|
||||
if reply == "" || actRan(reply) {
|
||||
t.Fatalf("malformed nexus body must degrade, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -232,7 +232,7 @@ func TestEcosystem_UnknownContractFieldsTolerated(t *testing.T) {
|
||||
nexus := newFakeNexus(t, body)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("%s contract shape must still resolve and execute, got %q", name, reply)
|
||||
}
|
||||
})
|
||||
@@ -250,7 +250,7 @@ func TestEcosystem_CancelledContextDegrades(t *testing.T) {
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Millisecond)
|
||||
defer cancel()
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if reply == "" || strings.Contains(reply, "выполнена") {
|
||||
if reply == "" || actRan(reply) {
|
||||
t.Fatalf("cancelled resolve must degrade, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -268,7 +268,7 @@ func TestEcosystem_ExecutionFailureIsNotSuccess(t *testing.T) {
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("failed execution must not read as success, got %q", reply)
|
||||
}
|
||||
if reply == "" {
|
||||
@@ -291,7 +291,7 @@ func TestEcosystem_SuccessfulActionWritesATrace(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
exec := tracesFor(t, h, "hexis", "execute")
|
||||
@@ -313,7 +313,7 @@ func TestEcosystem_TracesStayOutOfFacts(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
if len(traces(t, h)) == 0 {
|
||||
@@ -434,7 +434,7 @@ func TestEcosystem_TotalOutageSaysSoForEveryPath(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Errorf("%s: total outage must not answer with silence", name)
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Errorf("%s: total outage must not claim success: %q", name, reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -105,13 +105,13 @@ func TestFakeNexus_FaultInjectionThenRecovery(t *testing.T) {
|
||||
|
||||
nexus.SetFault(503)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("nexus outage must not report success, got %q", reply)
|
||||
}
|
||||
|
||||
nexus.SetFault(0)
|
||||
reply = h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !strings.Contains(reply, "выполнена") {
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("expected success once nexus recovers, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
hexisclient "github.com/kami/hexis/pkg/client"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -85,7 +86,7 @@ func TestHexisMutatingRequiresConfirm(t *testing.T) {
|
||||
|
||||
// The follow-up "да" turn executes exactly the parked capability.
|
||||
confirmReply, handled := h.resolveConfirm(ctx, "да")
|
||||
if !handled || !strings.Contains(confirmReply, "выполнена") {
|
||||
if !handled || !actRan(confirmReply) {
|
||||
t.Fatalf("confirm should execute, got handled=%v reply=%q", handled, confirmReply)
|
||||
}
|
||||
if !*executed {
|
||||
@@ -125,7 +126,7 @@ func TestHexisReadOnlyExecutesImmediately(t *testing.T) {
|
||||
if h.pendingHexis != nil {
|
||||
t.Fatal("read-only cap should not park a confirmation")
|
||||
}
|
||||
if !strings.Contains(reply, "выполнена") {
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("unexpected reply %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -186,7 +187,7 @@ func TestHexisNexusErrorFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("nexus dependency failure must not fall through with an empty reply")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("nexus dependency failure must not report success, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -219,7 +220,7 @@ func TestHexisUnavailableFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("hexis dependency failure must not fall through with an empty reply")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("hexis dependency failure must not report success, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -241,3 +242,73 @@ func TestHexisNotFoundStillFallsThrough(t *testing.T) {
|
||||
t.Fatal("not_found resolution must never execute a hexis capability")
|
||||
}
|
||||
}
|
||||
|
||||
// actRan — the reply is the line she says when a capability ran against an
|
||||
// entity. The tests used to look for the substring "выполнена", which was a
|
||||
// literal out of the act file: the review reworded that line to "готово: {name}"
|
||||
// and seventeen assertions went with it (Vikunja #521).
|
||||
func actRan(reply string) bool {
|
||||
return phraser.IsA(phraser.ActDoneEntity, map[string]string{"name": muzickIndexer}, reply)
|
||||
}
|
||||
|
||||
// muzickIndexer — the display name every ecosystem fixture resolves to.
|
||||
const muzickIndexer = "Muzick indexer"
|
||||
|
||||
// read_only used to be the whole decision on this path, which meant a
|
||||
// capability that destroys what it names got the same single spoken "да" as one
|
||||
// that restarts a service. Hexis declares the tier and the voice path is not an
|
||||
// authorised surface for the top one (Vikunja #523).
|
||||
func TestHexisIrreversibleCapabilityIsNotRunFromVoice(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_wipe","name":"restart","read_only":false,"risk":"irreversible","requires_confirmation":true}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if *executed {
|
||||
t.Fatal("an irreversible capability ran from the voice path")
|
||||
}
|
||||
if h.pendingHexis != nil {
|
||||
t.Fatal("an irreversible capability parked a confirm; a spoken да is not enough authority")
|
||||
}
|
||||
if !strings.Contains(reply, "не вернуть") {
|
||||
t.Errorf("reply = %q; want it to name why she will not run it", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The other half: Hexis calling a capability safe is enough to run it, even
|
||||
// though read_only is the field that used to decide. Nothing here re-derives.
|
||||
func TestHexisSafeCapabilityRunsOnItsDeclaredTier(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_status","name":"restart","read_only":true,"risk":"safe"}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !*executed {
|
||||
t.Fatal("a capability Hexis calls safe should run")
|
||||
}
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("unexpected reply %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// A mutating capability with no declared tier keeps the confirm turn it has
|
||||
// always had, so the split does not quietly loosen an existing box.
|
||||
func TestHexisUndeclaredTierStillConfirms(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_restart","name":"restart","read_only":false}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if *executed {
|
||||
t.Fatal("a mutating capability ran without a confirm")
|
||||
}
|
||||
if h.pendingHexis == nil {
|
||||
t.Fatal("a mutating capability did not park a confirm")
|
||||
}
|
||||
if !strings.Contains(reply, "да или нет") {
|
||||
t.Errorf("reply = %q; want the confirm question", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -142,7 +142,7 @@ func TestEcosystemTrace_SuccessfulActionTracesEveryHop(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,81 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"regexp"
|
||||
"strings"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// latinRun matches a run of Latin-script words — the shape a service, host or
|
||||
// project name takes in a Russian sentence. Digits, dot, dash and underscore
|
||||
// ride along because "muzick-indexer" and "nginx.conf" are one name, not two.
|
||||
var latinRun = regexp.MustCompile(`[A-Za-z][A-Za-z0-9._-]*(?:\s+[A-Za-z][A-Za-z0-9._-]*)*`)
|
||||
|
||||
// maxEntityReferences caps how many names one utterance may send to Nexus. The
|
||||
// cap is not about correctness, it is about one turn not fanning out into a
|
||||
// dozen HTTP calls when the utterance is a paragraph of English.
|
||||
const maxEntityReferences = 4
|
||||
|
||||
// hasLatin reports whether s carries a Latin letter.
|
||||
func hasLatin(s string) bool {
|
||||
for _, r := range s {
|
||||
if unicode.In(r, unicode.Latin) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// entityReferences returns the names Nexus is asked to resolve, in the order
|
||||
// they were said.
|
||||
//
|
||||
// Normally there is one, and it is the router's Text slot — the verb phrase the
|
||||
// model wrote. But the resident model rewrites a Russian utterance as it routes,
|
||||
// and on the way it transliterates: "перезапусти muzick indexer" came back as
|
||||
// "перезагрузить музик индексер" (Vikunja #476). Nexus is then asked for a
|
||||
// service nobody has ever named, so the act cannot resolve its target even with
|
||||
// every gate open.
|
||||
//
|
||||
// The recovery is deliberately narrow. Only when the utterance holds a Latin run
|
||||
// and the model's Text holds none has a name certainly been rewritten. Anything
|
||||
// else keeps the Text slot, so an English utterance and a Russian entity name
|
||||
// are both untouched. Un-transliterating the Cyrillic back is not attempted: the
|
||||
// surface form he said is right there, and guessing at a reverse mapping would
|
||||
// invent a second name to be wrong about.
|
||||
//
|
||||
// What this does NOT do is pick. It used to return the longest run, and length
|
||||
// is a guess: "перезапусти nginx на muzick-indexer" has two names in it and the
|
||||
// longer one is not reliably the target. Nexus owns which names it knows
|
||||
// (docs/ecosystem.md — ambiguous resolution asks the owner, it does not pick),
|
||||
// so every run goes over and Nexus answers. Two runs that both resolve are a
|
||||
// clarify, not a coin toss.
|
||||
func entityReferences(dec router.Decision) []string {
|
||||
text := dec.Slots.Text
|
||||
if hasLatin(text) || !hasLatin(dec.Utterance) {
|
||||
return []string{text}
|
||||
}
|
||||
var refs []string
|
||||
seen := map[string]bool{}
|
||||
for _, m := range latinRun.FindAllString(dec.Utterance, -1) {
|
||||
m = strings.TrimSpace(m)
|
||||
// A single stray letter is not a name.
|
||||
if len(m) < 2 {
|
||||
continue
|
||||
}
|
||||
key := strings.ToLower(m)
|
||||
if seen[key] {
|
||||
continue
|
||||
}
|
||||
seen[key] = true
|
||||
refs = append(refs, m)
|
||||
if len(refs) == maxEntityReferences {
|
||||
break
|
||||
}
|
||||
}
|
||||
if len(refs) == 0 {
|
||||
return []string{text}
|
||||
}
|
||||
return refs
|
||||
}
|
||||
@@ -0,0 +1,222 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// TestEntityReferences pins when his own words win over the model's, and that
|
||||
// every name he said goes over rather than one of them being picked.
|
||||
func TestEntityReferences(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
utterance string
|
||||
text string
|
||||
want []string
|
||||
}{
|
||||
{
|
||||
name: "the model transliterated the name",
|
||||
utterance: "перезапусти muzick indexer",
|
||||
text: "перезагрузить музик индексер",
|
||||
want: []string{"muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "it kept the name, so nothing to repair",
|
||||
utterance: "перезапусти muzick indexer",
|
||||
text: "перезагрузить muzick indexer",
|
||||
want: []string{"перезагрузить muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "an all-Russian entity name is not a rewrite",
|
||||
utterance: "перезапусти домашний сервер",
|
||||
text: "перезагрузить домашний сервер",
|
||||
want: []string{"перезагрузить домашний сервер"},
|
||||
},
|
||||
{
|
||||
name: "an English turn never enters the recovery",
|
||||
utterance: "restart muzick indexer",
|
||||
text: "restart muzick indexer",
|
||||
want: []string{"restart muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "both names go over, in the order he said them",
|
||||
utterance: "а перезапусти-ка nginx на muzick-indexer, пожалуйста",
|
||||
text: "перезагрузить нгинкс",
|
||||
want: []string{"nginx", "muzick-indexer"},
|
||||
},
|
||||
{
|
||||
name: "one stray letter is not a name",
|
||||
utterance: "перезапусти сервер a",
|
||||
text: "перезагрузить сервер",
|
||||
want: []string{"перезагрузить сервер"},
|
||||
},
|
||||
{
|
||||
name: "the same name twice is one question",
|
||||
utterance: "перезапусти nginx, ну правда, nginx",
|
||||
text: "перезагрузить нгинкс",
|
||||
want: []string{"nginx"},
|
||||
},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
dec := router.Decision{Utterance: tc.utterance, Slots: router.Slots{Text: tc.text}}
|
||||
got := entityReferences(dec)
|
||||
if len(got) != len(tc.want) {
|
||||
t.Fatalf("entityReferences = %q, want %q", got, tc.want)
|
||||
}
|
||||
for i := range got {
|
||||
if got[i] != tc.want[i] {
|
||||
t.Fatalf("entityReferences = %q, want %q", got, tc.want)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestNexusIsAskedForTheNameHeSaid — the defect end to end (Vikunja #476): the
|
||||
// router hands over a transliterated Text, and Nexus must still be asked about
|
||||
// the service that exists.
|
||||
func TestNexusIsAskedForTheNameHeSaid(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти muzick indexer",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Text: "перезагрузить музик индексер", Fn: "restart", HasFn: true},
|
||||
}
|
||||
h.handleHexisAct(ctx, dec)
|
||||
|
||||
reqs := nexus.Requests()
|
||||
if len(reqs) == 0 {
|
||||
t.Fatal("nexus was never asked")
|
||||
}
|
||||
body := string(reqs[0].Body)
|
||||
if !strings.Contains(body, "muzick indexer") {
|
||||
t.Fatalf("nexus resolve body = %s, want the name he said", body)
|
||||
}
|
||||
}
|
||||
|
||||
// TestAnEntityActReachesHexisInsteadOfAsking — the second half of #476. The
|
||||
// stage-3 gate thins an act with no allowlisted fn, and that question used to
|
||||
// be the whole turn, so the Hexis path was unreachable from voice or chat.
|
||||
func TestAnEntityActReachesHexisInsteadOfAsking(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти muzick indexer",
|
||||
Intent: router.IntentAct,
|
||||
Stage: 3,
|
||||
Clarify: true,
|
||||
Slots: router.Slots{Text: "restart status muzick indexer"},
|
||||
}
|
||||
reply := h.hexisBeforeClarify(ctx, dec)
|
||||
if reply == "" {
|
||||
t.Fatal("a resolvable entity act must reach hexis rather than fall through to the question")
|
||||
}
|
||||
if hexis.Count("", "/api/v1") == 0 {
|
||||
t.Fatal("hexis was never contacted")
|
||||
}
|
||||
}
|
||||
|
||||
// TestClarifyStillAsksWithoutHexis — the narrowing. No ecosystem, no change:
|
||||
// she asks exactly what she asked before.
|
||||
func TestClarifyStillAsksWithoutHexis(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти muzick indexer",
|
||||
Intent: router.IntentAct,
|
||||
Stage: 3,
|
||||
Clarify: true,
|
||||
Slots: router.Slots{Text: "перезагрузить музик индексер"},
|
||||
}
|
||||
if reply := h.hexisBeforeClarify(context.Background(), dec); reply != "" {
|
||||
t.Fatalf("no hexis must mean no reply, got %q", reply)
|
||||
}
|
||||
if _, asked := h.askClarify(voiceCtx(), dec); !asked {
|
||||
t.Fatal("she must still ask what to do")
|
||||
}
|
||||
}
|
||||
|
||||
// nexusInOrder serves one resolve answer per call, in order, so a test can say
|
||||
// what Nexus knows about the first name and what it knows about the second. The
|
||||
// last body repeats once the list runs out.
|
||||
func nexusInOrder(t *testing.T, bodies ...string) *fakeServer {
|
||||
t.Helper()
|
||||
var mu sync.Mutex
|
||||
n := 0
|
||||
return newFakeServer(t, map[string]http.HandlerFunc{
|
||||
"POST /api/v1/resolve": func(w http.ResponseWriter, r *http.Request) {
|
||||
mu.Lock()
|
||||
body := bodies[min(n, len(bodies)-1)]
|
||||
n++
|
||||
mu.Unlock()
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
_, _ = w.Write([]byte(body))
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
// TestTwoResolvedNamesAsk — «перезапусти nginx на muzick-indexer» names a
|
||||
// service and the host it runs on. Both are real, and which one he meant is not
|
||||
// in the utterance, so she asks. Picking one by length was the old behaviour and
|
||||
// length is not evidence (Vikunja #524).
|
||||
func TestTwoResolvedNamesAsk(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := nexusInOrder(t,
|
||||
fixtureNexusResolved("ent_nginx", "nginx", "service"),
|
||||
fixtureNexusResolved("ent_host", "Muzick indexer", "device"),
|
||||
)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти nginx на muzick-indexer",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Text: "перезагрузить нгинкс", Fn: "restart", HasFn: true},
|
||||
}
|
||||
reply := h.handleHexisAct(ctx, dec)
|
||||
if !strings.Contains(reply, "nginx") || !strings.Contains(reply, "Muzick indexer") {
|
||||
t.Fatalf("reply = %q, want both names she found", reply)
|
||||
}
|
||||
if hexis.Count("POST", "/api/v1/execute") != 0 {
|
||||
t.Fatal("she must not execute against a target she is still asking about")
|
||||
}
|
||||
}
|
||||
|
||||
// TestTheNameNexusKnowsWins — the other half. Two names go over and only one is
|
||||
// an entity, so there is nothing to ask about and the act runs.
|
||||
func TestTheNameNexusKnowsWins(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := nexusInOrder(t,
|
||||
fixtureNexusNotFound(),
|
||||
fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"),
|
||||
)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти nginx на muzick-indexer",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Text: "перезагрузить нгинкс", Fn: "restart", HasFn: true},
|
||||
}
|
||||
reply := h.handleHexisAct(ctx, dec)
|
||||
if reply == "" {
|
||||
t.Fatal("the resolvable name must carry the act")
|
||||
}
|
||||
if len(nexus.Requests()) != 2 {
|
||||
t.Fatalf("nexus asked %d times, want both names", len(nexus.Requests()))
|
||||
}
|
||||
if hexis.Count("POST", "/api/v1/execute") == 0 {
|
||||
t.Fatal("hexis was never asked to run it")
|
||||
}
|
||||
}
|
||||
@@ -28,11 +28,10 @@ func TestApplyAction_FactCapture_QueuesEntityResolution(t *testing.T) {
|
||||
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
embedder: emb,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: rtr,
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
memStore: memory.NewInMemoryStore(),
|
||||
dataStore: st,
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"log"
|
||||
"strings"
|
||||
"unicode"
|
||||
)
|
||||
|
||||
// ungroundedConfidence — what a self fact is worth when its value appears
|
||||
// nowhere in what he said. Below `query_min_score` is not the point (recall
|
||||
// gates on vector distance, not on this number); the point is that
|
||||
// `/history` and every future reader can tell a value he said from a value
|
||||
// the model supplied.
|
||||
const ungroundedConfidence = 0.6
|
||||
|
||||
// factConfidence scores a self fact by whether its value is grounded in the
|
||||
// utterance it came from. Grounded stays 1.00, which is what a tapped fact
|
||||
// has always been worth. Ungrounded drops, and says so in the log.
|
||||
//
|
||||
// An empty value is grounded by definition: the key alone carries the fact
|
||||
// ("поужинал"), and there is nothing for the model to have invented.
|
||||
func factConfidence(utterance, value string) float64 {
|
||||
if strings.TrimSpace(value) == "" {
|
||||
return 1.0
|
||||
}
|
||||
if valueGrounded(utterance, value) {
|
||||
return 1.0
|
||||
}
|
||||
log.Printf("voice: fact value %q is not in %q — writing at confidence %.2f",
|
||||
value, utterance, ungroundedConfidence)
|
||||
return ungroundedConfidence
|
||||
}
|
||||
|
||||
// valueGrounded reports whether every word of value traces back to a word he
|
||||
// actually said. The comparison is on a 4-rune prefix, so the model's
|
||||
// normalization survives ("пил воду" → "вода") while an invented value
|
||||
// ("1.20" for a question about Go) does not.
|
||||
func valueGrounded(utterance, value string) bool {
|
||||
said := factTokens(utterance)
|
||||
words := factTokens(value)
|
||||
if len(words) == 0 {
|
||||
return true
|
||||
}
|
||||
for _, w := range words {
|
||||
if !anyTokenMatches(said, w) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func anyTokenMatches(said []string, w string) bool {
|
||||
for _, s := range said {
|
||||
if s == w || sameStem(s, w) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// sameStem is inflection tolerance and nothing more: it compares all but the
|
||||
// last rune of the shorter word, and never fewer than three. Russian marks
|
||||
// case on the ending, so "пил воду" and the stored "вода" are the same word he
|
||||
// said, while "1.20" and "версия" are not. A word of three runes or fewer must
|
||||
// match outright, where a shorter prefix would match half the language.
|
||||
func sameStem(a, b string) bool {
|
||||
ar, br := []rune(a), []rune(b)
|
||||
shorter := min(len(ar), len(br))
|
||||
n := shorter - 1
|
||||
if n < 3 || len(ar) < n || len(br) < n {
|
||||
return false
|
||||
}
|
||||
return string(ar[:n]) == string(br[:n])
|
||||
}
|
||||
|
||||
// factTokens lowercases and splits on everything that is not a letter or a
|
||||
// digit, the same shape planTokens uses in the router.
|
||||
func factTokens(s string) []string {
|
||||
return strings.FieldsFunc(strings.ToLower(s), func(r rune) bool {
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,235 @@
|
||||
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/tool"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
func newFactGateHandler(t *testing.T, now time.Time) (*reactiveHandler, ipc.CoreAPI) {
|
||||
t.Helper()
|
||||
st := newTestStore(t)
|
||||
api := ipc.NewStoreAPI(st)
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, tool.NewMatcher(api), 0.55, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
}
|
||||
return h, api
|
||||
}
|
||||
|
||||
// The write half of #470: a question routed to IntentFact must not become a
|
||||
// fact about him, and must not leave a vector behind for recall to serve.
|
||||
func TestActionFact_QuestionIsNotWritten(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, api := newFactGateHandler(t, time.Now())
|
||||
|
||||
reply := h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "какая последняя версия языка Go?",
|
||||
Slots: router.Slots{Key: "go_version", HasKey: true, Value: `"1.20"`},
|
||||
})
|
||||
|
||||
if _, err := api.LatestFact(ctx, "go_version"); err == nil {
|
||||
t.Fatal("a question was stored as a fact about him")
|
||||
}
|
||||
hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "какая последняя версия языка Go?"), 3)
|
||||
if err != nil {
|
||||
t.Fatalf("memory search: %v", err)
|
||||
}
|
||||
if len(hits) != 0 {
|
||||
t.Fatalf("the question was indexed for recall: %+v", hits)
|
||||
}
|
||||
// It went down the query chain instead. Nothing is configured to answer a
|
||||
// world question in this harness, so "не знаю." is the honest outcome —
|
||||
// what matters is that the turn was answered, not stored.
|
||||
if reply == "" {
|
||||
t.Fatal("the turn was neither stored nor answered")
|
||||
}
|
||||
}
|
||||
|
||||
// The capture that must survive the gate: an explicit instruction to record,
|
||||
// even though it contains an interrogative.
|
||||
func TestActionFact_ExplicitCaptureStillWrites(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, api := newFactGateHandler(t, time.Now())
|
||||
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запиши что я пил воду",
|
||||
Slots: router.Slots{Key: "water", HasKey: true, Value: `"вода"`},
|
||||
})
|
||||
|
||||
f, err := api.LatestFact(ctx, "water")
|
||||
if err != nil {
|
||||
t.Fatalf("an explicit capture was refused: %v", err)
|
||||
}
|
||||
if f.Confidence != 1.0 {
|
||||
t.Errorf("confidence = %v, want 1.0 for a value he said", f.Confidence)
|
||||
}
|
||||
// #493: what recall reads back is the fact, not the sentence he said.
|
||||
// queryMemory returns a fact's text verbatim, so the utterance sitting here
|
||||
// meant "запиши что я пил воду" was the answer to "когда я пил воду?".
|
||||
hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 3)
|
||||
if err != nil {
|
||||
t.Fatalf("memory search: %v", err)
|
||||
}
|
||||
if len(hits) != 1 {
|
||||
t.Fatalf("the fact was not indexed once: %+v", hits)
|
||||
}
|
||||
if got := hits[0].Meta["text"]; got != "water — вода" {
|
||||
t.Errorf("indexed text = %q, want the fact", got)
|
||||
}
|
||||
if got := hits[0].Meta["utterance"]; got != "запиши что я пил воду" {
|
||||
t.Errorf("utterance provenance = %q, want it kept alongside", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestFactConfidence(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance, value string
|
||||
want float64
|
||||
}{
|
||||
{"запиши что я пил воду", `"вода"`, 1.0},
|
||||
{"я выпил кофе", `"кофе"`, 1.0},
|
||||
{"поужинал", "", 1.0},
|
||||
{"отметь что я полил кактус", `"полил кактус"`, 1.0},
|
||||
{"какая последняя версия языка Go", `"1.20"`, ungroundedConfidence},
|
||||
{"кто премьер Японии", `"Тонио Озаки"`, ungroundedConfidence},
|
||||
}
|
||||
for _, c := range cases {
|
||||
if got := factConfidence(c.utterance, c.value); got != c.want {
|
||||
t.Errorf("factConfidence(%q, %q) = %v, want %v", c.utterance, c.value, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func mustEmbedPassage(t *testing.T, h *reactiveHandler, text string) []float32 {
|
||||
t.Helper()
|
||||
vec, err := router.EmbedQuery(context.Background(), h.recall.embedder, text)
|
||||
if err != nil {
|
||||
t.Fatalf("embed %q: %v", text, err)
|
||||
}
|
||||
return vec
|
||||
}
|
||||
|
||||
// The write half of #481: a complaint about a thing is a state of the
|
||||
// afternoon, not a fact about him. Stored as a `self` row at confidence 1.00
|
||||
// it comes back on recall as if the network were still down.
|
||||
func TestActionFact_ComplaintIsNotWritten(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, api := newFactGateHandler(t, time.Now())
|
||||
|
||||
reply := h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "сеть какая-то медленная",
|
||||
Slots: router.Slots{Key: "network_speed", HasKey: true, Value: "медленная"},
|
||||
})
|
||||
|
||||
if _, err := api.LatestFact(ctx, "network_speed"); err == nil {
|
||||
t.Fatal("a passing complaint was stored as a fact about him")
|
||||
}
|
||||
hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "сеть какая-то медленная"), 3)
|
||||
if err != nil {
|
||||
t.Fatalf("memory search: %v", err)
|
||||
}
|
||||
if len(hits) != 0 {
|
||||
t.Fatalf("the complaint was indexed for recall: %+v", hits)
|
||||
}
|
||||
if reply == "" {
|
||||
t.Fatal("the turn was neither stored nor answered")
|
||||
}
|
||||
}
|
||||
|
||||
// And the complaint he asked her to keep: the capture verb wins, as it does
|
||||
// over the question gate.
|
||||
func TestActionFact_AskedToRememberAComplaintStillWrites(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, api := newFactGateHandler(t, time.Now())
|
||||
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запомни что интернет не работает",
|
||||
Slots: router.Slots{Key: "internet", HasKey: true, Value: "не работает"},
|
||||
})
|
||||
|
||||
if _, err := api.LatestFact(ctx, "internet"); err != nil {
|
||||
t.Fatalf("an explicit capture was refused: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A second tap of the same key supersedes the first, so recall must hold one
|
||||
// vector and it must be the new value (Vikunja #493). Before this the id
|
||||
// carried a timestamp, both rows stayed, and the superseded value went on
|
||||
// competing for the turn.
|
||||
func TestActionFact_ARetapSupersedesTheOldVector(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newFactGateHandler(t, time.Now())
|
||||
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запиши что я пил воду",
|
||||
Slots: router.Slots{Key: "water", HasKey: true, Value: `"250мл"`},
|
||||
})
|
||||
// A later tap of the same key. The clock moves, so the old id and the new
|
||||
// one differ — which is exactly what used to leave two rows behind.
|
||||
h.now = func() time.Time { return time.Now().Add(time.Hour) }
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запиши что я пил воду",
|
||||
Slots: router.Slots{Key: "water", HasKey: true, Value: `"500мл"`},
|
||||
})
|
||||
|
||||
hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 5)
|
||||
if err != nil {
|
||||
t.Fatalf("memory search: %v", err)
|
||||
}
|
||||
if len(hits) != 1 {
|
||||
t.Fatalf("want one vector for the key, got %d: %+v", len(hits), hits)
|
||||
}
|
||||
if got := hits[0].Meta["text"]; got != "water — 500мл" {
|
||||
t.Errorf("indexed text = %q, want the current value", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Another key is not this key. A prefix delete that widened would take the
|
||||
// whole index with it.
|
||||
func TestActionFact_ARetapLeavesOtherKeysAlone(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
h, _ := newFactGateHandler(t, time.Now())
|
||||
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запиши что я обедал",
|
||||
Slots: router.Slots{Key: "meal", HasKey: true, Value: `"суп"`},
|
||||
})
|
||||
h.actionFact(ctx, router.Decision{
|
||||
Intent: router.IntentFact,
|
||||
Utterance: "запиши что я пил воду",
|
||||
Slots: router.Slots{Key: "water", HasKey: true, Value: `"250мл"`},
|
||||
})
|
||||
|
||||
hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "обед"), 5)
|
||||
if err != nil {
|
||||
t.Fatalf("memory search: %v", err)
|
||||
}
|
||||
var found bool
|
||||
for _, hit := range hits {
|
||||
if hit.Meta["text"] == "meal — суп" {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatalf("writing water dropped the meal vector: %+v", hits)
|
||||
}
|
||||
}
|
||||
@@ -178,6 +178,14 @@ func (fs *fakeServer) Requests() []capturedRequest {
|
||||
return out
|
||||
}
|
||||
|
||||
// ResetRequests drops the captured requests, so a test can assert about one
|
||||
// turn without subtracting the setup turn's calls.
|
||||
func (fs *fakeServer) ResetRequests() {
|
||||
fs.mu.Lock()
|
||||
defer fs.mu.Unlock()
|
||||
fs.requests = nil
|
||||
}
|
||||
|
||||
func jsonHandler(status int, body string) http.HandlerFunc {
|
||||
return func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
@@ -330,7 +338,17 @@ func newFakeNexus(t *testing.T, resolveBody string) *fakeServer {
|
||||
// Maven's praxisClient calls. Every route returns its fixed body until a
|
||||
// fault is injected via SetFault.
|
||||
func newFakePraxis(t *testing.T, attentionBody string) *fakeServer {
|
||||
// One healthy source by default: an empty attention list only means
|
||||
// all-clear when something is actually polling (Vikunja #540), and the
|
||||
// other tests here are about attention rather than about source health.
|
||||
return newFakePraxisWithSources(t, attentionBody, `[{"source_id":"src_ntfy","health":"ok"}]`)
|
||||
}
|
||||
|
||||
// newFakePraxisWithSources is newFakePraxis with the /api/v1/sources body
|
||||
// under the test's control, for the degraded and no-sources hedges.
|
||||
func newFakePraxisWithSources(t *testing.T, attentionBody, sourcesBody string) *fakeServer {
|
||||
return newFakeServer(t, map[string]http.HandlerFunc{
|
||||
"GET /api/v1/sources": jsonHandler(http.StatusOK, sourcesBody),
|
||||
"GET /api/v1/tools/attention": jsonHandler(http.StatusOK, attentionBody),
|
||||
"GET /api/v1/tools/changes": jsonHandler(http.StatusOK, `[]`),
|
||||
"POST /api/v1/tools/surface": jsonHandler(http.StatusOK, `{}`),
|
||||
|
||||
@@ -29,12 +29,12 @@ func buildFeedHandler(t *testing.T, feedsOn bool, notes ...ipc.Note) *reactiveHa
|
||||
}
|
||||
}
|
||||
return &reactiveHandler{
|
||||
api: ipc.NewStoreAPI(st),
|
||||
replier: voice.NewStubReplier(),
|
||||
phraser: phraser.NewStub(),
|
||||
now: func() time.Time { return now },
|
||||
feedsOn: feedsOn,
|
||||
embedder: nil,
|
||||
api: ipc.NewStoreAPI(st),
|
||||
replier: voice.NewStubReplier(),
|
||||
phraser: phraser.NewStub(),
|
||||
now: func() time.Time { return now },
|
||||
feedsOn: feedsOn,
|
||||
recall: recallWiring{embedder: nil},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -79,7 +79,7 @@ func TestQueryFeedsByCategory(t *testing.T) {
|
||||
t.Fatalf("reply = %q, want only the технологии item", reply)
|
||||
}
|
||||
reply, _ = askFeeds(t, h, "что нового по спорту?")
|
||||
if !strings.Contains(reply, "ничего") {
|
||||
if !phraser.IsQ(phraser.QueryFeedsTopic, nil, reply) {
|
||||
t.Fatalf("reply = %q, want an honest empty answer for an unread category", reply)
|
||||
}
|
||||
}
|
||||
@@ -87,16 +87,22 @@ func TestQueryFeedsByCategory(t *testing.T) {
|
||||
// "не настроены" and "ничего нового" are different truths, and neither may be
|
||||
// answered by the model inventing a bulletin.
|
||||
func TestQueryFeedsOffAndEmptyDiffer(t *testing.T) {
|
||||
// Against the entries, not against a substring: both of these have several
|
||||
// wordings, so "ничего нового" passed only on the turns the picker happened
|
||||
// to choose the first one.
|
||||
off := buildFeedHandler(t, false)
|
||||
reply, ok := askFeeds(t, off, "что нового в лентах?")
|
||||
if !ok || !strings.Contains(reply, "не настроены") {
|
||||
if !ok || !phraser.IsQ(phraser.QueryFeedsOff, nil, reply) {
|
||||
t.Fatalf("feeds off: reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
on := buildFeedHandler(t, true)
|
||||
reply, ok = askFeeds(t, on, "что нового в лентах?")
|
||||
if !ok || !strings.Contains(reply, "ничего нового") {
|
||||
if !ok || !phraser.IsQ(phraser.QueryFeedsEmpty, nil, reply) {
|
||||
t.Fatalf("feeds on but empty: reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
if phraser.IsQ(phraser.QueryFeedsOff, nil, reply) {
|
||||
t.Fatalf("an empty feed answered as an unconfigured one: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
func TestQueryFeedsPassesOnANonFeedQuestion(t *testing.T) {
|
||||
@@ -194,3 +200,22 @@ func TestFeedWorkerFetcherIsAllowlisted(t *testing.T) {
|
||||
t.Fatal("the poller fetched a private address")
|
||||
}
|
||||
}
|
||||
|
||||
// TestQueryFeedsPassesWhenTheWorldCanAnswer — the defect (Vikunja #474). The
|
||||
// deployed box has no feeds block and does have SearXNG, and "что происходит
|
||||
// сейчас в новостях про искусственный интеллект?" got a configuration status
|
||||
// instead of the live answer sitting one source below.
|
||||
func TestQueryFeedsPassesWhenTheWorldCanAnswer(t *testing.T) {
|
||||
h := buildFeedHandler(t, false)
|
||||
h.search = &searchWiring{max: 3, runes: 1500}
|
||||
|
||||
if reply, ok := askFeeds(t, h, "что нового в лентах?"); ok {
|
||||
t.Fatalf("feeds off with a search configured must fall through, got %q", reply)
|
||||
}
|
||||
// With nothing below that reads the world, the honest status is still said:
|
||||
// general knowledge would otherwise answer with an invented bulletin.
|
||||
h.search = nil
|
||||
if reply, ok := askFeeds(t, h, "что нового в лентах?"); !ok || !strings.Contains(reply, "не настроены") {
|
||||
t.Fatalf("no search and no ZIMs: reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
}
|
||||
|
||||
+78
-9
@@ -1,24 +1,79 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// voiceDialogueID — the single dialogue-session key. This is a single-user box
|
||||
// (ponytail), so one slot suffices; a second speaker would need per-speaker ids,
|
||||
// which waits on voice-print attribution (see PROGRESS multi-user deferral).
|
||||
// voiceDialogueID — the dialogue-session and clarify key for the microphone.
|
||||
// This is a single-user box (ponytail), so one slot per reach suffices; a
|
||||
// second speaker would need per-speaker ids, which waits on voice-print
|
||||
// attribution (see PROGRESS multi-user deferral).
|
||||
const voiceDialogueID = "voice"
|
||||
|
||||
// toDialogueSlots projects the router's slots onto the dialogue layer's subset
|
||||
// (everything except the fact Value, which the dialogue layer doesn't carry).
|
||||
// textDialogueID — the clarify key for a text turn that named no conversation.
|
||||
// Separate from the mic: an old client that sends no id still must not answer
|
||||
// a question she asked out loud.
|
||||
const textDialogueID = "text"
|
||||
|
||||
// dialogueKey — the context key carrying the id of the conversation this turn
|
||||
// belongs to. It rides the context rather than a parameter for the same reason
|
||||
// the correlation id does: every step of the turn needs it, most of them only
|
||||
// to hand to the next one, and threading it by hand would put it in six
|
||||
// clarify signatures that have nothing else to say about it.
|
||||
type dialogueKey struct{}
|
||||
|
||||
// dialogueIDFor builds the id a turn is held under: the conversation the reach
|
||||
// named, qualified by the tap it arrived on, or the tap's own fallback when it
|
||||
// named none.
|
||||
//
|
||||
// A parked clarifying question used to be held under voiceDialogueID no matter
|
||||
// where the turn came from, so one unanswerable question captured the next
|
||||
// three utterances from anywhere. Three independent curl sessions fed a
|
||||
// capture attempt that had already failed, and a reminder among them was lost
|
||||
// (Vikunja #466).
|
||||
func dialogueIDFor(src turnSource, conversation string) string {
|
||||
if conversation != "" {
|
||||
return string(src) + ":" + conversation
|
||||
}
|
||||
if src == sourceVoice {
|
||||
return voiceDialogueID
|
||||
}
|
||||
return textDialogueID
|
||||
}
|
||||
|
||||
// withDialogueID tags a turn with that id.
|
||||
func withDialogueID(ctx context.Context, id string) context.Context {
|
||||
return context.WithValue(ctx, dialogueKey{}, id)
|
||||
}
|
||||
|
||||
// dialogueIDOf reads it back. Falls back to the microphone's slot, which is
|
||||
// what an unthreaded caller — a test, an internal replay — gets.
|
||||
func dialogueIDOf(ctx context.Context) string {
|
||||
if id, ok := ctx.Value(dialogueKey{}).(string); ok && id != "" {
|
||||
return id
|
||||
}
|
||||
return voiceDialogueID
|
||||
}
|
||||
|
||||
// toDialogueSlots and applyDialogueSlots are the only bridge between
|
||||
// router.Slots and dialogue.Slots. dialogue must not import router (import
|
||||
// cycle), so the two structs are hand-kept copies and every field has to be
|
||||
// carried by hand here. Adding a field to either struct without adding it to
|
||||
// BOTH functions loses a slot silently — nothing fails to build. The tests in
|
||||
// slotsparity_test.go fail when the field sets or the converters stop matching;
|
||||
// when they do, fix these two functions, not the tests.
|
||||
|
||||
// toDialogueSlots projects the router's slots onto the dialogue layer's copy.
|
||||
func toDialogueSlots(s router.Slots) dialogue.Slots {
|
||||
return dialogue.Slots{
|
||||
Time: s.Time,
|
||||
HasTime: s.HasTime,
|
||||
Key: s.Key,
|
||||
Value: s.Value,
|
||||
HasKey: s.HasKey,
|
||||
Text: s.Text,
|
||||
Fn: s.Fn,
|
||||
@@ -27,11 +82,10 @@ func toDialogueSlots(s router.Slots) dialogue.Slots {
|
||||
}
|
||||
}
|
||||
|
||||
// applyDialogueSlots writes inherited dialogue slots back onto router slots,
|
||||
// preserving router-only fields (Value) the dialogue layer never touched.
|
||||
// applyDialogueSlots writes dialogue slots back onto router slots.
|
||||
func applyDialogueSlots(base router.Slots, d dialogue.Slots) router.Slots {
|
||||
base.Time, base.HasTime = d.Time, d.HasTime
|
||||
base.Key, base.HasKey = d.Key, d.HasKey
|
||||
base.Key, base.Value, base.HasKey = d.Key, d.Value, d.HasKey
|
||||
base.Text = d.Text
|
||||
base.Fn, base.Args, base.HasFn = d.Fn, d.Args, d.HasFn
|
||||
return base
|
||||
@@ -43,7 +97,8 @@ var anaphoraResolver router.AnaphoraResolver
|
||||
// followUpMerge fills the current turn's missing slots from a prior
|
||||
// non-expired session — the multi-turn seam. It handles three cases:
|
||||
//
|
||||
// 1. Same-intent: inherit missing slots via InheritSlots (existing behavior).
|
||||
// 1. Same-intent: inherit missing slots via InheritSlots (existing behavior),
|
||||
// except a reminder time the current sentence named and the parser missed.
|
||||
// 2. Cross-intent anaphora: if the current utterance contains a pronoun
|
||||
// ("это" / "он" / "она" etc.) AND the prior session has a key, inherit
|
||||
// the key for fact-lookup queries and reminder creation.
|
||||
@@ -59,8 +114,22 @@ func followUpMerge(prev *dialogue.Session, dec router.Decision, now time.Time) r
|
||||
|
||||
// Case 1: same-intent inheritance (existing).
|
||||
if prev.Intent == dialogue.Intent(dec.Intent) {
|
||||
// A reminder that named an hour nobody could read must not borrow the
|
||||
// last one's. Two reminders in a row and the second landed at the
|
||||
// first's time, confirmed as if it had been read from the sentence:
|
||||
// "напомни без четверти восемь выходить" fired at 07:30 (V-543). The
|
||||
// hour is also what fills before the action's own fallback parse can
|
||||
// run, so inheriting it hid a time that did parse.
|
||||
//
|
||||
// Inheriting is still right when the sentence names no time at all,
|
||||
// which is the follow-up this seam exists for.
|
||||
blockTime := dec.Intent == router.IntentReminder &&
|
||||
!dec.Slots.HasTime && router.MentionsTime(dec.Utterance)
|
||||
merged := dialogue.InheritSlots(prev.Slots, toDialogueSlots(dec.Slots))
|
||||
dec.Slots = applyDialogueSlots(dec.Slots, merged)
|
||||
if blockTime {
|
||||
dec.Slots.Time, dec.Slots.HasTime = time.Time{}, false
|
||||
}
|
||||
return dec
|
||||
}
|
||||
|
||||
|
||||
@@ -35,6 +35,42 @@ func TestFollowUpMerge(t *testing.T) {
|
||||
}
|
||||
})
|
||||
|
||||
// V-543, measured on the box: four reminders in a row all landed at the
|
||||
// first one's hour, each confirmed as if it had been read from the sentence.
|
||||
// A sentence that names a time and fails to parse must ask, not borrow.
|
||||
t.Run("a named time that did not parse is not inherited", func(t *testing.T) {
|
||||
for _, utt := range []string{
|
||||
"напомни без четверти восемь выходить",
|
||||
"напомни в половине первого пообедать",
|
||||
"напомни завтра принять лекарство",
|
||||
"remind me at noon to stretch",
|
||||
} {
|
||||
cur := router.Decision{
|
||||
Intent: router.IntentReminder,
|
||||
Utterance: utt,
|
||||
Slots: router.Slots{Text: utt},
|
||||
}
|
||||
got := followUpMerge(prev, cur, base.Add(30*time.Second))
|
||||
if got.Slots.HasTime {
|
||||
t.Errorf("%q borrowed the previous hour %v", utt, got.Slots.Time)
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
// The follow-up this seam exists for still works: the sentence names no
|
||||
// time, so the previous one is the only one it could mean.
|
||||
t.Run("a follow-up naming no time still inherits", func(t *testing.T) {
|
||||
cur := router.Decision{
|
||||
Intent: router.IntentReminder,
|
||||
Utterance: "и ещё полить цветы",
|
||||
Slots: router.Slots{Text: "полить цветы"},
|
||||
}
|
||||
got := followUpMerge(prev, cur, base.Add(30*time.Second))
|
||||
if !got.Slots.HasTime || !got.Slots.Time.Equal(fireAt) {
|
||||
t.Errorf("time not inherited: HasTime=%v Time=%v", got.Slots.HasTime, got.Slots.Time)
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("current slot wins over prior (gaps only)", func(t *testing.T) {
|
||||
own := base.Add(48 * time.Hour)
|
||||
cur := router.Decision{
|
||||
|
||||
@@ -0,0 +1,180 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/morph"
|
||||
)
|
||||
|
||||
// Command history — "что я тебе говорил?", "что ты записала сегодня?"
|
||||
// (Vikunja #456).
|
||||
//
|
||||
// Read-only over the facts that already exist. No new mechanism and no new
|
||||
// storage: everything he tapped in is already a row with a source and a
|
||||
// timestamp, and this only reads them back.
|
||||
|
||||
// A history question needs three things in one utterance: the interrogative,
|
||||
// whose turn is being asked about, and a verb of saying or recording. Any two of
|
||||
// them are a different question. "что я говорил про сервер" names a topic and
|
||||
// the notes pass answers it better; "записал молоко" is a capture.
|
||||
//
|
||||
// The verbs are matched by lemma through internal/morph, not by a truncated
|
||||
// prefix (Vikunja #530). The pairs here used to hold "рассказ" and "записал",
|
||||
// which is the defect V-528 fixed in complaint.go: "рассказ" is also the noun,
|
||||
// so "что я рассказал ей" and "что я читал рассказ" were the same string test.
|
||||
// Aspect pairs are separate lemmas in the dictionary, so both members are listed.
|
||||
var (
|
||||
// historySpokenVerbs — what HE did. "что я тебе говорил".
|
||||
historySpokenVerbs = []string{"говорить", "сказать", "рассказать", "рассказывать", "отметить", "отмечать"}
|
||||
|
||||
// historyRecordedVerbs — what SHE did with it. "что ты записала сегодня".
|
||||
historyRecordedVerbs = []string{"записать", "запомнить", "отметить", "отмечать"}
|
||||
|
||||
// firstPersonSubjects and secondPersonSubjects — whose turn the question is
|
||||
// about. Only the subject forms: "что я тебе говорил" is his turn, and the
|
||||
// dative "тебе" in it is not the subject.
|
||||
firstPersonSubjects = []string{"я"}
|
||||
secondPersonSubjects = []string{"ты"}
|
||||
)
|
||||
|
||||
// historyMarkersEn — the English pairs, kept as substrings because the
|
||||
// dictionary is Russian. Each half alone is a different question, the same way
|
||||
// the Russian test needs all three parts.
|
||||
var historyMarkersEn = [][2]string{
|
||||
{"what did i", "tell"},
|
||||
{"what did you", "record"},
|
||||
}
|
||||
|
||||
// historyRecall — the word that turns a history question into a recall
|
||||
// question. "что я говорил про сервер" names a topic, and the notes pass
|
||||
// answers a topic far better than a list of the last five facts does.
|
||||
var historyRecall = []string{" про ", " об ", " о ", " about "}
|
||||
|
||||
// isHistoryQuery reports whether he is asking what he told her.
|
||||
func isHistoryQuery(u string) bool {
|
||||
s := " " + strings.ToLower(strings.TrimSpace(u)) + " "
|
||||
if s == " " {
|
||||
return false
|
||||
}
|
||||
for _, r := range historyRecall {
|
||||
if strings.Contains(s, r) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
for _, pair := range historyMarkersEn {
|
||||
if strings.Contains(s, pair[0]) && strings.Contains(s, pair[1]) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
toks := historyTokens(s)
|
||||
if !hasAny(toks, "что", "чего") {
|
||||
return false
|
||||
}
|
||||
if hasAny(toks, firstPersonSubjects...) && hasVerbForm(toks, historySpokenVerbs) {
|
||||
return true
|
||||
}
|
||||
return hasAny(toks, secondPersonSubjects...) && hasVerbForm(toks, historyRecordedVerbs)
|
||||
}
|
||||
|
||||
// historyTokens splits an utterance into bare words. The punctuation goes
|
||||
// because "говорил?" is the same word as "говорил".
|
||||
func historyTokens(s string) []string {
|
||||
toks := strings.Fields(s)
|
||||
out := make([]string, 0, len(toks))
|
||||
for _, t := range toks {
|
||||
if t = strings.Trim(t, ".,!?;:—–-()\"'«»"); t != "" {
|
||||
out = append(out, t)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func hasAny(toks []string, want ...string) bool {
|
||||
for _, t := range toks {
|
||||
for _, w := range want {
|
||||
if t == w {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// hasVerbForm reports whether any token is a form of any of the lemmas. Both
|
||||
// sides go through the dictionary, so a caller may name the infinitive and he
|
||||
// may say the past tense.
|
||||
func hasVerbForm(toks []string, lemmas []string) bool {
|
||||
for _, t := range toks {
|
||||
for _, l := range lemmas {
|
||||
if morph.SameWord(t, l) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// historyScan — how many recent facts are read before filtering. Deliberately
|
||||
// larger than historyReadOut: a poller writing every few minutes would
|
||||
// otherwise push everything he said out of the window, the same way his own
|
||||
// notes used to crowd out the feed headlines.
|
||||
const historyScan = 100
|
||||
|
||||
// historyReadOut — how many she says out loud. Five is what fits in one spoken
|
||||
// breath; the rest are on /history, which is the surface for reading a list.
|
||||
const historyReadOut = 5
|
||||
|
||||
// historyWindow — how far back "recently" reaches. A day, because the question
|
||||
// is about this conversation and not about the archive.
|
||||
const historyWindow = 24 * time.Hour
|
||||
|
||||
// queryHistory answers what he told her, from the facts he tapped in.
|
||||
//
|
||||
// Only "tap:" sources. A fact written by a poller, an inference or the ambient
|
||||
// relay is a thing she learned, not a thing he said, and reading those back
|
||||
// under "что я тебе говорил?" would put words in his mouth.
|
||||
//
|
||||
// Placed with the other sources that read his own rows and above the recall
|
||||
// pass: the notes pass would otherwise answer this from whatever note happens
|
||||
// to be nearest, which reads as an answer and is not one.
|
||||
func (h *reactiveHandler) queryHistory(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isHistoryQuery(t.dec.Utterance) {
|
||||
return "", false
|
||||
}
|
||||
facts, err := h.api.RecentFacts(ctx, historyScan)
|
||||
if err != nil {
|
||||
log.Printf("voice: history: recent facts: %v", err)
|
||||
return "не получилось посмотреть, что ты говорил.", true
|
||||
}
|
||||
cutoff := h.now().Add(-historyWindow)
|
||||
var said []string
|
||||
for _, f := range facts {
|
||||
if !strings.HasPrefix(f.Source, "tap:") || f.Ts.Before(cutoff) {
|
||||
continue
|
||||
}
|
||||
said = append(said, historyLine(f.Key, f.Value, f.Ts))
|
||||
if len(said) == historyReadOut {
|
||||
break
|
||||
}
|
||||
}
|
||||
if len(said) == 0 {
|
||||
// Claim the turn rather than fall through. "ничего не говорил" is the
|
||||
// true answer, and recall would answer it with an old note instead.
|
||||
return "за последние сутки ты мне ничего такого не говорил.", true
|
||||
}
|
||||
return "ты говорил: " + strings.Join(said, "; "), true
|
||||
}
|
||||
|
||||
// historyLine — one fact as she says it. The hour and minute, because the day
|
||||
// is already bounded by historyWindow and a date would be noise.
|
||||
func historyLine(key, value string, ts time.Time) string {
|
||||
what := key
|
||||
if value != "" {
|
||||
what = key + " — " + value
|
||||
}
|
||||
return fmt.Sprintf("%s (%s)", what, ts.Local().Format("15:04"))
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// historyAPI serves a fixed set of recent facts.
|
||||
type historyAPI struct {
|
||||
ipc.UnimplementedCoreAPI
|
||||
facts []ipc.Fact
|
||||
calls int
|
||||
}
|
||||
|
||||
func (a *historyAPI) RecentFacts(context.Context, int) ([]ipc.Fact, error) {
|
||||
a.calls++
|
||||
return a.facts, nil
|
||||
}
|
||||
|
||||
func historyHandler(now time.Time, facts ...ipc.Fact) (*reactiveHandler, *historyAPI) {
|
||||
api := &historyAPI{facts: facts}
|
||||
return &reactiveHandler{api: api, now: func() time.Time { return now }}, api
|
||||
}
|
||||
|
||||
func askHistory(h *reactiveHandler, u string) (string, bool) {
|
||||
return h.queryHistory(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: u},
|
||||
})
|
||||
}
|
||||
|
||||
func TestIsHistoryQuery(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
text string
|
||||
want bool
|
||||
}{
|
||||
{"что я тебе говорил?", true},
|
||||
{"что ты записала сегодня?", true},
|
||||
{"что я отмечал?", true},
|
||||
// Forms the truncated prefixes did not reach. The dictionary answers
|
||||
// these because it lemmatises both sides (V-530).
|
||||
{"что я тебе рассказывал?", true},
|
||||
{"что я сказала вчера", true},
|
||||
{"что ты запомнила?", true},
|
||||
// The noun, not the verb. "рассказ" was a prefix of the old pair, so
|
||||
// this read as a history question — the same defect V-528 fixed in
|
||||
// complaint.go, where "лаг" matched "лагерь".
|
||||
{"что я читал рассказ", false},
|
||||
// A verb of saying with nobody saying it.
|
||||
{"что записать?", false},
|
||||
// A named topic is a recall question, and the notes pass answers it
|
||||
// better than a list of the last five facts does.
|
||||
{"что я говорил про сервер?", false},
|
||||
{"что у меня сегодня?", false},
|
||||
{"", false},
|
||||
} {
|
||||
if got := isHistoryQuery(tc.text); got != tc.want {
|
||||
t.Errorf("isHistoryQuery(%q) = %v, want %v", tc.text, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestHistoryReadsOnlyWhatHeSaid(t *testing.T) {
|
||||
now := time.Date(2026, 8, 4, 20, 0, 0, 0, time.UTC)
|
||||
h, api := historyHandler(now,
|
||||
ipc.Fact{Key: "water", Value: "выпил", Source: "tap:voice", Ts: now.Add(-time.Hour)},
|
||||
// Learned, not said: a poller writing this back under "что я тебе
|
||||
// говорил?" would put words in his mouth.
|
||||
ipc.Fact{Key: "spent_today", Value: "1200", Source: "poll:zenmoney", Ts: now.Add(-time.Hour)},
|
||||
// Older than the window.
|
||||
ipc.Fact{Key: "shower", Value: "принял", Source: "tap:voice", Ts: now.Add(-30 * time.Hour)},
|
||||
)
|
||||
reply, ok := askHistory(h, "что я тебе говорил?")
|
||||
if !ok {
|
||||
t.Fatal("the history question must be claimed before the recall sources")
|
||||
}
|
||||
if !strings.Contains(reply, "water") {
|
||||
t.Errorf("reply = %q, want the fact he tapped in", reply)
|
||||
}
|
||||
if strings.Contains(reply, "spent_today") || strings.Contains(reply, "shower") {
|
||||
t.Errorf("reply = %q, want only what he said inside the window", reply)
|
||||
}
|
||||
if api.calls != 1 {
|
||||
t.Errorf("RecentFacts called %d times, want 1", api.calls)
|
||||
}
|
||||
}
|
||||
|
||||
// Nothing said is an answer of its own. Falling through would hand the question
|
||||
// to recall, which answers it with an old note.
|
||||
func TestHistorySaysWhenThereIsNothing(t *testing.T) {
|
||||
now := time.Date(2026, 8, 4, 20, 0, 0, 0, time.UTC)
|
||||
h, _ := historyHandler(now)
|
||||
reply, ok := askHistory(h, "что я тебе говорил?")
|
||||
if !ok || !strings.Contains(reply, "ничего") {
|
||||
t.Fatalf("reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
}
|
||||
|
||||
// Five is what fits in one spoken breath; the rest are on /history.
|
||||
func TestHistoryStopsAtFive(t *testing.T) {
|
||||
now := time.Date(2026, 8, 4, 20, 0, 0, 0, time.UTC)
|
||||
var facts []ipc.Fact
|
||||
for i := 0; i < 12; i++ {
|
||||
facts = append(facts, ipc.Fact{Key: "k", Value: "v", Source: "tap:voice", Ts: now.Add(-time.Minute)})
|
||||
}
|
||||
h, _ := historyHandler(now, facts...)
|
||||
reply, _ := askHistory(h, "что ты записала?")
|
||||
if got := strings.Count(reply, ";"); got != historyReadOut-1 {
|
||||
t.Fatalf("reply = %q has %d separators, want %d", reply, got, historyReadOut-1)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
package main
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestHasCyrillic(t *testing.T) {
|
||||
for _, s := range []string{"что такое фотосинтез", "кто такой Elon Musk", "фотосинтез"} {
|
||||
if !hasCyrillic(s) {
|
||||
t.Errorf("hasCyrillic(%q) = false; it is a Russian question", s)
|
||||
}
|
||||
}
|
||||
for _, s := range []string{"what is photosynthesis", "", "3:2"} {
|
||||
if hasCyrillic(s) {
|
||||
t.Errorf("hasCyrillic(%q) = true; there is no Cyrillic in it", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The book choice and the rewrite decision are the same decision: a Russian
|
||||
// book reads his question as he asked it, an English one needs it translated
|
||||
// into keywords first (V-508).
|
||||
func TestKiwixBookChoice(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
wiring kiwixWiring
|
||||
utterance string
|
||||
wantBook string
|
||||
wantVerb bool
|
||||
}{
|
||||
{"a russian question reads the russian book verbatim",
|
||||
kiwixWiring{book: "en", bookRU: "ru"}, "что такое фотосинтез", "ru", true},
|
||||
{"an english question reads the english book",
|
||||
kiwixWiring{book: "en", bookRU: "ru"}, "what is photosynthesis", "en", false},
|
||||
{"no russian book configured leaves every question on the english one",
|
||||
kiwixWiring{book: "en"}, "что такое фотосинтез", "en", false},
|
||||
} {
|
||||
book, verbatim := tc.wiring.book, false
|
||||
if tc.wiring.bookRU != "" && hasCyrillic(tc.utterance) {
|
||||
book, verbatim = tc.wiring.bookRU, true
|
||||
}
|
||||
if book != tc.wantBook || verbatim != tc.wantVerb {
|
||||
t.Errorf("%s: book=%q verbatim=%v, want %q/%v", tc.name, book, verbatim, tc.wantBook, tc.wantVerb)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,62 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/kiwix"
|
||||
"github.com/kami/maven/internal/llm"
|
||||
)
|
||||
|
||||
// kiwixWiring — the offline encyclopedia, assembled. nil ⇒ off, which is the
|
||||
// default: the query chain simply has no ZIM source.
|
||||
//
|
||||
// The rewriter is separately optional. Searching without one is legal and
|
||||
// mostly useless against English ZIMs, but it is the honest degraded mode when
|
||||
// there is no llama-server to rewrite with, and it is what `rewrite: false`
|
||||
// asks for.
|
||||
type kiwixWiring struct {
|
||||
client *kiwix.Client
|
||||
rewriter *kiwix.Rewriter // nil ⇒ the question is searched verbatim
|
||||
book string
|
||||
// bookRU — searched instead of book when the question is Cyrillic, and
|
||||
// searched verbatim because it is in his language already (V-508). Empty ⇒
|
||||
// every question goes to book.
|
||||
bookRU string
|
||||
max int
|
||||
runes int
|
||||
}
|
||||
|
||||
// wireKiwix builds the ZIM reader from the `kiwix` block, or returns nil when
|
||||
// there is none. config.Normalise has already dropped a block with no URL and
|
||||
// filled the two size defaults, so this does no validation of its own.
|
||||
//
|
||||
// The llm client is the phraser's swap-aware one (llmClientFor), so a model
|
||||
// swap re-points the rewriter with everything else. A nil client means there is
|
||||
// no resident model at all; that degrades the rewriter, not the source.
|
||||
func wireKiwix(cfg *config.Config, c *llm.Client) *kiwixWiring {
|
||||
if cfg.Kiwix == nil {
|
||||
return nil
|
||||
}
|
||||
kc := cfg.Kiwix
|
||||
w := &kiwixWiring{
|
||||
client: kiwix.New(kc.URL),
|
||||
book: kc.Book,
|
||||
bookRU: kc.BookRU,
|
||||
max: kc.MaxResults,
|
||||
runes: kc.SnippetRunes,
|
||||
}
|
||||
if kc.BookRU != "" {
|
||||
log.Printf("voice: kiwix: russian questions read %q verbatim", kc.BookRU)
|
||||
}
|
||||
switch {
|
||||
case !kc.RewriteEnabled():
|
||||
log.Printf("voice: kiwix at %s (book %q, query rewriting off by config)", kc.URL, kc.Book)
|
||||
case c == nil:
|
||||
log.Printf("voice: kiwix at %s (book %q, no llama-server: searching questions verbatim)", kc.URL, kc.Book)
|
||||
default:
|
||||
w.rewriter = kiwix.NewRewriter(c)
|
||||
log.Printf("voice: kiwix at %s (book %q)", kc.URL, kc.Book)
|
||||
}
|
||||
return w
|
||||
}
|
||||
@@ -0,0 +1,187 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/kiwix"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
// searchRSS is what kiwix-serve answers a /search with, trimmed to the fields
|
||||
// ParseSearchRSS reads.
|
||||
func searchRSS(items ...string) string {
|
||||
return `<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel>` +
|
||||
strings.Join(items, "") + `</channel></rss>`
|
||||
}
|
||||
|
||||
func rssItem(title, snippet string) string {
|
||||
return "<item><title>" + title + "</title><link>/x</link><description>" + snippet + "</description></item>"
|
||||
}
|
||||
|
||||
// stubKiwixServer answers every search with the given body and records the
|
||||
// pattern it was asked for, so a test can assert on what left the process.
|
||||
type stubKiwixServer struct {
|
||||
*httptest.Server
|
||||
lastPattern string
|
||||
lastBook string
|
||||
}
|
||||
|
||||
func newStubKiwix(t *testing.T, body string, status int) *stubKiwixServer {
|
||||
t.Helper()
|
||||
s := &stubKiwixServer{}
|
||||
s.Server = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if status != 0 && status != http.StatusOK {
|
||||
w.WriteHeader(status)
|
||||
return
|
||||
}
|
||||
// Two endpoints on one server: /search answers the RSS, everything else
|
||||
// is an article read. Only the search is recorded — an article fetch
|
||||
// carries no query string and would blank the assertions.
|
||||
if r.URL.Path != "/search" {
|
||||
w.Header().Set("Content-Type", "text/html")
|
||||
_, _ = w.Write([]byte("<html><title>Article</title><body><p>the lead paragraph</p></body></html>"))
|
||||
return
|
||||
}
|
||||
s.lastPattern = r.URL.Query().Get("pattern")
|
||||
s.lastBook = r.URL.Query().Get("books.name")
|
||||
w.Header().Set("Content-Type", "application/xml")
|
||||
_, _ = w.Write([]byte(body))
|
||||
}))
|
||||
t.Cleanup(s.Close)
|
||||
return s
|
||||
}
|
||||
|
||||
// buildKiwixHandler wires the source with no rewriter: the question is searched
|
||||
// verbatim, which keeps the assertion about what was sent unambiguous.
|
||||
func buildKiwixHandler(base string) *reactiveHandler {
|
||||
return &reactiveHandler{
|
||||
replier: voice.NewStubReplier(),
|
||||
phraser: phraser.NewStub(),
|
||||
kiwix: &kiwixWiring{
|
||||
client: kiwix.New(base),
|
||||
book: "wikipedia_en_all_maxi",
|
||||
max: config.DefaultKiwixResults,
|
||||
runes: config.DefaultKiwixSnippetRunes,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
func askKiwix(h *reactiveHandler, q string) (string, bool) {
|
||||
return h.queryKiwix(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: q},
|
||||
})
|
||||
}
|
||||
|
||||
// The default daemon has no `kiwix` block, and a source that is off must not
|
||||
// claim the turn — the model answers next, exactly as it did before.
|
||||
func TestQueryKiwixOffPassesThrough(t *testing.T) {
|
||||
h := &reactiveHandler{replier: voice.NewStubReplier(), phraser: phraser.NewStub()}
|
||||
if reply, ok := askKiwix(h, "почему небо синее?"); ok {
|
||||
t.Errorf("an unconfigured kiwix claimed the turn: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
func TestQueryKiwixAnswersFromSnippets(t *testing.T) {
|
||||
s := newStubKiwix(t, searchRSS(rssItem("Rayleigh scattering", "shorter wavelengths scatter more")), 0)
|
||||
h := buildKiwixHandler(s.URL)
|
||||
|
||||
reply, ok := askKiwix(h, "почему небо синее?")
|
||||
if !ok {
|
||||
t.Fatal("kiwix found a hit and did not claim the turn")
|
||||
}
|
||||
if reply == "" {
|
||||
t.Error("claimed the turn with an empty reply")
|
||||
}
|
||||
if s.lastBook != "wikipedia_en_all_maxi" {
|
||||
t.Errorf("books.name = %q, want the configured book", s.lastBook)
|
||||
}
|
||||
}
|
||||
|
||||
// No hit is not a failure worth announcing: the ZIM does not cover it, and the
|
||||
// model answering next beats "ничего не нашла".
|
||||
func TestQueryKiwixNoHitsPassesThrough(t *testing.T) {
|
||||
s := newStubKiwix(t, searchRSS(), 0)
|
||||
if reply, ok := askKiwix(buildKiwixHandler(s.URL), "почему небо синее?"); ok {
|
||||
t.Errorf("an empty result set claimed the turn: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// A dead or misconfigured server must degrade to the model, not to an error
|
||||
// spoken out loud. A turn never breaks on a capability.
|
||||
func TestQueryKiwixServerErrorPassesThrough(t *testing.T) {
|
||||
s := newStubKiwix(t, "", http.StatusBadRequest)
|
||||
if reply, ok := askKiwix(buildKiwixHandler(s.URL), "почему небо синее?"); ok {
|
||||
t.Errorf("a 400 claimed the turn: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The privacy rule in CLAUDE.md, asserted rather than assumed: only the
|
||||
// utterance is searched. No note, no fact, no persona block travels with it.
|
||||
func TestQueryKiwixSendsOnlyTheQuestion(t *testing.T) {
|
||||
s := newStubKiwix(t, searchRSS(rssItem("X", "y")), 0)
|
||||
h := buildKiwixHandler(s.URL)
|
||||
// A turn carrying notes an earlier source already pulled. They must not
|
||||
// reach the query string.
|
||||
_, _ = h.queryKiwix(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо синее?"},
|
||||
notes: []ipc.Note{{Text: "пароль от роутера hunter2"}},
|
||||
})
|
||||
if strings.Contains(s.lastPattern, "hunter2") {
|
||||
t.Fatalf("a stored note leaked into the search query: %q", s.lastPattern)
|
||||
}
|
||||
if s.lastPattern != "почему небо синее?" {
|
||||
t.Errorf("pattern = %q, want the utterance verbatim", s.lastPattern)
|
||||
}
|
||||
}
|
||||
|
||||
func TestWireKiwixOffWithoutABlock(t *testing.T) {
|
||||
if w := wireKiwix(&config.Config{}, nil); w != nil {
|
||||
t.Error("wireKiwix built a source with no config block")
|
||||
}
|
||||
}
|
||||
|
||||
// No llama-server means no rewriter, but the source still works: searching the
|
||||
// question verbatim is the honest degraded mode, not a reason to stay dark.
|
||||
func TestWireKiwixWithoutAnLLMHasNoRewriter(t *testing.T) {
|
||||
w := wireKiwix(&config.Config{Kiwix: &config.KiwixConfig{
|
||||
URL: "http://kiwix:8080", Book: "b", MaxResults: 5, SnippetRunes: 1500,
|
||||
}}, nil)
|
||||
if w == nil {
|
||||
t.Fatal("wireKiwix returned nil for a configured block")
|
||||
}
|
||||
if w.rewriter != nil {
|
||||
t.Error("built a rewriter with no llm client")
|
||||
}
|
||||
if w.book != "b" {
|
||||
t.Errorf("book = %q", w.book)
|
||||
}
|
||||
}
|
||||
|
||||
// The whole point of reading the article: kiwix's own snippet is usually the
|
||||
// navigation box at the foot of the page, so the lead paragraph must be what
|
||||
// reaches the phraser.
|
||||
func TestQueryKiwixReadsTheArticleNotTheSnippet(t *testing.T) {
|
||||
junk := "Ecological economics Ecological footprint Ecological forecasting"
|
||||
s := newStubKiwix(t, searchRSS(rssItem("Photosynthesis", junk)), 0)
|
||||
h := buildKiwixHandler(s.URL)
|
||||
h.phraser = nil // no phraser ⇒ the fallback reads back what it was given
|
||||
|
||||
reply, ok := askKiwix(h, "что такое фотосинтез?")
|
||||
if !ok {
|
||||
t.Fatal("did not claim the turn")
|
||||
}
|
||||
if !strings.Contains(reply, "the lead paragraph") {
|
||||
t.Errorf("reply did not come from the article: %q", reply)
|
||||
}
|
||||
if strings.Contains(reply, "Ecological economics") {
|
||||
t.Errorf("recited the navigation-box snippet: %q", reply)
|
||||
}
|
||||
}
|
||||
+69
-3
@@ -127,8 +127,10 @@ func run(args []string) error {
|
||||
cfgPath := flag.String("config", defaultConfigPath(), "path to mavend JSON config")
|
||||
wrappedKeyPath := flag.String("wrapped-key-file", "", "path to wrapped encryption key blob (enables cold-start unlock)")
|
||||
reembed := flag.Bool("reembed", false, "re-embed every stored note and fact with the configured embedder, then serve normally (run once after an embedder swap; the daemon does not answer until it finishes)")
|
||||
allowSeed := flag.Bool("allow-seed", false, "enable the backdated seed_event write path (QA only: it lets a caller place a fact in the past and mint a routine the tick loop will then act on; off means the method has nothing to write with)")
|
||||
flag.CommandLine.Parse(args)
|
||||
reembedOnStart = *reembed
|
||||
allowSeedOnStart = *allowSeed
|
||||
cfg, err := config.Load(*cfgPath)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -236,7 +238,7 @@ func run(args []string) error {
|
||||
coreFor := func() ipc.CoreAPI { return newIntakeAPI(ipc.NewStoreAPI(st), evBus, time.Now) }
|
||||
|
||||
if !locked {
|
||||
rules = loop.DefaultRules()
|
||||
rules = wireRules(cfg)
|
||||
gatherer = loop.NewGatherer(st, rules)
|
||||
if cfg.QuietHours != nil {
|
||||
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
|
||||
@@ -251,6 +253,7 @@ func run(args []string) error {
|
||||
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),
|
||||
@@ -337,10 +340,14 @@ func run(args []string) error {
|
||||
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 {
|
||||
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
|
||||
@@ -508,7 +515,7 @@ func run(args []string) error {
|
||||
}
|
||||
|
||||
// Wire everything.
|
||||
rules = loop.DefaultRules()
|
||||
rules = wireRules(cfg)
|
||||
gatherer = loop.NewGatherer(st, rules)
|
||||
if cfg.QuietHours != nil {
|
||||
gatherer.SetQuietHours(cfg.QuietHours.Start, cfg.QuietHours.End)
|
||||
@@ -522,6 +529,7 @@ func run(args []string) error {
|
||||
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),
|
||||
@@ -600,9 +608,11 @@ func run(args []string) error {
|
||||
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)
|
||||
}
|
||||
srv.SetAPI(newAPI)
|
||||
srv.Check = (&auth.Gate{Enrollment: auth.NewFloorEnrollment(), Session: passkeySess}).Check
|
||||
@@ -751,7 +761,15 @@ func run(args []string) error {
|
||||
if voiceW != nil {
|
||||
voiceW.close()
|
||||
}
|
||||
wg.Wait()
|
||||
// Bounded. Every worker below watches ctx, but one parked in a model call
|
||||
// or an HTTP fetch can outlast the supervisor's patience, and run() has to
|
||||
// return for `defer st.Close()` to seal the database. A worker abandoned
|
||||
// mid-tick loses one tick; a shutdown that never returns loses every write
|
||||
// since the last clean stop — which is how the deployed ciphertext went
|
||||
// eleven days stale in July 2026.
|
||||
if !waitWorkers(&wg, workerGrace) {
|
||||
log.Printf("mavend: workers still running after %s, sealing anyway", workerGrace)
|
||||
}
|
||||
log.Printf("mavend: bye")
|
||||
return nil
|
||||
}
|
||||
@@ -776,9 +794,57 @@ func personaFacts(cfg *config.Config) persona.Facts {
|
||||
return f
|
||||
}
|
||||
|
||||
// cacheRAMMiB resolves phraser.cache_ram_mib into the phraser's field. Unset
|
||||
// means 512 MiB and not "whatever the server does", because the server's own
|
||||
// default is 8 GiB of prompt cache and that is what put 7.9 GB of RSS and half
|
||||
// a gigabyte of swap on homesrv for a 1.1 GB model. A negative value is the
|
||||
// deliberate opt-out: no flag is passed, the server's default applies, and the
|
||||
// operator owns the consequence.
|
||||
func cacheRAMMiB(configured int) int {
|
||||
if configured == 0 {
|
||||
return 512
|
||||
}
|
||||
if configured < 0 {
|
||||
return 0
|
||||
}
|
||||
return configured
|
||||
}
|
||||
|
||||
// contextBlockFn returns the per-turn renderer of the shared context block.
|
||||
// Per turn, not once at startup, because the block states the current time.
|
||||
func contextBlockFn(cfg *config.Config, now func() time.Time) func() string {
|
||||
f := personaFacts(cfg)
|
||||
return func() string { return f.Block(now()) }
|
||||
}
|
||||
|
||||
// workerGrace — how long shutdown waits for the background workers before it
|
||||
// goes ahead and seals without them. Comfortably inside docker's ten-second
|
||||
// default so the seal still lands before SIGKILL.
|
||||
const workerGrace = 4 * time.Second
|
||||
|
||||
// waitWorkers waits on wg for at most d. Reports whether they all finished.
|
||||
func waitWorkers(wg *sync.WaitGroup, d time.Duration) bool {
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
wg.Wait()
|
||||
close(done)
|
||||
}()
|
||||
select {
|
||||
case <-done:
|
||||
return true
|
||||
case <-time.After(d):
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
// should find the answer in the boot log.
|
||||
func wireRules(cfg *config.Config) []loop.Rule {
|
||||
rules, dropped := loop.RulesExcept(cfg.DisabledRules)
|
||||
for _, name := range dropped {
|
||||
log.Printf("loop: rule %q disabled by config", name)
|
||||
}
|
||||
return rules
|
||||
}
|
||||
|
||||
@@ -29,11 +29,11 @@ import (
|
||||
// minutes of evaluation was five minutes of a mute assistant.
|
||||
//
|
||||
// The background client now yields the slot while a turn is in flight, so the
|
||||
// collision is handled where it belongs and this is a prompt budget again.
|
||||
// Sixty seconds is long enough for a Thinking model here, and an evaluation cut
|
||||
// off costs nothing, because it is retried at the next interval. Raise it if
|
||||
// observations start truncating.
|
||||
const memoryEvalTimeout = 60 * time.Second
|
||||
// collision is solved where it belongs and this is a prompt budget again. Five
|
||||
// minutes is safe once more, and it is back: 60s truncated a Thinking model
|
||||
// mid-synthesis, which costs an observation for no latency saved. The gate, not
|
||||
// this number, is what keeps a voice turn from waiting.
|
||||
const memoryEvalTimeout = 5 * time.Minute
|
||||
|
||||
// memoryEvalWorker — ticker + evaluator.
|
||||
type memoryEvalWorker struct {
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/llm"
|
||||
)
|
||||
|
||||
// No `workstation` block is the shipping deploy. The seam must then be the
|
||||
// resident client itself, with nothing probing anything.
|
||||
func TestModelSeamUnconfiguredIsResidentOnly(t *testing.T) {
|
||||
resident := llm.New("http://127.0.0.1:1", time.Second)
|
||||
hot, pair := modelSeam(&config.Config{}, resident)
|
||||
if pair != nil {
|
||||
t.Error("built a pair with no workstation configured")
|
||||
}
|
||||
if hot == nil {
|
||||
t.Fatal("no seam at all, so the cascade would route with the classifier")
|
||||
}
|
||||
}
|
||||
|
||||
// A workstation with no resident model behind it has no floor, and a Pair with
|
||||
// no floor is a configuration mistake rather than a degraded mode.
|
||||
func TestModelSeamWithoutResidentIsNil(t *testing.T) {
|
||||
cfg := &config.Config{Workstation: &config.WorkstationConfig{URL: "http://127.0.0.1:1"}}
|
||||
cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
|
||||
hot, pair := modelSeam(cfg, nil)
|
||||
if hot != nil || pair != nil {
|
||||
t.Errorf("built a seam with no floor: hot=%v pair=%v", hot, pair)
|
||||
}
|
||||
}
|
||||
|
||||
// The configured case: the seam is the pair, and the pair notices a workstation
|
||||
// that answers /health.
|
||||
func TestModelSeamPrefersAnAnsweringWorkstation(t *testing.T) {
|
||||
up := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
}))
|
||||
defer up.Close()
|
||||
|
||||
cfg := &config.Config{Workstation: &config.WorkstationConfig{
|
||||
URL: up.URL,
|
||||
Probe: config.Duration(10 * time.Millisecond),
|
||||
}}
|
||||
cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
|
||||
|
||||
hot, pair := modelSeam(cfg, llm.New("http://127.0.0.1:1", time.Second))
|
||||
if pair == nil || hot == nil {
|
||||
t.Fatal("no pair built for a configured workstation")
|
||||
}
|
||||
defer pair.Stop()
|
||||
|
||||
deadline := time.Now().Add(2 * time.Second)
|
||||
for !pair.Available() && time.Now().Before(deadline) {
|
||||
time.Sleep(5 * time.Millisecond)
|
||||
}
|
||||
if !pair.Available() {
|
||||
t.Fatal("the pair never saw a workstation that answers /health")
|
||||
}
|
||||
}
|
||||
|
||||
// A card held by a CPT run answers 503, and that must read as unavailable
|
||||
// rather than as an error a turn has to handle.
|
||||
func TestModelSeamHeldCardIsUnavailable(t *testing.T) {
|
||||
busy := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
http.Error(w, "model not loaded", http.StatusServiceUnavailable)
|
||||
}))
|
||||
defer busy.Close()
|
||||
|
||||
cfg := &config.Config{Workstation: &config.WorkstationConfig{
|
||||
URL: busy.URL,
|
||||
Probe: config.Duration(10 * time.Millisecond),
|
||||
}}
|
||||
cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
|
||||
|
||||
_, pair := modelSeam(cfg, llm.New("http://127.0.0.1:1", time.Second))
|
||||
if pair == nil {
|
||||
t.Fatal("no pair built for a configured workstation")
|
||||
}
|
||||
defer pair.Stop()
|
||||
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
if pair.Available() {
|
||||
t.Error("a 503 from the supervisor read as available")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,39 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/morning"
|
||||
)
|
||||
|
||||
// TestMorningNudgeBodySeparatesOptional — the one message a routine is allowed
|
||||
// per day says what was not done, then what he could still do (Vikunja #473).
|
||||
func TestMorningNudgeBodySeparatesOptional(t *testing.T) {
|
||||
cand := morning.Candidate{
|
||||
Routine: morning.Routine{Name: "утро"},
|
||||
Missing: []morning.Item{
|
||||
{Key: "meds", Label: "таблетки"},
|
||||
{Key: "stretch", Label: "растяжка", Optional: true},
|
||||
},
|
||||
}
|
||||
body := morningNudgeBody(cand)
|
||||
if !strings.Contains(body, "не сделано — таблетки") {
|
||||
t.Fatalf("the required item must be named as not done: %q", body)
|
||||
}
|
||||
if !strings.Contains(body, "если будет время — растяжка") {
|
||||
t.Fatalf("the optional item must read softer: %q", body)
|
||||
}
|
||||
if strings.Contains(body, "не сделано — таблетки, растяжка") {
|
||||
t.Fatalf("optional must not be folded into the required list: %q", body)
|
||||
}
|
||||
|
||||
// Nothing optional missing: the sentence is what it always was.
|
||||
only := morning.Candidate{
|
||||
Routine: morning.Routine{Name: "утро"},
|
||||
Missing: []morning.Item{{Key: "meds", Label: "таблетки"}},
|
||||
}
|
||||
if got, want := morningNudgeBody(only), "утро: не сделано — таблетки"; got != want {
|
||||
t.Fatalf("morningNudgeBody = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
+5
-20
@@ -11,6 +11,7 @@ import (
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/netscan"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// scanBudget — the whole spoken scan, end to end. A voice turn that takes
|
||||
@@ -106,7 +107,7 @@ func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
|
||||
res, err := w.scan(ctx)
|
||||
if err != nil {
|
||||
log.Printf("netscan: scan: %v", err)
|
||||
return "не получилось просканировать сеть.", true
|
||||
return phraser.Q(phraser.QueryFailNetscan, nil), true
|
||||
}
|
||||
// A truncated run is not a statement about the LAN. Saying "нашла 6
|
||||
// устройств" after stopping two thirds of the way through the range is a
|
||||
@@ -116,9 +117,9 @@ func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
|
||||
tail = ", но успела посмотреть не всю сеть"
|
||||
}
|
||||
if len(res.Hosts) == 0 {
|
||||
return "в сети никого не нашла" + tail + ".", true
|
||||
return phraser.Q(phraser.QueryNetEmpty, map[string]string{"tail": tail}), true
|
||||
}
|
||||
out := fmt.Sprintf("нашла %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
|
||||
out := fmt.Sprintf("нашла %d %s", len(res.Hosts), phraser.Devices(len(res.Hosts)))
|
||||
if shape := scanShape(res.Hosts); shape != "" {
|
||||
out += ", " + shape
|
||||
}
|
||||
@@ -179,7 +180,7 @@ func (w *netWiring) writeScanRecord(ctx context.Context, res netscan.Result) {
|
||||
if w.api == nil {
|
||||
return
|
||||
}
|
||||
head := fmt.Sprintf("сканирование сети: %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
|
||||
head := fmt.Sprintf("сканирование сети: %d %s", len(res.Hosts), phraser.Devices(len(res.Hosts)))
|
||||
if res.Truncated {
|
||||
head += " (не вся сеть)"
|
||||
}
|
||||
@@ -210,22 +211,6 @@ func (w *netWiring) writeScanRecord(ctx context.Context, res netscan.Result) {
|
||||
}
|
||||
}
|
||||
|
||||
// hostWord — Russian counts inflect the noun: 1 устройство, 2-4 устройства,
|
||||
// 5+ устройств, and the teens are all the last form.
|
||||
func hostWord(n int) string {
|
||||
if n%100 >= 11 && n%100 <= 14 {
|
||||
return "устройств"
|
||||
}
|
||||
switch n % 10 {
|
||||
case 1:
|
||||
return "устройство"
|
||||
case 2, 3, 4:
|
||||
return "устройства"
|
||||
default:
|
||||
return "устройств"
|
||||
}
|
||||
}
|
||||
|
||||
// isNetworkQuery recognises a question about the LAN, narrowly. It needs a
|
||||
// network word AND an ask: "интернет не работает" is a complaint, not a request
|
||||
// to scan, and a scan she runs unasked is exactly the noisy behaviour the
|
||||
|
||||
+21
-12
@@ -10,6 +10,8 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestWireNetScanOffUnlessEnabled(t *testing.T) {
|
||||
@@ -74,18 +76,6 @@ func TestScanSummaryOnAnEmptyRange(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestHostWordAgreesWithTheCount(t *testing.T) {
|
||||
for n, want := range map[int]string{
|
||||
1: "устройство", 2: "устройства", 4: "устройства", 5: "устройств",
|
||||
11: "устройств", 12: "устройств", 21: "устройство", 22: "устройства",
|
||||
25: "устройств", 111: "устройств", 101: "устройство", 0: "устройств",
|
||||
} {
|
||||
if got := hostWord(n); got != want {
|
||||
t.Errorf("hostWord(%d) = %q, want %q", n, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestIsNetworkQuery(t *testing.T) {
|
||||
yes := []string{
|
||||
"какие устройства в сети?",
|
||||
@@ -169,3 +159,22 @@ func TestScanSummarySpeaksACountAndWritesTheAddresses(t *testing.T) {
|
||||
t.Errorf("a repeat question rescanned and rewrote the record (%d notes)", api.n)
|
||||
}
|
||||
}
|
||||
|
||||
// An unconfigured scanner names the gap instead of declining the turn.
|
||||
//
|
||||
// Falling through sent "какие устройства в сети?" to the search leg, which
|
||||
// answered with a paragraph about routers in general — and put a question about
|
||||
// his own LAN on an upstream engine, which the personal boundary exists to
|
||||
// prevent (Vikunja #479).
|
||||
func TestQueryNetworkNamesTheGapWhenNotConfigured(t *testing.T) {
|
||||
h := &reactiveHandler{}
|
||||
reply, ok := h.queryNetwork(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Utterance: "какие устройства в сети?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("an unconfigured scanner let the question fall through to search")
|
||||
}
|
||||
if !phraser.IsQ(phraser.QueryNetOff, nil, reply) {
|
||||
t.Errorf("got %q, want the gap named", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,145 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"strings"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// Ordinal selection over a list she just read (Vikunja #448).
|
||||
//
|
||||
// The dialogue session already carried the intent, the slots and the history.
|
||||
// What it did not carry was the list: she recited five tasks, he said "второй",
|
||||
// and there was nothing for that word to point at, so it routed as a fresh
|
||||
// utterance and meant nothing.
|
||||
//
|
||||
// Candidates are bound when she speaks the list, in the order she spoke it (see
|
||||
// tasks.Spoken). Binding afterwards would resolve "второй" against a fresh
|
||||
// query, and the list can change between two turns.
|
||||
//
|
||||
// An ordinal with no verb is read back, not acted on: "второй" names a task, it
|
||||
// does not say what to do with it. Acting on the bare word would guess, and a
|
||||
// wrong guess here closes work he never finished.
|
||||
|
||||
// candidateOrdinals — the words that pick a position, by index. Prefix match,
|
||||
// because Russian declines them: "первый", "первую", "первое".
|
||||
var candidateOrdinals = []struct {
|
||||
word string
|
||||
nth int
|
||||
}{
|
||||
{"перв", 1}, {"втор", 2}, {"трет", 3}, {"четв", 4}, {"пят", 5},
|
||||
{"first", 1}, {"second", 2}, {"third", 3},
|
||||
}
|
||||
|
||||
// candidateDigits — "второй" said as a number. Matched whole, never by prefix:
|
||||
// "15" starts with "1" and is a time, not a position.
|
||||
var candidateDigits = map[string]int{"1": 1, "2": 2, "3": 3, "4": 4, "5": 5}
|
||||
|
||||
// candidateLast — "последний" picks the end of the list whatever its length.
|
||||
var candidateLast = []string{"последн", "last"}
|
||||
|
||||
// parseOrdinal reads which position he named. 0 and false when he named none.
|
||||
// A negative result means the last one.
|
||||
func parseOrdinal(text string) (int, bool) {
|
||||
// Token by token, not substring: " 1" would otherwise match inside
|
||||
// "напомни в 15:00" and turn a reminder into a selection.
|
||||
for _, tok := range strings.FieldsFunc(strings.ToLower(text), func(r rune) bool {
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
}) {
|
||||
for _, w := range candidateLast {
|
||||
if strings.HasPrefix(tok, w) {
|
||||
return -1, true
|
||||
}
|
||||
}
|
||||
if n, ok := candidateDigits[tok]; ok {
|
||||
return n, true
|
||||
}
|
||||
for _, o := range candidateOrdinals {
|
||||
// Prefix, because Russian declines them: "первый", "первую".
|
||||
if strings.HasPrefix(tok, o.word) {
|
||||
return o.nth, true
|
||||
}
|
||||
}
|
||||
}
|
||||
return 0, false
|
||||
}
|
||||
|
||||
// candidateVerbs — what he wants done with the one he picked. Nothing here is
|
||||
// destructive: a task moves forward or is dropped, and both are recorded with a
|
||||
// provenance the /tasks page shows.
|
||||
var candidateVerbs = []struct {
|
||||
words []string
|
||||
status string
|
||||
say string
|
||||
}{
|
||||
{[]string{"готов", "сделал", "выполнил", "закрыл", "done"}, store.TaskDone, "закрыла"},
|
||||
{[]string{"не надо", "убери", "отмени", "не буду", "drop"}, store.TaskDropped, "убрала"},
|
||||
{[]string{"подтвержда", "беру", "да,", "буду делать"}, store.TaskOpen, "взяла в работу"},
|
||||
}
|
||||
|
||||
func parseCandidateVerb(text string) (status, say string, ok bool) {
|
||||
s := strings.ToLower(strings.TrimSpace(text))
|
||||
for _, v := range candidateVerbs {
|
||||
for _, w := range v.words {
|
||||
if strings.Contains(s, w) {
|
||||
return v.status, v.say, true
|
||||
}
|
||||
}
|
||||
}
|
||||
return "", "", false
|
||||
}
|
||||
|
||||
// offerCandidates records the list she just read, so his next words can pick
|
||||
// from it. Best effort: no session store, or a session that expired between the
|
||||
// question and the answer, means the words route normally.
|
||||
func (h *reactiveHandler) offerCandidates(ctx context.Context, cands []dialogue.Candidate) {
|
||||
if h.dialogueSessions == nil || len(cands) == 0 {
|
||||
return
|
||||
}
|
||||
h.dialogueSessions.SetCandidates(dialogueIDOf(ctx), h.now(), cands)
|
||||
}
|
||||
|
||||
// resolveCandidate handles "второй", "первую сделал", "последнюю убери" against
|
||||
// the list she just read.
|
||||
func (h *reactiveHandler) resolveCandidate(ctx context.Context, text string, src turnSource) (string, bool) {
|
||||
if h.dialogueSessions == nil {
|
||||
return "", false
|
||||
}
|
||||
sess := h.dialogueSessions.Get(dialogueIDOf(ctx), h.now())
|
||||
if sess == nil || len(sess.Candidates) == 0 {
|
||||
return "", false
|
||||
}
|
||||
nth, ok := parseOrdinal(text)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
if nth < 0 {
|
||||
nth = len(sess.Candidates)
|
||||
}
|
||||
if nth > len(sess.Candidates) {
|
||||
// Claim the turn: he is picking from her list and named a position she
|
||||
// did not read. Routing it fresh would answer something else entirely.
|
||||
return fmt.Sprintf("я назвала только %d.", len(sess.Candidates)), true
|
||||
}
|
||||
pick := sess.Candidates[nth-1]
|
||||
status, say, hasVerb := parseCandidateVerb(text)
|
||||
if !hasVerb || pick.Kind != "task" {
|
||||
// Read it back and keep the list: naming one is often the first half of
|
||||
// a sentence, and the second half is the next turn.
|
||||
return pick.Label, true
|
||||
}
|
||||
if err := h.api.SetTaskStatus(ctx, pick.Ref, status, h.now(), string(src)); err != nil {
|
||||
log.Printf("voice: candidate %d → %s: %v", pick.Ref, status, err)
|
||||
return "не получилось изменить задачу.", true
|
||||
}
|
||||
// Spent: the list she read is no longer the list, and a second ordinal
|
||||
// against it would close the wrong task.
|
||||
h.dialogueSessions.SetCandidates(dialogueIDOf(ctx), h.now(), nil)
|
||||
log.Printf("voice: candidate %d (%q) → %s", pick.Ref, pick.Label, status)
|
||||
return say + ": " + pick.Label, true
|
||||
}
|
||||
@@ -0,0 +1,130 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func TestParseOrdinalReadsThePosition(t *testing.T) {
|
||||
cases := []struct {
|
||||
text string
|
||||
want int
|
||||
ok bool
|
||||
}{
|
||||
{"второй", 2, true},
|
||||
{"вторую сделал", 2, true},
|
||||
{"первую убери", 1, true},
|
||||
{"последнюю не надо", -1, true},
|
||||
{"3", 3, true},
|
||||
{"the second one", 2, true},
|
||||
// No position named.
|
||||
{"какие у меня задачи", 0, false},
|
||||
{"", 0, false},
|
||||
// A digit inside a time is not a position.
|
||||
{"напомни в 15:00", 0, false},
|
||||
}
|
||||
for _, c := range cases {
|
||||
got, ok := parseOrdinal(c.text)
|
||||
if ok != c.ok || (ok && got != c.want) {
|
||||
t.Errorf("parseOrdinal(%q) = %d,%v; want %d,%v", c.text, got, ok, c.want, c.ok)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalPassesWithNothingOffered(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
if _, handled := h.resolveCandidate(context.Background(), "второй", sourceVoice); handled {
|
||||
t.Error("an ordinal with no list behind it was claimed")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalReadsBackWithoutAVerb(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
ids := seedTasks(t, st, "купить хлеб", "позвонить маме")
|
||||
putCandidates(h, context.Background(), ids, "купить хлеб", "позвонить маме")
|
||||
|
||||
reply, handled := h.resolveCandidate(ctx, "второй", sourceVoice)
|
||||
if !handled || !strings.Contains(reply, "позвонить маме") {
|
||||
t.Fatalf("a bare ordinal did not read the task back: %q handled=%v", reply, handled)
|
||||
}
|
||||
// Still live: naming one is often the first half of a sentence.
|
||||
if _, handled := h.resolveCandidate(ctx, "первый", sourceVoice); !handled {
|
||||
t.Error("the list was spent by a read-back")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalWithAVerbMovesTheTask(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
ids := seedTasks(t, st, "купить хлеб", "позвонить маме")
|
||||
putCandidates(h, context.Background(), ids, "купить хлеб", "позвонить маме")
|
||||
|
||||
reply, handled := h.resolveCandidate(ctx, "первую сделал", sourceVoice)
|
||||
if !handled || !strings.Contains(reply, "купить хлеб") {
|
||||
t.Fatalf("the pick was not acted on: %q handled=%v", reply, handled)
|
||||
}
|
||||
live, err := st.ListTasks(ctx, "live")
|
||||
if err != nil {
|
||||
t.Fatalf("list tasks: %v", err)
|
||||
}
|
||||
for _, task := range live {
|
||||
if task.ID == ids[0] {
|
||||
t.Fatalf("task %d is still live after he closed it", task.ID)
|
||||
}
|
||||
}
|
||||
// Spent: a second ordinal against a list that no longer holds would close
|
||||
// the wrong task.
|
||||
if _, handled := h.resolveCandidate(ctx, "второй", sourceVoice); handled {
|
||||
t.Error("the list survived the pick it was spent on")
|
||||
}
|
||||
}
|
||||
|
||||
func TestOrdinalPastTheEndSaysHowMany(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ids := seedTasks(t, st, "купить хлеб")
|
||||
putCandidates(h, context.Background(), ids, "купить хлеб")
|
||||
|
||||
reply, handled := h.resolveCandidate(context.Background(), "третий", sourceVoice)
|
||||
if !handled || !strings.Contains(reply, "1") {
|
||||
t.Fatalf("a position she never read was not answered: %q handled=%v", reply, handled)
|
||||
}
|
||||
}
|
||||
|
||||
// ordinalNow — a fixed capture time; the ranker only needs the rows to exist.
|
||||
var ordinalNow = time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC)
|
||||
|
||||
func seedTasks(t *testing.T, st *store.Store, texts ...string) []int64 {
|
||||
t.Helper()
|
||||
ctx := context.Background()
|
||||
var ids []int64
|
||||
for _, text := range texts {
|
||||
res, err := st.CaptureTask(ctx, store.Task{
|
||||
Text: text,
|
||||
Source: "tap:voice",
|
||||
Status: store.TaskOpen,
|
||||
CreatedTs: ordinalNow,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("capture task: %v", err)
|
||||
}
|
||||
ids = append(ids, res.ID)
|
||||
}
|
||||
return ids
|
||||
}
|
||||
|
||||
// putCandidates binds a list to the reach the ctx names, the way queryTasks
|
||||
// does when she recites one.
|
||||
func putCandidates(h *reactiveHandler, ctx context.Context, ids []int64, labels ...string) {
|
||||
cands := make([]dialogue.Candidate, 0, len(ids))
|
||||
for i, id := range ids {
|
||||
cands = append(cands, dialogue.Candidate{Kind: "task", Ref: id, Label: labels[i]})
|
||||
}
|
||||
h.dialogueSessions.Put(dialogueIDOf(ctx), &dialogue.Session{Timestamp: h.now()})
|
||||
h.offerCandidates(ctx, cands)
|
||||
}
|
||||
@@ -9,6 +9,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/pattern"
|
||||
"github.com/kami/maven/internal/store"
|
||||
@@ -283,3 +284,81 @@ func TestTickProposalCooldownSpacesAnnouncements(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestVoiceYesDoesNotAcceptRoutine — Vikunja #367. Accepting a routine hands
|
||||
// the tick loop a standing new reason to speak, which DESIGN.md puts at layer
|
||||
// 3, and voice is structurally incapable of layer 3. A spoken "да" must park
|
||||
// the decision for the authed page, not flip the row itself.
|
||||
func TestVoiceYesDoesNotAcceptRoutine(t *testing.T) {
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
seedRefillEvents(t, st, ctx, now, pattern.MinEvents-1)
|
||||
|
||||
h := &reactiveHandler{api: ipc.NewStoreAPI(st), dataStore: st, now: func() time.Time { return now }}
|
||||
|
||||
// The MinEvents'th event is the one that makes the pattern detectable, and
|
||||
// it goes through the voice path so the proposal is parked for a y/n.
|
||||
last := now.Add(time.Duration(pattern.MinEvents-1) * 7 * 24 * time.Hour)
|
||||
factID, err := st.WriteFact(ctx, last, store.KindSelf, "cat_water", "refill", "voice", 1.0, sql.NullInt64{})
|
||||
if err != nil {
|
||||
t.Fatalf("write fact: %v", err)
|
||||
}
|
||||
if phrase := h.detectPattern(ctx, factID, "cat_water", "refill", last); phrase == "" {
|
||||
t.Fatal("expected a parked routine proposal")
|
||||
}
|
||||
|
||||
reply, handled := h.resolveConfirm(ctx, "да")
|
||||
if !handled {
|
||||
t.Fatal("the spoken yes should be consumed by the routine confirm")
|
||||
}
|
||||
if !strings.Contains(reply, "рутин") {
|
||||
t.Fatalf("reply should send him to the routines page, got %q", reply)
|
||||
}
|
||||
|
||||
rows, err := st.ListProposedRoutinesByStatus(ctx, store.RoutineAccepted)
|
||||
if err != nil {
|
||||
t.Fatalf("list accepted: %v", err)
|
||||
}
|
||||
if len(rows) != 0 {
|
||||
t.Fatalf("voice accepted a routine: %+v", rows)
|
||||
}
|
||||
proposed, err := st.ListProposedRoutinesByStatus(ctx, store.RoutineProposed)
|
||||
if err != nil {
|
||||
t.Fatalf("list proposed: %v", err)
|
||||
}
|
||||
if len(proposed) != 1 {
|
||||
t.Fatalf("proposed routines = %d, want 1 (still waiting for the page)", len(proposed))
|
||||
}
|
||||
}
|
||||
|
||||
// TestVoiceNoStillDismissesRoutine — declining does not move the boundary
|
||||
// outward, so voice keeps it. Only acceptance is gated.
|
||||
func TestVoiceNoStillDismissesRoutine(t *testing.T) {
|
||||
st := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
now := refNow()
|
||||
seedRefillEvents(t, st, ctx, now, pattern.MinEvents-1)
|
||||
|
||||
h := &reactiveHandler{api: ipc.NewStoreAPI(st), dataStore: st, now: func() time.Time { return now }}
|
||||
|
||||
last := now.Add(time.Duration(pattern.MinEvents-1) * 7 * 24 * time.Hour)
|
||||
factID, err := st.WriteFact(ctx, last, store.KindSelf, "cat_water", "refill", "voice", 1.0, sql.NullInt64{})
|
||||
if err != nil {
|
||||
t.Fatalf("write fact: %v", err)
|
||||
}
|
||||
if phrase := h.detectPattern(ctx, factID, "cat_water", "refill", last); phrase == "" {
|
||||
t.Fatal("expected a parked routine proposal")
|
||||
}
|
||||
|
||||
if _, handled := h.resolveConfirm(ctx, "нет"); !handled {
|
||||
t.Fatal("the spoken no should be consumed by the routine confirm")
|
||||
}
|
||||
rows, err := st.ListProposedRoutinesByStatus(ctx, store.RoutineDismissed)
|
||||
if err != nil {
|
||||
t.Fatalf("list dismissed: %v", err)
|
||||
}
|
||||
if len(rows) != 1 {
|
||||
t.Fatalf("dismissed routines = %d, want 1", len(rows))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,134 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"regexp"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/phraser/eval"
|
||||
)
|
||||
|
||||
// The persona checks, run before she speaks (Vikunja #399).
|
||||
//
|
||||
// RunChecks and RunTalkChecks only ever ran from the eval package, so
|
||||
// everything the fixtures measured was offline knowledge: we could say "about
|
||||
// one reply in three is broken" and still ship every one of them. This runs the
|
||||
// cheap half of that on the live path, and replaces a failing message with the
|
||||
// deterministic floor.
|
||||
//
|
||||
// Which checks: the unambiguous string tests only — feminine self-reference,
|
||||
// how she addresses him, and a leaked-reasoning test. Not length, which is
|
||||
// path-specific, and not ontopic, which compares against fragments the fixture
|
||||
// supplies and runtime does not have. Not hisgender either — see guardSpoken.
|
||||
//
|
||||
// No retry. A retry doubles the latency on the exact turn that is already going
|
||||
// badly, and on the nudge path the moment has passed.
|
||||
//
|
||||
// The known cost, written down because it is real: a wrongly flagged good reply
|
||||
// is replaced by a flatter stub one. That is the right trade — a stub sentence
|
||||
// is dull, a leaked reasoning trace is broken — but it means these checks can
|
||||
// no longer be tuned for sensitivity alone.
|
||||
|
||||
// checkLeak — the name reported when the model's scaffolding reaches the text.
|
||||
const checkLeak = "leak"
|
||||
|
||||
// leakPatterns — reasoning and protocol that belongs to the model, not to him.
|
||||
// The resident model is a Thinking variant, so an unclosed reasoning block is
|
||||
// the failure mode, not a hypothetical (Vikunja #398).
|
||||
var leakPatterns = []*regexp.Regexp{
|
||||
regexp.MustCompile(`(?i)<\s*/?\s*think`),
|
||||
regexp.MustCompile(`(?i)thinking\s*(process|:)`),
|
||||
regexp.MustCompile(`(?i)^\s*(assistant|user|system)\s*:`),
|
||||
// Raw contract JSON: the parser already unwraps a good one, so a body that
|
||||
// still carries the keys is one it could not read.
|
||||
regexp.MustCompile(`"(response|mood|body|summary)"\s*:`),
|
||||
// The persona block quoted back at him.
|
||||
regexp.MustCompile(`(?i)(ты\s+—?\s*мэйвен|системный промпт|system prompt)`),
|
||||
}
|
||||
|
||||
// checkPersonaLeak reports whether the model's own scaffolding is in the text.
|
||||
func checkPersonaLeak(body string) (string, bool) {
|
||||
for _, re := range leakPatterns {
|
||||
if m := re.FindString(body); m != "" {
|
||||
return "leaked " + strings.TrimSpace(m), false
|
||||
}
|
||||
}
|
||||
return "", true
|
||||
}
|
||||
|
||||
// personaRejects counts what the guard caught, by check name, so the real
|
||||
// production rate is knowable rather than inferred from the fixture.
|
||||
var personaRejects = struct {
|
||||
mu sync.Mutex
|
||||
by map[string]int
|
||||
}{by: map[string]int{}}
|
||||
|
||||
func personaRejectCounts() map[string]int {
|
||||
personaRejects.mu.Lock()
|
||||
defer personaRejects.mu.Unlock()
|
||||
out := make(map[string]int, len(personaRejects.by))
|
||||
for k, v := range personaRejects.by {
|
||||
out[k] = v
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// guardSpoken checks a phrased message. It returns the failed check and false
|
||||
// when the message must not be said; path names the caller, for the log.
|
||||
//
|
||||
// An empty message passes: the caller already treats that as a failure and
|
||||
// falls back on its own, and reporting it as a persona breach would put a
|
||||
// misleading line in the count.
|
||||
func guardSpoken(path, body string) (string, bool) {
|
||||
if strings.TrimSpace(body) == "" {
|
||||
return "", true
|
||||
}
|
||||
if detail, ok := checkPersonaLeak(body); !ok {
|
||||
return rejectSpoken(path, checkLeak, detail, body), false
|
||||
}
|
||||
// Feminine and address only. HisGender is not run here: it reads a
|
||||
// sentence-initial feminine verb with no pronoun — "записала, что ты выпил
|
||||
// воды" — as a woman being addressed, when it is her own correct
|
||||
// self-reference. Offline that is a point of score; on this path it would
|
||||
// replace a good reply with a stub one on every fact she confirms.
|
||||
for _, r := range []eval.Result{eval.Feminine(body), eval.Address(body)} {
|
||||
if !r.Pass {
|
||||
return rejectSpoken(path, r.Name, r.Detail, body), false
|
||||
}
|
||||
}
|
||||
return "", true
|
||||
}
|
||||
|
||||
// rejectSpoken logs what she nearly said and counts it. The whole text, not a
|
||||
// prefix: the point of the log line is that the failure can be read back later
|
||||
// and argued with.
|
||||
func rejectSpoken(path, check, detail, body string) string {
|
||||
personaRejects.mu.Lock()
|
||||
personaRejects.by[check]++
|
||||
personaRejects.mu.Unlock()
|
||||
log.Printf("persona: %s rejected on %s (%s): %q", path, check, detail, body)
|
||||
return check
|
||||
}
|
||||
|
||||
// guardNudge checks a phrased nudge and falls back to the deterministic floor
|
||||
// when it fails. The nudge path, unlike the reply path, cannot ask again: the
|
||||
// tick has already decided she speaks, so the choice is the floor's wording or
|
||||
// a broken sentence.
|
||||
func guardNudge(pn delivery.PhrasedNudge, cand loop.Candidate) delivery.PhrasedNudge {
|
||||
if _, ok := guardSpoken("nudge", pn.Body); ok {
|
||||
return pn
|
||||
}
|
||||
stub, err := phraser.NewStub().PhraseNudge(context.Background(), cand)
|
||||
if err != nil {
|
||||
// The Stub is templates over the candidate and does not fail. If it
|
||||
// somehow does, the model's text is still what the rule decided to
|
||||
// say, and saying nothing is the worse outcome.
|
||||
return pn
|
||||
}
|
||||
return stub
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
)
|
||||
|
||||
func TestGuardPassesWhatSheShouldSay(t *testing.T) {
|
||||
good := []string{
|
||||
"записала: купить хлеб.",
|
||||
"поняла, напомню в 11:00.",
|
||||
"ты не пил воду с утра.",
|
||||
"я рада, что получилось.",
|
||||
"",
|
||||
}
|
||||
for _, body := range good {
|
||||
if check, ok := guardSpoken("test", body); !ok {
|
||||
t.Errorf("guardSpoken(%q) rejected on %s", body, check)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestGuardStopsWhatSheShouldNot(t *testing.T) {
|
||||
bad := []struct {
|
||||
body string
|
||||
want string
|
||||
}{
|
||||
{"<think>он просил воду</think> попей воды.", checkLeak},
|
||||
{"Thinking Process: он давно не пил.", checkLeak},
|
||||
{`{"response": "попей воды", "mood": "neutral"}`, checkLeak},
|
||||
{"я напомнил тебе про воду.", "feminine"},
|
||||
{"вы давно не пили воду.", "address"},
|
||||
}
|
||||
for _, c := range bad {
|
||||
check, ok := guardSpoken("test", c.body)
|
||||
if ok {
|
||||
t.Errorf("guardSpoken(%q) let it through", c.body)
|
||||
continue
|
||||
}
|
||||
if check != c.want {
|
||||
t.Errorf("guardSpoken(%q) failed on %s; want %s", c.body, check, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestGuardCountsWhatItCaught(t *testing.T) {
|
||||
before := personaRejectCounts()[checkLeak]
|
||||
if _, ok := guardSpoken("test", "<think>…"); ok {
|
||||
t.Fatal("a leaked reasoning block was let through")
|
||||
}
|
||||
if after := personaRejectCounts()[checkLeak]; after != before+1 {
|
||||
t.Errorf("leak count %d; want %d", after, before+1)
|
||||
}
|
||||
}
|
||||
|
||||
// TestGuardNudgeFallsBackToTheFloor — a broken nudge is replaced by the
|
||||
// deterministic wording, not dropped and not retried.
|
||||
func TestGuardNudgeFallsBackToTheFloor(t *testing.T) {
|
||||
cand := loop.Candidate{Rule: loop.Rule{Name: "water"}}
|
||||
bad := delivery.PhrasedNudge{Candidate: cand, Body: "Thinking Process: он не пил.", Mood: "neutral"}
|
||||
got := guardNudge(bad, cand)
|
||||
if got.Body == bad.Body {
|
||||
t.Fatal("the broken nudge was delivered unchanged")
|
||||
}
|
||||
if strings.TrimSpace(got.Body) == "" {
|
||||
t.Fatal("the nudge was dropped rather than re-worded")
|
||||
}
|
||||
good := delivery.PhrasedNudge{Candidate: cand, Body: "попей воды.", Mood: "neutral"}
|
||||
if guardNudge(good, cand).Body != good.Body {
|
||||
t.Error("a good nudge was replaced")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,154 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"math"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The personal boundary decides one thing: is this question about him. It used
|
||||
// to decide it by matching possession words, and that was the whole defect
|
||||
// behind Vikunja #495. "что я говорил про бэкапы?" is his data by definition —
|
||||
// nothing outside the box has ever heard him say anything — and it carried no
|
||||
// possession word, so it walked past the boundary into SearXNG and came back
|
||||
// answered out of a Habr article about somebody else's backups.
|
||||
//
|
||||
// The first fix was one more marker class, `я говорил|сказал|писал|…`, plus a
|
||||
// carve-out so "как я говорил, почему небо синее" stayed a world question. Both
|
||||
// halves are a lexicon, and a lexicon is the wrong instrument here: Russian
|
||||
// gives every verb a dozen surface forms, the preamble list has no end, and
|
||||
// every utterance the list misses is one that reaches the world. It also drifts
|
||||
// silently — a missing verb looks exactly like no bug.
|
||||
//
|
||||
// So the boundary asks the embedder instead. Two frozen seed sets — questions
|
||||
// about him, questions about the world — are embedded once, and the turn's own
|
||||
// query vector, already computed by queryEmbed upstream, is scored against
|
||||
// both. Nearest side wins. Word order, verb form and unseen phrasing stop
|
||||
// mattering, which is exactly what a lexicon could not do.
|
||||
//
|
||||
// Measured 03-08-2026 against multilingual-e5-small on 19 held-out utterances,
|
||||
// none of them a seed: 19 right (TestONNXPersonalBoundary). A 20th, "as i said,
|
||||
// what is the population of india", missed by +0.008 during the first pass and
|
||||
// is a world seed now, which is why it is not in the held-out set. True
|
||||
// positives clear the world side by +0.014 to +0.089 and the nearest true
|
||||
// negative sits at -0.005, so the gate is the sign of the difference and
|
||||
// nothing tighter: the margins are too thin to justify a threshold, and the
|
||||
// asymmetry favours claiming anyway. A false claim costs one honest "не знаю";
|
||||
// a false pass sends his life to an upstream engine.
|
||||
//
|
||||
// The embedder is the one model CLAUDE.md pins to homesrv permanently, and it
|
||||
// is what makes this affordable: no llama-server call, no network, one cosine
|
||||
// per seed against a vector the turn already has.
|
||||
|
||||
// personalSeeds — questions about him. Frozen: they are scoring data, so
|
||||
// editing one moves the boundary and must be re-measured, not eyeballed. Cover
|
||||
// both classes the boundary owns, possession and first-person speech, in both
|
||||
// languages.
|
||||
var personalSeeds = []string{
|
||||
"что я говорил про это",
|
||||
"я тебе рассказывал об этом?",
|
||||
"что я записал про врача",
|
||||
"я упоминал эту тему?",
|
||||
"что у меня сегодня",
|
||||
"когда моя встреча",
|
||||
"what did i say about this",
|
||||
"did i mention this to you",
|
||||
}
|
||||
|
||||
// worldSeeds — questions the world can answer, including the two shapes that
|
||||
// look personal and are not: a first-person preamble on a world question ("как
|
||||
// я говорил, ..."), and first person without possession ("что я могу
|
||||
// посмотреть вечером"). Refusing those is the opposite mistake and the older
|
||||
// comment on personalMarkers already named it.
|
||||
var worldSeeds = []string{
|
||||
"почему небо синее",
|
||||
"какая столица франции",
|
||||
"как сварить борщ",
|
||||
"кто написал эту книгу",
|
||||
"what is the capital of france",
|
||||
"how do i boil an egg",
|
||||
"как я говорил, почему небо синее",
|
||||
"as i said, why is the sky blue",
|
||||
"as i said, what is the population of india",
|
||||
"что я могу посмотреть вечером",
|
||||
"что мне почитать про историю",
|
||||
"что я должен знать про питон",
|
||||
"what can i watch tonight",
|
||||
}
|
||||
|
||||
// personalBoundary holds the embedded seeds. Zero value is usable and means
|
||||
// "not loaded yet"; a handler built without an embedder never loads and the
|
||||
// boundary falls back to personalMarkers.
|
||||
type personalBoundary struct {
|
||||
once sync.Once
|
||||
personal [][]float32
|
||||
world [][]float32
|
||||
loaded bool
|
||||
}
|
||||
|
||||
// load embeds both seed sets, once per process. Seeds are embedded on the QUERY
|
||||
// side, like the utterance they are compared with — a question against a
|
||||
// question. Mixing sides would measure the e5 prefix, not the meaning.
|
||||
func (b *personalBoundary) load(ctx context.Context, emb router.Embedder) {
|
||||
b.once.Do(func() {
|
||||
if emb == nil {
|
||||
return
|
||||
}
|
||||
embedAll := func(ss []string) [][]float32 {
|
||||
out := make([][]float32, 0, len(ss))
|
||||
for _, s := range ss {
|
||||
v, err := router.EmbedQuery(ctx, emb, s)
|
||||
if err != nil {
|
||||
log.Printf("voice: personal boundary seeds unavailable (%v); falling back to possession markers", err)
|
||||
return nil
|
||||
}
|
||||
out = append(out, v)
|
||||
}
|
||||
return out
|
||||
}
|
||||
p, w := embedAll(personalSeeds), embedAll(worldSeeds)
|
||||
if p == nil || w == nil {
|
||||
return
|
||||
}
|
||||
b.personal, b.world, b.loaded = p, w, true
|
||||
})
|
||||
}
|
||||
|
||||
// score returns the best similarity to each side. ok is false when the seeds
|
||||
// are not loaded, which is the caller's signal to use the markers instead.
|
||||
func (b *personalBoundary) score(vec []float32) (personal, world float64, ok bool) {
|
||||
if !b.loaded || len(vec) == 0 {
|
||||
return 0, 0, false
|
||||
}
|
||||
best := func(seeds [][]float32) float64 {
|
||||
m := -1.0
|
||||
for _, s := range seeds {
|
||||
if c := cosine(vec, s); c > m {
|
||||
m = c
|
||||
}
|
||||
}
|
||||
return m
|
||||
}
|
||||
return best(b.personal), best(b.world), true
|
||||
}
|
||||
|
||||
// cosine — same math as internal/router and internal/memory, small enough that
|
||||
// importing one of them for it would be the larger coupling.
|
||||
func cosine(a, b []float32) float64 {
|
||||
if len(a) != len(b) {
|
||||
return 0
|
||||
}
|
||||
var dot, na, nb float64
|
||||
for i := range a {
|
||||
dot += float64(a[i]) * float64(b[i])
|
||||
na += float64(a[i]) * float64(a[i])
|
||||
nb += float64(b[i]) * float64(b[i])
|
||||
}
|
||||
if na == 0 || nb == 0 {
|
||||
return 0
|
||||
}
|
||||
return dot / (math.Sqrt(na) * math.Sqrt(nb))
|
||||
}
|
||||
@@ -0,0 +1,94 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// A handler with no embedder never loads the seeds, so the boundary falls back
|
||||
// to the possession markers. That is the offline floor and it must keep working
|
||||
// — an embedder that fails to load must not open the boundary.
|
||||
func TestBoundaryFallsBackToMarkersWithNoEmbedder(t *testing.T) {
|
||||
h := personalHandler()
|
||||
if !h.isPersonalTurn(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Utterance: "во сколько у меня встреча"},
|
||||
}) {
|
||||
t.Error("no embedder: a possession question must still be personal")
|
||||
}
|
||||
if h.isPersonalTurn(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Utterance: "почему небо синее"},
|
||||
}) {
|
||||
t.Error("no embedder: a world question must still pass")
|
||||
}
|
||||
}
|
||||
|
||||
// TestONNXPersonalBoundary — the number that matters, scored against the
|
||||
// embedder homesrv actually runs. Opt-in via MAVEN_ONNX_LIB, exactly like
|
||||
// TestONNXRecall in internal/memory/recalleval.
|
||||
//
|
||||
// Every case here is held out: none of these strings is a seed. The #495
|
||||
// regression is the first row — "что я говорил про бэкапы?" reached SearXNG and
|
||||
// was answered from a Habr article, and no possession word appears in it.
|
||||
func TestONNXPersonalBoundary(t *testing.T) {
|
||||
lib := os.Getenv("MAVEN_ONNX_LIB")
|
||||
if lib == "" {
|
||||
t.Skip("MAVEN_ONNX_LIB unset — see AGENTS.md § Embedder model for intent routing")
|
||||
}
|
||||
dir := filepath.Join("../..", "models/embedder/multilingual-e5-small")
|
||||
emb, err := router.NewONNXEmbedder(filepath.Join(dir, "model_quantized.onnx"), filepath.Join(dir, "tokenizer.json"), lib)
|
||||
if err != nil {
|
||||
t.Skipf("onnx embedder unavailable: %v", err)
|
||||
}
|
||||
defer emb.Close()
|
||||
|
||||
cases := []struct {
|
||||
utterance string
|
||||
personal bool
|
||||
}{
|
||||
{"что я говорил про бэкапы?", true},
|
||||
{"что я сказал вчера про отпуск", true},
|
||||
{"я писал что-нибудь про сервер", true},
|
||||
{"я упоминал про конференцию?", true},
|
||||
{"что я отмечал по поводу переезда", true},
|
||||
{"я рассказывал тебе про новую работу?", true},
|
||||
{"во сколько у меня встреча", true},
|
||||
{"когда мой следующий отпуск", true},
|
||||
{"what did i say about backups", true},
|
||||
{"did i tell you about the doctor", true},
|
||||
{"как я говорил, почему небо синее", false},
|
||||
{"как уже я говорил, какая столица франции", false},
|
||||
{"почему трава зелёная", false},
|
||||
{"столица франции", false},
|
||||
{"как мне сварить борщ", false},
|
||||
{"что мне посмотреть вечером", false},
|
||||
{"я хочу узнать про рим", false},
|
||||
{"кто такой гагарин", false},
|
||||
{"how do i boil an egg", false},
|
||||
}
|
||||
|
||||
h := &reactiveHandler{recall: recallWiring{embedder: emb}}
|
||||
ctx := context.Background()
|
||||
wrong := 0
|
||||
for _, c := range cases {
|
||||
vec, err := router.EmbedQuery(ctx, emb, c.utterance)
|
||||
if err != nil {
|
||||
t.Fatalf("embed %q: %v", c.utterance, err)
|
||||
}
|
||||
turn := &queryTurn{dec: router.Decision{Utterance: c.utterance}, vec: vec}
|
||||
got := h.isPersonalTurn(ctx, turn)
|
||||
p, w, ok := h.recall.boundary.score(vec)
|
||||
if !ok {
|
||||
t.Fatal("seeds did not load with a working embedder")
|
||||
}
|
||||
if got != c.personal {
|
||||
wrong++
|
||||
t.Errorf("%q: personal=%v want %v (personal %.4f world %.4f)", c.utterance, got, c.personal, p, w)
|
||||
}
|
||||
t.Logf("personal=%-5v personal %.4f world %.4f delta %+.4f %s", got, p, w, p-w, c.utterance)
|
||||
}
|
||||
t.Logf("personal boundary: %d/%d held-out utterances correct", len(cases)-wrong, len(cases))
|
||||
}
|
||||
@@ -0,0 +1,160 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// "отметь второй пункт" names a position, and only the daemon knows which item
|
||||
// that is. The router fills the value slot with "2"; this is where it becomes an
|
||||
// item id (Vikunja #516).
|
||||
func TestPositionResolvesAgainstTheLastSpokenList(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[
|
||||
{"id":"item_a","title":"диск заканчивается"},
|
||||
{"id":"item_b","title":"бэкап не прошёл"},
|
||||
{"id":"item_c","title":"сертификат истекает"}
|
||||
]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
if reply := h.handlePraxisAct(context.Background(), praxisActDec("list_attention")); reply == "" {
|
||||
t.Fatal("attention returned nothing")
|
||||
}
|
||||
|
||||
cases := []struct{ ref, wantItem string }{
|
||||
{"2", "item_b"},
|
||||
{"1", "item_a"},
|
||||
{"last", "item_c"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
praxis.ResetRequests()
|
||||
reply := h.handlePraxisAct(context.Background(), praxisItemDec("acknowledge_item", c.ref))
|
||||
if !strings.Contains(reply, "принято") {
|
||||
t.Errorf("ref %q: reply %q", c.ref, reply)
|
||||
}
|
||||
if !requestedPathContaining(praxis, c.wantItem) {
|
||||
t.Errorf("ref %q did not acknowledge %s; paths %v", c.ref, c.wantItem, paths(praxis))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A position past the end must not acknowledge the wrong item. It asks.
|
||||
func TestPositionPastTheEndAsksInsteadOfGuessing(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[{"id":"item_a","title":"диск заканчивается"}]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
|
||||
praxis.ResetRequests()
|
||||
reply := h.handlePraxisAct(context.Background(), praxisItemDec("resolve_item", "4"))
|
||||
if !strings.Contains(reply, "какой пункт") {
|
||||
t.Errorf("a position with no item should ask, got %q", reply)
|
||||
}
|
||||
if requestedPathContaining(praxis, "item_a") {
|
||||
t.Error("the only surfaced item was resolved for a position that did not name it")
|
||||
}
|
||||
}
|
||||
|
||||
// No digest yet means no positions. Nothing is mutated.
|
||||
func TestPositionWithNoSpokenListAsks(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
reply := h.handlePraxisAct(context.Background(), praxisItemDec("acknowledge_item", "1"))
|
||||
if !strings.Contains(reply, "какой пункт") {
|
||||
t.Errorf("want the ask, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// An explicit id is not a position and passes through untouched.
|
||||
func TestExplicitItemIDIsNotRewritten(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[{"id":"item_a","title":"диск"}]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
|
||||
praxis.ResetRequests()
|
||||
h.handlePraxisAct(context.Background(), praxisItemDec("pin_item", "item_zz"))
|
||||
if !requestedPathContaining(praxis, "item_zz") {
|
||||
t.Errorf("the id he gave was not the one called; paths %v", paths(praxis))
|
||||
}
|
||||
}
|
||||
|
||||
// An item Praxis sent without a title is never spoken, so it holds no position.
|
||||
func TestUnspokenItemsHoldNoPosition(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[
|
||||
{"id":"item_silent"},
|
||||
{"id":"item_said","title":"бэкап не прошёл"}
|
||||
]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
|
||||
praxis.ResetRequests()
|
||||
h.handlePraxisAct(context.Background(), praxisItemDec("acknowledge_item", "1"))
|
||||
if !requestedPathContaining(praxis, "item_said") {
|
||||
t.Errorf("position 1 is the first item she SAID; paths %v", paths(praxis))
|
||||
}
|
||||
}
|
||||
|
||||
// The item id travels in the POST body, so that is what these read.
|
||||
func paths(f *fakeServer) []string {
|
||||
var out []string
|
||||
for _, r := range f.Requests() {
|
||||
out = append(out, r.Path+" "+string(r.Body))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func requestedPathContaining(f *fakeServer, want string) bool {
|
||||
for _, r := range f.Requests() {
|
||||
if strings.Contains(string(r.Body), want) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// "отметь это как сделанное" after a one-item digest points at that item.
|
||||
func TestDemonstrativeResolvesWhenOneItemWasSpoken(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[{"id":"item_only","title":"бэкап не прошёл"}]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
|
||||
praxis.ResetRequests()
|
||||
reply := h.handlePraxisAct(context.Background(), praxisItemDec("acknowledge_item", "this"))
|
||||
if !strings.Contains(reply, "принято") {
|
||||
t.Errorf("reply %q", reply)
|
||||
}
|
||||
if !requestedPathContaining(praxis, "item_only") {
|
||||
t.Errorf("the one surfaced item was not acknowledged; paths %v", paths(praxis))
|
||||
}
|
||||
}
|
||||
|
||||
// Pointing at one of several is a guess, and a wrong guess transitions the wrong
|
||||
// item. The turn goes back to the cascade instead.
|
||||
func TestDemonstrativeWithSeveralItemsGivesTheTurnBack(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[
|
||||
{"id":"item_a","title":"диск"},
|
||||
{"id":"item_b","title":"бэкап"}
|
||||
]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
h.handlePraxisAct(context.Background(), praxisActDec("list_attention"))
|
||||
|
||||
praxis.ResetRequests()
|
||||
if reply := h.handlePraxisAct(context.Background(), praxisItemDec("resolve_item", "this")); reply != "" {
|
||||
t.Errorf("want a fall-through, got %q", reply)
|
||||
}
|
||||
for _, p := range paths(praxis) {
|
||||
if strings.Contains(p, "resolve") {
|
||||
t.Error("an ambiguous demonstrative resolved an item anyway")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// "я это сделал" with no digest behind it is a sentence about his day.
|
||||
func TestDemonstrativeWithNoDigestGivesTheTurnBack(t *testing.T) {
|
||||
praxis := newFakePraxis(t, `[]`)
|
||||
h := newPraxisTestHandler(t, praxis)
|
||||
|
||||
if reply := h.handlePraxisAct(context.Background(), praxisItemDec("resolve_item", "this")); reply != "" {
|
||||
t.Errorf("want a fall-through, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,95 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// The row is the whole mechanism, and nothing wrote it (Vikunja #532).
|
||||
//
|
||||
// The existing hysteresis test in internal/store scores the pure function and
|
||||
// passed throughout, which is exactly why this went unnoticed: Resolve was
|
||||
// always correct and was always handed the cold-start Away. So this test asserts
|
||||
// the round trip — the tick writes what gather resolved, and the next load
|
||||
// reads it back — rather than re-testing the function.
|
||||
func TestTickPersistsTheResolvedBucket(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
st := newTestStore(t)
|
||||
now := time.Now()
|
||||
|
||||
// Cold start: no row, so a load must say Away and the zero time.
|
||||
b, score, updated, err := st.LoadPresenceState(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("load before: %v", err)
|
||||
}
|
||||
if b != store.Away || score != 0 || !updated.IsZero() {
|
||||
t.Fatalf("cold start = %s/%v/%v, want away/0/zero", b, score, updated)
|
||||
}
|
||||
|
||||
tl := &tickLoop{store: st}
|
||||
tl.savePresence(ctx, loop.State{Presence: store.Present, PresenceScore: 0.9}, now)
|
||||
|
||||
b, score, updated, err = st.LoadPresenceState(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("load after: %v", err)
|
||||
}
|
||||
if b != store.Present {
|
||||
t.Errorf("bucket = %s, want present", b)
|
||||
}
|
||||
if score != 0.9 {
|
||||
t.Errorf("score = %v, want 0.9", score)
|
||||
}
|
||||
if updated.IsZero() {
|
||||
t.Error("updated_ts was not written, so /dash still reads (never)")
|
||||
}
|
||||
}
|
||||
|
||||
// The singleton stays a singleton, and a later tick overwrites rather than
|
||||
// accumulating. A row per tick would make LoadPresenceState's single-row query
|
||||
// return whichever one SQLite felt like.
|
||||
func TestPresenceStateIsOverwrittenNotAppended(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
st := newTestStore(t)
|
||||
tl := &tickLoop{store: st}
|
||||
now := time.Now()
|
||||
|
||||
tl.savePresence(ctx, loop.State{Presence: store.Present, PresenceScore: 0.9}, now)
|
||||
tl.savePresence(ctx, loop.State{Presence: store.Away, PresenceScore: 0.1}, now.Add(time.Minute))
|
||||
|
||||
b, score, _, err := st.LoadPresenceState(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("load: %v", err)
|
||||
}
|
||||
if b != store.Away || score != 0.1 {
|
||||
t.Fatalf("got %s/%v, want the second write (away/0.1)", b, score)
|
||||
}
|
||||
}
|
||||
|
||||
// What the persisted row buys: the hold band. A score sitting between Exit and
|
||||
// Enter holds Present when the last bucket was Present, and stays Away when it
|
||||
// was Away. Before the write existed the second arm was the only one that could
|
||||
// ever run, so presence dropped at roughly four minutes of idle instead of
|
||||
// holding to the exit threshold at about nine.
|
||||
func TestPersistedBucketIsWhatFeedsHysteresis(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
st := newTestStore(t)
|
||||
tl := &tickLoop{store: st}
|
||||
|
||||
mid := (store.PresenceExit + store.PresenceEnter) / 2
|
||||
if mid <= store.PresenceExit || mid >= store.PresenceEnter {
|
||||
t.Fatalf("%v is not inside the hold band", mid)
|
||||
}
|
||||
|
||||
tl.savePresence(ctx, loop.State{Presence: store.Present, PresenceScore: 0.9}, time.Now())
|
||||
last, _, _, err := st.LoadPresenceState(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("load: %v", err)
|
||||
}
|
||||
if got := store.Resolve(mid, last); got != store.Present {
|
||||
t.Errorf("Resolve(%v, %s) = %s, want present — the hold band did not apply", mid, last, got)
|
||||
}
|
||||
}
|
||||
@@ -85,15 +85,17 @@ func buildRecallHandler(t *testing.T, question string, mems []recallCase) (*reac
|
||||
|
||||
phr := &recordingPhraser{Stub: phraser.NewStub()}
|
||||
h := &reactiveHandler{
|
||||
api: ipc.NewStoreAPI(st),
|
||||
embedder: emb,
|
||||
api: ipc.NewStoreAPI(st),
|
||||
recall: recallWiring{
|
||||
embedder: emb,
|
||||
memStore: mem,
|
||||
minScore: 0.55,
|
||||
minMargin: 0.008,
|
||||
},
|
||||
replier: voice.NewStubReplier(),
|
||||
phraser: phr,
|
||||
now: func() time.Time { return now },
|
||||
memStore: mem,
|
||||
dataStore: st,
|
||||
queryMinScore: 0.55,
|
||||
queryMinMargin: 0.008,
|
||||
weatherProvider: nil,
|
||||
}
|
||||
return h, phr
|
||||
@@ -121,8 +123,8 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "выучил пару аккордов", score: 0.50, kind: "note"},
|
||||
})
|
||||
reply := askQuery(t, h, q)
|
||||
if want := "вот что я нашла: молоко стоит в холодильнике"; reply != want {
|
||||
t.Errorf("reply %q, want %q", reply, want)
|
||||
if !phraser.IsSourcesFallback(reply, "молоко стоит в холодильнике") {
|
||||
t.Errorf("reply %q, want the note read back", reply)
|
||||
}
|
||||
// One text, the winning memory's — the answer came from the memory
|
||||
// pass, not from handing the phraser every note in the table.
|
||||
@@ -151,7 +153,7 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "молоко стоит в холодильнике", score: 0.860, kind: "note"},
|
||||
{text: "молоко закончилось", score: 0.858, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, q); reply != "не знаю." {
|
||||
if reply := askQuery(t, h, q); !phraser.IsUnknownFallback(reply) {
|
||||
t.Errorf("reply %q, want silence", reply)
|
||||
}
|
||||
})
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"sync"
|
||||
)
|
||||
|
||||
// The query source that claimed a turn was visible in the daemon log and
|
||||
// nowhere else (V-539). A QA step reading /chat could see a wrong answer but
|
||||
// not tell a wrong answer from a wrongly ordered chain: "почему небо голубое"
|
||||
// answered badly reads the same whether search claimed it, the ZIM did, or the
|
||||
// resident model answered from memory.
|
||||
//
|
||||
// It rides the context rather than a return value because 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. The sink is per turn, created by the caller that wants to read it;
|
||||
// a turn with no sink notes nothing, which is what the mic path does.
|
||||
type querySourceKey struct{}
|
||||
|
||||
// querySourceSink holds the name of the source that claimed one turn. The mutex
|
||||
// is there because a query source may fan out to goroutines of its own, not
|
||||
// because two turns share a sink.
|
||||
type querySourceSink struct {
|
||||
mu sync.Mutex
|
||||
name string
|
||||
}
|
||||
|
||||
func (s *querySourceSink) note(name string) {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
s.name = name
|
||||
}
|
||||
|
||||
// Name is the source that claimed, or empty when nothing did or the turn was
|
||||
// not a query at all.
|
||||
func (s *querySourceSink) Name() string {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
return s.name
|
||||
}
|
||||
|
||||
// withQuerySourceSink returns a context that collects the claiming source, and
|
||||
// the sink to read after the turn has answered.
|
||||
func withQuerySourceSink(ctx context.Context) (context.Context, *querySourceSink) {
|
||||
sink := &querySourceSink{}
|
||||
return context.WithValue(ctx, querySourceKey{}, sink), sink
|
||||
}
|
||||
|
||||
// noteQuerySource records which source claimed the turn. It is a no-op when the
|
||||
// caller did not ask for one.
|
||||
func noteQuerySource(ctx context.Context, name string) {
|
||||
if sink, ok := ctx.Value(querySourceKey{}).(*querySourceSink); ok {
|
||||
sink.note(name)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,35 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestQuerySourceSinkCollectsTheClaimingName(t *testing.T) {
|
||||
ctx, sink := withQuerySourceSink(context.Background())
|
||||
if sink.Name() != "" {
|
||||
t.Fatalf("a fresh sink names a source: %q", sink.Name())
|
||||
}
|
||||
noteQuerySource(ctx, "kiwix")
|
||||
if got := sink.Name(); got != "kiwix" {
|
||||
t.Errorf("sink.Name() = %q, want kiwix", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A turn with no sink must not panic. The mic path asks for no source, and a
|
||||
// query source calls noteQuerySource unconditionally.
|
||||
func TestNoteQuerySourceWithoutASinkIsSilent(t *testing.T) {
|
||||
noteQuerySource(context.Background(), "search")
|
||||
}
|
||||
|
||||
// The last source to claim wins, because only one does: actionQuery returns on
|
||||
// the first claim. This pins that the sink overwrites rather than appends, so a
|
||||
// second turn on the same context could not read a stale name.
|
||||
func TestQuerySourceSinkKeepsTheLastNote(t *testing.T) {
|
||||
ctx, sink := withQuerySourceSink(context.Background())
|
||||
noteQuerySource(ctx, "search")
|
||||
noteQuerySource(ctx, "kiwix")
|
||||
if got := sink.Name(); got != "kiwix" {
|
||||
t.Errorf("sink.Name() = %q, want kiwix", got)
|
||||
}
|
||||
}
|
||||
+71
-37
@@ -11,6 +11,8 @@ import (
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// resolveQuietToggle — pre-route keyword check. Returns (reply, true) when
|
||||
@@ -32,10 +34,10 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
return "", false
|
||||
}
|
||||
val := "false"
|
||||
reply := "тихий режим выключен."
|
||||
reply := phraser.Ack(phraser.AckQuietOff, nil)
|
||||
if on {
|
||||
val = "true"
|
||||
reply = "тихий режим включён. буду реже напоминать."
|
||||
reply = phraser.Ack(phraser.AckQuietOn, nil)
|
||||
}
|
||||
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: h.now(),
|
||||
@@ -46,34 +48,44 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
Confidence: 1.0,
|
||||
}); err != nil {
|
||||
log.Printf("voice: write quiet_hours: %v", err)
|
||||
return "не получилось переключить тихий режим.", true
|
||||
return phraser.Ack(phraser.FailQuiet, nil), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
// quietInflections — the inflectional endings a stem may carry and still be
|
||||
// the same word. Adjective/adverb/noun/verb endings, all ≤3 letters. This is
|
||||
// what separates "тихий"/"тихом"/"тихо" (stem "тих" + a real ending) from
|
||||
// "тихонько"/"потихоньку", which are different words: "онько" is not an
|
||||
// ending, and "потихоньку" doesn't start with the stem at all.
|
||||
var quietInflections = []string{
|
||||
"", "а", "е", "и", "й", "о", "у", "ы", "ю", "я",
|
||||
"ая", "ее", "ей", "ем", "ие", "ий", "им", "их", "ия", "ию", "ое", "ой", "ом", "ую", "ые", "ый", "ым", "ых", "ья",
|
||||
"ами", "ого", "ому", "ыми", "ать", "ить", "ять",
|
||||
}
|
||||
|
||||
// quietStem reports whether tok is the given stem carrying at most one
|
||||
// inflectional ending. Word boundaries come from tokenisation (see
|
||||
// quietTokens), not from a regexp — Go's \b is ASCII-oriented and treats every
|
||||
// Cyrillic letter as a non-word character, so `\bтих\b` would happily match
|
||||
// inside "тихонько". Comparing whole tokens sidesteps that entirely.
|
||||
func quietStem(tok, stem string) bool {
|
||||
if !strings.HasPrefix(tok, stem) {
|
||||
return false
|
||||
}
|
||||
suffix := tok[len(stem):]
|
||||
for _, e := range quietInflections {
|
||||
if suffix == e {
|
||||
// quietStem reports whether tok is one of the words a vocabulary slot accepts.
|
||||
// A slot is written as alternatives joined by "|", and an alternative comes in
|
||||
// two flavours:
|
||||
//
|
||||
// - a dictionary form, matched through the dictionary, so every case and
|
||||
// gender of it counts. This is what the nouns and adjectives want: "тихий",
|
||||
// "тихом", "тихо" and "тише" are one word.
|
||||
// - a form prefixed with "=", matched as the exact token. This is what the
|
||||
// VERBS want, and it is not a shortcut. A command is an imperative, and the
|
||||
// dictionary quite correctly files "говори" and "говорил" under one lemma —
|
||||
// so lemma-matching a verb slot read "он говорил тихим голосом весь вечер",
|
||||
// a remark about his evening, as an order to go quiet. Aspect pairs are two
|
||||
// separate verbs, which is why several imperatives are listed by hand.
|
||||
//
|
||||
// Word boundaries come from tokenisation (see quietTokens), not from a regexp —
|
||||
// Go's \b is ASCII-oriented and treats every Cyrillic letter as a non-word
|
||||
// character, so `\bтих\b` would happily match inside "тихонько". Comparing whole
|
||||
// tokens sidesteps that entirely.
|
||||
//
|
||||
// The comparison is a dictionary lookup, not a stem plus a list of 36 endings
|
||||
// (Vikunja #526). The distinction the old comment described is exactly the one a
|
||||
// dictionary makes: "тихий", "тихом", "тихо" and "тише" are one word inflected,
|
||||
// while "тихонько" and "потихоньку" are different words — and the dictionary
|
||||
// knows that without anybody deciding that "онько" is not an ending.
|
||||
func quietStem(tok, slot string) bool {
|
||||
for _, form := range strings.Split(slot, "|") {
|
||||
if exact, ok := strings.CutPrefix(form, "="); ok {
|
||||
if tok == exact {
|
||||
return true
|
||||
}
|
||||
continue
|
||||
}
|
||||
if morph.SameWord(tok, form) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
@@ -116,7 +128,10 @@ func quietPhrase(tokens, pattern []string) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// quietOffPhrases / quietOnPhrases — the toggle vocabulary, as stem sequences.
|
||||
// quietOffPhrases / quietOnPhrases — the toggle vocabulary, as sequences of
|
||||
// dictionary forms. They used to be truncated stems ("тих", "выключ"), which is
|
||||
// what the ending list existed to complete; a dictionary form needs no
|
||||
// completing (Vikunja #526).
|
||||
//
|
||||
// Note what is NOT here any more: the OFF list used to carry {"не", "тих"} and
|
||||
// the ON list {"не", "шум"} / {"не", "беспоко"}. Both were adjacency patterns,
|
||||
@@ -127,25 +142,42 @@ func quietPhrase(tokens, pattern []string) bool {
|
||||
var (
|
||||
quietOffPhrases = [][]string{
|
||||
{"quiet", "off"}, {"quiet", "end"},
|
||||
{"громк", "режим"}, {"шумн", "режим"},
|
||||
{"отмен", "тих"}, {"выключ", "тих"},
|
||||
{"громкий", "режим"}, {"шумный", "режим"},
|
||||
{"=отмени|=отменяй|=отменить", "тихий"},
|
||||
{"=выключи|=выключай|=выключить", "тихий"},
|
||||
}
|
||||
quietOnPhrases = [][]string{
|
||||
{"quiet", "on"}, {"quiet", "mode"},
|
||||
{"тих", "режим"}, {"не", "шум"}, {"не", "беспоко"},
|
||||
{"тих"},
|
||||
{"тихий", "режим"}, {"не", "=шуми|=шумите"}, {"не", "=беспокой|=беспокоить"},
|
||||
// The noun form and the comparative. "режим тишины" is how the
|
||||
// setting is named half the time, and "сделай потише" is how it is
|
||||
// actually asked for out loud. Both used to fall through to the
|
||||
// router, which has no quiet intent, so the command did nothing.
|
||||
{"режим", "тишина"}, {"=сделай", "тихий"}, {"=сделай", "потише"},
|
||||
{"=говори", "тихий"}, {"=будь", "потише"},
|
||||
{"тихий"}, {"потише"},
|
||||
}
|
||||
)
|
||||
|
||||
// quietWordStems — every word that names the setting. Used by the
|
||||
// negated-but-unmatched fallback in classifyQuietToggle, which has to
|
||||
// recognise "хватит тишины" without an ON phrase having matched.
|
||||
var quietWordStems = []string{"тихий", "тишина", "потише"}
|
||||
|
||||
// quietNegatorWords — negators that are whole words with no useful stem.
|
||||
var quietNegatorWords = map[string]bool{
|
||||
"не": true, "нет": true, "хватит": true, "no": true, "not": true, "off": true,
|
||||
}
|
||||
|
||||
// quietNegatorStems — negators that inflect. Matched through quietStem, the
|
||||
// same one-ending rule the toggle vocabulary uses, so "выключи", "выключить"
|
||||
// and "выключай" all count and "выключатель" does not.
|
||||
var quietNegatorStems = []string{"выключ", "отмен", "прекрат", "убер", "stop", "cancel", "disable"}
|
||||
// quietNegatorStems — negators that inflect. Imperatives, matched exactly for
|
||||
// the reason quietStem gives: "выключи" is a command and "выключил" is a report
|
||||
// about earlier, and one lemma covers both. "выключатель" was never a negator
|
||||
// and is not one now.
|
||||
var quietNegatorStems = []string{
|
||||
"=выключи|=выключай|=выключить", "=отмени|=отменяй|=отменить",
|
||||
"=прекрати|=прекращай|=прекратить", "=убери|=убирай|=убрать",
|
||||
"stop", "cancel", "disable",
|
||||
}
|
||||
|
||||
// quietNegated reports whether the utterance carries a negator. Two ON phrases
|
||||
// are themselves built on "не" — "не шуми", "не беспокой" — and those are
|
||||
@@ -197,8 +229,10 @@ func classifyQuietToggle(text string) (on, off bool) {
|
||||
// on after he asked for it to stop.
|
||||
if quietNegated(tokens, nil) {
|
||||
for _, t := range tokens {
|
||||
if quietStem(t, "тих") {
|
||||
return false, true
|
||||
for _, stem := range quietWordStems {
|
||||
if quietStem(t, stem) {
|
||||
return false, true
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -47,6 +47,15 @@ func TestResolveQuietToggle(t *testing.T) {
|
||||
{"побудь в тихом режиме", quietOn},
|
||||
{"Тихий Режим!", quietOn},
|
||||
{"тихая", quietOn},
|
||||
// The noun form and the comparative.
|
||||
{"включи режим тишины", quietOn},
|
||||
{"режим тишины", quietOn},
|
||||
{"сделай потише", quietOn},
|
||||
{"сделай тише", quietOn},
|
||||
{"потише", quietOn},
|
||||
// English, as the fixture phrases it.
|
||||
{"turn quiet mode back on", quietOn},
|
||||
{"enable quiet mode", quietOn},
|
||||
|
||||
// OFF vocabulary — all seven, incl. the three that used to say ON.
|
||||
{"quiet off", quietOff},
|
||||
@@ -60,6 +69,12 @@ func TestResolveQuietToggle(t *testing.T) {
|
||||
{"выключи тихий режим", quietOff},
|
||||
{"отмени тихий режим пожалуйста", quietOff},
|
||||
{"верни громкий режим", quietOff},
|
||||
{"выключи режим тишины", quietOff},
|
||||
{"хватит тишины", quietOff},
|
||||
{"turn off quiet mode", quietOff},
|
||||
{"quiet mode off", quietOff},
|
||||
{"stop quiet mode", quietOff},
|
||||
{"disable quiet mode", quietOff},
|
||||
|
||||
// False positives: "тихо"/"тихий" as ordinary Russian.
|
||||
{"очень тихий сегодня день", quietNone},
|
||||
@@ -68,6 +83,8 @@ func TestResolveQuietToggle(t *testing.T) {
|
||||
{"потихоньку", quietNone},
|
||||
{"тихонько", quietNone},
|
||||
{"он говорил тихим голосом весь вечер", quietNone},
|
||||
{"в тишине лучше думается", quietNone},
|
||||
{"на улице стало потише", quietNone},
|
||||
|
||||
// Unrelated.
|
||||
{"напомни завтра позвонить маме", quietNone},
|
||||
|
||||
@@ -2,12 +2,14 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"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"
|
||||
)
|
||||
@@ -24,11 +26,10 @@ func TestReactiveNotesReminders(t *testing.T) {
|
||||
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
embedder: emb,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: rtr,
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
memStore: memory.NewInMemoryStore(),
|
||||
dataStore: st,
|
||||
}
|
||||
|
||||
@@ -43,9 +44,12 @@ func TestReactiveNotesReminders(t *testing.T) {
|
||||
HasTime: true,
|
||||
},
|
||||
}
|
||||
// The confirmation is phrased from the row now (Vikunja #507), so it
|
||||
// names the stored hour rather than leaving the replier to read one
|
||||
// out of the sentence.
|
||||
reply := h.applyAction(ctx, dec)
|
||||
if reply != "" {
|
||||
t.Errorf("expected empty reply from applyAction, got %q", reply)
|
||||
if want := "хорошо, напомню завтра в " + fireAt.Format("15:04") + "."; reply != want {
|
||||
t.Errorf("reply = %q, want %q", reply, want)
|
||||
}
|
||||
reminders, err := st.ListReminders(ctx, 10)
|
||||
if err != nil {
|
||||
@@ -85,3 +89,37 @@ func TestReactiveNotesReminders(t *testing.T) {
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// TestSpokenTaskCaptureFilesATask — the whole path, from the utterance to the
|
||||
// task table. It went dead when the router started claiming the marker as an
|
||||
// act: capture rides the note intent, so nothing below actionNote was ever
|
||||
// reached and every capture answered "Что сделать?" (Vikunja #467).
|
||||
func TestSpokenTaskCaptureFilesATask(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
st := newTestStore(t)
|
||||
api := ipc.NewStoreAPI(st)
|
||||
now := time.Now()
|
||||
emb := router.NewHashEmbedder(1024)
|
||||
matcher := tool.NewMatcher(api)
|
||||
h := &reactiveHandler{
|
||||
api: api,
|
||||
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
|
||||
router: buildRouter(emb, matcher, 0.55, nil),
|
||||
replier: voice.NewStubReplier(),
|
||||
now: func() time.Time { return now },
|
||||
dataStore: st,
|
||||
}
|
||||
|
||||
reply := h.handleText(ctx, "web", "добавь в задачи купить молоко")
|
||||
if !strings.Contains(reply, "купить молоко") {
|
||||
t.Fatalf("capture did not claim the turn: %q", reply)
|
||||
}
|
||||
open, err := st.ListTasks(ctx, store.TaskOpen)
|
||||
if err != nil || len(open) != 1 {
|
||||
t.Fatalf("task was not filed: tasks=%v err=%v", open, err)
|
||||
}
|
||||
// The words he said, not the model's rewrite of them.
|
||||
if open[0].Text != "купить молоко" {
|
||||
t.Fatalf("task text was rewritten: %q", open[0].Text)
|
||||
}
|
||||
}
|
||||
|
||||
+41
-1
@@ -1,6 +1,9 @@
|
||||
package main
|
||||
|
||||
import "github.com/kami/maven/internal/memory"
|
||||
import (
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// bestRecall is the read side of the long-term memory store: the top hit when
|
||||
// it clears the confidence gate. The index holds BOTH notes and facts, and
|
||||
@@ -23,3 +26,40 @@ func bestRecall(results []memory.Result, minScore, minMargin float64) (memory.Re
|
||||
}
|
||||
return results[0], true
|
||||
}
|
||||
|
||||
// recallWiring — the recall subsystem's dependencies, held as one group on
|
||||
// reactiveHandler (Vikunja #433). It is the worked example for the wiring
|
||||
// decision in docs/handler-wiring.md: cohesive groups of fields, not thirty
|
||||
// loose ones, so a handler names what it needs and the package can be split
|
||||
// later without exporting the whole struct.
|
||||
//
|
||||
// The zero value is usable and means "no recall": no embedder, no vector
|
||||
// store, and a gate that is never consulted because nothing is ever searched.
|
||||
type recallWiring struct {
|
||||
// embedder — reused for note write/query (same model as the classifier).
|
||||
embedder router.Embedder
|
||||
|
||||
// memStore — the vector index over notes and facts.
|
||||
memStore memory.Store
|
||||
|
||||
// topics — the embedded seed sets behind the weather, house and LAN
|
||||
// recognisers (topics.go). Same lifecycle as boundary below: zero value is
|
||||
// usable, loads on first query, and with no embedder it never loads and
|
||||
// each source falls back to its own keyword test.
|
||||
topics topicIndex
|
||||
|
||||
// boundary — the embedded seed sets behind the personal boundary
|
||||
// (personalboundary.go). Zero value is usable and loads on first query;
|
||||
// with no embedder it never loads and the boundary uses personalMarkers.
|
||||
boundary personalBoundary
|
||||
|
||||
// minScore — the note-recall confidence gate. Top cosine below this ⇒
|
||||
// "I don't know" instead of a guess. Tuned for the ONNX embedder; a knob,
|
||||
// not load-bearing math (same posture as the presence thresholds). Set by
|
||||
// wireVoice from VoiceConfig; default 0.55.
|
||||
minScore float64
|
||||
|
||||
// minMargin — the second half of that gate: how far the top hit must beat
|
||||
// the runner-up. 0 ⇒ margin off.
|
||||
minMargin float64
|
||||
}
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// A reminder confirmation is the one sentence that must match a database row.
|
||||
// It used to be phrased by the replier from Slots.Text, which meant it named
|
||||
// whatever hour the sentence contained — including an hour the parser had
|
||||
// rejected or read differently (Vikunja #507).
|
||||
|
||||
func TestReminderConfirmNamesTheStoredHour(t *testing.T) {
|
||||
now := time.Date(2026, 8, 5, 9, 0, 0, 0, time.UTC)
|
||||
got := reminderConfirm(now.Add(10*time.Hour), now) // 19:00 today
|
||||
if !strings.Contains(got, "19:00") {
|
||||
t.Fatalf("confirmation = %q, want the stored 19:00 in it", got)
|
||||
}
|
||||
if !strings.Contains(got, "сегодня") {
|
||||
t.Fatalf("confirmation = %q, want it to say сегодня", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReminderConfirmUsesADateBeyondTheDayWords(t *testing.T) {
|
||||
// dayPrefix answers "это" past послезавтра, and "напомню это в 09:00" is
|
||||
// not a sentence. A date is.
|
||||
now := time.Date(2026, 8, 5, 9, 0, 0, 0, time.UTC)
|
||||
got := reminderConfirm(now.Add(10*24*time.Hour), now)
|
||||
if strings.Contains(got, "это") {
|
||||
t.Fatalf("confirmation = %q, want a date rather than the fallback day word", got)
|
||||
}
|
||||
if !strings.Contains(got, "15 августа") {
|
||||
t.Fatalf("confirmation = %q, want the date in it", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReminderConfirmIsFeminineAndInformal(t *testing.T) {
|
||||
// The persona checks the phrasing eval enforces apply here too, and this
|
||||
// sentence never passes through a phraser.
|
||||
now := time.Date(2026, 8, 5, 9, 0, 0, 0, time.UTC)
|
||||
got := reminderConfirm(now.Add(time.Hour), now)
|
||||
for _, bad := range []string{"вы", "ваш", "напомнил ", "рад "} {
|
||||
if strings.Contains(strings.ToLower(got), bad) {
|
||||
t.Fatalf("confirmation = %q contains %q", got, bad)
|
||||
}
|
||||
}
|
||||
if !strings.HasPrefix(got, "хорошо, напомню") {
|
||||
t.Fatalf("confirmation = %q, want it to open with the promise", got)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"regexp"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
)
|
||||
|
||||
// reminderMarker — the words that open a reminder. Stripped because they are
|
||||
// the instruction, not the thing to say at the hour.
|
||||
//
|
||||
// The verbs come from the lexicon (Vikunja #530). They are a closed set of the
|
||||
// commands she answers to, exactly like capture_verbs, and the literal that
|
||||
// stood here knew four of them.
|
||||
var reminderMarker = regexp.MustCompile(`(?i)^\s*(?:` + alternation(lexicon.ReminderVerbs()) +
|
||||
`)\s*(?:мне|me)?[\s,:—-]*`)
|
||||
|
||||
// reminderTimeWords — the time expressions a reminder carries, removed from
|
||||
// the body because the fire time is already a column. Ordered longest-first
|
||||
// where two could match the same words, so "через полтора часа" does not leave
|
||||
// "полтора" behind.
|
||||
//
|
||||
// Go's \b is ASCII-only and never fires next to a Cyrillic letter, so the word
|
||||
// boundaries here are written out as whitespace or an end of string — the same
|
||||
// trap the agenda grammars hit.
|
||||
//
|
||||
// The Russian word lists are gone (Vikunja #530). The day words are
|
||||
// lexicon.DayOffsetWords, which is why "вчера" and "позавчера" are stripped now
|
||||
// and were not before, and the times of day are lexicon.PartsOfDay. What is
|
||||
// still written out here is the shape of a clock reading — a preposition, digits,
|
||||
// a colon — which is structured input rather than a claim about Russian.
|
||||
var reminderTimeWords = []*regexp.Regexp{
|
||||
regexp.MustCompile(`(?i)(^|\s)через\s+\S+(\s+(часа?|часов|минут[уы]?|секунд[уы]?|дня|дней|недел[юи]))?(\s|$)`),
|
||||
regexp.MustCompile(`(?i)(^|\s)(в|во)\s+\d{1,2}(:\d{2})?(\s*(часа?|часов))?(\s*(утра|вечера|дня|ночи))?(\s|$)`),
|
||||
regexp.MustCompile(`(?i)(^|\s)(` + alternation(lexicon.DayOffsetWords()) + `)(\s|$)`),
|
||||
regexp.MustCompile(`(?i)(^|\s)(` + alternation(lexicon.PartsOfDay()) + `)(\s|$)`),
|
||||
regexp.MustCompile(`(?i)(^|\s)(at|in)\s+\d{1,2}(:\d{2})?\s*(am|pm)?(\s|$)`),
|
||||
}
|
||||
|
||||
// alternation folds a lexicon set into one regexp branch, longest member first
|
||||
// so "послезавтра" is not matched as "завтра" with a tail left behind. Sorted
|
||||
// rather than taken as given, because two members of equal length must still
|
||||
// produce the same pattern on every build.
|
||||
func alternation(set []string) string {
|
||||
out := make([]string, 0, len(set))
|
||||
for _, w := range set {
|
||||
out = append(out, regexp.QuoteMeta(w))
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool {
|
||||
if len(out[i]) != len(out[j]) {
|
||||
return len(out[i]) > len(out[j])
|
||||
}
|
||||
return out[i] < out[j]
|
||||
})
|
||||
return strings.Join(out, "|")
|
||||
}
|
||||
|
||||
// reminderBody is what she says at the hour.
|
||||
//
|
||||
// The whole utterance used to be stored, so /reminders read "напомни завтра в
|
||||
// 9 утра выпить таблетки" where it should read "выпить таблетки", and the
|
||||
// agenda recited the marker back at him (Vikunja #469). The fire time is
|
||||
// already a column, and the marker is an instruction that was carried out.
|
||||
//
|
||||
// Falls back to the fuller text whenever stripping would leave nothing: an
|
||||
// empty body is a reminder that fires and says nothing, which is worse than a
|
||||
// wordy one.
|
||||
func reminderBody(utterance, text string) string {
|
||||
body := strings.TrimSpace(text)
|
||||
if body == "" {
|
||||
body = strings.TrimSpace(utterance)
|
||||
}
|
||||
stripped := reminderMarker.ReplaceAllString(body, "")
|
||||
for _, re := range reminderTimeWords {
|
||||
stripped = re.ReplaceAllString(stripped, " ")
|
||||
}
|
||||
stripped = strings.TrimSpace(strings.Join(strings.Fields(stripped), " "))
|
||||
stripped = strings.Trim(stripped, " ,;:—-")
|
||||
if stripped == "" {
|
||||
return body
|
||||
}
|
||||
return stripped
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
package main
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestReminderBody(t *testing.T) {
|
||||
for _, tc := range []struct{ utterance, text, want string }{
|
||||
// The row from the QA sitting: the whole utterance was the body.
|
||||
{"напомни завтра в 9 утра выпить таблетки", "завтра в 9 утра выпить таблетки", "выпить таблетки"},
|
||||
{"напомни мне позвонить маме в семь вечера", "позвонить маме в 7 вечера", "позвонить маме"},
|
||||
{"напомни через полчаса проверить бэкап", "через полчаса проверить бэкап", "проверить бэкап"},
|
||||
{"remind me to call mom at 7pm", "to call mom at 7pm", "to call mom"},
|
||||
// Nothing left after stripping ⇒ keep what there was. A reminder that
|
||||
// fires and says nothing is worse than a wordy one.
|
||||
{"напомни завтра", "завтра", "завтра"},
|
||||
{"", "", ""},
|
||||
} {
|
||||
if got := reminderBody(tc.utterance, tc.text); got != tc.want {
|
||||
t.Errorf("reminderBody(%q, %q) = %q, want %q", tc.utterance, tc.text, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,209 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Conversation repair (Vikunja #455).
|
||||
//
|
||||
// The classifier has been able to learn from a correction since it was
|
||||
// written — CorrectMisroute appends the utterance as a new example for the
|
||||
// intent he names, append-only, no retrain. Nothing in the daemon could reach
|
||||
// it: the only caller was a test. So the mechanism existed and the behaviour
|
||||
// did not.
|
||||
//
|
||||
// This is the reachable half. He says she got it wrong and names what it
|
||||
// should have been, she redoes the previous utterance under that intent, and
|
||||
// she says out loud that the correction landed — because a correction he
|
||||
// cannot see is indistinguishable from one that was dropped.
|
||||
//
|
||||
// Taken before routing, like the confirm and clarify turns: "нет, это была
|
||||
// заметка" is an answer to the previous turn, not a fresh command, and routing
|
||||
// it as one files the correction itself as a note.
|
||||
|
||||
// routedTurn — the previous utterance and where it went, which is all a
|
||||
// correction needs to point at.
|
||||
type routedTurn struct {
|
||||
utterance string
|
||||
intent router.Intent
|
||||
at time.Time
|
||||
}
|
||||
|
||||
// repairWindow — how long a turn stays correctable. Long enough that he can
|
||||
// hear the wrong answer, think, and say so; short enough that "это заметка"
|
||||
// half an hour later is a fresh sentence and not a verdict on something he has
|
||||
// forgotten.
|
||||
const repairWindow = 5 * time.Minute
|
||||
|
||||
// repairMarkers — the ways he says she got it wrong. One of these must appear:
|
||||
// naming an intent alone is an ordinary sentence ("напиши заметку"), and
|
||||
// treating it as a correction would rewrite the last turn every time he used
|
||||
// the word.
|
||||
//
|
||||
// From the lexicon, and staying a list rather than becoming seeds (Vikunja
|
||||
// #528). This runs pre-route, before the turn vector exists, and a correction
|
||||
// redoes the previous request — so a near-miss would act on something he never
|
||||
// said. The set's note in lexicon_ru_v1.json carries the same reasoning.
|
||||
var repairMarkers = lexicon.RepairMarkers()
|
||||
|
||||
// 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
|
||||
// compares the words themselves (Vikunja #528).
|
||||
var repairIntents = []struct {
|
||||
word string
|
||||
intent router.Intent
|
||||
say string
|
||||
}{
|
||||
{"заметка", router.IntentNote, "заметка"},
|
||||
{"напоминание", router.IntentReminder, "напоминание"},
|
||||
{"напомнить", router.IntentReminder, "напоминание"},
|
||||
{"факт", router.IntentFact, "факт"},
|
||||
{"вопрос", router.IntentQuery, "вопрос"},
|
||||
{"команда", router.IntentAct, "команда"},
|
||||
{"note", router.IntentNote, "заметка"},
|
||||
{"reminder", router.IntentReminder, "напоминание"},
|
||||
{"fact", router.IntentFact, "факт"},
|
||||
{"question", router.IntentQuery, "вопрос"},
|
||||
}
|
||||
|
||||
// parseRepair reads a spoken correction: a marker saying she was wrong, plus
|
||||
// the intent it should have been.
|
||||
//
|
||||
// The negated half is skipped. "это заметка, а не напоминание" names both
|
||||
// intents, and the one he is correcting TO is the one he did not put "не" in
|
||||
// front of.
|
||||
func parseRepair(utterance string) (router.Intent, string, bool) {
|
||||
s := strings.ToLower(strings.TrimSpace(utterance))
|
||||
if s == "" {
|
||||
return "", "", false
|
||||
}
|
||||
// A leading "нет" is a marker on its own — "нет, это заметка" is the
|
||||
// shortest correction he actually says. Only leading: "нет" in the middle
|
||||
// of a sentence is an ordinary word.
|
||||
marked := strings.HasPrefix(s, "нет") || strings.HasPrefix(s, "no,")
|
||||
for _, m := range repairMarkers {
|
||||
if marked || strings.Contains(s, m) {
|
||||
marked = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !marked {
|
||||
return "", "", false
|
||||
}
|
||||
// Over tokens, not byte offsets. The negation test used to read the string
|
||||
// immediately before a match, which meant it could only see "не" spelled
|
||||
// exactly there; a token list makes the previous word plain to read.
|
||||
toks := repairTokens(s)
|
||||
best, say, at := router.Intent(""), "", -1
|
||||
for i, tok := range toks {
|
||||
if at >= 0 && i > at {
|
||||
break
|
||||
}
|
||||
for _, w := range repairIntents {
|
||||
if !morph.SameWord(tok, w.word) {
|
||||
continue
|
||||
}
|
||||
if i > 0 && (toks[i-1] == "не" || toks[i-1] == "not") {
|
||||
// The one he is ruling out: "не напоминание, а заметка".
|
||||
continue
|
||||
}
|
||||
// Leftmost wins: "это заметка, а не напоминание" corrects to the
|
||||
// first.
|
||||
if at < 0 || i < at {
|
||||
best, say, at = w.intent, w.say, i
|
||||
}
|
||||
}
|
||||
}
|
||||
if at < 0 {
|
||||
return "", "", false
|
||||
}
|
||||
return best, say, true
|
||||
}
|
||||
|
||||
// repairTokens splits a correction into lowercase word tokens. Punctuation goes,
|
||||
// because "это заметка, а не напоминание" glues a comma to the word the negation
|
||||
// test has to look past.
|
||||
func repairTokens(s string) []string {
|
||||
return strings.FieldsFunc(s, func(r rune) bool {
|
||||
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
||||
})
|
||||
}
|
||||
|
||||
// recordTurn keeps the utterance a correction would point at. Only turns she
|
||||
// acted on: a clarify asked instead of acting, so there is nothing yet to be
|
||||
// wrong about.
|
||||
func (h *reactiveHandler) recordTurn(utterance string, intent router.Intent) {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
h.lastRouted = &routedTurn{utterance: utterance, intent: intent, at: h.now()}
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) takeLastTurn() *routedTurn {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
last := h.lastRouted
|
||||
// Taken, not read: one utterance is corrected once. Saying "нет, не так"
|
||||
// twice would otherwise redo the same request twice.
|
||||
h.lastRouted = nil
|
||||
return last
|
||||
}
|
||||
|
||||
// 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) {
|
||||
corrected, say, ok := parseRepair(text)
|
||||
if !ok || h.router == nil {
|
||||
return "", false
|
||||
}
|
||||
last := h.takeLastTurn()
|
||||
if last == nil || h.now().Sub(last.at) > repairWindow {
|
||||
return "", false
|
||||
}
|
||||
if last.intent == corrected {
|
||||
// She already did what he is asking for. Correcting the classifier
|
||||
// here would teach it the label it produced, and redoing the request
|
||||
// would file it twice.
|
||||
return "", false
|
||||
}
|
||||
learned := true
|
||||
if err := h.router.CorrectMisroute(ctx, last.utterance, corrected); err != nil {
|
||||
// The redo is still worth doing: he asked for something and it did not
|
||||
// happen. Only the learning half is lost, and he is told so.
|
||||
log.Printf("voice: repair: could not learn %q as %s: %v", last.utterance, corrected, err)
|
||||
learned = false
|
||||
}
|
||||
log.Printf("voice: repair — %q was %s, corrected to %s (learned=%v)", last.utterance, last.intent, corrected, learned)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: last.utterance,
|
||||
Stage: 2,
|
||||
Intent: corrected,
|
||||
Slots: h.extractor.Extract(ctx, corrected, last.utterance, h.now()),
|
||||
}
|
||||
// A reminder's Text is what she says at the hour and stays empty when it
|
||||
// was not spoken, so the gap is asked about rather than filled with the
|
||||
// whole sentence. Everywhere else the utterance IS the payload.
|
||||
if dec.Slots.Text == "" && corrected != router.IntentReminder {
|
||||
dec.Slots.Text = last.utterance
|
||||
}
|
||||
return repairLine(say, learned) + " " + h.finishClarified(ctx, dec), true
|
||||
}
|
||||
|
||||
// repairLine — what she says before redoing it, so the correction is visible
|
||||
// and not just filed. Feminine, informal, no apology: he corrected a routing
|
||||
// call, he did not complain about her.
|
||||
func repairLine(say string, learned bool) string {
|
||||
if !learned {
|
||||
return "поняла, это " + say + " — переделываю, но запомнить поправку не вышло."
|
||||
}
|
||||
return "поняла, это " + say + " — запомнила."
|
||||
}
|
||||
@@ -0,0 +1,151 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestParseRepairReadsTheCorrectedIntent(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want router.Intent
|
||||
ok bool
|
||||
}{
|
||||
{"нет, ты не поняла, это заметка", router.IntentNote, true},
|
||||
{"нет, это заметка", router.IntentNote, true},
|
||||
{"это не напоминание, а заметка", router.IntentNote, true},
|
||||
{"это заметка, а не напоминание", router.IntentNote, true},
|
||||
{"ты не так поняла — это факт", router.IntentFact, true},
|
||||
{"неправильно поняла, это был вопрос", router.IntentQuery, true},
|
||||
{"you got it wrong, that was a note", router.IntentNote, true},
|
||||
// No marker: an ordinary request that happens to name an intent.
|
||||
{"запиши заметку купить хлеб", "", false},
|
||||
{"напомни мне про заметку", "", false},
|
||||
// A marker with no intent named: nothing to correct to.
|
||||
{"ты не так поняла", "", false},
|
||||
{"", "", false},
|
||||
}
|
||||
for _, c := range cases {
|
||||
got, _, ok := parseRepair(c.utterance)
|
||||
if ok != c.ok || (ok && got != c.want) {
|
||||
t.Errorf("parseRepair(%q) = %q,%v; want %q,%v", c.utterance, got, ok, c.want, c.ok)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestRepairTeachesTheClassifierAndRedoesTheTurn is the whole feature: the
|
||||
// previous utterance is filed under the intent he named, the classifier keeps
|
||||
// it as an example, and he hears that it landed.
|
||||
func TestRepairTeachesTheClassifierAndRedoesTheTurn(t *testing.T) {
|
||||
h, st, now := newClarifyHandler(t)
|
||||
emb := router.NewHashEmbedder(256)
|
||||
cls := router.NewClassifier(emb)
|
||||
h.recall.embedder = emb
|
||||
h.router = router.New(router.Config{Classifier: cls, Extractor: h.extractor})
|
||||
ctx := context.Background()
|
||||
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
reply, handled := h.resolveRepair(ctx, "нет, ты не поняла, это заметка")
|
||||
if !handled {
|
||||
t.Fatal("a spoken correction was not handled")
|
||||
}
|
||||
if !strings.Contains(reply, "заметка") {
|
||||
t.Errorf("the correction is not named out loud: %q", reply)
|
||||
}
|
||||
if strings.Contains(reply, "не вышло") {
|
||||
t.Errorf("learning failed unexpectedly: %q", reply)
|
||||
}
|
||||
|
||||
ex := cls.Examples(router.IntentNote)
|
||||
if len(ex) != 1 || ex[0].Text != "купить хлеб" {
|
||||
t.Fatalf("the classifier did not learn the correction: %+v", ex)
|
||||
}
|
||||
notes, err := st.RecentNotes(ctx, 5)
|
||||
if err != nil {
|
||||
t.Fatalf("recent notes: %v", err)
|
||||
}
|
||||
if len(notes) != 1 || !strings.Contains(notes[0].Text, "купить хлеб") {
|
||||
t.Fatalf("the request was not redone as a note: %+v", notes)
|
||||
}
|
||||
_ = now
|
||||
}
|
||||
|
||||
func TestRepairNeedsARecentTurnToPointAt(t *testing.T) {
|
||||
h, _, now := newClarifyHandler(t)
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(router.NewHashEmbedder(256))})
|
||||
ctx := context.Background()
|
||||
|
||||
// Nothing said yet.
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("a correction with no previous turn was handled")
|
||||
}
|
||||
// Said, but long ago.
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
*now = now.Add(repairWindow + time.Minute)
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("a correction outside the window was handled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestRepairIsSpentOnce(t *testing.T) {
|
||||
h, _, _ := 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()
|
||||
|
||||
h.recordTurn("купить хлеб", router.IntentFact)
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); !handled {
|
||||
t.Fatal("the first correction was not handled")
|
||||
}
|
||||
if _, handled := h.resolveRepair(ctx, "нет, это заметка"); handled {
|
||||
t.Error("the same turn was corrected twice")
|
||||
}
|
||||
}
|
||||
|
||||
// TestRepairPassesWhenSheAlreadyDidThat — he names the intent she used. There
|
||||
// is nothing to teach and redoing it would file the request a second time.
|
||||
func TestRepairPassesWhenSheAlreadyDidThat(t *testing.T) {
|
||||
h, _, _ := newClarifyHandler(t)
|
||||
h.router = router.New(router.Config{Classifier: router.NewClassifier(router.NewHashEmbedder(256))})
|
||||
h.recordTurn("купить хлеб", router.IntentNote)
|
||||
if _, handled := h.resolveRepair(context.Background(), "нет, это заметка"); handled {
|
||||
t.Error("a correction to the intent she already used was handled")
|
||||
}
|
||||
}
|
||||
|
||||
// TestRepairIntentWordCollisions — the prefix list matched more than the word
|
||||
// (Vikunja #528). "команд" is inside "командировка" and "факт" inside
|
||||
// "фактически", and either one used to name an intent she would redo the turn
|
||||
// under.
|
||||
func TestRepairIntentWordCollisions(t *testing.T) {
|
||||
for _, s := range []string{
|
||||
"нет, это про командировку",
|
||||
"нет, фактически всё нормально",
|
||||
} {
|
||||
if _, _, ok := parseRepair(s); ok {
|
||||
t.Errorf("parseRepair(%q) claimed a correction", s)
|
||||
}
|
||||
}
|
||||
// The declined forms the prefixes existed to cover still work, and the
|
||||
// negated half is still skipped.
|
||||
for _, tc := range []struct {
|
||||
utterance string
|
||||
want router.Intent
|
||||
}{
|
||||
{"нет, это заметка", router.IntentNote},
|
||||
{"ты не так поняла, это заметку надо было", router.IntentNote},
|
||||
{"нет, это напоминание, а не заметка", router.IntentReminder},
|
||||
{"нет, не напоминание, а заметка", router.IntentNote},
|
||||
{"нет, это командой было", router.IntentAct},
|
||||
} {
|
||||
got, _, ok := parseRepair(tc.utterance)
|
||||
if !ok || got != tc.want {
|
||||
t.Errorf("parseRepair(%q) = %q, %v; want %q, true", tc.utterance, got, ok, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
+22
-99
@@ -2,120 +2,43 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/persona"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
// completer is the LLM seam for the replier (subset of router.Completer).
|
||||
// *llm.Client satisfies it.
|
||||
type completer interface {
|
||||
Complete(ctx context.Context, r llm.Req) (string, error)
|
||||
}
|
||||
|
||||
// llmReplier phrases reactive confirmations with the resident model
|
||||
// (Qwen3-1.7B). Stub is the
|
||||
// floor on any error (offline-safe). Maven speaks as "she", feminine RU.
|
||||
// llmReplier is the daemon-side wiring around phraser.Replier: it owns the
|
||||
// deterministic floor, and nothing else. The phrasing itself, the prompt and the
|
||||
// output parsing live in internal/phraser so the eval can score them (#396).
|
||||
type llmReplier struct {
|
||||
c completer
|
||||
p *phraser.Replier
|
||||
stub *voice.StubReplier
|
||||
|
||||
// block renders the shared context block per turn (who he is, the time).
|
||||
// nil ⇒ the prompt stands alone.
|
||||
block func() string
|
||||
}
|
||||
|
||||
func newLLMReplier(c completer, block func() string) *llmReplier {
|
||||
return &llmReplier{c: c, stub: voice.NewStubReplier(), block: block}
|
||||
func newLLMReplier(c phraser.Completer, block func() string) *llmReplier {
|
||||
return &llmReplier{p: phraser.NewReplier(c, block), stub: voice.NewStubReplier()}
|
||||
}
|
||||
|
||||
const replySystem = `Ты — Maven, домашняя ассистентка (о себе — в женском роде). Владелец — мужчина, говоришь с ним на "ты", в единственном числе; никогда не "вы"/"ваш" и не "он"/"его". Подтверди действие РОВНО ОДНИМ коротким предложением (≤120 символов), по-русски, спокойно и без официальных формулировок. Не задавай вопросов, не повторяй слова, не добавляй ничего после точки. Отвечай ТОЛЬКО одним объектом JSON с полями "response" (текст) и "mood" (ровно одно из: neutral, happy, thinking, tired, confused).
|
||||
Пример: {"response": "Записала, что ты выпил стакан воды.", "mood": "neutral"}
|
||||
Никогда не пиши "..." в поле response.`
|
||||
|
||||
// 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 {
|
||||
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,
|
||||
// and it used to be the same words every time (Vikunja #457). Still no
|
||||
// model call — this text has to be right every time, and it is not worth
|
||||
// a generation to say something this small.
|
||||
return clarifyMissedLine(d)
|
||||
}
|
||||
out, err := r.p.PhraseReply(context.Background(), d)
|
||||
if err != nil || out == "" {
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
|
||||
defer cancel()
|
||||
out, err := r.c.Complete(ctx, llm.Req{
|
||||
System: persona.Prepend(r.block, replySystem),
|
||||
User: replyContext(d),
|
||||
MaxTokens: 512,
|
||||
RepeatPenalty: 1.3,
|
||||
})
|
||||
if err != nil {
|
||||
// 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)
|
||||
}
|
||||
out = stripThink(out)
|
||||
if response, _ := parseResponseMood(out); response != "" {
|
||||
return response
|
||||
}
|
||||
// fallback: try plain-text parsing
|
||||
if out = firstSentence(out); out != "" {
|
||||
return out
|
||||
}
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
|
||||
// firstSentence trims the model's output to a single clean confirmation: first
|
||||
// line, first sentence, whitespace-normalized — the last-line defense against a
|
||||
// small model that rambles past the first period despite the prompt + stop.
|
||||
// stripThink removes the <think> block that Thinking-variant models emit.
|
||||
func stripThink(s string) string {
|
||||
if i := strings.LastIndex(s, "</think>"); i >= 0 {
|
||||
s = strings.TrimSpace(s[i+8:])
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
func firstSentence(s string) string {
|
||||
s = strings.TrimSpace(s)
|
||||
if i := strings.IndexByte(s, '\n'); i >= 0 {
|
||||
s = s[:i]
|
||||
}
|
||||
// keep up to and including the first sentence-ending punctuation.
|
||||
if i := strings.IndexAny(s, ".!?"); i >= 0 {
|
||||
s = s[:i+1]
|
||||
}
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
|
||||
// parseResponseMood extracts {"response","mood"} from LLM output, tolerant
|
||||
// of thinking tokens and extra text before/after the JSON block.
|
||||
func parseResponseMood(raw string) (response, mood string) {
|
||||
cleaned := strings.TrimSpace(raw)
|
||||
start := strings.Index(cleaned, "{")
|
||||
end := strings.LastIndex(cleaned, "}")
|
||||
if start < 0 || end < 0 || end <= start {
|
||||
return "", ""
|
||||
}
|
||||
var parsed struct {
|
||||
Response string `json:"response"`
|
||||
Mood string `json:"mood"`
|
||||
}
|
||||
if err := json.Unmarshal([]byte(cleaned[start:end+1]), &parsed); err != nil {
|
||||
return "", ""
|
||||
}
|
||||
return parsed.Response, parsed.Mood
|
||||
}
|
||||
|
||||
// replyContext renders the decision into a compact RU description for the model.
|
||||
func replyContext(d router.Decision) string {
|
||||
switch d.Intent {
|
||||
case router.IntentFact:
|
||||
return "записала факт: " + d.Slots.Key + " " + d.Slots.Value
|
||||
case router.IntentNote:
|
||||
return "сохранила заметку: " + d.Slots.Text
|
||||
case router.IntentReminder:
|
||||
return "поставила напоминание: " + d.Slots.Text
|
||||
default:
|
||||
return string(d.Intent) + ": " + d.Slots.Text
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -5,27 +5,23 @@ import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
type mockCompleter struct {
|
||||
// The phrasing itself is tested in internal/phraser. What is left here is the
|
||||
// only thing the daemon adds: the stub floor, on the three ways a reply can
|
||||
// fail to arrive.
|
||||
type stubCompleter struct {
|
||||
out string
|
||||
err error
|
||||
}
|
||||
|
||||
func (m mockCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
|
||||
func (s stubCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return s.out, s.err }
|
||||
|
||||
func TestLLMReplierReturnsLLMReply(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
|
||||
got := r.Reply(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")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToPlainText(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: "записала, кофе закончился"}, nil)
|
||||
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"}})
|
||||
if got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, want %q", got, "записала, кофе закончился")
|
||||
@@ -33,36 +29,51 @@ func TestLLMReplierFallsBackToPlainText(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnError(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{err: errTestLLMDown}, nil)
|
||||
noteDec := router.Decision{Intent: router.IntentNote}
|
||||
got := r.Reply(noteDec)
|
||||
want := voice.NewStubReplier().Reply(noteDec)
|
||||
if got != want {
|
||||
t.Errorf("on llm error: got %q, want stub %q", got, want)
|
||||
}
|
||||
r := newLLMReplier(stubCompleter{err: errReplierTest}, nil)
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "llm error")
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: ""}, nil)
|
||||
noteDec := router.Decision{Intent: router.IntentNote}
|
||||
got := r.Reply(noteDec)
|
||||
want := voice.NewStubReplier().Reply(noteDec)
|
||||
if got != want {
|
||||
t.Errorf("on empty llm: got %q, want stub %q", got, want)
|
||||
r := newLLMReplier(stubCompleter{out: ""}, nil)
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "empty llm")
|
||||
}
|
||||
|
||||
// A clarify never reaches the model, and since Vikunja #457 it is answered from
|
||||
// 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"})
|
||||
if got == "я всё поняла" {
|
||||
t.Fatal("a clarify must not be phrased by the model")
|
||||
}
|
||||
if want := clarifyMissedFor("мгм"); got != want {
|
||||
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 {
|
||||
t.Log("two utterances hashed to the same line, which is allowed but should be rare")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLLMReplierClarifyUsesStub(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: "я всё поняла"}, nil)
|
||||
clarifyDec := router.Decision{Clarify: true}
|
||||
got := r.Reply(clarifyDec)
|
||||
want := voice.NewStubReplier().Reply(clarifyDec)
|
||||
if got != want {
|
||||
t.Errorf("on clarify: got %q, want stub %q", got, want)
|
||||
// assertAck — the stub picks between variants now, so two calls to it are not
|
||||
// expected to match. What must hold is that the reply is a line that entry can
|
||||
// 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) {
|
||||
t.Errorf("on %s: got %q, want a %q line", what, got, key)
|
||||
}
|
||||
}
|
||||
|
||||
var errTestLLMDown = errTest("llm down")
|
||||
func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
|
||||
t.Helper()
|
||||
got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
|
||||
if got != want {
|
||||
t.Errorf("on %s: got %q, want stub %q", what, got, want)
|
||||
}
|
||||
}
|
||||
|
||||
var errReplierTest = errTest("llm down")
|
||||
|
||||
type errTest string
|
||||
|
||||
|
||||
+29
-37
@@ -4,6 +4,10 @@
|
||||
// plural agreement, clock/date rendering, and the "do I actually know this
|
||||
// place/day" guards that pick an honest reply over a confidently wrong one.
|
||||
// Extend this file rather than voice.go for anything in that shape.
|
||||
//
|
||||
// Count agreement is not here. It is say.CountWord, because there were four
|
||||
// copies of the same three-way rule and two of the sites that needed it were
|
||||
// spelling one form out (Vikunja #521).
|
||||
package main
|
||||
|
||||
import (
|
||||
@@ -11,17 +15,15 @@ import (
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
var ruWeekdays = []string{
|
||||
"воскресенье", "понедельник", "вторник", "среда",
|
||||
"четверг", "пятница", "суббота",
|
||||
}
|
||||
|
||||
var ruMonths = []string{
|
||||
"января", "февраля", "марта", "апреля", "мая", "июня",
|
||||
"июля", "августа", "сентября", "октября", "ноября", "декабря",
|
||||
}
|
||||
// Weekday and month names are a closed class — the language has seven and
|
||||
// twelve — so they live complete in internal/lexicon, where internal/ttsnorm
|
||||
// reads the same twelve month names instead of keeping a second copy
|
||||
// (Vikunja #525).
|
||||
|
||||
// onlyLocalTimeReply — the honest answer when the user asks the time somewhere
|
||||
// other than here. She only keeps one clock, and saying so is better than
|
||||
@@ -33,13 +35,15 @@ var ruMonths = []string{
|
||||
const onlyLocalTimeReply = "я знаю только местное время, про другие города пока не скажу."
|
||||
|
||||
// notPlaceAfterV — words that follow "в" without naming a place, so
|
||||
// mentionsUnknownPlace does not mistake them for a city.
|
||||
var notPlaceAfterV = map[string]bool{
|
||||
"данный": true, "данную": true, "этот": true, "эту": true,
|
||||
"котором": true, "какое": true, "какой": true, "который": true,
|
||||
"общем": true, "точности": true, "курсе": true, "сутках": true,
|
||||
"часах": true, "минутах": true, "секундах": true, "неделе": true,
|
||||
}
|
||||
// mentionsUnknownPlace does not mistake them for a city. Closed set, kept
|
||||
// complete in internal/lexicon.
|
||||
var notPlaceAfterV = func() map[string]bool {
|
||||
m := map[string]bool{}
|
||||
for _, w := range lexicon.NotPlaceAfterV() {
|
||||
m[w] = true
|
||||
}
|
||||
return m
|
||||
}()
|
||||
|
||||
// mentionsUnknownPlace reports whether the question has a "в <слово>" phrase
|
||||
// that looks like a place we do not know ("который час в киеве"). Used only to
|
||||
@@ -94,11 +98,11 @@ func mentionsUnknownDay(u string) bool {
|
||||
// ruClock renders the clock part of the time reply: "15 часов 4 минуты".
|
||||
func ruClock(t time.Time) string {
|
||||
h, m := t.Hour(), t.Minute()
|
||||
hourWord := ruPlural(h, "час", "часа", "часов")
|
||||
hourWord := say.CountWord(h, "час", "часа", "часов")
|
||||
if m == 0 {
|
||||
return fmt.Sprintf("%d %s ровно", h, hourWord)
|
||||
}
|
||||
return fmt.Sprintf("%d %s %d %s", h, hourWord, m, ruPlural(m, "минута", "минуты", "минут"))
|
||||
return fmt.Sprintf("%d %s %d %s", h, hourWord, m, say.CountWord(m, "минута", "минуты", "минут"))
|
||||
}
|
||||
|
||||
// dayPrefix names the day relative to now ("завтра", "вчера", …) so the date
|
||||
@@ -118,22 +122,6 @@ func dayPrefix(now, day time.Time) string {
|
||||
return "это"
|
||||
}
|
||||
|
||||
func ruPlural(n int, one, two, many string) string {
|
||||
n = n % 100
|
||||
if n > 10 && n < 20 {
|
||||
return many
|
||||
}
|
||||
n = n % 10
|
||||
switch n {
|
||||
case 1:
|
||||
return one
|
||||
case 2, 3, 4:
|
||||
return two
|
||||
default:
|
||||
return many
|
||||
}
|
||||
}
|
||||
|
||||
// hasDurationWords checks whether u is asking about elapsed/remaining time
|
||||
// rather than the current clock — guards replySystem from replying "сейчас
|
||||
// X часов" to "сколько времени прошло". Mirrors the stage0.go build filter.
|
||||
@@ -169,12 +157,16 @@ func formatTime(t time.Time) string {
|
||||
case diff < 10*time.Minute:
|
||||
return "несколько минут назад"
|
||||
case diff < 60*time.Minute:
|
||||
return fmt.Sprintf("%d минут назад", int(diff.Minutes()))
|
||||
n := int(diff.Minutes())
|
||||
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "минуту", "минуты", "минут"))
|
||||
case diff < 2*time.Hour:
|
||||
return "час назад"
|
||||
case diff < 24*time.Hour:
|
||||
return fmt.Sprintf("%d часа назад", int(diff.Hours()))
|
||||
n := int(diff.Hours())
|
||||
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "час", "часа", "часов"))
|
||||
default:
|
||||
return t.Format("2 января 15:04")
|
||||
// Not t.Format("2 января …"): Go reads that as a literal, so every
|
||||
// fact older than a day used to read as January (Vikunja #507).
|
||||
return fmt.Sprintf("%d %s %s", t.Day(), lexicon.MonthGenitive(int(t.Month())), t.Format("15:04"))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"log"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/websearch"
|
||||
)
|
||||
|
||||
// searchWiring — the metasearch source, assembled. nil ⇒ off, which is the
|
||||
// default: no `search` block, no query ever leaves the LAN.
|
||||
//
|
||||
// Thinner than kiwixWiring because there is nothing to rewrite. SearXNG ranks
|
||||
// with real engines, so the question goes out as he asked it, and that is the
|
||||
// reason this source sits ahead of the ZIMs rather than behind them.
|
||||
type searchWiring struct {
|
||||
client *websearch.Client
|
||||
max int
|
||||
runes int
|
||||
}
|
||||
|
||||
// wireSearch builds the search client from the `search` block, or returns nil
|
||||
// when there is none. config.Normalise has already dropped a block with no URL
|
||||
// and filled the two size defaults, so this does no validation of its own.
|
||||
func wireSearch(cfg *config.Config) *searchWiring {
|
||||
if cfg.Search == nil {
|
||||
return nil
|
||||
}
|
||||
sc := cfg.Search
|
||||
log.Printf("voice: web search at %s (language %q, engines %q)", sc.URL, sc.Language, sc.Engines)
|
||||
return &searchWiring{
|
||||
client: websearch.New(sc.URL, websearch.Options{
|
||||
Language: sc.Language,
|
||||
Engines: sc.Engines,
|
||||
Timeout: time.Duration(sc.Timeout),
|
||||
}),
|
||||
max: sc.MaxResults,
|
||||
runes: sc.SnippetRunes,
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,107 @@
|
||||
// mavend/seed.go — the backdated-fact seam (Vikunja #518).
|
||||
//
|
||||
// The pattern detector needs four events for one action+object, spread by at
|
||||
// least pattern.MinIntervalDays, before it proposes a routine. Nothing could
|
||||
// produce that against a running daemon in one sitting: the only writer is a
|
||||
// fact write at time.Now(), so V-43, V-46, V-247 and V-254 all stopped at the
|
||||
// same missing step and had been stopped there since they were filed.
|
||||
//
|
||||
// This is the write path that unblocks them, and it is deliberately the narrow
|
||||
// one. It takes a fact, not an event, so pattern.Extract runs for real and a
|
||||
// key the extractor ignores seeds nothing. It runs detectAndPropose, so what a
|
||||
// seed proves is the daemon's own wiring rather than the detector in isolation
|
||||
// — which is what an eval-lab fixture would have proved, and is not what those
|
||||
// four tasks doubt.
|
||||
//
|
||||
// It is off unless mavend was started with -allow-seed, and AuthStepUp in the
|
||||
// authority table besides. See ipc.SeedEventReq and auth.Requirement.
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/pattern"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// errSeedDisabled — what a caller gets on an ordinary box. Named rather than
|
||||
// inline so the mavweb route can tell "not allowed here" apart from "the seed
|
||||
// ran and the extractor declined", which look the same to a reader otherwise.
|
||||
var errSeedDisabled = errors.New("mavend: seeding is off (start with -allow-seed)")
|
||||
|
||||
// seedSource — every seeded fact carries this, and no other writer uses it.
|
||||
// The point is that seeded data stays identifiable forever: a fact that came
|
||||
// from a QA sitting must never be mistaken for something he said, either by a
|
||||
// person reading /history or by the wipe in V-494 when it lands.
|
||||
const seedSource = "seed:qa"
|
||||
|
||||
// seedStoreIfAllowed returns st only when -allow-seed was passed, and logs the
|
||||
// fact loudly when it does. A box that can rewrite its own past should say so
|
||||
// in its boot log, so nobody reads a seeded routine months later as evidence of
|
||||
// something he actually did.
|
||||
func seedStoreIfAllowed(st *store.Store) *store.Store {
|
||||
if !allowSeedOnStart {
|
||||
return nil
|
||||
}
|
||||
log.Printf("seed: -allow-seed is ON — backdated fact writes are permitted under source %q (Vikunja #518)", seedSource)
|
||||
return st
|
||||
}
|
||||
|
||||
// SeedEvent writes the fact at the caller's timestamp, extracts an event from
|
||||
// it, and runs the same detect-and-propose step the voice path runs.
|
||||
//
|
||||
// Best-effort is NOT the shape here, unlike detectPattern: a seed that half
|
||||
// worked is a QA result nobody can trust, so every step reports its own
|
||||
// failure. Extraction declining is not a failure — it is the extractor's
|
||||
// documented answer for a value outside its lexicon, and Extracted says so.
|
||||
func (d *daemonAPI) SeedEvent(ctx context.Context, req ipc.SeedEventReq) (ipc.SeedEventResp, error) {
|
||||
if d.seedStore == nil {
|
||||
return ipc.SeedEventResp{}, errSeedDisabled
|
||||
}
|
||||
if req.Key == "" || req.Value == "" {
|
||||
return ipc.SeedEventResp{}, errors.New("mavend: seed needs a key and a value")
|
||||
}
|
||||
if req.Ts.IsZero() {
|
||||
return ipc.SeedEventResp{}, errors.New("mavend: seed needs an explicit timestamp")
|
||||
}
|
||||
|
||||
// No Subject, unlike the voice path: a seeded key must not queue a Nexus
|
||||
// resolution. QA data has no business reaching the ecosystem.
|
||||
factID, err := d.seedStore.WriteFact(ctx, req.Ts, store.KindSelf, req.Key, req.Value, seedSource, 1.0, sql.NullInt64{})
|
||||
if err != nil {
|
||||
return ipc.SeedEventResp{}, fmt.Errorf("seed write fact: %w", err)
|
||||
}
|
||||
resp := ipc.SeedEventResp{FactID: factID}
|
||||
|
||||
ev := pattern.Extract(factID, req.Key, req.Value, req.Ts)
|
||||
if ev == nil {
|
||||
// The fact is written and stays written. Saying so matters: a caller
|
||||
// that assumed a seed always produces an event would otherwise read
|
||||
// four silent successes and conclude the detector is broken.
|
||||
log.Printf("seed: %s=%s wrote fact %d, no event (value outside the action lexicon)", req.Key, req.Value, factID)
|
||||
return resp, nil
|
||||
}
|
||||
resp.Extracted, resp.Action, resp.Object = true, ev.Action, ev.Object
|
||||
|
||||
eventID, err := d.seedStore.CreateEvent(ctx, factID, ev.Action, ev.Object, req.Ts)
|
||||
if err != nil {
|
||||
return resp, fmt.Errorf("seed create event: %w", err)
|
||||
}
|
||||
resp.EventID = eventID
|
||||
|
||||
r, routineID, err := detectAndPropose(ctx, d.seedStore, ev.Action, ev.Object, req.Ts)
|
||||
if err != nil {
|
||||
return resp, fmt.Errorf("seed detect: %w", err)
|
||||
}
|
||||
if r == nil {
|
||||
return resp, nil // too few events yet, too irregular, or already decided
|
||||
}
|
||||
resp.Proposed, resp.RoutineID, resp.IntervalDays = true, routineID, r.IntervalDays
|
||||
log.Printf("seed: proposed routine %d — %s/%s every %.1f days", routineID, r.Action, r.Object, r.IntervalDays)
|
||||
return resp, nil
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user