The gate is about to become a required status check on main. A required
check that is path-filtered never reports on a pull request outside the
filter, and that pull request then waits forever on a check that will
never arrive. The suites read Markdown off disk with no build step, no
model key, and no network, so running them unconditionally costs well
under a minute.
Reactor now lives at github.com/openprose/reactor with its complete
history and a pinned copy of the Skill at skill-v0.15.0; its packages
(@openprose/reactor 0.3.3, reactor-cli 0.2.4, reactor-devtools 0.3.1)
publish from there and are labelled experimental (alpha).
This repository is OpenProse only again: the language spec, the Skill,
std/co, and the examples — installable and testable with no build step.
- Remove packages/reactor*, tools/eval-harness, the Reactor-driven
example suites and test kits, both Reactor workflows, and the vitest
aliases into packages/reactor/dist.
- Retire `prose react`, the reactor shell-out exception, and reactor.md
from the Skill; replace the README's Reactor section with a short
"Harnesses" pointer.
- Keep the four corpus-wide example guards as tests/open-prose/examples-corpus.
- Add ci-skill.yml: pnpm install --frozen-lockfile && pnpm test:skill —
the conformance suites now run in CI for the first time.
- Record the `prose react` and reactor-cli changelog entries under the
tags they actually shipped in.
The run-phase vocabulary (concepts/reactor.md, the spec titles) is
de-branded in a follow-up.
Dependency installs and CI jobs both executed code this repo never
reviewed. This closes those paths without changing what anything
resolves to.
pnpm 9 ran every dependency's install lifecycle script and had no
allow-list model, so CI executed install hooks from the whole tree on
every PR. pnpm 10.34.5 blocks them by default and carries the fix for
the fail-open integrity check in CVE-2026-50021. minimumReleaseAge holds
freshly published versions out of resolution for 48 hours, the window in
which a registry compromise is typically caught and yanked.
The two `*` peer ranges in reactor-cli were the only place the workspace
opted out of range discipline: any future major satisfied them, including
a hijacked one. Both now carry carets on the versions already resolved,
and the README install lines are pinned to match, since a 0.x caret does
not cross the minor line.
Third-party actions take the commit SHA their movable tags resolved to,
with a monthly grouped Dependabot entry so those pins do not go stale.
GitHub-maintained actions stay on tags as a stated trust decision rather
than a claim that pinning them would buy nothing.
The benchmark jobs needed the most work, since they run an external
repository's code with five LLM provider keys in scope. Dispatch inputs
now travel through the step environment as quoted variables instead of
being interpolated into shell. The pi version is hardcoded rather than
dispatchable: npm accepts package sources after the `@` — an alias, a
repository, a tarball URL — so an input in that position chose a package
rather than a version. The remaining ref override is documented as an
operator escape hatch whose clone target is fixed.
The publish job holds a credential that can publish under our name and
installed npm at latest before using it. It now pins an exact version
above the floor OIDC trusted publishing requires, and fails at that step
if the pin does not take.
CI also fails on a tampered or unsigned tarball now, checked per
publishable package rather than once at the root where npm would only
see dev tooling. The advisory audit runs alongside it as a signal, not a
gate.
Nothing re-resolves: no version or integrity line in the lockfile moves.
The open-prose skill ships as a plain folder, so everything under
skills/open-prose/examples/ reaches every install. Each runtime example
shipped a committed replay/ state-dir (around 480 binary world-model files), a
generator, and a test suite wired to the workspace through a dist alias with no
local package.json. That machinery is internal validation, not the template a
user lifts: it cannot run from a copied folder, and it shipped generated
artifacts nobody should copy.
Keep the shipped examples to what a user actually adapts, and move the
validation into the repo's test tree:
- Move each example's tests, generator, and committed replay/ into
tests/open-prose/examples/<name>/. The shipped example is now its .prose
contracts under src/, a README, and a .gitignore.
- Re-point the vitest include and the test scripts; the byte-deterministic
offline coverage runs unchanged, just rooted under tests/.
- Rewrite the example READMEs to point at the reactor CLI for producing and
replaying a run, and drop the stale committed-fixture sections.
- Update the examples-gate workflow description to match the new layout.
No language, CLI, or runtime behavior changes, and the example contracts are
untouched. Verified with the offline gate (REACTOR_OFFLINE=1): the conformance
suite, the relocated example tests, and the eval harness all pass.
* fix(cli): typecheck repository-reactor-bridge test against branded Receipt fields
#106 hard-branded the reactor Receipt identity fields (node: NodeId,
contract_fingerprint / fingerprints: Fingerprint) and added this bridge test in
the same commit, constructing the Receipt fixture from raw strings — so the test
was born failing tsc. CLI Release Check only runs on tools/cli + release-script
paths and main has no required checks, so #106 merged with the typecheck red and
it stayed hidden (no cli-path change re-ran the check) until a release-infra PR
surfaced it.
Author the fixture with the same brand constructors the production bridge uses
(asNodeId / asFingerprint from @openprose/reactor/internals). The constructors are
identity-at-runtime brands, so behavior is unchanged: the affected test passes
10/10 and tsc is clean.
Note: this unmasks a SEPARATE pre-existing failure, also from #106 — the
repository-ir compiler fixtures were regenerated with kind
"openprose.compile-phase-ir" while validateRepositoryIr and its tests still expect
"openprose.repository-ir" (23 failing tests). That is a distinct IR-reconciliation
fix, tracked separately.
* fix(cli): restore repository-ir v0 validator tests with CLI-owned fixtures
#106 migrated the SKILL compiler's golden outputs (repo-root
tests/open-prose/compiler/) from repository-ir v0 to compile-phase-ir v2, but the
CLI's own compile path (compileRepositorySource -> validateRepositoryIr ->
repositoryIrToTopology) stayed v0. repository-ir.test.ts and
responsibility-status.test.ts borrowed those golden files across the package
boundary, so the v0 validator was being fed v2 inputs -> 21 failing tests.
Give the CLI's v0 validator tests their OWN v0 fixtures under
tools/cli/tests/prose/fixtures/repository-ir/ (recovered from f12dcda~1, the last
commit before the migration; the CLI compiler and validator are unchanged since,
so they still describe the current contract). The two compilers no longer share
fixtures: the SKILL compiler's compile-phase-ir fixtures are validated by
compiler-ir.test.ts; these repository-ir v0 fixtures are the CLI's. A README in the
fixtures dir documents the split and the migration path.
No validator or compiler change (not papering over) — the v0 validator is simply
fed correct v0 inputs. tools/cli suite: 573 -> 594 passing; the v0 validator suite
is 30/30. The 2 remaining failures (quickstart's dangling deleted-demo reference
and the agent-observatory example's missing id) are unrelated non-IR #106 fallout,
tracked separately.
* chore: deprecate prose-cli npm publish flow; park the eval suite
The `prose` CLI (@openprose/prose-cli) is deprecated in favor of the reactor
harness (@openprose/reactor + @openprose/reactor-cli) and the SKILL/plugin. This
removes its npm publish flow (it will be marked deprecated on npm manually) and
parks the eval harness out of the working tree.
Rip out the prose-cli publish flow:
- delete .github/workflows/{release,cli-release-check,cli-real-harness-smoke}.yml
and scripts/release-preflight.sh (the "OpenProse Release" publisher + its
preflight/checks).
- drop the `cli` track from .version-bump.json (only the skill/plugin track
releases here now) and the prose-cli sections from RELEASE.md.
- decouple the root build/test/lint scripts from @openprose/prose-cli.
Park the eval suite (it is rethought from scratch in the reactor backlog):
- remove the judge-era harness tools/cli/src/evals (45) + tools/cli/tests/evals
(18) and spec/04-Evals.md; they are copied verbatim into the planning
backlog-reactor for rehydration, and the methodology is synthesized there.
The harness was import-isolated (no code imported it); removal breaks nothing.
- fix the now-dangling spec/02 cross-reference to 04-Evals.md.
- remove the obsolete quickstart.test.ts (it read a #106-deleted demo test file).
The reactor packages, the new reactor-native tools/eval-harness, the skill
examples gate, and plugin-manifest are unaffected; prose-cli still typechecks.
When reactor is already published, publish_pkg returns before its pnpm-pack
builds reactor/dist, so reactor-cli + reactor-devtools fail to resolve
@openprose/reactor (TS2307) on an idempotent re-run. Build all three up front.
Ships @openprose/reactor 0.3.0, @openprose/reactor-cli 0.2.0, @openprose/reactor-devtools 0.2.0: the Reactor harness (compile-once-intelligent then dumb reconciler, content-addressed receipts, cost scales with surprise) with the distilled ideal public API — curated front door, full @openai/agents passthrough, one typed handle, one Substrate, unified observe, branded ids, and additive forward seams for the fixpoint.
Prepare the Reactor packages for the interim 0.1.0-rc.2 release.
Narrow the package publish workflow to reactor-v* tags, bump Reactor and Cradle package versions, refresh the Cradle package pin for the rc.2 tarball, and update release-candidate evidence helpers and package docs.
* Fix CLI workflows for the pnpm-workspace consolidation
The Reactor consolidation moved the CLI into the pnpm workspace, but the
npm-to-pnpm workflow conversion was incomplete and broke CI on main.
- Add the missing pnpm/action-setup step before every setup-node that
sets cache: pnpm (cli-real-harness-smoke, cli-release-check, release).
Without pnpm on PATH, setup-node fails: "Unable to locate executable
file: pnpm".
- Rework the npm-package-smoke job to pack with pnpm. npm pack does not
rewrite the workspace: protocol dependency on @openprose/reactor;
pnpm pack does. The install smoke now resolves that dependency from a
locally packed reactor tarball so it does not depend on the registry.
* Build the Reactor dependency before the CLI compiles in CI
After the workspace consolidation the CLI typechecks and builds against
@openprose/reactor, which must be built first.
- Add a "Build workspace" step before every CLI typecheck/build step
(node-checks, release-tarball-smoke, cli-real-harness-smoke, and the
release workflow's verify-cli and release-assets jobs).
- Drop the deleted tools/cli/package-lock.json entries from
.version-bump.json so bump-version.sh --check no longer fails.
* Drop Node 18 from the CLI check matrix
The CLI now requires Node 20+ (engines.node >=20.0.0, enforced by
install.sh). The Node 18 matrix leg fails install.sh's version gate.
* feat(spec): declared ### Skills section with fail-closed compile resolution
Implements the spec from issue #60. Components declare required harness
skills via a `### Skills` section (colon form, e.g. `document-skills:pdf`).
`prose compile` resolves declared skills against ./skills/, ~/.claude/skills/,
~/.codex/skills/, and ~/.agents/skills/, and fails closed with
`skill_unresolved` before forwarding to the agent harness when any are
missing.
- Spec: skills/open-prose/contract-markdown.md gains a ### Skills row in
the Canonical Sections table and a ## Skills H2 covering colon naming,
search order, the BYO-harness invariant, and fail-closed semantics.
- Implementation: tools/cli/src/skills/declared.ts (parser + resolver +
directory walker + DeclaredSkillsUnresolvedError). Pure functions; no
I/O beyond readFile / readdir / stat.
- Wiring: tools/cli/src/commands/compile.ts pre-checks declared skills
before forwarding the compile prompt; fails closed with
CompileValidationError when any are unresolved. Gated behind the
existing skillPreflight option for test parity.
- Example: skills/open-prose/examples/declared-skills/ shows the
document-skills:pdf canonical pattern.
- Tests: 19 new (18 in declared.test.ts covering parser/resolver/walker/
error formatter; 1 in cli.test.ts asserting compile fails closed before
the harness is invoked when a declared skill is missing).
- BYO harness: OpenProse never installs harness skills; resolution failure
is the user's signal to install the named skill themselves.
Resolves#60.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(spec): move skill resolution into compiler program; trim spec per review
Address review feedback on #62:
- contract-markdown.md: drop the "not duplicated in frontmatter" clause —
the rejected alternative shouldn't propagate into the spec.
- contract-markdown.md: fail-closed clause now mentions only `prose compile`;
`prose run` enforcement is deferred per the PR description.
- compiler/index.prose.md: add a `skills_resolver` agent that owns the
search-path order, scope aggregation, BYO invariant, and fail-closed
semantics. Skill resolution is now a compiler/program-level
responsibility, not a harness responsibility, so other harnesses running
the compiler get the same behavior.
- skills/declared.ts: add a header comment pointing at the program-level
spec; this module is the harness implementation of `skills_resolver`.
- examples/declared-skills/README.md: update wording to reference the
compiler agent.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(ci): make smoke artifacts case-specific
* fix(ci): use deterministic audit policy
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
The `open-prose` plugin ships to two marketplaces (Claude Code and Codex) via three manifest surfaces with overlapping but drifted metadata. This change unifies copy across those surfaces behind a single declarative source, ships visual assets for the Codex `interface` block, gates drift in CI, and adds a maintainer-facing submission playbook to `RELEASE.md`.
## Changes
- **Copy sync** — `.plugin-meta.json` declares the canonical strings; `scripts/sync-copy.sh` writes them into every declared destination (mirrors `bump-version.sh`). `--check` mode asserts byte-equality and reports drift.
- **Unified manifests** — same descriptions across `.claude-plugin/`, `.codex-plugin/`, and `.agents/plugins/`. Registry name aligned to `openprose` (plugin name `open-prose` unchanged). Codex `skills` path normalized.
- **Visual assets** — `assets/plugin/logo.png` (512×512) and `assets/plugin/composer-icon.png` (64×64), wired into the Codex `interface` block with `brandColor` (`#8a6b2e`), `websiteURL`, and the icon slots.
- **CI gates** — four new steps in `.github/workflows/plugin-manifest.yml` covering copy sync, asset presence, Codex interface completeness, and unified registry names. Existing version-sync gate untouched.
- **Submission playbook** — new `## Marketplace submission` section in `RELEASE.md` covering Claude Code (live today) and the Codex Plugin Directory (curated; self-serve coming soon).
The CLI now ships first-party agent SDKs only. The `codex` harness —
a thin shim around `codex exec` — has been removed. Supported
harnesses: `codex-sdk`, `claude-sdk`, `mock`.
BREAKING CHANGE: `--harness codex` (and `PROSE_HARNESS=codex`) no
longer works. Switch to `--harness codex-sdk` for first-party,
in-process Codex SDK execution. `codex-sdk` remains the default,
so most users are unaffected.
- Delete `codex-cli.ts` and `process-harness.ts`; keep
`process-runner.ts` for the OpenProse skill installer
- Trim `codex-options.ts` to SDK-shaped helpers
- Drop `codex` from the smoke script and CI matrix
- Align README, post-release playtest, and package metadata
Moves `@openprose/prose-cli` from `cli/` to `tools/cli/` and seeds a
`tools/` convention at the repo root for shippable tooling published as
standalone artifacts. Package internals are unchanged — only paths
outside the package that hard-code the `cli/` segment were updated.
## What changed
- `git mv cli tools/cli` — package files render as 100%-similarity
renames, so `git log --follow` is preserved.
- `.github/workflows/cli-publish.yml`,
`.github/workflows/cli-release-check.yml`, and
`.github/workflows/cli-real-harness-smoke.yml`: every literal `cli/`
path (`paths:`, `working-directory:`, `cache-dependency-path:`,
artifact `path:`, and inline `node`/`bash` invocations) now points
at `tools/cli/`. `cli-skills-smoke.yml` had no `cli/` references and
is untouched.
- `tools/cli/package.json`: `repository.directory` and `homepage` flip
to `tools/cli` so the npm registry "Repository" link resolves.
- `README.md`: the badge nav, the prose-layout paragraph, and the repo
layout table now point at `tools/cli/`, plus a new `tools/` row
introducing the convention.
- `RELEASE.md`: cross-references to `cli/RELEASE.md` updated.
- `tools/cli/README.md`, `tools/cli/RELEASE.md`,
`tools/cli/POST_RELEASE_PLAYTEST.md`: public installer URL updated to
`https://raw.githubusercontent.com/openprose/prose/main/tools/cli/install.sh`.
OpenProse already installed as a Claude Code plugin via
`npx skills add openprose/prose`, but the packaging surface was
uneven: missing manifest fields, no native Codex envelope, no
plugin-track release process, and a couple of doc/audience
inconsistencies. This commit closes those gaps without changing
skill behavior.
OpenProse now ships from the repo root as a dual-host plugin
envelope — `.claude-plugin/` for Claude Code, `.codex-plugin/`
plus `.agents/plugins/` for Codex — with `skills/open-prose/`
as the shared core and `prose ...` as the only user-facing
command surface.
Codex envelope:
- .codex-plugin/plugin.json with first-class catalog metadata
(displayName, developer, descriptions, category, capabilities,
defaultPrompt, privacy/terms URLs).
- .agents/plugins/marketplace.json local-source catalog, installable
by anyone who clones this repo.
Claude Code manifest hygiene:
- Added license, homepage, and skills: ./skills so the plugin is
self-describing.
- Added marketplace.json metadata.description, clearing the sole
`claude plugin validate` warning.
- Deleted the stale .claude-plugin/README.md.
Skill metadata:
- Added license: MIT to skills/open-prose/SKILL.md frontmatter
(no top-level version — Claude Code strips unrecognized top-level
frontmatter keys; see anthropics/claude-code#13005).
- Fixed an inconsistent parse-table cell pair in
skills/open-prose/deps.md.
Audience boundaries:
- AGENTS.md is now contributor-only per agents.md.
- Recommended consumer [agents] Codex config moved to README.md
alongside the Quickstart.
Release process:
- scripts/bump-version.sh + .version-bump.json bump both manifests
atomically, with a --check mode for CI. The Claude Code
marketplace deduplicates by version, so a forgotten bump silently
strands users on cached copies; this gate prevents that.
- scripts/extract-changelog.sh pulls a single `## [X.Y.Z]` block
out of CHANGELOG.md.
- RELEASE.md documents the manual flow.
- .github/workflows/release.yml verifies declared versions match
on `v*` tag push and publishes a GitHub Release.
CI:
- New plugin-manifest.yml: every-PR gate validating both plugin.json
files, asserting declared skills paths resolve, and running
bump-version.sh --check.
- cli-skills-smoke.yml: added `npx skills list openprose/prose`
discoverability check alongside the existing install smoke.
- openprose-smoke/run.ts: removed a dead commands/prose-*.md regex.
Add a required smoke CI path for the `open-prose` skill.
- Add focused smoke fixtures for core OpenProse execution behavior.
- Add a TypeScript runner that installs the PR skill into isolated workspaces and validates `.prose/runs/` outputs.
- Add a GitHub Actions workflow with read-only permissions, fork safety, pinned tooling, artifact capture, and hardened Claude Code invocation.
- Validate the suite with both dry-run checks and a local live `9/9` smoke run.
Picks up the thinking choice input and RLMIFY_THINKING env wiring
from rlm-harness-skill so gh workflow run can pass -f thinking=<level>.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lets gh workflow run discover the rlmified LongCoT smoke workflow.
The shim, example, and skills/rlmify/ live on the rlm-harness-skill
branch; workflow_dispatch --ref rlm-harness-skill checks them out
at run time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
workflow_dispatch action that runs the LongCoT benchmark using
pi-mono (@mariozechner/pi-coding-agent) as the inference harness.
Defaults (difficulty=longcot, thinking=high, no tools/scaffolding,
2 retries) mirror the paper for 1:1 result comparison; README
covers iteration with longcot-mini + slice inputs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Jose Montes de Oca