Skip to content

[MEDIUM] chore(pstack): sync the fork to Open Pstack 1.16.0 - #3

Closed
fitziboy3-source wants to merge 129 commits into
adam/releasefrom
adam/sync-1.16.0
Closed

fitziboy3-source wants to merge 129 commits into
adam/releasefrom
adam/sync-1.16.0

Conversation

@fitziboy3-source

Copy link
Copy Markdown
Owner

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 /recall worktree fix. This brings adam/release to it and keeps the fork's patches.

What changed

  • Merge of the port's v1.16.0 into adam/release, versioned 1.16.0-adam.20261101.
  • The seven skill and provenance files the October 19 interim import touched take the port's copy. The verifier keeps the fork's repository pin, formal verification recipes and Codex policy mapping.
  • scripts/sync-port.sh does the deterministic part of the next sync. FORK.md records it, patch 6 (the verifier) and the sync.

Scope

  • Covers the port's 1.16.0 and every fork patch that shipped before it.
  • Leaves out Cursor pstack 0.15.30 to 0.15.36 (the statechart skill, ketchup-video, agentic Orchestrate). No port has translated them yet.
  • create-formal-verification-skill is model-invocable, as the port ships it. The October 19 build had it typed-only.

Blast Radius

Every lane that installs pstack@open-pstack from adam/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 on adam/release and a reinstall.

Verification

  • bun run static, bun run typecheck and bun 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.
  • The session hook prints nothing without the flag file and the mandate with it.
  • tests/cloud-setup-test.sh has one failure, "the kit ships passive", which fails the same way on adam/release today: 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.
  • Live gate: pending on the exact head.

Risk tier: MEDIUM.

Where the work lives: pushed to adam/sync-1.16.0 on this fork, not merged, nothing deploys.

🤖 Generated with Claude Code

mergify Bot and others added 30 commits October 13, 2026 16:30
release: Open Pstack 1.8.0 with the model catalog and the Windows SessionStart fix (ericlitman#174)
…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>
…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>
ericlitman and others added 12 commits October 21, 2026 00:47
…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>
@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Status on head 4dabb9a (2026-11-01)

Local checks on this head with bun 1.4.4: bun run static, bun run typecheck, bun run test (505 pass) and the verifier's own tests (206 pass). The session hook prints nothing without the flag file and the mandate with it. tests/cloud-setup-test.sh has one stale failure, "the kit ships passive", which fails the same way on adam/release. GitHub checks verify and wrapper pass.

Fork-authored design pass (the seventeen red flags) on scripts/sync-port.sh, the three verifier resolutions and the records: nothing fired. One note, not a flag: the script uses macOS sed -i '', like the other operator scripts here, so it runs on the Mac, not in a Linux VM.

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>
@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Live evidence: Open Pstack

  • Candidate SHA: 1c6b00cd417c13ec39f7e65879c60c78ff9fb287
  • Base SHA: 0eacabdd48477847ac6e88657a28805842aefad4
  • Result: FAILED — verification did not complete; rerun required
  • Self-test: required in both harnesses
  • Planned sessions: 10 (limit 12)
  • Publisher revision: 1c6b00cd417c13ec39f7e65879c60c78ff9fb287
  • Evidence-set SHA-256: e25d38abe170897e75112513760734140c7661dfc274695b22525d44082047a4
  • Policy: every new head requires a fresh run; this verifier does not change PR state, queue, or merge.

fitziboy3-source and others added 4 commits November 1, 2026 17:32
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>
@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Live evidence: Open Pstack

  • Candidate SHA: 7bfdd73fe76ce3db317ec76d3026b6e6f6494294
  • Base SHA: 0eacabdd48477847ac6e88657a28805842aefad4
  • Result: FAILED — verification did not complete; rerun required
  • Self-test: required in both harnesses
  • Planned sessions: 10 (limit 12)
  • Publisher revision: 7bfdd73fe76ce3db317ec76d3026b6e6f6494294
  • Evidence-set SHA-256: f4897b649f3cabdd59c483d828cdbd4ebe46191f9d9812740ec6524188cd6772
  • Policy: every new head requires a fresh run; this verifier does not change PR state, queue, or merge.

fitziboy3-source and others added 3 commits November 1, 2026 17:39
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>
@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Live evidence: Open Pstack

  • Candidate SHA: 94998eb7035c9e58e503b5121b4c1c6187804aac
  • Base SHA: 0eacabdd48477847ac6e88657a28805842aefad4
  • Result: PASSED — named features verified
  • Self-test: completed in both harnesses
  • Planned sessions: 10 (limit 12)
  • Publisher revision: 94998eb7035c9e58e503b5121b4c1c6187804aac
  • Evidence-set SHA-256: fcae634d62b72fe61e12c21d93d20577b9087f4ca9758a744ef49680acf6e3c1
  • Installation (claude): CLI 2.1.316 (Claude Code), plugin 1.16.0-adam.20261101, candidate 94998eb7035c9e58e503b5121b4c1c6187804aac, tree 2ecc34ff43f5495c37d7220e22db2d56e0c3c96759c1f4207f7a01a3cbf1ed8d.
  • Installation (codex): CLI codex-cli 0.162.1, plugin 1.16.0-adam.20261101, candidate 94998eb7035c9e58e503b5121b4c1c6187804aac, tree 2ecc34ff43f5495c37d7220e22db2d56e0c3c96759c1f4207f7a01a3cbf1ed8d.
  • Observation (claude / hook:startup): surface claude -p stream-json with the candidate plugin-dir; action recipe hook:startup: startup; result passed: startup:exit-0 startup:hook-context-injected; 2 assertions machine-checked; transcript SHA-256 e62de33e2c0e16579d607aa8a85be65d92bbc4b9730786125e0d942a6c2aa755; artifact-set SHA-256 f0742b82d4de17cdfb0f1c51eb2e6e3e19ab9b7b741f57b1f407c9439a0bc2d6.
  • Observation (claude / skill-invocation:poteto-mode): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:poteto-mode: route-without-dispatch; result passed: route-without-dispatch:exit-0 route-without-dispatch:skill-loaded route-without-dispatch:configured-native-route route-without-dispatch:no-dispatch; 4 assertions machine-checked; transcript SHA-256 d01994d369bd0c9b3454b41ac4d66d2c0908fc9498716e430199bf4e4435b7a3; artifact-set SHA-256 e8e4cb5022085725301ad22219d6444dd393abbdc1c4e4bcb500fcbaa969ffc9.
  • Observation (claude / skill-invocation:create-formal-verification-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:create-formal-verification-skill: create-and-mutate; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 a4bb96cb8b55912c22d1e3724d1202d95b71d0418f444ef7395d62efe6946270; artifact-set SHA-256 53c5dfa46bc849a40ba9f40f3fb04ca8425666a5eebc09009eeefd299eed2f7c.
  • Observation (claude / skill-invocation:maintain-formal-verification-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:maintain-formal-verification-skill: stale-model; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 aac5c511bfe6d04b920e2842b34e15ffec566c5fdde06d30078a6b41dfb4c143; artifact-set SHA-256 8ed0f8b8159274c635cba3df629c1319840500bf8ae6f470c42574882b6e3b00.
  • Observation (claude / project-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe project-skill: doctor; result passed: doctor:exit-0 doctor:skill-loaded doctor:doctor-ran doctor:doctor-canonical-pass; 4 assertions machine-checked; transcript SHA-256 8e1dc3f9e9a2353752c740f4f379c0c024d5b1a30e690b7376df27ba22409c09; artifact-set SHA-256 77f6b2bac8a1fd038d0d6d4c1754dc8e2a465fa0d59dab0ab2ecba234eaaf3d1.
  • Observation (codex / hook:startup): surface codex exec --json with the run-owned candidate installation; action recipe hook:startup: startup; result passed: startup:exit-0 startup:hook-context-injected; 2 assertions machine-checked; transcript SHA-256 73adbf8376cf3c64828ed5f5e1cfc686ec8fcc5592d1e42c9447affeb33a2cb0; artifact-set SHA-256 c4222eef512522277d348500334180ba47cc6536372318813123a5286d76e2fd.
  • Observation (codex / skill-invocation:poteto-mode): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:poteto-mode: route-without-dispatch; result passed: route-without-dispatch:exit-0 route-without-dispatch:skill-loaded route-without-dispatch:configured-native-route route-without-dispatch:no-dispatch; 4 assertions machine-checked; transcript SHA-256 9a27d476d04d759fda0a0f85ffeb68d9ae833974e80b81a5997dc4da5ccd02c3; artifact-set SHA-256 465074ac1c0d7e44adc6ec14762705b3bb1d25bfd688b1a945c0d45de0ff7204.
  • Observation (codex / skill-invocation:create-formal-verification-skill): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:create-formal-verification-skill: create-and-mutate; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 255334885ec46a2abc1ab7f23bf711da95fd5bfa6765d8f192d750b75b665e80; artifact-set SHA-256 9cc5adac2b5497dd74ab15c318c51798fbf72a742e5a353bf87a3c88049a94ec.
  • Observation (codex / skill-invocation:maintain-formal-verification-skill): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:maintain-formal-verification-skill: stale-model; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 d06a2fe4cc630eb73b9dc4ea462da358279f71ffb5e7a07b567d78468afe3901; artifact-set SHA-256 2014515417b5bd683d4aa4b6dfb6546048651521970f9b4d6d3ac019144e2f8f.
  • Observation (codex / project-skill): surface codex exec --json with the run-owned candidate installation; action recipe project-skill: doctor; result passed: doctor:exit-0 doctor:skill-loaded doctor:doctor-ran doctor:doctor-canonical-pass; 4 assertions machine-checked; transcript SHA-256 dc76f8805415997f595023069208d612349ca400fe98a0058d92bc256b6fa942; artifact-set SHA-256 fb57a12216ec8d993fd2ef5bda220f23dce82391244f878b9e5224c06710777d.
  • Policy: every new head requires a fresh run; this verifier does not change PR state, queue, or merge.

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>
@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Live evidence: Open Pstack

  • Candidate SHA: 92c09a0c8d260ae270af60e58b9be4c6a77f2b45
  • Base SHA: 0eacabdd48477847ac6e88657a28805842aefad4
  • Result: PASSED — named features verified
  • Self-test: completed in both harnesses
  • Planned sessions: 10 (limit 12)
  • Publisher revision: 92c09a0c8d260ae270af60e58b9be4c6a77f2b45
  • Evidence-set SHA-256: 4ab6920dc67d2b7de35dd4e93d6099fa5923eabac9953c562ca526c04bc902f6
  • Installation (claude): CLI 2.1.316 (Claude Code), plugin 1.16.0-adam.20261101, candidate 92c09a0c8d260ae270af60e58b9be4c6a77f2b45, tree 2ecc34ff43f5495c37d7220e22db2d56e0c3c96759c1f4207f7a01a3cbf1ed8d.
  • Installation (codex): CLI codex-cli 0.162.1, plugin 1.16.0-adam.20261101, candidate 92c09a0c8d260ae270af60e58b9be4c6a77f2b45, tree 2ecc34ff43f5495c37d7220e22db2d56e0c3c96759c1f4207f7a01a3cbf1ed8d.
  • Observation (claude / hook:startup): surface claude -p stream-json with the candidate plugin-dir; action recipe hook:startup: startup; result passed: startup:exit-0 startup:hook-context-injected; 2 assertions machine-checked; transcript SHA-256 f9bd3864466aabb57203ab9ac1c72193d5bb5155b45831accfdeb835b2925c13; artifact-set SHA-256 f0742b82d4de17cdfb0f1c51eb2e6e3e19ab9b7b741f57b1f407c9439a0bc2d6.
  • Observation (claude / skill-invocation:poteto-mode): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:poteto-mode: route-without-dispatch; result passed: route-without-dispatch:exit-0 route-without-dispatch:skill-loaded route-without-dispatch:configured-native-route route-without-dispatch:no-dispatch; 4 assertions machine-checked; transcript SHA-256 efcabd5d9392649338949c12a33fb8ffe57e754b5cf9f0cf94ad7ec1c9a634fb; artifact-set SHA-256 e8e4cb5022085725301ad22219d6444dd393abbdc1c4e4bcb500fcbaa969ffc9.
  • Observation (claude / skill-invocation:create-formal-verification-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:create-formal-verification-skill: create-and-mutate; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 eac55677ce1b79980ddc446938560e8fddd9cc8c8f826d18f635ebd682b35b1d; artifact-set SHA-256 499226f34c8026aa7c47d6748ae77adf83c45704ed45b19e5e8be3cf38f9b702.
  • Observation (claude / skill-invocation:maintain-formal-verification-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe skill-invocation:maintain-formal-verification-skill: stale-model; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 f54d598e9b640686b2fcfa8cf6dfb148d03ff150ef54a32468db9f278847b3e3; artifact-set SHA-256 b79f7a3ea0e3313dfd885e37e997ac642c247e67527af0604e3b99b93460585b.
  • Observation (claude / project-skill): surface claude -p stream-json with the candidate plugin-dir; action recipe project-skill: doctor; result passed: doctor:exit-0 doctor:skill-loaded doctor:doctor-ran doctor:doctor-canonical-pass; 4 assertions machine-checked; transcript SHA-256 43ccb6b18f29bfc3f03837e285d664ca5a1501083e11ba0a43e5a8d94fe52208; artifact-set SHA-256 2e925cc77b3be70eaae9b864c35ca50eb6897a5d038d79f075707814dbc447e8.
  • Observation (codex / hook:startup): surface codex exec --json with the run-owned candidate installation; action recipe hook:startup: startup; result passed: startup:exit-0 startup:hook-context-injected; 2 assertions machine-checked; transcript SHA-256 4b163b8deafe2b79a98ead4e242bc966a47b28942fb1da7eec41e0a9a5a1e092; artifact-set SHA-256 30280c4cdfcb6d39c7097996fcf664dffb03d5913ce781e3bbb3cf4c47ad5860.
  • Observation (codex / skill-invocation:poteto-mode): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:poteto-mode: route-without-dispatch; result passed: route-without-dispatch:exit-0 route-without-dispatch:skill-loaded route-without-dispatch:configured-native-route route-without-dispatch:no-dispatch; 4 assertions machine-checked; transcript SHA-256 c38fb6a6807ea8ae90bc6f34e4316e83c1099e74ce309bb478a1014e6c488375; artifact-set SHA-256 75c578054cb1be036f25445058b1cfbe03e29cfb0920a3e0af6cfd08fcd5edca.
  • Observation (codex / skill-invocation:create-formal-verification-skill): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:create-formal-verification-skill: create-and-mutate; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 75214f73d19613c6587382cd943874c29826619199004e94f0b3679270c25a4f; artifact-set SHA-256 262d44dc58c9a3a8fa058ff4dfd98b9b181d05909974662c46e9a12485dc6850.
  • Observation (codex / skill-invocation:maintain-formal-verification-skill): surface codex exec --json with the run-owned candidate installation; action recipe skill-invocation:maintain-formal-verification-skill: stale-model; result passed 8 assertions; ids retained privately; 8 assertions machine-checked; transcript SHA-256 e00a600a1bf4f997e4b736f1556f483228adca0c30c3428d2dac979637df8dc6; artifact-set SHA-256 5727b08369e67a0c5c22b0e529abc412028d91db766aa25d054f4ac985ebfebf.
  • Observation (codex / project-skill): surface codex exec --json with the run-owned candidate installation; action recipe project-skill: doctor; result passed: doctor:exit-0 doctor:skill-loaded doctor:doctor-ran doctor:doctor-canonical-pass; 4 assertions machine-checked; transcript SHA-256 96ad4e4b19be7642b572d80cded87e705fc5f68e0414bc9f62f64e1a1f966421; artifact-set SHA-256 4155485ccd32e1df62c3720c4943dc69fc714824f6f0c41ff89f609d6fb6c502.
  • Policy: every new head requires a fresh run; this verifier does not change PR state, queue, or merge.

@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Live evidence: Open Pstack

  • Candidate SHA: dcd87bbe27aca17fe677f3b47cb1530101afc137
  • Base SHA: 0eacabdd48477847ac6e88657a28805842aefad4
  • Result: FAILED — verification did not complete; rerun required
  • Self-test: required in both harnesses
  • Planned sessions: 10 (limit 12)
  • Publisher revision: dcd87bbe27aca17fe677f3b47cb1530101afc137
  • Evidence-set SHA-256: cc92c16e2d28972bb824df8a6b3f68f7a337b5d8e0f9333a74b1ecfd58216c62
  • Policy: every new head requires a fresh run; this verifier does not change PR state, queue, or merge.

@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Superseded by #4; the review repairs move to a follow-up

Pull request 4 merged the same port v1.16.0 sync into adam/release with Cursor pstack 0.15.30 to 0.15.36 on top, so this PR's merge is now conflicting and its sync is redundant. The work that is not in adam/release yet is the verifier's repairs from this PR's Codex review and live-gate runs, and scripts/sync-port.sh: the operator-path registry mappings, the formal cases' bypassPermissions (without it Claude Code 2.1.316 refuses the generated skill's write and the create case fails, as run 2 here showed), routed eligibility by harness, the sync-commit check, and the cloud test's stale passive assertion. They are being rebased onto the new adam/release as a small follow-up PR with its own live gate.

Live-gate record on this PR: run 4 on 94998eb and run 5 on 92c09a0 passed all ten sessions in both harnesses (hook:startup, skill-invocation:poteto-mode, both formal skills, project-skill). Those heads carry the same runtime files as #4's first commit. No gate has exercised #4's second commit (0.15.30 to 0.15.36).

@fitziboy3-source

Copy link
Copy Markdown
Owner Author

Closed: superseded by #4; the review repairs continue in the follow-up PR.

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.

3 participants