Repository navigation
[MEDIUM] chore(pstack): sync the fork to Open Pstack 1.16.0 - #3
fitziboy3-source wants to merge 129 commits into
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>
…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>
Open Pstack 1.16.0 tracks Cursor pstack 0.15.29 and supersedes the fork's interim import of 0.15.28 from 2026-10-19. Conflicts fell into three groups: 46 files where the fork's copy was byte-identical to port 1.15.0 take the port's 1.16.0 copy; the seven skill and provenance files the interim import touched take the port's copy, since 0.15.29 contains 0.15.28; the verifier keeps the fork's REPO pin, formal recipes and Codex policy mapping, without the comments the port's sweep removed. The manifests carry 1.16.0-adam.20261101. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The static check requires a CHANGES.md section for the manifest version; the fork's patch list and sync record stay in FORK.md. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
It reproduces this merge's deterministic resolutions on a fresh branch and leaves only the judgment files conflicted. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The port ships the skill model-invocable on Claude Code and no Codex policy file. One shared skill tree keeps one policy per skill, so the fork's typed-only Codex file from the interim import goes. The maintenance skill stays typed-only in both harnesses. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Status on head 4dabb9a (2026-11-01)Local checks on this head with bun 1.4.4: Fork-authored design pass (the seventeen red flags) on Pending: the Codex cross-review and the exact-head live gate. Both go through the harness account router, which admitted no account today (one Claude home failed its quota probe, one is signed out, the third and both Codex homes are blocked by the paid-usage guards). They run once Adam names the account. |
The live gate classifies every path a PR changes and refuses an unmapped one; the operator script is not a shipped surface. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Live evidence: Open Pstack
|
The script swallowed every merge failure, so a refusal to overwrite local edits still reached the unconditional manifest and provenance rewrites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
…anch's policy The verifier refused any PR touching front-door.py, cloud-setup.sh or the cloud test as unmapped. The cloud test asserted a passive kit, which the branch has not shipped since October 5; it now asserts the installed skill matches the source byte for byte. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude Code 2.1.316 refuses a Write under any .claude/skills/ folder in dontAsk mode, so the creation case could not land the generated skill and the live gate failed. The port's setup cases already run this way for the same reason. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Live evidence: Open Pstack
|
A Claude permission override on a shared recipe refused the routed run for Codex too, which needs no override. The check is now a function with its own test. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The live gate's third run wrote the skill with the seven-character hash git prints, and the contract check required the full one. A short hash is what git log takes, so the check now accepts either. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A prefix found anywhere in the skill let an unchanged record pass when a diagnostic line mentioned the new head, and accepted a wrong hash that shared seven characters. The check now takes the token the sync-commit record declares and requires it to be a prefix of the expected commit. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Live evidence: Open Pstack
|
A sentence that mentions the sync commit and a hash satisfied the record check. The parser now takes the hash from a line whose label is "Sync commit", in the table and colon forms the generated skills use. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Live evidence: Open Pstack
|
Live evidence: Open Pstack
|
Superseded by #4; the review repairs move to a follow-upPull request 4 merged the same port v1.16.0 sync into Live-gate record on this PR: run 4 on |
|
Closed: superseded by #4; the review repairs continue in the follow-up PR. |
Why
The lanes run the fork's October 19 build of the kit. The port released Open Pstack 1.16.0 on October 21 with Cursor pstack 0.15.29, Claude Haiku 5.5 lanes, foreground subagent waits on Claude Code and the
/recallworktree fix. This bringsadam/releaseto it and keeps the fork's patches.What changed
v1.16.0intoadam/release, versioned1.16.0-adam.20261101.scripts/sync-port.shdoes the deterministic part of the next sync.FORK.mdrecords it, patch 6 (the verifier) and the sync.Scope
create-formal-verification-skillis model-invocable, as the port ships it. The October 19 build had it typed-only.Blast Radius
Every lane that installs
pstack@open-pstackfromadam/release: three Claude homes, two Codex homes and the cloud setup script. The front-door hook, its flag gate and the model sheet are unchanged. Rollback is a revert onadam/releaseand a reinstall.Verification
bun run static,bun run typecheckandbun run test(505 pass) and the verifier's own tests (206 pass) on the head, with bun 1.4.4. The verifier's lockfile needs bun 1.4 or newer; 1.3 cannot read it.tests/cloud-setup-test.shhas one failure, "the kit ships passive", which fails the same way onadam/releasetoday: the branch has been active since October 5 and the test still expects passive.scripts/sync-port.sh, rerun on a fresh branch, reproduces this merge except for the ten files resolved by hand.Risk tier: MEDIUM.
Where the work lives: pushed to
adam/sync-1.16.0on this fork, not merged, nothing deploys.🤖 Generated with Claude Code