feat: Add diff analyzer tests (closes #176)

GENOME.md

@@ -1,239 +0,0 @@
-# GENOME.md — compounding-intelligence
-
-*Auto-generated codebase genome. See timmy-home#676.*
-
----
-
-## Project Overview
-
-**What:** A system that turns 1B+ daily agent tokens into durable, compounding fleet intelligence.
-
-**Why:** Every agent session starts at zero. The same mistakes get made repeatedly — the same HTTP 405 is rediscovered as a branch protection issue, the same token path is searched for from scratch. Intelligence evaporates when the session ends.
-
-**How:** Three pipelines form a compounding loop:
-
-```
-SESSION ENDS → HARVESTER → KNOWLEDGE STORE → BOOTSTRAPPER → NEW SESSION STARTS SMARTER
-                              ↓
-                         MEASURER → Prove it's working
-```
-
-**Status:** Early stage. Template and test scaffolding exist. Core pipeline scripts (harvester.py, bootstrapper.py, measurer.py, session_reader.py) are planned but not yet implemented. The knowledge extraction prompt is complete and validated.
-
----
-
-## Architecture
-
-```mermaid
-graph TD
-    A[Session Transcript<br/>.jsonl] --> B[Harvester]
-    B --> C{Extract Knowledge}
-    C --> D[knowledge/index.json]
-    C --> E[knowledge/global/*.md]
-    C --> F[knowledge/repos/{repo}.md]
-    C --> G[knowledge/agents/{agent}.md]
-    D --> H[Bootstrapper]
-    H --> I[Bootstrap Context<br/>2k token injection]
-    I --> J[New Session<br/>starts smarter]
-    J --> A
-    D --> K[Measurer]
-    K --> L[metrics/dashboard.md]
-    K --> M[Velocity / Hit Rate<br/>Error Reduction]
-```
-
-### Pipeline 1: Harvester
-
-**Status:** Prompt designed. Script not implemented.
-
-Reads finished session transcripts (JSONL). Uses `templates/harvest-prompt.md` to extract durable knowledge into five categories:
-
-| Category | Description | Example |
-|----------|-------------|---------|
-| `fact` | Concrete, verifiable information | "Repository X has 5 files" |
-| `pitfall` | Errors encountered, wrong assumptions | "Token is at ~/.config/gitea/token, not env var" |
-| `pattern` | Successful action sequences | "Deploy: test → build → push → webhook" |
-| `tool-quirk` | Environment-specific behaviors | "URL format requires trailing slash" |
-| `question` | Identified but unanswered | "Need optimal batch size for harvesting" |
-
-Output schema per knowledge item:
-```json
-{
-  "fact": "One sentence description",
-  "category": "fact|pitfall|pattern|tool-quirk|question",
-  "repo": "repo-name or 'global'",
-  "confidence": 0.0-1.0
-}
-```
-
-### Pipeline 2: Bootstrapper
-
-**Status:** Not implemented.
-
-Queries knowledge store before session start. Assembles a compact 2k-token context from relevant facts. Injects into session startup so the agent begins with full situational awareness.
-
-### Pipeline 3: Measurer
-
-**Status:** Not implemented.
-
-Tracks compounding metrics: knowledge velocity (facts/day), error reduction (%), hit rate (knowledge used / knowledge available), task completion improvement.
-
----
-
-## Directory Structure
-
-```
-compounding-intelligence/
-├── README.md                           # Project overview and architecture
-├── GENOME.md                           # This file (codebase genome)
-├── knowledge/                          # [PLANNED] Knowledge store
-│   ├── index.json                      # Machine-readable fact index
-│   ├── global/                         # Cross-repo knowledge
-│   ├── repos/{repo}.md                 # Per-repo knowledge
-│   └── agents/{agent}.md               # Agent-type notes
-├── scripts/
-│   ├── test_harvest_prompt.py          # Basic prompt validation (2.5KB)
-│   └── test_harvest_prompt_comprehensive.py  # Full prompt structure test (6.8KB)
-├── templates/
-│   └── harvest-prompt.md               # Knowledge extraction prompt (3.5KB)
-├── test_sessions/
-│   ├── session_success.jsonl           # Happy path test data
-│   ├── session_failure.jsonl           # Failure path test data
-│   ├── session_partial.jsonl           # Incomplete session test data
-│   ├── session_patterns.jsonl          # Pattern extraction test data
-│   └── session_questions.jsonl         # Question identification test data
-└── metrics/                            # [PLANNED] Compounding metrics
-    └── dashboard.md
-```
-
----
-
-## Entry Points and Data Flow
-
-### Entry Point 1: Knowledge Extraction (Harvester)
-
-```
-Input:  Session transcript (JSONL)
-        ↓
-        templates/harvest-prompt.md (LLM prompt)
-        ↓
-        Knowledge items (JSON array)
-        ↓
-Output: knowledge/index.json + per-repo/per-agent markdown files
-```
-
-### Entry Point 2: Session Bootstrap (Bootstrapper)
-
-```
-Input:  Session context (repo, agent type, task type)
-        ↓
-        knowledge/index.json (query relevant facts)
-        ↓
-        2k-token bootstrap context
-        ↓
-Output: Injected into session startup
-```
-
-### Entry Point 3: Measurement (Measurer)
-
-```
-Input:  knowledge/index.json + session history
-        ↓
-        Velocity, hit rate, error reduction calculations
-        ↓
-Output: metrics/dashboard.md
-```
-
----
-
-## Key Abstractions
-
-### Knowledge Item
-The atomic unit. One sentence, one category, one confidence score. Designed to be small enough that 1000 items fit in a 2k-token bootstrap context.
-
-### Knowledge Store
-A directory structure that mirrors the fleet's mental model:
-- `global/` — knowledge that applies everywhere (tool quirks, environment facts)
-- `repos/` — knowledge specific to each repo
-- `agents/` — knowledge specific to each agent type
-
-### Confidence Score
-0.0–1.0 scale. Defines how certain the harvester is about each extracted fact:
-- 0.9–1.0: Explicitly stated with verification
-- 0.7–0.8: Clearly implied by multiple data points
-- 0.5–0.6: Suggested but not fully verified
-- 0.3–0.4: Inferred from limited data
-- 0.1–0.2: Speculative or uncertain
-
-### Bootstrap Context
-The 2k-token injection that a new session receives. Assembled from the most relevant knowledge items for the current task, filtered by confidence > 0.7, deduplicated, and compressed.
-
----
-
-## API Surface
-
-### Internal (scripts not yet implemented)
-
-| Script | Input | Output | Status |
-|--------|-------|--------|--------|
-| `harvester.py` | Session JSONL path | Knowledge items JSON | PLANNED |
-| `bootstrapper.py` | Repo + agent type | 2k-token context string | PLANNED |
-| `measurer.py` | Knowledge store path | Metrics JSON | PLANNED |
-| `session_reader.py` | Session JSONL path | Parsed transcript | PLANNED |
-
-### Prompt (templates/harvest-prompt.md)
-
-The extraction prompt is the core "API." It takes a session transcript and returns structured JSON. It defines:
-- Five extraction categories
-- Output format (JSON array of knowledge items)
-- Confidence scoring rubric
-- Constraints (no hallucination, specificity, relevance, brevity)
-- Example input/output pair
-
----
-
-## Test Coverage
-
-### What Exists
-
-| File | Tests | Coverage |
-|------|-------|----------|
-| `scripts/test_harvest_prompt.py` | 2 tests | Prompt file existence, sample transcript |
-| `scripts/test_harvest_prompt_comprehensive.py` | 5 tests | Prompt structure, categories, fields, confidence scoring, size limits |
-| `test_sessions/*.jsonl` | 5 sessions | Success, failure, partial, patterns, questions |
-
-### What's Missing
-
-1. **Harvester integration test** — Does the prompt actually extract correct knowledge from real transcripts?
-2. **Bootstrapper test** — Does it assemble relevant context correctly?
-3. **Knowledge store test** — Does the index.json maintain consistency?
-4. **Confidence calibration test** — Do high-confidence facts actually prove true in later sessions?
-5. **Deduplication test** — Are duplicate facts across sessions handled?
-6. **Staleness test** — How does the system handle outdated knowledge?
-
----
-
-## Security Considerations
-
-1. **No secrets in knowledge store** — The harvester must filter out API keys, tokens, and credentials from extracted facts. The prompt constraints mention this but there is no automated guard.
-
-2. **Knowledge poisoning** — A malicious or corrupted session could inject false facts. Confidence scoring partially mitigates this, but there is no verification step.
-
-3. **Access control** — The knowledge store has no access control. Any process that can read the directory can read all facts. In a multi-tenant setup, this is a concern.
-
-4. **Transcript privacy** — Session transcripts may contain user data. The harvester must not extract personally identifiable information into the knowledge store.
-
----
-
-## The 100x Path (from README)
-
-```
-Month 1:  15,000 facts, sessions 20% faster
-Month 2:  45,000 facts, sessions 40% faster, first-try success up 30%
-Month 3:  90,000 facts, fleet measurably smarter per token
-```
-
-Each new session is better than the last. The intelligence compounds.
-
----
-
-*Generated by codebase-genome pipeline. Ref: timmy-home#676.*

scripts/diff_analyzer.py

@@ -0,0 +1,216 @@
+#!/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/test_diff_analyzer.py

@@ -0,0 +1,189 @@
+#!/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()