Updated documentation

AGENTS.md

@@ -93,7 +93,7 @@ publish-only.
 
 ## Testing
 
-- `tests/` has 838 tests, all hardware- and network-free. Preserve that: inject fakes instead of
+- `tests/` has 1028 tests, all hardware- and network-free. Preserve that: inject fakes instead of
   touching real `pactl`, audio devices, an LLM, or `sherpa_onnx` (the speaker lane uses a fake
   embedder; no ONNX in tests).
 - Key seams: `Daemon(...)` accepts `capture_factory`, `vad_factory`, `transcriber_factory`,

docs/ASSISTANT.md

@@ -51,7 +51,7 @@ Set `[llm].enabled = false` to run without an LLM (commands then report
 | `idle` | listening; nothing is sent to the model |
 | `command_armed` | the next complete turn becomes a command; the text accumulates live |
 | `executing` | a command is running through the tool loop |
-| `chat` | every completed spoken turn is sent to the model; no tools |
+| `chat` | completed turns go to the model — spoken only when `send transcripts` is on, typed `chat-send` always; no tools |
 
 Command and chat modes are mutually exclusive.
 

docs/DEVELOPMENT.md

@@ -19,7 +19,7 @@ Tests cover:
 - **Config loading and language normalization**
 - **Provisioning**: `setup`/`ensure`/`teardown`, orphan-name cleanup, and `clear` idempotency
 - **Event bus**: envelope codec, ring replay, subscriber fan-out
-- **Assistant**: mode machine, command readiness/timeouts, tool schema validation, LLM client/history trimming, audit log
+- **Assistant**: mode machine, command readiness/timeouts, tool schema validation, LLM client/history trimming, audit log, and the `chat_capture`/`triage_chat` capture gating
 - **Triage & brief**: Laya lane, questions-file validation, signal normalization, the fail-open `substantive_update` gate, the periodic `periodic_s` accumulating-speech trigger, single-outstanding `brief-update` coalescing, the code-owned append-only `FactLedger` (dedupe/eviction/render), the stateless brief engine, and the durable brief file
 - **Speakers**: prototype matching, mint/confirm/adapt guards, daemon wiring, assistant roster and naming, offline pre-enrollment (`tests/test_speaker_enroll.py`)
 - **Debug**: `DebugSink` JSONL lines, disabled-means-None, emit-throw safety, per-day byte cap, concurrent-emit integrity (`tests/test_debug.py`); assistant lock-free emits via `debug_sink_factory` (`tests/test_assistant_service.py`)
@@ -71,7 +71,7 @@ src/stt_daemon/
     ├── client.py        - Control-socket client
     └── app.py           - Textual app + `stt-tui` entry point
 
-tests/                    - 838 tests, no audio hardware or live LLM required
+tests/                    - 1028 tests, no audio hardware or live LLM required
 
 scripts/
 ├── audio-sink.sh        - Thin wrapper over `stt-daemon setup|clear|list`

docs/TRIAGE.md

@@ -1,8 +1,9 @@
 # Triage Panel
 
 The triage panel is a display-only signal readout in the assistant TUI. On each settled
-turn (no chat mode required) the assistant classifies the most recent transcribed
-utterances with a local Laya **multilingual** model running in-process, then folds the turn
+turn (no chat mode required) — and on each chat turn when the `send to triage` toggle is on —
+the assistant classifies the most recent utterances (transcribed speech, plus labeled chat
+turns when enabled) with a local Laya **multilingual** model running in-process, then folds the turn
 into a living plain-text brief on the existing `[llm]` lane through a dedicated brief
 conversation. Signals and brief land in a right-hand pane. Nothing here triggers a mode, a
 command, or a tool: the panel only shows what the model inferred.
@@ -43,8 +44,9 @@ disk, and it is a no-op when `[triage].enabled = false`.
 ## How the brief works
 
 ```
-settled turn (any mode), or every periodic_s while speech keeps accumulating
-    -> newest transcribed-utterance window (window entries, condensed under state_char_budget)
+settled turn (any mode), every periodic_s while speech keeps accumulating, or a chat turn
+    -> newest utterance window (window entries, condensed under state_char_budget;
+       transcribed speech, plus labeled chat turns when send-to-triage is on)
     -> Laya multilingual classification (in-process lane)
     -> signals (emitted; flagged per should_escalate)
     -> extract_enabled and the fail-open gate pass?
@@ -62,9 +64,13 @@ settled turn (any mode), or every periodic_s while speech keeps accumulating
    arriving: the timer arms on the first transcript of a burst and re-arms on every accepted
    submit, so a long monologue is classified roughly every `periodic_s` instead of only when
    it stops. Set `periodic_s = 0` to disable the periodic trigger and require a settled turn.
-   A repeated window is skipped, so an identical set of utterances never re-gates.
-2. **Window.** The window is the newest `window` transcribed utterances from the STT
-   stream, not the chat conversation history. `build_state` condenses it newest-first
+   A repeated window is skipped, so an identical set of utterances never re-gates. When the
+   TUI's `send to triage` toggle is on (see [ASSISTANT.md](ASSISTANT.md)), each chat turn also
+   forces a pass through the same guards; the assistant reply is appended, plus the user's
+   message when `send transcripts` is off.
+2. **Window.** The window is the newest `window` entries: transcribed utterances from the STT
+   stream, plus labeled chat turns (`You:`/`Assistant:`) when `send to triage` is on — never
+   the raw chat conversation history. `build_state` condenses it newest-first
    under `state_char_budget` and restores chronological order, with `- ` prefixed lines.
 3. **Classification.** The condensed state, the loaded questions, the last transcript
    language, and the current triage generation go to the Laya lane. The lane runs one
@@ -80,8 +86,9 @@ settled turn (any mode), or every periodic_s while speech keeps accumulating
    Escalation only drives the per-item `flagged` flag and the `⚠` marker in the panel;
    it drives neither the gate nor the brief.
 5. **Brief update (code-owned ledger).** The service queues **one** `brief-update` job on
-   the existing LLM lane. The job carries the speaker-labeled pending deltas (the transcripts
-   that arrived since the last accepted update) plus the current signal words under a `Focus:`
+   the existing LLM lane. The job carries the speaker-labeled pending deltas (the transcripts,
+   plus labeled chat turns when `send to triage` is on, that arrived since the last accepted
+   update) plus the current signal words under a `Focus:`
    header; a Laya error still runs with the deltas only. The brief engine is **stateless**: it
    sends exactly two messages per call — a static system prompt and ONE user turn containing
    `CURRENT LEDGER` (the recorded facts), `CURRENT BRIEF` (the volatile narrative), and
@@ -286,7 +293,7 @@ file.
 |---|---|---|
 | `enabled` | `false` | Master gate. `false` means no lane, no panel, and behavior identical to before. |
 | `questions_file` | `"questions.json"` | Laya questions JSON in the working directory. Missing or invalid means `no_questions`. |
-| `window` | `500` | Recent transcribed utterances available per classification; the char budget is the real limiter. |
+| `window` | `500` | Recent utterance entries available per classification (transcripts, plus labeled chat turns when send-to-triage is on); the char budget is the real limiter. |
 | `state_char_budget` | `3000` | Character cap (~750 tokens) for the condensed state sent to Laya. |
 | `periodic_s` | `30.0` | Accumulating-speech cadence in seconds: while new utterances keep arriving without a settled turn, triage re-runs every `periodic_s`; `<= 0` disables the periodic trigger. |
 | `predict_max_tokens` | `1024` | Max tokens sent to Laya; the multilingual checkpoint supports 1024; state shares this budget with the ~192-token question head (~830-token state room). |