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

scripts/dependency_graph.py

@@ -1,249 +0,0 @@
-#!/usr/bin/env python3
-"""
-Cross-Repo Dependency Graph Builder
-
-Scans repos for import/require/reference patterns and builds a directed
-dependency graph. Detects circular dependencies. Outputs DOT and Mermaid.
-
-Usage:
-  python3 scripts/dependency_graph.py /path/to/repos/
-  python3 scripts/dependency_graph.py --repos repo1,repo2,repo3 --format mermaid
-  python3 scripts/dependency_graph.py --repos-dir /path/to/ --format dot --output deps.dot
-
-Patterns detected:
-  - Python: import X, from X import Y
-  - JavaScript: require("X"), import ... from "X"
-  - Go: import "X"
-  - Ansible: include_role, import_role
-  - Docker/Compose: image: X, depends_on
-  - Config references: repo-name in YAML/TOML/JSON
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-from collections import defaultdict
-from pathlib import Path
-
-
-# Known repo names for matching
-KNOWN_REPOS = [
-    "hermes-agent", "timmy-config", "timmy-home", "the-nexus", "the-door",
-    "the-beacon", "fleet-ops", "burn-fleet", "timmy-dispatch", "turboquant",
-    "compounding-intelligence", "the-playground", "second-son-of-timmy",
-    "ai-safety-review", "the-echo-pattern", "timmy-academy", "wolf",
-    "the-testament",
-]
-
-
-def normalize_repo_name(name: str) -> str:
-    """Normalize a repo name for comparison."""
-    return name.lower().replace("_", "-").replace(".git", "").strip()
-
-
-def scan_file_for_deps(filepath: str, content: str, own_repo: str) -> set:
-    """Scan a file's content for references to other repos."""
-    deps = set()
-    own_norm = normalize_repo_name(own_repo)
-
-    for repo in KNOWN_REPOS:
-        repo_norm = normalize_repo_name(repo)
-        if repo_norm == own_norm:
-            continue
-
-        # Direct name references
-        patterns = [
-            repo,  # exact name
-            repo.replace("-", "_"),  # underscore variant
-            repo.replace("-", ""),  # no separator
-            f"/{repo}/",  # path reference
-            f'"{repo}"',  # quoted
-            f"'{repo}'",  # single quoted
-            f"Timmy_Foundation/{repo}",  # full Gitea path
-            f"Timmy_Foundation.{repo}",  # Python module path
-        ]
-
-        for pattern in patterns:
-            if pattern in content:
-                deps.add(repo)
-                break
-
-    return deps
-
-
-def scan_repo(repo_path: str, repo_name: str = None) -> dict:
-    """Scan a repo directory for dependencies."""
-    path = Path(repo_path)
-    if not path.is_dir():
-        return {"error": f"Not a directory: {repo_path}"}
-
-    if not repo_name:
-        repo_name = path.name
-
-    deps = set()
-    files_scanned = 0
-    exts = {".py", ".js", ".ts", ".go", ".yaml", ".yml", ".toml", ".json",
-            ".md", ".sh", ".bash", ".Dockerfile", ".tf", ".hcl"}
-
-    for fpath in path.rglob("*"):
-        if not fpath.is_file():
-            continue
-        if fpath.suffix not in exts:
-            continue
-        # Skip common non-source dirs
-        parts = fpath.parts
-        if any(p in (".git", "node_modules", "__pycache__", ".venv", "venv",
-                      "vendor", "dist", "build", ".tox") for p in parts):
-            continue
-
-        try:
-            content = fpath.read_text(errors="ignore")
-        except:
-            continue
-
-        file_deps = scan_file_for_deps(str(fpath), content, repo_name)
-        deps.update(file_deps)
-        files_scanned += 1
-
-    return {
-        "repo": repo_name,
-        "dependencies": sorted(deps),
-        "files_scanned": files_scanned,
-    }
-
-
-def detect_cycles(graph: dict) -> list:
-    """Detect circular dependencies using DFS."""
-    cycles = []
-    visited = set()
-    rec_stack = set()
-
-    def dfs(node, path):
-        visited.add(node)
-        rec_stack.add(node)
-
-        for neighbor in graph.get(node, {}).get("dependencies", []):
-            if neighbor not in visited:
-                result = dfs(neighbor, path + [neighbor])
-                if result:
-                    return result
-            elif neighbor in rec_stack:
-                cycle_start = path.index(neighbor)
-                return path[cycle_start:] + [neighbor]
-
-        rec_stack.remove(node)
-        return None
-
-    for node in graph:
-        if node not in visited:
-            cycle = dfs(node, [node])
-            if cycle:
-                cycles.append(cycle)
-
-    return cycles
-
-
-def to_dot(graph: dict) -> str:
-    """Generate DOT format output."""
-    lines = ["digraph dependencies {"]
-    lines.append("  rankdir=LR;")
-    lines.append("  node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];")
-    lines.append("  edge [color="#4a4a6a"];")
-    lines.append("")
-
-    for repo, data in sorted(graph.items()):
-        dep_count = len(data.get("dependencies", []))
-        fill = "#2d1b69" if dep_count > 2 else "#16213e"
-        lines.append(f'  "{repo}" [fillcolor="{fill}"];')
-        for dep in data.get("dependencies", []):
-            lines.append(f'  "{repo}" -> "{dep}";')
-
-    lines.append("}")
-    return "\n".join(lines)
-
-
-def to_mermaid(graph: dict) -> str:
-    """Generate Mermaid format output."""
-    lines = ["graph LR"]
-
-    for repo, data in sorted(graph.items()):
-        for dep in data.get("dependencies", []):
-            lines.append(f"    {repo.replace('-','_')} --> {dep.replace('-','_')}")
-
-    # Add node labels
-    lines.append("")
-    for repo in sorted(graph.keys()):
-        lines.append(f"    {repo.replace('-','_')}[{repo}]")
-
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Build cross-repo dependency graph")
-    parser.add_argument("repos_dir", nargs="?", help="Directory containing repos")
-    parser.add_argument("--repos", help="Comma-separated list of repo paths")
-    parser.add_argument("--format", choices=["dot", "mermaid", "json"], default="json")
-    parser.add_argument("--output", "-o", help="Output file (default: stdout)")
-    parser.add_argument("--cycles-only", action="store_true", help="Only report cycles")
-    args = parser.parse_args()
-
-    results = {}
-    repo_paths = []
-
-    if args.repos:
-        repo_paths = [p.strip() for p in args.repos.split(",")]
-    elif args.repos_dir:
-        base = Path(args.repos_dir)
-        repo_paths = [str(p) for p in base.iterdir() if p.is_dir() and not p.name.startswith(".")]
-    else:
-        parser.print_help()
-        sys.exit(1)
-
-    for rpath in repo_paths:
-        name = Path(rpath).name
-        print(f"Scanning {name}...", file=sys.stderr)
-        result = scan_repo(rpath, name)
-        if "error" not in result:
-            results[name] = result
-
-    # Detect cycles
-    cycles = detect_cycles(results)
-
-    if args.cycles_only:
-        if cycles:
-            print("CIRCULAR DEPENDENCIES DETECTED:")
-            for cycle in cycles:
-                print(f"  {' -> '.join(cycle)}")
-            sys.exit(1)
-        else:
-            print("No circular dependencies found.")
-            sys.exit(0)
-
-    # Output
-    output = {}
-    if args.format == "dot":
-        output = to_dot(results)
-    elif args.format == "mermaid":
-        output = to_mermaid(results)
-    else:
-        output = json.dumps({
-            "repos": results,
-            "cycles": cycles,
-            "summary": {
-                "total_repos": len(results),
-                "total_deps": sum(len(r["dependencies"]) for r in results.values()),
-                "cycles_found": len(cycles),
-            }
-        }, indent=2)
-
-    if args.output:
-        Path(args.output).write_text(output)
-        print(f"Written to {args.output}", file=sys.stderr)
-    else:
-        print(output)
-
-
-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.")