feat: cross-repo dependency graph builder (#93)

scripts/dependency_graph.py

@@ -0,0 +1,249 @@
+#!/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_metadata.py

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