Map gemma's speaker answer back to a present character

The dialogue prompt renders each present character as
`- person_1: brown ponytail, green dress (f)`, and gemma answers with what it was
shown: the description (15 lines), a bare local_id (9), a stale mark label (2),
or a name with the gender marker attached (2). All of them fell through
normalize_speaker as free-form names and never matched the registry, so 28 of 51
speech lines on job 778297bc lost a speaker the pipeline had already identified.
_apply_speaker_labels now resolves every string the prompt showed, drops an
id-shaped answer that names nobody present, and strips a trailing gender marker
so an off-panel name can still match.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

worker_vision.py

@@ -123,16 +123,59 @@ def _set_of_mark(local_path: str, present: list):
     return marked, "\n" + "\n".join(parts) + "\n", {f["label"]: f["local_id"] or "unknown" for f in faces}
 
 
-def _apply_speaker_labels(dialogue: list, label_map: dict) -> list:
-    """map a set-of-mark face label ("P1") in the speaker field back to its local_id. gemma may also
-    answer with the local_id directly (legend shows both) — that already matches, so it's left as-is."""
-    if not label_map:
-        return dialogue
+_GENDER_SUFFIX = re.compile(r"\s*\((?:m|f|male|female|man|woman|unknown)\)\s*$", re.I)
+_ID_SHAPED = re.compile(r"^(?:person|char|face|p)[\s_-]*\d+$", re.I)
+
+
+def _present_keys(present: list) -> dict:
+    """Every string the dialogue prompt shows for a present character, mapped to its local_id.
+
+    `build_dialogue_prompt` renders each one as `- person_1: brown ponytail, green dress (f)`, and gemma
+    answers with any part of that line, most often the description. Those answers used to fall through
+    `normalize_speaker` as free-form NAMES and never matched the registry, losing 28 of 51 speech lines
+    on job 778297bc. A key shared by two present characters is dropped: it cannot identify either."""
+    keys: dict = {}
+    for c in present:
+        lid = (c.get("local_id") or "").strip()
+        if not lid:
+            continue
+        name, desc, gender = c.get("name") or "", c.get("desc") or "", c.get("gender") or ""
+        shown = name or desc or "unknown"
+        forms = {lid, name, desc, shown}
+        if gender and gender != "unknown":
+            forms |= {f"{f} ({gender})" for f in (name, desc, shown) if f}
+        for f in forms:
+            k = f.strip().casefold()
+            if not k or k == "unknown":       # the prompt prints "unknown" for a nameless character
+                continue
+            keys[k] = lid if keys.get(k, lid) == lid else None   # ambiguous key -> unusable
+    return {k: v for k, v in keys.items() if v}
+
+
+def _apply_speaker_labels(dialogue: list, label_map: dict, present: list | None = None) -> list:
+    """Map gemma's speaker answer back to a panel-local id.
+
+    Three answer shapes reach here: a set-of-mark face label ("P1"), a local_id, and any string the
+    prompt showed for a present character. An id-shaped answer that names nobody present is junk and
+    becomes "unknown" rather than a name claim (invariant 6). A trailing gender marker is stripped, so
+    "Seonho (m)" can still match the registry name "Seonho" off-panel."""
+    keys = _present_keys(present or [])
     for d in dialogue:
         s = (d.get("speaker") or "").strip()
+        if not s:
+            continue
         if s in label_map:
             d["speaker"] = label_map[s]
             d["speaker_method"] = "som_face"
+            continue
+        bare = _GENDER_SUFFIX.sub("", s).strip()
+        lid = keys.get(s.casefold()) or keys.get(bare.casefold())
+        if lid:
+            d["speaker"] = lid
+        elif _ID_SHAPED.match(bare):
+            d["speaker"] = "unknown"          # an id for nobody present: never mint a name from it
+        elif bare != s:
+            d["speaker"] = bare               # off-panel name, gender marker stripped
     return dialogue
 
 
@@ -465,7 +508,7 @@ async def dialogue(data: DialogueInput):
     result.setdefault("entities", [])
     result.setdefault("named", [])   # [{local_id, name}] explicit namings -> bound to character_id by orchestrator
     result["named"] = _normalize_claims(result["named"], data.panel_id)
-    _apply_speaker_labels(result["dialogue"], label_map)
+    _apply_speaker_labels(result["dialogue"], label_map, data.present_characters)
     resolve_speakers(result["dialogue"], data.present_characters)
     result["panel_id"] = data.panel_id
     result.update(_dialogue_envelope([data.panel_id], [] if parse_failed else [result], parse_failed))
@@ -580,7 +623,7 @@ async def dialogue_window(data: DialogueWindowInput):
         d = by_id.get(pid)
         if d is None:                 # missing is unresolved, never manufactured as a silent success
             continue
-        _apply_speaker_labels(d.get("dialogue", []), label_maps.get(pid, {}))
+        _apply_speaker_labels(d.get("dialogue", []), label_maps.get(pid, {}), present_by_id.get(pid, []))
         out.append({
             "panel_id": pid,
             "dialogue": resolve_speakers(d.get("dialogue", []), present_by_id.get(pid, [])),
@@ -1001,6 +1044,20 @@ if __name__ == "__main__":
     lbl = _apply_speaker_labels([{"speaker": "P1"}, {"speaker": "Aria"}, {"speaker": "unknown"}],
                                 {"P1": "person_3"})
     assert lbl[0]["speaker"] == "person_3" and lbl[1]["speaker"] == "Aria" and lbl[2]["speaker"] == "unknown"
+    # gemma answers with what the prompt SHOWED, not the id: description, name+gender, bare id, junk id.
+    # Each shape cost real lines on job 778297bc by falling through as a free-form name.
+    shown = [{"local_id": "person_1", "desc": "brown ponytail, green dress", "gender": "f"},
+             {"local_id": "person_2", "name": "Seonho", "gender": "m"}]
+    got = _apply_speaker_labels([{"speaker": "brown ponytail, green dress (f)"}, {"speaker": "Seonho"},
+                                 {"speaker": "person_2"}, {"speaker": "person_9"},
+                                 {"speaker": "Haeseon (f)"}, {"speaker": "unknown"}], {}, shown)
+    assert [d["speaker"] for d in got] == ["person_1", "person_2", "person_2", "unknown",
+                                           "Haeseon", "unknown"], got
+    # a description shared by two present characters identifies neither
+    twins = [{"local_id": "person_1", "desc": "schoolgirl"}, {"local_id": "person_2", "desc": "schoolgirl"}]
+    assert _apply_speaker_labels([{"speaker": "schoolgirl"}], {}, twins)[0]["speaker"] == "schoolgirl"
+    # a nameless present character is shown as "unknown"; that must not become an id
+    assert _apply_speaker_labels([{"speaker": "unknown"}], {}, [{"local_id": "person_1"}])[0]["speaker"] == "unknown"
     # real detector face -> nearest present char's identity; each present char claimed once; leftover unknown
     pf = _pair_faces_to_present(
         [{"bbox": [10, 10, 50, 50]}, {"bbox": [200, 10, 240, 50]}, {"bbox": [400, 10, 440, 50]}],