The system prompt showed the JSON contract as {"response": "..."} and the
user prompt repeated it. A 0.8B copies whatever sits in the response slot, so
7 of 15 nudges came back as literally "...".
Changes, all prompt-side — the {"response","mood"} contract is unchanged:
- nudge system prompt is Russian, feminine self-reference, with filled-in
examples on topics that never appear as rules, so copying them is visible
- rule names get a Russian gloss and a required keyword, named last in the
prompt where a small model weights it hardest
- durations render in Russian, not English
- the no-parse fallback says something Russian instead of "water — care",
which was going straight to a Russian piper voice
- same "..." placeholder removed from replier_llm.go
Scored on internal/phraser/eval: 0/15 -> 13/15.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
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
Daemon side of Decision B: parse {"response","mood"} across the 4 consumers
(replier, nudges, reminders, chat), fall back to legacy formats. Drop the
LLM router — the classifier handles routing; replier/phraser share one
llm.Client (timeout 20s->60s). llm.Client reads reasoning_content when
content is empty (thinking models).
Docs: TTS piper-student plan (OmniVoice teacher -> piper student, from
scratch, phoneme-first). CLAUDE.md training guide.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- 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.
- VoiceConfig: add QueryMinScore (default 0.55) + Persona config fields
- voice.go: remove queryMinScore const, wire from cfg.Voice.QueryMinScore
as reactiveHandler field
- llmphraser.go: add Persona to Config, prepend to system prompts in
chat and query paths (systemPrompt/querySystemPrompt methods)
- main.go: pass personaFromCfg into both phraser config blocks
- Makefile: add download-embedder target (Xenova/paraphrase-multilingual-
MiniLM-L12-v2, ~90MB ONNX)
- AGENTS.md: document embedder model download + libonnxruntime setup
- server.go: fix pre-existing wg.Add vs wg.Wait data race using accept
mutex. make test green, zero races across all 29 packages.
Task 4 created and tested router.KnowledgePrompt() but the live path in
LLMPhraser.PhraseQuery used a separate hardcoded copy of the same RU
anti-hallucination prompt, leaving KnowledgePrompt() as dead code and two
strings that could drift. Point the phraser at the tested helper so there
is a single source of truth.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- 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>
worker/server.go: dispatch now receives a per-connection context instead of
context.Background(), so handler cancellation propagates on conn close.
voice/server.go: same — per-conn context fed through safeDispatch into
HandlePushToTalk instead of context.Background().
store/reminders.go: propagate LastInsertId error.
store/nudges.go: propagate LastInsertId and RowsAffected errors.
store/tools.go: propagate RowsAffected error.
config/config.go: applyDefaults now respects StateDir when set, using it as
the base for empty DBPath/SocketPath instead of silently ignoring it.
phraser/llmphraser.go: close stderr pipe fd when cmd.Start() fails.
kami