Repository navigation
/office-hours keeps its founder resources out of the skill file (GST-3024) - #4463
Merged
Merged
Conversation
…ad of the prompt (GST-3024) The 34-entry resource pool moves from office-hours/sections/design-and-handoff.md into lib/founder-resources.ts, served by bin/gstack-founder-resources (index lists unshown entries from the builder profile, show prints the chosen ones). Behavior is unchanged; the skill's union shrinks by 8,504 bytes. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
😎 This pull request was merged. |
…did (GST-3024) The command now prints every entry not yet shown, blurbs and URLs included, so picking resources sees what it saw before; it drops the index/show split, reports PROFILE_READ: failed when the builder profile can't be read, and its argument handling is tested through runScriptSync. 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>
…urce move (GST-3024) The previous commit picked up four section files that belong to the follow-up content change. Nothing loads them yet; they return with that change. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…lback (GST-3024) Review-Finding: p1/specialist-batched#1 reader=testing Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
4 tasks done
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
capy-ai Bot
added a commit
that referenced
this pull request
Nov 18, 2026
- A test, or a scratch repository in the temp directory, can no longer write approval rows into your real Capy Drive (GST-3027). (#4466) - An unattended /autoplan run on Claude Code no longer says the publication guard is off while it is on. (#4481) - A phase report written only in reasoning now gets a denial that says so and names the fix. (#4481) - `gstack-autoplan revise` no longer refuses a plan that the first `next` accepted. (#4470) - `revise --plan` with a different file now says the run follows that file. (#4470) - A second-model plan review in `/autoplan` is no longer reported as unavailable when it actually ran (GST-3051). (#4471) - The /ship conductor trial plan now lets case reverts that conflict with later code be resolved by hand in docs, tests and the planted file, so large pull requests can be cases (GST-3003). (#4460) - A locked plan for a trial of /ship without its separate conductor subagent (GST-3003). (#4456) - A driven /ship now runs each phase as one command, counts its calls, and stops itself at 100 minutes. (#4451) - /ship stops asking owners to clear two kinds of bookkeeping noise: base-side merge text and a reviewer's confirmation prose. (#4458) - A base merge that only touched base-side text no longer stops `/ship` finish for an owner's grant. (#4458) - A reviewer's confirmation prose no longer becomes a Critical finding that only an owner can clear. (#4458) - A CI run that passed only after its failed jobs were re-run is now marked wherever gstack reuses it. (#4473) - /ship reuses CI's passing test run when merging the base changed no file, and stops instead of quietly starting hour-long test runs or reviewing an empty diff (GST-3019). (#4461) - /ship on Codex no longer stops at the test coverage audit. (#4489) - A cold first-use check before an app build reaches its owner (GST-3025). (#4465) - `skill_prefix=true` now survives updates when gbrain is installed. (#4454) - The OpenClaw docs no longer send you to ClawHub, which held only April 2026 builds of office-hours, ceo-review and retro and no longer has gstack skills (the docs also said four skills while listing three). (#4454) - `gstack-issue-links` no longer reads other repositories' issues as gstack's. (#4454) - /ship's pre-gate finds the tests of a monorepo app that imports through its own `@/` alias. (#4464) - /office-hours explains why it recommends a mode. (#4450) - /office-hours keeps its 34 founder videos and essays out of the skill file. (#4463) - Two `gstack-owner-answers add` runs for the same answer no longer collide. (#4490) - A Captain can check an ask against the owner's earlier answers before sending it. (#4467) - `gstack-post` stops reading /ship's own receipt identifiers as phone numbers, so posting a /ship PR body no longer needs a confirm. (#4488) - GitHub release notes now list every change in plain words, with a link to its pull request. (#4390) - gstack's router no longer gives bug reports a special rule, so the model fixes a bug the way it would without gstack. (#4442) - /ship's review plan now sorts Swift and Xcode files by risk instead of sending every iOS PR to the full review panel (GST-3041). (#4469) - /ship's review plan now sends Swift code that touches private user data to the full review panel (GST-3052). (#4472) - A round grant at /ship's review round cap now buys the fix round it names, in the same run or the next (GST-2968). (#4479) - The secrets check stops flagging three kinds of ordinary code as a secret, and catches two misses. (#4457) - A security finding's location and reason no longer go into a PR body. (#4486) - The token-capped /ship child on Claude Code now starts its prompt with the typed `/ship` command, so the skill actually loads. (#4487) - A /ship receipt now counts the second-model review's blocking findings, and refuses to be written while one is still open. (#4485) - A `/ship` with a token cap on Claude Code no longer stops at its first handoff. (#4452) - /ship's push step now always ends with one line that says whether it pushed (GST-3053). (#4474) - A PR's review-round count can no longer be overwritten by the body `/ship` posts. (#4440) - One queued record with a malformed path no longer stops artifacts sync for every project. (#4455) - A failed artifacts push stays reported until a push succeeds. (#4455) - The /sync-gbrain memory row no longer says OK when pages failed to import. (#4455) - ### Tests (#4495) - A policy-floor test no longer fails once gstack's own version reaches the minor after the newest policy key; it now checks a floor above both, so the v1.101.0.0 release can pass CI. (#4495) - CI now uploads free-suite test results to Trunk with analytics-uploader v2.1.8 and analytics-cli 0.17.0, up from v2.1.6 and 0.16.2. (#4453) - Packing a checkout for a Ubicloud run no longer fails when git beside it is rewriting a ref. (#4447) - The /plan-ceo-review HOLD SCOPE eval no longer fails a review because its follow-up question didn't repeat the mode name. (#4447) - Unattended /autoplan now records the owner's relayed gate reply instead of refusing it. (#4484) - Unattended /autoplan now runs the second-model review you turned on, and waits for it instead of ending the session. (#4459) - Two /autoplan runs started in the same second no longer share a run id. (#4459) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
/office-hours no longer carries its 34 founder videos and essays in the skill file; the closing runs a new
gstack-founder-resourcescommand that prints the ones a user hasn't been shown yet.Why: the skill was 9 bytes from its size cap, and the approved partner-session improvements need room. This frees about 8.6 KB.
Nothing to do as a reader.
What changed
The skill file was full, so the next round of /office-hours improvements had nowhere to go. The resource list now lives in
lib/founder-resources.ts(the 34 entries exactly as the prompt had them), and the closing section runsbin/gstack-founder-resources. The command prints the totals, then eitherRESOURCES: exhaustedor every entry the user hasn't seen, under its category header, in the prompt's own form. It reads what was already shown from the builder profile, or from--shown. The opt-out check still runs first, and the selection rules and format are unchanged.Small behavior changes: selection now sees only the unshown entries (before, it saw all 34 and skipped shown URLs itself); "all shown" counts pool URLs instead of any 34 logged URLs, which is the same today; and when the builder profile can't be read the command says
PROFILE_READ: failedand offers everything, as the prompt did.Why
It frees the bytes the approved content change for /office-hours needs, without raising the skill's size cap.
Blast radius
Only the /office-hours closing section calls the new command, and the generated section matches its template (gen:skill-docs reports no stale output). The command's default path, its profile-read fallback and the pool's exact bytes are pinned by tests that ran green here and in the full free suite.
Test Coverage
Coverage audit (read-only): 11 of 15 paths covered before review. Review added two command tests for the default profile read and the unreadable-profile fallback, so the remaining gaps are
--helpexiting 0 and the agent picking only from the printed list, which is an eval-level behavior.Tests ran: bun run test 1688 files (CI run 44190576458)
Tests ran: targeted 28
Pre-Landing Review
One test gap: the command's default path, which reads the builder profile, had no test. Fixed with two tests (5623235). The adversarial reviewer found four low-severity notes, listed below; the second-model review (GPT-6.1 Sol) was clean.
Review notes
Below the blocking floor (advisory, informational, test-gap or wording items); recorded here and not fixed in this PR.
bin/gstack-founder-resources:30PROFILE_READ: failed falls back to the full pool and the prompt has no instruction for that line; same as the old prompt's failure behavior.lib/founder-resources.ts:66Dedup is exact URL string matching; variant URL forms in old logs are not filtered.lib/founder-resources.ts:68RESOURCES_SHOWN_COUNT from the command counts pool hits while the builder profile's line of the same name counts every logged URL.test/founder-resources-bin.test.ts:58New profile cases spawn the bash profile bin through runScriptSync; Windows behavior unverified.Exploratory QA
Functional smoke on the command, in an isolated state folder: no history prints all 34 with no failure line; a logged shown URL drops out and counts as 1; a corrupt profile prints
PROFILE_READ: failedand the full pool. All three passed (exit 0). Not probed:--helpand the agent's selection from the list.Eval Results
No paid evals ran. This change moves text without changing what the skill tells the agent to do; the planned eval measures the content change that follows. The selector listed 110 probes only because
test/helpers/free-fixtures-data.tsis a shared input of the paid runner.Scope Drift
Scope Check: DRIFT DETECTED, then fixed. An earlier commit picked up four unfinished section files from the follow-up content change (
office-hours/sections/landscape.md(.tmpl),phase-2c-pivot-discovery.md(.tmpl)). Nothing loaded them; a242ac0 takes them back out, and they return with that change.Plan Completion
test/helpers/carve-guards.tsis not lowered: deferred as a P1 TODO; the content change sets the measured valueTODOS
No TODO items completed in this PR. Added a P1 TODO for the office-hours parity pin.
Documentation
Status: current. No documentation changes needed.
Scope: base da98d0a to head 65bfb41 on office-hours-resources-lookup (10 files: founder-resources lib, bin and tests, office-hours handoff section and template, changelog.d fragment, TODOS). Worktree clean.
Documentation health:
office-hours/sections/design-and-handoff.md.tmpl: Current. It already describesgstack-founder-resources,RESOURCES: exhaustedand the selection rules.office-hours/sections/design-and-handoff.md: Current (generated, matches template diff).docs/state-root.md: Current. Thefounder_resourcesconfig key is unchanged.office-hours/SKILL.md.tmpl: Current. The Phase 6 resources log entry is unchanged.Coverage debt: none new. The tracked parity-pin follow-up stays in TODOS (GST-3024). Diagram drift: none.
Tests
Agent notes
Refs p1/specialist-batched#1
Refs GST-3024
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=0 fixed=1 scope=frozen ledgers_read=3 dispatches=4
Gate edits: none detected (4 listed, 1 read; patterns: RH-1,RH-3,RH-4,RH-12,RH-13,RH-14,RH-15,RH-16; unlisted idioms: none)
Scoped reader after the review fix: clean (anthropic/claude-opus-5-5, test/founder-resources-bin.test.ts).
Approvals
No approvals recorded for branch office-hours-resources-lookup.
Plan: approved (record r-d3a4125ef6f6)
Plan check: approved (record r-d3a4125ef6f6)
Plan source: autoplan run-yibgts-20261117204732 (approved; decision F1, two PRs).
Agent notes