From b3d17a140edb7770904e3219541d15b427dc484e Mon Sep 17 00:00:00 2001 From: garrytan Date: Sun, 8 Nov 2026 05:32:34 +0000 Subject: [PATCH] Ask Capy lane reports and replies to open with what failed, was skipped or is unverified (GST-1455) factory.md point 10 asks reports and replies to open with Failed or skipped: and Unverified: lines, under 200 words, top 10 plus an offer past 10 items (3,447 -> 3,596 B; the page budget rises to 3,600). The lane report's Outcome and the READY lane lines gain a Failed or skipped: line; the existing Unverified: lines stay where the controller reads them. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- captain/templates/READY.md | 1 + captain/templates/report.md | 2 +- capy/skill/gstack/factory.md | 2 +- test/capy-skill-wrapper.test.ts | 7 ++++--- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/captain/templates/READY.md b/captain/templates/READY.md index 221b1f538..002d59948 100644 --- a/captain/templates/READY.md +++ b/captain/templates/READY.md @@ -36,6 +36,7 @@ The lane's own lines, after the block: ```text pin: # the full head SHA, restated +Failed or skipped: screen choice: <--no-screen: cases ran focused and passed | --screen: > flaky: > review passes: (deferred: ) diff --git a/captain/templates/report.md b/captain/templates/report.md index 13c0319d9..ac2f8b2c4 100644 --- a/captain/templates/report.md +++ b/captain/templates/report.md @@ -4,7 +4,7 @@ Written by the lane when it finishes. The controller reads this before chat. ## Outcome - + Unverified: diff --git a/capy/skill/gstack/factory.md b/capy/skill/gstack/factory.md index e7db9c720..bfb2fc395 100644 --- a/capy/skill/gstack/factory.md +++ b/capy/skill/gstack/factory.md @@ -11,7 +11,7 @@ What seven Captain crews agreed on. Your crew's CREW.md and recorded approvals d 7. **Measure before you act.** Run the real system on the merged tree you ship; a real run outranks a reviewed plan. Each number names its run, commit or uncapped query; say what you did not verify. 8. **Evals decide, and losses get reported.** Preregister bars, cap and stop rule before paying [/eval-plan]. Cheap proof (a keyless fake, a smoke) first. Controls: no-skill and placebo arms, clean decoys. Report use and pass apart; quote spend from the meter. A new part needs proof it helps or a dated test plan [ETHOS.md: 9. Earn Its Place]. 9. **Flakes: one rerun, a ledger, a daily fix.** Only the policy's rerun, never for a harness or infra red; a second red is real; never loosen a test. [docs/captain.md: The daily flaky pass] -10. **Quiet.** Message on a decision, a blocker, a READY or a finished phase. A broadcast needing no reply goes in the Captain's notes; never reply just to acknowledge. +10. **Quiet.** Message on a decision, a blocker, a READY or a finished phase. Reports and replies open with `Failed or skipped:` and `Unverified:` lines (each item or none), under 200 words; past 10 items, top 10 and an offer. A broadcast needing no reply goes in the Captain's notes; never reply just to acknowledge. 11. **Ask once, plainly.** One ask per decision, explained like the owner is five: your Captain's name, then a lettered line each: "A: hit problem p, which happens when h. We could do 1) x, 2) y or 3) z. Recommendation x because why. A1 to take recommendation." "do it" takes every recommendation; "A2" takes option 2. Owner tasks: the exact link (in Capy: path and field), numbered steps, the reply word. Never re-ask a standing rule; check what you can yourself. [docs/captain.md: The ask format] 12. **Fresh threads, closed out.** One thread per unit of work; past 500M tokens, rotate [/runaway-stopper]. Crew threads never create threads: ask your Captain (Captain to Captain across projects), or report one you made by code for crew.add. Its Captain archives only its crew's threads; threads outside every crew are the owner's, even its automation's. Size reviews to the diff; read the meter. [docs/ship-budget.md; docs/captain.md: New threads join the crew] 13. **The owner's model preference.** `gstack-models resolve --role agent` picks agent models, except cross-family voices and eval subjects. [docs/model-policy.md: Your model preference] diff --git a/test/capy-skill-wrapper.test.ts b/test/capy-skill-wrapper.test.ts index e35bf2d98..4d2936c08 100644 --- a/test/capy-skill-wrapper.test.ts +++ b/test/capy-skill-wrapper.test.ts @@ -639,11 +639,12 @@ describe('capy skill: factory.md, the auto-loaded "how we work" page', () => { return [...new Set(problems)]; } - test('it fits the 3,450-byte budget, and every citation, heading and skill it names resolves', () => { + test('it fits the 3,600-byte budget, and every citation, heading and skill it names resolves', () => { const text = fs.readFileSync(FACTORY, 'utf8'); // 3,300 since #3634; raised to 3,450 (the page's new size, rounded up to the next 25 bytes) for point 12's - // R68 clause (Garry, 2026-11-03: crew threads ask their Captain for new threads). Raise it only by what a rule needs. - expect(Buffer.byteLength(text)).toBeLessThanOrEqual(3450); + // R68 clause (Garry, 2026-11-03: crew threads ask their Captain for new threads). Raised to 3,600 for point 10's + // GST-1455 report shape (Garry, 2026-11-05: "do it"). Raise it only by what a rule needs. + expect(Buffer.byteLength(text)).toBeLessThanOrEqual(3600); expect(text).toMatch(/^# How we work/); expect(citationProblems(text)).toEqual([]); });