feat: add session_metadata.py — structured session metadata extractor (#6)

scripts/license_checker.py

@@ -1,506 +0,0 @@
-#!/usr/bin/env python3
-"""
-License Checker — Pipeline 5.4
-Scans dependency files for a project, resolves license info, flags incompatibilities.
-
-Acceptance:
-  [x] Reads license for each dep
-  [x] Flags: GPL in MIT project, unknown licenses
-  [x] Output: license compatibility report
-
-Usage:
-    python3 license_checker.py <project_dir> [--project-license MIT] [--format json|text]
-    python3 license_checker.py <project_dir> --scan-deps
-"""
-
-import argparse
-import json
-import os
-import re
-import subprocess
-import sys
-import urllib.request
-import urllib.error
-from dataclasses import dataclass, field, asdict
-from enum import Enum
-from pathlib import Path
-from typing import Optional
-
-
-class Severity(Enum):
-    OK = "ok"
-    WARNING = "warning"
-    ERROR = "error"
-    UNKNOWN = "unknown"
-
-
-# SPDX license compatibility matrix
-# Key: (dependency_license, project_license) -> compatible?
-# Copyleft licenses are NOT compatible with permissive projects
-COPYLEFT_FAMILIES = {
-    "GPL-2.0", "GPL-2.0-only", "GPL-2.0-or-later",
-    "GPL-3.0", "GPL-3.0-only", "GPL-3.0-or-later",
-    "AGPL-3.0", "AGPL-3.0-only", "AGPL-3.0-or-later",
-    "LGPL-2.0", "LGPL-2.1", "LGPL-3.0",
-    "LGPL-2.0-only", "LGPL-2.1-only", "LGPL-3.0-only",
-    "LGPL-2.0-or-later", "LGPL-2.1-or-later", "LGPL-3.0-or-later",
-    "MPL-2.0",  # Weak copyleft — file-level
-    "EUPL-1.1", "EUPL-1.2",
-    "OSL-3.0",
-    "SSPL-1.0",
-    "CC-BY-SA-4.0", "CC-BY-SA-3.0",
-    "CC-BY-NC-4.0", "CC-BY-NC-3.0",
-}
-
-PERMISSIVE_LICENSES = {
-    "MIT", "BSD-2-Clause", "BSD-3-Clause", "Apache-2.0",
-    "ISC", "Unlicense", "CC0-1.0", "0BSD", "BSL-1.0",
-    "Zlib", "PSF-2.0", "Python-2.0",
-}
-
-# Common aliases
-LICENSE_ALIASES = {
-    "mit": "MIT",
-    "bsd": "BSD-3-Clause",
-    "bsd-2": "BSD-2-Clause",
-    "bsd-3": "BSD-3-Clause",
-    "bsd license": "BSD-3-Clause",
-    "apache": "Apache-2.0",
-    "apache 2.0": "Apache-2.0",
-    "apache-2.0": "Apache-2.0",
-    "apache software license": "Apache-2.0",
-    "apache software license 2.0": "Apache-2.0",
-    "gpl": "GPL-3.0",
-    "gpl-2": "GPL-2.0",
-    "gpl-3": "GPL-3.0",
-    "gplv2": "GPL-2.0",
-    "gplv3": "GPL-3.0",
-    "gnu general public license": "GPL-3.0",
-    "gnu general public license v3": "GPL-3.0",
-    "gnu general public license v2": "GPL-2.0",
-    "gnu lesser general public license v2": "LGPL-2.1",
-    "gnu lesser general public license v3": "LGPL-3.0",
-    "lgpl": "LGPL-3.0",
-    "lgpl-2.1": "LGPL-2.1",
-    "lgpl-3": "LGPL-3.0",
-    "agpl": "AGPL-3.0",
-    "agpl-3.0": "AGPL-3.0",
-    "agplv3": "AGPL-3.0",
-    "isc": "ISC",
-    "mpl": "MPL-2.0",
-    "mpl-2.0": "MPL-2.0",
-    "mozilla public license 2.0": "MPL-2.0",
-    "unlicense": "Unlicense",
-    "public domain": "Unlicense",
-    "cc0": "CC0-1.0",
-    "cc0-1.0": "CC0-1.0",
-    "psf": "PSF-2.0",
-    "python software foundation license": "PSF-2.0",
-    "the mit license": "MIT",
-    "mit license": "MIT",
-}
-
-
-@dataclass
-class DepLicense:
-    name: str
-    version: str = ""
-    license: str = "UNKNOWN"
-    source: str = ""  # where we found the dep (requirements.txt, package.json, etc.)
-    severity: Severity = Severity.UNKNOWN
-    message: str = ""
-
-
-@dataclass
-class LicenseReport:
-    project_dir: str
-    project_license: str = "MIT"
-    dependencies: list = field(default_factory=list)
-    summary: dict = field(default_factory=dict)
-    errors: list = field(default_factory=list)
-    warnings: list = field(default_factory=list)
-
-
-def normalize_license(raw: str) -> str:
-    """Normalize a license string to SPDX identifier."""
-    if not raw or raw.strip() in ("UNKNOWN", "UNKNOWN:", ""):
-        return "UNKNOWN"
-    cleaned = raw.strip().lower()
-    # Remove version specifiers like "MIT License (MIT)"
-    cleaned = re.sub(r"\(.*?\)", "", cleaned).strip()
-    cleaned = re.sub(r"\s+license$", "", cleaned).strip()
-    cleaned = re.sub(r"^the\s+", "", cleaned).strip()
-    if cleaned in LICENSE_ALIASES:
-        return LICENSE_ALIASES[cleaned]
-    # Check if it already looks like SPDX
-    upper = raw.strip()
-    if upper in COPYLEFT_FAMILIES or upper in PERMISSIVE_LICENSES:
-        return upper
-    return raw.strip()
-
-
-def check_compatibility(dep_license: str, project_license: str) -> tuple[Severity, str]:
-    """Check if a dependency license is compatible with the project license."""
-    if dep_license == "UNKNOWN":
-        return Severity.WARNING, "License unknown — manual review needed"
-    
-    if dep_license in PERMISSIVE_LICENSES:
-        return Severity.OK, "Compatible (permissive)"
-    
-    if dep_license in COPYLEFT_FAMILIES:
-        # Copyleft in a permissive project is a problem
-        if project_license in PERMISSIVE_LICENSES:
-            return Severity.ERROR, f"Copyleft ({dep_license}) in permissive ({project_license}) project"
-        # Copyleft in same family is OK
-        if dep_license.startswith(project_license.split("-")[0]):
-            return Severity.OK, "Compatible (same copyleft family)"
-        return Severity.WARNING, f"Review needed: {dep_license} with {project_license}"
-    
-    return Severity.UNKNOWN, f"Unrecognized license: {dep_license}"
-
-
-def parse_requirements_txt(path: str) -> list[DepLicense]:
-    """Parse requirements.txt format."""
-    deps = []
-    with open(path) as f:
-        for line in f:
-            line = line.strip()
-            if not line or line.startswith("#") or line.startswith("-"):
-                continue
-            # Parse name==version or name>=version etc.
-            match = re.match(r"^([a-zA-Z0-9_.-]+)(?:[>=<!~].*)?$", line)
-            if match:
-                deps.append(DepLicense(name=match.group(1), source="requirements.txt"))
-    return deps
-
-
-def parse_pyproject_toml(path: str) -> list[DepLicense]:
-    """Parse pyproject.toml dependencies."""
-    deps = []
-    try:
-        # Use tomllib (Python 3.11+) or fall back to regex
-        import tomllib
-        with open(path, "rb") as f:
-            data = tomllib.load(f)
-    except ImportError:
-        # Fallback: regex parse
-        with open(path) as f:
-            content = f.read()
-        # Find [project.dependencies] section
-        match = re.search(r"\[project\]\s*dependencies\s*=\s*\[(.*?)\]", content, re.DOTALL)
-        if match:
-            for dep_str in re.findall(r'"([^"]+)"', match.group(1)):
-                name = re.match(r"^([a-zA-Z0-9_.-]+)", dep_str)
-                if name:
-                    deps.append(DepLicense(name=name.group(1), source="pyproject.toml"))
-        return deps
-
-    project_deps = data.get("project", {}).get("dependencies", [])
-    for dep_str in project_deps:
-        name = re.match(r"^([a-zA-Z0-9_.-]+)", dep_str)
-        if name:
-            deps.append(DepLicense(name=name.group(1), source="pyproject.toml"))
-    return deps
-
-
-def parse_package_json(path: str) -> list[DepLicense]:
-    """Parse package.json dependencies."""
-    deps = []
-    with open(path) as f:
-        data = json.load(f)
-    for section in ("dependencies", "devDependencies"):
-        for name, version in data.get(section, {}).items():
-            deps.append(DepLicense(name=name, version=version, source="package.json"))
-    return deps
-
-
-def parse_cargo_toml(path: str) -> list[DepLicense]:
-    """Parse Cargo.toml dependencies (basic)."""
-    deps = []
-    with open(path) as f:
-        for line in f:
-            match = re.match(r'^([a-zA-Z0-9_-]+)\s*=\s*"', line.strip())
-            if match and line.strip()[0] != "[" and line.strip() != "[dependencies]":
-                deps.append(DepLicense(name=match.group(1), source="Cargo.toml"))
-    return deps
-
-
-def parse_go_mod(path: str) -> list[DepLicense]:
-    """Parse go.mod dependencies."""
-    deps = []
-    with open(path) as f:
-        in_require = False
-        for line in f:
-            line = line.strip()
-            if line == "require (":
-                in_require = True
-                continue
-            if line == ")" and in_require:
-                in_require = False
-                continue
-            if in_require:
-                parts = line.split()
-                if len(parts) >= 2:
-                    deps.append(DepLicense(name=parts[0], version=parts[1], source="go.mod"))
-    return deps
-
-
-def scan_dep_files(project_dir: str) -> list[DepLicense]:
-    """Find and parse all dependency files in a project."""
-    all_deps = []
-    parsers = {
-        "requirements.txt": parse_requirements_txt,
-        "requirements-dev.txt": parse_requirements_txt,
-        "requirements_prod.txt": parse_requirements_txt,
-        "pyproject.toml": parse_pyproject_toml,
-        "setup.py": None,  # TODO: parse setup.py
-        "package.json": parse_package_json,
-        "Cargo.toml": parse_cargo_toml,
-        "go.mod": parse_go_mod,
-    }
-    
-    for filename, parser in parsers.items():
-        path = os.path.join(project_dir, filename)
-        if os.path.exists(path) and parser:
-            try:
-                deps = parser(path)
-                all_deps.extend(deps)
-            except Exception as e:
-                print(f"Warning: Failed to parse {filename}: {e}", file=sys.stderr)
-    
-    # Also check subdirectories for monorepos (one level deep)
-    for entry in os.listdir(project_dir):
-        subdir = os.path.join(project_dir, entry)
-        if os.path.isdir(subdir) and not entry.startswith("."):
-            for filename, parser in parsers.items():
-                path = os.path.join(subdir, filename)
-                if os.path.exists(path) and parser:
-                    try:
-                        deps = parser(path)
-                        for d in deps:
-                            d.source = f"{entry}/{filename}"
-                        all_deps.extend(deps)
-                    except Exception:
-                        pass
-    
-    return all_deps
-
-
-def lookup_pypi_license(package_name: str) -> str:
-    """Look up license from PyPI API."""
-    try:
-        url = f"https://pypi.org/pypi/{package_name}/json"
-        req = urllib.request.Request(url, headers={"Accept": "application/json"})
-        resp = urllib.request.urlopen(req, timeout=10)
-        data = json.loads(resp.read())
-        # Try classifiers first
-        for classifier in data.get("info", {}).get("classifiers", []):
-            if classifier.startswith("License ::"):
-                parts = classifier.split(" :: ")
-                if len(parts) >= 3:
-                    return parts[-1]
-        # Fall back to license field
-        lic = data.get("info", {}).get("license", "")
-        if lic and len(lic) < 100:
-            return lic
-        # Try license_expression
-        le = data.get("info", {}).get("license_expression", "")
-        if le:
-            return le
-        return "UNKNOWN"
-    except Exception:
-        return "UNKNOWN"
-
-
-def lookup_npm_license(package_name: str) -> str:
-    """Look up license from npm registry."""
-    try:
-        url = f"https://registry.npmjs.org/{package_name}"
-        req = urllib.request.Request(url, headers={"Accept": "application/json"})
-        resp = urllib.request.urlopen(req, timeout=10)
-        data = json.loads(resp.read())
-        lic = data.get("license", "UNKNOWN")
-        if isinstance(lic, dict):
-            lic = lic.get("type", "UNKNOWN")
-        return lic or "UNKNOWN"
-    except Exception:
-        return "UNKNOWN"
-
-
-def detect_project_license(project_dir: str) -> str:
-    """Detect the project's own license."""
-    for name in ("LICENSE", "LICENSE.md", "LICENSE.txt", "LICENCE", "COPYING"):
-        path = os.path.join(project_dir, name)
-        if os.path.exists(path):
-            with open(path) as f:
-                content = f.read().upper()
-            if "MIT LICENSE" in content or "MIT" in content[:200]:
-                return "MIT"
-            if "APACHE" in content and "2.0" in content:
-                return "Apache-2.0"
-            if "GNU GENERAL PUBLIC LICENSE" in content:
-                if "VERSION 3" in content:
-                    return "GPL-3.0"
-                if "VERSION 2" in content:
-                    return "GPL-2.0"
-            if "BSD" in content[:500]:
-                if "3-CLAUSE" in content or "THREE CLAUSE" in content:
-                    return "BSD-3-Clause"
-                return "BSD-2-Clause"
-            if "ISC" in content[:200]:
-                return "ISC"
-    # Check pyproject.toml
-    pypath = os.path.join(project_dir, "pyproject.toml")
-    if os.path.exists(pypath):
-        with open(pypath) as f:
-            content = f.read()
-        match = re.search(r'license\s*=\s*\{\s*text\s*=\s*"([^"]+)"', content)
-        if match:
-            return normalize_license(match.group(1))
-        match = re.search(r'license\s*=\s*"([^"]+)"', content)
-        if match:
-            return normalize_license(match.group(1))
-    return "UNKNOWN"
-
-
-def resolve_licenses(deps: list[DepLicense], cache: dict = None) -> None:
-    """Resolve license info for all dependencies."""
-    if cache is None:
-        cache = {}
-    
-    for dep in deps:
-        if dep.name in cache:
-            dep.license = cache[dep.name]
-            continue
-        
-        # Determine ecosystem
-        if dep.source in ("package.json",):
-            raw = lookup_npm_license(dep.name)
-        else:
-            raw = lookup_pypi_license(dep.name)
-        
-        dep.license = normalize_license(raw)
-        cache[dep.name] = dep.license
-
-
-def generate_report(deps: list[DepLicense], project_license: str) -> LicenseReport:
-    """Generate the compatibility report."""
-    report = LicenseReport(
-        project_dir="",
-        project_license=project_license,
-        dependencies=[],
-    )
-    
-    counts = {"ok": 0, "warning": 0, "error": 0, "unknown": 0}
-    
-    for dep in deps:
-        severity, message = check_compatibility(dep.license, project_license)
-        dep.severity = severity
-        dep.message = message
-        counts[severity.value] += 1
-        
-        if severity == Severity.ERROR:
-            report.errors.append(f"{dep.name}: {message}")
-        elif severity == Severity.WARNING:
-            report.warnings.append(f"{dep.name}: {message}")
-        
-        report.dependencies.append(asdict(dep))
-    
-    report.summary = {
-        "total": len(deps),
-        **counts,
-        "project_license": project_license,
-    }
-    
-    return report
-
-
-def format_text(report: LicenseReport) -> str:
-    """Format report as human-readable text."""
-    lines = []
-    lines.append("=" * 60)
-    lines.append("  LICENSE COMPATIBILITY REPORT")
-    lines.append("=" * 60)
-    lines.append(f"  Project License: {report.project_license}")
-    lines.append(f"  Dependencies: {report.summary.get('total', 0)}")
-    lines.append(f"  OK: {report.summary.get('ok', 0)}  "
-                 f"WARN: {report.summary.get('warning', 0)}  "
-                 f"ERR: {report.summary.get('error', 0)}  "
-                 f"UNK: {report.summary.get('unknown', 0)}")
-    lines.append("-" * 60)
-    
-    for dep in report.dependencies:
-        icon = {"ok": "[OK]", "warning": "[!!]", "error": "[XX]", "unknown": "[??]"}
-        sev = dep.get("severity", "unknown")
-        name = dep.get("name", "?")
-        lic = dep.get("license", "?")
-        msg = dep.get("message", "")
-        lines.append(f"  {icon.get(sev, '[ ]')} {name:30s} {lic:20s} {msg}")
-    
-    if report.errors:
-        lines.append("-" * 60)
-        lines.append("  ERRORS:")
-        for e in report.errors:
-            lines.append(f"    - {e}")
-    
-    if report.warnings:
-        lines.append("-" * 60)
-        lines.append("  WARNINGS:")
-        for w in report.warnings:
-            lines.append(f"    - {w}")
-    
-    lines.append("=" * 60)
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="License Checker — Pipeline 5.4")
-    parser.add_argument("project_dir", help="Project directory to scan")
-    parser.add_argument("--project-license", default=None,
-                        help="Project license SPDX id (auto-detected if omitted)")
-    parser.add_argument("--format", choices=["json", "text"], default="text",
-                        help="Output format")
-    parser.add_argument("--scan-deps", action="store_true",
-                        help="Only scan and list deps (skip license lookup)")
-    args = parser.parse_args()
-    
-    project_dir = os.path.abspath(args.project_dir)
-    if not os.path.isdir(project_dir):
-        print(f"Error: {project_dir} is not a directory", file=sys.stderr)
-        sys.exit(1)
-    
-    # Detect project license
-    project_license = args.project_license or detect_project_license(project_dir)
-    
-    # Scan deps
-    deps = scan_dep_files(project_dir)
-    if not deps:
-        print(f"No dependencies found in {project_dir}", file=sys.stderr)
-        sys.exit(0)
-    
-    print(f"Found {len(deps)} dependencies", file=sys.stderr)
-    
-    if args.scan_deps:
-        for d in deps:
-            print(f"  {d.name} ({d.source})")
-        sys.exit(0)
-    
-    # Resolve licenses
-    print("Resolving licenses...", file=sys.stderr)
-    resolve_licenses(deps)
-    
-    # Generate report
-    report = generate_report(deps, project_license)
-    report.project_dir = project_dir
-    
-    if args.format == "json":
-        print(json.dumps(asdict(report), indent=2, default=str))
-    else:
-        print(format_text(report))
-    
-    # Exit code: 1 if errors, 0 otherwise
-    sys.exit(1 if report.errors else 0)
-
-
-if __name__ == "__main__":
-    main()

scripts/session_metadata.py

@@ -0,0 +1,276 @@
+#!/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()

tests/test_license_checker.py

@@ -1,186 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for license_checker.py — Pipeline 5.4"""
-
-import json
-import os
-import sys
-import tempfile
-import unittest
-
-# Add scripts dir to path
-sys.path.insert(0, os.path.dirname(__file__))
-
-from license_checker import (
-    normalize_license,
-    check_compatibility,
-    parse_requirements_txt,
-    parse_package_json,
-    parse_pyproject_toml,
-    parse_go_mod,
-    detect_project_license,
-    scan_dep_files,
-    generate_report,
-    format_text,
-    Severity,
-    DepLicense,
-)
-
-
-class TestNormalizeLicense(unittest.TestCase):
-    def test_mit_aliases(self):
-        for alias in ["mit", "MIT License", "The MIT License", "MIT license"]:
-            self.assertEqual(normalize_license(alias), "MIT")
-
-    def test_apache_aliases(self):
-        for alias in ["Apache 2.0", "Apache-2.0", "apache software license"]:
-            self.assertEqual(normalize_license(alias), "Apache-2.0")
-
-    def test_gpl_aliases(self):
-        self.assertEqual(normalize_license("GPL-3.0"), "GPL-3.0")
-        self.assertEqual(normalize_license("gplv3"), "GPL-3.0")
-
-    def test_unknown(self):
-        self.assertEqual(normalize_license(""), "UNKNOWN")
-        self.assertEqual(normalize_license("UNKNOWN"), "UNKNOWN")
-
-    def test_already_spdx(self):
-        self.assertEqual(normalize_license("BSD-3-Clause"), "BSD-3-Clause")
-
-
-class TestCheckCompatibility(unittest.TestCase):
-    def test_permissive_ok(self):
-        sev, msg = check_compatibility("MIT", "MIT")
-        self.assertEqual(sev, Severity.OK)
-
-    def test_gpl_in_mit_error(self):
-        sev, msg = check_compatibility("GPL-3.0", "MIT")
-        self.assertEqual(sev, Severity.ERROR)
-
-    def test_unknown_warning(self):
-        sev, msg = check_compatibility("UNKNOWN", "MIT")
-        self.assertEqual(sev, Severity.WARNING)
-
-    def test_apache_in_mit_ok(self):
-        sev, msg = check_compatibility("Apache-2.0", "MIT")
-        self.assertEqual(sev, Severity.OK)
-
-    def test_lgpl_in_mit_error(self):
-        sev, msg = check_compatibility("LGPL-3.0", "MIT")
-        self.assertEqual(sev, Severity.ERROR)
-
-
-class TestParseRequirements(unittest.TestCase):
-    def test_basic(self):
-        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-            f.write("requests>=2.28.0\nflask==2.3.0\n# comment\npytest\n")
-            f.flush()
-            deps = parse_requirements_txt(f.name)
-        os.unlink(f.name)
-        names = [d.name for d in deps]
-        self.assertIn("requests", names)
-        self.assertIn("flask", names)
-        self.assertIn("pytest", names)
-        self.assertEqual(len(deps), 3)
-
-    def test_skip_flags(self):
-        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
-            f.write("-r other.txt\n--index-url https://pypi.org\nreal-dep\n")
-            f.flush()
-            deps = parse_requirements_txt(f.name)
-        os.unlink(f.name)
-        self.assertEqual(len(deps), 1)
-        self.assertEqual(deps[0].name, "real-dep")
-
-
-class TestParsePackageJson(unittest.TestCase):
-    def test_basic(self):
-        data = {
-            "dependencies": {"express": "^4.18.0", "lodash": "^4.17.21"},
-            "devDependencies": {"jest": "^29.0.0"},
-        }
-        with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as f:
-            json.dump(data, f)
-            f.flush()
-            deps = parse_package_json(f.name)
-        os.unlink(f.name)
-        names = [d.name for d in deps]
-        self.assertIn("express", names)
-        self.assertIn("jest", names)
-        self.assertEqual(len(deps), 3)
-
-
-class TestParseGoMod(unittest.TestCase):
-    def test_basic(self):
-        content = """module example.com/mymod
-
-go 1.21
-
-require (
-    github.com/gin-gonic/gin v1.9.1
-    github.com/stretchr/testify v1.8.4
-)
-"""
-        with tempfile.NamedTemporaryFile(mode="w", suffix=".mod", delete=False) as f:
-            f.write(content)
-            f.flush()
-            deps = parse_go_mod(f.name)
-        os.unlink(f.name)
-        self.assertEqual(len(deps), 2)
-        self.assertEqual(deps[0].name, "github.com/gin-gonic/gin")
-
-
-class TestDetectProjectLicense(unittest.TestCase):
-    def test_mit_file(self):
-        with tempfile.TemporaryDirectory() as d:
-            with open(os.path.join(d, "LICENSE"), "w") as f:
-                f.write("MIT License\n\nCopyright (c) 2024...\n")
-            self.assertEqual(detect_project_license(d), "MIT")
-
-    def test_apache_file(self):
-        with tempfile.TemporaryDirectory() as d:
-            with open(os.path.join(d, "LICENSE"), "w") as f:
-                f.write("Apache License Version 2.0...")
-            self.assertEqual(detect_project_license(d), "Apache-2.0")
-
-    def test_no_license(self):
-        with tempfile.TemporaryDirectory() as d:
-            self.assertEqual(detect_project_license(d), "UNKNOWN")
-
-
-class TestScanDeps(unittest.TestCase):
-    def test_multi_ecosystem(self):
-        with tempfile.TemporaryDirectory() as d:
-            with open(os.path.join(d, "requirements.txt"), "w") as f:
-                f.write("flask\nrequests\n")
-            with open(os.path.join(d, "package.json"), "w") as f:
-                json.dump({"dependencies": {"express": "^4.0.0"}}, f)
-            deps = scan_dep_files(d)
-            names = [d.name for d in deps]
-            self.assertIn("flask", names)
-            self.assertIn("express", names)
-
-
-class TestGenerateReport(unittest.TestCase):
-    def test_basic(self):
-        deps = [
-            DepLicense(name="flask", license="BSD-3-Clause", source="requirements.txt"),
-            DepLicense(name="gpl-pkg", license="GPL-3.0", source="requirements.txt"),
-            DepLicense(name="unknown-pkg", license="UNKNOWN", source="requirements.txt"),
-        ]
-        report = generate_report(deps, "MIT")
-        self.assertEqual(report.summary["ok"], 1)
-        self.assertEqual(report.summary["error"], 1)
-        self.assertEqual(report.summary["warning"], 1)
-        self.assertEqual(len(report.errors), 1)
-        self.assertIn("gpl-pkg", report.errors[0])
-
-    def test_format_text(self):
-        deps = [DepLicense(name="flask", license="BSD-3-Clause", source="requirements.txt")]
-        report = generate_report(deps, "MIT")
-        text = format_text(report)
-        self.assertIn("LICENSE COMPATIBILITY REPORT", text)
-        self.assertIn("flask", text)
-
-
-if __name__ == "__main__":
-    unittest.main()