97d565e3cd
* feat: add mem-search skill with progressive disclosure architecture Add comprehensive mem-search skill for accessing claude-mem's persistent cross-session memory database. Implements progressive disclosure workflow and token-efficient search patterns. Features: - 12 search operations (observations, sessions, prompts, by-type, by-concept, by-file, timelines, etc.) - Progressive disclosure principles to minimize token usage - Anti-patterns documentation to guide LLM behavior - HTTP API integration for all search functionality - Common workflows with composition examples Structure: - SKILL.md: Entry point with temporal trigger patterns - principles/: Progressive disclosure + anti-patterns - operations/: 12 search operation files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add CHANGELOG entry for mem-search skill Document mem-search skill addition in Unreleased section with: - 100% effectiveness compliance metrics - Comparison to previous search skill implementation - Progressive disclosure architecture details - Reference to audit report documentation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add mem-search skill audit report Add comprehensive audit report validating mem-search skill against Anthropic's official skill-creator documentation. Report includes: - Effectiveness metrics comparison (search vs mem-search) - Critical issues analysis for production readiness - Compliance validation across 6 key dimensions - Reference implementation guidance Result: mem-search achieves 100% compliance vs search's 67% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: Add comprehensive search architecture analysis document - Document current state of dual search architectures (HTTP API and MCP) - Analyze HTTP endpoints and MCP search server architectures - Identify DRY violations across search implementations - Evaluate the use of curl as the optimal approach for search - Provide architectural recommendations for immediate and long-term improvements - Outline action plan for cleanup, feature parity, DRY refactoring * refactor: Remove deprecated search skill documentation and operations * refactor: Reorganize documentation into public and context directories Changes: - Created docs/public/ for Mintlify documentation (.mdx files) - Created docs/context/ for internal planning and implementation docs - Moved all .mdx files and assets to docs/public/ - Moved all internal .md files to docs/context/ - Added CLAUDE.md to both directories explaining their purpose - Updated docs.json paths to work with new structure Benefits: - Clear separation between user-facing and internal documentation - Easier to maintain Mintlify docs in dedicated directory - Internal context files organized separately 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Enhance session management and continuity in hooks - Updated new-hook.ts to clarify session_id threading and idempotent session creation. - Modified prompts.ts to require claudeSessionId for continuation prompts, ensuring session context is maintained. - Improved SessionStore.ts documentation on createSDKSession to emphasize idempotent behavior and session connection. - Refined SDKAgent.ts to detail continuation prompt logic and its reliance on session.claudeSessionId for unified session handling. --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Alex Newman <thedotmack@gmail.com>
4.8 KiB
4.8 KiB
Get Context Timeline
Get a chronological timeline of observations, sessions, and prompts around a specific point in time.
When to Use
- User asks: "What was happening when we deployed?"
- User asks: "Show me context around that bug fix"
- User asks: "What happened before and after that change?"
- Need temporal context around an event
Command
# Using observation ID as anchor
curl -s "http://localhost:37777/api/timeline/context?anchor=1234&depth_before=10&depth_after=10"
# Using session ID as anchor
curl -s "http://localhost:37777/api/timeline/context?anchor=S545&depth_before=10&depth_after=10"
# Using ISO timestamp as anchor
curl -s "http://localhost:37777/api/timeline/context?anchor=2024-11-09T12:00:00Z&depth_before=10&depth_after=10"
Parameters
- anchor (required): Point in time to center timeline
- Observation ID:
1234 - Session ID:
S545 - ISO timestamp:
2024-11-09T12:00:00Z
- Observation ID:
- depth_before: Number of records before anchor (default: 10, max: 50)
- depth_after: Number of records after anchor (default: 10, max: 50)
- project: Filter by project name (optional)
Response Structure
Returns unified chronological timeline:
{
"anchor": 1234,
"depth_before": 10,
"depth_after": 10,
"total_records": 21,
"timeline": [
{
"record_type": "observation",
"id": 1230,
"type": "feature",
"title": "Added authentication middleware",
"created_at_epoch": 1699564700000
},
{
"record_type": "prompt",
"id": 1250,
"session_id": "S545",
"prompt_preview": "How do I add JWT authentication?",
"created_at_epoch": 1699564750000
},
{
"record_type": "observation",
"id": 1234,
"type": "feature",
"title": "Implemented JWT authentication",
"created_at_epoch": 1699564800000,
"is_anchor": true
},
{
"record_type": "session",
"id": 545,
"session_id": "S545",
"title": "Implemented JWT authentication system",
"created_at_epoch": 1699564900000
}
]
}
How to Present Results
Present as chronological narrative with anchor highlighted:
## Timeline around Observation #1234
### Before (10 records)
**2:45 PM** - 🟣 Observation #1230: Added authentication middleware
**2:50 PM** - 💬 User asked: "How do I add JWT authentication?"
### ⭐ Anchor Point (2:55 PM)
🟣 **Observation #1234**: Implemented JWT authentication
### After (10 records)
**3:00 PM** - 🎯 Session #545 completed: Implemented JWT authentication system
**3:05 PM** - 🔴 Observation #1235: Fixed token expiration edge case
For complete formatting guidelines, see formatting.md.
Anchor Types
Observation ID:
- Use when you know the specific observation ID
- Example:
anchor=1234
Session ID:
- Use when you want context around a session
- Example:
anchor=S545
ISO Timestamp:
- Use when you know approximate time
- Example:
anchor=2024-11-09T14:30:00Z
Error Handling
Missing anchor parameter:
{"error": "Missing required parameter: anchor"}
Fix: Add the anchor parameter
Anchor not found:
{"error": "Anchor not found: 9999"}
Response: "Observation #9999 not found. Check the ID or try a different anchor."
Invalid timestamp:
{"error": "Invalid timestamp format"}
Fix: Use ISO 8601 format: 2024-11-09T14:30:00Z
Tips
- Start with depth_before=10, depth_after=10 for balanced context
- Increase depth for broader investigation (max: 50 each)
- Use observation IDs from search results as anchors
- Timelines show all record types interleaved chronologically
- Perfect for understanding "what was happening when X occurred"
Token Efficiency:
- depth 10/10: ~3,000-4,000 tokens (21 records)
- depth 20/20: ~6,000-8,000 tokens (41 records)
- depth 50/50: ~15,000-20,000 tokens (101 records)
- See ../principles/progressive-disclosure.md
When to Use Timeline
Use timeline when:
- Need context around specific event
- Understanding sequence of events
- Investigating "what was happening then?"
- Want all record types (observations, sessions, prompts) together
Don't use timeline when:
- Just need recent work (use recent-context)
- Looking for specific topics (use search)
- Don't have an anchor point (use timeline-by-query)
Comparison with Timeline-by-Query
| Feature | timeline | timeline-by-query |
|---|---|---|
| Requires anchor | Yes (ID or timestamp) | No (uses search query) |
| Best for | Known event investigation | Finding then exploring context |
| Steps | 1 (direct timeline) | 2 (search + timeline) |
| Use when | You have observation ID | You have search term |
Timeline is faster when you already know the anchor point.