Merge pull request 'fix: session_pair_harvester uses role/content format (#91)' (#240) from step35/91-feat-session-transcript-trai into main

scripts/session_pair_harvester.py

@@ -22,114 +22,95 @@ import sys
 from pathlib import Path
 from typing import Optional
 
+from session_reader import extract_conversation, read_session
+
 
 def compute_hash(text: str) -> str:
     """Content hash for deduplication."""
     return hashlib.sha256(text.encode()).hexdigest()[:16]
 
 
-def extract_pairs_from_session(session_data: dict, min_ratio: float = 1.5,
+def extract_pairs_from_conversation(conversation: list, session_id: str, model: str,
+                                min_ratio: float = 1.5,
                                 min_response_words: int = 20) -> list:
-    """Extract terse→rich pairs from a single session object."""
+    """Extract terse→rich pairs from a normalized conversation."""
     pairs = []
-    conversations = session_data.get("conversations", [])
-    session_id = session_data.get("id", "unknown")
-    model = session_data.get("model", "unknown")
-
     seen_hashes = set()
 
-    for i, msg in enumerate(conversations):
-        # Look for assistant/gpt responses
-        if msg.get("from") not in ("gpt", "assistant"):
+    for i, msg in enumerate(conversation):
+        # Look for assistant responses
+        if msg.get('role') != 'assistant':
             continue
 
-        response_text = msg.get("value", "")
+        response_text = msg.get('content', '')
         if not response_text or len(response_text.split()) < min_response_words:
             continue
 
-        # Find the preceding human message
+        # Find the preceding user message
         prompt_text = ""
         for j in range(i - 1, -1, -1):
-            if conversations[j].get("from") == "human":
-                prompt_text = conversations[j].get("value", "")
+            if conversation[j].get('role') == 'user':
+                prompt_text = conversation[j].get('content', '')
                 break
 
         if not prompt_text:
             continue
 
         # Filter: skip tool results, system messages embedded as human
-        if prompt_text.startswith("{") and "output" in prompt_text[:100]:
-            continue  # likely a tool result
-        if prompt_text.startswith("# SOUL.md") or prompt_text.startswith("You are"):
-            continue  # system prompt leak
+        if prompt_text.startswith('{') and 'output' in prompt_text[:100]:
+            continue
+        if prompt_text.startswith('# SOUL.md') or prompt_text.startswith('You are'):
+            continue
 
         # Quality filters
         prompt_words = len(prompt_text.split())
         response_words = len(response_text.split())
 
-        # Must have meaningful length ratio
         if prompt_words == 0 or response_words == 0:
             continue
         ratio = response_words / prompt_words
         if ratio < min_ratio:
             continue
 
-        # Skip responses that are mostly code
-        code_blocks = response_text.count("```")
-        if code_blocks >= 4 and len(response_text.replace("```", "").strip()) < 50:
+        code_blocks = response_text.count('```')
+        if code_blocks >= 4 and len(response_text.replace('```', '').strip()) < 50:
             continue
 
-        # Skip responses with tool call artifacts
-        if "tool_call" in response_text[:100] or "function_call" in response_text[:100]:
+        if 'tool_call' in response_text[:100] or 'function_call' in response_text[:100]:
             continue
 
-        # Deduplicate by content hash
         content_hash = compute_hash(prompt_text + response_text[:200])
         if content_hash in seen_hashes:
             continue
         seen_hashes.add(content_hash)
 
-        # Clean up response: remove markdown headers if too many
         clean_response = response_text
 
         pairs.append({
-            "terse": prompt_text.strip(),
-            "rich": clean_response.strip(),
-            "source": session_id,
-            "model": model,
-            "prompt_words": prompt_words,
-            "response_words": response_words,
-            "ratio": round(ratio, 2),
+            'terse': prompt_text.strip(),
+            'rich': clean_response.strip(),
+            'source': session_id,
+            'model': model,
+            'prompt_words': prompt_words,
+            'response_words': response_words,
+            'ratio': round(ratio, 2),
         })
 
     return pairs
 
 
-def extract_from_jsonl_file(filepath: str, **kwargs) -> list:
-    """Extract pairs from a session JSONL file."""
-    pairs = []
-    path = Path(filepath)
 
-    if not path.exists():
-        print(f"Warning: {filepath} not found", file=sys.stderr)
-        return pairs
-
-    content = path.read_text()
-    lines = content.strip().split("\n")
-
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-        try:
-            session = json.loads(line)
-        except json.JSONDecodeError:
-            continue
-
-        session_pairs = extract_pairs_from_session(session, **kwargs)
-        pairs.extend(session_pairs)
-
-    return pairs
+def extract_from_jsonl_file(path: str, **kwargs) -> list:
+    """Read a session file and extract training pairs using normalized conversation."""
+    session_messages = read_session(path)
+    if not session_messages:
+        return []
+    conversation = extract_conversation(session_messages)
+    # Derive session_id and model from first real message metadata
+    first_msg = next((m for m in session_messages if m.get('role') or m.get('from')), {})
+    session_id = first_msg.get('meta_session_id', Path(path).name)
+    model = first_msg.get('model', 'unknown')
+    return extract_pairs_from_conversation(conversation, session_id, model, **kwargs)
 
 
 def deduplicate_pairs(pairs: list) -> list: