feat: add codebase genome diff script for structural change detection

Introduces genome_diff.py — a tool for detecting structural changes between
two git refs: file-level changes, function/class signature modifications,
and dependency import changes.

Addresses #132.

knowledge/SCHEMA.md

@@ -43,26 +43,9 @@ The harvester writes to both. The bootstrapper reads from index.json. Humans edi
 | `last_confirmed` | date | no | ISO-8601 date last seen in a session |
 | `expires` | date | no | Optional. After this date, fact is stale |
 | `related` | string[] | no | IDs of related facts |
-| `provenance` | object | no | Provenance metadata — see Provenance Object section below |
 
 ### ID Format: `{domain}:{category}:{sequence}`
 
-
-
-### Provenance Object
-
-Every fact may include a [`provenance`](#fact-object) field that tracks its origin.
-
-| Field | Type | Required | Description |
-|-------|------|----------|-------------|
-| `source_session` | string | yes | Session ID / file path where this fact was extracted |
-| `source_model` | string | yes | Model name used for extraction (e.g., `xiaomi/mimo-v2-pro`) |
-| `source_provider` | string | yes | Provider name (`nous`, `openrouter`, `anthropic`, `openai`, etc.) |
-| `timestamp` | date-time | yes | Extraction timestamp (ISO-8601 UTC) |
-| `extraction_method` | enum | yes | `llm_extraction`, `manual`, or `retroactive_harvest` |
-| `confidence` | float | yes | Confidence at extraction time (0.0–1.0) |
-| `verified` | boolean | yes | `true` if fact has been manually reviewed, else `false` |
-
 ### Categories
 
 | Category | Definition |
@@ -102,35 +85,6 @@ knowledge/
     └── {agent-type}.yaml
 ```
 
-
-
-### Provenance Object (added via `write_knowledge()` and harvester)
-
-```json
-{
-  "source_session": "string — session ID or file path",
-  "source_model": "string — model used for extraction",
-  "source_provider": "string — provider name (nous, openrouter, etc.)",
-  "timestamp": "string — ISO-8601 UTC extraction time",
-  "extraction_method": "string — llm_extraction|manual|retroactive_harvest",
-  "confidence": "float — 0.0–1.0 confidence from extraction",
-  "verified": "boolean — whether fact has been manually verified"
-}
-```
-
-The `provenance` field is attached to every fact harvested via `write_knowledge()`. It provides traceability: which session produced this fact, which model/provider extracted it, when, and with what confidence.
-
-| Provenance Field | Type | Required | Description |
-|------------------|------|----------|-------------|
-| `source_session` | string | yes | Session ID / file path where extracted |
-| `source_model` | string | yes | Model name (e.g., `xiaomi/mimo-v2-pro`) |
-| `source_provider` | string | yes | Provider (`nous`, `openrouter`, `anthropic`, `openai`) |
-| `timestamp` | date-time | yes | Extraction timestamp (ISO-8601) |
-| `extraction_method` | enum | yes | `llm_extraction`, `manual`, or `retroactive_harvest` |
-| `confidence` | float | yes | Confidence score (0.0–1.0) at extraction time |
-| `verified` | boolean | yes | `true` if manually reviewed, else `false` |
-
-
 ## YAML File Format
 
 YAML files use frontmatter for metadata, then markdown sections with fact entries:

schemas/provenance.json

@@ -1,52 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "title": "Knowledge Provenance",
-  "description": "Provenance metadata attached to every knowledge fact",
-  "type": "object",
-  "required": [
-    "source_session",
-    "source_model",
-    "source_provider",
-    "timestamp"
-  ],
-  "properties": {
-    "source_session": {
-      "type": "string",
-      "description": "Session ID or file path where this fact was extracted"
-    },
-    "source_model": {
-      "type": "string",
-      "description": "Model used for extraction (e.g., 'xiaomi/mimo-v2-pro')"
-    },
-    "source_provider": {
-      "type": "string",
-      "description": "Provider name (nous, openrouter, anthropic, etc.)"
-    },
-    "timestamp": {
-      "type": "string",
-      "format": "date-time",
-      "description": "UTC ISO-8601 timestamp when this fact was extracted"
-    },
-    "extraction_method": {
-      "type": "string",
-      "description": "How the fact was extracted (llm_extraction, manual, retroactive_harvest)",
-      "enum": [
-        "llm_extraction",
-        "manual",
-        "retroactive_harvest"
-      ],
-      "default": "llm_extraction"
-    },
-    "confidence": {
-      "type": "number",
-      "minimum": 0,
-      "maximum": 1,
-      "description": "Confidence assigned during extraction (copied from top-level fact)"
-    },
-    "verified": {
-      "type": "boolean",
-      "description": "Whether this fact has been manually verified",
-      "default": false
-    }
-  }
-}

scripts/genome_diff.py

@@ -0,0 +1,288 @@
+#!/usr/bin/env python3
+"""
+Codebase Genome Diff — Detect structural changes between two versions.
+
+Compares two git refs (commits, branches, tags) and produces a human-readable
+report of structural changes:
+  • Added/removed/renamed files
+  • Changed functions/classes (signature modifications)
+  • New dependencies (imports, requirements, etc.)
+
+Usage:
+    python3 scripts/genome_diff.py --ref1 <commit1> --ref2 <commit2>
+    python3 scripts/genome_diff.py --ref1 main --ref2 feature-branch
+    python3 scripts/genome_diff.py --ref1 v1.0 --ref2 v2.0 --output report.txt
+"""
+
+import argparse
+import json
+import os
+import re
+import subprocess
+import sys
+from dataclasses import dataclass, field
+from typing import List, Dict, Any, Optional
+
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, SCRIPT_DIR)
+from diff_analyzer import DiffAnalyzer, ChangeCategory
+
+
+@dataclass
+class FunctionChange:
+    file: str
+    name: str
+    kind: str  # 'function' or 'class'
+    change_type: str  # 'added' or 'removed' (simplified)
+    old_line: Optional[int] = None
+    new_line: Optional[int] = None
+
+
+@dataclass
+class DependencyChange:
+    file: str
+    module: str
+    change_type: str  # 'added' or 'removed' or 'modified'
+    line: int = 0
+
+
+@dataclass
+class GenomeDiffReport:
+    ref1: str
+    ref2: str
+    file_changes: List[Dict[str, Any]] = field(default_factory=list)
+    function_changes: List[FunctionChange] = field(default_factory=list)
+    dependency_changes: List[DependencyChange] = field(default_factory=list)
+    total_files_changed: int = 0
+    total_functions_changed: int = 0
+    total_dependencies_changed: int = 0
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "ref1": self.ref1,
+            "ref2": self.ref2,
+            "summary": {
+                "files": self.total_files_changed,
+                "functions": self.total_functions_changed,
+                "dependencies": self.total_dependencies_changed,
+            },
+            "file_changes": self.file_changes,
+            "function_changes": [fc.__dict__ for fc in self.function_changes],
+            "dependency_changes": [dc.__dict__ for dc in self.dependency_changes],
+        }
+
+    def human_report(self) -> str:
+        lines = []
+        lines.append(f"Codebase Genome Diff: {self.ref1} → {self.ref2}")
+        lines.append("=" * 60)
+        lines.append(f"  Files changed: {self.total_files_changed}")
+        lines.append(f"  Functions changed: {self.total_functions_changed}")
+        lines.append(f"  Dependencies changed: {self.total_dependencies_changed}")
+        lines.append("")
+
+        for fc in self.file_changes:
+            kind = []
+            if fc.get('is_new'):
+                kind.append("NEW")
+            if fc.get('is_deleted'):
+                kind.append("DELETED")
+            if fc.get('is_renamed'):
+                kind.append("RENAMED")
+            if fc.get('is_binary'):
+                kind.append("BINARY")
+            kind_str = f" [{', '.join(kind)}]" if kind else ""
+            lines.append(f"  {fc['path']}{kind_str}  (+{fc['added_lines']}/-{fc['deleted_lines']})")
+        lines.append("")
+
+        for fc in self.function_changes:
+            op = {'added': '+', 'removed': '-', 'modified': '~'}.get(fc.change_type, '?')
+            lines.append(f"  [{op}] {fc.file}: {fc.kind} '{fc.name}'")
+        lines.append("")
+
+        for dc in self.dependency_changes:
+            op = '+' if dc.change_type == 'added' else '-'
+            lines.append(f"  [{op}] {dc.file}: {dc.module}")
+        lines.append("")
+
+        return "\n".join(lines)
+
+
+def run_git_diff(ref1: str, ref2: str) -> str:
+    result = subprocess.run(
+        ['git', 'diff', '--unified=0', f'{ref1}...{ref2}'],
+        capture_output=True, text=True, cwd=SCRIPT_DIR
+    )
+    if result.returncode not in (0, 1):
+        print(f"git diff failed: {result.stderr}", file=sys.stderr)
+        sys.exit(1)
+    return result.stdout
+
+
+def extract_function_changes(diff_text: str) -> List[FunctionChange]:
+    changes: List[FunctionChange] = []
+    pattern = re.compile(r'^([+\-])\s*(def|class)\s+(\w+)', re.MULTILINE)
+    hunk_header_re = re.compile(r'^@@\s+-(\d+)(?:,(\d+))?\s+\+(\d+)(?:,(\d+))?\s+@@')
+    current_old_line: Optional[int] = None
+    current_new_line: Optional[int] = None
+
+    for line in diff_text.split('\n'):
+        hdr = hunk_header_re.match(line)
+        if hdr:
+            current_old_line = int(hdr.group(1))
+            current_new_line = int(hdr.group(3))
+            continue
+        m = pattern.match(line)
+        if m:
+            op = m.group(1)
+            kind = m.group(2)
+            name = m.group(3)
+            change_type = "added" if op == '+' else "removed"
+            line_num = current_new_line if change_type == "added" else current_old_line
+            changes.append(FunctionChange(
+                file="<unknown>",
+                name=name,
+                kind=kind,
+                change_type=change_type,
+                new_line=line_num if change_type == "added" else None,
+                old_line=line_num if change_type == "removed" else None,
+            ))
+            # Advance line counters heuristically
+            if op == '-':
+                if current_old_line is not None:
+                    current_old_line += 1
+            elif op == '+':
+                if current_new_line is not None:
+                    current_new_line += 1
+        elif line.startswith(' '):
+            if current_old_line is not None:
+                current_old_line += 1
+            if current_new_line is not None:
+                current_new_line += 1
+        # lines starting with other prefixes (like \\ No newline) ignored
+    return changes
+
+
+def extract_dependency_changes(diff_text: str, analyzer: DiffAnalyzer) -> List[DependencyChange]:
+    changes: List[DependencyChange] = []
+    import_pattern = re.compile(
+        r'^([+\-])\s*(?:import\s+([\w\.]+)|from\s+([\w\.]+)\s+import)',
+        re.MULTILINE
+    )
+    file_diffs = analyzer._split_files(diff_text)
+    for file_diff in file_diffs:
+        file_match = re.search(r'^diff --git a/.*? b/(.*?)$', file_diff, re.MULTILINE)
+        if not file_match:
+            continue
+        filepath = file_match.group(1)
+
+        # Scan each line for import changes
+        for line in file_diff.split('\n'):
+            m = import_pattern.match(line)
+            if m:
+                change_type = "added" if m.group(1) == '+' else "removed"
+                module = m.group(2) or m.group(3)
+                changes.append(DependencyChange(
+                    file=filepath,
+                    module=module,
+                    change_type=change_type,
+                    line=0
+                ))
+
+        # Detect if this file is a dependency manifest
+        req_file_pattern = re.compile(
+            r'^[\+\-].*?(requirements(.*?)\.txt|pyproject\.toml|setup\.py|Pipfile)'
+        )
+        if any(req_file_pattern.match(line) for line in file_diff.split('\n')):
+            if not any(c.file == filepath and c.module == "<file>" for c in changes):
+                changes.append(DependencyChange(
+                    file=filepath,
+                    module="<file>",
+                    change_type="modified",
+                    line=0
+                ))
+    return changes
+
+
+def correlate_function_changes_with_files(diff_text: str, functions: List[FunctionChange]) -> List[FunctionChange]:
+    result: List[FunctionChange] = []
+    # Split diff into per-file sections
+    file_sections: List[tuple[str, str]] = []
+    current_file: Optional[str] = None
+    current_lines: List[str] = []
+    for line in diff_text.split('\n'):
+        if line.startswith('diff --git'):
+            if current_file is not None:
+                file_sections.append((current_file, '\n'.join(current_lines)))
+            m = re.match(r'^diff --git a/.*? b/(.*?)$', line)
+            current_file = m.group(1) if m else "unknown"
+            current_lines = [line]
+        else:
+            current_lines.append(line)
+    if current_file is not None:
+        file_sections.append((current_file, '\n'.join(current_lines)))
+
+    pattern = re.compile(r'^([+\-])\s*(def|class)\s+(\w+)', re.MULTILINE)
+    for filepath, section in file_sections:
+        for m in pattern.finditer(section):
+            op = m.group(1)
+            kind = m.group(2)
+            name = m.group(3)
+            change_type = "added" if op == '+' else "removed"
+            result.append(FunctionChange(
+                file=filepath,
+                name=name,
+                kind=kind,
+                change_type=change_type
+            ))
+    return result
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Codebase Genome Diff — structural changes between versions")
+    parser.add_argument("--ref1", required=True, help="First git ref (commit, branch, tag)")
+    parser.add_argument("--ref2", required=True, help="Second git ref")
+    parser.add_argument("--output", help="Write report to file")
+    parser.add_argument("--json", action="store_true", help="Output JSON instead of human report")
+    args = parser.parse_args()
+
+    try:
+        diff_text = run_git_diff(args.ref1, args.ref2)
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not diff_text.strip():
+        print(f"No differences between {args.ref1} and {args.ref2}.")
+        sys.exit(0)
+
+    analyzer = DiffAnalyzer()
+    summary = analyzer.analyze(diff_text)
+
+    file_changes = [fc.to_dict() for fc in summary.files]
+    func_changes = extract_function_changes(diff_text)
+    func_changes = correlate_function_changes_with_files(diff_text, func_changes)
+    dep_changes = extract_dependency_changes(diff_text, analyzer)
+
+    report = GenomeDiffReport(
+        ref1=args.ref1,
+        ref2=args.ref2,
+        file_changes=file_changes,
+        function_changes=func_changes,
+        dependency_changes=dep_changes,
+        total_files_changed=len(file_changes),
+        total_functions_changed=len(func_changes),
+        total_dependencies_changed=len(dep_changes),
+    )
+
+    output = json.dumps(report.to_dict(), indent=2) if args.json else report.human_report()
+
+    if args.output:
+        with open(args.output, 'w') as f:
+            f.write(output + '\n')
+        print(f"Report written to {args.output}")
+    else:
+        print(output)
+
+
+if __name__ == '__main__':
+    main()

scripts/harvester.py

@@ -27,22 +27,6 @@ sys.path.insert(0, str(SCRIPT_DIR))
 
 from session_reader import read_session, extract_conversation, truncate_for_context, messages_to_text
 
-def extract_provider(api_base: str) -> str:
-    """Infer provider name from API base URL."""
-    url = api_base.lower()
-    if 'nousresearch' in url or 'nous' in url:
-        return 'nous'
-    if 'openrouter' in url:
-        return 'openrouter'
-    if 'anthropic' in url:
-        return 'anthropic'
-    if 'openai' in url:
-        return 'openai'
-    # Fallback: try to extract hostname
-    from urllib.parse import urlparse
-    host = urlparse(api_base).netloc
-    return host.split('.')[0] if host else 'unknown' 
-
 # --- Configuration ---
 
 DEFAULT_API_BASE = os.environ.get("HARVESTER_API_BASE", "https://api.nousresearch.com/v1")
@@ -245,34 +229,15 @@ def validate_fact(fact: dict) -> bool:
     return True
 
 
-def write_knowledge(index: dict, new_facts: list[dict], knowledge_dir: str, source_session: str = "", model: str = "", provider: str = ""):
-    """Write new facts to the knowledge store.
-    
-    Adds provenance metadata to each fact. If model/provider are empty, tries to
-    infer from environment or defaults.
-    """
+def write_knowledge(index: dict, new_facts: list[dict], knowledge_dir: str, source_session: str = ""):
+    """Write new facts to the knowledge store."""
     kdir = Path(knowledge_dir)
     kdir.mkdir(parents=True, exist_ok=True)
     
-    # Determine model/provider defaults if not provided
-    model = model or os.environ.get("HARVESTER_MODEL", "xiaomi/mimo-v2-pro")
-    provider = provider or os.environ.get("HARVESTER_PROVIDER", "nous")
-    
-    timestamp = datetime.now(timezone.utc).isoformat()
-    
-    # Add provenance to each fact
+    # Add source tracking to each fact
     for fact in new_facts:
-        provenance = {
-            'source_session': source_session,
-            'source_model': model,
-            'source_provider': provider,
-            'timestamp': timestamp,
-            'extraction_method': 'llm_extraction',
-            'confidence': fact.get('confidence', 0.5),
-            'verified': False
-        }
-        fact['provenance'] = provenance
-        fact['harvested_at'] = timestamp
+        fact['source_session'] = source_session
+        fact['harvested_at'] = datetime.now(timezone.utc).isoformat()
     
     # Update index
     index['facts'].extend(new_facts)
@@ -365,7 +330,7 @@ def harvest_session(session_path: str, knowledge_dir: str, api_base: str, api_ke
         
         # 8. Write (unless dry run)
         if new_facts and not dry_run:
-            write_knowledge(existing_index, new_facts, knowledge_dir, source_session=session_path, model=model, provider=extract_provider(api_base))
+            write_knowledge(existing_index, new_facts, knowledge_dir, source_session=session_path)
         
         stats['elapsed_seconds'] = round(time.time() - start_time, 2)
         return stats