forked from bchanot/claude
chore(memory): feat B BDR-123, TODO, journal, plan and contract
This commit is contained in:
1 parent
887cf89004
commit
9e0deccbb0
6 files changed
+123
-2
No files matched your search
@@ -0,0 +1,35 @@
|
||||
# PLAN r3 — routing-ceiling-rule (feat B, BLK-032 routing policy)
|
||||
|
||||
r2 after the 2026-10-21 challenge (correctness CONCERNS, robustness FATAL, simplicity SOLID): dispatch target named (/feat or /bugfix, user pick), inline-writing best-tier skills deferred in BDR-123 (user pick), deploy `changed` entry dropped, challenge-plan.md:48 citer, README enforcement clause anchored, oracles 3/6/7 tightened, bullet-old artifact dropped. r3 after round 2: keyword-rule lift to Fable named as a known gap closed by feat C (user pick), exception list completed, mirror citers (plan-challenger.md:111, README.md:95) patched, challenge-plan.md phrase pair, oracle 6 fixed, router-internal line refs trimmed.
|
||||
|
||||
Contract: `.claude/tasks/contracts/2026-10-21-routing-ceiling-rule-1753.md`
|
||||
|
||||
## Why
|
||||
Feat A (merged b961ce6) moved the session model to `opus` and the gates to the `audit` row. BLK-032's last open point: a doctrine ceiling so main on Fable (reached through best-tier rows: plan/reflect/orchestrate/escalate) never writes code inline beyond a hotfix edit. Today CLAUDE.global.md:49-51 lets main do "work doable in a few tool calls" inline, and BDR-115 says a pin is "never ceiling". README still describes the pre-feat-A doctrine (l.17, l.72-73).
|
||||
|
||||
## Checklist (dispatch-ready)
|
||||
[ ] CLAUDE.global.md:49-58 — replace the 10-line Sub-agents bullet (old text: `git show develop:CLAUDE.global.md | sed -n 49,58p`) with the 10-line text of `.claude/tasks/plans/2026-10-21-routing-ceiling-rule-1753.bullet.txt`, byte for byte (copy the file content, do not retype). Nothing else in the file.
|
||||
[ ] README.md:15-17 — replace "(haiku collects, sonnet executes,\n opus judges, the session model only reflects)." with "(haiku collects, sonnet executes,\n opus judges and runs the session, Fable plans and runs the merge gates)." Reflow the bullet to ≤80 columns, 2-space continuation indent.
|
||||
[ ] README.md:72-73 — replace "Doctrine: the session model (Fable) does main-loop reflection ONLY —\nbrainstorm, plan, contract, audit judgment, gates, loop decisions — enforced" with "Doctrine: the main loop runs on the `opus` session model; the model-router rows lift it to Fable for main-loop reflection ONLY: brainstorm, plan, contract, audit judgment, loop decisions. On Fable it writes no code past the `/hotfix` scope; the fresh gates run as dispatched agents on the `audit` row. The Fable/Opus model floor is enforced" and reflow the paragraph to the file's width (≤80) up to the next sentence boundary; the rest of the paragraph ("by a blocking gate (`lib/model-gate.md`) at the entry of the 17 reflection skills…") stays word for word.
|
||||
[ ] skills/deploy/SKILL.md frontmatter — `effort: low` → `effort: xhigh` (row `verify` = work/xhigh since the d3635b6 dialog write; the census then drops its WARN floor drift).
|
||||
[ ] mods/model-router/routing.json — delete the `changed.skills.deploy` entry (`{"from": "apply", "to": "verify"}`), leaving `"changed": {}`; keep `skills.deploy = "verify"` and `confirmed.skills.deploy = "verify"`. Why: once the floor follows the row, `verify` is the shipped state; a stale `from: apply` would make `/route forget deploy|all` restore `apply` (register.ts:2629-2631) against an `xhigh` floor with no `changed` entry → census hard FAIL.
|
||||
[ ] lib/challenge-plan.md:47-48 — replace the phrase pair "off\nthe session model. The session model (Fable)\nkeeps only this loop" with "off\nthe main loop. The main loop (Fable through its best-tier row)\nkeeps only this loop"; reflow ≤80 columns, the rest of the paragraph word for word.
|
||||
[ ] agents/plan-challenger.md:111 — "(big tier; the session model stays on the inline loop)" → "(big tier; the main loop, on Fable through its best-tier row, stays inline)". Reflow ≤80 columns.
|
||||
[ ] README.md:95 — "| interviewer, client-handover-writer | unpinned (inline-load = session model) |" → "| interviewer, client-handover-writer | unpinned (inline-load = the main loop's model) |"; rest of the row unchanged.
|
||||
[ ] run: full `make test` (single-suite runs only as a fail-fast before it); then the contract oracles.
|
||||
|
||||
## Edge cases
|
||||
- The ceiling binds main on Fable only. Main reaches Fable three ways: a best-tier skill row (incl. /hotfix, /feat, /bugfix on `reflect`), which holds for the run and the turns after it until `/route clear`, `/route off`, a user `/model` or a typed skill on another tier; a `route(phase=…)` call, whose answer names the model; a default keyword prompt rule (`plan|design|architecture…` → plan, `why|review|audit|analyze…` → reflect, `ultrathink` → escalate), which lifts one turn and tells main nothing (the status line is terminal UI only). [known gap, user pick 2026-10-21] The keyword path leaves the ceiling unwitnessed; feat C caps the keyword rules at the session model (effort only, like the classifier), after which every lift to Fable comes with a route answer. BLK-032 closes after feat C, not here.
|
||||
- [deferred 2026-10-21, user pick] Best-tier skills that write code inline and dispatch no executor conflict with the ceiling: the design Build stack (frontend-design, 21st-ui-build, emil-design-eng, design-motion-principles Create mode, site-motion, build-threejs-scroll-worlds, scroll-*, 21st-ai, on `reflect`; CLAUDE.global.md "Design work" sends every Build UI past 2 files there), writing-skills, deprecation-and-migration (`reflect`), /tour single-project fixes and /audit-delta STEP 3d (`plan`), /harden STEP 3 bundle apply (`reflect`). BDR-123 names them as a declared temporary exception; a later run remaps them or makes them dispatch. The exception lives in this repo's registry only: sessions in other projects see the two always-on rules (Design work, Sub-agents) collide with no visible carve-out. TODO line at capitalize.
|
||||
- Fable held down: opus stands in on best-tier phases with effort one notch up; the ceiling (keyed on Fable) does not bind then. Accepted residual, named in BDR-123.
|
||||
- Dispatch target: /feat or /bugfix (pinned sonnet executors, contract, gates). A bare `general-purpose` spawn would inherit Fable (no row; the router pins it only when main sits below the session model).
|
||||
- Live doctrine: `~/.claude/CLAUDE.md` is a symlink to the working-tree CLAUDE.global.md; the edit is live machine-wide from the executor's write, for every new session. Rollback before merge: `git checkout develop`.
|
||||
- `/hotfix` scope reference: CLAUDE.global.md:80 defines it ("≤2 files, obvious fix"); the rule cites it instead of repeating it (budget).
|
||||
- No skill/agent/lib file quotes the Sub-agents sentences (grep 2026-10-21: no citer of "few tool calls", "Skill-mandated", "whatever the task size"). The session-model claim has three live citers, all patched above: lib/challenge-plan.md:47-48, agents/plan-challenger.md:111, README.md:95. skills/feat/SKILL.md:6 and skills/code-clean/SKILL.md:36 ("session model" for inline reflection) are named in BDR-123 as stale, left for the feat C run that touches routing wording.
|
||||
- "main context stays clean" dropped from the bullet to fit 320 lines: rationale of "one task each", no rule lost.
|
||||
|
||||
## Disposition
|
||||
- BDR-066 [in force, partial supersede by BDR-123 at capitalize]: "reflection inline on session model (Fable)" → session model is opus; Fable reached by rows; ceiling added. Executors sonnet unchanged.
|
||||
- BDR-115 [in force, partial supersede]: "pin = default, never ceiling" stays for agent pins; the main loop on Fable gets a doctrine ceiling on WRITING code (a behavioural rule, not a router cap).
|
||||
- BDR-085 / density budget 320 → honored (contract 2).
|
||||
- LRN-224 → no gate wording changes here.
|
||||
Reference in new issue
Block a user