chore(consistency): sync task status from DB [auto]

Updated by fix-consistency on 2026-05-17:
  - update .custodian-brief.md for llm-connect

.custodian-brief.md

@@ -2,23 +2,23 @@
 # Custodian Brief — llm-connect
 
 **Domain:** custodian  
-**Last synced:** 2026-05-17 17:21 UTC  
+**Last synced:** 2026-05-17 17:51 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`
+Progress: 10/23 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
+- · Cold-start behaviour falls through to static RoutingPolicy.resolve when observations are missing  `1927d369`
+- · Functional contract doc for adaptive policy and sample-size/freshness trade-off  `4d4717c1`
+- · Tests: floor enforcement, tie-break, cold-start, window-size effect, fallback chain  `304bd782`
+- · ShadowingAdapter wraps a candidate adapter, also invokes the baseline adapter, grades, and appends to QualityLedger  `62dd507f`
+- · Sampling: caller-configurable shadow_rate so production load is not doubled  `ccb73e92`
+- … and 6 more open tasks
 
 ---
 ## MCP Orientation (when available)