fix: add directory exclusions for scan performance (#170)

Analyzes cron jobs, docs, scripts, session transcripts, and shell history to find manual processes that could be automated.

Outputs ranked proposals with confidence scores and impact ratings.

scripts/automation_opportunity_finder.py

@@ -0,0 +1,554 @@
+#!/usr/bin/env python3
+"""
+Automation Opportunity Finder — Scan fleet for manual processes that could be automated.
+
+Analyzes:
+1. Cron jobs — finds manual steps between scheduled tasks
+2. Documentation — extracts TODO/FIXME/manual-step patterns
+3. Scripts — detects repeated command sequences
+4. Session transcripts — finds repeated tool-call patterns
+
+Usage:
+    python3 scripts/automation_opportunity_finder.py --hermes-home ~/.hermes
+    python3 scripts/automation_opportunity_finder.py --hermes-home ~/.hermes --json
+    python3 scripts/automation_opportunity_finder.py --hermes-home ~/.hermes --output proposals.json
+"""
+
+import argparse
+import json
+import os
+import re
+import sys
+from collections import Counter, defaultdict
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+
+# ---------------------------------------------------------------------------
+# Patterns that signal manual work
+# ---------------------------------------------------------------------------
+
+MANUAL_STEP_PATTERNS = [
+    # Explicit manual markers
+    (r"(?i)\bTODO[:\s]", "todo"),
+    (r"(?i)\bFIXME[:\s]", "fixme"),
+    (r"(?i)\bMANUAL[:\s]", "manual_step"),
+    (r"(?i)\bHACK[:\s]", "hack"),
+    (r"(?i)\bWORKAROUND[:\s]", "workaround"),
+    # Step-by-step instructions in docs
+    (r"(?i)^(\d+)[.\)]\s+(run|execute|ssh|scp|curl|cd|make|docker|ansible|git)", "sequential_step"),
+    # Explicitly manual operations
+    (r"(?i)\bmanually\b", "manual_keyword"),
+    (r"(?i)\bby hand\b", "manual_keyword"),
+    (r"(?i)\bdon\'?t forget to\b", "manual_keyword"),
+    (r"(?i)\bremember to\b", "manual_keyword"),
+    (r"(?i)\bmake sure to\b", "manual_keyword"),
+]
+
+# Shell commands that appear frequently in runbooks — signal automatable workflows
+SHELL_COMMAND_PATTERNS = [
+    "ssh ", "scp ", "rsync ", "curl ", "wget ",
+    "docker ", "docker-compose ", "kubectl ",
+    "ansible-playbook ", "terraform ", "systemctl ",
+    "systemctl restart", "systemctl status",
+    "git push", "git pull", "git merge", "git checkout",
+    "pip install", "npm install", "cargo build",
+]
+
+# Directories to skip during scans — large/uninteresting trees
+EXCLUDE_DIRS = frozenset({
+    "node_modules", "venv", ".venv", "__pycache__", ".git",
+    "site-packages", "dist", "build", ".tox", ".mypy_cache",
+    ".pytest_cache", "coverage", ".next", "vendor",
+    "skills",  # hermes skills dir is huge
+    "audio_cache", "skins", "profiles",
+})
+
+# Session tool calls that appear repeatedly — candidates for workflow automation
+TOOL_SEQUENCE_MIN_OCCURRENCES = 3
+
+
+# ---------------------------------------------------------------------------
+# Analyzers
+# ---------------------------------------------------------------------------
+
+def analyze_cron_jobs(hermes_home: str) -> List[Dict[str, Any]]:
+    """Analyze cron job definitions for automation gaps."""
+    proposals = []
+    cron_dir = Path(hermes_home) / "cron"
+    jobs_file = cron_dir / "jobs.json"
+
+    if not jobs_file.exists():
+        # Try YAML format
+        for ext in (".yaml", ".yml"):
+            alt = cron_dir / f"jobs{ext}"
+            if alt.exists():
+                jobs_file = alt
+                break
+
+    if not jobs_file.exists():
+        return proposals
+
+    try:
+        if jobs_file.suffix == ".json":
+            with open(jobs_file) as f:
+                jobs = json.load(f)
+        else:
+            try:
+                import yaml
+                with open(jobs_file) as f:
+                    jobs = yaml.safe_load(f)
+            except ImportError:
+                return proposals
+    except (json.JSONDecodeError, Exception):
+        return proposals
+
+    if not isinstance(jobs, list):
+        return proposals
+
+    # Look for disabled jobs (someone turned them off — might need a different approach)
+    disabled = [j for j in jobs if not j.get("enabled", True)]
+    if disabled:
+        names = [j.get("name", j.get("id", "?")) for j in disabled[:5]]
+        proposals.append({
+            "category": "cron_disabled",
+            "title": f"{len(disabled)} disabled cron job(s) may need automation rework",
+            "description": f"These jobs were disabled: {', '.join(names)}. Investigate why and whether a different automation approach is needed.",
+            "confidence": 0.7,
+            "impact": "medium",
+            "sources": [str(jobs_file)],
+        })
+
+    # Look for jobs with high error counts
+    error_jobs = [j for j in jobs if j.get("last_status") == "error"]
+    if error_jobs:
+        names = [j.get("name", j.get("id", "?")) for j in error_jobs[:5]]
+        proposals.append({
+            "category": "cron_errors",
+            "title": f"{len(error_jobs)} cron job(s) failing — may need automation rework",
+            "description": f"Jobs with errors: {', '.join(names)}. Failure patterns suggest missing dependencies or fragile automation.",
+            "confidence": 0.8,
+            "impact": "high",
+            "sources": [str(jobs_file)],
+        })
+
+    # Look for jobs with delivery errors (platform issues)
+    delivery_errors = [j for j in jobs if j.get("last_delivery_error")]
+    if delivery_errors:
+        proposals.append({
+            "category": "cron_delivery",
+            "title": f"{len(delivery_errors)} cron job(s) have delivery failures",
+            "description": "Delivery failures suggest missing retry logic or platform integration gaps.",
+            "confidence": 0.75,
+            "impact": "medium",
+            "sources": [str(jobs_file)],
+        })
+
+    # Look for jobs on short intervals that could be event-driven
+    for job in jobs:
+        schedule = job.get("schedule", "")
+        # Check for very frequent schedules (every minute, every 5 min)
+        if isinstance(schedule, str) and re.match(r"^\*\/([1-5])\s", schedule):
+            proposals.append({
+                "category": "cron_frequency",
+                "title": f"Job '{job.get('name', job.get('id', '?'))}' runs every {schedule.split()[0]} — consider event-driven",
+                "description": f"High-frequency cron ({schedule}) may be better as event-driven or daemon.",
+                "confidence": 0.6,
+                "impact": "low",
+                "sources": [str(jobs_file)],
+            })
+
+    return proposals
+
+
+def analyze_documents(root_dirs: List[str]) -> List[Dict[str, Any]]:
+    """Scan documentation for manual step patterns."""
+    proposals = []
+    doc_extensions = {".md", ".txt", ".rst", ".adoc"}
+    findings_by_category = defaultdict(list)
+
+    for root_dir in root_dirs:
+        root = Path(root_dir)
+        if not root.exists():
+            continue
+
+        for path in root.rglob("*"):
+            if path.is_dir():
+                continue
+            if path.suffix not in doc_extensions:
+                continue
+            # Skip excluded dirs and hidden dirs
+            parts = path.relative_to(root).parts if root in path.parents or root == path.parent else path.parts
+            if any(p.startswith(".") or p in EXCLUDE_DIRS for p in parts):
+                continue
+            if len(parts) > 8:
+                continue
+
+            try:
+                content = path.read_text(errors="replace")
+            except (PermissionError, OSError):
+                continue
+
+            lines = content.split("\n")
+            for i, line in enumerate(lines):
+                stripped = line.strip()
+                if not stripped:
+                    continue
+
+                for pattern, category in MANUAL_STEP_PATTERNS:
+                    if re.search(pattern, stripped):
+                        findings_by_category[category].append({
+                            "file": str(path),
+                            "line": i + 1,
+                            "text": stripped[:200],
+                        })
+
+    # Generate proposals from findings
+    for category, findings in findings_by_category.items():
+        if len(findings) < 2:
+            continue
+
+        file_count = len(set(f["file"] for f in findings))
+        proposals.append({
+            "category": f"manual_{category}",
+            "title": f"{len(findings)} '{category}' markers across {file_count} doc(s)",
+            "description": f"Found in: {', '.join(set(Path(f['file']).name for f in findings[:5]))}",
+            "confidence": 0.65,
+            "impact": "medium",
+            "sources": list(set(f["file"] for f in findings[:10])),
+            "details": findings[:5],  # sample
+        })
+
+    return proposals
+
+
+def analyze_scripts(root_dirs: List[str]) -> List[Dict[str, Any]]:
+    """Detect repeated command sequences in scripts."""
+    proposals = []
+    script_extensions = {".py", ".sh", ".bash", ".zsh"}
+    command_counter = Counter()
+    command_locations = defaultdict(list)
+
+    for root_dir in root_dirs:
+        root = Path(root_dir)
+        if not root.exists():
+            continue
+
+        for path in root.rglob("*"):
+            if path.is_dir():
+                continue
+            if path.suffix not in script_extensions:
+                continue
+            parts = path.relative_to(root).parts if root in path.parents or root == path.parent else path.parts
+            if any(p.startswith(".") or p in EXCLUDE_DIRS for p in parts):
+                continue
+            if len(parts) > 8:
+                continue
+
+            try:
+                content = path.read_text(errors="replace")
+            except (PermissionError, OSError):
+                continue
+
+            lines = content.split("\n")
+            for i, line in enumerate(lines):
+                stripped = line.strip()
+                if not stripped or stripped.startswith("#"):
+                    continue
+
+                for cmd_prefix in SHELL_COMMAND_PATTERNS:
+                    if cmd_prefix in stripped:
+                        # Normalize the command
+                        normalized = re.sub(r"\s+", " ", stripped)[:120]
+                        command_counter[normalized] += 1
+                        command_locations[normalized].append(f"{path}:{i+1}")
+
+    # Proposals for commands appearing 3+ times
+    for cmd, count in command_counter.most_common(20):
+        if count < 3:
+            break
+        locs = command_locations[cmd]
+        file_count = len(set(loc.split(":")[0] for loc in locs))
+        proposals.append({
+            "category": "repeated_command",
+            "title": f"Command repeated {count}x across {file_count} file(s): {cmd[:80]}",
+            "description": f"Locations: {', '.join(locs[:3])}",
+            "confidence": min(0.5 + (count * 0.1), 0.95),
+            "impact": "medium",
+            "sources": list(set(loc.split(":")[0] for loc in locs)),
+        })
+
+    return proposals
+
+
+def analyze_session_transcripts(session_dirs: List[str]) -> List[Dict[str, Any]]:
+    """Find repeated tool-call patterns in session transcripts."""
+    proposals = []
+    tool_sequence_counter = Counter()
+    tool_sequence_examples = {}
+
+    for session_dir in session_dirs:
+        session_path = Path(session_dir)
+        if not session_path.exists():
+            continue
+
+        for path in session_path.rglob("*.jsonl"):
+            try:
+                content = path.read_text(errors="replace")
+            except (PermissionError, OSError):
+                continue
+
+            # Extract tool calls in sequence
+            tool_sequence = []
+            for line in content.split("\n"):
+                line = line.strip()
+                if not line:
+                    continue
+                try:
+                    msg = json.loads(line)
+                except json.JSONDecodeError:
+                    continue
+
+                # Look for tool calls in assistant messages
+                if msg.get("role") == "assistant" and msg.get("tool_calls"):
+                    for tc in msg["tool_calls"]:
+                        func_name = tc.get("function", {}).get("name", "?")
+                        tool_sequence.append(func_name)
+
+            # Find 2-call sequences
+            for i in range(len(tool_sequence) - 1):
+                seq = (tool_sequence[i], tool_sequence[i + 1])
+                tool_sequence_counter[seq] += 1
+                if seq not in tool_sequence_examples:
+                    tool_sequence_examples[seq] = str(path.name)
+
+            # Find 3-call sequences
+            for i in range(len(tool_sequence) - 2):
+                seq = (tool_sequence[i], tool_sequence[i + 1], tool_sequence[i + 2])
+                tool_sequence_counter[seq] += 1
+                if seq not in tool_sequence_examples:
+                    tool_sequence_examples[seq] = str(path.name)
+
+    # Generate proposals for frequently repeated sequences
+    for seq, count in tool_sequence_counter.most_common(20):
+        if count < TOOL_SEQUENCE_MIN_OCCURRENCES:
+            break
+        seq_str = " -> ".join(seq)
+        proposals.append({
+            "category": "tool_sequence",
+            "title": f"Tool sequence '{seq_str}' repeated {count} times",
+            "description": f"Consider creating a workflow/skill that automates this sequence.",
+            "confidence": min(0.5 + (count * 0.05), 0.9),
+            "impact": "medium",
+            "sources": [tool_sequence_examples.get(seq, "unknown")],
+        })
+
+    return proposals
+
+
+def analyze_shell_history(root_dirs: List[str]) -> List[Dict[str, Any]]:
+    """Find repeated shell commands from history files."""
+    proposals = []
+    command_counter = Counter()
+
+    for root_dir in root_dirs:
+        root = Path(root_dir)
+        history_files = []
+
+        # Look for shell history files
+        for name in (".bash_history", ".zsh_history", ".python_history"):
+            p = root / name
+            if p.exists():
+                history_files.append(p)
+
+        # Also check in hermes home
+        for p in root.glob("**/*history*"):
+            if p.is_file() and p.suffix in ("", ".txt", ".log"):
+                history_files.append(p)
+
+        for hf in history_files:
+            try:
+                content = hf.read_text(errors="replace")
+            except (PermissionError, OSError):
+                continue
+
+            for line in content.split("\n"):
+                stripped = line.strip()
+                # ZSH history format: ": 1234567890:0;command"
+                stripped = re.sub(r"^:\s*\d+:\d+;", "", stripped)
+                if not stripped or len(stripped) < 5:
+                    continue
+                # Skip trivial commands
+                if stripped in ("ls", "cd", "pwd", "clear", "exit"):
+                    continue
+                command_counter[stripped] += 1
+
+    for cmd, count in command_counter.most_common(10):
+        if count < 5:
+            break
+        proposals.append({
+            "category": "shell_repetition",
+            "title": f"Shell command run {count}+ times: {cmd[:80]}",
+            "description": "Frequently repeated shell command — candidate for alias, function, or script.",
+            "confidence": min(0.4 + (count * 0.05), 0.85),
+            "impact": "low",
+            "sources": ["shell_history"],
+        })
+
+    return proposals
+
+
+# ---------------------------------------------------------------------------
+# Proposal output
+# ---------------------------------------------------------------------------
+
+def deduplicate_proposals(proposals: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """Remove duplicate proposals based on title similarity."""
+    seen_titles = set()
+    unique = []
+    for p in proposals:
+        # Normalize title for dedup
+        key = re.sub(r"\d+", "N", p["title"]).lower()
+        if key not in seen_titles:
+            seen_titles.add(key)
+            unique.append(p)
+    return unique
+
+
+def rank_proposals(proposals: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """Sort proposals by impact * confidence (highest first)."""
+    impact_weight = {"critical": 1.0, "high": 0.8, "medium": 0.5, "low": 0.2}
+    return sorted(
+        proposals,
+        key=lambda p: impact_weight.get(p.get("impact", "low"), 0.2) * p.get("confidence", 0.5),
+        reverse=True,
+    )
+
+
+def format_text_report(proposals: List[Dict[str, Any]]) -> str:
+    """Format proposals as human-readable text."""
+    if not proposals:
+        return "No automation opportunities found."
+
+    lines = [
+        "=" * 70,
+        "  AUTOMATION OPPORTUNITY REPORT",
+        f"  Generated: {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M UTC')}",
+        f"  Proposals: {len(proposals)}",
+        "=" * 70,
+        "",
+    ]
+
+    for i, p in enumerate(proposals, 1):
+        score = p.get("confidence", 0.5) * {"critical": 1.0, "high": 0.8, "medium": 0.5, "low": 0.2}.get(p.get("impact", "low"), 0.2)
+        lines.append(f"[{i}] {p['title']}")
+        lines.append(f"    Category: {p['category']}  |  Impact: {p.get('impact','?')}  |  Confidence: {p.get('confidence',0):.0%}  |  Score: {score:.2f}")
+        lines.append(f"    {p['description']}")
+        if p.get("sources"):
+            lines.append(f"    Sources: {', '.join(p['sources'][:3])}")
+        lines.append("")
+
+    # Summary by category
+    cat_counts = Counter(p["category"] for p in proposals)
+    lines.append("-" * 70)
+    lines.append("Summary by category:")
+    for cat, count in cat_counts.most_common():
+        lines.append(f"  {cat}: {count}")
+
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+def main():
+    parser = argparse.ArgumentParser(description="Find automation opportunities across the fleet")
+    parser.add_argument("--hermes-home", default=os.path.expanduser("~/.hermes"),
+                        help="Path to hermes home directory (default: ~/.hermes)")
+    parser.add_argument("--scan-dirs", nargs="*",
+                        help="Additional directories to scan (default: hermes-home + cwd)")
+    parser.add_argument("--session-dirs", nargs="*",
+                        help="Session transcript directories (default: hermes-home/sessions)")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--output", "-o", help="Write proposals to file")
+    parser.add_argument("--min-confidence", type=float, default=0.3,
+                        help="Minimum confidence threshold (default: 0.3)")
+    parser.add_argument("--categories", nargs="*",
+                        help="Only include these categories (cron, docs, scripts, sessions, shell)")
+    args = parser.parse_args()
+
+    hermes_home = os.path.expanduser(args.hermes_home)
+
+    # Default scan directories
+    scan_dirs = [hermes_home, "."]
+    if args.scan_dirs:
+        scan_dirs.extend(args.scan_dirs)
+
+    session_dirs = [os.path.join(hermes_home, "sessions")]
+    if args.session_dirs:
+        session_dirs.extend(args.session_dirs)
+
+    # Also check common session locations
+    for subdir in ("transcripts", "session-db"):
+        p = os.path.join(hermes_home, subdir)
+        if os.path.isdir(p):
+            session_dirs.append(p)
+
+    categories = set(args.categories) if args.categories else {"cron", "docs", "scripts", "sessions", "shell"}
+
+    # Run analyzers
+    all_proposals = []
+
+    if "cron" in categories:
+        all_proposals.extend(analyze_cron_jobs(hermes_home))
+
+    if "docs" in categories:
+        all_proposals.extend(analyze_documents(scan_dirs))
+
+    if "scripts" in categories:
+        all_proposals.extend(analyze_scripts(scan_dirs))
+
+    if "sessions" in categories:
+        all_proposals.extend(analyze_session_transcripts(session_dirs))
+
+    if "shell" in categories:
+        all_proposals.extend(analyze_shell_history(scan_dirs))
+
+    # Deduplicate and rank
+    all_proposals = deduplicate_proposals(all_proposals)
+    all_proposals = rank_proposals(all_proposals)
+
+    # Filter by confidence
+    all_proposals = [p for p in all_proposals if p.get("confidence", 0) >= args.min_confidence]
+
+    # Output
+    output = {
+        "generated_at": datetime.now(timezone.utc).isoformat(),
+        "hermes_home": hermes_home,
+        "scan_dirs": scan_dirs,
+        "total_proposals": len(all_proposals),
+        "proposals": all_proposals,
+    }
+
+    if args.json:
+        result = json.dumps(output, indent=2)
+    else:
+        result = format_text_report(all_proposals)
+
+    if args.output:
+        with open(args.output, "w") as f:
+            if args.json:
+                json.dump(output, f, indent=2)
+            else:
+                f.write(result)
+        print(f"Written to {args.output}", file=sys.stderr)
+    else:
+        print(result)
+
+    return 0 if all_proposals else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/gitea_issue_parser.py

@@ -1,162 +0,0 @@
-#!/usr/bin/env python3
-"""
-Gitea Issue Body Parser
-
-Extracts structured data from Gitea issue markdown bodies:
-- Title
-- Context section
-- Acceptance criteria (checkboxes)
-- Labels
-- Epic/parent references
-
-Usage:
-  python3 scripts/gitea_issue_parser.py <issue_body.txt
-  python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123
-  echo "issue body" | python3 scripts/gitea_issue_parser.py --stdin
-
-Output: JSON with {title, context, criteria[], labels[], epic_ref}
-"""
-
-import argparse
-import json
-import re
-import sys
-from typing import Optional
-
-
-def parse_issue_body(body: str, title: str = "", labels: list = None) -> dict:
-    """Parse a Gitea issue body into structured JSON."""
-    result = {
-        "title": title,
-        "context": "",
-        "criteria": [],
-        "labels": labels or [],
-        "epic_ref": None,
-        "sections": {},
-    }
-
-    if not body:
-        return result
-
-    # Extract epic/parent reference from title or body
-    epic_pattern = r"#(\d+)"
-    title_refs = re.findall(epic_pattern, title)
-    body_refs = re.findall(epic_pattern, body[:200])  # Check early body refs
-
-    # Look for "Closes #N" or "Part of #N" or "Epic: #N"
-    close_match = re.search(r"(?:Closes?|Fixes?|Resolves?)\s+#(\d+)", body, re.IGNORECASE)
-    part_match = re.search(r"(?:Part of|Epic|Parent|Blocks?)\s+#(\d+)", body, re.IGNORECASE)
-
-    if close_match:
-        result["epic_ref"] = f"#{close_match.group(1)}"
-    elif part_match:
-        result["epic_ref"] = f"#{part_match.group(1)}"
-    elif title_refs:
-        result["epic_ref"] = f"#{title_refs[0]}"
-    elif body_refs:
-        result["epic_ref"] = f"#{body_refs[0]}"
-
-    # Split into sections by ## headers
-    section_pattern = r"^##\s+(.+)$"
-    lines = body.split("\n")
-    current_section = None
-    current_content = []
-
-    for line in lines:
-        header_match = re.match(section_pattern, line)
-        if header_match:
-            # Save previous section
-            if current_section:
-                result["sections"][current_section] = "\n".join(current_content).strip()
-            current_section = header_match.group(1).strip().lower()
-            current_content = []
-        else:
-            current_content.append(line)
-
-    # Save last section
-    if current_section:
-        result["sections"][current_section] = "\n".join(current_content).strip()
-
-    # Extract context
-    for key in ["context", "background", "description", "problem"]:
-        if key in result["sections"]:
-            result["context"] = result["sections"][key]
-            break
-
-    # Extract acceptance criteria (checkboxes)
-    criteria_section = None
-    for key in ["acceptance criteria", "acceptance_criteria", "criteria", "requirements", "definition of done"]:
-        if key in result["sections"]:
-            criteria_section = result["sections"][key]
-            break
-
-    if criteria_section:
-        checkbox_pattern = r"-\s*\[[ xX]?\]\s*(.+)"
-        for match in re.finditer(checkbox_pattern, criteria_section):
-            result["criteria"].append(match.group(1).strip())
-
-        # Also try plain numbered/bulleted lists if no checkboxes found
-        if not result["criteria"]:
-            list_pattern = r"^\s*(?:\d+\.|-|\*)\s+(.+)"
-            for match in re.finditer(list_pattern, criteria_section, re.MULTILINE):
-                result["criteria"].append(match.group(1).strip())
-
-    # If no sectioned criteria found, scan whole body for checkboxes
-    if not result["criteria"]:
-        for match in re.finditer(r"-\s*\[[ xX]?\]\s*(.+)", body):
-            result["criteria"].append(match.group(1).strip())
-
-    return result
-
-
-def parse_from_url(api_url: str, token: str = None) -> dict:
-    """Parse an issue from a Gitea API URL."""
-    import urllib.request
-
-    headers = {}
-    if token:
-        headers["Authorization"] = f"token {token}"
-
-    req = urllib.request.Request(api_url, headers=headers)
-    resp = json.loads(urllib.request.urlopen(req, timeout=30).read())
-
-    title = resp.get("title", "")
-    body = resp.get("body", "")
-    labels = [l["name"] for l in resp.get("labels", [])]
-
-    return parse_issue_body(body, title, labels)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Parse Gitea issue body into structured JSON")
-    parser.add_argument("input", nargs="?", help="Issue body file (or - for stdin)")
-    parser.add_argument("--url", help="Gitea API URL for the issue")
-    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
-    parser.add_argument("--token", help="Gitea API token (or set GITEA_TOKEN env var)")
-    parser.add_argument("--title", default="", help="Issue title (for epic ref extraction)")
-    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()
-
-    import os
-    token = args.token or os.environ.get("GITEA_TOKEN")
-
-    if args.url:
-        result = parse_from_url(args.url, token)
-    elif args.stdin or (args.input and args.input == "-"):
-        body = sys.stdin.read()
-        result = parse_issue_body(body, args.title, args.labels)
-    elif args.input:
-        with open(args.input) 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_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_automation_opportunity_finder.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+"""Tests for scripts/automation_opportunity_finder.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(
+    "aof",
+    os.path.join(os.path.dirname(__file__) or ".", "automation_opportunity_finder.py"),
+)
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+
+
+def test_analyze_cron_jobs_no_file():
+    """Returns empty list when no cron jobs file exists."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        result = mod.analyze_cron_jobs(tmpdir)
+        assert result == []
+        print("PASS: test_analyze_cron_jobs_no_file")
+
+
+def test_analyze_cron_jobs_disabled():
+    """Detects disabled cron jobs."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        cron_dir = os.path.join(tmpdir, "cron")
+        os.makedirs(cron_dir)
+        jobs = [
+            {"id": "j1", "name": "backup", "enabled": False, "schedule": "0 * * * *"},
+            {"id": "j2", "name": "health", "enabled": True, "schedule": "*/5 * * * *"},
+        ]
+        with open(os.path.join(cron_dir, "jobs.json"), "w") as f:
+            json.dump(jobs, f)
+        result = mod.analyze_cron_jobs(tmpdir)
+        assert any(p["category"] == "cron_disabled" for p in result)
+        print("PASS: test_analyze_cron_jobs_disabled")
+
+
+def test_analyze_cron_jobs_errors():
+    """Detects cron jobs with error status."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        cron_dir = os.path.join(tmpdir, "cron")
+        os.makedirs(cron_dir)
+        jobs = [
+            {"id": "j1", "name": "broken", "enabled": True, "last_status": "error", "schedule": "0 * * * *"},
+        ]
+        with open(os.path.join(cron_dir, "jobs.json"), "w") as f:
+            json.dump(jobs, f)
+        result = mod.analyze_cron_jobs(tmpdir)
+        assert any(p["category"] == "cron_errors" for p in result)
+        print("PASS: test_analyze_cron_jobs_errors")
+
+
+def test_analyze_documents_finds_todos():
+    """Detects TODO markers in documents."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        docs_dir = os.path.join(tmpdir, "docs")
+        os.makedirs(docs_dir)
+        for i in range(3):
+            with open(os.path.join(docs_dir, f"guide{i}.md"), "w") as f:
+                f.write(f"# Guide {i}\n\nTODO: Automate this step\n")
+        result = mod.analyze_documents([tmpdir])
+        assert any(p["category"] == "manual_todo" for p in result)
+        todo_proposals = [p for p in result if p["category"] == "manual_todo"]
+        assert todo_proposals[0]["details"].__len__() == 3
+        print("PASS: test_analyze_documents_finds_todos")
+
+
+def test_analyze_scripts_repeated_commands():
+    """Detects repeated shell commands across scripts."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        scripts_dir = os.path.join(tmpdir, "scripts")
+        os.makedirs(scripts_dir)
+        repeated_cmd = "docker restart myapp"
+        for i in range(4):
+            with open(os.path.join(scripts_dir, f"deploy{i}.sh"), "w") as f:
+                f.write(f"#!/bin/bash\n{repeated_cmd}\n")
+        result = mod.analyze_scripts([tmpdir])
+        assert any(p["category"] == "repeated_command" for p in result)
+        print("PASS: test_analyze_scripts_repeated_commands")
+
+
+def test_analyze_session_transcripts():
+    """Detects repeated tool-call sequences."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        sessions_dir = os.path.join(tmpdir, "sessions")
+        os.makedirs(sessions_dir)
+        for i in range(4):
+            with open(os.path.join(sessions_dir, f"session{i}.jsonl"), "w") as f:
+                f.write(json.dumps({"role": "user", "content": f"task {i}"}) + "\n")
+                f.write(json.dumps({
+                    "role": "assistant",
+                    "content": "working",
+                    "tool_calls": [
+                        {"function": {"name": "read_file"}},
+                        {"function": {"name": "write_file"}},
+                    ]
+                }) + "\n")
+        result = mod.analyze_session_transcripts([sessions_dir])
+        assert any(p["category"] == "tool_sequence" for p in result)
+        seq_proposals = [p for p in result if p["category"] == "tool_sequence"]
+        assert any("read_file" in p["title"] and "write_file" in p["title"] for p in seq_proposals)
+        print("PASS: test_analyze_session_transcripts")
+
+
+def test_deduplicate_proposals():
+    """Deduplicates proposals with similar titles."""
+    proposals = [
+        {"title": "TODO found 3 times", "category": "manual_todo", "confidence": 0.7, "impact": "medium", "description": "x", "sources": []},
+        {"title": "TODO found 3 times", "category": "manual_todo", "confidence": 0.7, "impact": "medium", "description": "x", "sources": []},
+        {"title": "FIXME found 5 times", "category": "manual_fixme", "confidence": 0.8, "impact": "medium", "description": "y", "sources": []},
+    ]
+    result = mod.deduplicate_proposals(proposals)
+    assert len(result) == 2
+    print("PASS: test_deduplicate_proposals")
+
+
+def test_rank_proposals():
+    """Ranks proposals by impact * confidence."""
+    proposals = [
+        {"title": "low", "category": "x", "confidence": 0.9, "impact": "low", "description": "", "sources": []},
+        {"title": "high", "category": "x", "confidence": 0.8, "impact": "high", "description": "", "sources": []},
+        {"title": "med", "category": "x", "confidence": 0.7, "impact": "medium", "description": "", "sources": []},
+    ]
+    result = mod.rank_proposals(proposals)
+    assert result[0]["title"] == "high"
+    assert result[-1]["title"] == "low"
+    print("PASS: test_rank_proposals")
+
+
+if __name__ == "__main__":
+    tests = [v for k, v in globals().items() if k.startswith("test_")]
+    passed = 0
+    failed = 0
+    for t in tests:
+        try:
+            t()
+            passed += 1
+        except Exception as e:
+            print(f"FAIL: {t.__name__}: {e}")
+            failed += 1
+    print(f"\n{passed}/{passed+failed} tests passed")
+    sys.exit(1 if failed else 0)

scripts/test_gitea_issue_parser.py

@@ -1,111 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for gitea_issue_parser."""
-
-import json
-import sys
-import os
-
-sys.path.insert(0, os.path.dirname(__file__))
-from gitea_issue_parser import parse_issue_body
-
-
-def test_basic_structure():
-    body = """## Context
-This is the background.
-
-## Acceptance Criteria
-- [ ] First criterion
-- [x] Second criterion (already done)
-- [ ] Third criterion
-
-## Labels
-`pipeline`, `extraction`
-"""
-    result = parse_issue_body(body, "Test Issue", ["pipeline", "extraction"])
-    assert result["title"] == "Test Issue"
-    assert "background" in result["context"].lower()
-    assert len(result["criteria"]) == 3
-    assert "First criterion" in result["criteria"]
-    assert result["labels"] == ["pipeline", "extraction"]
-    print("PASS: test_basic_structure")
-
-
-def test_epic_ref():
-    body = "Closes #645\n\nSome description."
-    result = parse_issue_body(body, "feat: thing (#688)")
-    assert result["epic_ref"] == "#645"
-    print("PASS: test_epic_ref")
-
-
-def test_epic_ref_from_title():
-    body = "Some description without close ref."
-    result = parse_issue_body(body, "feat: scene descriptions (#645)")
-    assert result["epic_ref"] == "#645"
-    print("PASS: test_epic_ref_from_title")
-
-
-def test_no_checkboxes():
-    body = """## Requirements
-1. First thing
-2. Second thing
-3. Third thing
-"""
-    result = parse_issue_body(body)
-    assert len(result["criteria"]) == 3
-    print("PASS: test_no_checkboxes")
-
-
-def test_empty_body():
-    result = parse_issue_body("", "Empty Issue")
-    assert result["title"] == "Empty Issue"
-    assert result["criteria"] == []
-    assert result["context"] == ""
-    print("PASS: test_empty_body")
-
-
-def test_real_issue_format():
-    body = """Closes #681
-
-## Changes
-
-Add `#!/usr/bin/env python3` shebang to 6 Python scripts.
-
-## Verification
-
-All 6 files confirmed missing shebangs before fix.
-
-## Impact
-
-Scripts can now be executed directly.
-"""
-    result = parse_issue_body(body, "fix: add python3 shebangs (#685)")
-    assert result["epic_ref"] == "#681"
-    assert "shebang" in result["context"].lower()
-    print("PASS: test_real_issue_format")
-
-
-def test_all_sections_captured():
-    body = """## Context
-Background info.
-
-## Acceptance Criteria
-- [ ] Do thing
-
-## Labels
-`test`
-"""
-    result = parse_issue_body(body)
-    assert "context" in result["sections"]
-    assert "acceptance criteria" in result["sections"]
-    print("PASS: test_all_sections_captured")
-
-
-if __name__ == "__main__":
-    test_basic_structure()
-    test_epic_ref()
-    test_epic_ref_from_title()
-    test_no_checkboxes()
-    test_empty_body()
-    test_real_issue_format()
-    test_all_sections_captured()
-    print("\nAll tests passed.")

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()