test: knowledge gap identifier tests (#172)

scripts/gitea_issue_parser.py

@@ -1,131 +0,0 @@
-#!/usr/bin/env python3
-"""
-Gitea Issue Body Parser — Extract structured data from markdown issue bodies.
-
-Usage:
-    cat issue_body.txt | python3 scripts/gitea_issue_parser.py --stdin --pretty
-    python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123 --pretty
-    python3 scripts/gitea_issue_parser.py body.txt --title "Fix thing (#42)" --labels pipeline extraction
-"""
-
-import argparse
-import json
-import re
-import sys
-from typing import Dict, List, Any, Optional
-
-
-def parse_issue_body(body: str, title: str = "", labels: List[str] = None) -> Dict[str, Any]:
-    """Parse a Gitea issue markdown body into structured JSON.
-    
-    Extracted fields:
-    - title: Issue title
-    - context: Background/description section
-    - criteria[]: Acceptance criteria (checkboxes or numbered lists)
-    - labels[]: Issue labels
-    - epic_ref: Parent/epic issue reference (from "Closes #N" or title)
-    - sections{}: All ## sections as key-value pairs
-    """
-    result = {
-        "title": title,
-        "context": "",
-        "criteria": [],
-        "labels": labels or [],
-        "epic_ref": None,
-        "sections": {},
-    }
-    
-    if not body:
-        return result
-    
-    # Extract epic reference from title or body
-    epic_patterns = [
-        r"(?:closes|fixes|addresses|refs?)\s+#(\d+)",
-        r"#(\d+)",
-    ]
-    for pattern in epic_patterns:
-        match = re.search(pattern, (title + " " + body).lower())
-        if match:
-            result["epic_ref"] = int(match.group(1))
-            break
-    
-    # Parse ## sections
-    section_pattern = r"^##\s+(.+?)$\n((?:^(?!##\s).*$\n?)*)"
-    for match in re.finditer(section_pattern, body, re.MULTILINE):
-        section_name = match.group(1).strip().lower().replace(" ", "_")
-        section_content = match.group(2).strip()
-        result["sections"][section_name] = section_content
-    
-    # Extract acceptance criteria (checkboxes)
-    checkbox_pattern = r"^\s*-\s*\[([ xX])\]\s*(.+)$"
-    for match in re.finditer(checkbox_pattern, body, re.MULTILINE):
-        checked = match.group(1).lower() == "x"
-        text = match.group(2).strip()
-        result["criteria"].append({"text": text, "checked": checked})
-    
-    # If no checkboxes, try numbered lists in "Acceptance Criteria" or "Criteria" section
-    if not result["criteria"]:
-        for section_name in ["acceptance_criteria", "criteria", "acceptance criteria"]:
-            if section_name in result["sections"]:
-                numbered = r"^\s*\d+\.\s*(.+)$"
-                for match in re.finditer(numbered, result["sections"][section_name], re.MULTILINE):
-                    result["criteria"].append({"text": match.group(1).strip(), "checked": False})
-                break
-    
-    # Extract context (first section or first paragraph before any ## heading)
-    first_heading = body.find("## ")
-    if first_heading > 0:
-        context_text = body[:first_heading].strip()
-    else:
-        context_text = body.split("\n\n")[0].strip()
-    # Clean up: remove "## Context" or "## Problem" header if present
-    context_text = re.sub(r"^#+\s*\w+\s*\n?", "", context_text).strip()
-    result["context"] = context_text[:500]  # Cap at 500 chars
-    
-    return result
-
-
-def fetch_issue_from_url(url: str) -> Dict[str, Any]:
-    """Fetch an issue from a Gitea API URL and parse it."""
-    import urllib.request
-    req = urllib.request.Request(url, headers={"Accept": "application/json"})
-    with urllib.request.urlopen(req) as resp:
-        data = json.loads(resp.read())
-    
-    return parse_issue_body(
-        body=data.get("body", ""),
-        title=data.get("title", ""),
-        labels=[l["name"] for l in data.get("labels", [])]
-    )
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Parse Gitea issue markdown into structured JSON")
-    parser.add_argument("file", nargs="?", help="Issue body file (or use --stdin)")
-    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
-    parser.add_argument("--url", help="Gitea API URL to fetch issue from")
-    parser.add_argument("--title", default="", help="Issue title")
-    parser.add_argument("--labels", nargs="*", default=[], help="Issue labels")
-    parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON output")
-    
-    args = parser.parse_args()
-    
-    if args.url:
-        result = fetch_issue_from_url(args.url)
-    elif args.stdin:
-        body = sys.stdin.read()
-        result = parse_issue_body(body, args.title, args.labels)
-    elif args.file:
-        with open(args.file) as f:
-            body = f.read()
-        result = parse_issue_body(body, args.title, args.labels)
-    else:
-        parser.print_help()
-        sys.exit(1)
-    
-    indent = 2 if args.pretty else None
-    print(json.dumps(result, indent=indent))
-
-
-if __name__ == "__main__":
-    main()

scripts/knowledge_gap_identifier.py

@@ -0,0 +1,275 @@
+"""
+Knowledge Gap Identifier — Pipeline 10.7
+
+Cross-references code, docs, and tests to find gaps:
+- Undocumented functions/classes
+- Untested code paths
+- Documented but missing implementations
+- Test files without corresponding source
+
+Produces a gap report with severity and suggestions.
+"""
+
+from __future__ import annotations
+
+import ast
+import os
+import re
+from dataclasses import dataclass, field
+from enum import Enum
+from pathlib import Path
+from typing import Dict, List, Optional, Set
+
+
+class GapSeverity(Enum):
+    INFO = "info"
+    WARNING = "warning"
+    ERROR = "error"
+
+
+class GapType(Enum):
+    UNDOCUMENTED = "undocumented"
+    UNTESTED = "untested"
+    MISSING_IMPLEMENTATION = "missing_implementation"
+    ORPHAN_TEST = "orphan_test"
+    STALE_DOC = "stale_doc"
+
+
+@dataclass
+class Gap:
+    """A single knowledge gap."""
+    gap_type: GapType
+    severity: GapSeverity
+    file: str
+    line: Optional[int]
+    name: str
+    description: str
+    suggestion: str
+
+
+@dataclass
+class GapReport:
+    """Full gap analysis report."""
+    repo_path: str
+    gaps: List[Gap] = field(default_factory=list)
+    stats: Dict[str, int] = field(default_factory=dict)
+
+    def summary(self) -> str:
+        lines = [f"Gap Report for {self.repo_path}", "=" * 40]
+        by_type = {}
+        for g in self.gaps:
+            by_type.setdefault(g.gap_type.value, []).append(g)
+
+        for gtype, items in sorted(by_type.items()):
+            lines.append(f"\n{gtype.upper()} ({len(items)}):")
+            for g in items:
+                loc = f"{g.file}:{g.line}" if g.line else g.file
+                lines.append(f"  [{g.severity.value}] {g.name} @ {loc}")
+                lines.append(f"    {g.description}")
+
+        lines.append(f"\nTotal gaps: {len(self.gaps)}")
+        self.stats = {k: len(v) for k, v in by_type.items()}
+        return "\n".join(lines)
+
+    def to_dict(self) -> dict:
+        return {
+            "repo_path": self.repo_path,
+            "total_gaps": len(self.gaps),
+            "stats": {k: len(v) for k, v in
+                      {gt: [g for g in self.gaps if g.gap_type == gt]
+                       for gt in GapType}.items() if v},
+            "gaps": [
+                {
+                    "type": g.gap_type.value,
+                    "severity": g.severity.value,
+                    "file": g.file,
+                    "line": g.line,
+                    "name": g.name,
+                    "description": g.description,
+                    "suggestion": g.suggestion,
+                }
+                for g in self.gaps
+            ],
+        }
+
+
+def _collect_python_files(root: Path) -> List[Path]:
+    """Collect .py files, excluding venv/node_modules/.git."""
+    skip = {".git", "venv", "env", ".venv", "node_modules", "__pycache__", ".tox", ".mypy_cache"}
+    files = []
+    for dirpath, dirnames, filenames in os.walk(root):
+        dirnames[:] = [d for d in dirnames if d not in skip]
+        for f in filenames:
+            if f.endswith(".py"):
+                files.append(Path(dirpath) / f)
+    return files
+
+
+def _extract_python_symbols(filepath: Path) -> Set[str]:
+    """Extract top-level function and class names from a Python file."""
+    symbols = set()
+    try:
+        source = filepath.read_text(encoding="utf-8", errors="replace")
+        tree = ast.parse(source, filename=str(filepath))
+    except (SyntaxError, UnicodeDecodeError):
+        return symbols
+
+    for node in ast.iter_child_nodes(tree):
+        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
+            symbols.add(node.name)
+    return symbols
+
+
+def _extract_doc_symbols(filepath: Path) -> Set[str]:
+    """Extract function/class names mentioned in markdown docs."""
+    symbols = set()
+    try:
+        text = filepath.read_text(encoding="utf-8", errors="replace")
+    except (UnicodeDecodeError, OSError):
+        return symbols
+
+    # Match backtick-quoted identifiers: `ClassName`, `func_name`, `func()`
+    for m in re.finditer(r"`([A-Za-z_]\w+)(?:\(\))?`", text):
+        symbols.add(m.group(1))
+    # Match ## ClassName or ### func_name headings
+    for m in re.finditer(r"^#{1,4}\s+(\w+)", text, re.MULTILINE):
+        symbols.add(m.group(1))
+    return symbols
+
+
+def _collect_test_files(root: Path) -> Dict[str, Path]:
+    """Map test module names to their file paths."""
+    test_map = {}
+    for dirpath, dirnames, filenames in os.walk(root):
+        dirnames[:] = [d for d in dirnames if d not in {".git", "venv", "node_modules"}]
+        for f in filenames:
+            if f.startswith("test_") and f.endswith(".py"):
+                # test_foo.py -> foo
+                module_name = f[5:-3]
+                test_map[module_name] = Path(dirpath) / f
+    return test_map
+
+
+class KnowledgeGapIdentifier:
+    """Analyzes a repo for knowledge gaps between code, docs, and tests."""
+
+    def analyze(self, repo_path: str) -> GapReport:
+        root = Path(repo_path).resolve()
+        report = GapReport(repo_path=str(root))
+
+        if not root.is_dir():
+            report.gaps.append(Gap(
+                gap_type=GapType.UNDOCUMENTED,
+                severity=GapSeverity.ERROR,
+                file=str(root),
+                line=None,
+                name="repo",
+                description="Path is not a directory",
+                suggestion="Provide a valid repo directory",
+            ))
+            return report
+
+        # Collect artifacts
+        py_files = _collect_python_files(root)
+        doc_files = list(root.glob("docs/**/*.md")) + list(root.glob("*.md"))
+        test_map = _collect_test_files(root / "tests") if (root / "tests").is_dir() else {}
+
+        # Extract symbols from each source file
+        source_symbols: Dict[str, Set[str]] = {}  # relative_path -> symbols
+        all_source_symbols: Set[str] = set()
+
+        for pf in py_files:
+            rel = str(pf.relative_to(root))
+            # Skip test files and setup/config
+            if "/tests/" in rel or rel.startswith("tests/") or rel.startswith("test_"):
+                continue
+            if pf.name in ("setup.py", "conftest.py", "conf.py"):
+                continue
+
+            syms = _extract_python_symbols(pf)
+            if syms:
+                source_symbols[rel] = syms
+                all_source_symbols.update(syms)
+
+        # Extract documented symbols
+        doc_symbols: Set[str] = set()
+        for df in doc_files:
+            doc_symbols.update(_extract_doc_symbols(df))
+
+        # Extract test-covered symbols
+        tested_modules: Set[str] = set(test_map.keys())
+
+        # --- Find gaps ---
+
+        # 1. Undocumented: source symbols not in any doc
+        for rel_path, syms in source_symbols.items():
+            for sym in sorted(syms):
+                if sym.startswith("_") and not sym.startswith("__"):
+                    continue  # Skip private
+                if sym not in doc_symbols:
+                    report.gaps.append(Gap(
+                        gap_type=GapType.UNDOCUMENTED,
+                        severity=GapSeverity.WARNING,
+                        file=rel_path,
+                        line=None,
+                        name=sym,
+                        description=f"{sym} defined in {rel_path} but not referenced in any docs",
+                        suggestion=f"Add documentation for {sym} in a .md file",
+                    ))
+
+        # 2. Untested: source modules without a corresponding test file
+        for rel_path in source_symbols:
+            module_name = Path(rel_path).stem
+            if module_name not in tested_modules and module_name not in ("__init__", "main", "config"):
+                report.gaps.append(Gap(
+                    gap_type=GapType.UNTESTED,
+                    severity=GapSeverity.ERROR,
+                    file=rel_path,
+                    line=None,
+                    name=module_name,
+                    description=f"No test file found for {rel_path}",
+                    suggestion=f"Create tests/test_{module_name}.py",
+                ))
+
+        # 3. Missing implementation: doc references symbol not in any source
+        referenced_but_missing = doc_symbols - all_source_symbols
+        for sym in sorted(referenced_but_missing):
+            # Filter out common non-code terms
+            if sym.lower() in {"todo", "fixme", "note", "example", "usage", "api",
+                               "install", "setup", "config", "license", "contributing",
+                               "changelog", "readme", "python", "bash", "json", "yaml",
+                               "http", "url", "cli", "gui", "ui", "api", "rest"}:
+                continue
+            if len(sym) < 3:
+                continue
+            report.gaps.append(Gap(
+                gap_type=GapType.MISSING_IMPLEMENTATION,
+                severity=GapSeverity.INFO,
+                file="(docs)",
+                line=None,
+                name=sym,
+                description=f"{sym} referenced in docs but not found in source code",
+                suggestion=f"Verify if {sym} should be implemented or update docs",
+            ))
+
+        # 4. Orphan tests: test files without matching source
+        for test_mod, test_path in test_map.items():
+            if test_mod not in tested_modules and not any(
+                test_mod in Path(f).stem for f in source_symbols
+            ):
+                # Check if any source file partially matches
+                matches_source = any(test_mod.replace("_", "-") in f or test_mod.replace("_", "") in Path(f).stem
+                                     for f in source_symbols)
+                if not matches_source:
+                    rel = str(test_path.relative_to(root))
+                    report.gaps.append(Gap(
+                        gap_type=GapType.ORPHAN_TEST,
+                        severity=GapSeverity.WARNING,
+                        file=rel,
+                        line=None,
+                        name=test_mod,
+                        description=f"Test file {rel} exists but no matching source module found",
+                        suggestion=f"Verify if the source was renamed or removed",
+                    ))
+
+        return report

scripts/knowledge_staleness_check.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+"""
+Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
+
+Usage:
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
+"""
+
+import argparse
+import hashlib
+import json
+import os
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Dict, List, Any, Optional
+
+
+def compute_file_hash(filepath: str) -> Optional[str]:
+    """Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
+    try:
+        with open(filepath, "rb") as f:
+            return "sha256:" + hashlib.sha256(f.read()).hexdigest()
+    except (FileNotFoundError, IsADirectoryError, PermissionError):
+        return None
+
+
+def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
+    """Check all entries in knowledge index for staleness.
+    
+    Returns list of entries with staleness info:
+    - status: "fresh" | "stale" | "missing_source" | "no_hash"
+    - current_hash: computed hash (if source exists)
+    - stored_hash: hash from index
+    """
+    with open(index_path) as f:
+        data = json.load(f)
+
+    facts = data.get("facts", [])
+    results = []
+
+    for entry in facts:
+        source_file = entry.get("source_file")
+        stored_hash = entry.get("source_hash")
+
+        if not source_file:
+            results.append({**entry, "status": "no_source", "current_hash": None})
+            continue
+
+        full_path = os.path.join(repo_root, source_file)
+        current_hash = compute_file_hash(full_path)
+
+        if current_hash is None:
+            results.append({**entry, "status": "missing_source", "current_hash": None})
+        elif not stored_hash:
+            results.append({**entry, "status": "no_hash", "current_hash": current_hash})
+        elif current_hash != stored_hash:
+            results.append({**entry, "status": "stale", "current_hash": current_hash})
+        else:
+            results.append({**entry, "status": "fresh", "current_hash": current_hash})
+
+    return results
+
+
+def fix_hashes(index_path: str, repo_root: str = ".") -> int:
+    """Add hashes to entries missing them. Returns count of fixed entries."""
+    with open(index_path) as f:
+        data = json.load(f)
+
+    fixed = 0
+    for entry in data.get("facts", []):
+        if entry.get("source_hash"):
+            continue
+        source_file = entry.get("source_file")
+        if not source_file:
+            continue
+        full_path = os.path.join(repo_root, source_file)
+        h = compute_file_hash(full_path)
+        if h:
+            entry["source_hash"] = h
+            fixed += 1
+
+    with open(index_path, "w") as f:
+        json.dump(data, f, indent=2)
+
+    return fixed
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check knowledge store staleness")
+    parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
+    parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
+
+    args = parser.parse_args()
+
+    if args.fix:
+        fixed = fix_hashes(args.index, args.repo)
+        print(f"Fixed {fixed} entries with missing hashes.")
+        return
+
+    results = check_staleness(args.index, args.repo)
+
+    if args.json:
+        print(json.dumps(results, indent=2))
+    else:
+        stale = [r for r in results if r["status"] != "fresh"]
+        fresh = [r for r in results if r["status"] == "fresh"]
+
+        print(f"Knowledge Store Staleness Check")
+        print(f"  Total entries: {len(results)}")
+        print(f"  Fresh: {len(fresh)}")
+        print(f"  Stale/Issues: {len(stale)}")
+        print()
+
+        if stale:
+            print("Issues found:")
+            for r in stale:
+                status = r["status"]
+                fact = r.get("fact", "?")[:60]
+                source = r.get("source_file", "?")
+                print(f"  [{status}] {source}: {fact}")
+        else:
+            print("All entries are fresh!")
+
+
+if __name__ == "__main__":
+    main()

scripts/test_gitea_issue_parser.py

@@ -1,109 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/gitea_issue_parser.py"""
-
-import sys
-import os
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-
-# Import from sibling
-import importlib.util
-spec = importlib.util.spec_from_file_location("parser", os.path.join(os.path.dirname(__file__) or ".", "gitea_issue_parser.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-parse_issue_body = mod.parse_issue_body
-
-
-def test_basic_parsing():
-    body = """## Context
-
-This is the background info.
-
-## Acceptance Criteria
-
-- [ ] First criterion
-- [x] Second criterion (done)
-
-## What to build
-
-Some description.
-"""
-    result = parse_issue_body(body, title="Test (#42)", labels=["bug"])
-    assert result["title"] == "Test (#42)"
-    assert result["labels"] == ["bug"]
-    assert result["epic_ref"] == 42
-    assert len(result["criteria"]) == 2
-    assert result["criteria"][0]["text"] == "First criterion"
-    assert result["criteria"][0]["checked"] == False
-    assert result["criteria"][1]["checked"] == True
-    assert "context" in result["sections"]
-    print("PASS: test_basic_parsing")
-
-
-def test_numbered_criteria():
-    body = """## Acceptance Criteria
-
-1. First item
-2. Second item
-3. Third item
-"""
-    result = parse_issue_body(body)
-    assert len(result["criteria"]) == 3
-    assert result["criteria"][0]["text"] == "First item"
-    print("PASS: test_numbered_criteria")
-
-
-def test_epic_ref_from_body():
-    body = "Closes #123\n\nSome description."
-    result = parse_issue_body(body)
-    assert result["epic_ref"] == 123
-    print("PASS: test_epic_ref_from_body")
-
-
-def test_empty_body():
-    result = parse_issue_body("")
-    assert result["criteria"] == []
-    assert result["context"] == ""
-    assert result["sections"] == {}
-    print("PASS: test_empty_body")
-
-
-def test_no_sections():
-    body = "Just a plain issue body with no headings."
-    result = parse_issue_body(body)
-    assert result["context"] == "Just a plain issue body with no headings."
-    print("PASS: test_no_sections")
-
-
-def test_multiple_sections():
-    body = """## Problem
-
-Something is broken.
-
-## Fix
-
-Do this instead.
-
-## Notes
-
-Additional info.
-"""
-    result = parse_issue_body(body)
-    assert "problem" in result["sections"]
-    assert "fix" in result["sections"]
-    assert "notes" in result["sections"]
-    assert "Something is broken" in result["sections"]["problem"]
-    print("PASS: test_multiple_sections")
-
-
-def run_all():
-    test_basic_parsing()
-    test_numbered_criteria()
-    test_epic_ref_from_body()
-    test_empty_body()
-    test_no_sections()
-    test_multiple_sections()
-    print("\nAll 6 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()

scripts/test_knowledge_staleness.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
+
+import json
+import os
+import sys
+import tempfile
+
+sys.path.insert(0, os.path.dirname(__file__) or ".")
+import importlib.util
+spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+check_staleness = mod.check_staleness
+fix_hashes = mod.fix_hashes
+compute_file_hash = mod.compute_file_hash
+
+
+def test_fresh_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("print('hello')")
+        h = compute_file_hash(src)
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "fresh"
+        print("PASS: test_fresh_entry")
+
+
+def test_stale_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("original content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
+        # Now change the source
+        with open(src, "w") as f:
+            f.write("modified content")
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "stale"
+        print("PASS: test_stale_entry")
+
+
+def test_missing_source():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "missing_source"
+        print("PASS: test_missing_source")
+
+
+def test_no_hash():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_hash"
+        assert results[0]["current_hash"].startswith("sha256:")
+        print("PASS: test_no_hash")
+
+
+def test_no_source_field():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "orphan"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_source"
+        print("PASS: test_no_source_field")
+
+
+def test_fix_hashes():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content for hashing")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
+        fixed = fix_hashes(idx, tmpdir)
+        assert fixed == 1
+        # Verify hash was added
+        with open(idx) as f:
+            data = json.load(f)
+        assert data["facts"][0]["source_hash"].startswith("sha256:")
+        print("PASS: test_fix_hashes")
+
+
+def test_empty_index():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": []}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results == []
+        print("PASS: test_empty_index")
+
+
+def test_compute_hash_nonexistent():
+    h = compute_file_hash("/nonexistent/path/file.py")
+    assert h is None
+    print("PASS: test_compute_hash_nonexistent")
+
+
+def run_all():
+    test_fresh_entry()
+    test_stale_entry()
+    test_missing_source()
+    test_no_hash()
+    test_no_source_field()
+    test_fix_hashes()
+    test_empty_index()
+    test_compute_hash_nonexistent()
+    print("\nAll 8 tests passed!")
+
+
+if __name__ == "__main__":
+    run_all()

tests/test_knowledge_gap_identifier.py

@@ -0,0 +1,141 @@
+"""Tests for knowledge_gap_identifier module."""
+
+import sys
+import os
+import tempfile
+import shutil
+from pathlib import Path
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'scripts'))
+
+from knowledge_gap_identifier import KnowledgeGapIdentifier, GapType, GapSeverity
+
+
+def _make_repo(tmpdir, structure):
+    """Create a test repo from a dict of {path: content}."""
+    for rel_path, content in structure.items():
+        p = Path(tmpdir) / rel_path
+        p.parent.mkdir(parents=True, exist_ok=True)
+        p.write_text(content)
+
+
+def test_undocumented_symbol():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/calculator.py": "def add(a, b):\n    return a + b\n",
+            "README.md": "# Calculator\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        undocumented = [g for g in report.gaps if g.gap_type == GapType.UNDOCUMENTED]
+        assert any(g.name == "add" for g in undocumented), "add should be undocumented"
+
+
+def test_documented_symbol_no_gap():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/calculator.py": "def add(a, b):\n    return a + b\n",
+            "README.md": "# Calculator\nUse `add()` to add numbers.\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        undocumented = [g for g in report.gaps
+                       if g.gap_type == GapType.UNDOCUMENTED and g.name == "add"]
+        assert len(undocumented) == 0, "add is documented, should not be flagged"
+
+
+def test_untested_module():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/calculator.py": "def add(a, b):\n    return a + b\n",
+            "src/helper.py": "def format(x):\n    return str(x)\n",
+            "tests/test_calculator.py": "from src.calculator import add\nassert add(1,2) == 3\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        untested = [g for g in report.gaps if g.gap_type == GapType.UNTESTED]
+        assert any("helper" in g.name for g in untested), "helper should be untested"
+
+
+def test_tested_module_no_gap():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/calculator.py": "def add(a, b):\n    return a + b\n",
+            "tests/test_calculator.py": "def test_add():\n    assert True\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        untested = [g for g in report.gaps
+                    if g.gap_type == GapType.UNTESTED and "calculator" in g.name]
+        assert len(untested) == 0, "calculator has tests, should not be flagged"
+
+
+def test_missing_implementation():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/app.py": "def run():\n    pass\n",
+            "docs/api.md": "# API\nUse `NonExistentClass` to do things.\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        missing = [g for g in report.gaps if g.gap_type == GapType.MISSING_IMPLEMENTATION]
+        assert any(g.name == "NonExistentClass" for g in missing)
+
+
+def test_private_symbols_skipped():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/app.py": "def _internal():\n    pass\ndef public():\n    pass\n",
+            "README.md": "# App\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        undocumented_names = [g.name for g in report.gaps if g.gap_type == GapType.UNDOCUMENTED]
+        assert "_internal" not in undocumented_names, "Private symbols should be skipped"
+        assert "public" in undocumented_names
+
+
+def test_empty_repo():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        assert len(report.gaps) == 0
+
+
+def test_invalid_path():
+    report = KnowledgeGapIdentifier().analyze("/nonexistent/path/xyz")
+    assert len(report.gaps) == 1
+    assert report.gaps[0].severity == GapSeverity.ERROR
+
+
+def test_report_summary():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/app.py": "class MyService:\n    def handle(self):\n        pass\n",
+            "README.md": "# App\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        summary = report.summary()
+        assert "UNDOCUMENTED" in summary
+        assert "MyService" in summary
+
+
+def test_report_to_dict():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        _make_repo(tmpdir, {
+            "src/app.py": "def hello():\n    pass\n",
+            "README.md": "# App\n",
+        })
+        report = KnowledgeGapIdentifier().analyze(tmpdir)
+        d = report.to_dict()
+        assert "total_gaps" in d
+        assert "gaps" in d
+        assert isinstance(d["gaps"], list)
+        assert d["total_gaps"] > 0
+
+
+if __name__ == "__main__":
+    test_undocumented_symbol()
+    test_documented_symbol_no_gap()
+    test_untested_module()
+    test_tested_module_no_gap()
+    test_missing_implementation()
+    test_private_symbols_skipped()
+    test_empty_repo()
+    test_invalid_path()
+    test_report_summary()
+    test_report_to_dict()
+    print("All 10 tests passed.")