generated from coulomb/repo-seed
Updated by fix-consistency on 2026-05-17: - update .custodian-brief.md for llm-connect
30 lines
1.4 KiB
Markdown
30 lines
1.4 KiB
Markdown
<!-- custodian-brief: generated by fix-consistency — do not edit manually -->
|
|
# Custodian Brief — llm-connect
|
|
|
|
**Domain:** custodian
|
|
**Last synced:** 2026-05-17 17:21 UTC
|
|
**State Hub:** http://127.0.0.1:8000 *(adjust if running on a remote machine)*
|
|
|
|
## Active Workstreams
|
|
|
|
### Adaptive Cost-Quality Routing
|
|
Progress: 5/23 done | workstream_id: `e1807fab-e29e-4517-b362-95737a96582d`
|
|
|
|
**Open tasks:**
|
|
- · GradingResult dataclass: quality_score, notes, grader_id, baseline_response, candidate_response `c12a595b`
|
|
- · BaselineGrader protocol plus PairedGrader that runs baseline and candidate calls and delegates to a Judge `80b98e31`
|
|
- · Judge protocol and built-ins: ExactMatchJudge, EmbeddingSimilarityJudge, LLMJudge `c2887fe3`
|
|
- · Functional contract doc covering judge bias caveats `7a4fd87a`
|
|
- · Tests: judges with canned inputs, stable grader result, deterministic LLMJudge rubric seed `8415a11d`
|
|
- · AdaptiveRoutingPolicy extends RoutingPolicy and selects the cheapest adapter whose observed mean quality clears the floor `0e9f9f8e`
|
|
- · Tie-breaking: prefer lower observed cost, then explicit preferred adapter from static rules `59d44712`
|
|
- … and 11 more open tasks
|
|
|
|
---
|
|
## MCP Orientation (when available)
|
|
|
|
If the state-hub MCP server is reachable, call:
|
|
`get_domain_summary("custodian")`
|
|
This provides richer cross-domain context.
|
|
If the MCP call fails, use this file as your orientation source.
|