feat(ask): Phase 3.5a guardrails (classifier + refusal gate + grounding + partial)

신규 파일:
- classifier_service.py: exaone binary classifier (sufficient/insufficient)
  parallel with evidence, circuit breaker, timeout 5s
- refusal_gate.py: multi-signal fusion (score + classifier)
  AND 조건, conservative fallback 3-tier (classifier 부재 시)
- grounding_check.py: strong/weak flag 분리
  strong: fabricated_number + intent_misalignment(important keywords)
  weak: uncited_claim + low_overlap + intent_misalignment(generic)
  re-gate: 2+ strong → refuse, 1 strong → partial
- sentence_splitter.py: regex 기반 (Phase 3.5b KSS 업그레이드)
- classifier.txt: exaone Y+ prompt (calibration examples 포함)
- search_synthesis_partial.txt: partial answer 전용 프롬프트
- 102_ask_events.sql: /ask 관측 테이블 (completeness 3-분리 지표)
- queries.yaml: Phase 3.5 smoke test 평가셋 10개

수정 파일:
- search.py /ask: classifier parallel + refusal gate + grounding re-gate
  + defense_layers 로깅 + AskResponse completeness/aspects/confirmed_items
- config.yaml: classifier model 섹션 (exaone3.5:7.8b GPU Ollama)
- config.py: classifier optional 파싱
- AskAnswer.svelte: 4분기 렌더 (full/partial/insufficient/loading)
- ask.ts: Completeness + ConfirmedItem 타입

P1 실측: exaone ternary 불안정 → binary gate 축소. partial은 grounding이 담당.
토론 9라운드 확정. plan: quiet-meandering-nova.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/prompts/classifier.txt

@@ -0,0 +1,33 @@
+You are an answerability judge. Given a query and evidence chunks, determine if the evidence can answer the query. Respond ONLY in JSON.
+
+## CALIBRATION (CRITICAL)
+- verdict=full: evidence is SUFFICIENT to answer the CORE of the query. Missing minor details does NOT make it insufficient.
+- verdict=partial: evidence covers SOME major aspects but CLEARLY MISSES others the user explicitly asked about.
+- verdict=insufficient: evidence has NO relevant information for the query, or is completely off-topic.
+
+Example: Query="제6장 주요 내용", Evidence covers 제6장 definition+scope → verdict=full (core is covered).
+Example: Query="제6장 처벌 조항", Evidence covers 제6장 definition but NOT 처벌 → verdict=partial.
+Example: Query="감귤 출하량", Evidence about 산업안전보건법 → verdict=insufficient.
+
+## Rules
+1. Your "verdict" must be based ONLY on whether the CONTENT semantically answers the query. Ignore retrieval scores for this field.
+2. "covered_aspects": query aspects that evidence covers. Korean labels for Korean queries.
+3. "missing_aspects": query aspects that evidence does NOT cover. Korean labels.
+4. Keep aspects concise (2-5 words each), non-overlapping.
+
+## Output Schema
+{
+  "verdict": "full" | "partial" | "insufficient",
+  "covered_aspects": ["aspect1"],
+  "missing_aspects": ["aspect2"],
+  "confidence": "high" | "medium" | "low"
+}
+
+## Query
+{query}
+
+## Evidence chunks:
+{chunks}
+
+## Retrieval scores (for reference only, NOT for verdict):
+[{scores}]

app/prompts/search_synthesis_partial.txt

@@ -0,0 +1,34 @@
+You are a grounded answer synthesizer handling a PARTIAL answer case. Some aspects of the query CAN be answered, others CANNOT. Respond ONLY in JSON.
+
+## Task
+Answer ONLY the covered aspects. Do NOT attempt to answer missing aspects.
+
+## Output Schema
+{
+  "confirmed_items": [
+    {"aspect": "aspect label", "text": "1~2 sentence answer", "citations": [1, 2]}
+  ],
+  "confidence": "medium" | "low",
+  "refused": false
+}
+
+## Rules
+- Each confirmed_item: aspect label + 1~2 sentences + inline [n] citations
+- ONLY use facts present in evidence. No outside knowledge, no guessing.
+- Do NOT mention or address missing_aspects in your text.
+- Korean query → Korean answer / English → English
+- confidence: medium (2+ strong evidence matches) / low (1 or weak)
+- Max total text: 400 chars across all items
+- 모든 주장 문장 끝에 [n] 필수
+
+## Covered aspects (answer these):
+{covered_aspects}
+
+## Missing aspects (do NOT answer these):
+{missing_aspects}
+
+## Query
+{query}
+
+## Evidence
+{numbered_evidence}