Three defects in internal/phraser, all of the shape "reports done when
nothing happened".
The reminder summary was cut in bytes: `len(s) > 60` and `s[:57]`, in two
copies (Stub.PhraseReminder and LLMPhraser.PhraseReminder). On Russian a
letter is two bytes, so the cut fell at about 28 letters instead of 60 and
landed inside a letter about half the time. Sendable.Summary is what
voicesink hands to piper and what the telegram sink posts, so the half rune
was spoken and sent. One rune-counting helper now, shared by both. The test
that covered this was ASCII, which is what let the arithmetic stand.
The evidence branch of PhraseQuery and the bare-prose tail of PhraseChat
both returned ("", nil) when the server answered and the model wrote no
tokens. The knowledge branch has guarded that with errEmptyResponse since it
was written; these two did not. The daemon's callers check for the empty
string and paper over it, so the visible cost was the eval, which scored a
silent model as bad phrasing rather than as a failure, and a log line that
never appeared.
Stub.PhraseReminder set no Mood. Its sibling PhraseNudge sets "neutral" and
says in a comment why: the Stub is a production fallback and owes the output
contract a value. The zero value is not one of the five moods.
No prompt and no spoken wording changed, so the phrasing eval is unmoved.
Two defects found probing the new source on the box.
"кто ты" was answered from one of his notes. The self source sat below
memory and notes, which match by proximity and have no idea the subject
is her. It belongs above all three: a question about her has no answer
in his data either.
And PhraseQuery opens every answer with "вот что я нашла: ", which is
deliberate — it marks the answer as a lookup. Her own description is the
one subject she did not look up, so this is PhraseSelf instead, same
read-only discipline and its own opener. The Stub reads the description
out as it stands, which needs no fallback: it is already her voice.
Stub and LLM paths both read loop.DownServices, so the message can never name
a service the predicate did not fire on. Two down at once are both named — he
needs the blast radius.
The accessors are functions now, so the call sites that compared against one
literal compare against the entry instead: IsUnknownFallback and
IsSourcesFallback in the daemon tests, the entry key in the phraser tests. A
reworded variant no longer breaks a Go test.
The eval scores every variant on the persona checks the nudges already pass.
Review of #108: "поговорили." reads as a summary of a conversation that did
not happen. One exported constant now, so the Stub, the LLMPhraser fallback
and the daemon all say the same thing.
internal/voice/replier.go keeps its own copy — that is the separate replier
seam, not this one.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Seventeen markdown files at the repo root, twelve of them dated one-shot
reports sitting next to CLAUDE.md. That is why stale docs read as
current: nothing in the path said which was which.
Root now keeps CLAUDE.md and AGENTS.md. Living docs move under docs/
and carry a Last verified line. Dated measurements move to docs/evals/
ISO-prefixed, and are never edited after the day, so a newer number is
a new file. The senior review moves to docs/archive/.
Every reference was rewritten across markdown, Go comments, the Makefile
and the recall fixture. The touched Go packages still build.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
wireVoice runs before the tick loop exists, so it could only be handed
the bare store adapter — and that adapter answers DayPlan with "not
available via direct store API", because a day plan is assembled by the
tick loop and is not a table to read. So queryDayPlan, which the query
chain reaches for "какие у меня планы на сегодня", failed for every
caller on the deployed daemon.
main already back-patches the other direction (daemonAPI.chatFn =
handler.handleText). This is the same seam in reverse, at both wiring
sites. No recursion risk: nothing in the voice path calls api.Chat.
With the plan reachable, it recited its reminders as literal JSON. The
payload unwrapper existed but was private to the phraser, so the day
plan had its own non-unwrapping copy. One owner now, store.ReminderText,
with the phraser delegating to it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
Review internal/phraser/eval/checks.go -- it IS the measurement. Each check
names in a comment which DESIGN.md line it defends: length, feminine
self-reference (windowed around "я" so the operator's own masculine
second-person forms are not flagged), the cringe list (pet names, emoji,
"!!", fake concern, apology, emotional support, asking how he feels,
praise), on-topic, mood enum. No send/veto signal anywhere, per
DESIGN.md § "Rules decide, LLM phrases".
Fixture (158 lines) and tests (252) do not count toward the diff ceiling;
the scorer itself is still ~650. Splitting eval.go from checks.go would
give two commits neither of which measures anything.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
The most load-bearing decision in the project was stated four incompatible
ways: the docs said Qwen3-1.7B, deploy/mavend.json said Qwen3.5-2B, the repo's
models/llm/ held an LFM2.5-1.2B gguf, and five code comments still said LFM.
Answering "which model is deployed" meant re-deriving it from scratch every
time.
Two facts the review missed, found while resolving it:
- /mnt/hdd1/llms is bind-mounted over /opt/maven/models/llm, which shadows the
repo's models/llm/. The LFM2.5 gguf sitting there was never loaded by
anything, so it was not evidence of the deployed model at all.
- That library holds Qwen3.5-0.8B, -2B and -4B, and no Qwen3-1.7B. The config
pointed at a file that does exist; the docs' Qwen3-1.7B was the stale claim,
the reverse of the assumed direction. Qwen3-1.7B is the CPT target, and that
training is still in flight (Vikunja #122), so no such gguf exists yet.
phraser.model_path moves to Qwen3.5-0.8B (Q4_K_M) — the smallest checkpoint on
disk, chosen for latency, and relevant to whether the LLM router is affordable
on this box. Docs and comments now say the same thing in one voice: 0.8B
resident now, CPT'd Qwen3-1.7B as the target, and the bind-mount shadowing
written down so the next reader does not mistake models/llm/ for ground truth.
Comments name the model, never a filename, so a swap stays a one-line config
change.
n_gpu_layers: 99 is correct and stays — compose passes /dev/dri and the render
gid for Vulkan offload to the Vega iGPU. CLAUDE.md's "CPU-only" was the stale
half of that contradiction and is corrected.
phraser.go also dropped a wrong "sub-1b, prompted not trained" size claim: the
target is trained end-to-end (RU CPT + joint persona/router SFT).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X5JApcrCRVGmqrxnhynSik
- Add llmphraser: LFM-based phraser implementing Phraser interface with
PhraseChat, PhraseNudge, PhraseReactive, and PhraseReminder methods.
- Add shared internal/llm/client: llama-server completion client used by
both the phraser (talking back) and router (routing), sharing one model.
- Add LLMReplier in mavend: replaces StubReplier for chat/nudge/reactive
replies, falls back to stub on model errors.
- Update Phraser interface: add PhraseChat method, update stub to match.
- Wire LLM phaser into mavend voice init, plumb LLM config from JSON.
- Add CalendarEvents method to recordingAPI in auth_test.go
- Add CalendarEvents method to fakeCore in handlers_test.go
Co-Authored-By: opencode <opencode@anthropic.com>
- Stub.PhraseQuery: empty notes → "не знаю." (was: "no notes")
- LLMPhraser.PhraseQuery: empty notes → general knowledge prompt to LLM
- Voice handler: on notes RAG failure, try phraser before giving up
- New router.KnowledgePrompt() pure function with test
Co-Authored-By: opencode <opencode@anthropic.com>
Completes the three in-flight open items and fixes the away-fallthrough bug.
Item 7 — passkey step-up (WebAuthn):
- internal/webauthn: ES256/P-256 register + assert with real ecdsa signature
verification, minimal CBOR/COSE decode, PasskeySession (L2→L3 on assert,
decays after TTL). Drop the RS256 offer we can't verify (register-ok/
assert-fail trap). Verify rpIdHash + UP/UV flags in FinishAssertion — UV is
the step-up gesture. Round-trip test with negative cases (tampered sig,
missing UV, wrong origin).
- cmd/mavweb: /auth/passkey enroll+assert page (the only surface that can do
a WebAuthn gesture) + the four begin/finish endpoints. Without this the
daemon's PasskeySession swap leaves /tools enable permanently blocked.
- daemon wires PasskeySession as the auth Session + srv.StepUp; policy gates
MethodAssertStepUp at AuthRead.
Item 5 — tools page: DisableTool through store/ipc/client/wire; /tools grows a
disable action and a link to the passkey page. Lifecycle test.
Item 6 — note RAG: PhraseQuery on the phraser (LLM-composed answer over top-k
notes, raw-notes fallback); IntentQuery routes through it. Stub returns a
deterministic summary.
Item 2 — away-fallthrough: on ErrVoiceNoSession the dispatcher now reroutes
through the AWAY table (sev3→ntfy, sev4→telegram-repeat-til-ack, sev≤2→drop)
instead of silently dropping / mis-routing to the present-list remainder.
Covers DispatchNudge + DispatchReminder. 4 tests.
Also: re-add ProposeTool to CoreAPI (dropped in a comment rewrite), fix
missing imports + a duplicate block left mid-edit, drop dead AssertStepUpFunc,
gitignore /mavcaldav.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
claude
kami