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

scripts/diff_analyzer.py

@@ -1,216 +0,0 @@
-#!/usr/bin/env python3
-"""
-Diff Analyzer — Parse unified diffs and categorize every change.
-
-Pipeline 6.1 for Compounding Intelligence.
-"""
-
-import re
-from dataclasses import dataclass, field, asdict
-from enum import Enum
-from typing import List, Dict, Any, Optional
-
-
-class ChangeCategory(Enum):
-    ADDED = "added"
-    DELETED = "deleted"
-    MODIFIED = "modified"
-    MOVED = "moved"
-    CONTEXT = "context"
-
-
-@dataclass
-class Hunk:
-    """A single diff hunk with header, line ranges, and category."""
-    header: str
-    old_start: int
-    old_count: int
-    new_start: int
-    new_count: int
-    lines: List[str] = field(default_factory=list)
-    category: ChangeCategory = ChangeCategory.CONTEXT
-
-    def to_dict(self) -> Dict[str, Any]:
-        d = asdict(self)
-        d["category"] = self.category.value
-        return d
-
-
-@dataclass
-class FileChange:
-    """A single file's changes."""
-    path: str
-    old_path: Optional[str] = None  # For renames
-    hunks: List[Hunk] = field(default_factory=list)
-    added_lines: int = 0
-    deleted_lines: int = 0
-    is_new: bool = False
-    is_deleted: bool = False
-    is_renamed: bool = False
-    is_binary: bool = False
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "path": self.path,
-            "old_path": self.old_path,
-            "hunks": [h.to_dict() for h in self.hunks],
-            "added_lines": self.added_lines,
-            "deleted_lines": self.deleted_lines,
-            "is_new": self.is_new,
-            "is_deleted": self.is_deleted,
-            "is_renamed": self.is_renamed,
-            "is_binary": self.is_binary,
-        }
-
-
-@dataclass
-class ChangeSummary:
-    """Aggregate stats + per-file breakdown."""
-    files: List[FileChange] = field(default_factory=list)
-    total_added: int = 0
-    total_deleted: int = 0
-    total_files_changed: int = 0
-    total_hunks: int = 0
-    new_files: int = 0
-    deleted_files: int = 0
-    renamed_files: int = 0
-    binary_files: int = 0
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "total_files_changed": self.total_files_changed,
-            "total_added": self.total_added,
-            "total_deleted": self.total_deleted,
-            "total_hunks": self.total_hunks,
-            "new_files": self.new_files,
-            "deleted_files": self.deleted_files,
-            "renamed_files": self.renamed_files,
-            "binary_files": self.binary_files,
-            "files": [f.to_dict() for f in self.files],
-        }
-
-
-class DiffAnalyzer:
-    """Parses unified diff format and produces structured ChangeSummary."""
-
-    HUNK_HEADER_RE = re.compile(r"^@@\s+-(\d+)(?:,(\d+))?\s+\+(\d+)(?:,(\d+))?\s+@@(.*)$")
-    DIFF_FILE_RE = re.compile(r"^diff --git a/(.*) b/(.*)")
-    RENAME_RE = re.compile(r"^rename from (.+)$")
-    RENAME_TO_RE = re.compile(r"^rename to (.+)$")
-    NEW_FILE_RE = re.compile(r"^new file mode")
-    DELETED_FILE_RE = re.compile(r"^deleted file mode")
-    BINARY_RE = re.compile(r"^Binary files .* differ")
-
-    def analyze(self, diff_text: str) -> ChangeSummary:
-        """Parse a unified diff and return a ChangeSummary."""
-        summary = ChangeSummary()
-        if not diff_text or not diff_text.strip():
-            return summary
-
-        # Split diff into per-file sections
-        file_diffs = self._split_files(diff_text)
-
-        for file_diff in file_diffs:
-            fc = self._parse_file_diff(file_diff)
-            summary.files.append(fc)
-            summary.total_added += fc.added_lines
-            summary.total_deleted += fc.deleted_lines
-            summary.total_hunks += len(fc.hunks)
-            if fc.is_new:
-                summary.new_files += 1
-            if fc.is_deleted:
-                summary.deleted_files += 1
-            if fc.is_renamed:
-                summary.renamed_files += 1
-            if fc.is_binary:
-                summary.binary_files += 1
-
-        summary.total_files_changed = len(summary.files)
-        return summary
-
-    def _split_files(self, diff_text: str) -> List[str]:
-        """Split a multi-file diff into individual file diffs."""
-        lines = diff_text.split("\n")
-        chunks = []
-        current = []
-        for line in lines:
-            if line.startswith("diff --git ") and current:
-                chunks.append("\n".join(current))
-                current = [line]
-            else:
-                current.append(line)
-        if current:
-            chunks.append("\n".join(current))
-        return chunks
-
-    def _parse_file_diff(self, diff_text: str) -> FileChange:
-        """Parse a single file's diff section."""
-        lines = diff_text.split("\n")
-        fc = FileChange(path="")
-
-        # Extract file paths
-        for line in lines:
-            m = self.DIFF_FILE_RE.match(line)
-            if m:
-                fc.path = m.group(2)
-                break
-
-        # Check for special states
-        for line in lines:
-            if self.NEW_FILE_RE.match(line):
-                fc.is_new = True
-            elif self.DELETED_FILE_RE.match(line):
-                fc.is_deleted = True
-            elif self.RENAME_RE.match(line):
-                fc.old_path = m.group(1) if (m := self.RENAME_RE.match(line)) else None
-                fc.is_renamed = True
-            elif self.BINARY_RE.match(line):
-                fc.is_binary = True
-                return fc  # No hunks for binary
-
-        # Rename TO
-        for line in lines:
-            m = self.RENAME_TO_RE.match(line)
-            if m and fc.is_renamed:
-                fc.path = m.group(1)
-
-        # Parse hunks
-        current_hunk = None
-        for line in lines:
-            m = self.HUNK_HEADER_RE.match(line)
-            if m:
-                if current_hunk:
-                    self._classify_hunk(current_hunk, fc)
-                    fc.hunks.append(current_hunk)
-                current_hunk = Hunk(
-                    header=m.group(5).strip(),
-                    old_start=int(m.group(1)),
-                    old_count=int(m.group(2) or 1),
-                    new_start=int(m.group(3)),
-                    new_count=int(m.group(4) or 1),
-                )
-            elif current_hunk and (line.startswith("+") or line.startswith("-") or line.startswith(" ")):
-                current_hunk.lines.append(line)
-
-        if current_hunk:
-            self._classify_hunk(current_hunk, fc)
-            fc.hunks.append(current_hunk)
-
-        return fc
-
-    def _classify_hunk(self, hunk: Hunk, fc: FileChange):
-        """Classify a hunk and count lines."""
-        added = sum(1 for l in hunk.lines if l.startswith("+"))
-        deleted = sum(1 for l in hunk.lines if l.startswith("-"))
-
-        fc.added_lines += added
-        fc.deleted_lines += deleted
-
-        if added > 0 and deleted == 0:
-            hunk.category = ChangeCategory.ADDED
-        elif deleted > 0 and added == 0:
-            hunk.category = ChangeCategory.DELETED
-        elif added > 0 and deleted > 0:
-            hunk.category = ChangeCategory.MODIFIED
-        else:
-            hunk.category = ChangeCategory.CONTEXT

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()

scripts/test_diff_analyzer.py

@@ -1,189 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/diff_analyzer.py — 10 tests."""
-
-import sys
-import os
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-
-import importlib.util
-spec = importlib.util.spec_from_file_location("da", os.path.join(os.path.dirname(__file__) or ".", "diff_analyzer.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-DiffAnalyzer = mod.DiffAnalyzer
-ChangeCategory = mod.ChangeCategory
-
-
-SAMPLE_ADD = """diff --git a/new.py b/new.py
-new file mode 100644
---- /dev/null
-+++ b/new.py
-@@ -0,0 +1,3 @@
-+def hello():
-+    print("world")
-+    return True
-"""
-
-SAMPLE_DELETE = """diff --git a/old.py b/old.py
-deleted file mode 100644
---- a/old.py
-+++ /dev/null
-@@ -1,2 +0,0 @@
--def goodbye():
--    pass
-"""
-
-SAMPLE_MODIFY = """diff --git a/app.py b/app.py
---- a/app.py
-+++ b/app.py
-@@ -1,3 +1,4 @@
- def main():
--    print("old")
-+    print("new")
-+    print("extra")
-     return 0
-"""
-
-SAMPLE_RENAME = """diff --git a/old_name.py b/new_name.py
-rename from old_name.py
-rename to new_name.py
---- a/old_name.py
-+++ b/new_name.py
-@@ -1,1 +1,1 @@
--old content
-+new content
-"""
-
-SAMPLE_MULTI = """diff --git a/a.py b/a.py
---- a/a.py
-+++ b/a.py
-@@ -1,1 +1,2 @@
- existing
-+added line
-diff --git b/b.py b/b.py
-new file mode 100644
---- /dev/null
-+++ b/b.py
-@@ -0,0 +1,1 @@
-+new file
-"""
-
-SAMPLE_BINARY = """diff --git a/img.png b/img.png
-Binary files a/img.png and b/img.png differ
-"""
-
-
-def test_empty():
-    a = DiffAnalyzer()
-    s = a.analyze("")
-    assert s.total_files_changed == 0
-    print("PASS: test_empty")
-
-def test_addition():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_ADD)
-    assert s.total_files_changed == 1
-    assert s.total_added == 3
-    assert s.total_deleted == 0
-    assert s.new_files == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.ADDED
-    print("PASS: test_addition")
-
-def test_deletion():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_DELETE)
-    assert s.total_deleted == 2
-    assert s.deleted_files == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.DELETED
-    print("PASS: test_deletion")
-
-def test_modification():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MODIFY)
-    assert s.total_added == 2
-    assert s.total_deleted == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
-    print("PASS: test_modification")
-
-def test_rename():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_RENAME)
-    assert s.renamed_files == 1
-    assert s.files[0].old_path == "old_name.py"
-    assert s.files[0].path == "new_name.py"
-    assert s.files[0].is_renamed == True
-    print("PASS: test_rename")
-
-def test_multiple_files():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MULTI)
-    assert s.total_files_changed == 2
-    assert s.new_files == 1
-    print("PASS: test_multiple_files")
-
-def test_binary():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_BINARY)
-    assert s.binary_files == 1
-    assert s.files[0].is_binary == True
-    assert len(s.files[0].hunks) == 0
-    print("PASS: test_binary")
-
-def test_to_dict():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MODIFY)
-    d = s.to_dict()
-    assert "total_files_changed" in d
-    assert "files" in d
-    assert isinstance(d["files"], list)
-    print("PASS: test_to_dict")
-
-def test_context_only():
-    diff = """diff --git a/f.py b/f.py
---- a/f.py
-+++ b/f.py
-@@ -1,3 +1,3 @@
- line1
--old
-+new
- line3
-"""
-    a = DiffAnalyzer()
-    s = a.analyze(diff)
-    # Has both added and deleted = MODIFIED
-    assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
-    print("PASS: test_context_only")
-
-def test_multi_hunk():
-    diff = """diff --git a/f.py b/f.py
---- a/f.py
-+++ b/f.py
-@@ -1,1 +1,2 @@
- existing
-+first addition
-@@ -10,1 +11,2 @@
- more
-+second addition
-"""
-    a = DiffAnalyzer()
-    s = a.analyze(diff)
-    assert s.total_hunks == 2
-    assert s.total_added == 2
-    print("PASS: test_multi_hunk")
-
-
-def run_all():
-    test_empty()
-    test_addition()
-    test_deletion()
-    test_modification()
-    test_rename()
-    test_multiple_files()
-    test_binary()
-    test_to_dict()
-    test_context_only()
-    test_multi_hunk()
-    print("\nAll 10 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()