Update für Feedback Loop

app/routers/chat.py

@@ -1,6 +1,12 @@
 """
-app/routers/chat.py — RAG Endpunkt (WP-06 Hybrid Router v3)
-Update: Transparenz über Intent-Source (Keyword vs. LLM).
+app/routers/chat.py — RAG Endpunkt (WP-06 Hybrid Router + WP-04c Feedback)
+Version: 2.3.2 (Merged Stability Patch)
+
+Features:
+- Hybrid Intent Router (Keyword + LLM)
+- Strategic Retrieval (Late Binding via Config)
+- Context Enrichment (Payload/Source Fallback)
+- Data Flywheel (Feedback Logging Integration)
 """
 
 from fastapi import APIRouter, HTTPException, Depends
@@ -15,6 +21,8 @@ from app.config import get_settings
 from app.models.dto import ChatRequest, ChatResponse, QueryRequest, QueryHit
 from app.services.llm_service import LLMService
 from app.core.retriever import Retriever 
+# [MERGE] Integration Feedback Service (WP-04c)
+from app.services.feedback_service import log_search 
 
 router = APIRouter()
 logger = logging.getLogger(__name__)
@@ -77,7 +85,7 @@ def _build_enriched_context(hits: List[QueryHit]) -> str:
         )
         title = hit.note_id or "Unbekannt"
         
-        # FIX: Wir holen den Typ aus Payload oder Source (Fallback)
+        # [FIX] Robustes Auslesen des Typs (Payload > Source > Unknown)
         payload = hit.payload or {}
         note_type = payload.get("type") or source.get("type", "unknown")
         note_type = str(note_type).upper()
@@ -173,7 +181,7 @@ async def chat_endpoint(
         retrieve_result = await retriever.search(query_req)
         hits = retrieve_result.results
         
-        # 3. Strategic Retrieval
+        # 3. Strategic Retrieval (WP-06 Kernfeature)
         if inject_types:
             logger.info(f"[{query_id}] Executing Strategic Retrieval for types: {inject_types}...")
             strategy_req = QueryRequest(
@@ -207,18 +215,37 @@ async def chat_endpoint(
         
         logger.info(f"[{query_id}] Sending to LLM (Intent: {intent}, Template: {prompt_key})...")
         
-        # System-Prompt separat übergeben
+        # System-Prompt separat übergeben (WP-06a Fix)
         answer_text = await llm.generate_raw_response(prompt=final_prompt, system=system_prompt)
 
         duration_ms = int((time.time() - start_time) * 1000)
         
+        # 6. Logging (Fire & Forget) - [MERGE POINT]
+        # Wir loggen alles für das Data Flywheel (WP-08 Self-Tuning)
+        try:
+            log_search(
+                query_id=query_id,
+                query_text=request.message,
+                results=hits,
+                mode="chat_rag",
+                metadata={
+                    "intent": intent,
+                    "intent_source": intent_source,
+                    "generated_answer": answer_text,
+                    "model": llm.settings.LLM_MODEL
+                }
+            )
+        except Exception as e:
+            logger.error(f"Logging failed: {e}")
+
+        # 7. Response
         return ChatResponse(
             query_id=query_id,
             answer=answer_text,
             sources=hits,
             latency_ms=duration_ms,
             intent=intent,
-            intent_source=intent_source # Source durchreichen
+            intent_source=intent_source
         )
 
     except Exception as e:

app/services/feedback_service.py

@@ -2,13 +2,18 @@
 app/services/feedback_service.py
 Service zum Loggen von Suchanfragen und Feedback (WP-04c).
 Speichert Daten als JSONL für späteres Self-Tuning (WP-08).
+
+Version: 1.1 (Chat-Support)
 """
 import json
 import os
 import time
+import logging
 from pathlib import Path
-from typing import Dict, Any, List
-from app.models.dto import QueryRequest, QueryResponse, FeedbackRequest
+from typing import Dict, Any, List, Union
+from app.models.dto import QueryRequest, QueryResponse, FeedbackRequest, QueryHit
+
+logger = logging.getLogger(__name__)
 
 # Pfad für Logs (lokal auf dem Beelink/PC)
 LOG_DIR = Path("data/logs")
@@ -19,18 +24,35 @@ def _ensure_log_dir():
     if not LOG_DIR.exists():
         os.makedirs(LOG_DIR, exist_ok=True)
 
-def log_search(req: QueryRequest, res: QueryResponse):
+def _append_jsonl(file_path: Path, data: dict):
+    try:
+        with open(file_path, "a", encoding="utf-8") as f:
+            f.write(json.dumps(data, ensure_ascii=False) + "\n")
+    except Exception as e:
+        logger.error(f"Failed to write log: {e}")
+
+def log_search(
+    query_id: str, 
+    query_text: str, 
+    results: List[QueryHit], 
+    mode: str = "unknown", 
+    metadata: Dict[str, Any] = None
+):
     """
-    Speichert den "Snapshot" der Suche.
-    WICHTIG: Wir speichern die Scores (Breakdown), damit wir später wissen,
-    warum das System so entschieden hat.
+    Generische Logging-Funktion für Suche UND Chat.
+    
+    Args:
+        query_id: UUID der Anfrage.
+        query_text: User-Eingabe.
+        results: Liste der Treffer (QueryHit Objekte).
+        mode: z.B. "semantic", "hybrid", "chat_rag".
+        metadata: Zusätzliche Infos (z.B. generierte Antwort, Intent).
     """
     _ensure_log_dir()
     
-    # Wir reduzieren die Datenmenge etwas (z.B. keine vollen Texte)
     hits_summary = []
-    for hit in res.results:
-        # Falls Explanation an war, speichern wir den Breakdown, sonst die Scores
+    for hit in results:
+        # Pydantic Model Dump für saubere Serialisierung
         breakdown = None
         if hit.explanation and hit.explanation.breakdown:
             breakdown = hit.explanation.breakdown.model_dump()
@@ -39,25 +61,24 @@ def log_search(req: QueryRequest, res: QueryResponse):
             "node_id": hit.node_id,
             "note_id": hit.note_id,
             "total_score": hit.total_score,
-            "breakdown": breakdown, # Wichtig für Training!
+            "breakdown": breakdown,
             "rank_semantic": hit.semantic_score,
-            "rank_edge": hit.edge_bonus
+            "rank_edge": hit.edge_bonus,
+            "type": hit.source.get("type") if hit.source else "unknown"
         })
 
     entry = {
         "timestamp": time.time(),
-        "query_id": res.query_id,
-        "query_text": req.query,
-        "mode": req.mode,
-        "top_k": req.top_k,
-        "hits": hits_summary
+        "query_id": query_id,
+        "query_text": query_text,
+        "mode": mode,
+        "hits_count": len(hits_summary),
+        "hits": hits_summary,
+        "metadata": metadata or {}
     }
 
-    try:
-        with open(SEARCH_LOG_FILE, "a", encoding="utf-8") as f:
-            f.write(json.dumps(entry, ensure_ascii=False) + "\n")
-    except Exception as e:
-        print(f"ERROR logging search: {e}")
+    _append_jsonl(SEARCH_LOG_FILE, entry)
+    logger.info(f"Logged search/chat interaction {query_id}")
 
 def log_feedback(fb: FeedbackRequest):
     """
@@ -73,8 +94,5 @@ def log_feedback(fb: FeedbackRequest):
         "comment": fb.comment
     }
 
-    try:
-        with open(FEEDBACK_LOG_FILE, "a", encoding="utf-8") as f:
-            f.write(json.dumps(entry, ensure_ascii=False) + "\n")
-    except Exception as e:
-        print(f"ERROR logging feedback: {e}")
+    _append_jsonl(FEEDBACK_LOG_FILE, entry)
+    logger.info(f"Logged feedback for {fb.query_id}")