forked from bchanot/claude
fix(model-routing): ronde edge fixes — feater applier carve-out, /refactor→sonnet dispatch, /analyze gate, audit-pin guards (F1-F5)
This commit is contained in:
Bastien Chanot
@@ -388,3 +388,5 @@ rules:
|
||||
- model routing WAVE 3 (same branch): /bugfix + /code-clean split like /feat — reflection inline, sonnet executors (bugfixer, code-cleaner). code-clean refactor now runs on sonnet (inline-load pin was inert). consumers rerouted (hotfix deeper-bug→/bugfix skill; onboard/tour read-only audit→big-model agent). Explore kept built-in (inherits big). census 42/0, loops-light 35/0. Branch still unmerged.
|
||||
- model routing waves 1-3 MERGED into develop (e5c7c51); LRN-125 added. WAVE 4 started on feature/client-handover-dispatch (off develop): client-handover doc-gen → sonnet. REDACTION-ONLY (user flipped from whole-writer — nested audits must run big either way). client-handover-writer trimmed to ship pipeline (STEP 1-8 preserved byte-for-byte) + delegates writing to NEW sonnet handover-doc-writer (gate-free, STEP 9-16). client-handover joins gated group. census 46/0. NOTE: a Task-20 implementer ran `git checkout -- settings.json`, discarding user /model=opus working-tree state (LRN-098) — flagged to user (re-run /model). Lesson worth an LRN: constrain SDD implementers from git ops on files outside their task.
|
||||
- wave-4 FINAL REVIEW (opus whole-branch): all 7 deliverable invariants hold, child gate-free, PACKAGE complete. Found 3 real regressions from the split — FIXED inline: (I2) DEPLOY_HINTS severed STEP2→STEP14 + (I3) --skip-seo flag dropped → both now forwarded via PACKAGE (parent resolved-list + dispatch template; child INPUT contract + gate); (I1) §7/§8 annex numbering drift in STEP 13/14 (operative steps said §6/§7 = stale 5-chapter scheme) realigned to authoritative §7/§8 + hard-rule renumbering M1/M2/M3 (Chapter 2/3/4 caps → 3/5/6; chapters 1–3 → 1–5, matching the gate windows). census lock added: lacks 'Agent(' on child (M5). census 47/0, shellcheck clean. Branch NOT merged (awaiting human signal).
|
||||
- waves 1-4 MERGED to develop (d8917bf). LRN-126/127 added.
|
||||
- post-merge RONDE (user "fais une ronde"): 4 big-model analyzer audits over 72 skills + 21 agents. Verdict: dispatch-graph INTACT (0 regressions), loops CLOSE (0 broken), tiering CORRECT (every dispatched agent), client-handover data-flow wired. The refactor preserved/improved everything it touched. NOTE: darwin-skill is a skill-PROMPT optimizer (mutates SKILL.md) — wrong tool for a post-merge verify; used bespoke analyzer fan-out on the big model (audit=reflection, dogfooded). Ronde surfaced edge findings → fixed on bugfix/model-routing-edge-fixes: F1 feater applier severed CONTRACT (real bug, LRN-126 instance — /seo,/geo dispatch feater as L1 applier with no CONTRACT but it mandated "read CONTRACT FIRST"; gave it hotfixer's applier carve-out); F2 /refactor inline-load→dispatch refactorer (sonnet pin was inert); F3 /analyze +MODEL GATE (ungated reflection); F4 interviewer drop inert sonnet pin; F5 census locks the ABSENT pin on seo/geo/validator-analyzer + client-handover-writer + interviewer (a stray sonnet pin would silently downgrade a live audit). census 47→57. Branch NOT merged.
|
||||
|
||||
@@ -1,5 +1,23 @@
|
||||
# TODO
|
||||
|
||||
## 2026-07-16 — model-routing edge fixes (bugfix/model-routing-edge-fixes)
|
||||
Post-merge ronde (4 big-model audits: dispatch-graph INTACT, loops CLOSE,
|
||||
tiering CORRECT, data-flow client-handover wired). Fixing the edge findings
|
||||
the ronde surfaced. Branch off develop, unmerged — human gate.
|
||||
- [x] F1 (real bug) feater applier carve-out — /seo,/geo dispatch feater as
|
||||
L1 applier with NO CONTRACT, but feater mandates "read CONTRACT FIRST"
|
||||
(hotfixer has the carve-out, feater didn't) → mirror hotfixer.md:16-45.
|
||||
- [x] F5 (guard) census: lock the ABSENT model: pin on seo/geo/validator-
|
||||
analyzer + client-handover-writer (stray sonnet pin would silently
|
||||
downgrade a live audit, uncaught).
|
||||
- [x] F4 (cleanup) drop interviewer's inert `model: sonnet` (reflection role,
|
||||
inline-loaded by gated init-project) + census guard.
|
||||
- [x] F2 (tier) /refactor inline-load → true-dispatch refactorer (sonnet pin
|
||||
was inert). refactorer verified dispatch-safe (no Ask/Agent, input=target).
|
||||
- [x] F3 (gate) /analyze add MODEL GATE (inline-loads the analyzer reflection
|
||||
agent, was ungated + undocumented). census: +analyze gated, +refactor excluded.
|
||||
- [x] verify: census 57/0, shellcheck clean (my files), full suite green; NO merge.
|
||||
|
||||
## 2026-07-15 — model routing (feature/model-routing)
|
||||
Spec + plan in docs/superpowers/ (transient, BDR-065). BDR-066. Branch
|
||||
unmerged — human gate.
|
||||
|
||||
+19
-4
@@ -7,9 +7,17 @@ model: sonnet
|
||||
|
||||
# FEATER — plan executor
|
||||
|
||||
You receive a CLOSED plan from the /feat orchestrator. Your job is faithful
|
||||
execution, not design. The thinking already happened; every choice you would
|
||||
want to make was either made in the plan or is a NEED-DECISION to report.
|
||||
You execute work ALREADY decided upstream — faithful execution, not design.
|
||||
The thinking already happened; every open choice is a NEED-DECISION to
|
||||
report, never an improvisation. Two dispatch sources, same job:
|
||||
|
||||
- **/feat orchestrator** — a CLOSED plan + CONTRACT (see INPUT).
|
||||
- **audit dispatchers (/seo, /geo)** — you are the L1 fix-bundle applier for
|
||||
the larger items (new legal/city pages, `.htaccess`, sitemaps); the
|
||||
dispatch prompt hands you a bundle item inline (files, concern, current,
|
||||
expected fix) with NO CONTRACT. Apply exactly that item, self-verify, do
|
||||
not commit. There is no FILE SCOPE contract on this path — the named files
|
||||
in the item ARE the scope.
|
||||
|
||||
## INPUT (in the dispatch prompt)
|
||||
|
||||
@@ -21,13 +29,20 @@ want to make was either made in the plan or is a NEED-DECISION to report.
|
||||
- `GAPS` (re-dispatch only): verifier/security verdict lines — fix ONLY
|
||||
those, touch nothing else.
|
||||
|
||||
Applier path (/seo, /geo): no CONTRACT/PLAN/BRANCH keys — the bundle item in
|
||||
the prompt is the work to apply. Skip the contract read; the `## OUTPUT`
|
||||
report below is optional on this path (the dispatcher needs the edit applied
|
||||
+ self-verified, not the report grammar).
|
||||
|
||||
## EXECUTION RULES
|
||||
|
||||
- Follow the plan to the letter. A plan hole or an open choice (naming,
|
||||
data shape, API surface, dependency) → STOP, report `NEED-DECISION` with
|
||||
the precise question. Never improvise a design decision.
|
||||
- Stay inside the contract FILE SCOPE. A needed file outside it →
|
||||
`NEED-DECISION` (the orchestrator owns scope changes); don't touch it.
|
||||
`NEED-DECISION` (the orchestrator owns scope changes); don't touch it. On
|
||||
the applier path the scope is the files named in the bundle item — apply
|
||||
only those.
|
||||
- Write tests alongside the code, as the plan names them. Run the relevant
|
||||
suite incrementally; run it fully before reporting.
|
||||
- Follow existing code patterns and CLAUDE.md limits (function size,
|
||||
|
||||
@@ -2,7 +2,6 @@
|
||||
name: interviewer
|
||||
description: Gather project info. Ask targeted questions, produce PROJECT BRIEF. First step of project init.
|
||||
tools: Read
|
||||
model: sonnet
|
||||
---
|
||||
|
||||
# INTERVIEWER
|
||||
|
||||
@@ -9,12 +9,12 @@ has() { if grep -qF "$2" "$R/$1"; then ok; else ko "$1 missing: $2"; fi; }
|
||||
lacks() { if grep -qF "$2" "$R/$1"; then ko "$1 must NOT contain: $2"; else ok; fi; }
|
||||
fm_lacks() { if awk 'NR<=10' "$R/$1" | grep -qF "$2"; then ko "$1 frontmatter must NOT contain: $2"; else ok; fi; }
|
||||
|
||||
# 1) gate wired in the 14 reflection orchestrators
|
||||
for s in ship-feature init-project feat bugfix onboard seo geo web-validate harden audit-delta tour code-clean hotfix client-handover; do
|
||||
# 1) gate wired in the 15 reflection skills (orchestrators + /analyze)
|
||||
for s in ship-feature init-project feat bugfix onboard seo geo web-validate harden audit-delta tour code-clean hotfix client-handover analyze; do
|
||||
has "skills/$s/SKILL.md" 'lib/model-gate.md'
|
||||
done
|
||||
# 2) gate NOT wired in the excluded skills (encodes the spec exclusion list)
|
||||
for s in commit-change doc status release-candidate; do
|
||||
# 2) gate NOT wired in the pure-execution/read-only skills (exclusion list)
|
||||
for s in commit-change doc status release-candidate refactor; do
|
||||
lacks "skills/$s/SKILL.md" 'lib/model-gate.md'
|
||||
done
|
||||
# 3) executor + gate pins
|
||||
@@ -53,6 +53,18 @@ has "agents/handover-doc-writer.md" 'model: sonnet'
|
||||
lacks "agents/handover-doc-writer.md" 'AskUserQuestion'
|
||||
lacks "agents/handover-doc-writer.md" 'Agent('
|
||||
has "agents/client-handover-writer.md" 'subagent_type="handover-doc-writer"'
|
||||
# 10) post-merge edge fixes (ronde): F1 feater applier carve-out, F2 /refactor
|
||||
# dispatch + pin, F3 /analyze gated (in loop 1), F4 interviewer un-pinned,
|
||||
# F5 audit agents' ABSENT pin locked (a stray sonnet pin would silently
|
||||
# downgrade a live audit even though the skill's gate passed)
|
||||
has "agents/feater.md" 'Applier path'
|
||||
has "skills/refactor/SKILL.md" 'subagent_type="refactorer"'
|
||||
has "agents/refactorer.md" 'model: sonnet'
|
||||
fm_lacks "agents/seo-analyzer.md" 'model:'
|
||||
fm_lacks "agents/geo-analyzer.md" 'model:'
|
||||
fm_lacks "agents/validator-analyzer.md" 'model:'
|
||||
fm_lacks "agents/client-handover-writer.md" 'model:'
|
||||
fm_lacks "agents/interviewer.md" 'model:'
|
||||
|
||||
printf 'model-routing census: %d pass, %d fail\n' "$pass" "$fail"
|
||||
[ "$fail" -eq 0 ]
|
||||
|
||||
@@ -5,6 +5,10 @@ argument-hint: <file/area to analyze — OR paste error/stack trace for DEBUG mo
|
||||
allowed-tools: Read, Grep, Glob, Bash
|
||||
---
|
||||
|
||||
MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE anything
|
||||
below. Verdict `small` → STOP — print the gate's remedy, end the turn, run
|
||||
no analysis. Deep factual analysis is reflection; it needs the big model.
|
||||
|
||||
Load and follow strictly:
|
||||
- $HOME/.claude/agents/analyzer.md
|
||||
|
||||
|
||||
@@ -2,11 +2,19 @@
|
||||
name: refactor
|
||||
description: 'Improve code quality without changing behavior — strict norm enforcement, targeted scope (file/module). Full-codebase audit+cleanup → /code-clean. Triggers: "refactor", "clean up code", "normaliser".'
|
||||
argument-hint: <file, function, or module to refactor>
|
||||
allowed-tools: Read, Write, Edit, Grep, Glob, Bash
|
||||
allowed-tools: Read, Write, Edit, Grep, Glob, Bash, Agent
|
||||
---
|
||||
|
||||
Load and follow strictly: `$HOME/.claude/agents/refactorer.md`.
|
||||
Dispatch the refactorer executor — behavior-preserving norm application is
|
||||
closed execution, so it runs pinned on **sonnet** (not the big session
|
||||
model). The scope you name is the only reflection; the agent applies norms.
|
||||
|
||||
If unreachable, emit `Refactorer agent missing.` and STOP. Never improvise — silent behavior change is unsafe.
|
||||
```
|
||||
Agent(subagent_type="refactorer")
|
||||
prompt: "Refactor to strict project norms, preserving external behavior
|
||||
exactly (zero behavioral regression, existing tests must pass). Target:
|
||||
$ARGUMENTS"
|
||||
```
|
||||
|
||||
$ARGUMENTS
|
||||
If the refactorer agent is unavailable, emit `Refactorer agent missing.` and
|
||||
STOP — never improvise, silent behavior change is unsafe.
|
||||
|
||||
Reference in New Issue
Block a user