fix(voice): hear "یادداشت" as a note request, and stop the note at the next instruction

Two reports from live dictation in fa.

The locale trigger vocabulary listed only verbs that ask for a note ("بنویس",
"یادداشت کن"). Naming the field itself — "توی یادداشت‌ها بنویس", "در توضیحات" —
reported no commentTrigger, and the resolver discards a comment without one, so
the note was silently dropped. Added the field-name shape to fa, en and nl.

Where the dictated note ends was never stated, so the model answered it
inconsistently: "توی توضیحات بنویس سلام چطوری و بفرست برای لابراتوآر سانشاین"
sometimes put the lab dispatch inside the comment. Added a no-overlap rule — a
clause reported as a lab, tooth, prosthesis or deadline is an instruction and
must not appear in comment as well — with that sentence as a worked example.

Both rules go in the prompt and in the JSON-schema field descriptions, because
the schema description is what the model reads while filling the field. No code
enforcement for the second: stripping an extracted clause out of free-speech
note text by string matching is guesswork, and the review sheet shows the note
before it is saved.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

docs/specs/voice-treatment-entry/progress.md

@@ -524,6 +524,32 @@ step — only build and deploy. Combined with `nest build` excluding `**/*spec.t
 running transpile-only under `isolatedModules`, nothing in this repo would ever catch a type error
 in a spec file. That is how two of them reached this branch unnoticed.
 
+## 2026-09-11 — note triggers and where a note ends (dyolink)
+
+Two reports from live dictation in `fa`, both prompt-side, no resolver change.
+
+1. «یادداشت» / «یادداشت‌ها» produced no trigger, so the note was discarded. The locale notes
+   listed only verbs that ask («بنویس», «یادداشت کن»); naming the field itself was not in the
+   vocabulary. Added the field-name shape for all three locales — fa «یادداشت/یادداشت‌ها/توضیحات/
+   کامنت», en "note/notes/comments/remarks", nl "notitie/notities/opmerkingen".
+2. The note swallowed the next instruction. For «توی توضیحات بنویس سلام چطوری و بفرست برای
+   لابراتوآر سانشاین» the model sometimes put the whole tail in `comment`, sometimes only
+   «سلام چطوری». Added a no-overlap invariant: a clause reported as a lab, tooth, prosthesis or
+   deadline is an instruction and must not also appear in `comment`, plus that exact sentence as
+   a worked example.
+
+Both rules are stated twice on purpose — in `extraction.prompt.ts` and in the `comment` /
+`commentTrigger` descriptions in `extraction.wire.ts`, since the schema description is what the
+model reads while filling the field.
+
+No code enforcement for (2). Stripping an extracted clause out of free-speech note text by string
+matching is guesswork, and the review sheet shows the note before it is saved.
+
+Files: `backend/src/modules/voice/extraction.prompt.ts`,
+`backend/src/modules/voice/extraction.wire.ts`, `docs/specs/voice-treatment-entry/spec.md`.
+Verified: `npx eslint src/modules/voice/**/*.ts` clean, `npm test -- extraction` 74/74.
+No unit test — both are prompt text, which the extraction specs deliberately do not assert on.
+
 ## Remaining before this is shippable
 
 - The **manual pass in §12** — none of it has been run. Safari and iPad especially, since that is

docs/specs/voice-treatment-entry/spec.md

@@ -535,7 +535,21 @@ what was captured, so nothing is hidden by leaving it out.
 
 Per-locale trigger vocabulary lives in the prompt's locale notes, exactly like the tooth
 vocabulary. The resolver only checks that a trigger was reported, so it needs no per-locale
-knowledge and stays locale-neutral by construction (§6).
+knowledge and stays locale-neutral by construction (§6). The vocabulary covers two shapes: a
+verb that asks («بنویس که», "noteer") and the *name of the field* the words go into («یادداشت»,
+«یادداشت‌ها», «توضیحات», "notes", "comments"). Naming the field is how a clinician usually asks,
+and the first version listed only the verbs, so «توی یادداشت‌ها بنویس» produced no trigger and
+the note was discarded.
+
+Where the dictated note ends is a second question, and the model answered it inconsistently: for
+«توی توضیحات بنویس سلام چطوری و بفرست برای لابراتوآر سانشاین» the note sometimes ran to the end
+of the sentence and swallowed the lab dispatch. The rule is that the note ends where the next
+instruction begins, stated as a no-overlap invariant: a clause reported as a lab, a tooth, a
+prosthesis or a deadline is that instruction and must not also appear in `comment`. It lives in
+both the prompt and the JSON-schema field description, because the schema description is what the
+model reads while it fills the field. This is a prompt-side rule with no code enforcement —
+stripping an already-extracted clause out of the note text by string matching would be guesswork
+on free speech, and the review sheet shows the note before it is saved.
 
 ### Prosthesis work implies the treatment type