omp-docs/core/dankvoice.md

@@ -83,16 +83,22 @@ saved sink. Thinking narration rides the same arming (`thinking: true`).
 
 ## Limits
 
-* Auto-speak narrates thinking and the final message only — mid-turn tool
-  chatter is never spoken; skipped in `print`/`json` modes so benches stay
-  silent.
+* Auto-speak narrates **each turn** — the assistant's prose and thinking while
+  the agent is still working — plus the settled final answer, spoken once. A
+  turn that lands while audio is still playing is dropped, not queued or
+  interrupting; tool-only turns stay silent; `print`/`json` modes never speak,
+  so benches stay quiet. Narration goes through the humanizer, so it lags its
+  turn by a rewrite round trip; `/say humanize off` removes the lag.
+* Arming is read at startup only — see **Arming auto-speak** above. A session
+  that never speaks is unarmed, not broken; `/say on` before debugging.
 * frank-tts deployment, voice packs and the registry are owned by the
   `serverAppConfigs` repo (`serverAppConfigs-docs/Dankclaw/Frank TTS.md`).
 
 ## Citations
 
 * Package repo `dank/dankvoice` (README, `docs/decisions/`) — behaviour and
-  knob truth.
+  knob truth. `docs/decisions/2026-10-19-turn-narration.md` records why
+  narration rides `turn_end` and not only `agent_end`.
 * Gitea issues #21, #23, #27, #32 (drop-in history) and #34 (this cutover)
   on `dank/command-center`.
 * Live endpoint probes 2026-10-18/19 documented in those issues.

omp-docs/log.md

@@ -20,10 +20,16 @@ on its concept page, linked here. Never re-expand an entry in place.
 
 Sessions spoke only on explicit `/say`: the settings file carried no `auto`
 key, and arming is session-scoped by design (`/say on` never persists). Set
-`"auto": true` in `~/.omp/cache/dankvoice.json`. Law: silence at session start
-is a config state — read `/say status` for `auto-speak on`, then watch
-`pgrep -a pw-play` for one player per segment, before blaming the endpoint.
-Details: [dankvoice](core/dankvoice.md).
+`"auto": true` in `~/.omp/cache/dankvoice.json`. Same report, second half:
+auto-speak listened only to `agent_end` — a settle that fires once per prompt
+and is skipped outright when the harness schedules a continuation — so nothing
+was narrated while an agent worked; fixed in dank/dankvoice#3, which narrates
+`turn_end` as well. Law: silence at session start is a config state — read
+`/say status` for `auto-speak on`, then watch `pgrep -a pw-play` for one player
+per segment, before blaming the endpoint. Law: whether the harness delivers an
+event to extensions is settled in minutes by a throwaway probe extension that
+timestamps `turn_end`/`agent_end` — never inferred from audio timing, which the
+humanizer lags by seconds. Details: [dankvoice](core/dankvoice.md).
 
 ## 2026-10-19 — LazyVim installed as an NVIM_APPNAME profile