Skip to content

v1.94.29.0 R56: everything in gstack earns its place (principle, evidence gates, inventory) - #3837

Merged
capy-ai[bot] merged 20 commits into
mainfrom
garrytan/r56-earns-its-place
Nov 3, 2026
Merged

capy-ai[bot] merged 20 commits into
mainfrom
garrytan/r56-earns-its-place

Conversation

@garrytan

@garrytan garrytan commented Nov 2, 2026 •

Copy link
Copy Markdown
Owner
{
  "schema_version": 1,
  "pr": 3837,
  "head": "95437450181f96348f907fae37c9d91783b3ced2",
  "version": "1.94.24.0",
  "base": "main",
  "gate": {
    "r56": {
      "pass": 131,
      "fail": 0,
      "skip": 0
    },
    "guards": {
      "pass": 43,
      "fail": 0,
      "skip": 0
    }
  },
  "session_kind": "unattended",
  "head_tree": "20527036a29e4a5111de8fde20cc91e80aa66694",
  "product_patch_id": "065e28760485f844c8b593467b81168c3811e5c7",
  "gstack_version": "1.92.61.0",
  "review_depth": {
    "depth": "full",
    "class": "code",
    "runtime_lines": 1139,
    "rules": "19881e1ecf7ed1ad",
    "base": "1ccab0d8bccba50e69587672fb82ac0574638a65",
    "registry": "1ccab0d8bccba50e69587672fb82ac0574638a65",
    "gate_scan": {
      "tagged": 0,
      "head": "95437450181f96348f907fae37c9d91783b3ced2"
    },
    "reasons": [
      "risk:money",
      "risk:security",
      "risk:data",
      "runtime=1139"
    ],
    "risk": [
      "money",
      "security",
      "data"
    ]
  },
  "pregate": "requires-remote cleared @20527036a29e (7 checks, current for 95437450181f)",
  "requires_remote": [
    "free-tests.yml/cso-macos-launcher: https://github.com/garrytan/gstack/actions/runs/41667257219/attempts/1",
    "free-tests.yml/macos-named-regressions: https://github.com/garrytan/gstack/actions/runs/41667257219/attempts/1",
    "windows-smoke.yml/windows-smoke: https://github.com/garrytan/gstack/actions/runs/41667257365/attempts/1",
    "pregate.json/remote_gate: remote-gate tree=20527036a29e tests=34971 skipped=113 runs=41667257219/1 profiles=ci-reuse/free-tests heads=95437450181f verified=2026-11-03T15:58:55.377Z"
  ],
  "issues": {
    "fixes": [],
    "refs": [],
    "flakes": []
  },
  "docs": {
    "status": "current",
    "scope": "README.md, docs/, ETHOS.md, CONTRIBUTING.md, eval-plan, write-skill and autoplan CEO-phase templates, capy/skill/gstack/factory.md (32 committed files dd9834d44..38cf87685, re-audit after the base merge)"
  },
  "review_loop": {
    "passes": 2,
    "blocking_found": 0,
    "deferred": 0,
    "noted": 11,
    "fixed": 0,
    "scope": "frozen",
    "fix_checks": 3,
    "rounds": 5,
    "dispatches": {
      "specialist": 6,
      "red-team": 2
    }
  },
  "review_loop_exception": {
    "accepted_by": "GStack Minder (Captain, GSTA-36)",
    "date": "2026-11-02",
    "via": "Captain ruling on #3837 relayed by the lane parent (rule 23)",
    "reason": "option A: one fix batch for review items 1-6, each with a test, plus one scoped fix-check; item 7 filed as GST-939; anything new at the floor ships as an open note",
    "fix_check": {
      "head": "a58377870e20aa1ba2f13025689a538d03d47393",
      "findings": 0,
      "files": [
        "lib/inventory.ts",
        "bin/gstack-inventory",
        "test/inventory.test.ts",
        "test/skill-bill.test.ts"
      ]
    }
  },
  "review_targeted": {
    "classes": [
      "money",
      "gate"
    ],
    "rules": "baeb8f7ef7da92d0",
    "brief_sha": "7f92a0d0a8319c3c0e076fb3b1a4689c45120b2be2c14dfc7d4cb03aafa9d6a5",
    "product_patch_id": "12e4af425ae2b7923fa49496f568fdadaae8ee76",
    "status": "done",
    "findings": 2,
    "raised_by": "targeted"
  },
  "carry": {
    "from": "38cf876850078b67f7a78ad9de7c8539342125b5",
    "reason": "base merge + test-only change + release metadata",
    "product_patch_id": "065e28760485f844c8b593467b81168c3811e5c7",
    "changed_paths": [
      "product:.github/docker/Dockerfile.ci",
      "product:.github/workflows/free-tests.yml",
      "product:.github/workflows/windows-free-tests.yml",
      "product:.gstack/pregate.json",
      "product:BROWSER.md",
      "metadata:CHANGELOG.md",
      "product:CLAUDE.md",
      "product:CONTRIBUTING.md",
      "product:README.md",
      "product:TODOS.md",
      "product:USING_GBRAIN_WITH_GSTACK.md",
      "metadata:VERSION",
      "metadata:agents-digest/gstack-AGENTS.md",
      "product:autoplan/DRIVER.md",
      "product:autoplan/DRIVER.md.tmpl",
      "product:autoplan/SKILL.md",
      "product:autoplan/shadow-decider.md",
      "product:bin/gstack-artifact",
      "product:bin/gstack-autoplan",
      "product:bin/gstack-capy-install",
      "product:bin/gstack-checks",
      "product:bin/gstack-clean",
      "product:bin/gstack-codex-probe",
      "product:bin/gstack-codex-session-import",
      "product:bin/gstack-config",
      "product:bin/gstack-developer-profile",
      "product:bin/gstack-diff-scope",
      "product:bin/gstack-docs-candidate",
      "product:bin/gstack-doctor-components.sh",
      "product:bin/gstack-eval-plan",
      "product:bin/gstack-evidence",
      "product:bin/gstack-factory-scorecard",
      "product:bin/gstack-flaky",
      "product:bin/gstack-gate-diff",
      "product:bin/gstack-gbrain-detect",
      "product:bin/gstack-memory-ingest.ts",
      "product:bin/gstack-patch-names",
      "product:bin/gstack-pregate",
      "product:bin/gstack-question-log",
      "product:bin/gstack-question-preference",
      "product:bin/gstack-redact-prepush",
      "product:bin/gstack-render-claude.sh",
      "product:bin/gstack-retro-metrics",
      "product:bin/gstack-review-bots",
      "product:bin/gstack-review-dispatch",
      "product:bin/gstack-review-log",
      "product:bin/gstack-review-plan",
      "product:bin/gstack-review-read",
      "product:bin/gstack-review-scope",
      "product:bin/gstack-ship-queue"
    ],
    "merge_commits": 2,
    "range_diff": "1:  a26dfe994 =  1:  a26dfe994 eval-plan: a no-gstack arm needs masking, install and audit lines\n 2:  37f515bae =  2:  37f515bae inventory: the R56 evidence ledger, gstack-inventory and skill-bill EVIDENCE\n 3:  85e3edad8 =  3:  85e3edad8 ETHOS 9, Earn Its Place: factory, /write-skill and /autoplan carry it\n 4:  6566d5e28 =  4:  6566d5e28 fixup! inventory: the R56 evidence ledger, gstack-inventory and skill-bill EVIDENCE\n 5:  dc218faa6 =  5:  dc218faa6 inventory: list the evidence table's other names and its unmapped rows\n 6:  c60f501fb =  6:  c60f501fb docs: the first inventory snapshot and the R56 changelog fragment\n 7:  28e483eca =  7:  28e483eca inventory: investigate's step procedure is a fair-test CUT-CANDIDATE (GST-814)\n 8:  5f0be66af =  8:  5f0be66af docs: the inventory snapshot after investigate's no-effect row\n 9:  d0b3028b5 =  9:  d0b3028b5 inventory: only the seeded backlog may be grandfathered, so a new part's row is checked (review fix)\n10:  5162637b8 = 10:  5162637b8 inventory: devex-review and retro name their GEVA-2 registry rows (R56-11, R56-12)\n11:  bbff925c7 = 11:  bbff925c7 docs: the inventory snapshot after the review fixes\n12:  6af40f41d = 12:  6af40f41d inventory: a concrete plan is a path, gstack-inventory never writes into a gstack install, and the ledger checks aliases, r48 and prior.why (review fixes)\n13:  cd67c41d8 = 13:  cd67c41d8 inventory: investigate's no-effect row notes that only Opus 5.5 was measured\n14:  b63cab3ff = 14:  b63cab3ff docs: the inventory snapshot after the review fixes\n15:  a58377870 = 15:  a58377870 changelog: R56 counts after investigate's row; grandfathering and the install guard\n16:  38cf87685 = 16:  38cf87685 test: register inventory-grandfathered.json as a free fixture",
    "covers": [
      "pre-landing review",
      "adversarial review",
      "gate integrity",
      "documentation audit"
    ],
    "reruns": [
      "CI at head (gstack-ship-queue ready requires it); test and helper code changed since the reviewed head runs there unreviewed"
    ],
    "ancestry": "linear",
    "trees": [
      "e92b29c391551906f38f12141bc37d7002f0f9a6",
      "bb6961ef3b46358b3a25b1df656fb007a38a180c"
    ]
  }
}

Garry, 2026-11-02: "Also work this principle of only include it if it is beneficial and good into gstack" (R56, GST-914). Plan approved at autoplan-20261102030915 gate_rev 2 ("Do it", relayed by GStack Minder).

What changes

  • The principle. ETHOS.md gains "9. Earn Its Place": a new part comes with evidence that it helps on frontier models, or a reason, an owner and a date for a fair test. A fair test means the claude_code preset, frontier models (R54) and a masked no-gstack arm. A fair null gets one R48 "Why null?" cycle, then keep, fix or cut. Safety guards keep their stated reason. factory.md item 8 points at it, still inside its 3,300-byte budget.
  • The gates. /write-skill's edit ladder asks each new skill, step, instruction, check or default for its evidence or an owned, dated measurement plan, recorded in an Evidence: commit trailer. /autoplan's CEO phase lists each part a plan adds and raises a finding when one has neither.
  • The ledger and inventory. docs/inventory/evidence.json holds one entry per part: 64 skills plus 7 shared parts. Each entry has a status (helps, no effect, hurts, untested or safety), and the required fields depend on the status. Every part present today is grandfathered. A new part can't pass on plan: none. bin/gstack-inventory validates the ledger (--check) and writes docs/inventory.md, a dated ranking by load per run with a "measure next" order. gstack-skill-bill prints each skill's EVIDENCE line.
  • Masked no-gstack arms. This is a GStack Minder order (FOUN-32's GGST-6 finding). /eval-plan's ## No-gstack arm now requires masking:, install: and audit: lines, and prereg --check refuses a section without them. docs/TESTING_INTERNALS.md#no-gstack-arm says that any arm that read a gstack skill file is contaminated and gets zero credit.

First inventory

Seeded from gstack-evals' fair-test table (GEVA-2, org-gstack-gbrain/research/gstack-part-evidence.json). No gstack part has a fair "helps" verdict yet. The ledger at this head reads 0 helps, 1 no effect (/investigate), 17 untested with a plan, 48 untested with none and 5 safety. The /investigate row is a CUT-CANDIDATE from HARN-1 (GST-814), and its note says: "Only Opus 5.5 (claude-opus-5-5) was measured; GPT-6.1 Sol was not, so this verdict covers one of the two frontier models ETHOS.md 9 names." Every earlier result ran on the SDK stub, on a small model or with an unmasked arm, and these are recorded as prior with the reason. Nothing is cut in this PR. Cut candidates go to GStack Minder as R48 verdicts.

Limits

No ceiling was raised. This PR doesn't touch lib/review-depth.ts, lib/review-risk.ts or .github/workflows, and it changes no eval case's or judge's model.

Review notes

Review ran at full depth (gate class, with money, security and data risk classes) in two passes, with Red Team, the targeted reader and the adversarial pass. The cross-family outside voice ran as a Capy GPT-6.1 Sol reader because Codex was unavailable.

Review-loop exception: accepted by GStack Minder (Captain, GSTA-36) 2026-11-02 via Captain ruling on #3837 relayed by the lane parent (rule 23): option A: one fix batch for review items 1-6, each with a test, plus one scoped fix-check; item 7 filed as GST-939; anything new at the floor ships as an open note (fix-check at a583778, 0 findings)

Fixed in this PR, each with a test that failed first:

  • Self-grandfathering: any new row could set grandfathered: true and skip the plan rules. Now only the 71 seeded keys in test/fixtures/inventory-grandfathered.json may be grandfathered (d0b3028).
  • A new part's plan must be a path (a tasks.json or a prereg .md), so "proposed, not yet preregistered" no longer passes (6af40f4).
  • gstack-inventory with no --root used to write into the installed gstack copy. It now defaults to the git repo you run it in, refuses a root with no ledger, refuses to write into a gstack install (resolved the way gstack resolves its install), and exits 2 on --root followed by a flag or nothing (6af40f4).
  • aliases is validated, r48 is checked on every status, and prior.why refuses prototype keys such as toString (6af40f4).
  • gstack-skill-bill prints EVIDENCE: unreadable: … for a corrupt ledger instead of telling you to add a row (6af40f4).

One finding is not fixed here. The PREREG fixtures promise a contamination audit that the model-panel and arm-benchmark runners don't implement yet, so it is filed as follow-up GST-939.

Below the blocking floor, listed and not fixed:

  • Local and selected-files pregate don't map docs/inventory/evidence.json or the DISPATCHES source files to test/inventory.test.ts, so a broken ledger row first fails in CI free-tests.
  • results --check re-runs prereg --check, so a preregistration frozen before the masking rule now fails results --check unless edited after the run. Every committed prereg in the repo was updated, so no test fails.
  • The masking-key check accepts any non-blank value, including "not masked".
  • A verdict row passes with one frontier model; the /investigate row says so in its note.
  • /eval-plan's install: guidance names Claude paths only, not Codex.
  • measure_by dates are never reported as overdue.
  • keyOf has no production caller.
  • The /write-skill trim dropped the words "resolves exact names only".
  • In a checkout with no evidence.json, skill-bill now says "unreadable: … ENOENT" where it used to say "missing: … add one".
  • To fit the new parts-list line in its size budget, autoplan/sections/ceo-phase.md.tmpl dropped "All 11 review sections: run fully, auto-decide each issue, log every decision." and the sentence explaining what amend-input exports (85e3eda). Both review passes covered that commit.
  • docs/inventory.md is a dated snapshot. After the base merge a few of its load numbers drifted (autoplan on-demand 18,701 to 18,756, captain 7,856 to 7,900, ubicloud 3,593 to 3,588) and a /ship source line moved from docs/review-policy.md:319 to :339. Rerunning bin/gstack-inventory refreshes it; this head doesn't.
  • The review log counts findings from its logged rows. The pass 1 row was logged before the outside voice's findings were classified, so the receipt's blocking count doesn't include the findings the fix batch above fixed. The fix-check count includes one fix-check that was voided because a commit landed while it ran; it was redone at the frozen head.

Base merge

Main dd9834d was merged under GStack Minder's rule 19 grant (e56d331). The one conflict, test/fixtures/skill-md-size-allowlist.json, took main's file and lowered the 12 */gstack-autoplan pins by 17 each to their measured sizes; no pin was raised. 38cf876 registers test/fixtures/inventory-grandfathered.json with its only reader, test/inventory.test.ts. One fix-check reviewer read both changes at this head and found nothing; the docs were re-audited after the merge.

Train gate

ETHOS.md selects the paid office-hours and plan-ceo-review behavioral cases. None ran on this PR; they run in the train gate.

Documentation

Status: current — the branch's R56 docs read correctly next to main dd9834d at head 38cf876; no edits.

Scope: the committed diff from dd9834d (32 files, no staged, unstaged or untracked content), covering ETHOS principle 9, CONTRIBUTING step 6, docs/TESTING_INTERNALS.md no-gstack masking, docs/troubleshooting.md PREREG_NO_GSTACK_ARM, docs/skills.md Evidence, capy/skill/gstack/factory.md and the evidence ledger.

File Status
ETHOS.md Current
CONTRIBUTING.md Current
docs/TESTING_INTERNALS.md Current
docs/troubleshooting.md Current
docs/skills.md Current
capy/skill/gstack/factory.md Current (3,298 B of 3,300)
docs/inventory.md Needs regeneration: generated snapshot drifted after the base merge (a few token counts, review-policy.md:319 -> :339)

Coverage debt: bin/gstack-inventory and docs/inventory/evidence.json have reference and how-to coverage, but README.md, AGENTS.md and docs/PROJECT_STRUCTURE.md do not list them. Diagram drift: none.

Open in Capy

garrytan and others added 6 commits November 2, 2026 05:03
prereg --check now refuses a loaded comparison whose ## No-gstack arm
section lacks masking:, install: or audit:, or says none for one of them
(PREREG_NO_GSTACK_ARM). On Capy, run agents inherit the instruction to load
the user-drive gstack skill, so the arm hides both Capy drives, checks that
no gstack is installed, and audits drive reads; an arm that read a gstack
skill file is contaminated and gets zero credit (TESTING_INTERNALS.md
#no-gstack-arm). The prereg template, /eval-plan, troubleshooting and the
two passing prereg fixtures carry the new lines. eval-plan's paragraph was
dieted to hold its context-budget ceiling.

Evidence: safety: keeps the no-gstack control uncontaminated (Captain order, FOUN-32 via GGST-6)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…VIDENCE

docs/inventory/evidence.json holds one row per inventory key: the skill
folders discoverTemplates() finds (root skill as gstack, symlinked folders
excluded) plus seven shared parts, 71 keys. lib/inventory.ts validates each
row by its status's own fields, with named codes (LEDGER_*), and joins the
ledger with lib/context-bill.ts buildBill. bin/gstack-inventory writes
docs/inventory.md, --check validates (exit 1 with codes), --json prints.
Paid dispatches per run for /ship and /autoplan are quoted from their own
docs and found by line, so a moved citation fails --check
(INVENTORY_SOURCE_MISSING). Every current row is grandfathered and seeded
from GEVA-2's table (org-gstack-gbrain/research/gstack-part-evidence.json):
in-flight fair tests and proposed registry rows as plans, earlier unfair
results under prior with why (stub, unmasked, ceiling, ...), five safety
rows. gstack-skill-bill prints the skill's EVIDENCE line.

Evidence: plan none (owner ruling R56, GST-914); the ledger itself is the measurement record
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Garry, 2026-11-02: "Also work this principle of only include it if it is
beneficial and good into gstack". ETHOS.md principle 9 states the rule, the
fair test (claude_code preset, frontier models per R54, masked no-gstack
arm), the R48 Why-null cycle, the safety exception, and measure biggest
first, linking docs/inventory.md. factory.md item 8 cites it, trimmed
elsewhere to 3,298 of 3,300 bytes with no rule dropped. /write-skill's edit
ladder step 2 is the evidence rule and section 4 adds the Evidence: commit
line. /autoplan's CEO phase lists each part a plan adds to gstack with its
evidence or owned, dated plan; two redundant lines went to keep autoplan
under its size pins (pins lowered by 17). CONTRIBUTING.md "Adding a new
skill" and docs/skills.md point at the ledger.

Skill-Size: 3273→3666 bytes (write-skill/SKILL.md.tmpl)
Skill-Size: 12738→12721 bytes (autoplan/sections/ceo-phase.md)
Evidence: plan none (owner ruling R56, GST-914); write-skill and autoplan rows stay grandfathered untested
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…-bill EVIDENCE

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Ledger rows carry aliases (the name GEVA-2's table uses where it differs from the key, such as upgrade for gstack-upgrade), and docs/inventory.md lists them beside the installed-name rule. Unmapped rows are labeled as evidence-table rows, and the ranking notes that a skill's on-demand files can also be a shared row's.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
docs/inventory.md is generated by bin/gstack-inventory at the previous commit: 71 parts ranked by load per run, 0 helps, 0 no-effect, 0 hurts, 16 untested with a plan (4 fair tests under way, 12 proposed), 50 untested with plan none, 5 safety.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
@trunk-io

trunk-io Bot commented Nov 2, 2026 •

Copy link
Copy Markdown

😎 This pull request was merged.

garrytan and others added 11 commits November 2, 2026 05:17
…(GST-814)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…t's row is checked (review fix)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…6-11, R56-12)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…nto a gstack install, and the ledger checks aliases, r48 and prior.why (review fixes)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…easured

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… install guard

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Conflict: test/fixtures/skill-md-size-allowlist.json took main's file; the 12 autoplan host pins are lowered to the guard's measured sizes (main minus 17 each, none raised).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
free-suite (1) at e56d331 failed FREE_FIXTURES inventory: the pinned grandfather fixture from d0b3028 had no paid touchfile and no FREE_FIXTURES entry. Its only reader is test/inventory.test.ts.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Conflict: test/fixtures/skill-md-size-allowlist.json took main's file; the 12 autoplan host pins are lowered to the guard's measured sizes (main minus 17 each, none raised).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Conflict: test/fixtures/skill-md-size-allowlist.json took main's file (with #3909's review pins and #3903); the 12 autoplan host pins are lowered to the guard's measured sizes (main minus 17 each, none raised).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
@github-actions github-actions Bot changed the title R56: everything in gstack earns its place (principle, evidence gates, inventory) v1.94.29.0 R56: everything in gstack earns its place (principle, evidence gates, inventory) Nov 3, 2026
@capy-ai
capy-ai Bot merged commit ade35bc into main Nov 3, 2026
49 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant