feat(matching): Jev entity matching phases 2-5 (per-field fan-out, variants, candidate ambiguity buttons)

Phase 2 — jev.py client: POST /v1/systemone, PINNED model jev-1.13.0 (drift warning when the response model differs), one retry on 429/5xx, fail-soft (None on any error), usage/latency returned for observability. Config adds TYPESAFE_API_KEY / JEV_* (thresholds 0.85/0.60, 15 questions per field); no daily cap by owner decision. bot/.env is now mounted read-only into the container so the key never enters compose/git.

Phase 3 — matching.py: برون‌گروهی (one request per field, parallel), درون‌گروهی (one choice question per mention sharing the same full candidate list + «_none»), درون‌واریانسی (all STT spellings in one question). Routing: conf>=exact → bind; floor..exact → ambiguity; else/_none → new; missing/failed field → difflib fallback (bug fixed during testing: a failed request used to record 'new' instead of falling back). Resolver gains full cached lists for suppliers/materials (paged) plus brands (API+DB) and specs (EAV values + draft specs). NLU prompt now emits entity_mentions (6 fields) with the voice-variant grouping rule; sanitize_mentions guards the shape. handle_message runs matching only for register_quote/update_draft/add_material behind JEV_ENABLED; jev_map threads into quote/material resolve_payload (Jev hit skips difflib; exact writes ids; ambiguity skips difflib). Spec effect per owner: spelling normalization only (normalize_brand_spec).

Phase 4 — entity-match ambiguity sub-messages: create_ambiguities() builds deduped entries {kind: entity_match, field, variants, candidates, details with Persian percentages}; new keyboards.ambiguity_candidates_keyboard renders one button per candidate + «هیچ‌کدام — ایجاد جدید»; callbacks handle amb⛏️{prefix}:{amb_id}:{idx} (applies the candidate via matching.apply_choice then re-resolves/renders) and amb:new (rejected → auto-create path at commit). Every user choice lands in observability (ambiguity.user_choice with arg+candidates).

Phase 5 — voice variants: NLU groups different STT spellings of one entity into one variants[] (verified live: مصطفوی/مستفدی → one supplier mention); tools/test_matching.py live section (RUN_LIVE=1) exercises real DeepSeek + real Jev without touching Bale.

Tests: test_jev.py 5/5 (mock HTTP: no-key, happy path, 429-retry, 400, exception), test_matching.py 11/11 mock + 3/3 live (real NLU produced 7 mentions with correct fields; real Jev matched «50 کیلویی»→«۵۰ کیلویی» 0.98 and «کیسه» 1.0 and correctly returned new against the emptied catalog); observability regression 8/8.

bot/app/config.py

@@ -139,6 +139,17 @@ class Settings(BaseSettings):
     OBS_VOICE_DIR: str = "data/voices"   # persistent volume (./bot/data) — keep forever
     OBS_PROMPT_VERSION: str = ""         # manual label for the NLU prompt in use
 
+    # Jev (TypeSafe) entity matching — phases 2-5. Model version is PINNED
+    # (phase 0 resolved jev-1.13.0) so upstream updates cannot silently change
+    # decisions; every response's actual model is recorded for drift detection.
+    TYPESAFE_API_KEY: str = ""
+    JEV_MODEL: str = "jev-1.13.0"
+    JEV_ENABLED: bool = True
+    JEV_TIMEOUT: float = 8.0
+    JEV_CONF_EXACT: float = 0.85
+    JEV_CONF_FLOOR: float = 0.60
+    JEV_MAX_QUESTIONS_PER_FIELD: int = 15
+
     LOG_LEVEL: str = "INFO"
 
     @property