jpmschweitzer/tatlock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 5 Wiki Activity
141 Commits 1 Branch 47 Tags
5376a346458ae6823b7e3c61c7a8a226962b7592
Commit Graph
3 Commits
Author SHA1 Message Date
jpmschweitzerandClaude Fable 5 5376a34645 refactor(agents): reduce protocol.py to the live AgentError 
Post-coordination-removal sweep: the coordination wire protocol
(AgentRequest, AgentResponse, DelegationIntent, CoordinationResult,
DelegationReason, TaskComplexity, ToolCallRecord, AgentTimeoutError,
AgentUnavailableError, DelegationError) had zero importers left in
src/ - only its own test module. AgentError stays (raised by
run_librarian, mapped to user-safe failures by delegation.py).
Also drops the stale coordination.py line from the README tree.

Import-cycle sanity: python -c 'import src.main' passes.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L
 2026-07-14 12:03:31 +02:00
jpmschweitzerandClaude Fable 5 18f2e0efbd feat(agents): enforce one librarian timeout budget 
- add LIBRARIAN_TIMEOUT config (default 180s) and enforce it with
  asyncio.wait_for inside delegate_to_librarian, covering the live
  paths (steward direct delegation and SSE streaming) that had no cap
- timeouts fail honestly: success=False with a curated butler sentence,
  detail in logs
- set an explicit timeout on TatlockOllamaProvider's AsyncOpenAI client
  from OLLAMA_TIMEOUT instead of the SDK default (~600s per LLM call)
- remove the contradictory unused 60s default from
  AgentRequest.timeout_seconds; coordination falls back to the
  configured budget

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-14 10:19:16 +02:00
jpmschweitzerandClaude Opus 4.5 22d44b3071 test(phase3): add comprehensive tests for multi-agent coordination 
Protocol tests (16):
- AgentRequest/AgentResponse serialization
- DelegationIntent and DelegationReason validation
- CoordinationResult aggregation
- Error type tests

Coordination tests (14):
- Engine initialization and agent availability
- Delegation execution (success, error, timeout)
- Multi-intent coordination
- Streaming delegation

Librarian tests (42):
- Library-desk client (all endpoints)
- Wiki operations (search, get, create, update)
- Smart-create with HybridRAG
- Capability registration
- Response model validation

Total: 72 new tests, all passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-11 21:30:43 +01:00