chore(memory): BDR-115 amendment 2 + LRN-210/211 + EVAL-042 + journal/TODO/contract w2b — feat model-router wave 2

.claude/memory/decisions.md

@@ -1402,4 +1402,4 @@ Branch feature/user-writing-web-rules, UNMERGED (human gate).
 - **Gates**: plan r1 → r3 through 3 challengers + 1 confirmation (2 BLOCKER + 10 MAJOR closed, [[EVAL-040]]); feater DONE first pass; GATE 0 MET; verifier CONFORME 6/6; security PASS + hardening round (criteria 7-11).
 - **Refs**: plan `.claude/tasks/plans/2026-10-08-model-router-mod.md`, contract `.claude/tasks/contracts/2026-10-08-model-router-w1a-1533.md`, [[BDR-107]], [[BDR-108]], [[BLK-029]], [[LRN-205]], [[LRN-206]].
 - **Amendment (2026-10-09, user decisions 2026-10-08 evening)**: (a) LOAD supersedes the "Load:" line: tracked relative symlink `skills/model-router` → `../mods/model-router`, loaded in place as `model-router@skills-dir` wherever link.sh links `~/.claude/skills`; `CLAUDE_CODE_PLUGIN_DIRS` dropped (absolute path, settings `env` has no `$HOME` expansion, settings.json tracked), local marketplace dropped (`add` writes an absolute path into settings.json). Proven by fresh-process `claude plugin list --json`. (b) PRECEDENCE amended: `ultrathink` and a typed `/effort-<l>` are the main turn's DEFAULT and MINIMUM (floor slot `turnFloor`): sticky `/route` effort > turn route effort > floor > engine, then floored; per axis; mid-turn prompt floors the running turn and the next (`wait` ignored). Rationale: user "un choix explicite bat la phase déduite"; a pure floor made `/effort-low` a no-op (challenge finding). (c) Per-machine kill switch `"enabled": false` in the untracked `~/.claude/model-router.json` (survives `/clear`, a failed reload keeps the previous config); `enabledPlugins` would dirty the tracked settings.json on every machine. (d) Hardening: `/route` composer-only; agent loops effort-only (model fixed at spawn); config caps; typed slash attested at `prompt.submit`. Commits 346d6ae, 1ff608a, 6430ac6; contracts `2026-10-08-model-router-floor-1835`, `2026-10-08-model-router-wiring-1835`; residuals parked in TODO.
-
+- **Amendment 2 (2026-10-10, wave 2 closed, commits bb56f3e + 1f2d33b)**: (a) rule 4 closed: rows for every repo skill (56) + agent (21) + Explore/Plan, PHASES by role (plan/reflect/orchestrate/escalate best · judge big · implement/write/verify/explore/apply work · mechanical cheap; `write` work/high + `apply` work/low added). User: pins "deleted or reworked", not copied → rows are the live source, tracked `model:`/`effort:` frontmatter KEPT as off-state floor, census-locked equal to rows (`lib/tests/effort-routing.test.sh`). Robustness BLOCKER closed: mod off → agents would inherit parent model. (b) Rule 5 amended: unrowed skill load changes nothing; best-tier skill row lives in `runMain` slot surviving turn end (precedence userMain > turnMain > runMain > floor > engine), dropped by `/route clear`, `/route off`, user `/model`, typed non-best skill; turn writers (route tool, prompt rules) never touch it. (c) Agents: model written at spawn WITHIN tier, upward only (never below frontmatter alias); explicit Agent params win; project-defined agent (agent.offer source projectSettings|localSettings) skipped. (d) Typed slash: name-bound marker at prompt.submit (composer|sdk|bridge) + pending slot + idle fallback (no live/spawning loop). (e) Shifters `effort-*`, `effort-pins.*`, `model-check.sh` DELETED; orchestrators call `mcp__model-router__route` per phase; gate witness = route answer id, remedy `/route on`; builtin `/effort` not a lever inside a run (levers `ultrathink`, `/route effort=max`). (f) SemVer: typed `/effort-*` removal = breaking → next release 3.0.0. Plan `.claude/tasks/plans/2026-10-09-model-router-w2-1546.md` r4, contracts `2026-10-09-model-router-w2a-1546`, `2026-10-10-model-router-w2b-1045`. Links [[LRN-210]], [[LRN-211]], [[EVAL-042]].

.claude/memory/evals.md

@@ -62,6 +62,7 @@ rules:
 | EVAL-039 | 2026-09-30 | ship-feature run higgsfield-pack: plan dry-run in scratch → 0 executor failure on 7 tasks; challenge found 7 MAJOR I missed; floor-guard caught 2 shellcheck suppressions of mine; final review found README/code gap | keep |
 | EVAL-040 | 2026-10-08 | model-router w1a plan: 3 challengers + 1 confirmation found 2 BLOCKER + 14 MAJOR on a plan judged closed; executor then passed every gate first time | keep the round, never dispatch a mod plan without it |
 | EVAL-041 | 2026-10-09 | model-router W1-C plan: 3 lenses FATAL (4 BLOCKER + 20 MAJOR) then 2 confirmations each FATAL with a NEW BLOCKER in my own revision; executor DONE first pass, 3 short text/hardening rounds | one confirmation is not enough when a revision removes a whole mechanism; the plan carried the risk, the code almost none |
+| EVAL-042 | 2026-10-10 | model-router W2 plan r1 → r4: 3 lenses (1 BLOCKER), 2 confirmations (1 BLOCKER then 0); W2-A verifier 3× ECARTS on coverage clauses only, W2-B ECARTS(7) → CONFORME; gate A→B read from engine records | second confirmation paid again (BLOCKER on my own r2 slot); compound coverage criterion = endless ECARTS; engine jsonl replaces the live log |
 
 ---
 
@@ -387,3 +388,9 @@ Dogfood: 3 blind lenses attacked the v1 plan for the plan-challenge feature itse
 - **Anomaly**: 6 BLOCKER + 29 MAJOR over four revisions, each confirmation found a flaw my own fix had introduced; the doctrine cap (one confirmation) would have shipped r2 with a 5-hour false outage. The executor never needed a re-dispatch for logic: all later rounds were text truthfulness and hardening.
 - **Action**: when a revision REMOVES or REPLACES a mechanism, re-challenge once more (state the deviation); keep plan sections additive with an explicit precedence line (r4 > r3 > r2) so executors and verifiers read one law; name superseded clauses of prior contracts in the Disposition. Links [[EVAL-040]], [[LRN-207]], [[BDR-115]].
 
+## EVAL-042 — model-router W2: challenge value held on the second confirmation; coverage-shaped criterion burned three verifiers
+- **Date**: 2026-10-10
+- **Output checked**: plan `.claude/tasks/plans/2026-10-09-model-router-w2-1546.md` r1 → r4; W2-A diff (register.ts, 88 kit tests); W2-B diff (43 files, 140-check census).
+- **Method**: 3 blind lenses (simplicity CONCERNS(5), correctness CONCERNS(10), robustness FATAL(8) → BLOCKER: mod off = agents inherit parent model); confirmation 1 robustness FATAL(8) → BLOCKER introduced by r2 (route calls wiped the sticky slot); confirmation 2 correctness CONCERNS(3), no BLOCKER → r4. W2-A: feater DONE + 4 rounds (1 internal decision, 3 coverage), GATE 0 MET, verifier ECARTS(3)/(1)/(1) all coverage, user accepted at cap; security PASS. W2-B: feater DONE first pass, verifier ECARTS(7) (5 FLOOR items = planned deletions needing a CLARIFICATIONS line, 2 prose, 1 scope add) → CONFORME 10/10; security PASS; full `make test` once (env red only). Gate A→B: 3/4 probes answered from engine jsonl, probe 4 (typed skill with a live agent) unobserved, recorded as a limit.
+- **Anomaly**: the user's rework answer ("delete or rework, not copy") changed the design mid-plan; r2's own fix carried a BLOCKER again (as in EVAL-041). Coverage criterion: 3 verifiers, 0 defects. FLOOR guard needs the test deletions named in CLARIFICATIONS, not only in criteria.
+- **Action**: keep the "second confirmation after a mechanism change" rule; write coverage criteria one clause each (LRN-210); when a plan deletes tests, write the authorizing CLARIFICATIONS line BEFORE the first verifier. Links [[EVAL-041]], [[LRN-210]], [[LRN-211]], [[BDR-115]].

.claude/memory/journal.md

@@ -591,3 +591,6 @@ rules:
 - /hotfix make-test-names-red-suites (user: '9 min pour un merge?'): measured from transcript timestamps, the merge took <20 s; 454 s went to make test run TWICE (full + per-suite sweep to name the red suite, because the aggregate rc is silent). Fix: Makefile test prints FAIL <suite> + summary, rc unchanged (GNU make returns 2 on a failed recipe; my first oracle expected 1). hotfixer DONE, GATE 0 MET 2/2, security PASS. Branch bugfix/make-test-names-red-suites UNMERGED (human signal). Method note: a mods/-only diff needs only the mods suite + doctrine census, the full run once before merge.
 - User go 'all, merge le, et je clear': LRN-207/208/209 + EVAL-041 written (ca96458); gitflow finish bugfix/make-test-names-red-suites → develop 5e0e5c0, branch removed. develop 28 commits ahead of origin, NOT pushed (manual mode, user publishes). Only settings.json dirty (user's own /model change). Session closes; next: wave 2 of model-router (TODO W2 line).
 - model-router W2-A landed (bb56f3e, feature/model-router-w2). User go 'lance la vague 2' + 4 pass-B answers: shifters deleted, pins reworked into phase rows (not copied), phases declared, slim gate. Plan r1→r4: 3 lenses (1 BLOCKER: mod off → agents inherit parent model → frontmatter kept as off-state floor), confirmation 1 FATAL (BLOCKER: route calls wiped the sticky slot → separate runMain), confirmation 2 CONCERNS (deviation: 2 confirmations, stated). Feater DONE + 4 gap rounds (A5 in-agent decision, 6+3+3 coverage tests, every one mutation-proven). GATE 0 MET; verifier ECARTS(3)/(1)/(1) all on coverage of criterion 3 clauses, never code → diagnosis at max: compound criterion → user accepted at the cap. Security PASS (2 MEDIUM pre-existing). Kit 58→88. Next: user /reload-plugins + live probe, then W2-B. Lesson for the next contract: one coverage clause per criterion, not twelve.
+
+## 2026-10-10
+- model-router W2-B landed (1f2d33b) + gate A→B. User /reload-plugins + typed /status; I read the engine jsonl instead of the UI log: main low on typed /status, analyzer opus/xhigh at step 0 → ordering + row-over-frontmatter proven; probe 4 unobserved (user away), limit recorded. Route tool checked live (`mcp__model-router__route`, deferred → ToolSearch once; answer names the id); session itself routed through it (reflect → orchestrate). W2-B: contract 10 criteria, feater DONE first pass (43 files), verifier ECARTS(7): 5 FLOOR items (planned test deletions → CLARIFICATIONS line), `/route on` wording, false CLAUDE.global.md sentence, plan-challenger scope add → CONFORME 10/10; I folded 3 observations by hand (SDD sonnet implementers `effort="medium"`, run-slot droppers, 80-col). Security PASS (push-guard false positive on a grep pattern; it also bit my registry heredoc). Full make test green (env red only). Doc audit SIGNIFICANT → user: apply all P1-P8, SemVer BREAKING → 3.0.0, registries all → BDR-115 amendment 2, LRN-210/211, EVAL-042. Pending: doc commit, memory commit, user merge decision (gitflow finish, human signal), publish by hand.

.claude/memory/learnings.md

@@ -1777,3 +1777,10 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 - **Context**: 2026-10-09 the pre-merge check took 454 s = full `make test` (48 suites) + a per-suite re-run to NAME the red one (aggregate rc, permanent env red design-tool-gate). Three more full passes earlier that day for mods/-only diffs. Hotfix efdd491: the recipe prints `FAIL <suite>` + `all suites green` / `<n> suite(s) red: …`. My oracle expected rc 1; GNU make returns 2 when a recipe line fails.
 - **Apply**: a diff confined to one component runs that component's suite + the doctrine census; the full suite runs ONCE before `gitflow finish`; read the FAIL lines, never re-run per suite. Oracles on `make` test `[ $rc -ne 0 ]`, not `-eq 1`. Links [[LRN-173]].
 
+## LRN-210 — One coverage clause per contract criterion; a compound "covered by kit tests" criterion yields ECARTS forever with zero defects
+- **Context**: W2-A contract criterion 3 bundled ~12 clauses under one "Covered by kit tests". Three fresh verifiers: ECARTS(3), (1), (1), each a NEW untested guard, code judged correct 3×. Cap hit, diagnosis at max, user accepted. 4 feater rounds added 30 tests (58 → 88), every one mutation-proven.
+- **Apply**: split coverage criteria: one clause = one criterion with its own test name; or make the oracle a mutation script (`CHECK:` flips the guard, expects a red test). Verifier reads clauses literally: write only what one test can prove. Links [[LRN-209]], [[EVAL-042]].
+
+## LRN-211 — Typed-slash routing: name-bound marker + idle fallback; run slot separate from turn routes; engine records are the live oracle
+- **Context**: mod needs "user typed /feat" from `skill.prompt`, which carries no origin. `prompt.submit` sees the raw `/name` first (composer|sdk|bridge): store the NAME (not a boolean; a bare flag leaked to the next preload), pending slot when mid-turn, consume only on the matching `skill.prompt`; fallback = no live/spawning loop AND allowed origin. Sticky run route in the SAME slot as turn routes was wiped by the first `route()` call (confirmation BLOCKER) → separate `runMain`, best-tier rows only (work/cheap rows leak low effort across turns). Live facts read from `~/.claude/projects/<repo>/<session>.jsonl` (+ `subagents/agent-*.jsonl`): `effort` + `message.model` per step. Typed `/status` → main low; analyzer step 0 opus/xhigh with frontmatter high (spawn bookkeeping precedes step 0; row beats frontmatter).
+- **Apply**: hook-side user-intent markers: bind to a name, add a pending slot for mid-turn, keep an ordering-independent fallback. Two lifetimes = two slots, never one slot with a source tag. Verify engine behaviour in the transcript jsonl, not in `$.ui.log`. Links [[BDR-115]], [[LRN-206]].