Repository navigation
Sync adam/release to Open Pstack 1.16.0 and Cursor pstack 0.15.36 (kit 1.16.0-adam.20261101) - #4
Merged
Merged
Conversation
release: Open Pstack 1.8.0 with the model catalog and the Windows SessionStart fix (ericlitman#174)
…iclitman#54) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…riclitman#54) docs/reference.md and the README described the native agents as Fable and Opus only, using the rolling alias. Each Claude family in the catalog now ships agents, and a registered exact pin keeps its own model. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…riclitman#69) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…r, and widen the pin scan (ericlitman#54) The new-families setup case checked only the rewritten sheet, so a run that probed Sonnet or the pin through the rolling Opus agent still passed. It now requires the Claude Agent calls to pstack-opus-5-5-max and pstack-sonnet-max, and a complete runner receipt for each external probe in its own empty probes directory. The three setup cases that remove Codex's AGENTS.md mirror now check that setup wrote it back as the sheet's exact bytes. The Claude pin scan covers Sonnet, and it removes only the registered pin's token before matching, so another pin on the same line still fails. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…access (ericlitman#80) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… mirror exactly (ericlitman#54) Step back on head 2's probe check, which inferred setup's internal probes from transcripts and kept growing variants (nested or extensionless receipts, wrong effort, undrained background agents). It is gone. A catalog case on Claude now dispatches pstack-sonnet-max and pstack-opus-5-5-max, and each child writes a fixture nonce it read, with its tool calls recorded under its Agent call. The Codex mirror check follows setup's contract exactly: one marker pair, and the sheet's exact bytes after the begin marker's newline. The pin scan's exemption ends only at a character that cannot continue a model ID. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…l overrides, tighten the mirror and pin scans (ericlitman#54) The new-families setup case now feeds a versioned Sonnet, which this PR's setup migration must write as claude:sonnet. The native-agents case rejects an Agent call that overrides the model. The mirror check counts a stray begin marker even without its newline, and the second pin scan no longer depends on the file path having no colon. ericlitman#54's acceptance criteria are corrected: setup's probe routes are not this PR's change, and the new routes are proven by the native-agents and runner cases. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…onnet feat(registry): add GPT-6 Luna, Sonnet and the exact Opus 5.5 pin (ericlitman#54)
Brings in ericlitman#54's head 4. The read-only-provider setup case now follows the same rule as new-families: it checks the written sheet and, on Codex, the mirror block, and drops its command-text check that the session ran pstack-runner. The runner feature proves the Devin route. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Brings in PR ericlitman#182's merge commit. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…and widen setup's writer roles (ericlitman#69) A Devin lane bypasses workspace trust, and Devin loads a project's .devin/config.json hooks and permissions and its .devin/mcp_config.json servers, with no key to turn them off. The runner now refuses a Devin lane whose cwd or any parent up to the git root holds .devin/, through an adapter-declared projectConfigDir checked before launch. An interruption is a cancellation only when Devin writes it as a system step. Setup refuses a read-only provider for every writer role: the four playbook roles, hardest tasks, arena runners and swarm workers. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…he refusal live, and guard only .devin directories (ericlitman#69) Architect runs Arena with its own runners, which write to their own output locations, so setup's writer roles include architect runners. A new setup case assigns bug-fix to Devin and requires setup's refusal with no configuration change, so the live gate tests the new rule. The project-config guard refuses only a .devin directory; a plain file holds no Devin config. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(runner): add a read-only Devin provider with SWE-2 and SWE-1.6 (ericlitman#69)
…riter Brings in ericlitman#69's heads 2 and 3: the .devin/ guard and projectConfigDir, the widened writer roles, and the writer-refusal setup case. The keep-setting case now checks the Codex mirror like every case that removes it, and the refusal case's role constant is renamed to REFUSED_ROLE beside ericlitman#80's WRITER_ROLE. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Brings in PR ericlitman#183's merge commit. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…nts keep writers bounded unless opted in (ericlitman#80) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…s setting, and parse quoted paths with newlines (ericlitman#80) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…access-writer feat(runner): let a model-sheet setting give Codex writer lanes full access (ericlitman#80)
…iclitman#185) Unfret registers one check per root package.json script and runs it with the packageManager named there. open-pstack had no root package.json, so each focal review lane ran bun install and the tests through run_command. The root scripts are CI's verify steps: test, typecheck and static. CI now calls them, so the reviewers and CI run one definition, and setup-bun reads the Bun version from packageManager instead of a second pin. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…tman#185) Both paths were unmapped, so a PR touching either failed closed before any install. CI now runs the root scripts, which include the verifier's own tests, so both are verifier enforcement like tests/skill-collision-repro.sh: a change to either selects project-skill and cannot pass as no runtime change. The fail-closed case for unregistered workflows keeps a new workflow path. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…unset (ericlitman#185) Unfret runs a registered check with only PATH, HOME, TMPDIR and locale variables, so run_check static failed 23 verifier tests on isolatedEnv's "Real USER and LOGNAME are required". The test script now supplies the account from id -un when the environment has none. The live verifier's guard is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…-scripts build: add root check scripts so Unfret registers and shares open-pstack's checks (ericlitman#185)
… and Codex full access (ericlitman#190) Bumps the manifests, marketplace entry and version lines to 1.9.0 and adds the 1.9.0 CHANGES.md section, written from PRs ericlitman#182 (ericlitman#54), ericlitman#183 (ericlitman#69) and ericlitman#184 (ericlitman#80), with one line for PR ericlitman#186 (ericlitman#185). The Cursor sync point stays at pstack 0.15.20. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…itman#172) The host's global git config routes trace2 events to the git-ai daemon, which writes .git/ai and refs/notes/ai into each fixture repository after the git command exits. In provenance.test.ts that write recreated the fixture root after the test renamed it, so the symlink at line 132 failed with EEXIST. Fixture git calls in the provenance, harness and publisher tests now run with GIT_CONFIG_GLOBAL=/dev/null and GIT_CONFIG_NOSYSTEM=1. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…t-isolation test(verify): keep fixture git out of the host's global config (ericlitman#172)
release: Open Pstack 1.9.0 with Luna, Sonnet, the Opus 5.5 pin, Devin and Codex full access (ericlitman#190)
…25 (ericlitman#191, ericlitman#187) Upstream added two typed-only skills after the 0.15.20 sync point: in-your-own-words (7d8d909, reworded in dbf4981) and sharpen (79afd75). Both are verbatim at 0.15.25 and keep disable-model-invocation, like the port's other typed-only skills. This commit carries soulmachine's PR ericlitman#188 as written: the two skills, their poteto-help rows, the typed-only list, the recipes, the README and reference rows, and the verifier feature registry entries. Co-authored-by: soulmachine <soulmachine@gmail.com> Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Applies the 17 upstream pstack commits from 1b6d44f to 99743e9 through scripts/upstream-audit.py and scripts/upstream-merge.py (11 verbatim, 11 clean merges, 28 hand-resolved, 3 unmapped and excluded). - poteto-mode takes ce649c0's "Match the model to the job" rule as upstream wrote it, adapted to the port's descriptors: the starting level is the role's configured effort, an unlisted effort moves to the row's nearest listed one, a configured ultra stays, and the speed sentences go because the port has no speed selector. Every routed skill and playbook points at the rule. provider-dispatch.md says the parent may move the effort per spawn and a child never does. - e5136d8's restated principles replace the port's local corrections to test-behavior-not-implementation, attack-the-premise and correct step 3. - Shipping keeps its nine landing steps and takes upstream's new rules and reasons. Autopilot-full takes upstream's seven steps with the port's guarded rebase and push in step 2, its step 5 merge prep, and the affirmative-failure stuck rule. Autopilot-stack takes upstream's four steps with the fork and topology rules folded into step 2. The landing invariants follow the moved text. - orch frontier reads the PR base chain instead of Graphite; watch-pr treats an owner-approval Code Review Gate as the gate; worktree-audit reads Origin PRs; ketchup, swarm, interrogate, the principles, and poteto-agent take upstream's cuts with the port's substitutions. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…er-constraints test(runner): encode two constraints the comment sweep left unenforced (ericlitman#222)
…riclitman#225) sumTestPassed ran the session's sum.mjs in the verifier parent, outside Codex's sandbox. The never-block case now recognizes the repair from the whole sum.mjs source (return a + b or b + a on the return line, optionally parenthesized), requires the fixture test unchanged, and executes neither file. Co-authored-by: andrewfree <507412+andrewfree@users.noreply.github.com> Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…-progress fix(verifier): require concrete work in the never-block case (ericlitman#225)
…riclitman#223) Removes the explanatory comment the port added to the catalog recipe, per the comment rule in AGENTS.md. NOTICE.md now covers every generated Claude-native lane family, and CHANGES.md records the Haiku 5.5 pin under Unreleased. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(pstack): support Claude Haiku 5.5 lanes (ericlitman#223)
…tman#232, ericlitman#233) Every generated lane agent set background: true, which Claude Code honors over a caller's run_in_background: false, so a subagent could not wait for a lane's report and polled instead. The generator drops the field. codex-tools.md now says once how the main session and a subagent wait on Claude Code, including the PR watcher, and the other files point there. The catalog live-gate case dispatches its lanes in the foreground and requires their reports inline. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…litman#232) The wait rule let a subagent rerun watch-pr only after a TIMEOUT exit, so after it fixed a BLOCKER (exit 3 or 4) and pushed, it stopped watching, against babysit step 6. It now reruns after a TIMEOUT and after every push or verdict it acts on, on GitHub only. The catalog case's prompt asks for all of its Agent calls, now three. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…code-waits fix(pstack): let Claude Code subagents wait in the foreground (ericlitman#232, ericlitman#233)
…riclitman#234) Apply scripts/upstream-merge.py from 99743e9 to 88d4751: 6 files verbatim, 3 clean merges, 3 for review. Add create-formal-verification-skill and maintain-formal-verification-skill, the ketchup, sharpen and typescript-best-practices changes, and the poteto-help routing and recipes. Resolve setup-pstack by keeping the port's step 9 and adding upstream's verification offers as steps 10 and 11. Resolve poteto-help by keeping the port's install lines, setup sentence and harness paragraph, and appending upstream's offers sentence. make-bot-ui stays absent. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…riclitman#234) Setup's new formal verification offer invokes the skill, and disable-model-invocation blocks that route on Claude Code. Drop the flag, guard it in the routed-skill invariant, and register both formal verification skills with the verifier. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ng (ericlitman#46) On a rerun whose sheet loads with a valid setting line, with no named change and no inconsistency or kept-predecessor choice, setup validates, prints the kept roles and efforts, probes, and writes without the step 2, 4 and 7 questions when every probe passes. The verification offers print one line each. Validation, permission checks, snapshots, readback and the smoke test still run, and a failed probe still stops without writing. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…verifier (ericlitman#46) Every setup prompt now declines setup's two verification offers, and first-run asserts that the fixture gained no project skill directory. keep-setting now starts from a complete sheet with the full-access line and an agreeing Codex mirror, gives no answers, and requires both files to keep their bytes with no AskUserQuestion call. keep-predecessor still covers missing-role completion. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…litman#234) UPSTREAM.md moves the sync point to 88d4751 (pstack 0.15.29), records the new exclusions and adaptations, adds the ericlitman#46 ledger entry, and refreshes "Incorporate a change" from this run (ericlitman#106). NOTICE.md gains a 0.15.26 to 0.15.29 provenance row, CHANGES.md a 1.16.0 section, and README.md and docs/reference.md the two formal verification skills, the new /sharpen, the version, the cursor-plugins install note and the Claude writer lane host requirement. Both manifests and the marketplace move to 1.16.0. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…n#235) recall, automate-me and the session-pickup playbook said Claude Code encodes only each / in the workspace path. It also encodes each ., so every .claude/worktrees/ session looked for a folder that does not exist. Reproduced on 2026-10-21 with the installed 1.15.0 plugin. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ly what it checks (ericlitman#46) keep-setting now prepares exactly the sheet a quiet rerun keeps, so a prepared file written in the session's start millisecond satisfied written() for a session that wrote nothing. The prepared sheet and Codex mirror now carry a past mtime. The case publishes no-question for Claude only, because a Codex session asks in plain text, which the session record does not keep. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ericlitman#46) keep-setting got the same "decline both offers" sentence as every setup case, so its no-question check could not fail on the offers a quiet rerun must only mention. keep-setting now gets no answers and must end with SETUP-DONE, create no skill directory, and, in Claude, attempt no AskUserQuestion. The parser keeps each session's final assistant text. A new accept-formal-offer case requires setup to load create-formal-verification-skill when the user accepts that offer. first-run's offers-declined assertion is renamed no-skill-directory. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…s handoff (ericlitman#234) Codex follows a skill reference by reading its SKILL.md with a shell command, so its rollout has no injected <skill> block for the formal creator. accept-formal-offer now also counts a successful read of the installed creator's SKILL.md, under this run's installation, whose output carries the creator's frontmatter. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… creator (ericlitman#234) The case's prompt named the formal verification offer, so a candidate whose setup no longer offered it could still load create-formal-verification-skill from the prompt and pass as routed. The prompt now declines /create-verification-skill and accepts any other offer, and never names the formal one. CHANGES.md now says which setup cases decline the offers. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…man#234) The accept-formal-offer case matched the creator's path spelling, so a real Codex session that read it through a relative path failed as not routed. The case now counts a successful command whose output carries the installed creator's frontmatter name and description lines, whatever the path spelling. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Restore the verifier's recipes, setup notes, parser and tests to main. This removes the accept-formal-offer case, the SETUP-DONE and ACCEPT-ROUTED sentinels, the parser's reply field, the offer-decline sentence and the extra keep-setting and first-run assertions. The registry still lists the two formal verification skills. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Takes the port's 1.16.0 content (Cursor pstack 0.15.29 sync, Haiku 5.5 lanes, foreground subagent waits, quiet setup reruns, transcript folder encoding, the comment sweep). Keeps the fork's patches: the flag-gated session hook, the model-invocable correct skill, the cloud installer and its test, FORK.md, TEAM-INSTALL.md, and the verifier's routing, formal and Codex-policy additions. The Claude flag on create-formal-verification-skill follows the port, which routes that skill by name from setup's offer; its Codex explicit-only policy file goes with it. maintain-formal-verification-skill stays typed-only.
Lauren Tan's skill changes from 88d4751 (0.15.29, the port's sync point) to ae5650f (0.15.36): the statechart and ketchup-video skills, the adversarial interrogate, the arena cross-judge rule, the agentic Orchestrate playbook, the first-message goal restatement, the Explain the Number update, the autopilot blocking rule, and the watch-pr, check-plan, worktree-audit and reflect fixes. Applied with the port's harness substitutions and standing exclusions; UPSTREAM.md records every commit left out and why. Retained against upstream: the orch store CLI (orch.ts, store.ts, orch.test.ts) and its test list entry, which the harness's chief-of-staff skill drives, and the port's Autopilot-stack landing procedure, babysit owner rule and Autopilot-full step 5. Version 1.16.0-adam.20261101.
The three-way merge appended upstream's test() cases, which call a runPlan helper the port's bun:test file does not have, so the suite stopped with "test is not defined". The same two cases now run through withExample inside the fences describe block.
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.
Closes #: no issue. The sync is recorded in the harness,
docs/design/pstack-front-door.mdsection 14, and in this fork'sFORK.md("November 1, 2026 update").What changed
Two commits on
adam/release, plus one test fix.v1.16.0(dc9d157, Cursor pstack 0.15.29): Claude Haiku 5.5 lanes, foreground subagent waits, quiet setup reruns, the transcript folder encoding fix, the comment sweep. Of the 64 conflicts, 46 took the port's side (the October squash had re-applied the same content) and 18 were resolved by hand so every patch inFORK.mdsurvives: the flag-gated session hook, the model-invocablecorrect, the cloud installer and its test,FORK.md,TEAM-INSTALL.md, and the verifier's routing, formal and Codex-policy additions.create-formal-verification-skillfollows the port and is model-invocable on both harnesses (setup's offer routes to it by name; the static test requires it), so its Codex explicit-only policy file is removed.maintain-formal-verification-skillstays typed-only.ae5650f), applied with the port's own sync rules (UPSTREAM.md, "Incorporate a change") re-implemented outside the checkout: 7 paths verbatim, 408 added, 4 deleted, 3 retained, 6 clean three-way merges, 14 hand resolutions, 6 unmapped Cursor manifest and guide paths left out. New skillsstatechartandketchup-video;interrogaterewritten as adversaries whose findings must be proven by a run; Arena's cross-judge never from the parent's provider and skipped when the pool has no other provider; the agentic Orchestrate playbook; the first-message goal restatement; "Explain the Number" before you measure; Autopilot's blocking rule; fixes towatch-pr,check-plan.mjs,worktree-audit.shandreflect.README-UPSTREAM.mdis her README verbatim.UPSTREAM.mdrecords every commit left out and why;CHANGES.mdandNOTICE.mdcarry the fork's section and provenance line.fd1d19d: upstream's two newcheck-plan.test.tscases, which the three-way merge had appended in upstream'stest()style with arunPlanhelper this file does not have, rewritten in the port'sit()style throughwithExample. Same assertions.Retained against upstream, as
FORK.mdpatch 6:scripts/orch/orch.ts,store.ts,orch.test.tsand theorchentry in the scripts' test list, because the harness's chief-of-staff skill drives that store CLI. The playbook text no longer names it.Version
1.16.0-adam.20261101in both plugin manifests, the Claude marketplace andUPSTREAM.md. The verifier'sregistry.jsonregisters both new skills and mapsstatechart/scripts/**totools(the shipped-tools recipe does not exercise it yet).Verification
verifyonfd1d19d: 455 tests pass, typecheck and static green; the Windows hookwrapperjob passes. (The first run on23673affailed on the appended test cases, fixed in commit 3.) Where the candidate was built, the static invariants and the verifier's registry coverage had been re-checked by reading (docs/design/evidence/pstack-sync-2026-11-01/invariants.pyin the harness);tests/cloud-setup-test.shis not covered by CI and has not been run.claude plugin update pstack@open-pstackagainst this head, and the Codex equivalent.verify-open-pstackperAGENTS.md; the smallest surfaces that carry the change are/pstack:statecharttyped,/pstack:interrogatetyped on a small diff, and Arena's Phase C on a Claude parent with Adam's sheet (Codex must judge).live-gatestatus on the final head links the evidence comment (installed version, surface, action, observed result).Mergify does not queue a pull request without
live-gateon its exact head. Do not merge, tag, release, or roll out without it. This PR targetsadam/release, which Mergify does not queue; the merge is Adam's word after the gate.🤖 Generated with Claude Code
https://claude.ai/code/session_018K2CaoMFwAdM9wX571Zvm4