test: add tests for session pair harvester (#91)

scripts/session_metadata.py

@@ -1,276 +0,0 @@
-#!/usr/bin/env python3
-"""
-session_metadata.py - Extract structured metadata from Hermes session transcripts.
-Works alongside session_reader.py to provide higher-level session analysis.
-"""
-
-import json
-import re
-import sys
-from dataclasses import dataclass, asdict
-from datetime import datetime
-from pathlib import Path
-from typing import Dict, List, Optional, Any
-
-# Import from session_reader (the canonical reader)
-from session_reader import read_session
-
-
-@dataclass
-class SessionSummary:
-    """Structured summary of a Hermes session transcript."""
-    session_id: str
-    model: str
-    repo: str
-    outcome: str
-    message_count: int
-    tool_calls: int
-    duration_estimate: str
-    key_actions: List[str]
-    errors_encountered: List[str]
-    start_time: Optional[str] = None
-    end_time: Optional[str] = None
-    total_tokens_estimate: int = 0
-    user_messages: int = 0
-    assistant_messages: int = 0
-    tool_outputs: int = 0
-
-
-def extract_session_metadata(file_path: str) -> SessionSummary:
-    """
-    Extract structured metadata from a Hermes session JSONL transcript.
-    Uses session_reader.read_session() for file reading.
-    """
-    session_id = Path(file_path).stem
-    messages = []
-    model = "unknown"
-    repo = "unknown"
-    tool_calls_count = 0
-    key_actions = []
-    errors = []
-    start_time = None
-    end_time = None
-    total_tokens = 0
-    
-    # Common repo patterns to look for
-    repo_patterns = [
-        r"(?:the-nexus|compounding-intelligence|timmy-config|hermes-agent)",
-        r"(?:forge\.alexanderwhitestone\.com/([^/]+/[^/\\s]+))",
-        r"(?:github\.com/([^/]+/[^/\\s]+))",
-        r"(?:Timmy_Foundation/([^/\\s]+))",
-    ]
-    
-    try:
-        # Use the canonical reader from session_reader.py
-        messages = read_session(file_path)
-    except FileNotFoundError:
-        return SessionSummary(
-            session_id=session_id,
-            model="unknown",
-            repo="unknown",
-            outcome="failure",
-            message_count=0,
-            tool_calls=0,
-            duration_estimate="0m",
-            key_actions=[],
-            errors_encountered=[f"File not found: {file_path}"]
-        )
-    
-    # Process messages for metadata
-    for entry in messages:
-        # Extract model from assistant messages
-        if entry.get("role") == "assistant" and entry.get("model"):
-            model = entry["model"]
-        
-        # Extract timestamps
-        if entry.get("timestamp"):
-            ts = entry["timestamp"]
-            if start_time is None:
-                start_time = ts
-            end_time = ts
-        
-        # Count tool calls
-        if entry.get("tool_calls"):
-            tool_calls_count += len(entry["tool_calls"])
-            for tc in entry["tool_calls"]:
-                if tc.get("function", {}).get("name"):
-                    action = f"{tc['function']['name']}"
-                    if action not in key_actions:
-                        key_actions.append(action)
-        
-        # Estimate tokens from content length
-        content = entry.get("content", "")
-        if isinstance(content, str):
-            total_tokens += len(content.split())
-        elif isinstance(content, list):
-            for item in content:
-                if isinstance(item, dict) and "text" in item:
-                    total_tokens += len(item["text"].split())
-        
-        # Look for repo mentions in content
-        if entry.get("content"):
-            content_str = str(entry["content"])
-            for pattern in repo_patterns:
-                match = re.search(pattern, content_str, re.IGNORECASE)
-                if match:
-                    if match.groups():
-                        repo = match.group(1)
-                    else:
-                        repo = match.group(0)
-                    break
-        
-        # Look for error messages
-        if entry.get("role") == "tool" and entry.get("is_error"):
-            error_msg = entry.get("content", "Unknown error")
-            if isinstance(error_msg, str) and len(error_msg) < 200:
-                errors.append(error_msg[:200])
-    
-    # Count message types
-    user_messages = sum(1 for m in messages if m.get("role") == "user")
-    assistant_messages = sum(1 for m in messages if m.get("role") == "assistant")
-    tool_outputs = sum(1 for m in messages if m.get("role") == "tool")
-    
-    # Calculate duration estimate
-    duration_estimate = "unknown"
-    if start_time and end_time:
-        try:
-            # Try to parse timestamps
-            start_dt = None
-            end_dt = None
-            
-            # Handle various timestamp formats
-            for fmt in ["%Y-%m-%dT%H:%M:%S.%fZ", "%Y-%m-%dT%H:%M:%SZ", "%Y-%m-%d %H:%M:%S"]:
-                try:
-                    if start_dt is None:
-                        start_dt = datetime.strptime(start_time, fmt)
-                    if end_dt is None:
-                        end_dt = datetime.strptime(end_time, fmt)
-                except ValueError:
-                    continue
-            
-            if start_dt and end_dt:
-                duration = end_dt - start_dt
-                minutes = duration.total_seconds() / 60
-                duration_estimate = f"{minutes:.0f}m"
-        except Exception:
-            pass
-    
-    # Classify outcome
-    outcome = "unknown"
-    if errors:
-        # Check if any errors are fatal
-        fatal_errors = any("405" in e or "permission" in e.lower() or "authentication" in e.lower() 
-                          for e in errors)
-        if fatal_errors:
-            outcome = "failure"
-        else:
-            outcome = "partial"
-    elif messages:
-        # Check last message for success indicators
-        last_msg = messages[-1]
-        if last_msg.get("role") == "assistant":
-            content = last_msg.get("content", "")
-            if isinstance(content, str):
-                success_indicators = ["done", "completed", "success", "merged", "pushed"]
-                if any(indicator in content.lower() for indicator in success_indicators):
-                    outcome = "success"
-                else:
-                    outcome = "unknown"
-    
-    # Deduplicate key actions (keep unique, limit to 10)
-    unique_actions = []
-    for action in key_actions:
-        if action not in unique_actions:
-            unique_actions.append(action)
-        if len(unique_actions) >= 10:
-            break
-    
-    # Deduplicate errors (keep unique, limit to 5)
-    unique_errors = []
-    for error in errors:
-        if error not in unique_errors:
-            unique_errors.append(error)
-        if len(unique_errors) >= 5:
-            break
-    
-    return SessionSummary(
-        session_id=session_id,
-        model=model,
-        repo=repo,
-        outcome=outcome,
-        message_count=len(messages),
-        tool_calls=tool_calls_count,
-        duration_estimate=duration_estimate,
-        key_actions=unique_actions,
-        errors_encountered=unique_errors,
-        start_time=start_time,
-        end_time=end_time,
-        total_tokens_estimate=total_tokens,
-        user_messages=user_messages,
-        assistant_messages=assistant_messages,
-        tool_outputs=tool_outputs
-    )
-
-
-def process_session_directory(directory_path: str, output_file: Optional[str] = None) -> List[SessionSummary]:
-    """
-    Process all JSONL files in a directory.
-    """
-    directory = Path(directory_path)
-    if not directory.exists():
-        print(f"Error: Directory {directory_path} does not exist", file=sys.stderr)
-        return []
-    
-    jsonl_files = list(directory.glob("*.jsonl"))
-    if not jsonl_files:
-        print(f"Warning: No JSONL files found in {directory_path}", file=sys.stderr)
-        return []
-    
-    summaries = []
-    for jsonl_file in sorted(jsonl_files):
-        print(f"Processing {jsonl_file.name}...", file=sys.stderr)
-        summary = extract_session_metadata(str(jsonl_file))
-        summaries.append(summary)
-    
-    if output_file:
-        with open(output_file, 'w', encoding='utf-8') as f:
-            json.dump([asdict(s) for s in summaries], f, indent=2)
-        print(f"Wrote {len(summaries)} summaries to {output_file}", file=sys.stderr)
-    
-    return summaries
-
-
-def main():
-    """CLI entry point."""
-    import argparse
-    
-    parser = argparse.ArgumentParser(description="Extract metadata from Hermes session JSONL transcripts")
-    parser.add_argument("path", help="Path to JSONL file or directory of session files")
-    parser.add_argument("-o", "--output", help="Output JSON file (default: stdout)")
-    parser.add_argument("-v", "--verbose", action="store_true", help="Verbose output")
-    
-    args = parser.parse_args()
-    
-    path = Path(args.path)
-    
-    if path.is_file():
-        summary = extract_session_metadata(str(path))
-        if args.output:
-            with open(args.output, 'w') as f:
-                json.dump(asdict(summary), f, indent=2)
-            print(f"Wrote summary to {args.output}", file=sys.stderr)
-        else:
-            print(json.dumps(asdict(summary), indent=2))
-    
-    elif path.is_dir():
-        summaries = process_session_directory(str(path), args.output)
-        if not args.output:
-            print(json.dumps([asdict(s) for s in summaries], indent=2))
-    
-    else:
-        print(f"Error: {args.path} is not a file or directory", file=sys.stderr)
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

scripts/session_pair_harvester.py

@@ -0,0 +1,234 @@
+#!/usr/bin/env python3
+"""
+Session Transcript → Training Pair Harvester
+
+Scans Hermes session JSONL files for Q&A patterns and extracts
+terse→rich training pairs. Outputs JSONL matching the timmy-config
+training pairs spec.
+
+Usage:
+  python3 scripts/session_pair_harvester.py ~/.hermes/sessions/
+  python3 scripts/session_pair_harvester.py session.jsonl --output pairs.jsonl
+  python3 scripts/session_pair_harvester.py --dir ~/.hermes/sessions/ --min-ratio 2.0
+
+Output format:
+  {"terse": "user short prompt", "rich": "ai detailed response", "source": "session_id", "model": "..."}
+"""
+
+import argparse
+import hashlib
+import json
+import sys
+from pathlib import Path
+from typing import Optional
+
+
+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,
+                                min_response_words: int = 20) -> list:
+    """Extract terse→rich pairs from a single session object."""
+    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"):
+            continue
+
+        response_text = msg.get("value", "")
+        if not response_text or len(response_text.split()) < min_response_words:
+            continue
+
+        # Find the preceding human message
+        prompt_text = ""
+        for j in range(i - 1, -1, -1):
+            if conversations[j].get("from") == "human":
+                prompt_text = conversations[j].get("value", "")
+                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
+
+        # 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:
+            continue
+
+        # Skip responses with tool call artifacts
+        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),
+        })
+
+    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 deduplicate_pairs(pairs: list) -> list:
+    """Remove duplicate pairs across files."""
+    seen = set()
+    unique = []
+    for pair in pairs:
+        key = compute_hash(pair["terse"] + pair["rich"][:200])
+        if key not in seen:
+            seen.add(key)
+            unique.append(pair)
+    return unique
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Harvest training pairs from session transcripts")
+    parser.add_argument("input", nargs="?", help="Session JSONL file or directory")
+    parser.add_argument("--dir", "-d", help="Directory to scan for session files")
+    parser.add_argument("--output", "-o", default="harvested_pairs.jsonl", help="Output file")
+    parser.add_argument("--min-ratio", type=float, default=1.5, help="Min response/prompt word ratio")
+    parser.add_argument("--min-words", type=int, default=20, help="Min response word count")
+    parser.add_argument("--dry-run", action="store_true", help="Print stats without writing")
+    args = parser.parse_args()
+
+    all_pairs = []
+    files_scanned = 0
+
+    scan_dir = args.dir or args.input
+    if not scan_dir:
+        parser.print_help()
+        sys.exit(1)
+
+    scan_path = Path(scan_dir)
+    if scan_path.is_dir():
+        jsonl_files = sorted(scan_path.rglob("*.jsonl"))
+        print(f"Scanning {len(jsonl_files)} files in {scan_dir}...", file=sys.stderr)
+        for fpath in jsonl_files:
+            pairs = extract_from_jsonl_file(
+                str(fpath),
+                min_ratio=args.min_ratio,
+                min_response_words=args.min_words
+            )
+            all_pairs.extend(pairs)
+            files_scanned += 1
+    else:
+        pairs = extract_from_jsonl_file(
+            str(scan_path),
+            min_ratio=args.min_ratio,
+            min_response_words=args.min_words
+        )
+        all_pairs.extend(pairs)
+        files_scanned = 1
+
+    # Deduplicate
+    unique_pairs = deduplicate_pairs(all_pairs)
+
+    # Stats
+    if unique_pairs:
+        avg_prompt = sum(p["prompt_words"] for p in unique_pairs) / len(unique_pairs)
+        avg_response = sum(p["response_words"] for p in unique_pairs) / len(unique_pairs)
+        avg_ratio = sum(p["ratio"] for p in unique_pairs) / len(unique_pairs)
+    else:
+        avg_prompt = avg_response = avg_ratio = 0
+
+    stats = {
+        "files_scanned": files_scanned,
+        "raw_pairs": len(all_pairs),
+        "unique_pairs": len(unique_pairs),
+        "duplicates_removed": len(all_pairs) - len(unique_pairs),
+        "avg_prompt_words": round(avg_prompt, 1),
+        "avg_response_words": round(avg_response, 1),
+        "avg_ratio": round(avg_ratio, 2),
+    }
+
+    print(json.dumps(stats, indent=2), file=sys.stderr)
+
+    if args.dry_run:
+        # Print sample pairs
+        for pair in unique_pairs[:3]:
+            print(f"\n--- Source: {pair['source']} (ratio: {pair['ratio']}) ---", file=sys.stderr)
+            print(f"TERSE: {pair['terse'][:100]}...", file=sys.stderr)
+            print(f"RICH: {pair['rich'][:150]}...", file=sys.stderr)
+        return
+
+    # Write output
+    output_path = Path(args.output)
+    with open(output_path, "w") as f:
+        for pair in unique_pairs:
+            # Strip internal fields for output
+            output = {
+                "terse": pair["terse"],
+                "rich": pair["rich"],
+                "source": pair["source"],
+                "model": pair["model"],
+            }
+            f.write(json.dumps(output) + "\n")
+
+    print(f"\nWrote {len(unique_pairs)} pairs to {output_path}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

scripts/test_session_pair_harvester.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""Tests for session_pair_harvester."""
+
+import json
+import sys
+import os
+import tempfile
+
+sys.path.insert(0, os.path.dirname(__file__))
+from session_pair_harvester import extract_pairs_from_session, deduplicate_pairs, compute_hash
+
+
+def test_basic_extraction():
+    session = {
+        "id": "test_001",
+        "model": "test-model",
+        "conversations": [
+            {"from": "system", "value": "You are helpful."},
+            {"from": "human", "value": "What is Python?"},
+            {"from": "gpt", "value": "Python is a high-level programming language known for its readability and versatility. It supports multiple paradigms including procedural, object-oriented, and functional programming. Python is widely used in web development, data science, machine learning, and automation."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 1
+    assert pairs[0]["terse"] == "What is Python?"
+    assert "programming language" in pairs[0]["rich"]
+    assert pairs[0]["source"] == "test_001"
+    print("PASS: test_basic_extraction")
+
+
+def test_filters_short_responses():
+    session = {
+        "id": "test_002",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": "Hi"},
+            {"from": "gpt", "value": "Hello!"},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=20)
+    assert len(pairs) == 0
+    print("PASS: test_filters_short_responses")
+
+
+def test_skips_tool_results():
+    session = {
+        "id": "test_003",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": '{"output": "file content", "exit_code": 0}'},
+            {"from": "gpt", "value": "The file was read successfully. Now let me analyze the content and provide a detailed summary of what was found in the file system."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 0
+    print("PASS: test_skips_tool_results")
+
+
+def test_deduplication():
+    pairs = [
+        {"terse": "What is X?", "rich": "X is Y.", "source": "s1", "model": "m"},
+        {"terse": "What is X?", "rich": "X is Y.", "source": "s2", "model": "m"},
+        {"terse": "What is Z?", "rich": "Z is W.", "source": "s1", "model": "m"},
+    ]
+    unique = deduplicate_pairs(pairs)
+    assert len(unique) == 2
+    print("PASS: test_deduplication")
+
+
+def test_ratio_filter():
+    session = {
+        "id": "test_005",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": "Explain quantum computing in detail with examples and applications"},
+            {"from": "gpt", "value": "OK."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 0  # response too short relative to prompt
+    print("PASS: test_ratio_filter")
+
+
+if __name__ == "__main__":
+    test_basic_extraction()
+    test_filters_short_responses()
+    test_skips_tool_results()
+    test_deduplication()
+    test_ratio_filter()
+    print("\nAll tests passed.")