mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
4a7c6a0701
Add an --all-docs mode to check-doc-skill-refs.sh that scans the union of the pinned doctrine files PLUS the full LIVE docs/** set (scripts/lib/docs-scope.sh), ratcheted by a new filename-pinned shrink baseline (scripts/.docs-skill-refs-baseline). Two-way ratchet: a non-baselined live doc with a dead `/skill` ref FAILS; a baselined file that no longer offends FAILS demanding a prune. Detection stays slash-syntax + headings only (never bare skill names). Default (no-flag) behavior is byte-identical. docs/SKILL-ROUTER.md (the curated router) is covered by --all-docs (a live docs/** file, never baselined) so a dead ref there FAILS strict, without perturbing the byte-identical default doc count. seed.go docs.skill-refs row: Match widened to docs/** + the baseline + the lib; Args set to [--all-docs --strict]. Burn-down (long-tail only): repointed retired `/retro`->/post-mortem, `/vibe`->/validate, `/ratchet`->/flywheel, `/research-multi`->/research, `/implement-wave`->/crank, and reworded the retired `/dream` across 13 docs/levels + docs/workflows + docs/philosophy pages, then pruned them from the baseline (91 -> 78 offenders). Owner-locked pages (comparisons/getting-started/positioning) stay baselined. Bats twin tests/scripts/check-doc-skill-refs-all-docs.bats covers all the modes.
2.1 KiB
2.1 KiB
Demo: /retro Session
A session showing learning extraction at the end of work.
Before
- You've been working for a while
- Solved some problems, discovered patterns
- About to end the session or hit context limits
Session
You: /retro
Claude: Reviewing this session to extract learnings...
**Session Summary:**
This session focused on debugging authentication timeouts.
**Problems Solved:**
1. JWT tokens expiring mid-request due to clock skew
- Solution: Added 30-second buffer to expiry check
- File: src/auth/jwt.ts:42
2. Redis connection pool exhaustion under load
- Solution: Increased pool size from 10 to 50
- File: config/redis.ts:8
**Patterns Discovered:**
- Always check token expiry with buffer time
- Connection pool size should be 5x expected concurrent users
- Log connection pool metrics for capacity planning
**Mistakes to Avoid:**
- Don't trust client-provided timestamps
- Don't cache tokens longer than their remaining TTL
**Writing to:** .agents/learnings/2025-01-15-auth-debugging.md
[Write] .agents/learnings/2025-01-15-auth-debugging.md
✓ Learnings saved.
After
.agents/
├── research/
└── learnings/
└── 2025-01-15-auth-debugging.md # <- New file
The Learnings File
# Auth Debugging Session - 2025-01-15
## Problems Solved
### JWT Token Expiry Race Condition
- **Symptom**: Intermittent 401 errors under load
- **Root Cause**: Clock skew between servers
- **Solution**: Added 30-second buffer (src/auth/jwt.ts:42)
### Redis Pool Exhaustion
- **Symptom**: Connection timeouts after 10 concurrent requests
- **Root Cause**: Pool size too small
- **Solution**: Increased to 50 (config/redis.ts:8)
## Patterns
- Token expiry checks need buffer time
- Pool size = 5x concurrent users
- Monitor pool metrics
## Don't Repeat
- Never trust client timestamps
- Don't cache tokens past their TTL
What You Learned
/post-mortemcaptures session knowledge before it's lost- Learnings are structured for future reference
- Problems, patterns, and mistakes are all valuable
- Run
/post-mortembefore context limits or session end