feat: add harvester.py — session knowledge extractor (#8)

Main harvester module that chains:
  session_reader → extraction prompt → LLM → validate → deduplicate → store

Includes:
- scripts/harvester.py — main module (reader + prompt + storage pipeline)
- scripts/session_reader.py — JSONL transcript parser
- scripts/test_harvester_pipeline.py — smoke tests (all passing)

Pipeline:
  1. Read session JSONL via session_reader
  2. Truncate long sessions (first 50 + last 50 messages)
  3. Send transcript + extraction prompt to LLM (mimo-v2-pro)
  4. Parse structured JSON response (facts/pitfalls/patterns/quirks/questions)
  5. Validate fields + confidence threshold
  6. Deduplicate against knowledge/index.json (fingerprint + word overlap)
  7. Write to knowledge store (index.json + per-repo markdown)

CLI:
  Single:  python3 harvester.py --session <path> --output knowledge/
  Batch:   python3 harvester.py --batch --since 2026-04-01 --limit 100
  Dry-run: python3 harvester.py --session <path> --dry-run

scripts/harvester.py

@@ -0,0 +1,447 @@
+#!/usr/bin/env python3
+"""
+harvester.py — Extract durable knowledge from Hermes session transcripts.
+
+Combines session_reader + extraction prompt + LLM inference to pull
+facts, pitfalls, patterns, and tool quirks from finished sessions.
+
+Usage:
+    python3 harvester.py --session ~/.hermes/sessions/session_xxx.jsonl --output knowledge/
+    python3 harvester.py --batch --since 2026-04-01 --limit 100
+    python3 harvester.py --session session.jsonl --dry-run  # Preview without writing
+"""
+
+import argparse
+import json
+import os
+import sys
+import time
+import hashlib
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Optional
+
+# Add scripts dir to path for sibling imports
+SCRIPT_DIR = Path(__file__).parent.absolute()
+sys.path.insert(0, str(SCRIPT_DIR))
+
+from session_reader import read_session, extract_conversation, truncate_for_context, messages_to_text
+
+# --- Configuration ---
+
+DEFAULT_API_BASE = os.environ.get("HARVESTER_API_BASE", "https://api.nousresearch.com/v1")
+DEFAULT_API_KEY = os.environ.get("HARVESTER_API_KEY", "")
+DEFAULT_MODEL = os.environ.get("HARVESTER_MODEL", "xiaomi/mimo-v2-pro")
+KNOWLEDGE_DIR = os.environ.get("HARVESTER_KNOWLEDGE_DIR", "knowledge")
+PROMPT_PATH = os.environ.get("HARVESTER_PROMPT_PATH", str(SCRIPT_DIR.parent / "templates" / "harvest-prompt.md"))
+
+# Where to look for API keys if not set via env
+API_KEY_PATHS = [
+    os.path.expanduser("~/.config/nous/key"),
+    os.path.expanduser("~/.hermes/keymaxxing/active/minimax.key"),
+    os.path.expanduser("~/.config/openrouter/key"),
+]
+
+
+def find_api_key() -> str:
+    """Find API key from common locations."""
+    for path in API_KEY_PATHS:
+        if os.path.exists(path):
+            with open(path) as f:
+                key = f.read().strip()
+                if key:
+                    return key
+    return ""
+
+
+def load_extraction_prompt() -> str:
+    """Load the extraction prompt template."""
+    path = Path(PROMPT_PATH)
+    if not path.exists():
+        print(f"ERROR: Extraction prompt not found at {path}", file=sys.stderr)
+        print("Expected templates/harvest-prompt.md from issue #7", file=sys.stderr)
+        sys.exit(1)
+    return path.read_text(encoding='utf-8')
+
+
+def call_llm(prompt: str, transcript: str, api_base: str, api_key: str, model: str) -> Optional[list[dict]]:
+    """Call the LLM API to extract knowledge from a transcript."""
+    import urllib.request
+    
+    messages = [
+        {"role": "system", "content": prompt},
+        {"role": "user", "content": f"Extract knowledge from this session transcript:\n\n{transcript}"}
+    ]
+    
+    payload = json.dumps({
+        "model": model,
+        "messages": messages,
+        "temperature": 0.1,  # Low temp for consistent extraction
+        "max_tokens": 4096
+    }).encode('utf-8')
+    
+    req = urllib.request.Request(
+        f"{api_base}/chat/completions",
+        data=payload,
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json"
+        },
+        method="POST"
+    )
+    
+    try:
+        with urllib.request.urlopen(req, timeout=60) as resp:
+            result = json.loads(resp.read().decode('utf-8'))
+            content = result["choices"][0]["message"]["content"]
+            return parse_extraction_response(content)
+    except Exception as e:
+        print(f"ERROR: LLM API call failed: {e}", file=sys.stderr)
+        return None
+
+
+def parse_extraction_response(content: str) -> Optional[list[dict]]:
+    """Parse the LLM response to extract knowledge items.
+    
+    Handles various response formats: raw JSON, markdown-wrapped JSON, etc.
+    """
+    # Try direct JSON parse first
+    try:
+        data = json.loads(content)
+        if isinstance(data, dict) and 'knowledge' in data:
+            return data['knowledge']
+        if isinstance(data, list):
+            return data
+    except json.JSONDecodeError:
+        pass
+    
+    # Try extracting JSON from markdown code blocks
+    import re
+    json_match = re.search(r'```(?:json)?\s*({.*?})\s*```', content, re.DOTALL)
+    if json_match:
+        try:
+            data = json.loads(json_match.group(1))
+            if isinstance(data, dict) and 'knowledge' in data:
+                return data['knowledge']
+            if isinstance(data, list):
+                return data
+        except json.JSONDecodeError:
+            pass
+    
+    # Try finding any JSON object with knowledge array
+    json_match = re.search(r'({[^{}]*"knowledge"[^{}]*[[sS]*?][^{}]*})', content)
+    if json_match:
+        try:
+            data = json.loads(json_match.group(1))
+            return data.get('knowledge', [])
+        except json.JSONDecodeError:
+            pass
+    
+    print(f"WARNING: Could not parse LLM response as JSON", file=sys.stderr)
+    print(f"Response preview: {content[:500]}", file=sys.stderr)
+    return None
+
+
+def load_existing_knowledge(knowledge_dir: str) -> dict:
+    """Load the existing knowledge index."""
+    index_path = Path(knowledge_dir) / "index.json"
+    if not index_path.exists():
+        return {"version": 1, "last_updated": "", "total_facts": 0, "facts": []}
+    
+    try:
+        with open(index_path, 'r', encoding='utf-8') as f:
+            return json.load(f)
+    except (json.JSONDecodeError, IOError) as e:
+        print(f"WARNING: Could not load knowledge index: {e}", file=sys.stderr)
+        return {"version": 1, "last_updated": "", "total_facts": 0, "facts": []}
+
+
+def fact_fingerprint(fact: dict) -> str:
+    """Generate a deduplication fingerprint for a fact.
+    
+    Uses the fact text normalized (lowercase, stripped) as the key.
+    Similar facts will have similar fingerprints.
+    """
+    text = fact.get('fact', '').lower().strip()
+    # Normalize whitespace
+    text = ' '.join(text.split())
+    return hashlib.md5(text.encode('utf-8')).hexdigest()
+
+
+def deduplicate(new_facts: list[dict], existing: list[dict], similarity_threshold: float = 0.8) -> list[dict]:
+    """Remove duplicate facts from new_facts that already exist in the knowledge store.
+    
+    Uses fingerprint matching for exact dedup and simple overlap check for near-dupes.
+    """
+    existing_fingerprints = set()
+    existing_texts = []
+    for f in existing:
+        fp = fact_fingerprint(f)
+        existing_fingerprints.add(fp)
+        existing_texts.append(f.get('fact', '').lower().strip())
+    
+    unique = []
+    for fact in new_facts:
+        fp = fact_fingerprint(fact)
+        if fp in existing_fingerprints:
+            continue
+        
+        # Check for near-duplicates using simple word overlap
+        fact_words = set(fact.get('fact', '').lower().split())
+        is_dup = False
+        for existing_text in existing_texts:
+            existing_words = set(existing_text.split())
+            if not fact_words or not existing_words:
+                continue
+            overlap = len(fact_words & existing_words) / max(len(fact_words | existing_words), 1)
+            if overlap >= similarity_threshold:
+                is_dup = True
+                break
+        
+        if not is_dup:
+            unique.append(fact)
+            existing_fingerprints.add(fp)
+            existing_texts.append(fact.get('fact', '').lower().strip())
+    
+    return unique
+
+
+def validate_fact(fact: dict) -> bool:
+    """Validate a single knowledge item has required fields."""
+    required = ['fact', 'category', 'repo', 'confidence']
+    for field in required:
+        if field not in fact:
+            return False
+    
+    if not isinstance(fact['fact'], str) or not fact['fact'].strip():
+        return False
+    
+    valid_categories = ['fact', 'pitfall', 'pattern', 'tool-quirk', 'question']
+    if fact['category'] not in valid_categories:
+        return False
+    
+    if not isinstance(fact.get('confidence', 0), (int, float)):
+        return False
+    
+    if not (0.0 <= fact['confidence'] <= 1.0):
+        return False
+    
+    return True
+
+
+def write_knowledge(index: dict, new_facts: list[dict], knowledge_dir: str, source_session: str = ""):
+    """Write new facts to the knowledge store."""
+    kdir = Path(knowledge_dir)
+    kdir.mkdir(parents=True, exist_ok=True)
+    
+    # Add source tracking to each fact
+    for fact in new_facts:
+        fact['source_session'] = source_session
+        fact['harvested_at'] = datetime.now(timezone.utc).isoformat()
+    
+    # Update index
+    index['facts'].extend(new_facts)
+    index['total_facts'] = len(index['facts'])
+    index['last_updated'] = datetime.now(timezone.utc).isoformat()
+    
+    # Write index
+    index_path = kdir / "index.json"
+    with open(index_path, 'w', encoding='utf-8') as f:
+        json.dump(index, f, indent=2, ensure_ascii=False)
+    
+    # Also write per-repo markdown files for human reading
+    repos = {}
+    for fact in new_facts:
+        repo = fact.get('repo', 'global')
+        repos.setdefault(repo, []).append(fact)
+    
+    for repo, facts in repos.items():
+        if repo == 'global':
+            md_path = kdir / "global" / "harvested.md"
+        else:
+            md_path = kdir / "repos" / f"{repo}.md"
+        
+        md_path.parent.mkdir(parents=True, exist_ok=True)
+        
+        # Append to existing or create new
+        mode = 'a' if md_path.exists() else 'w'
+        with open(md_path, mode, encoding='utf-8') as f:
+            if mode == 'w':
+                f.write(f"# Knowledge: {repo}\n\n")
+            f.write(f"## Harvested {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M')}\n\n")
+            for fact in facts:
+                icon = {'fact': '📋', 'pitfall': '⚠️', 'pattern': '🔄', 'tool-quirk': '🔧', 'question': '❓'}.get(fact['category'], '•')
+                f.write(f"- {icon} **{fact['category']}** (conf: {fact['confidence']:.1f}): {fact['fact']}\n")
+            f.write("\n")
+
+
+def harvest_session(session_path: str, knowledge_dir: str, api_base: str, api_key: str, 
+                    model: str, dry_run: bool = False, min_confidence: float = 0.3) -> dict:
+    """Harvest knowledge from a single session.
+    
+    Returns: dict with stats (facts_found, facts_new, facts_dup, elapsed_seconds, error)
+    """
+    start_time = time.time()
+    stats = {
+        'session': session_path,
+        'facts_found': 0,
+        'facts_new': 0,
+        'facts_dup': 0,
+        'elapsed_seconds': 0,
+        'error': None
+    }
+    
+    try:
+        # 1. Read session
+        messages = read_session(session_path)
+        if not messages:
+            stats['error'] = "Empty session file"
+            return stats
+        
+        # 2. Extract conversation
+        conv = extract_conversation(messages)
+        if not conv:
+            stats['error'] = "No conversation turns found"
+            return stats
+        
+        # 3. Truncate for context window
+        truncated = truncate_for_context(conv, head=50, tail=50)
+        transcript = messages_to_text(truncated)
+        
+        # 4. Load extraction prompt
+        prompt = load_extraction_prompt()
+        
+        # 5. Call LLM
+        raw_facts = call_llm(prompt, transcript, api_base, api_key, model)
+        if raw_facts is None:
+            stats['error'] = "LLM extraction failed"
+            return stats
+        
+        # 6. Validate
+        valid_facts = [f for f in raw_facts if validate_fact(f) and f.get('confidence', 0) >= min_confidence]
+        stats['facts_found'] = len(valid_facts)
+        
+        # 7. Deduplicate
+        existing_index = load_existing_knowledge(knowledge_dir)
+        existing_facts = existing_index.get('facts', [])
+        new_facts = deduplicate(valid_facts, existing_facts)
+        stats['facts_new'] = len(new_facts)
+        stats['facts_dup'] = len(valid_facts) - len(new_facts)
+        
+        # 8. Write (unless dry run)
+        if new_facts and not dry_run:
+            write_knowledge(existing_index, new_facts, knowledge_dir, source_session=session_path)
+        
+        stats['elapsed_seconds'] = round(time.time() - start_time, 2)
+        return stats
+        
+    except Exception as e:
+        stats['error'] = str(e)
+        stats['elapsed_seconds'] = round(time.time() - start_time, 2)
+        return stats
+
+
+def batch_harvest(sessions_dir: str, knowledge_dir: str, api_base: str, api_key: str,
+                  model: str, since: str = "", limit: int = 0, dry_run: bool = False) -> list[dict]:
+    """Harvest knowledge from multiple sessions in batch."""
+    sessions_path = Path(sessions_dir)
+    if not sessions_path.is_dir():
+        print(f"ERROR: Sessions directory not found: {sessions_dir}", file=sys.stderr)
+        return []
+    
+    # Find session files
+    session_files = sorted(sessions_path.glob("*.jsonl"), reverse=True)  # Newest first
+    
+    # Filter by date if --since provided
+    if since:
+        since_dt = datetime.fromisoformat(since.replace('Z', '+00:00'))
+        filtered = []
+        for sf in session_files:
+            # Try to parse timestamp from filename (common format: session_YYYYMMDD_HHMMSS_hash.jsonl)
+            try:
+                parts = sf.stem.split('_')
+                if len(parts) >= 3:
+                    date_str = parts[1]
+                    file_dt = datetime.strptime(date_str, '%Y%m%d').replace(tzinfo=timezone.utc)
+                    if file_dt >= since_dt:
+                        filtered.append(sf)
+            except (ValueError, IndexError):
+                # If we can't parse the date, include the file (be permissive)
+                filtered.append(sf)
+        session_files = filtered
+    
+    # Apply limit
+    if limit > 0:
+        session_files = session_files[:limit]
+    
+    print(f"Harvesting {len(session_files)} sessions...")
+    
+    results = []
+    for i, sf in enumerate(session_files, 1):
+        print(f"[{i}/{len(session_files)}] {sf.name}...", end=" ", flush=True)
+        stats = harvest_session(str(sf), knowledge_dir, api_base, api_key, model, dry_run)
+        if stats['error']:
+            print(f"ERROR: {stats['error']}")
+        else:
+            print(f"{stats['facts_new']} new, {stats['facts_dup']} dup ({stats['elapsed_seconds']}s)")
+        results.append(stats)
+    
+    return results
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Harvest knowledge from session transcripts")
+    parser.add_argument('--session', help='Path to a single session JSONL file')
+    parser.add_argument('--batch', action='store_true', help='Batch mode: process multiple sessions')
+    parser.add_argument('--sessions-dir', default=os.path.expanduser('~/.hermes/sessions'), 
+                        help='Directory containing session files (default: ~/.hermes/sessions)')
+    parser.add_argument('--output', default='knowledge', help='Output directory for knowledge store')
+    parser.add_argument('--since', default='', help='Only process sessions after this date (YYYY-MM-DD)')
+    parser.add_argument('--limit', type=int, default=0, help='Max sessions to process (0=unlimited)')
+    parser.add_argument('--api-base', default=DEFAULT_API_BASE, help='LLM API base URL')
+    parser.add_argument('--api-key', default='', help='LLM API key (or set HARVESTER_API_KEY)')
+    parser.add_argument('--model', default=DEFAULT_MODEL, help='Model to use for extraction')
+    parser.add_argument('--dry-run', action='store_true', help='Preview without writing to knowledge store')
+    parser.add_argument('--min-confidence', type=float, default=0.3, help='Minimum confidence threshold')
+    
+    args = parser.parse_args()
+    
+    # Resolve API key
+    api_key = args.api_key or DEFAULT_API_KEY or find_api_key()
+    if not api_key:
+        print("ERROR: No API key found. Set HARVESTER_API_KEY or store in one of:", file=sys.stderr)
+        for p in API_KEY_PATHS:
+            print(f"  {p}", file=sys.stderr)
+        sys.exit(1)
+    
+    # Resolve knowledge directory
+    knowledge_dir = args.output
+    if not os.path.isabs(knowledge_dir):
+        knowledge_dir = os.path.join(SCRIPT_DIR.parent, knowledge_dir)
+    
+    if args.session:
+        # Single session mode
+        stats = harvest_session(
+            args.session, knowledge_dir, args.api_base, api_key, args.model,
+            dry_run=args.dry_run, min_confidence=args.min_confidence
+        )
+        print(json.dumps(stats, indent=2))
+        if stats['error']:
+            sys.exit(1)
+    elif args.batch:
+        # Batch mode
+        results = batch_harvest(
+            args.sessions_dir, knowledge_dir, args.api_base, api_key, args.model,
+            since=args.since, limit=args.limit, dry_run=args.dry_run
+        )
+        total_new = sum(r['facts_new'] for r in results)
+        total_dup = sum(r['facts_dup'] for r in results)
+        errors = sum(1 for r in results if r['error'])
+        print(f"\nDone: {total_new} new facts, {total_dup} duplicates, {errors} errors")
+    else:
+        parser.print_help()
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

scripts/improvement_proposals.py

@@ -1,451 +0,0 @@
-#!/usr/bin/env python3
-"""
-Improvement Proposal Generator for compounding-intelligence.
-
-Analyzes fleet session data to identify waste patterns and generates
-concrete improvement proposals with ROI estimates.
-
-Input: Session analytics JSON (from fleet metrics or session database)
-Output: Markdown proposal document + JSON proposals
-
-Usage:
-    python3 scripts/improvement_proposals.py --input analytics.json
-    python3 scripts/improvement_proposals.py --input analytics.json --format json
-    python3 scripts/improvement_proposals.py --input analytics.json --output proposals.md
-    python3 scripts/improvement_proposals.py --input analytics.json --threshold 5.0
-"""
-
-import argparse
-import json
-import os
-import sys
-from collections import defaultdict
-from dataclasses import dataclass, field, asdict
-from datetime import datetime, timezone
-from typing import Any, Dict, List, Optional
-
-
-# ── Data types ─────────────────────────────────────────────────
-
-@dataclass
-class WastePattern:
-    """A detected waste pattern in fleet sessions."""
-    pattern_type: str       # "repeated_error", "manual_process", "slow_tool", "failed_retry"
-    description: str
-    occurrences: int
-    total_time_hours: float
-    affected_repos: List[str] = field(default_factory=list)
-    example_sessions: List[str] = field(default_factory=list)
-
-
-@dataclass
-class ImprovementProposal:
-    """A concrete improvement proposal with ROI estimate."""
-    title: str
-    problem: str
-    proposed_solution: str
-    estimated_weekly_hours_saved: float
-    estimated_monthly_hours_saved: float
-    implementation_hours: float
-    roi_weeks: float           # weeks to break even
-    priority: str              # "critical", "high", "medium", "low"
-    affected_area: str
-    supporting_evidence: List[str] = field(default_factory=list)
-
-
-# ── Session analysis ──────────────────────────────────────────
-
-def analyze_sessions(sessions: List[dict]) -> List[WastePattern]:
-    """
-    Analyze session data to find waste patterns.
-
-    Looks for:
-    - Repeated errors (same error across sessions)
-    - Manual processes (long sequences of similar actions)
-    - Slow tools (tools with high latency)
-    - Failed retries (multiple attempts at same task)
-    """
-    patterns = []
-
-    # Track error frequency across sessions
-    error_counts: Dict[str, List[dict]] = defaultdict(list)
-    tool_latencies: Dict[str, List[float]] = defaultdict(list)
-    retry_counts: Dict[str, int] = defaultdict(int)
-    manual_sequences: List[dict] = []
-
-    for session in sessions:
-        session_id = session.get("session_id", "unknown")
-        repo = session.get("repo", "global")
-        messages = session.get("messages", [])
-        errors = session.get("errors", [])
-        tool_calls = session.get("tool_calls", [])
-        duration_min = session.get("duration_minutes", 0)
-
-        # 1. Repeated errors
-        for err in errors:
-            err_key = _normalize_error(err.get("message", ""))
-            if err_key:
-                error_counts[err_key].append({
-                    "session_id": session_id,
-                    "repo": repo,
-                })
-
-        # 2. Tool latency tracking
-        for tc in tool_calls:
-            tool_name = tc.get("tool", "unknown")
-            latency = tc.get("latency_ms", 0)
-            if latency > 0:
-                tool_latencies[tool_name].append(latency)
-
-        # 3. Failed retries (same tool called 3+ times in sequence)
-        prev_tool = None
-        streak = 0
-        for tc in tool_calls:
-            tool_name = tc.get("tool", "unknown")
-            if tool_name == prev_tool:
-                streak += 1
-            else:
-                if streak >= 3:
-                    retry_counts[prev_tool] += 1
-                streak = 1
-            prev_tool = tool_name
-        if streak >= 3:
-            retry_counts[prev_tool] += 1
-
-        # 4. Manual processes (10+ sequential tool calls with no automation)
-        if len(tool_calls) > 10:
-            tool_sequence = [tc.get("tool") for tc in tool_calls]
-            unique_tools = set(tool_sequence)
-            if len(unique_tools) <= 3 and len(tool_calls) > 10:
-                manual_sequences.append({
-                    "session_id": session_id,
-                    "repo": repo,
-                    "tool_count": len(tool_calls),
-                    "unique_tools": list(unique_tools),
-                    "duration_min": duration_min,
-                })
-
-    # Generate patterns from collected data
-
-    # Repeated errors (appearing in 3+ sessions)
-    for err_key, occurrences in error_counts.items():
-        if len(occurrences) >= 3:
-            repos = list(set(o["repo"] for o in occurrences))
-            sessions_list = [o["session_id"] for o in occurrences[:5]]
-            # Estimate time wasted: 5 min per error occurrence
-            hours = len(occurrences) * 5 / 60
-            patterns.append(WastePattern(
-                pattern_type="repeated_error",
-                description=f"Error: {err_key[:100]}",
-                occurrences=len(occurrences),
-                total_time_hours=round(hours, 1),
-                affected_repos=repos,
-                example_sessions=sessions_list,
-            ))
-
-    # Slow tools (avg latency > 5000ms across 5+ calls)
-    for tool, latencies in tool_latencies.items():
-        if len(latencies) >= 5:
-            avg_ms = sum(latencies) / len(latencies)
-            if avg_ms > 5000:
-                hours = sum(latencies) / 1000 / 3600
-                patterns.append(WastePattern(
-                    pattern_type="slow_tool",
-                    description=f"Tool '{tool}' averages {avg_ms:.0f}ms latency",
-                    occurrences=len(latencies),
-                    total_time_hours=round(hours, 1),
-                    affected_repos=["global"],
-                    example_sessions=[],
-                ))
-
-    # Failed retries
-    for tool, count in retry_counts.items():
-        if count >= 2:
-            hours = count * 10 / 60  # ~10 min per failed retry sequence
-            patterns.append(WastePattern(
-                pattern_type="failed_retry",
-                description=f"Tool '{tool}' had {count} retry sequences (3+ consecutive calls)",
-                occurrences=count,
-                total_time_hours=round(hours, 1),
-                affected_repos=["global"],
-                example_sessions=[],
-            ))
-
-    # Manual processes
-    for seq in manual_sequences:
-        hours = seq["duration_min"] / 60
-        patterns.append(WastePattern(
-            pattern_type="manual_process",
-            description=f"Session {seq['session_id'][:12]}: {seq['tool_count']} tool calls with only {len(seq['unique_tools'])} unique tools",
-            occurrences=1,
-            total_time_hours=round(hours, 1),
-            affected_repos=[seq["repo"]],
-            example_sessions=[seq["session_id"]],
-        ))
-
-    return sorted(patterns, key=lambda p: p.total_time_hours, reverse=True)
-
-
-def _normalize_error(message: str) -> str:
-    """Normalize error message to a common key."""
-    if not message:
-        return ""
-    msg = message.lower().strip()
-    # Remove variable parts (paths, IDs, timestamps)
-    import re
-    msg = re.sub(r'/\S+', '/PATH', msg)
-    msg = re.sub(r'\b[0-9a-f]{8,}\b', 'HASH', msg)
-    msg = re.sub(r'\d{4}-\d{2}-\d{2}[tT]\d{2}:\d{2}', 'TIME', msg)
-    return msg[:150]
-
-
-# ── Proposal generation ───────────────────────────────────────
-
-def generate_proposals(
-    patterns: List[WastePattern],
-    hourly_rate: float = 50.0,
-    implementation_overhead: float = 1.5,
-) -> List[ImprovementProposal]:
-    """
-    Generate improvement proposals from waste patterns.
-
-    Args:
-        patterns: Detected waste patterns
-        hourly_rate: Developer hourly rate for ROI calculation
-        implementation_overhead: Multiplier for implementation time estimate
-    """
-    proposals = []
-
-    # Group patterns by type
-    by_type: Dict[str, List[WastePattern]] = defaultdict(list)
-    for p in patterns:
-        by_type[p.pattern_type].append(p)
-
-    # 1. Repeated errors → Create fix/skill
-    for p in by_type.get("repeated_error", []):
-        weekly_hours = p.total_time_hours / 4  # monthly → weekly
-        impl_hours = max(1.0, p.occurrences * 0.25) * implementation_overhead
-        roi_weeks = impl_hours / weekly_hours if weekly_hours > 0 else float('inf')
-
-        proposals.append(ImprovementProposal(
-            title=f"Fix repeated error: {p.description[:60]}",
-            problem=f"This error occurred {p.occurrences} times across {len(p.affected_repos)} repos, wasting ~{p.total_time_hours:.1f} hours.",
-            proposed_solution="Root-cause the error and create a permanent fix or mitigation skill.",
-            estimated_weekly_hours_saved=round(weekly_hours, 1),
-            estimated_monthly_hours_saved=round(p.total_time_hours, 1),
-            implementation_hours=round(impl_hours, 1),
-            roi_weeks=round(roi_weeks, 1),
-            priority=_priority_from_roi(roi_weeks),
-            affected_area="reliability",
-            supporting_evidence=[f"{p.occurrences} occurrences in sessions: {', '.join(p.example_sessions[:3])}"],
-        ))
-
-    # 2. Slow tools → Optimize or replace
-    for p in by_type.get("slow_tool", []):
-        weekly_hours = p.total_time_hours / 4
-        impl_hours = 3.0 * implementation_overhead  # optimization task
-        roi_weeks = impl_hours / weekly_hours if weekly_hours > 0 else float('inf')
-
-        proposals.append(ImprovementProposal(
-            title=f"Optimize slow tool: {p.description[:60]}",
-            problem=f"Tool has {p.occurrences} calls with high latency, wasting ~{p.total_time_hours:.1f} hours total.",
-            proposed_solution="Profile the tool, add caching, or replace with a faster alternative.",
-            estimated_weekly_hours_saved=round(weekly_hours, 1),
-            estimated_monthly_hours_saved=round(p.total_time_hours, 1),
-            implementation_hours=round(impl_hours, 1),
-            roi_weeks=round(roi_weeks, 1),
-            priority=_priority_from_roi(roi_weeks),
-            affected_area="performance",
-            supporting_evidence=[f"{p.occurrences} slow calls detected"],
-        ))
-
-    # 3. Failed retries → Add retry logic or validation
-    for p in by_type.get("failed_retry", []):
-        weekly_hours = p.total_time_hours / 4
-        impl_hours = 2.0 * implementation_overhead
-        roi_weeks = impl_hours / weekly_hours if weekly_hours > 0 else float('inf')
-
-        proposals.append(ImprovementProposal(
-            title=f"Reduce retries for tool '{p.description[:50]}'",
-            problem=f"Tool had {p.occurrences} retry sequences, wasting ~{p.total_time_hours:.1f} hours.",
-            proposed_solution="Add input validation, pre-flight checks, or automatic retry with backoff.",
-            estimated_weekly_hours_saved=round(weekly_hours, 1),
-            estimated_monthly_hours_saved=round(p.total_time_hours, 1),
-            implementation_hours=round(impl_hours, 1),
-            roi_weeks=round(roi_weeks, 1),
-            priority=_priority_from_roi(roi_weeks),
-            affected_area="reliability",
-            supporting_evidence=[f"{p.occurrences} retry sequences detected"],
-        ))
-
-    # 4. Manual processes → Automate
-    total_manual_hours = sum(p.total_time_hours for p in by_type.get("manual_process", []))
-    manual_patterns = by_type.get("manual_process", [])
-    if manual_patterns:
-        weekly_hours = total_manual_hours / 4
-        impl_hours = len(manual_patterns) * 2.0 * implementation_overhead
-        roi_weeks = impl_hours / weekly_hours if weekly_hours > 0 else float('inf')
-
-        proposals.append(ImprovementProposal(
-            title=f"Automate {len(manual_patterns)} manual processes",
-            problem=f"{len(manual_patterns)} sessions had long manual tool sequences, wasting ~{total_manual_hours:.1f} hours.",
-            proposed_solution="Create composite skills or scripts that combine the repeated tool sequences into single operations.",
-            estimated_weekly_hours_saved=round(weekly_hours, 1),
-            estimated_monthly_hours_saved=round(total_manual_hours, 1),
-            implementation_hours=round(impl_hours, 1),
-            roi_weeks=round(roi_weeks, 1),
-            priority=_priority_from_roi(roi_weeks),
-            affected_area="automation",
-            supporting_evidence=[f"{len(manual_patterns)} manual sessions detected"],
-        ))
-
-    return sorted(proposals, key=lambda p: p.estimated_monthly_hours_saved, reverse=True)
-
-
-def _priority_from_roi(roi_weeks: float) -> str:
-    """Determine priority from ROI break-even time."""
-    if roi_weeks <= 1:
-        return "critical"
-    elif roi_weeks <= 4:
-        return "high"
-    elif roi_weeks <= 12:
-        return "medium"
-    return "low"
-
-
-# ── Output formatting ─────────────────────────────────────────
-
-def format_proposals_markdown(
-    proposals: List[ImprovementProposal],
-    patterns: List[WastePattern],
-    generated_at: str,
-) -> str:
-    """Format proposals as a markdown document."""
-    lines = [
-        "# Improvement Proposals",
-        "",
-        f"Generated: {generated_at}",
-        f"Based on analysis of {sum(p.occurrences for p in patterns)} waste events across {len(set(r for p in patterns for r in p.affected_repos))} repos.",
-        "",
-        "---",
-        "",
-        "## Summary",
-        "",
-        f"| Metric | Value |",
-        f"|--------|-------|",
-        f"| Total proposals | {len(proposals)} |",
-        f"| Critical priority | {sum(1 for p in proposals if p.priority == 'critical')} |",
-        f"| Total monthly hours wasted | {sum(p.estimated_monthly_hours_saved for p in proposals):.1f}h |",
-        f"| Total weekly hours recoverable | {sum(p.estimated_weekly_hours_saved for p in proposals):.1f}h |",
-        f"| Implementation investment | {sum(p.implementation_hours for p in proposals):.1f}h |",
-        "",
-        "---",
-        "",
-    ]
-
-    for i, prop in enumerate(proposals, 1):
-        lines.extend([
-            f"## {i}. {prop.title}",
-            "",
-            f"**Priority:** {prop.priority.upper()}  ",
-            f"**Area:** {prop.affected_area}  ",
-            f"**ROI break-even:** {prop.roi_weeks:.1f} weeks",
-            "",
-            "### Problem",
-            "",
-            prop.problem,
-            "",
-            "### Proposed Solution",
-            "",
-            prop.proposed_solution,
-            "",
-            "### ROI Estimate",
-            "",
-            f"- Weekly hours saved: **{prop.estimated_weekly_hours_saved}h**",
-            f"- Monthly hours saved: **{prop.estimated_monthly_hours_saved}h**",
-            f"- Implementation time: **{prop.implementation_hours}h**",
-            f"- Break-even: **{prop.roi_weeks:.1f} weeks**",
-            "",
-        ])
-
-        if prop.supporting_evidence:
-            lines.extend([
-                "### Evidence",
-                "",
-            ])
-            for ev in prop.supporting_evidence:
-                lines.append(f"- {ev}")
-            lines.append("")
-
-        lines.extend(["---", ""])
-
-    # Waste pattern appendix
-    lines.extend([
-        "## Appendix: Detected Waste Patterns",
-        "",
-        "| Type | Description | Occurrences | Hours |",
-        "|------|-------------|-------------|-------|",
-    ])
-    for p in patterns[:20]:
-        lines.append(
-            f"| {p.pattern_type} | {p.description[:60]} | {p.occurrences} | {p.total_time_hours}h |"
-        )
-    lines.append("")
-
-    return "\n".join(lines)
-
-
-def format_proposals_json(proposals: List[ImprovementProposal]) -> str:
-    """Format proposals as JSON."""
-    return json.dumps(
-        [asdict(p) for p in proposals],
-        indent=2,
-        default=str,
-    )
-
-
-# ── Main ──────────────────────────────────────────────────────
-
-def main():
-    parser = argparse.ArgumentParser(description="Generate improvement proposals from session analytics")
-    parser.add_argument("--input", required=True, help="Path to session analytics JSON file")
-    parser.add_argument("--output", help="Output file path (default: stdout)")
-    parser.add_argument("--format", choices=["markdown", "json"], default="markdown", help="Output format")
-    parser.add_argument("--hourly-rate", type=float, default=50.0, help="Developer hourly rate for ROI calc")
-    parser.add_argument("--threshold", type=float, default=2.0, help="Min monthly hours to include proposal")
-
-    args = parser.parse_args()
-
-    with open(args.input) as f:
-        data = json.load(f)
-
-    sessions = data if isinstance(data, list) else data.get("sessions", [])
-
-    if not sessions:
-        print("No sessions found in input file.", file=sys.stderr)
-        sys.exit(1)
-
-    # Analyze
-    patterns = analyze_sessions(sessions)
-    proposals = generate_proposals(patterns, hourly_rate=args.hourly_rate)
-
-    # Filter by threshold
-    proposals = [p for p in proposals if p.estimated_monthly_hours_saved >= args.threshold]
-
-    generated_at = datetime.now(timezone.utc).isoformat()
-
-    if args.format == "markdown":
-        output = format_proposals_markdown(proposals, patterns, generated_at)
-    else:
-        output = format_proposals_json(proposals)
-
-    if args.output:
-        with open(args.output, "w") as f:
-            f.write(output)
-        print(f"Wrote {len(proposals)} proposals to {args.output}", file=sys.stderr)
-    else:
-        print(output)
-
-
-if __name__ == "__main__":
-    main()

scripts/knowledge_staleness_check.py

@@ -1,131 +0,0 @@
-#!/usr/bin/env python3
-"""
-Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
-
-Usage:
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
-"""
-
-import argparse
-import hashlib
-import json
-import os
-import sys
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Dict, List, Any, Optional
-
-
-def compute_file_hash(filepath: str) -> Optional[str]:
-    """Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
-    try:
-        with open(filepath, "rb") as f:
-            return "sha256:" + hashlib.sha256(f.read()).hexdigest()
-    except (FileNotFoundError, IsADirectoryError, PermissionError):
-        return None
-
-
-def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
-    """Check all entries in knowledge index for staleness.
-    
-    Returns list of entries with staleness info:
-    - status: "fresh" | "stale" | "missing_source" | "no_hash"
-    - current_hash: computed hash (if source exists)
-    - stored_hash: hash from index
-    """
-    with open(index_path) as f:
-        data = json.load(f)
-
-    facts = data.get("facts", [])
-    results = []
-
-    for entry in facts:
-        source_file = entry.get("source_file")
-        stored_hash = entry.get("source_hash")
-
-        if not source_file:
-            results.append({**entry, "status": "no_source", "current_hash": None})
-            continue
-
-        full_path = os.path.join(repo_root, source_file)
-        current_hash = compute_file_hash(full_path)
-
-        if current_hash is None:
-            results.append({**entry, "status": "missing_source", "current_hash": None})
-        elif not stored_hash:
-            results.append({**entry, "status": "no_hash", "current_hash": current_hash})
-        elif current_hash != stored_hash:
-            results.append({**entry, "status": "stale", "current_hash": current_hash})
-        else:
-            results.append({**entry, "status": "fresh", "current_hash": current_hash})
-
-    return results
-
-
-def fix_hashes(index_path: str, repo_root: str = ".") -> int:
-    """Add hashes to entries missing them. Returns count of fixed entries."""
-    with open(index_path) as f:
-        data = json.load(f)
-
-    fixed = 0
-    for entry in data.get("facts", []):
-        if entry.get("source_hash"):
-            continue
-        source_file = entry.get("source_file")
-        if not source_file:
-            continue
-        full_path = os.path.join(repo_root, source_file)
-        h = compute_file_hash(full_path)
-        if h:
-            entry["source_hash"] = h
-            fixed += 1
-
-    with open(index_path, "w") as f:
-        json.dump(data, f, indent=2)
-
-    return fixed
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Check knowledge store staleness")
-    parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
-    parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
-    parser.add_argument("--json", action="store_true", help="Output as JSON")
-    parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
-
-    args = parser.parse_args()
-
-    if args.fix:
-        fixed = fix_hashes(args.index, args.repo)
-        print(f"Fixed {fixed} entries with missing hashes.")
-        return
-
-    results = check_staleness(args.index, args.repo)
-
-    if args.json:
-        print(json.dumps(results, indent=2))
-    else:
-        stale = [r for r in results if r["status"] != "fresh"]
-        fresh = [r for r in results if r["status"] == "fresh"]
-
-        print(f"Knowledge Store Staleness Check")
-        print(f"  Total entries: {len(results)}")
-        print(f"  Fresh: {len(fresh)}")
-        print(f"  Stale/Issues: {len(stale)}")
-        print()
-
-        if stale:
-            print("Issues found:")
-            for r in stale:
-                status = r["status"]
-                fact = r.get("fact", "?")[:60]
-                source = r.get("source_file", "?")
-                print(f"  [{status}] {source}: {fact}")
-        else:
-            print("All entries are fresh!")
-
-
-if __name__ == "__main__":
-    main()

scripts/session_reader.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+session_reader.py — Parse Hermes session JSONL transcripts.
+
+Each line in a session file is a JSON object representing a message.
+Standard fields: role (user|assistant|system), content (str), timestamp (str).
+Tool calls and tool results are also captured.
+"""
+
+import json
+import sys
+from pathlib import Path
+from typing import Iterator, Optional
+
+
+def read_session(path: str) -> list[dict]:
+    """Read a session JSONL file and return all messages as a list."""
+    messages = []
+    with open(path, 'r', encoding='utf-8') as f:
+        for line_num, line in enumerate(f, 1):
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                msg = json.loads(line)
+                messages.append(msg)
+            except json.JSONDecodeError as e:
+                print(f"WARNING: Skipping malformed JSON at line {line_num}: {e}", file=sys.stderr)
+    return messages
+
+
+def read_session_iter(path: str) -> Iterator[dict]:
+    """Iterate over session messages without loading all into memory."""
+    with open(path, 'r', encoding='utf-8') as f:
+        for line_num, line in enumerate(f, 1):
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                yield json.loads(line)
+            except json.JSONDecodeError as e:
+                print(f"WARNING: Skipping malformed JSON at line {line_num}: {e}", file=sys.stderr)
+
+
+def extract_conversation(messages: list[dict]) -> list[dict]:
+    """Extract user/assistant conversation turns, skipping tool-only messages."""
+    conversation = []
+    for msg in messages:
+        role = msg.get('role', '')
+        content = msg.get('content', '')
+        
+        # Skip empty messages and pure tool calls
+        if role in ('user', 'assistant', 'system'):
+            if isinstance(content, str) and content.strip():
+                conversation.append({
+                    'role': role,
+                    'content': content.strip(),
+                    'timestamp': msg.get('timestamp', '')
+                })
+            elif isinstance(content, list):
+                # Multimodal content — extract text parts
+                text_parts = []
+                for part in content:
+                    if isinstance(part, dict) and part.get('type') == 'text':
+                        text_parts.append(part.get('text', ''))
+                if text_parts:
+                    conversation.append({
+                        'role': role,
+                        'content': '\n'.join(text_parts),
+                        'timestamp': msg.get('timestamp', '')
+                    })
+    return conversation
+
+
+def truncate_for_context(messages: list[dict], head: int = 50, tail: int = 50) -> list[dict]:
+    """Truncate long sessions: keep first N + last N messages.
+    
+    This preserves session start (initial context) and end (final results),
+    skipping the messy middle of long debugging sessions.
+    """
+    if len(messages) <= head + tail:
+        return messages
+    
+    truncated = messages[:head]
+    truncated.append({
+        'role': 'system',
+        'content': f'[{len(messages) - head - tail} messages truncated]',
+        'timestamp': ''
+    })
+    truncated.extend(messages[-tail:])
+    return truncated
+
+
+def messages_to_text(messages: list[dict]) -> str:
+    """Convert message list to plain text for LLM consumption."""
+    lines = []
+    for msg in messages:
+        role = msg.get('role', 'unknown').upper()
+        content = msg.get('content', '')
+        if msg.get('role') == 'system' and 'truncated' in content:
+            lines.append(f'--- {content} ---')
+        else:
+            lines.append(f'{role}: {content}')
+    return '\n\n'.join(lines)
+
+
+def get_session_metadata(path: str) -> dict:
+    """Extract metadata from a session file (first message often has config info)."""
+    messages = read_session(path)
+    if not messages:
+        return {'path': path, 'message_count': 0}
+    
+    first = messages[0]
+    last = messages[-1]
+    
+    return {
+        'path': path,
+        'message_count': len(messages),
+        'first_timestamp': first.get('timestamp', ''),
+        'last_timestamp': last.get('timestamp', ''),
+        'first_role': first.get('role', ''),
+        'has_tool_calls': any(m.get('tool_calls') for m in messages),
+    }
+
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        print(f"Usage: {sys.argv[0]} <session.jsonl>")
+        sys.exit(1)
+    
+    path = sys.argv[1]
+    meta = get_session_metadata(path)
+    print(json.dumps(meta, indent=2))
+    
+    messages = read_session(path)
+    conv = extract_conversation(messages)
+    print(f"\nConversation: {len(conv)} turns")
+    
+    truncated = truncate_for_context(conv)
+    print(f"After truncation: {len(truncated)} turns")
+    print(f"\nPreview (first 500 chars):")
+    print(messages_to_text(truncated[:5])[:500])

scripts/test_harvest_prompt_comprehensive.py

@@ -1,212 +0,0 @@
-#!/usr/bin/env python3
-"""
-Comprehensive test script for knowledge extraction prompt.
-Validates prompt structure, requirements, and consistency.
-"""
-
-import json
-import re
-from pathlib import Path
-
-def test_prompt_structure():
-    """Test that the prompt has the required structure."""
-    prompt_path = Path("templates/harvest-prompt.md")
-    if not prompt_path.exists():
-        return False, "harvest-prompt.md not found"
-    
-    content = prompt_path.read_text()
-    
-    # Check for required sections
-    required_sections = [
-        "System Prompt",
-        "Instructions", 
-        "Categories",
-        "Output Format",
-        "Confidence Scoring",
-        "Constraints",
-        "Example"
-    ]
-    
-    for section in required_sections:
-        if section.lower() not in content.lower():
-            return False, f"Missing required section: {section}"
-    
-    # Check for required categories
-    required_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
-    for category in required_categories:
-        if category not in content:
-            return False, f"Missing required category: {category}"
-    
-    # Check for required output fields
-    required_fields = ["fact", "category", "repo", "confidence"]
-    for field in required_fields:
-        if field not in content:
-            return False, f"Missing required output field: {field}"
-    
-    # Check prompt size (should be ~1k tokens, roughly 4k chars)
-    if len(content) > 5000:
-        return False, f"Prompt too large: {len(content)} chars (max ~5000)"
-    
-    if len(content) < 1000:
-        return False, f"Prompt too small: {len(content)} chars (min ~1000)"
-    
-    return True, "Prompt structure is valid"
-
-def test_confidence_scoring():
-    """Test that confidence scoring is properly defined."""
-    prompt_path = Path("templates/harvest-prompt.md")
-    content = prompt_path.read_text()
-    
-    # Check for confidence scale definitions
-    confidence_levels = [
-        ("0.9-1.0", "explicitly stated"),
-        ("0.7-0.8", "clearly implied"),
-        ("0.5-0.6", "suggested"),
-        ("0.3-0.4", "inferred"),
-        ("0.1-0.2", "speculative")
-    ]
-    
-    for level, description in confidence_levels:
-        if level not in content:
-            return False, f"Missing confidence level: {level}"
-        if description.lower() not in content.lower():
-            return False, f"Missing confidence description: {description}"
-    
-    return True, "Confidence scoring is properly defined"
-
-def test_example_quality():
-    """Test that examples are clear and complete."""
-    prompt_path = Path("templates/harvest-prompt.md")
-    content = prompt_path.read_text()
-    
-    # Check for example input/output
-    if "example" not in content.lower():
-        return False, "No examples provided"
-    
-    # Check that example includes all categories
-    example_section = content[content.lower().find("example"):]
-    
-    # Look for JSON example
-    json_match = re.search(r'\{[\s\S]*"knowledge"[\s\S]*\}', example_section)
-    if not json_match:
-        return False, "No JSON example found"
-    
-    example_json = json_match.group(0)
-    
-    # Check for all categories in example
-    for category in ["fact", "pitfall", "pattern", "tool-quirk", "question"]:
-        if category not in example_json:
-            return False, f"Example missing category: {category}"
-    
-    return True, "Examples are clear and complete"
-
-def test_constraint_coverage():
-    """Test that constraints cover all requirements."""
-    prompt_path = Path("templates/harvest-prompt.md")
-    content = prompt_path.read_text()
-    
-    required_constraints = [
-        "No hallucination",
-        "only extract",
-        "explicitly",
-        "partial",
-        "failed sessions",
-        "1k tokens"
-    ]
-    
-    for constraint in required_constraints:
-        if constraint.lower() not in content.lower():
-            return False, f"Missing constraint: {constraint}"
-    
-    return True, "Constraints cover all requirements"
-
-def test_test_sessions():
-    """Test that test sessions exist and are valid."""
-    test_sessions_dir = Path("test_sessions")
-    if not test_sessions_dir.exists():
-        return False, "test_sessions directory not found"
-    
-    session_files = list(test_sessions_dir.glob("*.jsonl"))
-    if len(session_files) < 5:
-        return False, f"Only {len(session_files)} test sessions found, need 5"
-    
-    # Check each session file
-    for session_file in session_files:
-        content = session_file.read_text()
-        lines = content.strip().split("\n")
-        
-        # Check that each line is valid JSON
-        for i, line in enumerate(lines, 1):
-            try:
-                json.loads(line)
-            except json.JSONDecodeError as e:
-                return False, f"Invalid JSON in {session_file.name}, line {i}: {e}"
-    
-    return True, f"Found {len(session_files)} valid test sessions"
-
-def run_all_tests():
-    """Run all tests and return results."""
-    tests = [
-        ("Prompt Structure", test_prompt_structure),
-        ("Confidence Scoring", test_confidence_scoring),
-        ("Example Quality", test_example_quality),
-        ("Constraint Coverage", test_constraint_coverage),
-        ("Test Sessions", test_test_sessions)
-    ]
-    
-    results = []
-    all_passed = True
-    
-    for test_name, test_func in tests:
-        try:
-            passed, message = test_func()
-            results.append({
-                "test": test_name,
-                "passed": passed,
-                "message": message
-            })
-            if not passed:
-                all_passed = False
-        except Exception as e:
-            results.append({
-                "test": test_name,
-                "passed": False,
-                "message": f"Error: {str(e)}"
-            })
-            all_passed = False
-    
-    # Print results
-    print("=" * 60)
-    print("HARVEST PROMPT TEST RESULTS")
-    print("=" * 60)
-    
-    for result in results:
-        status = "✓ PASS" if result["passed"] else "✗ FAIL"
-        print(f"{status}: {result['test']}")
-        print(f"  {result['message']}")
-        print()
-    
-    print("=" * 60)
-    if all_passed:
-        print("ALL TESTS PASSED!")
-    else:
-        print("SOME TESTS FAILED!")
-    print("=" * 60)
-    
-    return all_passed, results
-
-if __name__ == "__main__":
-    all_passed, results = run_all_tests()
-    
-    # Save results to file
-    with open("test_results.json", "w") as f:
-        json.dump({
-            "all_passed": all_passed,
-            "results": results,
-            "timestamp": "2026-04-14T19:05:00Z"
-        }, f, indent=2)
-    
-    print(f"Results saved to test_results.json")
-    
-    # Exit with appropriate code
-    exit(0 if all_passed else 1)

scripts/test_harvester_pipeline.py

@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+"""
+Smoke test for harvester pipeline — verifies the full chain:
+session_reader -> prompt -> LLM (mocked) -> validate -> deduplicate -> store
+
+Does NOT call the real LLM. Tests plumbing only.
+"""
+
+import json
+import sys
+import tempfile
+import os
+from pathlib import Path
+
+# Setup path
+SCRIPT_DIR = Path(__file__).parent.absolute()
+sys.path.insert(0, str(SCRIPT_DIR))
+
+from session_reader import read_session, extract_conversation, truncate_for_context, messages_to_text
+from harvester import validate_fact, deduplicate, load_existing_knowledge, fact_fingerprint
+
+
+def test_session_reader():
+    """Test that session_reader parses JSONL correctly."""
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.jsonl', delete=False) as f:
+        f.write('{"role": "user", "content": "Hello", "timestamp": "2026-04-13T10:00:00Z"}\n')
+        f.write('{"role": "assistant", "content": "Hi there", "timestamp": "2026-04-13T10:00:01Z"}\n')
+        f.write('{"role": "user", "content": "Clone the repo", "timestamp": "2026-04-13T10:00:02Z"}\n')
+        f.write('{"role": "assistant", "content": "Cloned successfully", "timestamp": "2026-04-13T10:00:05Z"}\n')
+        path = f.name
+
+    messages = read_session(path)
+    assert len(messages) == 4, f"Expected 4 messages, got {len(messages)}"
+
+    conv = extract_conversation(messages)
+    assert len(conv) == 4, f"Expected 4 conversation turns, got {len(conv)}"
+
+    text = messages_to_text(conv)
+    assert "USER: Hello" in text
+    assert "ASSISTANT: Hi there" in text
+
+    truncated = truncate_for_context(conv, head=2, tail=2)
+    assert len(truncated) == 4  # 4 <= head+tail, so no truncation
+
+    os.unlink(path)
+    print("  [PASS] session_reader pipeline works")
+
+
+def test_validate_fact():
+    """Test fact validation."""
+    good = {"fact": "Gitea token is at ~/.config/gitea/token", "category": "tool-quirk", "repo": "global", "confidence": 0.9}
+    assert validate_fact(good), "Valid fact should pass"
+
+    bad_missing = {"fact": "Something", "category": "fact"}
+    assert not validate_fact(bad_missing), "Missing fields should fail"
+
+    bad_category = {"fact": "Something", "category": "nonsense", "repo": "x", "confidence": 0.5}
+    assert not validate_fact(bad_category), "Bad category should fail"
+
+    bad_conf = {"fact": "Something", "category": "fact", "repo": "x", "confidence": 1.5}
+    assert not validate_fact(bad_conf), "Confidence > 1.0 should fail"
+
+    print("  [PASS] fact validation works")
+
+
+def test_deduplicate():
+    """Test deduplication."""
+    existing = [
+        {"fact": "Token is at ~/.config/gitea/token", "category": "tool-quirk", "repo": "global", "confidence": 0.9}
+    ]
+    new = [
+        {"fact": "Token is at ~/.config/gitea/token", "category": "tool-quirk", "repo": "global", "confidence": 0.9},  # exact dup
+        {"fact": "Deploy uses Ansible on port 22", "category": "pattern", "repo": "fleet", "confidence": 0.8},  # unique
+    ]
+    result = deduplicate(new, existing)
+    assert len(result) == 1, f"Expected 1 unique, got {len(result)}"
+    assert result[0]["fact"] == "Deploy uses Ansible on port 22"
+    print("  [PASS] deduplication works")
+
+
+def test_knowledge_store_roundtrip():
+    """Test loading and writing knowledge index."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        # Load empty index
+        index = load_existing_knowledge(tmpdir)
+        assert index["total_facts"] == 0
+
+        # Write a fact
+        new_facts = [{"fact": "Test fact", "category": "fact", "repo": "test", "confidence": 0.9}]
+
+        # Use harvester's write function
+        from harvester import write_knowledge
+        write_knowledge(index, new_facts, tmpdir, source_session="test.jsonl")
+
+        # Reload and verify
+        index2 = load_existing_knowledge(tmpdir)
+        assert index2["total_facts"] == 1
+        assert index2["facts"][0]["fact"] == "Test fact"
+        assert index2["facts"][0]["source_session"] == "test.jsonl"
+
+        # Check markdown was written
+        md_path = Path(tmpdir) / "repos" / "test.md"
+        assert md_path.exists(), "Markdown file should be created"
+
+    print("  [PASS] knowledge store roundtrip works")
+
+
+def test_full_chain_no_llm():
+    """Test the full pipeline minus the LLM call."""
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.jsonl', delete=False) as f:
+        f.write('{"role": "user", "content": "Clone compounding-intelligence", "timestamp": "2026-04-13T10:00:00Z"}\n')
+        f.write('{"role": "assistant", "content": "Cloned successfully", "timestamp": "2026-04-13T10:00:05Z"}\n')
+        session_path = f.name
+
+    with tempfile.TemporaryDirectory() as knowledge_dir:
+        # Step 1: Read
+        messages = read_session(session_path)
+        assert len(messages) == 2
+
+        # Step 2: Extract conversation
+        conv = extract_conversation(messages)
+        assert len(conv) == 2
+
+        # Step 3: Truncate
+        truncated = truncate_for_context(conv, head=50, tail=50)
+
+        # Step 4: Convert to text (this goes to the LLM)
+        transcript = messages_to_text(truncated)
+        assert "Clone compounding-intelligence" in transcript
+
+        # Step 5-7: Would be LLM call, validate, deduplicate
+        # We simulate LLM output here
+        mock_facts = [
+            {"fact": "compounding-intelligence repo was cloned", "category": "fact", "repo": "compounding-intelligence", "confidence": 0.9}
+        ]
+        valid = [f for f in mock_facts if validate_fact(f)]
+
+        # Step 6: Deduplicate
+        index = load_existing_knowledge(knowledge_dir)
+        new_facts = deduplicate(valid, index.get("facts", []))
+        assert len(new_facts) == 1
+
+        # Step 7: Store
+        from harvester import write_knowledge
+        write_knowledge(index, new_facts, knowledge_dir, source_session=session_path)
+
+        # Verify
+        index2 = load_existing_knowledge(knowledge_dir)
+        assert index2["total_facts"] == 1
+
+    os.unlink(session_path)
+    print("  [PASS] full chain (reader -> validate -> dedup -> store) works")
+
+
+if __name__ == "__main__":
+    print("Running harvester pipeline smoke tests...")
+    test_session_reader()
+    test_validate_fact()
+    test_deduplicate()
+    test_knowledge_store_roundtrip()
+    test_full_chain_no_llm()
+    print("\nAll tests passed.")

scripts/test_improvement_proposals.py

@@ -1,282 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/improvement_proposals.py — 15 tests."""
-
-import json
-import os
-import sys
-import tempfile
-
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-import importlib.util
-
-spec = importlib.util.spec_from_file_location(
-    "ip", os.path.join(os.path.dirname(__file__) or ".", "improvement_proposals.py")
-)
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-
-analyze_sessions = mod.analyze_sessions
-generate_proposals = mod.generate_proposals
-format_proposals_markdown = mod.format_proposals_markdown
-format_proposals_json = mod.format_proposals_json
-_normalize_error = mod._normalize_error
-
-
-# ── Helper to build test sessions ─────────────────────────────
-
-def _make_session(session_id, repo="test-repo", errors=None, tool_calls=None, duration=30):
-    return {
-        "session_id": session_id,
-        "repo": repo,
-        "errors": [{"message": e} for e in (errors or [])],
-        "tool_calls": tool_calls or [],
-        "duration_minutes": duration,
-        "messages": [],
-    }
-
-
-def _make_tool_calls(repeats):
-    """Create tool call list with repeated tools."""
-    calls = []
-    for tool, count in repeats:
-        for _ in range(count):
-            calls.append({"tool": tool, "latency_ms": 100})
-    return calls
-
-
-# ── Tests ─────────────────────────────────────────────────────
-
-def test_empty_sessions():
-    patterns = analyze_sessions([])
-    assert patterns == []
-    print("PASS: test_empty_sessions")
-
-
-def test_no_patterns_on_clean_sessions():
-    sessions = [
-        _make_session("s1", tool_calls=[{"tool": "read_file", "latency_ms": 50}]),
-        _make_session("s2", tool_calls=[{"tool": "write_file", "latency_ms": 80}]),
-    ]
-    patterns = analyze_sessions(sessions)
-    # No repeated errors, no slow tools, no retries
-    assert len(patterns) == 0
-    print("PASS: test_no_patterns_on_clean_sessions")
-
-
-def test_repeated_error_detection():
-    """Same error across 3+ sessions triggers pattern."""
-    sessions = [
-        _make_session(f"s{i}", errors=["ModuleNotFoundError: No module named bannerlord_trace"])
-        for i in range(4)
-    ]
-    patterns = analyze_sessions(sessions)
-    repeated = [p for p in patterns if p.pattern_type == "repeated_error"]
-    assert len(repeated) == 1
-    assert repeated[0].occurrences == 4
-    print("PASS: test_repeated_error_detection")
-
-
-def test_repeated_error_threshold():
-    """2 occurrences should NOT trigger (threshold is 3)."""
-    sessions = [
-        _make_session("s1", errors=["TimeoutError: connection timed out"]),
-        _make_session("s2", errors=["TimeoutError: connection timed out"]),
-    ]
-    patterns = analyze_sessions(sessions)
-    repeated = [p for p in patterns if p.pattern_type == "repeated_error"]
-    assert len(repeated) == 0
-    print("PASS: test_repeated_error_threshold")
-
-
-def test_slow_tool_detection():
-    """Tool with avg latency > 5000ms across 5+ calls."""
-    calls = [{"tool": "git_push", "latency_ms": 8000} for _ in range(10)]
-    sessions = [_make_session("s1", tool_calls=calls)]
-    patterns = analyze_sessions(sessions)
-    slow = [p for p in patterns if p.pattern_type == "slow_tool"]
-    assert len(slow) == 1
-    assert "git_push" in slow[0].description
-    print("PASS: test_slow_tool_detection")
-
-
-def test_fast_tool_not_flagged():
-    """Tool under 5000ms avg should not trigger."""
-    calls = [{"tool": "read_file", "latency_ms": 50} for _ in range(10)]
-    sessions = [_make_session("s1", tool_calls=calls)]
-    patterns = analyze_sessions(sessions)
-    slow = [p for p in patterns if p.pattern_type == "slow_tool"]
-    assert len(slow) == 0
-    print("PASS: test_fast_tool_not_flagged")
-
-
-def test_failed_retry_detection():
-    """3+ consecutive calls to same tool triggers retry pattern."""
-    calls = _make_tool_calls([("execute_code", 5)])
-    sessions = [_make_session("s1", tool_calls=calls)]
-    sessions.extend([
-        _make_session(f"s{i}", tool_calls=_make_tool_calls([("execute_code", 4)]))
-        for i in range(2, 5)
-    ])
-    patterns = analyze_sessions(sessions)
-    retries = [p for p in patterns if p.pattern_type == "failed_retry"]
-    assert len(retries) >= 1
-    print("PASS: test_failed_retry_detection")
-
-
-def test_manual_process_detection():
-    """10+ tool calls with <= 3 unique tools."""
-    calls = _make_tool_calls([("terminal", 8), ("read_file", 5)])
-    sessions = [_make_session("s1", tool_calls=calls, duration=25)]
-    patterns = analyze_sessions(sessions)
-    manual = [p for p in patterns if p.pattern_type == "manual_process"]
-    assert len(manual) == 1
-    print("PASS: test_manual_process_detection")
-
-
-def test_generate_proposals_from_patterns():
-    """Proposals generated from waste patterns."""
-    sessions = [
-        _make_session(f"s{i}", errors=["Error: push timeout"])
-        for i in range(5)
-    ]
-    patterns = analyze_sessions(sessions)
-    proposals = generate_proposals(patterns)
-    assert len(proposals) >= 1
-    assert proposals[0].estimated_monthly_hours_saved > 0
-    assert proposals[0].priority in ("critical", "high", "medium", "low")
-    print("PASS: test_generate_proposals_from_patterns")
-
-
-def test_proposal_roi_positive():
-    """ROI weeks should be a positive number for recoverable time."""
-    patterns = [mod.WastePattern(
-        pattern_type="repeated_error",
-        description="Test error",
-        occurrences=10,
-        total_time_hours=5.0,
-        affected_repos=["test"],
-    )]
-    proposals = generate_proposals(patterns)
-    assert len(proposals) == 1
-    assert proposals[0].roi_weeks > 0
-    assert proposals[0].roi_weeks < 100
-    print("PASS: test_proposal_roi_positive")
-
-
-def test_proposals_sorted_by_impact():
-    """Proposals should be sorted by monthly hours saved (descending)."""
-    sessions = [
-        _make_session("s1", errors=["Minor warning"] * 3, duration=5),
-        _make_session("s2", errors=["Critical failure: deploy crashed"] * 5, duration=60),
-    ]
-    # Add more sessions to cross threshold
-    for i in range(3, 7):
-        sessions.append(_make_session(f"s{i}", errors=["Critical failure: deploy crashed"]))
-
-    patterns = analyze_sessions(sessions)
-    proposals = generate_proposals(patterns)
-    if len(proposals) >= 2:
-        for i in range(len(proposals) - 1):
-            assert proposals[i].estimated_monthly_hours_saved >= proposals[i + 1].estimated_monthly_hours_saved
-    print("PASS: test_proposals_sorted_by_impact")
-
-
-def test_format_markdown():
-    """Markdown output should contain expected sections."""
-    patterns = [mod.WastePattern(
-        pattern_type="repeated_error", description="Test", occurrences=5,
-        total_time_hours=2.5, affected_repos=["repo"],
-    )]
-    proposals = generate_proposals(patterns)
-    md = format_proposals_markdown(proposals, patterns, "2026-04-15T00:00:00Z")
-    assert "# Improvement Proposals" in md
-    assert "## Summary" in md
-    assert "### Problem" in md
-    assert "### ROI Estimate" in md
-    assert "## Appendix" in md
-    print("PASS: test_format_markdown")
-
-
-def test_format_json():
-    """JSON output should be valid and parseable."""
-    patterns = [mod.WastePattern(
-        pattern_type="slow_tool", description="Slow", occurrences=10,
-        total_time_hours=3.0, affected_repos=["global"],
-    )]
-    proposals = generate_proposals(patterns)
-    output = format_proposals_json(proposals)
-    parsed = json.loads(output)
-    assert isinstance(parsed, list)
-    assert len(parsed) == len(proposals)
-    assert "title" in parsed[0]
-    assert "roi_weeks" in parsed[0]
-    print("PASS: test_format_json")
-
-
-def test_normalize_error():
-    """Error normalization should remove paths and hashes."""
-    err1 = _normalize_error("Failed to clone /Users/apayne/repo with token abc123def456")
-    assert "/PATH" in err1
-    assert "HASH" in err1
-    assert "/Users/apayne" not in err1
-
-    err2 = _normalize_error("")
-    assert err2 == ""
-
-    err3 = _normalize_error("Simple error message")
-    assert "simple error" in err3
-    print("PASS: test_normalize_error")
-
-
-def test_cli_integration():
-    """End-to-end test: write input JSON, run script, check output."""
-    import subprocess
-
-    sessions = [
-        _make_session(f"s{i}", errors=["Connection refused: port 8080"])
-        for i in range(5)
-    ]
-
-    with tempfile.TemporaryDirectory() as tmpdir:
-        input_path = os.path.join(tmpdir, "analytics.json")
-        output_path = os.path.join(tmpdir, "proposals.md")
-
-        with open(input_path, "w") as f:
-            json.dump({"sessions": sessions}, f)
-
-        script = os.path.join(os.path.dirname(__file__) or ".", "improvement_proposals.py")
-        result = subprocess.run(
-            [sys.executable, script, "--input", input_path, "--output", output_path],
-            capture_output=True, text=True, timeout=10,
-        )
-
-        assert result.returncode == 0, f"CLI failed: {result.stderr}"
-        assert os.path.exists(output_path)
-
-        with open(output_path) as f:
-            content = f.read()
-        assert "# Improvement Proposals" in content
-        print("PASS: test_cli_integration")
-
-
-def run_all():
-    test_empty_sessions()
-    test_no_patterns_on_clean_sessions()
-    test_repeated_error_detection()
-    test_repeated_error_threshold()
-    test_slow_tool_detection()
-    test_fast_tool_not_flagged()
-    test_failed_retry_detection()
-    test_manual_process_detection()
-    test_generate_proposals_from_patterns()
-    test_proposal_roi_positive()
-    test_proposals_sorted_by_impact()
-    test_format_markdown()
-    test_format_json()
-    test_normalize_error()
-    test_cli_integration()
-    print("\nAll 15 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()

scripts/test_knowledge_staleness.py

@@ -1,129 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
-
-import json
-import os
-import sys
-import tempfile
-
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-import importlib.util
-spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-check_staleness = mod.check_staleness
-fix_hashes = mod.fix_hashes
-compute_file_hash = mod.compute_file_hash
-
-
-def test_fresh_entry():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("print('hello')")
-        h = compute_file_hash(src)
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "fresh"
-        print("PASS: test_fresh_entry")
-
-
-def test_stale_entry():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("original content")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
-        # Now change the source
-        with open(src, "w") as f:
-            f.write("modified content")
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "stale"
-        print("PASS: test_stale_entry")
-
-
-def test_missing_source():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "missing_source"
-        print("PASS: test_missing_source")
-
-
-def test_no_hash():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("content")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "no_hash"
-        assert results[0]["current_hash"].startswith("sha256:")
-        print("PASS: test_no_hash")
-
-
-def test_no_source_field():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "orphan"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "no_source"
-        print("PASS: test_no_source_field")
-
-
-def test_fix_hashes():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("content for hashing")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
-        fixed = fix_hashes(idx, tmpdir)
-        assert fixed == 1
-        # Verify hash was added
-        with open(idx) as f:
-            data = json.load(f)
-        assert data["facts"][0]["source_hash"].startswith("sha256:")
-        print("PASS: test_fix_hashes")
-
-
-def test_empty_index():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": []}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results == []
-        print("PASS: test_empty_index")
-
-
-def test_compute_hash_nonexistent():
-    h = compute_file_hash("/nonexistent/path/file.py")
-    assert h is None
-    print("PASS: test_compute_hash_nonexistent")
-
-
-def run_all():
-    test_fresh_entry()
-    test_stale_entry()
-    test_missing_source()
-    test_no_hash()
-    test_no_source_field()
-    test_fix_hashes()
-    test_empty_index()
-    test_compute_hash_nonexistent()
-    print("\nAll 8 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()

test_sessions/session_failure.jsonl

@@ -1,18 +0,0 @@
-{"role": "user", "content": "Deploy the application to production"}
-{"role": "assistant", "content": "I'll deploy the application to production.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@prod-server 'cd /app && git pull && docker-compose up -d'"}}]}
-{"role": "tool", "content": "ssh: connect to host prod-server port 22: Connection refused"}
-{"role": "assistant", "content": "Connection refused. Let me check the server status.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ping -c 3 prod-server"}}]}
-{"role": "tool", "content": "PING prod-server (192.168.1.100): 56 data bytes\nRequest timeout for icmp_seq 0\nRequest timeout for icmp_seq 1\nRequest timeout for icmp_seq 2\n--- prod-server ping statistics ---\n3 packets transmitted, 0 packets received, 100.0% packet loss"}
-{"role": "assistant", "content": "The server appears to be down. Let me check if there's an alternative deployment method."}
-{"role": "user", "content": "Try using the VPS instead"}
-{"role": "assistant", "content": "I'll try deploying to the VPS.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@vps-server 'cd /app && git pull && docker-compose up -d'"}}]}
-{"role": "tool", "content": "Permission denied (publickey)."}
-{"role": "assistant", "content": "Permission denied. The SSH key might not be set up correctly. Let me check the SSH configuration.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat ~/.ssh/config"}}]}
-{"role": "tool", "content": "Host vps-server\n    HostName 167.99.126.228\n    User deploy\n    IdentityFile ~/.ssh/id_rsa_vps"}
-{"role": "assistant", "content": "The SSH config looks correct. Let me check if the key exists.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la ~/.ssh/id_rsa_vps"}}]}
-{"role": "tool", "content": "ls: /Users/user/.ssh/id_rsa_vps: No such file or directory"}
-{"role": "assistant", "content": "The SSH key doesn't exist. This is a pitfall - we need to generate the SSH key first."}
-{"role": "user", "content": "Generate a new SSH key for the VPS"}
-{"role": "assistant", "content": "I'll generate a new SSH key.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh-keygen -t rsa -b 4096 -f ~/.ssh/id_rsa_vps -N ''"}}]}
-{"role": "tool", "content": "Generating public/private rsa key pair.\nYour identification has been saved in /Users/user/.ssh/id_rsa_vps\nYour public key has been saved in /Users/user/.ssh/id_rsa_vps.pub\nThe key fingerprint is:\nSHA256:abc123... user@machine"}
-{"role": "assistant", "content": "SSH key generated. Now I need to add it to the VPS."}

test_sessions/session_partial.jsonl

@@ -1,14 +0,0 @@
-{"role": "user", "content": "Check the Gitea API for open issues"}
-{"role": "assistant", "content": "I'll check the Gitea API for open issues.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
-{"role": "tool", "content": "curl: (6) Could not resolve host: forge.alexanderwhitestone.com"}
-{"role": "assistant", "content": "DNS resolution failed. Let me check the network connectivity.", "tool_calls": [{"function": "terminal", "arguments": {"command": "nslookup forge.alexanderwhitestone.com"}}]}
-{"role": "tool", "content": "Server:		8.8.8.8\nAddress:	8.8.8.8#53\n\n** server can't find forge.alexanderwhitestone.com: NXDOMAIN"}
-{"role": "assistant", "content": "The domain doesn't resolve. This might be a DNS issue. Let me try using the IP address directly.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
-{"role": "tool", "content": "curl: (60) SSL certificate problem: self signed certificate"}
-{"role": "assistant", "content": "SSL certificate issue. The server is using a self-signed certificate. Let me try with -k flag to skip SSL verification.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
-{"role": "tool", "content": "[]"}
-{"role": "assistant", "content": "No open issues found. The API returned an empty array."}
-{"role": "user", "content": "Check if there are any pull requests"}
-{"role": "assistant", "content": "Let me check for pull requests.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/pulls?state=open"}}]}
-{"role": "tool", "content": "[{"id": 20, "title": "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)", "state": "open", "user": {"login": "Rockachopa"}, "created_at": "2026-04-14T17:28:20Z"}]"}
-{"role": "assistant", "content": "Found 1 open pull request: PR #20 - "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)" by Rockachopa."}

test_sessions/session_patterns.jsonl

@@ -1,10 +0,0 @@
-{"role": "user", "content": "How do I deploy a new version of the application?"}
-{"role": "assistant", "content": "Here's the deployment process:\n1. Run tests: pytest\n2. Build Docker image: docker build -t app:latest .\n3. Push to registry: docker push registry.example.com/app:latest\n4. Update production: ssh prod 'cd /app && docker-compose pull && docker-compose up -d'\n5. Verify: curl https://app.example.com/health"}
-{"role": "user", "content": "What if tests fail?"}
-{"role": "assistant", "content": "If tests fail:\n1. Check the error logs: pytest -v\n2. Fix the failing tests\n3. Re-run tests: pytest\n4. If still failing, check recent changes: git log --oneline -10\n5. Consider reverting: git revert HEAD"}
-{"role": "user", "content": "What if the Docker build fails?"}
-{"role": "assistant", "content": "If Docker build fails:\n1. Check Dockerfile syntax: docker build --no-cache -t app:latest .\n2. Check for missing dependencies: cat requirements.txt\n3. Check disk space: df -h\n4. Clean up Docker: docker system prune -f\n5. Try building with verbose output: docker build --progress=plain -t app:latest ."}
-{"role": "user", "content": "What if the push to registry fails?"}
-{"role": "assistant", "content": "If push to registry fails:\n1. Check registry credentials: docker login registry.example.com\n2. Check registry space: curl https://registry.example.com/v2/_catalog\n3. Check image size: docker images app:latest\n4. Try tagging with version: docker tag app:latest registry.example.com/app:v1.0.0\n5. Push with version tag: docker push registry.example.com/app:v1.0.0"}
-{"role": "user", "content": "What if the production update fails?"}
-{"role": "assistant", "content": "If production update fails:\n1. Check SSH connection: ssh prod 'echo connected'\n2. Check disk space on prod: ssh prod 'df -h'\n3. Check Docker status: ssh prod 'docker ps -a'\n4. Check logs: ssh prod 'docker-compose logs --tail=100'\n5. Rollback: ssh prod 'cd /app && git checkout HEAD~1 && docker-compose up -d'"}

test_sessions/session_questions.jsonl

@@ -1,12 +0,0 @@
-{"role": "user", "content": "I need to implement a new feature for the application"}
-{"role": "assistant", "content": "I can help you implement a new feature. What feature would you like to add?"}
-{"role": "user", "content": "I want to add user authentication"}
-{"role": "assistant", "content": "User authentication is a good feature. I have a few questions:\n1. What authentication method do you prefer? (JWT, OAuth, Session-based)\n2. Do you need social login? (Google, GitHub, etc.)\n3. What user data do you need to store?\n4. Do you need role-based access control?\n5. What's your database? (PostgreSQL, MySQL, SQLite)"}
-{"role": "user", "content": "I prefer JWT, no social login, just email and password, no roles, PostgreSQL"}
-{"role": "assistant", "content": "Great choices. Here's the implementation plan:\n1. Create user model with email and password hash\n2. Create JWT token generation and validation\n3. Create login endpoint: POST /api/auth/login\n4. Create register endpoint: POST /api/auth/register\n5. Create middleware for protected routes\n6. Add password hashing with bcrypt\n7. Add rate limiting for login attempts\n8. Add password reset functionality\n9. Add email verification\n10. Test all endpoints"}
-{"role": "user", "content": "What about password reset?"}
-{"role": "assistant", "content": "For password reset:\n1. Create reset token table\n2. Create forgot password endpoint: POST /api/auth/forgot-password\n3. Send reset email with token\n4. Create reset password endpoint: POST /api/auth/reset-password\n5. Validate reset token and expiration\n6. Update password and delete token\n7. Send confirmation email"}
-{"role": "user", "content": "What about email verification?"}
-{"role": "assistant", "content": "For email verification:\n1. Add email_verified field to user model\n2. Create verification token table\n3. Send verification email on registration\n4. Create verify email endpoint: GET /api/auth/verify-email?token=...\n5. Validate token and update email_verified\n6. Add middleware to check email_verified for certain routes\n7. Add resend verification email endpoint"}
-{"role": "user", "content": "What about rate limiting?"}
-{"role": "assistant", "content": "For rate limiting:\n1. Use Redis for rate limit storage\n2. Create rate limit middleware\n3. Set limits: 5 login attempts per minute, 3 password resets per hour\n4. Return 429 Too Many Requests when limit exceeded\n5. Add X-RateLimit headers to responses\n6. Log rate limit violations\n7. Add whitelist for trusted IPs"}

test_sessions/session_success.jsonl

@@ -1,13 +0,0 @@
-{"role": "user", "content": "Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence"}
-{"role": "assistant", "content": "I'll clone the repository for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence.git"}}]}
-{"role": "tool", "content": "Cloning into 'compounding-intelligence'...\nremote: Enumerating objects: 15, done.\nremote: Counting objects: 100% (15/15), done.\nremote: Compressing objects: 100% (12/12), done.\nremote: Total 15 (delta 2), reused 0 (delta 0), pack-reused 0\nReceiving objects: 100% (15/15), done.\nResolving deltas: 100% (2/2), done."}
-{"role": "assistant", "content": "Repository cloned successfully. Let me check the structure.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/"}}]}
-{"role": "tool", "content": "total 8\ndrwxr-xr-x   5 user  staff  160 Apr 14 17:21 .\ndrwxr-xr-x  12 user  staff  384 Apr 14 17:21 ..\ndrwxr-xr-x  13 user  staff  416 Apr 14 17:21 .git\n-rw-r--r--   1 user  staff  1234 Apr 14 17:21 README.md\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 knowledge\n-rw-r--r--   1 user  staff   456 Apr 14 17:21 metrics\ndrwxr-xr-x   4 user  staff  128 Apr 14 17:21 scripts\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 templates"}
-{"role": "user", "content": "What files are in the templates directory?"}
-{"role": "assistant", "content": "Let me check the templates directory.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/templates/"}}]}
-{"role": "tool", "content": "total 0\ndrwxr-xr-x  3 user  staff   96 Apr 14 17:21 .\ndrwxr-xr-x  5 user  staff  160 Apr 14 17:21 ..\n-rw-r--r--  1 user  staff    0 Apr 14 17:21 .gitkeep"}
-{"role": "assistant", "content": "The templates directory currently only contains a .gitkeep file. No templates have been added yet."}
-{"role": "user", "content": "Create a harvest-prompt.md template in the templates directory."}
-{"role": "assistant", "content": "I'll create the harvest-prompt.md template for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat > compounding-intelligence/templates/harvest-prompt.md << 'EOF'\n# Knowledge Extraction Prompt\n\nExtract knowledge from session transcripts.\nEOF"}}]}
-{"role": "tool", "content": ""}
-{"role": "assistant", "content": "Template created successfully. The harvest-prompt.md file is now in the templates directory."}