docs: auto-speak narrates every turn, not only the final answer (Refs #36)

The Limits bullet still described the pre-fix behaviour ("thinking and the
final message only"), which dank/dankvoice#3 just retired: narration rides
`turn_end`, so the assistant's prose and thinking are spoken while the agent
works. Records the two rules an operator needs when audio seems missing —
arming is read at startup only, and a turn landing during playback is dropped
rather than queued — plus where the design rationale lives.

kb-lint 0 violations, index-coverage 0 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