feat(engine): implement self-reflection (reflector) stage in multi-agent pipeline

- Added ReflectorAgent for meta-cognition and critical review between Research and Writing
- Updated WriterAgent to explicitly address reflection critiques
- Introduced 'g1nation.enableReflection' configuration setting
- Added comprehensive integration tests for the self-reflection stage
- Documented design decisions in ADR-0010 and related discussion records

src/agents/factory.ts

@@ -134,12 +134,13 @@ Your mission is to extract, filter, and synthesize critical data based on a stra
 }
 
 export class WriterAgent extends BaseAgent {
-    private readonly persona = `You are the [Lead Synthesis Writer & Editor]. 
+    private readonly persona = `You are the [Lead Synthesis Writer & Editor].
 Your goal is to produce a state-of-the-art final report that wows the user.
 - TONE: Authoritative yet accessible. Professional developer/consultant style.
 - STRUCTURE: Use an executive summary, detailed analysis sections, and a "Final Recommendation" block.
 - LANGUAGE: Always respond in the user's language (KOREAN).
-- POLISHING: Ensure logical flow between sections. Make it look like a premium report.`;
+- POLISHING: Ensure logical flow between sections. Make it look like a premium report.
+- SELF-CORRECTION: When a [REFLECTION CRITIQUE] block is provided, you MUST address each listed gap, contradiction, or missing-evidence item explicitly before producing the final report. Do not silently ignore the critique.`;
 
     async execute(input: string, originalRequest?: string, signal?: AbortSignal, options?: AgentExecuteOptions): Promise<string> {
         // [Astra v4.0] Advisor 모드 처리
@@ -154,13 +155,65 @@ Analyze the provided report and suggest 3 high-impact next actions for the user.
 
         // Fix 3: Trim input if it's too long (Basic Context Diet)
         const trimmedData = input.length > 8000 ? input.substring(0, 8000) + '... [Data Trimmed for Performance]' : input;
-        
+
         const policy = options?.context || '';
+        const reflection = options?.priorResults?.reflection;
+        // Reflector 결과가 있으면 별도 블록으로 주입. 길이 4000자 cap (Writer 입력 비대화 방지).
+        const reflectionBlock = reflection && reflection.trim().length > 0
+            ? `\n5. [REFLECTION CRITIQUE — must be addressed]:\n${reflection.length > 4000 ? reflection.substring(0, 4000) + '... [Critique Trimmed]' : reflection}`
+            : '';
+
         const wrappedInput = `### SYSTEM INSTRUCTION: FINAL SYNTHESIS
 1. Gathered Research Data: ${trimmedData}
 2. User's Original Objective: ${originalRequest}
 3. Applied Knowledge & Filtering Policy: ${policy}
-4. Mission: Write the definitive final report in KOREAN.`;
+4. Mission: Write the definitive final report in KOREAN.${reflectionBlock}`;
+        return this.callLLM(this.persona, wrappedInput, signal);
+    }
+}
+
+export class ReflectorAgent extends BaseAgent {
+    private readonly persona = `You are the [Internal Critic & Self-Reflection Officer].
+Your sole role is META-COGNITION: stress-test the plan and the research output BEFORE the Writer commits to a final report.
+- POSTURE: Skeptical, rigorous, blunt. You are looking for what is WRONG, not what is right.
+- DO NOT: rewrite the report, add new content, or speculate beyond the evidence provided.
+- DO: surface gaps, unsupported claims, contradictions, drift from the original objective, and missing perspectives.
+- OUTPUT STRICTLY in this Markdown shape (Korean):
+  ## 🧭 Alignment with Objective
+  - <원래 요청 대비 일치/이탈 평가>
+  ## 🕳 Gaps & Missing Evidence
+  - <plan에는 있지만 research가 다루지 않은 항목>
+  ## ⚖️ Contradictions / Conflicts
+  - <research 내부 또는 brain context와의 모순; 없으면 "발견되지 않음">
+  ## 🚨 Unsupported / Weak Claims
+  - <근거가 빈약하거나 일반화된 진술>
+  ## ✅ Guidance for Writer
+  - <Writer가 최종 리포트에서 반드시 보정해야 할 3~5개 구체 지시>
+- CONSTRAINT: 최대 500단어. 새 지식을 만들지 말고, 제공된 자료에서만 판단할 것.`;
+
+    async execute(input: string, _context?: string, signal?: AbortSignal, options?: AgentExecuteOptions): Promise<string> {
+        const plan = options?.priorResults?.plan || '(plan unavailable)';
+        const research = input;
+        const originalPrompt = options?.priorResults?.originalPrompt || '(original prompt unavailable)';
+        const brainContext = options?.context || '';
+
+        // Reflector 는 중간 단계이므로 비대한 입력을 방지하기 위해 각 섹션을 cap.
+        const cap = (s: string, n: number) => s.length > n ? s.substring(0, n) + '... [trimmed]' : s;
+
+        const wrappedInput = `### SYSTEM INSTRUCTION: SELF-REFLECTION PASS
+1. Original User Objective:
+${cap(originalPrompt, 1500)}
+
+2. Planner Blueprint:
+${cap(plan, 3000)}
+
+3. Researcher Output (to be critiqued):
+${cap(research, 5000)}
+
+4. Knowledge / Brain Context (for cross-check only — do not invent beyond this):
+${cap(brainContext, 2000)}
+
+5. Mission: Run a single rigorous reflection pass and output the structured critique exactly as specified by your persona.`;
         return this.callLLM(this.persona, wrappedInput, signal);
     }
 }