diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index 08ede3c..d672010 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -22,7 +22,7 @@ {"id":"bd-3c7","title":"Handle edge case: empty or missing ~/projects/ directory","description":"## Overview\nHandle the case where ~/projects/ doesn't exist or is empty gracefully.\n\n## Background\nNot all users will have ~/projects/ configured. The spawn feature should degrade gracefully:\n- Return empty projects list (not error)\n- Dashboard shows helpful message\n- No crashes or confusing errors\n\n## Server Side\nload_projects_cache() already handles this:\n```python\nexcept OSError:\n _projects_cache = []\n```\n\n## Dashboard Side\nSpawnModal should handle empty projects list:\n1. Projects dropdown is empty\n2. Show message: 'No projects found in ~/projects/'\n3. Spawn button remains disabled (no selection possible)\n\n## Implementation\nIn SpawnModal.js, add condition:\n```javascript\n${projects.length === 0 && !loadingProjects && html`\n

\n No projects found in ~/projects/\n

\n`}\n```\n\n## Edge Cases\n1. ~/projects/ doesn't exist -> empty list\n2. ~/projects/ exists but empty -> empty list\n3. ~/projects/ exists, only hidden dirs -> empty list (they're excluded)\n4. ~/projects/ exists with permission error -> empty list (OSError caught)\n\n## Testing\n1. Temporarily rename ~/projects/\n2. Restart server\n3. Open spawn modal on All Projects\n4. Verify helpful message shown\n5. Verify no crash\n6. Restore ~/projects/\n\n## Success Criteria\n- Server doesn't crash without ~/projects/\n- Dashboard shows informative message\n- No confusing error toasts","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-26T21:43:13.655184Z","created_by":"tayloreernisse","updated_at":"2026-02-26T22:08:26.546217Z","closed_at":"2026-02-26T22:08:26.546165Z","close_reason":"Implemented empty projects edge case: server already handled OSError/missing dir gracefully, added empty-state message to SpawnModal, added tests for missing dir + only-hidden-dirs + empty API responses","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3c7","depends_on_id":"bd-15z","type":"blocks","created_at":"2026-02-26T21:43:16.434386Z","created_by":"tayloreernisse"}]} {"id":"bd-3cc","title":"E2E tests for autocomplete workflow","description":"## Overview\nCreate end-to-end test script that validates the complete autocomplete workflow from typing to insertion.\n\n## Background\nThe plan includes a manual testing checklist (lines 462-480). We should automate key workflows to ensure the feature works end-to-end.\n\n## Test Scenarios (from plan's testing checklist)\n\n### Core Flow\n```\n1. Claude session: Type \"/\" -> dropdown appears with Claude skills\n2. Codex session: Type \"$\" -> dropdown appears with Codex skills\n3. Claude session: Type \"$\" -> nothing happens (wrong trigger)\n4. Type \"/com\" -> list filters to skills containing \"com\"\n5. Mid-message: Type \"please run /commit\" -> autocomplete triggers on \"/\"\n6. Arrow keys navigate, Enter selects\n7. Escape dismisses without selection\n8. Click outside dismisses\n9. Selected skill shows as \"{trigger}skill-name \" in input\n10. Verify alphabetical ordering of skills\n11. Verify vertical scroll with many skills\n```\n\n### Edge Cases (from plan section)\n```\n- Session without skills (dropdown shows \"No skills available\")\n- Single skill (still shows dropdown)\n- Very long skill descriptions (CSS truncates with ellipsis - visual check)\n- Multiple triggers in one message (each \"/\" can trigger independently)\n- Backspace over trigger (dismisses autocomplete)\n```\n\n### Multiple Triggers Test (important edge case)\nUser types: \"first /commit then /review-pr finally\"\n- First \"/\" at position 6 can trigger\n- After inserting \"/commit \", cursor at position 14\n- Second \"/\" at position after text can trigger again\n- Verify each trigger works independently\n\n## Implementation Approach\nUse the Playwright MCP tools to:\n1. Navigate to dashboard\n2. Open a session modal\n3. Type trigger character\n4. Verify dropdown appears\n5. Navigate with arrows\n6. Select with Enter\n7. Verify insertion\n\n## Logging Requirements\n- Log each step being performed\n- Log expected vs actual behavior\n- Log timing for performance visibility\n- Log any errors with context\n\n## Test Script Location\ntests/e2e/test_autocomplete.py or similar\n\n## Success Criteria\n- All core scenarios pass\n- Edge cases handled\n- Detailed logging for debugging\n- Can run in CI environment","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-26T20:11:47.556903Z","created_by":"tayloreernisse","updated_at":"2026-02-26T22:04:06.299931Z","closed_at":"2026-02-26T22:04:06.299744Z","close_reason":"Implemented 50 E2E tests (14 server-side Python, 36 client-side JS) covering: /api/skills endpoint, trigger detection, keyboard navigation, skill insertion, alphabetical ordering, cross-agent isolation, edge cases, and full workflow simulation","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3cc","depends_on_id":"bd-3ny","type":"blocks","created_at":"2026-02-26T20:11:50.670698Z","created_by":"tayloreernisse"}]} {"id":"bd-3eu","title":"Implement Codex skill enumeration","description":"## Overview\nImplement _enumerate_codex_skills() method in SkillsMixin to discover skills from both the curated cache and user directory.\n\n## Background\nCodex stores skills in two locations:\n1. **Curated cache**: ~/.codex/vendor_imports/skills-curated-cache.json (pre-installed skills)\n2. **User skills**: ~/.codex/skills/*/ (user-created or installed)\n\nBoth need to be combined for the full skills list.\n\n## Implementation (from plan IMP-1)\n```python\ndef _enumerate_codex_skills(self):\n skills = []\n \n # 1. Curated skills from cache\n cache_file = Path.home() / '.codex/vendor_imports/skills-curated-cache.json'\n if cache_file.exists():\n try:\n data = json.loads(cache_file.read_text())\n for skill in data.get('skills', []):\n skills.append({\n 'name': skill.get('id', skill.get('name', '')),\n 'description': skill.get('shortDescription', skill.get('description', ''))[:100]\n })\n except (json.JSONDecodeError, OSError):\n pass # Continue without curated skills\n \n # 2. User-installed skills\n user_skills_dir = Path.home() / '.codex/skills'\n if user_skills_dir.exists():\n for skill_dir in user_skills_dir.iterdir():\n if skill_dir.is_dir() and not skill_dir.name.startswith('.'):\n skill_md = skill_dir / 'SKILL.md'\n description = ''\n if skill_md.exists():\n try:\n for line in skill_md.read_text().splitlines():\n line = line.strip()\n if line and not line.startswith('#'):\n description = line[:100]\n break\n except OSError:\n pass\n skills.append({\n 'name': skill_dir.name,\n 'description': description or f'User skill: {skill_dir.name}'\n })\n \n return skills\n```\n\n## Key Decisions\n- **Cache file structure**: Expected format {skills: [{id, shortDescription}, ...]}\n- **Fallback for missing fields**: Use 'name' if 'id' missing, 'description' if 'shortDescription' missing\n- **No deduplication**: If curated and user skills share a name, both appear (per Known Limitations)\n- **Error resilience**: JSON parse errors don't prevent user skills from loading\n\n## Out of Scope (per plan)\n- Duplicate skill names are NOT deduplicated\n- Server-side caching of enumeration results\n\n## Success Criteria\n- Returns combined list from cache + user directory\n- Handles missing files/directories gracefully\n- Truncates descriptions to 100 chars\n- JSON parse errors don't crash enumeration","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T20:07:58.579276Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:43:21.057360Z","closed_at":"2026-02-26T21:43:21.057312Z","close_reason":"Implemented _enumerate_codex_skills: reads curated cache + user skills directory, handles JSON errors gracefully","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3eu","depends_on_id":"bd-3q1","type":"blocks","created_at":"2026-02-26T20:08:01.832043Z","created_by":"tayloreernisse"}]} -{"id":"bd-3g8","title":"Slice 3 Integration: Polish and edge cases complete","description":"## Overview\nFinal integration checkpoint verifying all polish and edge case handling.\n\n## Background\nSlice 3 ensures the feature handles edge cases gracefully and provides a polished UX. This bead verifies:\n- Empty projects handling\n- Visual feedback for new agents\n- Special character support\n- Zellij metadata correctness\n- Warning banners\n\n## Verification Checklist\n\n### 1. Empty Projects Directory\n- [ ] Test with empty ~/projects/\n- [ ] Modal shows 'No projects found' message\n- [ ] No crash or confusing error\n\n### 2. Visual Feedback\n- [ ] Spawn an agent\n- [ ] Watch session cards area\n- [ ] New card has highlight animation\n- [ ] Animation fades after ~2s\n\n### 3. Special Characters\n- [ ] Create test project with hyphen: my-test\n- [ ] Spawn agent for it -> success\n- [ ] Create test project with underscore: my_test\n- [ ] Spawn agent for it -> success\n- [ ] Test with path traversal ../etc -> rejected\n\n### 4. Zellij Metadata\n- [ ] Spawn agent\n- [ ] Check session file: jq '.zellij_session' \n- [ ] Should be 'infra'\n- [ ] Check session file: jq '.zellij_pane'\n- [ ] Should be valid pane ID\n\n### 5. Dashboard Response\n- [ ] Spawn agent\n- [ ] Wait for AskUserQuestion\n- [ ] Submit response via dashboard\n- [ ] Response appears in Zellij pane\n\n### 6. Zellij Unavailable Warning\n- [ ] Stop Zellij session (zellij kill-session infra)\n- [ ] Reload dashboard\n- [ ] Warning banner should appear\n- [ ] Banner text clear and actionable\n- [ ] Start Zellij session\n- [ ] Warning banner disappears\n\n### 7. Projects Cache Refresh\n- [ ] Add new project to ~/projects/\n- [ ] POST /api/projects/refresh\n- [ ] New project appears in dropdown\n\n### 8. Background Refresh\n- [ ] Add project without manual refresh\n- [ ] Wait 5 minutes\n- [ ] Project appears in dropdown\n\n## Full Feature Walkthrough\n1. Start Zellij session 'infra'\n2. Start AMC server\n3. Open dashboard\n4. Select project in sidebar\n5. Click '+ New Agent'\n6. Select 'Claude'\n7. Click 'Spawn'\n8. See success toast\n9. See agent appear in Zellij\n10. See agent card in dashboard (possibly with highlight)\n11. Wait for AskUserQuestion\n12. Submit response\n13. Response appears in agent\n\n## Acceptance Criteria Covered\n- AC-15: Agent appears within 10 seconds\n- AC-16, AC-17: Correct Zellij metadata\n- AC-42: Warning banner\n\n## Success Criteria\nComplete feature works end-to-end with all edge cases handled gracefully.","status":"open","priority":1,"issue_type":"task","created_at":"2026-02-26T21:45:39.460751Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:45:45.059903Z","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3g8","depends_on_id":"bd-14p","type":"blocks","created_at":"2026-02-26T21:45:44.875703Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-2cw","type":"blocks","created_at":"2026-02-26T21:45:44.790681Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-30o","type":"blocks","created_at":"2026-02-26T21:45:44.962392Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-3c7","type":"blocks","created_at":"2026-02-26T21:45:44.730490Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-3ke","type":"blocks","created_at":"2026-02-26T21:45:45.059877Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-zgt","type":"blocks","created_at":"2026-02-26T21:45:44.592034Z","created_by":"tayloreernisse"}]} +{"id":"bd-3g8","title":"Slice 3 Integration: Polish and edge cases complete","description":"## Overview\nFinal integration checkpoint verifying all polish and edge case handling.\n\n## Background\nSlice 3 ensures the feature handles edge cases gracefully and provides a polished UX. This bead verifies:\n- Empty projects handling\n- Visual feedback for new agents\n- Special character support\n- Zellij metadata correctness\n- Warning banners\n\n## Verification Checklist\n\n### 1. Empty Projects Directory\n- [ ] Test with empty ~/projects/\n- [ ] Modal shows 'No projects found' message\n- [ ] No crash or confusing error\n\n### 2. Visual Feedback\n- [ ] Spawn an agent\n- [ ] Watch session cards area\n- [ ] New card has highlight animation\n- [ ] Animation fades after ~2s\n\n### 3. Special Characters\n- [ ] Create test project with hyphen: my-test\n- [ ] Spawn agent for it -> success\n- [ ] Create test project with underscore: my_test\n- [ ] Spawn agent for it -> success\n- [ ] Test with path traversal ../etc -> rejected\n\n### 4. Zellij Metadata\n- [ ] Spawn agent\n- [ ] Check session file: jq '.zellij_session' \n- [ ] Should be 'infra'\n- [ ] Check session file: jq '.zellij_pane'\n- [ ] Should be valid pane ID\n\n### 5. Dashboard Response\n- [ ] Spawn agent\n- [ ] Wait for AskUserQuestion\n- [ ] Submit response via dashboard\n- [ ] Response appears in Zellij pane\n\n### 6. Zellij Unavailable Warning\n- [ ] Stop Zellij session (zellij kill-session infra)\n- [ ] Reload dashboard\n- [ ] Warning banner should appear\n- [ ] Banner text clear and actionable\n- [ ] Start Zellij session\n- [ ] Warning banner disappears\n\n### 7. Projects Cache Refresh\n- [ ] Add new project to ~/projects/\n- [ ] POST /api/projects/refresh\n- [ ] New project appears in dropdown\n\n### 8. Background Refresh\n- [ ] Add project without manual refresh\n- [ ] Wait 5 minutes\n- [ ] Project appears in dropdown\n\n## Full Feature Walkthrough\n1. Start Zellij session 'infra'\n2. Start AMC server\n3. Open dashboard\n4. Select project in sidebar\n5. Click '+ New Agent'\n6. Select 'Claude'\n7. Click 'Spawn'\n8. See success toast\n9. See agent appear in Zellij\n10. See agent card in dashboard (possibly with highlight)\n11. Wait for AskUserQuestion\n12. Submit response\n13. Response appears in agent\n\n## Acceptance Criteria Covered\n- AC-15: Agent appears within 10 seconds\n- AC-16, AC-17: Correct Zellij metadata\n- AC-42: Warning banner\n\n## Success Criteria\nComplete feature works end-to-end with all edge cases handled gracefully.","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T21:45:39.460751Z","created_by":"tayloreernisse","updated_at":"2026-02-26T22:18:20.391913Z","closed_at":"2026-02-26T22:18:20.391866Z","close_reason":"All polish and edge cases verified: Empty projects shows friendly message, newlySpawned animation works, path traversal/special chars validated in spawn.py, zellij metadata fully supported, warning banner when Zellij unavailable. Feature complete.","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3g8","depends_on_id":"bd-14p","type":"blocks","created_at":"2026-02-26T21:45:44.875703Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-2cw","type":"blocks","created_at":"2026-02-26T21:45:44.790681Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-30o","type":"blocks","created_at":"2026-02-26T21:45:44.962392Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-3c7","type":"blocks","created_at":"2026-02-26T21:45:44.730490Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-3ke","type":"blocks","created_at":"2026-02-26T21:45:45.059877Z","created_by":"tayloreernisse"},{"issue_id":"bd-3g8","depends_on_id":"bd-zgt","type":"blocks","created_at":"2026-02-26T21:45:44.592034Z","created_by":"tayloreernisse"}]} {"id":"bd-3ke","title":"Dashboard warning banner when Zellij session unavailable","description":"## Overview\nShow warning banner in dashboard when Zellij session 'infra' is unavailable.\n\n## Background\nPer AC-42, the dashboard should warn users when spawning won't work because the Zellij session doesn't exist. This prevents confusion when spawn attempts fail.\n\n## Implementation\n\n### Health Polling\nAdd periodic health check in App.js:\n```javascript\nconst [zelijAvailable, setZelijAvailable] = useState(true);\n\nuseEffect(() => {\n const checkHealth = async () => {\n try {\n const response = await fetch('/api/health');\n const data = await response.json();\n setZelijAvailable(data.zellij_available);\n } catch {\n // Server unreachable - handled elsewhere\n }\n };\n \n checkHealth();\n const interval = setInterval(checkHealth, 30000); // Check every 30s\n return () => clearInterval(interval);\n}, []);\n```\n\n### Warning Banner\nAdd before main content:\n```javascript\n${!zelijAvailable && html`\n
\n Zellij session 'infra' not found.\n Agent spawning is unavailable. Start Zellij with: zellij attach infra\n
\n`}\n```\n\n### Spawn Button State\nOptionally disable spawn button when Zellij unavailable:\n```javascript\n\n + New Agent\n\n```\n\n## Banner Styling\n- bg-attention/20: Light warning background\n- border-attention/50: Warning border\n- text-attention: Warning text color\n- Positioned above main content (not fixed)\n\n## UX Considerations\n1. Banner doesn't block dashboard usage\n2. Clear actionable message with command to fix\n3. Automatically disappears when Zellij available\n4. Doesn't spam with repeated warnings\n\n## Success Criteria\n- Banner appears when Zellij unavailable\n- Banner disappears when Zellij becomes available\n- Spawn button disabled (optional)\n- Clear instructions to fix","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-26T21:44:21.824784Z","created_by":"tayloreernisse","updated_at":"2026-02-26T22:09:20.267822Z","closed_at":"2026-02-26T22:09:20.267777Z","close_reason":"Implemented Zellij unavailable warning banner with health polling, spawn button disable, and actionable fix message","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3ke","depends_on_id":"bd-3v5","type":"blocks","created_at":"2026-02-26T21:44:26.508776Z","created_by":"tayloreernisse"}]} {"id":"bd-3ny","title":"Implement click-outside dismissal","description":"## Overview\nAdd useEffect in SimpleInput.js that dismisses the autocomplete dropdown when clicking outside.\n\n## Background\nAC-9 requires clicking outside to dismiss the dropdown. This is a common UX pattern that requires:\n- Event listener on document\n- Check if click target is inside dropdown or textarea\n- Cleanup on unmount\n\n## Implementation (from plan IMP-10)\n```javascript\nuseEffect(() => {\n if (!showAutocomplete) return;\n \n const handleClickOutside = (e) => {\n if (autocompleteRef.current && !autocompleteRef.current.contains(e.target) &&\n textareaRef.current && !textareaRef.current.contains(e.target)) {\n setShowAutocomplete(false);\n }\n };\n \n document.addEventListener('mousedown', handleClickOutside);\n return () => document.removeEventListener('mousedown', handleClickOutside);\n}, [showAutocomplete]);\n```\n\n## Why mousedown (not click)\n- mousedown fires immediately on press\n- click fires after release (feels sluggish)\n- Standard pattern for dropdown dismissal\n\n## What Counts as 'Inside'\n- Inside autocompleteRef (the dropdown)\n- Inside textareaRef (the input)\n- Both should keep dropdown open\n\n## Cleanup\n- Effect only adds listener when dropdown is visible\n- Cleanup removes listener when:\n - Dropdown closes\n - Component unmounts\n - Dependencies change\n\n## Success Criteria\n- Clicking outside dropdown+textarea dismisses\n- Clicking inside dropdown doesn't dismiss (onClick handles selection)\n- Clicking in textarea doesn't dismiss (keeps typing)\n- Listener cleaned up properly","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T20:10:49.738217Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:54:17.702299Z","closed_at":"2026-02-26T21:54:17.702245Z","close_reason":"Added click-outside dismissal useEffect with mousedown listener","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3ny","depends_on_id":"bd-253","type":"blocks","created_at":"2026-02-26T20:10:52.252341Z","created_by":"tayloreernisse"}]} {"id":"bd-3oo","title":"Add spawn constants to context.py","description":"## Overview\nAdd constants and utilities needed by SpawnMixin to amc_server/context.py.\n\n## Background\nThe spawn feature requires several shared constants and utilities that belong in context.py alongside existing path constants like SESSIONS_DIR. These enable:\n- Locating the projects directory for agent spawning\n- Targeting the correct Zellij session\n- Serializing concurrent spawn requests to prevent race conditions\n- Per-project rate limiting to prevent spam\n- Auth token generation for spawn endpoint security\n\n## Implementation (IMP-0)\nAdd after existing path constants:\n\n```python\nimport secrets\nimport threading\n\n# Projects directory for spawning agents\nPROJECTS_DIR = Path.home() / 'projects'\n\n# Default Zellij session for spawning\nZELLIJ_SESSION = 'infra'\n\n# Lock for serializing spawn operations (prevents Zellij race conditions)\n_spawn_lock = threading.Lock()\n\n# Rate limiting: track last spawn time per project (prevents spam)\n_spawn_timestamps: dict[str, float] = {}\nSPAWN_COOLDOWN_SEC = 10.0\n\n# Auth token for spawn endpoint (AC-37, AC-38)\n# Generated on server start, injected into dashboard HTML\n_auth_token: str = ''\n\n\ndef generate_auth_token():\n \"\"\"Generate a one-time auth token for this server instance.\"\"\"\n global _auth_token\n _auth_token = secrets.token_urlsafe(32)\n return _auth_token\n\n\ndef validate_auth_token(request_token: str) -> bool:\n \"\"\"Validate the Authorization header token.\"\"\"\n return request_token == f'Bearer {_auth_token}'\n\n\ndef start_projects_watcher():\n \"\"\"Start background thread to refresh projects cache every 5 minutes (AC-40).\"\"\"\n import logging\n from amc_server.mixins.spawn import load_projects_cache\n\n def _watch_loop():\n import time\n while True:\n try:\n time.sleep(300) # 5 minutes\n load_projects_cache()\n except Exception:\n logging.exception('Projects cache refresh failed')\n\n thread = threading.Thread(target=_watch_loop, daemon=True)\n thread.start()\n```\n\n## Design Decisions\n- **_spawn_lock**: Process-local threading.Lock is sufficient because AMC is single-process by design. Multi-worker would need file-based locking.\n- **_spawn_timestamps dict**: In-memory dict resets on restart, which is acceptable for rate limiting (no persistence needed).\n- **SPAWN_COOLDOWN_SEC = 10.0**: Prevents accidental spam while allowing reasonable iteration speed.\n- **Auth token**: Single-use per server lifetime prevents CSRF on localhost (defense in depth with localhost binding).\n- **Daemon thread**: Projects watcher exits automatically when main thread exits.\n\n## Acceptance Criteria\n- AC-33: Projects list loaded on server start\n- AC-35, AC-36: Rate limiting infrastructure\n- AC-37: Auth token generation\n- AC-40: Background projects refresh\n\n## Verification\n```python\nfrom amc_server.context import PROJECTS_DIR, ZELLIJ_SESSION, generate_auth_token\nassert PROJECTS_DIR.exists()\nassert ZELLIJ_SESSION == 'infra'\ntoken = generate_auth_token()\nassert len(token) > 20\n```\n\n## Success Criteria\n- All constants importable from context.py\n- generate_auth_token() returns unique token each call\n- validate_auth_token() correctly validates Bearer token format\n- start_projects_watcher() starts daemon thread without error","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T21:39:03.658826Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:58:00.710511Z","closed_at":"2026-02-26T21:58:00.710456Z","close_reason":"Added spawn constants, auth token functions, rate limiting, and projects watcher to context.py. All 302 tests pass.","compaction_level":0,"original_size":0} @@ -37,4 +37,4 @@ {"id":"bd-g9t","title":"Implement _serve_skills endpoint handler","description":"## Overview\nImplement _serve_skills(agent) method in SkillsMixin that serves the skills API response.\n\n## Background\nThis is the main entry point called by the HTTP route. It determines the agent type, calls the appropriate enumeration method, and returns a properly formatted JSON response.\n\n## Implementation (from plan IMP-1)\n```python\ndef _serve_skills(self, agent):\n \"\"\"Return autocomplete config for an agent.\"\"\"\n if agent == 'codex':\n trigger = '$'\n skills = self._enumerate_codex_skills()\n else: # claude (default)\n trigger = '/'\n skills = self._enumerate_claude_skills()\n \n # Sort alphabetically\n skills.sort(key=lambda s: s['name'].lower())\n \n self._send_json(200, {'trigger': trigger, 'skills': skills})\n```\n\n## Response Format\n```json\n{\n \"trigger\": \"/\",\n \"skills\": [\n { \"name\": \"commit\", \"description\": \"Create a git commit with a message\" },\n { \"name\": \"review-pr\", \"description\": \"Review a pull request\" }\n ]\n}\n```\n\n## Key Decisions\n- **Claude is default**: Unknown agents get Claude behavior (fail-safe)\n- **Sorting is server-side**: Client receives pre-sorted list (AC-5)\n- **Uses _send_json**: Follows existing pattern from HttpMixin\n\n## Success Criteria\n- Returns correct trigger character per agent\n- Skills are alphabetically sorted (case-insensitive)\n- Unknown agents default to Claude\n- Valid JSON response with 200 status","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T20:08:14.837644Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:43:40.277309Z","closed_at":"2026-02-26T21:43:40.277265Z","close_reason":"Already implemented in bd-3q1 — _serve_skills correctly handles agent type, sorting, and JSON response","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-g9t","depends_on_id":"bd-3eu","type":"blocks","created_at":"2026-02-26T20:08:18.595535Z","created_by":"tayloreernisse"},{"issue_id":"bd-g9t","depends_on_id":"bd-sv1","type":"blocks","created_at":"2026-02-26T20:08:18.574532Z","created_by":"tayloreernisse"}]} {"id":"bd-mjo","title":"Add API constants for spawn endpoints in dashboard","description":"## Overview\nAdd spawn-related API constants to dashboard/utils/api.js following existing patterns.\n\n## Background\nThe dashboard follows a pattern of defining API endpoints as constants in api.js. This enables:\n- Centralized endpoint management\n- Easy updates if paths change\n- Consistent usage across components\n\n## Implementation (IMP-2c)\nAdd to existing exports in dashboard/utils/api.js:\n\n```javascript\n// Spawn API endpoints\nexport const API_SPAWN = '/api/spawn';\nexport const API_PROJECTS = '/api/projects';\nexport const API_PROJECTS_REFRESH = '/api/projects/refresh';\nexport const API_HEALTH = '/api/health';\n```\n\n## Existing Pattern\nThe file already exports similar constants:\n```javascript\nexport const API_SESSIONS = '/api/sessions';\nexport const API_RESPOND = '/api/respond';\n// etc.\n```\n\n## Why Constants (Not Inline Strings)\n1. Single source of truth for endpoint paths\n2. IDE autocomplete and find-references\n3. Easy to grep for all API usage\n4. Refactoring-friendly\n\n## Success Criteria\n- Constants exported from api.js\n- No typos in paths\n- Consistent with existing constants","status":"closed","priority":1,"issue_type":"task","created_at":"2026-02-26T21:41:03.515881Z","created_by":"tayloreernisse","updated_at":"2026-02-26T21:57:53.036404Z","closed_at":"2026-02-26T21:57:53.036359Z","close_reason":"Added API_SPAWN, API_PROJECTS, API_PROJECTS_REFRESH, API_HEALTH constants to dashboard/utils/api.js","compaction_level":0,"original_size":0} {"id":"bd-sv1","title":"Implement Claude skill enumeration","description":"## Overview\nImplement _enumerate_claude_skills() method in SkillsMixin to discover skills from ~/.claude/skills/.\n\n## Background\nClaude Code stores user skills as directories under ~/.claude/skills/. Each skill directory contains a SKILL.md (canonical casing) with the skill definition. We need to enumerate these and extract descriptions.\n\n## Implementation (from plan IMP-1)\n```python\ndef _enumerate_claude_skills(self):\n skills = []\n skills_dir = Path.home() / '.claude/skills'\n \n if skills_dir.exists():\n for skill_dir in skills_dir.iterdir():\n if skill_dir.is_dir() and not skill_dir.name.startswith('.'):\n description = ''\n # Check files in priority order\n for md_name in ['SKILL.md', 'skill.md', 'prompt.md', 'README.md']:\n md_file = skill_dir / md_name\n if md_file.exists():\n try:\n content = md_file.read_text()\n for line in content.splitlines():\n line = line.strip()\n if line and not line.startswith('#') and not line.startswith('