diff --git a/backend/detect_learning.py b/backend/detect_learning.py
index 20f392d..dc36776 100644
--- a/backend/detect_learning.py
+++ b/backend/detect_learning.py
@@ -22,6 +22,8 @@ WINDOW = 80
_DECISION_IDENTITY = "identity"
_DECISION_NOT = "not_identity"
+_DECISION_ASK = "ask"
+_CUE_BARE = "_bare"
def get_detect_operating_mode() -> str:
@@ -136,31 +138,82 @@ def _in_user_text(label: str, user_body: str) -> bool:
)
-def _excerpt(user_body: str, start: int | None, end: int | None, label: str) -> str:
+def _resolve_user_span(
+ user_body: str,
+ start: int | None,
+ end: int | None,
+ label: str,
+ rendered: str = "",
+) -> tuple[int, int] | None:
text = user_body or ""
- if start is None or end is None or start < 0 or end > len(text):
- match = re.search(rf"(?= 0:
+ user_left, user_right = left - origin, right - origin
+ if 0 <= user_left < user_right <= len(text) and text[user_left:user_right].casefold() == needle:
+ return user_left, user_right
+ if not needle:
+ return None
+ match = re.search(rf"(? bool:
+def excerpt_view(
+ user_body: str,
+ start: int | None,
+ end: int | None,
+ label: str,
+ rendered: str = "",
+) -> dict:
+ text = user_body or ""
+ span = _resolve_user_span(text, start, end, label, rendered)
+ if not span:
+ snippet = text[:WINDOW]
+ return {"excerpt": snippet, "highlight_start": None, "highlight_end": None}
+ left_i, right_i = span
+ clip_left = max(0, left_i - WINDOW)
+ clip_right = min(len(text), right_i + WINDOW)
+ prefix = "…" if clip_left > 0 else ""
+ suffix = "…" if clip_right < len(text) else ""
+ snippet = text[clip_left:clip_right]
+ return {
+ "excerpt": f"{prefix}{snippet}{suffix}",
+ "highlight_start": left_i - clip_left + len(prefix),
+ "highlight_end": right_i - clip_left + len(prefix),
+ }
+
+
+def _excerpt(user_body: str, start: int | None, end: int | None, label: str) -> str:
+ return excerpt_view(user_body, start, end, label)["excerpt"]
+
+
+def needs_review(profile_id: str, mapping: dict, user_body: str, rendered: str = "") -> bool:
label = mapping.get("local_label") or ""
if mapping.get("source") == "confirmed_registry":
- sense = get_sense(profile_id, label)
- return bool(sense["ambiguous"]) and _in_user_text(label, user_body)
+ return (
+ _in_user_text(label, user_body)
+ and decision_for_mention(
+ profile_id, label, user_body, mapping.get("start"), mapping.get("end"), rendered
+ )
+ == _DECISION_ASK
+ )
if mapping.get("source") != "request_local":
return False
if not is_maskable_label(label) or not _in_user_text(label, user_body):
return False
- sense = get_sense(profile_id, label)
- if sense["identity_hits"] > 0 and not sense["ambiguous"]:
- return False
- return True
+ return (
+ decision_for_mention(
+ profile_id, label, user_body, mapping.get("start"), mapping.get("end"), rendered
+ )
+ == _DECISION_ASK
+ )
def _word_matches(text: str):
@@ -172,6 +225,143 @@ def _prev_word(text: str, index: int) -> str:
return (words[-1].lower() if words else "")
+def cue_for_mention(
+ user_body: str,
+ start: int | None,
+ end: int | None,
+ label: str,
+ rendered: str = "",
+) -> str:
+ span = _resolve_user_span(user_body, start, end, label, rendered)
+ if not span:
+ return _CUE_BARE
+ return _prev_word(user_body, span[0]) or _CUE_BARE
+
+
+def _mention_fields(
+ user_body: str,
+ start: int | None,
+ end: int | None,
+ label: str,
+ rendered: str = "",
+) -> dict:
+ span = _resolve_user_span(user_body, start, end, label, rendered)
+ return {
+ **excerpt_view(user_body, start, end, label, rendered),
+ "user_start": span[0] if span else None,
+ "user_end": span[1] if span else None,
+ "cue": (_prev_word(user_body, span[0]) or _CUE_BARE) if span else _CUE_BARE,
+ }
+
+
+def get_cue_decision(profile_id: str, label: str, cue: str) -> str | None:
+ key = normalize_label(label) or (label or "").strip()
+ token = (cue or _CUE_BARE).strip().casefold() or _CUE_BARE
+ if not key:
+ return None
+ with get_db() as conn:
+ row = row_to_dict(
+ conn.execute(
+ """
+ SELECT decision FROM label_sense_cues
+ WHERE profile_id = ? AND lower(normalized_label) = lower(?) AND cue = ?
+ """,
+ (profile_id, key, token),
+ ).fetchone()
+ )
+ value = ((row or {}).get("decision") or "").strip()
+ return value if value in {_DECISION_IDENTITY, _DECISION_NOT} else None
+
+
+def record_cue(profile_id: str, label: str, cue: str, decision: str) -> None:
+ key = normalize_label(label) or (label or "").strip()
+ token = (cue or _CUE_BARE).strip().casefold() or _CUE_BARE
+ if not key or decision not in {_DECISION_IDENTITY, _DECISION_NOT}:
+ return
+ with get_db() as conn:
+ conn.execute(
+ """
+ INSERT INTO label_sense_cues (
+ profile_id, normalized_label, cue, decision, hits, updated
+ )
+ VALUES (?, ?, ?, ?, 1, datetime('now'))
+ ON CONFLICT(profile_id, normalized_label, cue) DO UPDATE SET
+ decision = excluded.decision,
+ hits = label_sense_cues.hits + 1,
+ updated = datetime('now')
+ """,
+ (profile_id, key, token, decision),
+ )
+
+
+def decision_for_mention(
+ profile_id: str,
+ label: str,
+ user_body: str,
+ start: int | None,
+ end: int | None,
+ rendered: str = "",
+) -> str:
+ """identity / not_identity from prior review, or ask once for a new cue."""
+ if not label:
+ return _DECISION_ASK
+ cue = cue_for_mention(user_body, start, end, label, rendered)
+ learned = get_cue_decision(profile_id, label, cue)
+ if learned:
+ return learned
+ sense = get_sense(profile_id, label)
+ identity_shaped = cue in KINSHIP
+ if sense["ambiguous"]:
+ return _DECISION_ASK
+ if sense["identity_hits"] > 0 and not sense["non_identity_hits"]:
+ return _DECISION_IDENTITY
+ if sense["non_identity_hits"] > 0 and not sense["identity_hits"]:
+ return _DECISION_ASK if identity_shaped else _DECISION_NOT
+ return _DECISION_ASK
+
+
+def apply_learned_decisions(
+ profile_id: str,
+ candidates: list[dict],
+ mappings: list[dict],
+ user_body: str,
+ rendered: str = "",
+) -> tuple[list[dict], list[dict]]:
+ remaining = []
+ for item in candidates:
+ verdict = decision_for_mention(
+ profile_id,
+ item.get("text") or "",
+ user_body,
+ item.get("user_start", item.get("start")),
+ item.get("user_end", item.get("end")),
+ rendered,
+ )
+ if verdict == _DECISION_ASK:
+ remaining.append(item)
+ kept = []
+ for mapping in mappings:
+ label = mapping.get("local_label") or ""
+ verdict = decision_for_mention(
+ profile_id,
+ label,
+ user_body,
+ mapping.get("start"),
+ mapping.get("end"),
+ rendered,
+ )
+ if verdict == _DECISION_NOT:
+ continue
+ kept.append(mapping)
+ if verdict == _DECISION_IDENTITY:
+ kind = mapping.get("entity_type") if mapping.get("entity_type") in ENTITY_TYPES else "PERSON"
+ try:
+ confirm_identity(profile_id, label, entity_type=kind)
+ except ValueError:
+ continue
+ return remaining, kept
+
+
def kinship_governed_labels(user_body: str) -> set[str]:
"""Labels after Frau/Sohn/… in the current user line. Not a food word list."""
found: set[str] = set()
@@ -214,15 +404,15 @@ def supplement_kinship_candidates(
return candidates, mappings
occupied: set[tuple[int, int, str]] = set()
for item in candidates:
- label = (item.get("text") or "").casefold()
- excerpt = item.get("excerpt") or ""
- for match in _word_matches(user_body):
- if match.group(0).casefold() != label:
- continue
- snippet = _excerpt(user_body, match.start(), match.end(), match.group(0))
- if snippet == excerpt or match.group(0) in excerpt:
- occupied.add((match.start(), match.end(), label))
- break
+ span = _resolve_user_span(
+ user_body,
+ item.get("start"),
+ item.get("end"),
+ item.get("text") or "",
+ rendered,
+ )
+ if span:
+ occupied.add((span[0], span[1], (item.get("text") or "").casefold()))
extra_mappings = list(mappings)
extra_candidates = list(candidates)
for match in _word_matches(user_body):
@@ -232,6 +422,11 @@ def supplement_kinship_candidates(
user_key = (match.start(), match.end(), label.casefold())
if user_key in occupied:
continue
+ if (
+ decision_for_mention(profile_id, label, user_body, match.start(), match.end(), rendered)
+ != _DECISION_ASK
+ ):
+ continue
occupied.add(user_key)
start, end = _align_user_span(rendered, user_body, match.start(), match.end())
identity_shaped = _prev_word(user_body, match.start()) in KINSHIP
@@ -242,7 +437,7 @@ def supplement_kinship_candidates(
"entity_type": "PERSON",
"start": start,
"end": end,
- "excerpt": _excerpt(user_body, match.start(), match.end(), label),
+ **_mention_fields(user_body, match.start(), match.end(), label, rendered),
"ambiguous": get_sense(profile_id, label)["ambiguous"],
"suggested": _DECISION_IDENTITY if identity_shaped else _DECISION_NOT,
}
@@ -264,11 +459,11 @@ def supplement_kinship_candidates(
return extra_candidates, extra_mappings
-def build_candidates(profile_id: str, mappings: list[dict], user_body: str) -> list[dict]:
+def build_candidates(profile_id: str, mappings: list[dict], user_body: str, rendered: str = "") -> list[dict]:
seen: set[tuple[int | None, int | None, str]] = set()
items: list[dict] = []
for mapping in mappings:
- if not needs_review(profile_id, mapping, user_body):
+ if not needs_review(profile_id, mapping, user_body, rendered):
continue
label = mapping.get("local_label") or ""
start = mapping.get("start")
@@ -284,7 +479,7 @@ def build_candidates(profile_id: str, mappings: list[dict], user_body: str) -> l
"entity_type": mapping.get("entity_type") or "PERSON",
"start": start,
"end": end,
- "excerpt": _excerpt(user_body, start, end, label),
+ **_mention_fields(user_body, start, end, label, rendered),
"ambiguous": get_sense(profile_id, label)["ambiguous"],
}
)
@@ -369,11 +564,19 @@ def apply_review_decisions(profile_id: str, pending: dict, decisions: list[dict]
decision = (raw.get("decision") or "").strip()
label = candidate.get("text") or ""
kind = candidate.get("entity_type") if candidate.get("entity_type") in ENTITY_TYPES else "PERSON"
+ cue = candidate.get("cue") or cue_for_mention(
+ pending.get("user_body") or "",
+ candidate.get("user_start", candidate.get("start")),
+ candidate.get("user_end", candidate.get("end")),
+ label,
+ )
if decision == _DECISION_IDENTITY:
record_sense(profile_id, label, identity=True)
+ record_cue(profile_id, label, cue, _DECISION_IDENTITY)
confirm_identity(profile_id, label, entity_type=kind)
elif decision == _DECISION_NOT:
record_sense(profile_id, label, identity=False)
+ record_cue(profile_id, label, cue, _DECISION_NOT)
drop_keys.add((candidate.get("start"), candidate.get("end"), label.casefold()))
mappings = []
for mapping in pending.get("mappings") or []:
@@ -459,9 +662,11 @@ def auto_resolve_ambiguous(profile_id: str, candidates: list[dict], mappings: li
decision = try_local_passage_decision(item.get("excerpt") or "", label)
if decision == _DECISION_NOT:
record_sense(profile_id, label, identity=False)
+ record_cue(profile_id, label, item.get("cue") or _CUE_BARE, _DECISION_NOT)
drop_keys.add((item.get("start"), item.get("end"), label.casefold()))
elif decision == _DECISION_IDENTITY:
record_sense(profile_id, label, identity=True)
+ record_cue(profile_id, label, item.get("cue") or _CUE_BARE, _DECISION_IDENTITY)
else:
remaining.append(item)
if not drop_keys:
diff --git a/backend/dialogue_turn.py b/backend/dialogue_turn.py
index 4a7cfaf..9f3a2d4 100644
--- a/backend/dialogue_turn.py
+++ b/backend/dialogue_turn.py
@@ -9,6 +9,7 @@ from conversation_signals import infer_signals
from debug_store import persist_engine_error, persist_step
from detect_learning import (
MODE_LEARNING,
+ apply_learned_decisions,
apply_review_decisions,
auto_resolve_ambiguous,
build_candidates,
@@ -439,10 +440,13 @@ def _learning_pause(profile_id: str, conversation_id: str, user: dict, assembled
return None
user_body = user.get("body") or ""
mappings = list(outcome.mappings or [])
- candidates = build_candidates(profile_id, mappings, user_body)
+ candidates = build_candidates(profile_id, mappings, user_body, rendered)
candidates, mappings = supplement_kinship_candidates(
profile_id, candidates, mappings, user_body, rendered
)
+ candidates, mappings = apply_learned_decisions(
+ profile_id, candidates, mappings, user_body, rendered
+ )
candidates, mappings = auto_resolve_ambiguous(profile_id, candidates, mappings)
if not candidates:
confirm_known_identity_spans(profile_id, mappings, user_body)
diff --git a/backend/migrations/025_label_sense_cues.sql b/backend/migrations/025_label_sense_cues.sql
new file mode 100644
index 0000000..d65d258
--- /dev/null
+++ b/backend/migrations/025_label_sense_cues.sql
@@ -0,0 +1,12 @@
+-- Remember mask-review decisions per local context cue (previous word).
+-- Not a word list: cues come from the user line, e.g. Frau vs. a food mention.
+
+CREATE TABLE IF NOT EXISTS label_sense_cues (
+ profile_id TEXT NOT NULL REFERENCES profiles(id) ON DELETE CASCADE,
+ normalized_label TEXT NOT NULL,
+ cue TEXT NOT NULL,
+ decision TEXT NOT NULL,
+ hits INTEGER NOT NULL DEFAULT 1,
+ updated TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP::text,
+ PRIMARY KEY (profile_id, normalized_label, cue)
+);
diff --git a/backend/schema.sql b/backend/schema.sql
index c330e15..a873de5 100644
--- a/backend/schema.sql
+++ b/backend/schema.sql
@@ -239,6 +239,16 @@ CREATE TABLE IF NOT EXISTS label_senses (
PRIMARY KEY (profile_id, normalized_label)
);
+CREATE TABLE IF NOT EXISTS label_sense_cues (
+ profile_id TEXT NOT NULL REFERENCES profiles(id) ON DELETE CASCADE,
+ normalized_label TEXT NOT NULL,
+ cue TEXT NOT NULL,
+ decision TEXT NOT NULL,
+ hits INTEGER NOT NULL DEFAULT 1,
+ updated TEXT NOT NULL DEFAULT (datetime('now')),
+ PRIMARY KEY (profile_id, normalized_label, cue)
+);
+
CREATE TABLE IF NOT EXISTS pending_mask_reviews (
id TEXT PRIMARY KEY,
profile_id TEXT NOT NULL REFERENCES profiles(id) ON DELETE CASCADE,
diff --git a/backend/sqlite_to_postgres.py b/backend/sqlite_to_postgres.py
index d8128a2..acf9349 100644
--- a/backend/sqlite_to_postgres.py
+++ b/backend/sqlite_to_postgres.py
@@ -44,6 +44,7 @@ TABLES = [
"identity_mappings",
"identity_review_proposals",
"label_senses",
+ "label_sense_cues",
"pending_mask_reviews",
"journal_days",
"journal_drafts",
diff --git a/backend/tests/test_detect_learning.py b/backend/tests/test_detect_learning.py
index 2775427..9037c3e 100644
--- a/backend/tests/test_detect_learning.py
+++ b/backend/tests/test_detect_learning.py
@@ -16,7 +16,13 @@ os.environ["KANSHO_FAKE_PROVIDER"] = "1"
os.environ["KANSHO_FAKE_DETECT"] = "1"
from fastapi.testclient import TestClient
-from detect_learning import get_detect_operating_mode, get_sense, record_sense
+from detect_learning import (
+ excerpt_view,
+ get_cue_decision,
+ get_detect_operating_mode,
+ get_sense,
+ record_sense,
+)
from dialogue_turn import visible_for_role
from identity_store import list_confirmed_identities
from main import app
@@ -161,6 +167,13 @@ def main() -> None:
status_ok(declined, "not_identity review")
expect(not any((item.get("canonical_label") or "").casefold() == "hanna" for item in list_confirmed_identities(profile_id)), "not_identity does not confirm Hanna")
expect(get_sense(profile_id, "Hanna")["non_identity_hits"] >= 1, "not_identity records a sense")
+ hanna_again = client.post(
+ f"/api/journal/conversations/{food_conv}/turn",
+ headers=headers,
+ json={"body": "Hanna aß mit uns."},
+ )
+ status_ok(hanna_again, "second Hanna turn")
+ expect(not hanna_again.json().get("pending_mask_review"), "known non-identity skips the popup")
record_sense(profile_id, "Clarissa", identity=True)
record_sense(profile_id, "Clarissa", identity=False)
@@ -180,12 +193,30 @@ def main() -> None:
kin = client.post(
f"/api/journal/conversations/{kin_conv}/turn",
headers=headers,
- json={"body": "Ich war mit meinem Sohn Rohan im Park."},
+ json={"body": "Ich war mit meinem Sohn Leon im Park."},
)
- status_ok(kin, "kinship Rohan pause")
+ status_ok(kin, "kinship Leon pause")
kin_review = kin.json().get("pending_mask_review") or {}
kin_names = [item.get("text") for item in kin_review.get("candidates") or []]
- expect("Rohan" in kin_names, "Sohn Rohan is offered even when Detect does not report it")
+ expect("Leon" in kin_names, "Sohn Leon is offered even when Detect does not report it")
+ leon = next((item for item in kin_review.get("candidates") or [] if item.get("text") == "Leon"), None)
+ expect(leon is not None, "Leon candidate id is present")
+ kin_done = client.post(
+ f"/api/journal/conversations/{kin_conv}/turn/review",
+ headers=headers,
+ json={
+ "review_id": kin_review["id"],
+ "decisions": [{"id": leon["id"], "decision": "identity"}],
+ },
+ )
+ status_ok(kin_done, "Leon identity review")
+ kin_again = client.post(
+ f"/api/journal/conversations/{kin_conv}/turn",
+ headers=headers,
+ json={"body": "Ich war mit meinem Sohn Leon im Park."},
+ )
+ status_ok(kin_again, "second Leon turn")
+ expect(not kin_again.json().get("pending_mask_review"), "confirmed Sohn Leon skips the popup")
sushi_conv = open_conv(client, headers)
sushi = client.post(
@@ -203,6 +234,73 @@ def main() -> None:
expect("Rohan" in sushi_names, "Rohan from Sohn is a candidate")
expect("Sushi" in sushi_names, "Sushi from Frau is a candidate")
expect("Restaurant" not in sushi_names, "plain Restaurant is not kinship-offered")
+ sushi_hits = [
+ item
+ for item in (sushi.json().get("pending_mask_review") or {}).get("candidates") or []
+ if item.get("text") == "Sushi"
+ ]
+ expect(len(sushi_hits) >= 2, "both Sushi mentions are offered")
+ expect(
+ sushi_hits[0].get("highlight_start") != sushi_hits[1].get("highlight_start"),
+ "the two Sushi mentions highlight different offsets",
+ )
+ for item in sushi_hits:
+ excerpt = item.get("excerpt") or ""
+ start = item.get("highlight_start")
+ end = item.get("highlight_end")
+ expect(excerpt[start:end] == "Sushi", "highlight covers the Sushi token")
+
+ homonym = (
+ "Gestern bin ich mit meiner Frau Sushi und meinem Sohn Rohan "
+ "Sushi essen gegangen."
+ )
+ first_at = homonym.index("Sushi")
+ second_at = homonym.rindex("Sushi")
+ first = excerpt_view(homonym, first_at, first_at + 5, "Sushi")
+ second = excerpt_view(homonym, second_at, second_at + 5, "Sushi")
+ expect(first["highlight_start"] < second["highlight_start"], "person Sushi sits left of dish Sushi")
+ expect(first["excerpt"][first["highlight_start"]:first["highlight_end"]] == "Sushi", "first highlight is Sushi")
+ expect(second["excerpt"][second["highlight_start"]:second["highlight_end"]] == "Sushi", "second highlight is Sushi")
+ prefix = "SYSTEM\n"
+ mapped = excerpt_view(
+ homonym,
+ len(prefix) + second_at,
+ len(prefix) + second_at + 5,
+ "Sushi",
+ prefix + homonym,
+ )
+ expect(mapped["highlight_start"] == second["highlight_start"], "rendered detect offsets map to the dish Sushi")
+
+ sushi_review = sushi.json().get("pending_mask_review") or {}
+ sushi_decisions = []
+ for item in sushi_review.get("candidates") or []:
+ label = item.get("text")
+ cue = item.get("cue")
+ if label == "Sushi" and cue != "frau":
+ sushi_decisions.append({"id": item["id"], "decision": "not_identity"})
+ else:
+ sushi_decisions.append({"id": item["id"], "decision": "identity"})
+ sushi_done = client.post(
+ f"/api/journal/conversations/{sushi_conv}/turn/review",
+ headers=headers,
+ json={"review_id": sushi_review["id"], "decisions": sushi_decisions},
+ )
+ status_ok(sushi_done, "homonym review")
+ expect(get_cue_decision(profile_id, "Sushi", "frau") == "identity", "Frau Sushi is stored as identity")
+ expect(get_cue_decision(profile_id, "Sushi", "rohan") == "not_identity", "dish Sushi after Rohan is stored")
+ expect(get_cue_decision(profile_id, "Rohan", "sohn") == "identity", "Sohn Rohan cue is stored")
+ sushi_again = client.post(
+ f"/api/journal/conversations/{sushi_conv}/turn",
+ headers=headers,
+ json={
+ "body": (
+ "Gestern bin ich mit meiner Frau Sushi und meinem Sohn Rohan "
+ "Sushi essen gegangen. Das Restaurant hat mich dabei total beeindruckt."
+ )
+ },
+ )
+ status_ok(sushi_again, "repeat homonym sentence")
+ expect(not sushi_again.json().get("pending_mask_review"), "same reviewed sentence does not re-ask")
back = client.put("/api/admin/providers/detect-mode", headers=headers, json={"mode": "semantic"})
expect(back.json()["detect_operating_mode"] == "semantic", "mode can return to semantic")
diff --git a/docs/architecture/functional/guardrails.md b/docs/architecture/functional/guardrails.md
index 5d3380a..9602abb 100644
--- a/docs/architecture/functional/guardrails.md
+++ b/docs/architecture/functional/guardrails.md
@@ -719,6 +719,8 @@ Additiv. Technische Abbildung: `../technical/privacy_gateway.md` §9.7.
**Entschieden (Übergang):** Eine Mini-Passage an ein internes Modell geht nur bei bereits mehrdeutiger Schreibweise und nur an ein lokales Detect. OpenRouter sieht diese Passage nicht. Fehlt das lokale Modell, bleibt das Popup.
+**Additiv 2026-09-10:** Eine bestätigte Nennung wird nicht erneut gefragt, wenn derselbe lokale Kontext wiederkehrt (vorheriges Wort, z. B. `Frau` gegenüber einer Speisenennung). Das ist kein Wortlisten-Editor. Unbekannte Kontexte derselben Schreibweise bleiben prüfpflichtig. Reines Zählen von Identität/nicht-schützenswert ohne diese Anwendung ist kein Lernen.
+
**Nicht:** Gateway abschalten, Detect-Treffer auto-speichern, `Sushi_`/`Sushi+` im Nutzertext, Pattern-Wortliste als Wahrheit.
---
diff --git a/docs/architecture/technical/privacy_gateway.md b/docs/architecture/technical/privacy_gateway.md
index eca0d50..9227749 100644
--- a/docs/architecture/technical/privacy_gateway.md
+++ b/docs/architecture/technical/privacy_gateway.md
@@ -265,6 +265,8 @@ Im Lernmodus untersucht Detect weiterhin den vollen gerenderten Generate-Egress.
Es gibt keine separat zu pflegende Doppeldeutigkeitsliste. Mehrdeutigkeit entsteht, wenn dieselbe Schreibweise beide Sinne hat. Nur dann darf ein **lokales** Detect-Modell eine Mini-Passage (Ausschnitt um die Nennung) entscheiden. Fehlt ein lokales Modell oder ist die Antwort unbrauchbar, bleibt das Popup. OpenRouter erhält diese Passage nicht.
+**Additiv 2026-09-10:** Bestätigungen speichern zusätzlich den lokalen Cue (Wort vor der Nennung, sonst `_bare`) in `label_sense_cues`. Derselbe Cue wird angewendet statt erneut gefragt. Verwandtschafts-Nachträge (`Frau`/`Sohn`/…) respektieren dieselbe Regel. Bekannte Nur-Identität und bekannte Nur-Allgemeinbedeutung werden nicht erneut gefragt; Verwandtschaft nach einer Nur-Allgemeinbedeutung bleibt einmal prüfpflichtig, damit ein Personen-Sinn entdeckt werden kann.
+
Nach der Bestätigung läuft Generate mit den geprüften Mappings (`precomputed_learning_review`), ohne zweiten Detect-Pass. Compact-Diagnose enthält weiterhin keine Klartextlabels. Tests: `backend/tests/test_detect_learning.py`.
## 10. Offene Fragen
diff --git a/frontend/src/app.css b/frontend/src/app.css
index db704f7..de57745 100644
--- a/frontend/src/app.css
+++ b/frontend/src/app.css
@@ -695,3 +695,16 @@ pre.code {
flex-wrap: wrap;
gap: 0.8rem;
}
+.mask-excerpt {
+ margin: 0.35rem 0 0;
+ color: var(--ink);
+ font-size: 0.95rem;
+ line-height: 1.45;
+}
+.mask-excerpt mark {
+ background: #f3e2b8;
+ color: inherit;
+ font-weight: 600;
+ padding: 0 0.12em;
+ border-radius: 3px;
+}
diff --git a/frontend/src/components/MaskReviewPanel.jsx b/frontend/src/components/MaskReviewPanel.jsx
index cbd5219..16ade1d 100644
--- a/frontend/src/components/MaskReviewPanel.jsx
+++ b/frontend/src/components/MaskReviewPanel.jsx
@@ -1,3 +1,28 @@
+function HighlightedExcerpt({ excerpt, highlightStart, highlightEnd, label }) {
+ if (!excerpt) return null
+ const start = Number(highlightStart)
+ const end = Number(highlightEnd)
+ if (Number.isInteger(start) && Number.isInteger(end) && start >= 0 && end <= excerpt.length && end > start) {
+ return (
+
+ {excerpt.slice(0, start)}
+ {excerpt.slice(start, end)}
+ {excerpt.slice(end)}
+
+ )
+ }
+ const needle = label || ''
+ const at = needle ? excerpt.toLowerCase().indexOf(needle.toLowerCase()) : -1
+ if (at < 0) return {excerpt}
+ return (
+
+ {excerpt.slice(0, at)}
+ {excerpt.slice(at, at + needle.length)}
+ {excerpt.slice(at + needle.length)}
+
+ )
+}
+
export default function MaskReviewPanel({ review, busy, onSubmit }) {
if (!review?.candidates?.length) return null
return (
@@ -7,7 +32,7 @@ export default function MaskReviewPanel({ review, busy, onSubmit }) {
Maskierung prüfen
- Lernmodus: nur diese Nennung. Bestätigen legt die Bezeichnung lokal ab.
+ Lernmodus: nur die gelb markierte Nennung. Bestätigen legt die Bezeichnung lokal ab.
„Nicht schützenswert“ verhindert die Maskierung. Beides bei demselben Wort markiert es als mehrdeutig.
@@ -30,7 +55,12 @@ export default function MaskReviewPanel({ review, busy, onSubmit }) {
{item.text}
· {item.entity_type}{item.ambiguous ? ' · mehrdeutig' : ''}
- {item.excerpt &&
{item.excerpt}
}
+