forked from bchanot/claude
4.8 KiB
4.8 KiB
PLAN — advisor-doctrine (BDR-150 follow-up)
APPROACH
- CLAUDE.global.md § Workflow: insert as a new bullet right after the "Sub-agents: one task each…" bullet, wrapped ≤ 80 columns, the user's text verbatim: "- Stronger model needed (an approach to settle before building, a stuck problem, a long task before calling it done) → call the advisor tool when it is listed (Fable, set by /advisor). Fable is never routed or pinned: the router tops out at opus (BDR-150)."
- lib/effort-shift.md:
a. wiring point 5: "(
general-purposemodel="opus",model: "opus"skill-runners) → expliciteffort=on the Agent call (xhighfor opus reviewers,highfor skill-runners)." Rest unchanged. b. Limits bullet: "…set the turn's effort only, never a model above the session model: Fable on main comes only from a hand pick (/model, picker), a typed/route model=fableor a machine override that puts fable in a tier (no shipped tier holds it, BDR-150)." c. ask-tier mention (~:92-94): "/route ask-tier off|onthe ask before a route lifts main or a rowed agent onto Fable (inert unless a machine override headsbestwith fable)". d. new section "## Advisor" placed before "## Never" (or before "## Limits" if "## Never" is absent), ≤ 8 lines: Fable runs as the advisor (settingsadvisorModel), never a route or pin target (BDR-150). Call it before committing to an approach on non-trivial work, when stuck (theescalatemoment, before raising effort to max), and before declaring a long task done. It is a server tool: the router cannot see or refuse it. The main loop calls it; do not assume a sub-agent has it. - lib/challenge-plan.md ~:48 "(Fable through its best-tier row)" → "(opus
through its best-tier row)"; ~:51 "the two merge gates sit on the
auditrow, Fable with an opus floor" → "… on theauditrow, opus". - agents/plan-challenger.md ~:111 "on Fable through its best-tier row" →
"on opus through its best-tier row"; ~:115 "sit on the
auditrow, Fable with an opus floor" → "sit on theauditrow, opus". - skills/tour/SKILL.md ~:83 "security-auditor (
auditrow: Fable, opus floor)" → "security-auditor (auditrow: opus)".
EDGE CASES
- Do not touch lib/effort-shift.md's /model dialog paragraph (fable is still offered there by hand, true).
- doctrine-citers census in make test: headings cited elsewhere must stay intact; adding "## Advisor" changes no existing heading.
DISPOSITION
Honors BDR-150 (Fable = advisor, never routed or pinned) and the user's 2026-11-16 wording choices. Amends nothing else.
FILES
CLAUDE.global.md, lib/effort-shift.md, lib/challenge-plan.md, agents/plan-challenger.md, skills/tour/SKILL.md.
r2 (challenge r1: correctness CONCERNS(1), robustness CONCERNS(1), simplicity CONCERNS(1)) — amends APPROACH; final
User answers 2026-11-17: only the main loop calls the advisor (sub-agents have the tool listed too: every challenger, gate and executor would send its whole transcript to Fable outside the router's caps); add the fallback "advisor absent or erroring → proceed as written"; wiring point 4 unchanged.
- CLAUDE.global.md § Workflow, new bullet right after the "Sub-agents: one task each…" bullet, text (user line, amended by the main-loop answer): "- Stronger model needed (an approach to settle before building, a stuck problem, a long task before calling it done) → the main loop calls the advisor tool when it is listed (Fable, set by /advisor); sub-agents do not. Fable is never routed or pinned: the router tops out at opus (BDR-150)." Wrap ≤ 80 columns like the neighbouring bullets (2-space continuation); the phrase "the advisor tool" stays on one line.
- lib/effort-shift.md:
a. wiring point 5 as in APPROACH 2a.
b. Limits: "Fable on main comes only from a hand pick (
/model, picker), a typed/route model=fable, a phase namingmodel: fableor a machine override that puts fable in a tier (no shipped tier or phase holds it, BDR-150)." Keep "a typed/route model=fable" on one line. c. ask-tier as in APPROACH 2c; keep "inert unless a machine override" on one line. d. "## Advisor" placed right before "## Never": the APPROACH 2d text, with "The main loop calls it; sub-agents do not, even when the tool is listed. Advisor absent or erroring (Fable out of credits, for example) → proceed as written." 3-5. As APPROACH 3-5. agents/plan-challenger.md: the second target spans lines 115-116 ("…sit on theauditrow, Fable with an" / "opus floor.)"): replace across both lines → "…sit on theauditrow, opus.)". - Rollback: the five files are live machine-wide from the working tree;
if anything misbehaves,
git checkout develop -- <the 5 files>. Do not run gates mid-edit.