bchanot/claude
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(model-router): wave 2-B — orchestrators declare phases, shifters and pins removed, frontmatter = off-state floor

Browse Source 
The 15 Skill(effort-*) citers now call mcp__model-router__route per phase
(orchestrate at a dispatch span, reflect/plan for the skill's own level,
apply at the bookkeeping tail, escalate at the verify-secure caps); built-in
judgment dispatches carry an explicit effort= param. lib/effort-shift.md is
the route doctrine, lib/model-gate.md the mod rule (route answer = witness,
/route on as remedy). Deleted: skills/effort-*, lib/effort-pins.txt/.sh,
lib/model-check.sh, their tests, the installers' re-apply blocks. The mod
drops its Skill(effort-*) bridge. The tracked model:/effort: frontmatter
stays as the off-state floor, census-locked equal to the rows
(lib/tests/effort-routing.test.sh rewritten, 140 checks; analyzer → xhigh).

Contract .claude/tasks/contracts/2026-10-10-model-router-w2b-1045.md, plan
r4 § W2-B: GATE 0 MET, verifier ECARTS(7) then CONFORME 10/10, security
PASS, full make test green (design-tool-gate env red only).
This commit is contained in:
bchanot
2026-10-10 11:24:54 +02:00
parent 65dff0e768
commit 1f2d33b7a6
43 changed files with 318 additions and 811 deletions
Download Patch File Download Diff File Expand all files Collapse all files
agents/plan-challenger.md
+5 -5
View File
@@ -106,11 +106,11 @@ the MAIN loop, never here):
- Dispatch THREE fresh challengers IN PARALLEL, one per lens
(correctness / robustness / simplicity), each blind to the others.
- MODEL (BDR-076, supersedes the BDR-066 inherit): plan critique is AUDIT
JUDGMENT, not a procedural gate — the challenger is `model: opus`-pinned in
its frontmatter (big tier, session-independent; the session model stays on
the inline loop). Never `model: "sonnet"` — a silent judgment downgrade.
(Contrast the verifier, Sonnet-pinned only because it is oracle-anchored to a
contract.)
JUDGMENT, not a procedural gate — the challenger is routed to the `judge`
row (opus) by the model-router, the `model: opus` frontmatter being the off-state floor (big
tier; the session model stays on the inline loop). Never `model: "sonnet"` —
a silent judgment downgrade. (Contrast the verifier on its `verify` row and
the executors on their `implement` row, both sonnet, oracle-anchored to a contract.)
- FAIL-SAFE — never fail open: a malformed/empty verdict, a missing `PROOF`, or
a dead challenger → retry ONCE fresh; a 2nd failure → escalate to the human and
NAME the lens. Never report "plan challenged" on a silently dropped lens (same