forked from bchanot/claude
chore(model-routing): wave-4 census + docs + BDR-066 (client-handover doc-gen → sonnet)
This commit is contained in:
Bastien Chanot
@@ -990,4 +990,5 @@ rules:
|
||||
- **Caveat (execution)**: /feat re-arch broke 5 stale assertions in lib/tests/loops-light.test.sh (locked OLD feater architecture) — repointed to skills/feat/SKILL.md (FSK, mirrors HOT/HSK split) + new dispatch lock + 1-line reflow in feat SKILL for single-line grep lock (LRN-093 class).
|
||||
- **Wave 2 (2026-07-15, user directive)**: wave-1 exclusion list left execution running on the big session model = the waste this split kills. REVERSES the "split hotfix rejected" alternative above (reason held for bugfix — investigation interleaved w/ fix — but NOT hotfix: LOCATE→apply is linear/separable). Changes: /hotfix split like /feat (LOCATE reflection inline + MODEL GATE, hotfixer sonnet EXECUTOR — rewritten dual-use: also the seo/geo/web-validate L1 applier; revert-not-loop preserved) → hotfix JOINS gated group, census 12→13. /commit-change dispatches sonnet commit-changer (propose→dispatcher gates→apply; grouping ON sonnet so NO model gate; AskUserQuestion dropped from agent). /release-candidate dispatches new sonnet release-executor (2 spans prep/finish; when-to-release + push + version-number decision STAY in dispatcher). /doc → doc-syncer (sonnet) dispatch; /status → status-reporter (kept HAIKU — right tier for read-only collection; win = off big model, not the tier). Gate exclusion list now = commit-change/doc/status/release-candidate. Consumer-staleness swept (LRN-113): feat Rule 1 DOWNGRADE + feat commit-split both repointed off the bare executor agents to the /hotfix + /commit-change skills.
|
||||
- **Wave 3 (2026-07-15/16, user directive)**: split the last two inline execution-carrying agents like /feat. /bugfix: investigation+diagnosis+contract inline behind the gate; bugfixer = sonnet EXECUTOR (fix + regression test from a closed FIX PLAN; no Agent/AskUserQuestion; BUGFIX-EXEC REPORT). verify+secure loop stays in main loop, executor = its re-dispatched dev (verify-secure-loop.md intro now: BOTH consumers dispatched, no inline branch). FINISHES reversing the "split bugfix rejected" carve-out (hotfix went wave 2, bugfix now) — investigation↔fix coupling accepted, mitigated by structured DIAGNOSIS + verify loop. /code-clean: PHASE-1 audit + validation gate inline (reflection); code-cleaner = sonnet PHASE-2 EXECUTOR (delete approved dead code, inline-load refactorer, re-audit) — refactor NOW on sonnet (inline-load pin was inert on big model). exported-symbol per-item consent stays AT THE GATE. Consumer-staleness swept: hotfix deeper-bug escalation → /bugfix skill (not bare agent); onboard STEP 6 + tour Phase B read-only-audit → general-purpose/analyzer (big model, NEVER the sonnet executor — audit stays big). Both skills STAY gated. Also: Explore built-in kept inheriting session (search feeds reflection = big deserved; custom sonnet override created then reverted — built-in already inherits + no owned prompt). census 36→42, loops-light repointed 35/0.
|
||||
- **Reference**: spec `docs/superpowers/specs/2026-07-15-model-routing-design.md` + plan `docs/superpowers/plans/2026-07-15-model-routing.md` (transient, BDR-065 lifecycle), branch `feature/model-routing`.
|
||||
- **Wave 4 (2026-07-16)**: client-handover doc-gen → sonnet, REDACTION-ONLY (user flipped from whole-writer after the full read). Key finding: nested audits (/seo,/harden,/web-validate — gated wave 1) must run BIG either way → whole-writer = ~7 extra gate-yields + resumable state machine on a CLIENT deliverable for ~0 extra sonnet work. Design: client-handover-writer TRIMMED to ship pipeline (STEP 1-8, all interactive gates native on big, nested audits inherit big) + doc-gen orchestration (resolve questions/NAP/precheck/overwrite/client-name inline → PACKAGE) → dispatches NEW sonnet handover-doc-writer (STEP 9-16: reads memory+git, synthesizes 6-chapter doc, word-count/skill-leak/anchor gates, renders HTML+PDF; GATE-FREE, no AskUserQuestion/Agent). client-handover JOINS gated group (orchestrates audits = reflection); its opus pin dropped (inherits big via inline-load). census 42→46. Branch feature/client-handover-dispatch (off develop, waves 1-3 merged first).
|
||||
- **Reference**: spec `docs/superpowers/specs/2026-07-15-model-routing-design.md` + plan `docs/superpowers/plans/2026-07-15-model-routing.md` (transient, BDR-065 lifecycle), branches `feature/model-routing` (waves 1-3, merged), `feature/client-handover-dispatch` (wave 4).
|
||||
|
||||
@@ -386,3 +386,4 @@ rules:
|
||||
- model routing shipped on feature/model-routing: BDR-066 (reflection inline big / executors sonnet / blocking gate), /feat re-arch, census guard. client-handover conversion deferred to plan 2.
|
||||
- model routing WAVE 2 (same branch, user directive): doc/status dispatch their agent (sonnet/haiku pins effective); /hotfix split like /feat (joins gated group 12→13, hotfixer dual-use executor); /commit-change → sonnet commit-changer (propose/apply, gates relocated); /release-candidate → sonnet release-executor (human gates + version decision kept in dispatcher). Consumer-staleness swept (feat Rule 1 + commit-split). census 36/0, make test green. Branch still unmerged.
|
||||
- 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.
|
||||
|
||||
@@ -28,7 +28,7 @@ unmerged — human gate.
|
||||
code-cleaner = PHASE-2 exec (refactor now runs on sonnet — inline-load pin
|
||||
was inert). Both skills STAY gated. census wave-3 + loops-light repoint
|
||||
(guarded). Supersedes BDR-050 bugfix carve-out.
|
||||
- [ ] WAVE 4 — client-handover (branch feature/client-handover-dispatch, off
|
||||
- [x] WAVE 4 — client-handover (branch feature/client-handover-dispatch, off
|
||||
develop). Shape FLIPPED to REDACTION-ONLY (full read: nested audits must
|
||||
run big either way since /seo,/harden,/web-validate are gated → whole-writer
|
||||
buys ~0 extra sonnet work for ~7 extra gate-yields). Design: parent
|
||||
|
||||
@@ -17,6 +17,7 @@ Format follows [Keep a Changelog](https://keepachangelog.com/).
|
||||
- web-validate `--fix`: bundle applied via `hotfixer` at L1 instead of inline Edit (BDR-061 alignment).
|
||||
- Model routing wave 2 — the pure-execution + reflection-split skills stop running execution on the big session model. `/doc` and `/status` now **dispatch** their agent (doc-syncer sonnet, status-reporter haiku) instead of inline-loading it, so the pin takes effect. `/hotfix` split like `/feat`: reflection (LOCATE root cause) inline behind the model gate, the fix applied by a `hotfixer` sonnet executor (rewritten dual-use — it is also the seo/geo/web-validate L1 applier); revert-not-loop preserved; hotfix joins the gated group (13th). `/commit-change` dispatches a sonnet `commit-changer` (propose → dispatcher-owned approval gates → apply; grouping runs on sonnet, `AskUserQuestion` removed from the agent). `/release-candidate` dispatches a new sonnet `release-executor` for the mechanical spans (prep / finish+tag), the two human gates (when-to-release, push) and the version-number decision staying in the dispatcher.
|
||||
- Model routing wave 3 — the last two inline execution-carrying skills split like `/feat`. `/bugfix`: root-cause investigation, diagnosis and contract run inline behind the model gate; the fix + regression test are applied by a `bugfixer` sonnet executor (was a single inline agent), with the verify+secure loop staying in the main loop and the executor as its re-dispatched dev. `/code-clean`: the dead-code / style / structural audit and the approval gate run inline; a `code-cleaner` sonnet PHASE-2 executor then applies the approved scope — and the style/structural refactor (which inline-loads `refactorer`) now finally runs on sonnet, its pin having been inert under the old inline-load. Both skills stay gated (they keep reflection); their read-only-audit consumers (`onboard`, `tour`) reroute to a big-model agent so an audit never runs on the sonnet executor. Supersedes the BDR-050 "bugfix stays inline" carve-out. The built-in `Explore` search agent is deliberately left inheriting the session (search feeds reflection).
|
||||
- Model routing wave 4 — client-handover doc-generation moved to sonnet (redaction-only). The ship-and-handover pipeline (baseline audits, fix loops, commit/push, deploy pause, live validate, gate) stays inline on the big session model in `client-handover-writer` — its interactive gates work natively and its nested `/seo`/`/harden`/`/web-validate` audits inherit the big model — and only the deliverable writing is delegated to a new sonnet `handover-doc-writer` (gate-free: reads memory + git, synthesizes the 6-chapter doc from a resolved PACKAGE, runs the word-count / skill-leak / anchor gates, renders branded HTML+PDF). `client-handover` joins the gated group (it orchestrates audits = reflection). Chosen over the whole-writer dispatch: the nested audits must run big either way, so whole-writer would have added ~7 gate-yields + a resumable state machine on a client deliverable for ~zero extra sonnet work.
|
||||
|
||||
### Security
|
||||
- **Magic MCP fully ask-gated** — all four `mcp__magic__*` tools (builder, refiner, inspiration, logo_search) moved to `permissions.ask` in `settings.json`; no magic call can auto-execute. The builder opens an unauthenticated local callback server (`127.0.0.1:9221+`, `Access-Control-Allow-Origin: *`, no token check) whose POST body is injected verbatim into the tool result the model consumes — the ask-gate is the mitigation on our side (BDR-059).
|
||||
|
||||
@@ -51,8 +51,8 @@ reflection orchestrators. Execution runs on pinned subagents:
|
||||
| commit-changer, release-executor, code-cleaner | sonnet (pinned) | dispatched execution — grouping+commit / release spans / approved cleanup (the audit + approval gate stay in the dispatcher) |
|
||||
| doc-syncer, onboarder, scaffolder, refactorer, interviewer, plugin-advisor | sonnet (pinned) | workers |
|
||||
| status-reporter | haiku (pinned) | mechanical collector |
|
||||
| client-handover-writer | opus (pinned, currently inert — inline-loaded; sonnet conversion planned) | deliverable writer |
|
||||
| analyzer, seo-analyzer, geo-analyzer, validator-analyzer | inherit session (Fable/Opus) | reflection / audit / inline playbooks |
|
||||
| handover-doc-writer | sonnet (pinned) | deliverable writer — synthesizes + renders the client doc from a resolved PACKAGE (dispatched by client-handover) |
|
||||
| analyzer, seo-analyzer, geo-analyzer, validator-analyzer, client-handover-writer | inherit session (Fable/Opus) | reflection / audit / inline playbooks / ship-and-handover pipeline |
|
||||
| Explore (built-in) | inherit session (Fable/Opus) | search feeds reflection — kept on the big model, not pinned down |
|
||||
|
||||
The pure-execution skills `/doc`, `/status`, `/commit-change`,
|
||||
|
||||
@@ -9,8 +9,8 @@ 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: $2"; else ok; fi; }
|
||||
|
||||
# 1) gate wired in the 13 reflection orchestrators
|
||||
for s in ship-feature init-project feat bugfix onboard seo geo web-validate harden audit-delta tour code-clean hotfix; do
|
||||
# 1) gate wired in the 14 reflection orchestrators
|
||||
for s in ship-feature init-project feat bugfix onboard seo geo web-validate harden audit-delta tour code-clean hotfix client-handover; do
|
||||
has "skills/$s/SKILL.md" 'lib/model-gate.md'
|
||||
done
|
||||
# 2) gate NOT wired in the excluded skills (encodes the spec exclusion list)
|
||||
@@ -48,6 +48,10 @@ lacks "agents/bugfixer.md" 'AskUserQuestion'
|
||||
has "skills/code-clean/SKILL.md" 'subagent_type="code-cleaner"'
|
||||
has "agents/code-cleaner.md" 'model: sonnet'
|
||||
lacks "agents/code-cleaner.md" 'AskUserQuestion'
|
||||
# 9) wave-4 — client-handover: pipeline (big) inline + gated, doc-gen dispatched to sonnet
|
||||
has "agents/handover-doc-writer.md" 'model: sonnet'
|
||||
lacks "agents/handover-doc-writer.md" 'AskUserQuestion'
|
||||
has "agents/client-handover-writer.md" 'subagent_type="handover-doc-writer"'
|
||||
|
||||
printf 'model-routing census: %d pass, %d fail\n' "$pass" "$fail"
|
||||
[ "$fail" -eq 0 ]
|
||||
|
||||
Reference in New Issue
Block a user