## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Users can stop a run and send another message on the same task.
> - Remote runners need evidence from their sandbox provider that
execution stopped.
> - Local process checks cannot prove that a remote process exited.
> - This pull request records provider stop receipts and uses them for
conversation admission.
> - New user messages can proceed after confirmed cleanup without
repeating interrupted actions.
## Linked Issues or Issue Description
Refs #13237 and #13239. Related: #13163 covers app-restart recovery;
this change covers an explicit stop followed by a new user message.
**What happened?**
A stopped remote Claude ACP task kept its execution hold after Daytona
cleanup succeeded. Native runners also rejected remote process
identities and retained stale session cleanup gates. A message sent
during cleanup could stay deferred after the sandbox stopped.
**Expected behavior**
After the provider confirms that the old execution stopped, a new user
message starts a fresh turn. Pending user messages must not need another
message to trigger admission. Prior action outcomes remain recorded.
**Steps to reproduce**
1. Start a long-running task in Daytona with a legacy Claude ACP or
native ACP runner.
2. Cancel the run while its tool is active.
3. Send a new message immediately, or after cleanup completes.
4. Observe the execution hold despite the old sandbox having stopped.
**Paperclip version or commit**
Reproduced on master at 7b829efdf6. The
branch is rebased on current master.
## What Changed
- Add optional provider stop receipts to sandbox release and destroy
hooks. Old plugins remain compatible.
- Bind receipts to the company, run, lease, and provider resource.
Failed cleanup cannot supply stop authority.
- Acknowledge legacy remote cancellation after confirmed termination.
- Admit native user continuations using remote receipts instead of host
process checks.
- Retire only the settled cleanup owner matching the stopped company,
run, and provider resource. Isolate cleanup gates between remote
sandboxes, including two sandboxes owned by one run.
- Reconsider user messages deferred during remote cleanup through normal
admission, including successful later cleanup retries.
- Preserve receipts through cleanup retries and inline cleanup after
failed startup.
- Permit provider destruction after a terminal remote checkpoint
failure. Busy ownership still blocks destruction.
- Add regression tests and update execution semantics.
- Give the real preview fixture ten seconds for cold startup. Reuse
release-mode Rust artifacts for the filtered parity checks, avoiding a
duplicate debug test build that exhausted CI disk twice; test filters
and assertions are unchanged.
## Verification
- Recursive typecheck and build passed.
- Targeted server, Daytona plugin, and native runtime tests passed. They
cover missing or mismatched receipts, failed cleanup, local process
protection, exact cleanup ownership, and a message sent during cleanup.
- Live Daytona tests passed for legacy Claude ACP, native per-turn,
native warm, and a newly created native runner using disposable
sandboxes. Each original run was cancelled; its explicit follow-up
completed with no execution hold. The disposable case confirmed a new
sandbox after deletion.
- Native tests used the provider's Opus 5 selector, `opus[1m]`, and the
Linux runner bundle from the sandbox image. Existing checkpoint/sync
finalization warnings remained visible before the native follow-ups
reached committed success. This change does not repair those separate
warnings or guarantee recovery of uncheckpointed files.
- A direct live provider test also passed with the final delete-wait
change: the destroy hook returned its receipt only after Daytona
reported the sandbox destroyed. The final Daytona plugin suite passed
all 153 tests; its build passed.
- After rebasing on master, 284 targeted server/plugin tests and 313
native executor tests passed. The native session runtime suite passed
all 128 tests.
- The review regression passed all 145 tests across the continuation,
environment runtime, and pending-cleanup sweep suites. Recursive
typecheck and build passed again after that fix.
- The security review's exact-resource finding is fixed. Cleanup
completion requires the same provider-resource scope used during session
creation. All 128 native runtime tests, 61 server continuation/cleanup
tests, recursive typecheck, and build passed after this fix. The
two-sandboxes-in-one-run regression proves one receipt cannot retire the
other quarantine.
- Greptile reviewed the final commit at 5/5, the security scan passed,
and no review threads remain unresolved. The final native executor suite
also passed all 313 tests.
- The full local suite reached 10,616 passing tests before stopping on
four failures. All four now pass in focused reruns: the final-code
continuation/teardown suites, the attachment suite, and the native
session test after building its required fake-provider binary. The
original full run overlapped source edits and did not reach the
remaining groups; it is not counted as a full-suite pass.
- The preview exposure suite passed all 25 applicable tests (three
Linux-only tests skipped locally) after the startup allowance change.
Both release-mode Rust parity commands passed locally. All final-head PR
checks passed, including full server/workspace/browser test groups, full
native runner verification, build, typecheck, canary dry-run, and the
aggregate gates.
## Risks
- A provider must return a receipt only after confirmed termination.
Incorrect provider claims could permit overlapping execution.
- Older providers without receipts retain the existing hold. Missing
evidence, failed cleanup, active ownership, pauses, approvals, and
budgets still block admission.
- This change preserves unknown action outcomes and old checkpoints. It
does not authorize replay or alter historical runs.
- No database migration or telemetry contract change is required.
## Model Used
OpenAI GPT-6 through Codex, with repository inspection, code execution,
and browser tools. The exact backend revision and context-window size
are not exposed in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub references)
- [x] My branch name describes the change and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run targeted tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The Claude local adapter can run agent turns through an ACP (Agent
Client Protocol) server, `claude-agent-acp`, instead of the plain CLI
> - Two separate packages each pin their own copy of that dependency:
`packages/adapters/claude-local` (the server-side adapter) and
`packages/paperclip-runner` (which builds the provider pack baked into
every managed sandbox image)
> - `claude-local` moved to `^0.73.0` in #12730, but `paperclip-runner`
was never bumped past `0.70.0` — nothing keeps the two in sync when only
one changes
> - That split means a sandbox image built from `paperclip-runner`'s
provider pack ships a `claude-agent-acp` the server-side adapter was
never actually compatible with
> - This pull request bumps `paperclip-runner`'s pin to `0.73.0`, the
only version that satisfies both packages' declared ranges at once, and
fixes the matching hardcoded version assertion in
`docker/daytona-runner/Dockerfile`
> - The benefit is one consistent, compatible `claude-agent-acp` version
across both the server host and every sandbox image built from this
source, instead of a silent split that only surfaces as a runtime
failure
## Linked Issues or Issue Description
No public issue exists for this specific split; opening directly per
CONTRIBUTING.md path B, following the bug report template fields.
**What happened?**
`packages/paperclip-runner/package.json` pins
`@agentclientprotocol/claude-agent-acp` at an exact `0.70.0`.
`packages/adapters/claude-local/package.json` requires `^0.73.0` (added
in #12730, 2026-09-02). Nobody re-synced `paperclip-runner`'s pin after
that change — the two packages' dependency graphs are independent, so a
bump in one doesn't propagate to the other. `paperclip-runner`'s copy is
what the fleet sandbox image's provider pack actually ships, so every
managed sandbox built from current source carries a `claude-agent-acp`
version the server-side adapter's own declared compatibility range
excludes.
**Expected behavior**
The two packages' `claude-agent-acp` pins should stay within a mutually
compatible range, so a sandbox image built from this source always ships
a version the server-side adapter actually supports.
**Steps to reproduce**
1. Check `packages/adapters/claude-local/package.json`'s
`@agentclientprotocol/claude-agent-acp` range (`^0.73.0`).
2. Check `packages/paperclip-runner/package.json`'s pin for the same
package (`0.70.0` before this PR).
3. Note that `^0.73.0` on a `0.x` version only admits patch releases
(`>=0.73.0 <0.74.0` per semver caret rules), so `0.70.0` falls outside
it.
**Paperclip version or commit**
`master` as of this PR (paperclip-runner still at `0.70.0` prior to this
change; claude-local's `^0.73.0` requirement landed in #12730).
**Deployment mode**
Any deployment that runs `claude_local` agents through the ACP engine
against a sandbox image built from `packages/paperclip-runner`'s
provider pack (managed cloud sandboxes in particular).
Related PRs for context (not duplicates — none of these touch
`paperclip-runner`'s pin):
- #12730 — introduced the `^0.73.0` requirement in `claude-local`
- #11873 — the last time `paperclip-runner`'s pin moved (`0.69.0` →
`0.70.0`)
- #13105 — separately made an unavailable ACP engine a hard failure
instead of a silent CLI fallback, which is what turned this version
split into a visible, run-blocking error rather than a quiet downgrade
## What Changed
- Bump `@agentclientprotocol/claude-agent-acp` from `0.70.0` to `0.73.0`
(exact pin, matching this package's existing pin style for its other
agent-CLI dependencies) in `packages/paperclip-runner/package.json`.
- Update the corresponding hardcoded version assertion (`test
"$(claude-agent-acp --version)" = "0.70.0"`) in
`docker/daytona-runner/Dockerfile` to `0.73.0`, so its own build-time
check stays accurate instead of failing on the next build for an
unrelated reason.
- `pnpm-lock.yaml` is intentionally **not** included —
`pr-trusted.yml`'s `Validate dependency resolution and regenerate stale
lockfile` step already regenerates it for the merge tree and hands it to
downstream `--frozen-lockfile` jobs as an artifact, so a manual lockfile
commit here would just be stale the moment CI runs.
## Verification
- `0.73.0` is a real published version on npm (confirmed via `npm view
@agentclientprotocol/claude-agent-acp versions`), and it's the *only*
version satisfying claude-local's `^0.73.0` range, so this isn't a guess
at compatibility — it's the unique intersection of both packages'
declared ranges.
- `grep -rn "0\.70\.0" docker/ packages/paperclip-runner/package.json`
after this change shows no remaining stale references to the old pin.
- I did not run a full local install/test pass against a hand-updated
lockfile, since regenerating one locally would conflict with leaving
`pnpm-lock.yaml` untouched per the note above; CI's own
lockfile-regeneration step is the intended verification path for a
manifest-only dependency bump like this one.
- Downstream/full verification (does a sandbox image actually built with
this pin work end-to-end) is tracked separately in `paperclip-cloud` —
an unrelated internal-only repo, so not linked here — where a sibling
fix restores the ACP servers to the runtime `PATH` in the fleet sandbox
image itself; both fixes are needed together for a working sandbox, but
this PR is scoped to the version pin alone.
## Risks
- Low risk: single-line dependency version bump plus a matching
test-assertion update, no code changes. `0.73.0` is a patch release
within claude-local's own already-declared-safe range, so there's no
reason to expect it changes behavior tenants depend on.
- The main risk is unknown breaking changes between `claude-agent-acp`
0.70.0 and 0.73.0 that aren't caught by the version-string assertion
alone (that check only confirms the binary reports the right version,
not that its behavior is unchanged). I have not audited that package's
own changelog between those versions.
- `docker/daytona-runner/Dockerfile` is a parallel/reference image (per
its own header comment, meant to stay aligned with the private
`paperclip-cloud/fleet-sandbox-image/Dockerfile`, which is out of scope
here) — this PR does not touch that other Dockerfile.
## Model Used
Claude Sonnet 5 (`claude-sonnet-5`), via Claude Code, with tool use
(file edits, shell/git, `gh` CLI, `npm view` for version verification).
No extended-thinking mode. Standard Claude Code context window.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass — see Verification: a
manifest-only bump with the lockfile intentionally left to CI's own
regeneration step; no local test run applicable
- [x] I have added or updated tests where applicable — version-pin bump
only, no new behavior to test
- [x] I have updated relevant documentation to reflect my changes — none
applicable
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green — pending CI run on this PR
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups —
pending review
- [x] I will address all Greptile and reviewer comments before
requesting merge
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
## Thinking Path
> - Paperclip runs Codex locally and in remote sandboxes.
> - The runner must preserve startup configuration and session identity.
> - Missing project trust can disable repository configuration.
> - Full-history requests use deprecated provider fields.
> - Resume usage describes old work and must not become new run usage.
> - This change corrects startup trust, state reads, and usage
classification.
## Linked Issues or Issue Description
**What happened?**
Normal Codex runs could show repository-trust and history-deprecation
warnings.
Resume could report the preceding turn's token snapshot as a late-turn
warning.
The historical last-usage value could also be attributed to the new run.
**Expected behavior**
Trust the server-selected startup root in isolated configuration. Read
lightweight
provider state and paginated evidence. Use historical cumulative usage
as a
baseline without a new charge or user-facing warning.
**Steps to reproduce**
1. Start a native Codex task in a selected repository.
2. Finish the turn and resume the provider thread.
3. Inspect provider notices, history requests, and per-run usage.
4. Repeat startup and cold resume inside a Daytona sandbox.
**Paperclip version or commit**
Codex CLI 0.153.4 is the pinned runtime and reproduced baseline.
Replayed onto master at 6abeb6733. Related authority work: Refs #13092.
This PR retains its startup cleanup and protocol-integrity checks.
**Deployment mode**
Local source checkout and disposable Daytona sandbox.
## What Changed
- Classify the exact historical resume usage event before the generic
stale-turn warning.
- Persist cumulative usage baselines across recovery of the same run.
- Use excludeTurns on resume and lightweight thread reads.
- Page turn metadata and selected turn items with cursor and identity
validation.
- Reject unsupported or incomplete history instead of guessing that
execution is idle.
- Trust the startup execution root on its host, including Git worktree
trust keys.
- Start Codex in that root and retain the selected sandbox profile on
later turns.
- Keep unrelated isolated configuration and Codex's separate hook trust
policy.
- Add Rust, TypeScript, accounting, native integration, and local
run-log documentation.
## Verification
- Codex and native-transport TypeScript: 333 passed before PR replay.
- Adjacent OpenCode/ACPX driver and accounting tests: 49 passed.
- Rust library, serialized: 226 passed. Native Codex integration: 72
passed, 1 ignored, plus two pagination regressions.
- Repository typecheck and build passed. All repository test groups have
passing coverage after fixture and resource retests; the initial
monolithic command was not clean.
- Fresh real Codex native browser tasks returned correct answers without
the three targeted notices. Answers persisted after refresh and restart.
- Real same-thread TypeScript driver tests passed locally and in
Daytona, including cold resume, configuration, skills, and an approved
harmless hook.
- Local usage summed to 64,607 tokens. Daytona usage summed to 42,737
tokens. Each sum matched its final session total exactly.
- See doc/plans/2026-09-09-codex-integration-acceptance.md for the scope
and limits of the live tests.
- After replay onto current master and review fixes: 334 Codex, backend,
and live-session tests passed, including checkpoint serialization and
real-runner process restart. TypeScript checks passed.
- The native Codex integration run passed 83 tests; the large lineage
test passed separately with the release runner (its debug build exceeded
the test deadline).
- All GitHub checks passed on the final PR head. Greptile is 5/5 with no
unresolved review threads. CI regenerates the lockfile for the added
TOML dependency, per repository policy.
- The first server shard hit a timing-dependent duplicate-key failure in
the unchanged artifact-document concurrency test. Its focused 11-test
suite passed locally. One CI retry on the same head passed all 103 files
and 1,405 tests (2 skipped): [retry
result](https://github.com/paperclipai/paperclip/actions/runs/34398832930/job/102631274667).
## Risks
- Trust applies only to the server-selected startup root and isolated
configuration. Sandbox and tool permissions remain authoritative.
- Codex still requires approval of individual hook hashes. This change
does not bypass that policy.
- Providers without the required history APIs fail explicitly.
- Daytona acceptance used the production TypeScript driver. Remote
Paperclip UI and remote Rust execution were not tested.
- No new public API, database state, recovery policy, or UI control is
included.
## Model Used
OpenAI Codex, GPT-6 (`gpt-6-astra`). Used for reasoning, code edits,
tool use,
and test execution. The exact context-window limit is not exposed in
this
session. Real-provider acceptance used Codex CLI 0.153.4 with
`gpt-5.6-sol`.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` OR (b) described the issue in-PR following the relevant issue
template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip manages AI agents and their work.
> - The new runner gives agents dedicated tools for common tasks.
> - Some API operations and parameters have no dedicated tool.
> - Agents need a controlled way to find and use those operations.
> - This pull request adds API search and calls through the real server
routes.
> - Existing tools remain the preferred path. The new tools are disabled
by default.
> - Paired tests measure correctness, tool choice, cost and time.
## Linked Issues or Issue Description
**Subsystem affected**
Paperclip Runner contracts, production tool authority and the server API
catalog.
**Problem or motivation**
The runner cannot use much of the API described by the old Paperclip
skill. A generic HTTP client would also let agents bypass runner control
rules.
**Proposed solution**
Add `search_api` and `call_api`. Resolve calls from the mounted API
catalog. Use server-held, run-bound credentials. Preserve route checks
and runner lifecycle rules. Keep the tools disabled until an operator
enables selected companies.
**Alternatives considered**
A dedicated tool for every endpoint would add a large initial prompt. An
unrestricted HTTP tool would weaken authorization and replay controls.
**Roadmap alignment**
This extends the native runner tooling. The repository owner requested
this design and implementation. The roadmap and related open PRs were
checked. No duplicate API escape-hatch PR was found.
## What Changed
- Register two compact fallback tools in canonical contracts and
provider projections.
- Build deterministic API discovery from OpenAPI, mounted experimental
routes and the old skill reference.
- Execute bounded JSON, text, file and download requests through
authenticated HTTP routes.
- Recheck active runs, company access and work modes. Block runner
lifecycle, scheduling, credential and approval bypasses. Keep routine
annotation collaboration available.
- Retain mutation receipts. Report uncertain outcomes without blindly
repeating writes.
- Add a company rollout gate and a durable eval worker with complete
cost accounting checks.
- Record child-task creation in the activity log with the agent and run.
- Add contract, authorization, file, replay and real runnerd/PRP/HTTP
tests.
- Document rollout gates and paid coverage limits. The companion eval
repository retains immutable attempts and reports.
## Verification
- Final app commit `da58370524c3626a744eec20164397c5fb6ba9ef`: all 32
checks passed; the unrelated Storybook visual check was skipped.
Greptile 5/5; no unresolved review threads.
- Full Linux build and recursive typecheck passed. Repository tests were
run by project and serialized shard; all 143 serialized server suites
passed.
- Runner TypeScript: 1,599 passed, two skipped. Rust release: 451
passing test reports. Conformance and replay parity passed. The required
API check passed 837 tests, including runnerd → PRP → authority → real
HTTP.
- Bindings cannot enable API tools without the explicit deployment flag.
Unit and real-authority tests prove the default-off boundary.
- The standalone API check builds and stages its own binary. It passed
after existing staged and debug binaries were removed from the test
container.
- UI and CLI tests passed. Initial environment failures (missing jq,
Docker overlay file identity, and parallel linker memory pressure) and
focused passing reruns are retained. The macOS full runner suite has
platform-specific failures; Linux is the qualified full-check platform.
- Eval harness: 27 tests passed; existing CI discovery ran 86 tests with
two unrelated skips. Credential export rejection is tested against the
actual report command.
- Luna and OpenRouter Sonnet each passed 60 common-workflow runs: ten
workflows, three repetitions per arm, zero unnecessary API fallback.
- Sonnet passed 11 selected capability/contract cases after fixes.
Gemini passed three smoke cases. DeepSeek exceeded the 120-second limit
and remains unqualified.
- Luna's two cost flags received focused follow-up. The original flags
and a later n=1 latency flag remain visible. Sonnet had no cost or
latency increase above 20%.
- The catalog contains 785 entries; 58 were exercised across all stages.
Most operation probes remain unrun and some need additional fixtures.
Authored probes do not establish successful coverage.
- Total conservative accounted cost: $9.875960. Active paid-campaign
time: 88.16/90 minutes. No missing accounting. Later security and
harness fixes have provider-free verification; no paid validation is
claimed for those revisions.
- Inspect the [qualification
report](https://github.com/paperclipai/paperclip-evals/blob/codex/seach-call-api-tools/evals/runner-api-tools/reports/2026-09-07-production/READINESS.md)
and [verification
record](https://github.com/paperclipai/paperclip-evals/blob/codex/seach-call-api-tools/evals/runner-api-tools/reports/2026-09-07-production/verification.json).
## Risks
- This is a broad authenticated API surface. Keep the default-off gate
until an operator selects initial rollout companies.
- Paid coverage is incomplete. Small regression samples do not prove all
workflows are unchanged.
- A timeout or server failure can follow a committed mutation. The
result reports an unknown outcome and requires state inspection.
- The new definitions add prompt tokens. The report retains cost flags
and cache variation.
- No database migration is required.
- Repository rules require code-owner approval before merge. Technical
CI and automated review are complete.
## Model Used
OpenAI Codex based on GPT-6 assisted with code, tests and review. The
exact serving model ID and context window are not exposed in this
session. It used reasoning, tool calls and code execution.
Eval models: `gpt-5.6-luna` with low reasoning,
`openrouter/anthropic/claude-sonnet-5`,
`openrouter/google/gemini-3.8-flash`, and
`openrouter/deepseek/deepseek-v4-flash-0731`. Attempts retain runtime
versions, model identity, usage and source provenance.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
- Paperclip Runner needs its runtime preinstalled for fast sandbox
startup.
- Native and local adapters should launch one current CLI installation
per provider.
- An older global copy can shadow that installation, and exact native
compatibility pins must match it.
- Update the qualified releases and binary digests, expose shared CLI
entrypoints from the provider pack, and prefer the image-owned bin
directory.
- Keep dependency installation in the image build; task startup only
discovers, links, and verifies artifacts.
## Linked Issues or Issue Description
**What happened?**
Remote native startup rejected a stale global Codex, while CLI-only
images lacked runnerd entirely.
**Expected behavior**
An image-baked runtime starts without uploading binaries or installing
packages. All adapters share the same current provider CLI.
**Steps to reproduce**
Start a native remote task with the old global Codex and the updated
runtime available only under `/opt/paperclip-runner/bin`.
**Paperclip version or commit**
Discovery behavior at `54a99d884`.
**Deployment mode**
Docker with a remote sandbox.
## What Changed
- Prefer `/opt/paperclip-runner/bin`, then the user's local bin
directory, then PATH. Existing metadata and version validation remains
in force.
- Qualify Codex 0.153.4, OpenCode 1.18.29, and Claude SDK 0.3.263 / CLI
2.1.263. Update binary digests, TypeScript/Rust checks, registry
defaults, and the displayed OpenCode version together.
- Share Codex and Claude's native executable with the ACP bridges
through exact dependency overrides. Preserve the separately qualified
ACP bridge implementations and their security patches.
- Expose shared provider-pack CLI launchers; fail the pack build if
Codex ACP resolves a separate Codex installation. Update the eval
image's other agent CLIs to current stable releases and remove duplicate
global provider installs.
- Document the single-current-CLI policy in source comments and
development guidance. Latest stable releases are resolved at
review/build preparation and pinned; task startup never auto-updates.
## Verification
- Native-session and adapter-registry suites: 158 tests passed.
- Provider suites: 88 tests passed, 7 Linux-only checks skipped on
macOS. One existing macOS temporary-path alias assertion passed when
rerun with canonical `TMPDIR=/private/tmp`.
- Package-contract and OpenCode materialization tests: 11 passed.
- Full typecheck, build, and token gates passed. Rust
native-provider/recovery tests: 19 passed.
- Broad local suite: 5,974 passed, 23 failed, 41 skipped. Failures are
in unchanged macOS workspace/path/port and connection suites; focused
runtime tests pass. All latest-head Linux PR checks passed, including
the full test shards, typecheck, build, runner verification, browser
suites, and canary dry run.
- The standalone fleet image built with one current provider CLI each
and passed native Codex/Claude binary-integrity checks. A disposable
Daytona sandbox reported ready in 798 ms; its baked runner completed an
API-key `gpt-5.6-luna` turn in 2,430 ms and returned the expected marker
with a usage receipt. No runtime artifacts were uploaded or installed.
- The normal shared `codex exec` entrypoint also completed an API-key
`gpt-5.6-luna` turn in 2,321 ms.
- Both image builds verify the complete generated lockfile against a
reviewed SHA-256 before package installation or lifecycle execution.
Root lockfile changes remain CI-owned. Merge and rollout remain on hold
for operator review.
## Risks
- Updating provider CLIs changes their behavior for all adapters;
version probes and live native smoke testing are required before image
promotion.
- The image-owned directory takes precedence. Its entries must launch
the same shared CLI as the global PATH, not a private older/newer copy.
- Application qualification pins and the deployed image must move
together. No startup fallback installation is added.
- No schema or authentication-policy changes.
## Model Used
OpenAI GPT-6 (Codex). The session does not expose a more specific model
ID or context-window size. Used reasoning, repository inspection, code
execution, and browser verification.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Direct Runner evals retain evidence across model configurations.
> - Evalbook already has a grid and a read-only Runner Lab chat viewer.
> - Public projection stripped the view and selected a second plain
result page.
> - This change uses the existing viewer for public and private results.
> - The data access differs, but the presentation does not.
## Linked Issues or Issue Description
Refs #12931, #12945. Related open runtime-contract PR #11634 does not
contain this report-only change.
**What happened?**
The public direct-eval campaign opened plain result pages. The
access-controlled artifact used the chat viewer. Users could not follow
the same recorded interaction from the published grid.
**Expected behavior**
Every newly generated Runner Evalbook opens the existing chat viewer.
The grid and durable run history remain. Public evidence has explicit
redactions.
**Steps to reproduce**
Open campaign gha-34062394019-1 from the direct-eval history. Click a
result, then compare its plain page with the corresponding Actions
artifact.
**Paperclip version or commit**
Reproduced at 83987210d6.
**Deployment mode**
Static GitHub Actions artifacts and S3/CloudFront publication.
Companion site-theme renderer:
https://github.com/paperclipai/paperclip-evals/pull/19. This removes the
Python light theme and links the same built stylesheet.
## What Changed
- Add a closed public chat projection. Require mock isolation evidence
before publishing recorded text. Scrub private references and withhold
tool payloads, reasoning and provider state.
- Validate public HTML against the exact trusted viewer shell and asset
bytes. Validate the public DTO and local links. Keep CSP restrictions on
outbound requests and forms.
- Make the workflow render both data projections with the canonical
viewer. Pass a viewer-only artifact to the trusted publisher. Reject an
old renderer pin before paid execution.
- Fix report-only start position, missing-state inspector, read-only
controls and redaction labels. Tool evidence links select and highlight
the Evidence tab even when reopened. Runner execution and the full-stack
E2E workflow are unchanged.
- Add a no-model report refresh command. Preserve original campaign
identity, measurements and immutable history; label report revisions.
- Document the single presentation and public/private evidence boundary.
- Use one Runner Lab stylesheet and local fonts for the grid, Latest,
test design, inventory, server gate and S3 history index. Keep static
styles scoped away from live chat.
- Emit exact published report/history URLs to the Actions summary and
job outputs only after successful upload. Set the deployment link from
that output.
- Switch public Eval and Evidence panes without rendering both at once.
- Add all-run history with like-for-like pass-rate and cost timelines,
regression/recovery lists, exact commit links, source refs and Actions
links.
- Record all-attempt costs including retries. Keep provider list cost
separate from estimates. Label missing coverage and historical
final-only costs.
- Retain all run records beyond 200, backfill a separate derived
analytics projection, and exclude report refreshes from measurements.
## Verification
- Focused report/publishing/projection/workflow/adapter tests: 29
passed.
- Workflow Evalbook adapter tests: three passed.
- Viewer unit tests: eight passed; Vite viewer build passed.
- Companion renderer tests: 59 total, 57 passed, two inventory tests
skipped because the expected sibling checkout is absent.
- Re-rendered all 375 retained attempts from the completed campaign and
validated the public bundle. Zero new model calls; 356/358 selected
cells still pass.
- Browser walkthrough: grid to failed chat; prompt, named tool calls,
correct blocked status, visible assertions, no loading spinner or
composer. Public payload redactions are explicit.
- Full typecheck and build passed locally. test:run ended with 17 failed
files and 19 failed tests in unrelated server/worktree areas (3772 tests
passed). Latest-head CI is the final merge gate. The browser sources
also typecheck with a temporary TypeScript-7-compatible path
configuration; the checked-in browser config still uses removed baseUrl
options and is unchanged here.
- Real Chromium verification passed for passing, failing and
missing-recording attempts in both the full and public bundles. It
checks tool expansion, navigation, reload, read-only controls, narrow
viewport visibility and the public no-network boundary. Future
publications run it automatically.
- Fresh live proof: three gpt-5.4-mini native Codex cases passed on the
first attempt (get-task-context, create-child-task,
workflow-context-document-progress); estimated total $0.00632625.
Generated the full canonical report and verified all three file://
pages, all seven DevTools tabs, and evidence cross-links in Chromium.
Private screenshots remain local.
- Follow-up 99697c2c5: viewer build, eight unit tests, browser token
gate and browser-source typecheck (existing TS7 configuration
workaround) passed. Added repeated tool-to-evidence navigation to the
publication browser gate.
- Site-theme follow-up: 26 publishing/security tests, 59 Python tests
(57 passed, two existing skips), eight viewer unit tests and the viewer
build passed. Chromium verified shared colors and
grid/test-design/Latest navigation.
- Re-rendered all 375 retained attempts with the shared site theme,
without new provider calls.
- Successful hosted publication: [refreshed
Evalbook](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-34062394019-1-report-site-theme-v3/index.html)
and [themed
history](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/index.html).
Real browser verified grid → test design → chat → All results and
history → run.
- Full maintained live suite completed on AWS: [Actions run
34074939112](https://github.com/paperclipai/paperclip/actions/runs/34074939112),
Paperclip 856813ba3a, evals
34e1846c06a39e641182dadce5de7ea739f657f1. All 358 cells across 11
configurations ran; 355 passed (99.2%), two behavior failures and one
infrastructure failure. Nine configurations are entirely green. All 360
retained attempts were rendered using the new design and published as an
immutable, zero-provider-call report refresh: [full
Evalbook](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-34074939112-1-report-history-v1/index.html).
The trusted master workflow ran the models; this PR's viewer rendered
their results afterward.
- Remaining live failures: native Codex mini did not emit the expected
discovery event for lazy-unauthorized-undisclosed (no mutation
occurred); GLM 5.3 scheduled a wake before approval in
workflow-governed-wait; GLM 5.3 timed out on create-task-document on
both attempts. No scoring rules were relaxed.
- Retry-inclusive recorded estimated model cost is at least $7.067692,
with usage for 357/360 attempts. Provider-reported list cost is a
separate alternative (at least $14.002806), not an additive cost.
Missing usage is unknown, not zero; AWS compute is excluded.
- [Production
history](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/index.html)
now contains nine model runs and two separately labeled report
refreshes. Matching full-suite comparison reports three newly failing
cells and two recoveries versus the previous run. This is observed
run-to-run variation, not proof of a deterministic code regression. Live
HTTP checks verify the newest report link, shared theme, exact source
SHAs and cost analytics.
- The new full report passed Chromium checks for passing, failing and
missing-recording chat pages, tool-to-Evidence links, grid/design/Latest
navigation, reload, read-only controls and narrow layouts. The Mac was
locked during final hosted verification; the new hosted history was
checked by HTTP and generated-page browser checks, not a fresh
interactive desktop walkthrough.
- History follow-up: 31 publishing/security/metrics tests pass. Viewer
build passes. Chromium checks desktop and narrow history pages with no
document-level horizontal overflow.
### Visual verification
Generated from the scrubbed completed campaign; no private provider
identities or raw tool payloads are included. Full private pages were
also browser-tested, but their private metadata is not published as
screenshots.
Latest shared-theme proof:
## Risks
- Public chat text is newly visible, but only for the isolated mock
boundary. The producer excludes raw payloads and the publisher fails
closed on unknown fields, secrets, shell changes and asset
substitutions.
- Requires the companion canonical renderer revision and an updated
RUNNER_PROTOCOL_EVALS_SHA after merge. Old pins fail before paid
execution.
- Existing published campaigns remain immutable. A report refresh is a
separate history entry, not a new model qualification.
- Successfully published the immutable site-theme refresh with the
configured report-bucket SSO profile. Original run records and
qualification pointers are preserved.
## Model Used
OpenAI Codex, GPT-5-based coding agent with reasoning, shell and browser
tools. Exact deployment model ID and context-window size are not exposed
in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green on
cad99dbf04
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
on cad99dbf04
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Paperclip Runner includes an issue-thread viewer for direct
Evalbook reports.
> - The runner package uses Vite 6.4.3.
> - Dependabot changed the React plugin from version 4.7.0 to version
6.1.1.
> - React plugin 6.1.1 requires Vite 7 or Vite 8 package internals.
> - The live evaluation workflow found this mismatch when it built the
viewer on a clean Linux worker.
> - This pull request restores the compatible plugin and adds the viewer
build to pull request CI.
> - The benefit is that CI detects this class of report-viewer build
failure before a paid evaluation campaign starts.
## Linked Issues or Issue Description
**What happened?**
The direct live evaluation workflow failed before model execution. The
`build:issue-thread` command could not load `@vitejs/plugin-react@6.1.1`
with Vite 6.4.3. The plugin imported the unavailable `vite/internal`
package path.
**Expected behavior**
The Evalbook issue-thread viewer must build from a clean frozen-lockfile
installation before the live evaluation matrix starts.
**Steps to reproduce**
1. Check out commit `165ca56a22adb60e5fda56045442d9c8498116a8`.
2. Run `pnpm install --frozen-lockfile --ignore-scripts`.
3. Run `pnpm --filter @paperclipai/paperclip-runner build:issue-thread`.
4. Observe the `ERR_PACKAGE_PATH_NOT_EXPORTED` error for
`vite/internal`.
**Paperclip version or commit**
`165ca56a22adb60e5fda56045442d9c8498116a8`
**Deployment mode**
Built from source in GitHub Actions on Ubuntu.
## What Changed
- Restore `@vitejs/plugin-react` 4.7.0 in the Vite 6 runner package.
- Follow the repository policy: trusted PR CI regenerates and verifies
the lockfile artifact, and the master refresh workflow commits the
lock-only update after merge.
- Build the Runner Evalbook viewer in pull request CI.
## Verification
- `ci / policy`: regenerated the dependency lock artifact successfully
- `pnpm --filter @paperclipai/paperclip-runner build:issue-thread`
- `actionlint .github/workflows/pr-trusted.yml
.github/workflows/runner-protocol-live-evals.yml`
- `node --test
packages/paperclip-runner/scripts/runner-protocol-eval-workflow-security.test.mjs`
- `git diff --check`
## Risks
Low risk. This change restores the previous React plugin major version
for one package. The selected version declares support for Vite 6. Pull
request CI now builds the affected viewer directly.
> This bug fix does not add or change a roadmap feature.
## Model Used
- OpenAI Codex with GPT-5. Tool use and code execution were enabled. The
Codex app managed the context window.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Runner executes agents through native and managed provider
drivers.
> - The direct live eval layer had drifted from the current Runner
contracts.
> - The old local workflow did not provide a complete parallel campaign
or durable report history.
> - The Runner also needed current native OpenCode and OpenRouter
qualification.
> - This pull request restores the direct campaign, corrects the runtime
gaps that the campaign found, and adds safe hosted Evalbook history.
> - The benefit is repeatable model comparison against an immutable
Runner and eval source revision.
## Linked Issues or Issue Description
Refs #11297
Refs #11634
**What existing behavior does this improve?**
This improves the direct live `paperclip-runner` eval workflow, provider
execution contract, and static Evalbook reporting path.
**Current behavior**
The direct evals do not have one maintained full campaign on current
`master`. OpenCode has no qualified multi-model OpenRouter roster.
Parallel provider bursts can compact committed events before the
transport observes them. Local reports do not have a separate safe S3
history index.
**Proposed behavior**
Run one immutable roster-plus-case matrix. Use the shared paid AWS
runner fleet. Keep raw artifacts access-controlled. Publish a sanitized
canonical Evalbook report under the separate `runner-protocol-evals` S3
prefix. Keep immutable campaign directories plus root history, latest,
and latest-green pointers.
**Reason and benefit**
Maintainers can compare native Codex, native OpenCode, ACPX, Claude
Managed, and AWS AgentCore behavior over time. They can inspect failures
without mixing this direct protocol layer with browser full-stack E2E.
**Breaking changes**
None. The new workflow and S3 prefix are additive. The existing Runner
full-stack E2E workflow and report remain separate.
## What Changed
- Added a trusted two-shard direct live workflow for up to 393
roster-plus-case cells.
- Reused the numeric actor allowlist, protected paid environment, and
RunsOn fleet controls from Runner full-stack E2E.
- Added immutable Runner and eval revision resolution, exact credential
boundaries, bounded retries, and cost ceilings.
- Added a public report projection that removes sessions, transcripts,
tool payloads, state, traces, raw failures, remote profile identities,
and credential-shaped values.
- Added additive S3 history under `runner-protocol-evals`, with
immutable campaigns and mutable root index pointers.
- Added native OpenCode model injection and current OpenRouter pricing
contracts.
- Fixed direct eval completion, workflow execution, semantic discovery,
warm-attach state reset, executable binding, and event-burst handling.
- Kept Runner browser full-stack E2E behavior and publication separate.
- Documented local and hosted direct eval operation.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner
test:runner-protocol-eval-publish` — 15 passed.
- `pnpm --filter @paperclipai/paperclip-runner build:typescript` —
passed.
- `actionlint .github/workflows/runner-protocol-live-evals.yml
.github/workflows/runner-full-stack-e2e.yml` — passed.
- Local current matrix at the revision in
[paperclip-evals#17](https://github.com/paperclipai/paperclip-evals/pull/17)
— 323 cells across 10 enabled configurations completed.
- Final local current matrix — 269 passed, 11 behavior failures, and 43
expected macOS-only ACPX platform failures.
- Targeted Runner checks — 13/13 eval-session tests, 15/15
publisher/security tests, and package typecheck passed; complete PR CI
is green, including all browser E2E shards.
## Risks
- Paid live campaigns can consume provider budget. Actor authorization,
exact per-cell ceilings, protected environments, and explicit schedule
enablement bound this risk.
- Public reports can leak provider data. The workflow publishes only a
separately projected report and validates every file before upload.
- The new workflow cannot publish until it is present on the default
branch. This pull request does not change the existing
`runner-full-stack-e2e` publication path.
- The campaign is large. It uses two GitHub matrices and caps combined
concurrency at the shared fleet limit.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex on GPT-5. The exact deployment ID and context-window size
are not exposed. The model used reasoning, code editing, browser
inspection, repository tools, and live provider execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip manages AI agents that perform work.
> - Paperclip Runner connects durable task runs to local provider
processes.
> - The full-stack paid matrix exposed failures after the runner
integrity repair.
> - Verified JavaScript entrypoints lost their relative module graph
when Linux executed them through descriptor paths.
> - Returned provider startup errors also remained pending and became
indeterminate after recovery.
> - Sparse Codex tool lifecycle events lost the `write_document`
identity before task transcript projection.
> - This pull request repairs those three boundaries and makes the
structured-question fixture deterministic.
> - The benefit is repeatable provider startup, exact failure replay,
and correct inline Plan placement.
## Linked Issues or Issue Description
Refs #12721 and #12700.
**What happened?**
The paid runner matrix failed ACPX and OpenCode startup before provider
session creation. The runner journal then replaced the original startup
error with an indeterminate recovery result. Native Codex saved a Plan
but rendered it only as a fallback card. A legacy Claude waiting reply
could also echo the reserved terminal marker before the answer arrived.
**Expected behavior**
Verified JavaScript providers must start from immutable
descriptor-backed artifacts. Returned startup failures must persist as
terminal failed command results. Native tool lifecycle updates must
preserve the `write_document` boundary. Pre-answer fixture output must
not contain the reserved terminal marker.
**Steps to reproduce**
1. Run the local provider cells in the Runner Full-Stack E2E workflow.
2. Observe ACPX and OpenCode fail during `session.open` before provider
execution.
3. Observe recovery report `execution_indeterminate` instead of the
original startup error.
4. Run the native Codex Plan cell and observe the fallback Plan card
after the tool activity row.
5. Run the legacy Claude structured-question resume cell and observe an
early marker echo in waiting prose.
**Paperclip version or commit**
`0f9452101740835ce0b1488a204bf48acd5bafc3`
**Deployment mode**
Local development with the paid GitHub Actions acceptance workflow.
## What Changed
- Bundle the ACPX sidecar and OpenCode proxy as self-contained Node ESM
entrypoints before hashing and verified descriptor launch.
- Anchor ACPX dynamic provider package resolution at a
controller-derived provider-pack root and keep that root out of the
provider child environment.
- Persist executor-returned startup errors as redacted durable failed
command results while retaining indeterminate recovery for true process
death.
- Coalesce sparse native tool items by stable ID so a late
`write_document` name, input, and result reach the transcript boundary
once.
- Forbid the structured-question fixture from spelling or announcing its
reserved terminal marker before the user answers.
## Verification
- Rust and TypeScript regression tests cover durable failed replay, true
crash ambiguity, bundle closure, package-root derivation, environment
filtering, exact Codex tool lifecycle coalescing, and prompt
determinism.
- Local execution is intentionally limited to formatters and static diff
checks. GitHub Actions will run tests, type checks, builds, and security
checks.
- After ordinary CI is green, scoped paid cells will validate one ACPX
launch, one OpenCode launch, native Codex Plan projection, and legacy
Claude structured resume before a complete matrix rerun.
- Prior failing matrix:
https://github.com/paperclipai/paperclip/actions/runs/33682434315
## Risks
- Bundling changes the bytes covered by provider launch hashes.
Provider-pack generation already hashes the final built files.
- ACPX still loads qualified provider packages dynamically. The
controller supplies a normalized package root, while existing version,
digest, path, and descriptor checks remain active.
- Durable `failed` is terminal. Replays return the same redacted result
and do not execute the provider effect twice.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex based on GPT-5 with agentic reasoning, repository
inspection, code editing, Git, parallel subagents, and GitHub Actions
coordination. The exact deployed snapshot and context-window size are
not exposed to this task.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked related public work or described the bug in
this PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
ticket id
- [ ] I have run tests locally and they pass (intentionally deferred to
GitHub Actions)
- [x] I have added or updated tests where applicable
- [x] No documentation change is required for this runtime repair
- [x] I have considered and documented the risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip manages AI agents and their provider runtimes.
> - Paid runner validation installs target dependencies with lifecycle
scripts disabled.
> - OpenCode leaves a sentinel executable until its package lifecycle
script runs.
> - Running arbitrary lifecycle code would weaken the paid-secret
boundary.
> - This pull request materializes one exact pinned binary before
secrets are exposed.
> - The benefit is working OpenCode validation without trusting
dependency install scripts.
## Linked Issues or Issue Description
**What happened?**
Every local OpenCode paid cell stopped before provider startup because
`pnpm install --ignore-scripts` correctly retained
`opencode-ai/bin/opencode.exe` as a sentinel.
**Expected behavior**
The trusted workflow must make the exact lockfile-pinned OpenCode
executable available without running package lifecycle scripts.
**Steps to reproduce**
Run a local legacy or native OpenCode paid cell from the trusted
workflow after the target dependency install. The provider health check
reports that the OpenCode postinstall script was not run.
**Paperclip version or commit**
Default branch commit `865b4854fb44d3689f1c0ff17e3e715d52aaea73`.
## What Changed
- Materialize only `opencode-linux-x64-baseline@1.18.17` into the
matching `opencode-ai@1.18.17` package.
- Verify package identity, version, regular-file type, SHA-256 equality,
executable permissions, and runtime `--version`.
- Invoke the helper for local OpenCode and breadth cells and for remote
provider-pack assembly.
- Retain `pnpm install --ignore-scripts`.
- Add helper and trusted-workflow security regressions.
## Verification
- Helper syntax checks passed.
- Helper unit tests passed: 2/2.
- Workflow-security tests passed: 5/5.
- Prettier, actionlint, and diff whitespace checks passed.
## Risks
Risk is low and contained to paid runner setup. The helper supports only
Linux x64, fails closed on package or version drift, and runs before
provider credentials enter the job.
## Model Used
OpenAI GPT-5 Codex with repository tools and code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change.
- [x] I have specified the model used.
- [x] I have checked ROADMAP.md and confirmed this does not duplicate
planned core work.
- [x] I have searched GitHub for duplicate or related PRs and found
none.
- [x] I have described the issue in this PR with the bug template
labels.
- [x] I have not referenced internal or instance-local issues.
- [x] My branch name describes the change.
- [x] Focused local tests pass.
- [x] I added tests for the change.
- [x] I updated the runner E2E security documentation.
- [x] I documented the risks above.
Bumps
[@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react)
from 4.7.0 to 6.1.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/vitejs/vite-plugin-react/releases">@vitejs/plugin-react's
releases</a>.</em></p>
<blockquote>
<h2>plugin-react@6.1.1</h2>
<h3>Add <code>compiler.logDiagnostics</code> option</h3>
<p>Recoverable React Compiler diagnostics are no longer logged by
default. Set <code>compiler.logDiagnostics</code> to <code>true</code>
to log them through Vite. Fatal diagnostics are always logged and fail
the transform.</p>
<h3>Respect environment sourcemap option for React Compiler transform
when <code>builder.sharedPlugins</code> is enabled (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1439">#1439</a>)</h3>
<p>The React Compiler transform was using the top-level sourcemap option
instead of the environment sourcemap option. This caused a problem when
the experimental <code>builder.sharedPlugins</code> was enabled.</p>
<h2>plugin-react@6.1.0</h2>
<h3>Add experimental native React Compiler support (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1419">#1419</a>)</h3>
<p>Add experimental native React Compiler support.</p>
<p>You can use it by installing <code>oxc-transform-react</code> and
enabling it via the <code>compiler</code> option:</p>
<pre lang="sh"><code>npm install -D oxc-transform-react
</code></pre>
<pre lang="js"><code>import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
<p>export default defineConfig({<br />
plugins: [<br />
react({ compiler: true })<br />
]<br />
})<br />
</code></pre></p>
<h2>plugin-react@6.0.5</h2>
<h3>Fixed the react compiler preset filter to be linear (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1353">#1353</a>)</h3>
<p>The improved filter in v6.0.3 was non-linear and caused a performance
regression (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/issues/1349">#1349</a>).
The filter was changed to be linear to avoid that.</p>
<h2>plugin-react@6.0.4</h2>
<h3>Fixed <code>$RefreshSig$ is not defined</code> error when running
<code>vite dev</code> with <code>NODE_ENV=production</code></h3>
<p>When running <code>vite dev</code> with
<code>NODE_ENV=production</code>, the app errored with
<code>$RefreshSig$ is not defined</code>.
This error is now fixed.</p>
<h2>plugin-react@6.0.3</h2>
<p>No release notes provided.</p>
<h2>plugin-react@6.0.2</h2>
<h3>Allow all options in reactCompilerPreset (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1189">#1189</a>)</h3>
<p>This is a type only change. Only <code>compilationMode</code> and
<code>target</code> options were available for
<code>reactCompilerPreset</code>.</p>
<h2>plugin-react@6.0.1</h2>
<h3>Expand <code>@rolldown/plugin-babel</code> peer dep range (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1146">#1146</a>)</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react/CHANGELOG.md">@vitejs/plugin-react's
changelog</a>.</em></p>
<blockquote>
<h2>6.1.1 (2026-08-28)</h2>
<h3>Add <code>compiler.logDiagnostics</code> option</h3>
<p>Recoverable React Compiler diagnostics are no longer logged by
default. Set <code>compiler.logDiagnostics</code> to <code>true</code>
to log them through Vite. Fatal diagnostics are always logged and fail
the transform.</p>
<h3>Respect environment sourcemap option for React Compiler transform
when <code>builder.sharedPlugins</code> is enabled (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1439">#1439</a>)</h3>
<p>The React Compiler transform was using the top-level sourcemap option
instead of the environment sourcemap option. This caused a problem when
the experimental <code>builder.sharedPlugins</code> was enabled.</p>
<h2>6.1.0 (2026-08-19)</h2>
<h3>Add experimental native React Compiler support (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1419">#1419</a>)</h3>
<p>Add experimental native React Compiler support.</p>
<p>You can use it by installing <code>oxc-transform-react</code> and
enabling it via the <code>compiler</code> option:</p>
<pre lang="sh"><code>npm install -D oxc-transform-react
</code></pre>
<pre lang="js"><code>import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
<p>export default defineConfig({<br />
plugins: [<br />
react({ compiler: true })<br />
]<br />
})<br />
</code></pre></p>
<h2>6.0.5 (2026-07-30)</h2>
<h3>Fixed the react compiler preset filter to be linear (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1353">#1353</a>)</h3>
<p>The improved filter in v6.0.3 was non-linear and caused a performance
regression (<a
href="https://redirect.github.com/vitejs/vite-plugin-react/issues/1349">#1349</a>).
The filter was changed to be linear to avoid that.</p>
<h2>6.0.4 (2026-07-22)</h2>
<h3>Fixed <code>$RefreshSig$ is not defined</code> error when running
<code>vite dev</code> with <code>NODE_ENV=production</code></h3>
<p>When running <code>vite dev</code> with
<code>NODE_ENV=production</code>, the app errored with
<code>$RefreshSig$ is not defined</code>.
This error is now fixed.</p>
<h2>6.0.3 (2026-06-23)</h2>
<h3>Improve the react compiler preset filter to reduce false-positives
(<a
href="https://redirect.github.com/vitejs/vite-plugin-react/pull/1138">#1138</a>)</h3>
<p>Improved the filter in the react compiler babel preset to reduce the
false-positives so that less modules are processed by the react
compiler.</p>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="04cac5020e"><code>04cac50</code></a>
release: plugin-react@6.1.1 (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1440">#1440</a>)</li>
<li><a
href="82d35abe49"><code>82d35ab</code></a>
fix(react): respect environment sourcemap option when
<code>builder.sharedPlugins</code>...</li>
<li><a
href="397e8471a5"><code>397e847</code></a>
fix(react): make logging diagnostics an opt-in for React Compiler (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1431">#1431</a>)</li>
<li><a
href="61006e6f52"><code>61006e6</code></a>
fix(deps): update all non-major dependencies (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1433">#1433</a>)</li>
<li><a
href="e2a649cbaa"><code>e2a649c</code></a>
chore: use <code>deps.neverBundle</code> instead of
<code>external</code> in tsdown config (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1430">#1430</a>)</li>
<li><a
href="fb2d6f3635"><code>fb2d6f3</code></a>
fix(deps): update all non-major dependencies (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1427">#1427</a>)</li>
<li><a
href="39b31735bf"><code>39b3173</code></a>
release: plugin-react@6.1.0 (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1428">#1428</a>)</li>
<li><a
href="f1340b0c76"><code>f1340b0</code></a>
feat(react): add native React Compiler support (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1419">#1419</a>)</li>
<li><a
href="9ab698eafc"><code>9ab698e</code></a>
fix(deps): update all non-major dependencies (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1375">#1375</a>)</li>
<li><a
href="68c0cb8796"><code>68c0cb8</code></a>
release: plugin-react@6.0.5 (<a
href="https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react/issues/1362">#1362</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/vitejs/vite-plugin-react/commits/plugin-react@6.1.1/packages/plugin-react">compare
view</a></li>
</ul>
</details>
<details>
<summary>Maintainer changes</summary>
<p>This version was pushed to npm by <a
href="https://www.npmjs.com/~GitHub%20Actions">GitHub Actions</a>, a new
releaser for <code>@vitejs/plugin-react</code> since your current
version.</p>
</details>
<br />
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner subsystem executes agent work across local and managed
provider backends.
> - The lower pull requests restore the task runtime, provider backends,
and managed-provider control plane.
> - The restored system needs repeatable full-stack checks before it can
ship safely.
> - Paid live checks also need clear access, cost, and secret controls.
> - This pull request adds acceptance, live evaluation, chaos, and
release gates for the restored runner stack.
> - The benefit is measurable runner parity with safer release
decisions.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This change covers runner tests, release workflows,
server contracts, and evaluation tools.
**Problem or motivation**
The runner stack did not have one complete acceptance surface for native
Codex, ACPX, Claude Managed, and AWS AgentCore. Release checks could
miss provider drift, task-view regressions, cost-policy errors, and
destructive cleanup errors.
**Proposed solution**
Add a 57-cell full-stack catalog, a Daytona image, and opt-in paid
workflows. Add live evaluation, chaos, cost-limit, redaction, and
release contract checks. Add AWS AgentCore infrastructure and guarded
provisioning tools. Keep the native runner experimental flag off by
default.
**Alternatives considered**
We considered manual smoke tests only. They do not give repeatable
evidence and they do not protect release branches. We also considered
one large pull request. The stacked pull requests keep each review below
the Greptile file limit.
**Roadmap alignment**
This work supports the shipped Cloud / Sandbox agents milestone and the
shipped Agent evals & feedback milestone in `ROADMAP.md`.
Related stack:
- #12699 adds managed provider backends and lifecycle support.
- #12691 adds qualified OpenCode and ACPX provider backends.
- #12685 restores task runtime rendering and steering.
## What Changed
- Add the runner full-stack harness with 57 catalog cells and 60 unit
tests.
- Add a Daytona runner image with digest-pinned base images and
base-aware image-content checks.
- Add guarded live evaluation and chaos workflows with a fixed
40-execution matrix; live and full-stack paid schedules now run only on
Sundays or by manual dispatch.
- Add in-flight reported-usage cost stops, post-turn cost caps,
exact-threshold failure classification, secret redaction, retry
classification, and actor authorization.
- Reattach stream and hard-budget listeners before restart-recovery
continuations so restored paid sessions cannot bypass in-flight
interruption.
- Preserve OpenCode usage and cost across tool-loop messages and turns
while exposing an explicit current-run delta to durable accounting.
- Keep PNG/WebM evidence in access-controlled artifacts only, reject
SVG, and publish only pruned inert structured per-attempt evidence.
- Add AWS AgentCore infrastructure, provisioning checks, and smoke
tools; reject unsafe model identifiers, require exact stack ownership
markers, and make failed-stack replacement explicit.
- Add evaluation-session contracts and capability reports.
- Add release workflow checks for immutable action pins, frozen
dependency installs, exact weekly cron shape, paid-run guards,
provider-secret isolation, and chaos test paths.
- Reauthorize the original and triggering numeric actor IDs as the first
step of every provider-secret job, including partial reruns, before
checkout or provider access.
- Give each full-stack matrix cell only its matching provider
credential, expose Daytona only to Daytona cells, and disable shared
dependency caches anywhere paid credentials or OIDC write access are
present.
- Protect the legacy manual E2E workflow with the same default-branch,
allowlist, environment, and per-job authorization boundary.
- Rotate live-eval candidates by week and retain 120 days of compatible
history so the seven-week trend window remains viable.
- Restore the root runner-acceptance commands and reconcile reported
snapshots,
raw receipts, and terminal usage without double counting or losing late
usage.
- Mark ACPX token deltas exact only when every budget field is present,
keep
cumulative cost/request authority separate, reject non-USD cost
labeling,
and include thought tokens in output-token budgets.
- Keep `enableNativeRunner` off by default. The acceptance harness
enables it only in its isolated test instance.
## Verification
Passed locally:
- `pnpm --filter @paperclipai/paperclip-runner typecheck`
- `pnpm test:runner-acceptance:typecheck`
- `pnpm test:runner-acceptance` (19 tests)
- focused OpenCode proxy, driver, runnerd transport, live-session, and
turn-stream tests (106 tests)
- `pnpm --filter @paperclipai/paperclip-runner exec vitest run
src/live/clean-room-server.test.ts` (22 tests)
- `pnpm test:e2e:runner:typecheck`
- `pnpm test:e2e:runner:unit` (62 tests)
- `node --test scripts/__tests__/release-verify-workflow.test.mjs`
- `pnpm --filter @paperclipai/paperclip-runner
test:runner-workflow-evals` (22 tests)
- `pnpm -r typecheck`
- `pnpm build`
- `node --test
packages/paperclip-runner/scripts/aws-agentcore-provisioning.test.mjs`
(6 tests)
- `git diff --check`
- `cargo test --manifest-path
packages/paperclip-runner/runner/Cargo.toml -p paperclip-runner-core
--lib --locked` (161 tests)
- focused ACPX provider-event tests (10 tests)
- The rebased PR changes 92 files. `pnpm-lock.yaml` is unchanged.
I did not run paid live provider jobs or provision AWS resources. Those
checks need credentials and can create cost.
## Risks
The paid workflows can create provider cost. They require an allowlisted
original and triggering actor, the protected `runner-e2e-paid`
environment, explicit opt-in variables, and cost limits. The four
provider credentials exist only in that master-only environment, which
requires allowlisted reviewer approval and disables administrator
bypass; repository and organization Actions scopes contain no copies.
Provider usage arrives after a billable request, so the live guard
cannot prevent one request from crossing a threshold. It interrupts
immediately on the first reported threshold hit and permits no
continuation.
Visual evidence can contain secrets rendered as pixels. PNG/WebM remain
only in access-controlled workflow artifacts; SVG and per-attempt XML
are excluded, and S3/Pages receive a pruned structured dashboard.
The AWS scripts can create cloud resources. They use explicit commands,
least-privilege roles, KMS encryption, saved nonsecret metadata, and
explicit teardown.
This pull request does not enable the experimental native runner for
existing instances.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex with GPT-5. The model used extended reasoning, tool use,
code execution, and parallel subagents.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner needs repeatable evaluation contracts.
> - Evaluation code must stay separate from provider launch and
production orchestration.
> - Offline fixtures need stable compatibility, scoring, traceability,
and report rules.
> - Published Runner consumers need only the supported evaluation
contract surface.
> - This pull request adds offline evaluation tooling and a
workspace-private matrix kernel.
> - The benefit is deterministic evaluation without credentials or paid
provider calls.
## Linked Issues or Issue Description
Refs #11297
This pull request extracts the offline evaluation unit from the earlier
aggregate Runner work.
## What Changed
- Add a workspace-private, provider-neutral evaluation matrix kernel.
- Add the public `@paperclipai/paperclip-runner/evals` compatibility and
native execution contracts.
- Add fail-closed runnerd artifact and protocol compatibility checks.
- Add deterministic workflow catalogs, scoring, traceability, and report
generation.
- Add sanitized Codex, OpenCode, and ACPX fixtures.
- Add package-boundary and clean-consumer checks.
- Add the eval package manifest to the Docker dependency stage.
- Add the generated protocol fixture digest without changing the
lockfile.
## Verification
GitHub Actions must run:
- Runner TypeScript and Rust type checks.
- Runner unit and protocol tests.
- Evaluation kernel tests.
- Workflow traceability checks.
- Clean-consumer and package-boundary checks.
- Repository test, type-check, build, policy, and security gates.
No local test command was run. The repository owner requested
GitHub-only verification.
## Risks
This is a large greenfield review surface with 51 files. The code does
not launch a live provider or load credentials. Package and protocol
drift fail closed. The workspace lockfile remains under the existing
CI-owned process.
## Model Used
OpenAI Codex with the GPT-5 agent model. The work used high reasoning,
repository inspection, tool use, and parallel code review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner package already provides the production protocol and
execution spine.
> - Contributors still need stable SDK surfaces, deterministic test
tools, and local inspection tools.
> - Those surfaces share generated contracts and must change as one
package boundary.
> - This pull request adds the package-local SDK, labs, examples, and
drift checks.
> - The benefit is a reviewable developer platform that does not change
application execution selection.
## Linked Issues or Issue Description
**Subsystem affected**
`packages/paperclip-runner` — runner SDK, conformance tools, and
developer tooling.
**Problem or motivation**
The production runner spine is present, but package consumers cannot
build deterministic integrations, inspect sessions, or verify
provider-neutral behavior through supported surfaces.
**Proposed solution**
Add browser, React, standalone, live-session, scenario, conformance, and
evaluation surfaces. Add generated contract inventories and
package-local verification scripts. Keep production application routing
unchanged.
**Alternatives considered**
We considered splitting each generated catalog, SDK surface, and demo
into separate pull requests. Those changes share exports, fixtures, and
drift gates. Splitting them would create intermediate package states
that do not build.
**Roadmap alignment**
No overlapping item appears in `ROADMAP.md`. This work extends the
runner package that is already on `master`.
## What Changed
- Add browser, React, standalone, live-session, and issue-thread SDK
surfaces.
- Add deterministic mock control-plane, scenario, conformance, replay,
and evaluation tools.
- Add bounded Codex, OpenCode, and ACPX development transports and
fixtures.
- Keep deferred managed-provider execution fail-closed. Persisted
compatibility data remains readable.
- Add generated capability inventories with their source files and drift
checks.
- Add examples, package documentation, browser checks, and
clean-consumer checks.
- Preserve the reviewed protocol bounds, replay compatibility aliases,
process environment isolation, and semantic redaction limits.
- Update the ACPX package patch that the existing workspace patch
registry already tracks.
- Do not change `pnpm-lock.yaml`, repository workflows, server runtime
selection, or the application UI.
## Verification
GitHub Actions is the verification authority for this pull request. The
repository CI, package TypeScript and Rust checks, package tests,
generated-output drift checks, browser checks, security scans, and
Greptile review must pass on the exact head.
Local test suites were not run because this series uses parallel GitHub
Actions for verification.
## Risks
This is a large greenfield package change. The main risks are public
export drift, generated-output drift, and optional React consumer
compatibility. Package boundary checks, clean-consumer checks, and
browser tests cover those risks. Production adapter selection and server
execution are outside this pull request.
## Stack
1. **This PR:** runner SDK and developer tooling.
2. [Codex production server
integration](https://github.com/paperclipai/paperclip/pull/12616).
3. [Provider-neutral task-thread
UI](https://github.com/paperclipai/paperclip/pull/12617).
## Model Used
OpenAI Codex, GPT-5, high-reasoning mode, with tool use and code
execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have described the issue in-PR following the feature request
template
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip Runner already has a hardened ACPX path for Codex.
> - Claude can reuse that protocol only with an exact package/model
profile and provider-lifetime fencing.
> - Pi needs a separately spawned runtime whose executable does not yet
have the descriptor-confined verified launch used by the ACP server.
> - This pull request therefore activates Claude only and keeps Pi
unavailable before installation or process launch.
## Linked Issues or Issue Description
**Subsystem affected**
Paperclip Runner ACPX driver, runtime host, sidecar, backend factory,
package dependency, and provider conformance tests.
**Problem or motivation**
The production ACPX backend was Codex-only. Claude needs the same
fail-closed model, authorization, cancellation, cleanup, and recovery
boundaries without exposing an unsafe secondary runtime path.
**Proposed solution**
Generalize the hardened ACPX runtime for the exact qualified `claude`
profile, add the pinned Claude ACP package and reviewed isolation patch,
and reject Pi before installation, backend construction, sidecar
initialization, Rust session admission, or process creation.
**Alternatives considered**
Activating Pi in this PR was rejected after security review because its
secondary runtime executable was pathname-based and lacked the verified
descriptor/snapshot boundary. Pi is deferred to a dedicated follow-up.
Replaying the older generic ACPX implementation was rejected because it
predates current hardening.
**Roadmap alignment**
ROADMAP.md does not list a conflicting ACPX-provider project. This
extends the existing Runner provider architecture.
## What Changed
- Generalized the ACPX backend, driver, runtime adapter, host, and
sidecar for the qualified Claude profile.
- Added Claude ACPX activation through its exact pinned package/model
pair and isolated-settings patch.
- Added provider-lifetime fencing for non-Codex qualified ACPX sessions.
- Kept Pi dependencies and its patch out of the package and build
configuration.
- Added fail-closed Pi rejection at driver validation, backend
construction, runtime-host admission, sidecar initialization, and Rust
session validation.
- Added focused tests for Claude selection, model enforcement, lifecycle
fencing, cancellation, recovery, and Pi rejection.
- Did not change or commit `pnpm-lock.yaml`; CI regenerates the PR
lockfile under the existing repository policy.
## Verification
- GitHub Actions is the authoritative verification environment for this
PR.
- CI runs dependency policy, runner package checks, protocol parity,
typecheck, build, security, and stack policy.
- Local tests were not run because this checkout is resource
constrained, per the requested workflow.
## Risks
- Claude package behavior can drift from the qualified protocol; the
package and patch are pinned and admission verifies the exact profile.
- Unsupported providers and models fail closed.
- Pi remains unavailable until descriptor-confined verified launch
exists for its separate runtime.
- Existing Codex ACPX behavior remains covered by shared conformance
tests.
> For core feature work, check [ROADMAP.md](ROADMAP.md) first and
discuss it in #dev before opening the PR. Feature PRs that overlap with
planned core work may need to be redirected.
## Model Used
OpenAI Codex, GPT-5.6, with repository tools, code execution, and
parallel agent review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs
- [x] I have described the issue in the PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name contains no internal task identifier
- [ ] I have run tests locally and they pass — GitHub Actions is
authoritative for this resource-constrained checkout
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation
- [x] I have considered and documented risks
- [ ] All applicable Paperclip CI gates are green
- [ ] Greptile is 5/5 with no actionable findings
## Stack
- Position: lowest unmerged PR
- Base: `master`
- Previous:
[#12588](https://github.com/paperclipai/paperclip/pull/12588), merged
qualified OpenCode runtime
- Next: [#12591](https://github.com/paperclipai/paperclip/pull/12591),
native application integration
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner provides a durable execution boundary for supported
providers.
> - The current production runtime supports Codex but cannot execute
OpenCode sessions.
> - OpenCode needs a qualified transport, strict input mapping, and
normalized events.
> - This pull request adds the OpenCode runtime as one isolated provider
unit.
> - The benefit is a reviewable provider expansion that does not weaken
the existing Codex path.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting: packages/paperclip-runner and the Codex-local adapter
configuration contract.
**Problem or motivation**
Paperclip Runner has provider-neutral contracts, but the production
backend factory cannot start a qualified OpenCode session. This blocks
OpenCode from using the durable runner path.
**Proposed solution**
Add the qualified OpenCode app-server proxy, driver, MCP bridge,
backend, fixtures, and factory wiring. Keep existing Codex behavior
unchanged.
**Alternatives considered**
Keeping OpenCode only on the direct adapter path would avoid this
runtime work, but it would not provide durable runner recovery or
normalized provider events.
**Roadmap alignment**
ROADMAP.md does not list a conflicting provider-runtime project. This
change extends the existing Paperclip Runner architecture.
## What Changed
- Added the qualified OpenCode app-server proxy and input queue.
- Added collaboration-mode and provider-event normalization.
- Added the OpenCode MCP bridge and native session backend.
- Added strict fixtures and focused unit coverage.
- Added only the package exports and adapter configuration required by
this runtime.
- Kept deferred SDK, lab, eval, and public package surfaces out of this
change.
## Verification
- GitHub Actions is the authoritative verification environment for this
PR.
- Run the package type checks and focused OpenCode tests in CI.
- Run repository typecheck, test, build, security, and policy gates
through the stack-aware workflow.
- Local tests were not run because this checkout is resource
constrained.
## Risks
- OpenCode protocol changes could affect event normalization or
recovery.
- The driver fails closed on malformed input and unsupported runtime
behavior.
- Existing Codex selection remains unchanged unless the stored provider
is OpenCode.
> For core feature work, check [ROADMAP.md](ROADMAP.md) first and
discuss it in #dev before opening the PR. Feature PRs that overlap with
planned core work may need to be redirected.
## Model Used
OpenAI Codex, GPT-5.6, with repository tools, code execution, and
parallel agent review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked existing issues or described the issue in-PR
following the relevant issue template
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [ ] I have run tests locally and they pass — GitHub Actions is
authoritative for this resource-constrained checkout
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Stack
- Position: 1 of 4
- Base: master
- Next: additional qualified provider runtimes
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner needs a bounded process boundary for each qualified
provider runtime.
> - The ACPX contract, Codex profile, structured questions, and recovery
rules now exist in the package.
> - The package does not yet provide an executable that applies those
rules to a real Codex ACPX host.
> - Provider admission must retain process, credential, and cleanup
ownership on every failure path.
> - A production selector must not depend on an unreviewed
provider-generic sidecar.
> - This pull request adds one installable Codex-only ACPX sidecar and
leaves it unselected.
> - The benefit is a testable package boundary for later runnerd
integration without changing current execution selection.
## Linked Issues or Issue Description
Refs #12409
Refs #12386
This pull request implements the Codex-only executable for the ACPX
sidecar contract merged in #12386. It builds on the question conformance
gate merged in #12409. Runnerd and the server do not select this
executable in this pull request.
## What Changed
- Publish the `paperclip-runner-acpx-sidecar` package binary and
document its current boundary.
- Add a versioned stdin/stdout sidecar that admits only the qualified
Codex ACPX profile and exact initialized model.
- Support atomic session open, run attachment, turn start and
cancellation, tool and input resolution, session read and snapshot, safe
suspension, close, and recovery identity checks.
- Bind runtime directory, workspace, permission mode, provider identity,
run identity, and semantic tool catalog before use.
- Validate completion and blocked results against the PRP result
contract. Bound pending tools, pending inputs, messages, events, usage,
diagnostics, and errors.
- Redact provider output and convert file locations to bounded
workspace-relative display data. Do not treat displayed paths as
file-access authority.
- Harden verified executable loading, module resolution, launch
environment filtering, process-group guardianship, and provider
termination.
- Retain managed credentials and every failed-admission resource until
the exact provider cleanup proves ownership was released.
- Keep failed-admission cleanup alive with bounded backoff until the
provider exits. Do not scrub credentials or admit a replacement while
cleanup still owns the provider.
- Use one runtime-host cleanup-owner registry and preserve sequential
cleanup retries across command timeouts and shutdown.
- Arm a credential-free same-group watchdog before provider admission so
guardian death reaps even a stopped provider; retain an independent
kernel EOF proof before releasing credentials.
- Add sidecar process, lifecycle, location, package, driver, credential,
installation, runtime-adapter, and runtime-host regression tests.
- Add `tsx` as a package test-only development dependency for the real
TypeScript sidecar process test.
## Verification
- Replay base: `b93ad538b63c81a1e3d24bbb54c02f8effdea787` (`master`
after #12409 merged).
- Exact replay head: `ca7e93f4385c37289c82b360ca8def0d88c1bd00`.
- Stable patch ID for the resolved 18-file delta:
`d293717a1e9f2485b61c553c58ea37690fc0a4fa`.
- The intended pull request delta contains exactly these 18 files:
- `packages/paperclip-runner/README.md`
- `packages/paperclip-runner/package.json`
- `packages/paperclip-runner/src/cli/acpx-runtime-sidecar.ts`
- `packages/paperclip-runner/src/cli/acpx-runtime-sidecar.test.ts`
- `packages/paperclip-runner/src/cli/acpx-sidecar-lifecycle.ts`
- `packages/paperclip-runner/src/cli/acpx-sidecar-locations.ts`
- `packages/paperclip-runner/src/cli/acpx-sidecar-locations.test.ts`
- `packages/paperclip-runner/src/drivers/acpx/codex-acpx-driver.ts`
- `packages/paperclip-runner/src/drivers/acpx/codex-acpx-driver.test.ts`
- `packages/paperclip-runner/src/drivers/acpx/codex-credentials.ts`
- `packages/paperclip-runner/src/drivers/acpx/codex-credentials.test.ts`
- `packages/paperclip-runner/src/drivers/acpx/codex-runtime-adapter.ts`
-
`packages/paperclip-runner/src/drivers/acpx/codex-runtime-adapter.test.ts`
- `packages/paperclip-runner/src/drivers/acpx/installation-integrity.ts`
-
`packages/paperclip-runner/src/drivers/acpx/installation-integrity.test.ts`
- `packages/paperclip-runner/src/drivers/acpx/runtime-host.ts`
- `packages/paperclip-runner/src/drivers/acpx/runtime-host.test.ts`
- `packages/paperclip-runner/test/acpx-codex-package-contract.test.mjs`
- The resolved combined delta is 4,725 additions and 665 deletions; it
preserves the lower-PR runtime-close semantics, repairs stale
successful-admission fixtures, deterministically observes renewed
reconciliation, accepts authoritative same-host cleanup recovery without
dropping pending owners, ignores superseded cleanup failures after a
newer owner recovers, and requires both guardian exit and independent
provider-lifetime EOF before releasing cleanup or credential ownership.
A readiness-gated, credential-free watchdog also reaps a stopped
provider if its guardian is externally killed.
- This change updates the runner package manifest, README, and test-only
dependencies. It does not change `pnpm-lock.yaml`, a workflow,
migration, server route, UI path, runnerd selection, or current
direct-adapter behavior.
- Focused GitHub verification: **PASSED** for the sidecar process,
lifecycle, location, package-contract, driver, credential,
installation-integrity, runtime-adapter, and runtime-host suites on the
replayed head.
- Package verification: **PASSED** for the clean tarball, Node shebang,
and exact binary mapping on the replayed head.
- GitHub Actions and security checks: **PASSED** for the replayed exact
head; full CI run `33357846557` completed 23/23 jobs successfully, and
Superagent, Socket, Snyk, supply-chain, and contributor-trust checks are
green. Storybook was intentionally skipped because this PR does not
touch its paths.
- Greptile: **5/5** on the exact head with zero unresolved review
threads.
- No local test result is claimed. GitHub Actions is the authoritative
verification environment for the replayed revision.
## Risks
This change has medium security and lifecycle risk because the new
executable crosses a process, credential, filesystem, and provider
boundary. The sidecar fails closed on unsupported providers, models,
permissions, identities, catalogs, forms, commands, and persistent-state
deletion. A cleanup owner can remain alive until a stubborn provider
exits. Its retries use bounded backoff, and admission stays closed while
ownership remains. Command and shutdown waits remain bounded without
abandoning the underlying cleanup. The new `tsx` dependency is
development-only. The package exposes a new binary, but no runnerd,
server, UI, or direct-adapter path starts it in this pull request.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex with GPT-5.6, extended reasoning, repository tool use, and
code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The package-local host boundary is ready for a concrete ACP
implementation, but the first production profile is Codex only.
> - ACPX must not inherit the server process environment or choose an
executable by pathname after admission.
> - Codex must not re-enable ambient apps, memory, skills, MCP
configuration, or instructions inside its isolated home.
> - This pull request pins only the two required production packages and
applies narrowly tested host patches.
> - The benefit is a minimal dependency boundary that follows the
repository's CI-owned lockfile process.
## Linked Issues or Issue Description
**Agent or provider**
Codex through `acpx@0.13.1` and `@agentclientprotocol/codex-acp@1.6.2`.
**Why this adapter is useful**
The injected runtime host needs a concrete ACP session manager and the
exact reviewed Codex ACP server. Upstream ACPX does not yet expose a
host-owned spawn callback, and upstream Codex ACP does not yet apply
Paperclip's isolated instruction, MCP, app, memory, and skill boundary.
Both behaviors are required before the dependency can execute inside the
runner.
**How the agent is invoked**
The next pull request will adapt these pinned packages to the private
runtime host. ACPX receives a host-owned callback that consumes the
already verified executable lease. Codex receives only the isolated
environment, explicit base instructions, explicit MCP servers, and the
skills rooted in its private `CODEX_HOME`. This pull request alone does
not spawn either package or register an adapter.
**Additional context**
This pull request is stacked on #12399. It adds no Pi, Claude, AWS, SDK,
lab, browser, or UI dependency. It intentionally does not commit
`pnpm-lock.yaml`: the repository policy job regenerates a manifest-only
PR lockfile artifact for downstream frozen installs, and the lockfile
bot updates master separately.
## What Changed
- Pin `acpx` to `0.13.1` and the Codex ACP server to `1.6.2` in the
runner package.
- Register both patches in the pnpm 9 root configuration and newer-pnpm
workspace configuration.
- Preserve the existing embedded-Postgres and ACPX 0.12 patch entries
used by other packages.
- Patch ACPX to evaluate an allowlisted environment at child-spawn time
and keep spawn cwd out of provider-visible session identity.
- Patch ACPX to accept a host-owned spawn callback with the resolved
arguments and options, allowing the verified command lease to own
execution.
- Patch Codex ACP to retain runner-owned MCP server identity in
permission requests.
- Patch Codex ACP to pass explicit Paperclip base instructions on both
start and resume.
- In isolated mode, disable ambient apps, memory, and existing MCP
configuration; load skills only from `CODEX_HOME`; and configure only
requested servers.
- Add a package contract test that enforces exact versions, Codex-only
dependency scope, both pnpm patch registries, and every required patch
hook.
## Verification
- Both patch files dry-apply successfully to fresh published tarballs
for `acpx@0.13.1` and `@agentclientprotocol/codex-acp@1.6.2`.
- A local no-lockfile install applied both patches; their runtime
markers and exact installed versions were inspected.
- Runner TypeScript typecheck — passed against the patched packages.
- Runner package tests — passed: 16 Node protocol/package tests and 426
Vitest tests.
- `pnpm -r typecheck` — passed for all applicable workspaces.
- `pnpm build` — passed, including runner binary, server, UI, and
workspace packages.
- `git diff --check` — passed.
- The diff contains 6 files and does not change `pnpm-lock.yaml`, a
GitHub workflow, server selection, or UI behavior.
## Risks
The primary risk is drift between published package contents and
checked-in compiled patches. Exact versions are pinned, both patches are
exercised by package-contract gates, and CI performs the authoritative
regenerated-lockfile frozen install. The spawn callback does not grant a
new executable path: the following adapter must consume the opaque
verified command lease. Codex isolation changes activate only when
`PAPERCLIP_ACPX_ISOLATED_CONTEXT=1`, so existing direct Codex adapters
are unaffected.
## Model Used
OpenAI Codex with GPT-5 and repository tool use.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked an existing public item or described the
issue in this PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal task
identifier
- [x] I have run the affected tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have documented the dependency, patch, isolation, and lockfile
boundaries
- [ ] All applicable GitHub Actions are green
- [ ] Greptile is 5/5 with every actionable comment resolved
- [x] I will address all review findings before requesting merge
## Thinking Path
> - Paperclip Runner now has a complete guarded Codex vertical slice.
> - The next provider series must not start by importing a provider
implementation or dependency bundle.
> - ACPX needs one bounded, versioned process boundary shared by
TypeScript and Rust.
> - A schema is the authority; checked-in generated inventories keep
both languages in lockstep.
> - Unknown versions, commands, event types, and properties must fail
closed.
> - This pull request therefore lands only the sidecar wire contract and
its drift gate.
> - No ACPX runtime, dependency, executable, package export, or
production selection is added.
## Linked Issues or Issue Description
This is the first package-local unit in the post-Codex provider series.
**What happened?**
The integration branch contains an ACPX provider, but its TypeScript
sidecar and Rust client need a small shared authority before either
implementation can be reviewed safely. Importing the final integration
implementation directly would mix the protocol, runtime, third-party
dependencies, and production wiring.
**Expected behavior**
The schema defines every ACPX sidecar request, response, event, command,
event type, and protocol version. Generated TypeScript and Rust
inventories must drift-check against that schema. No runtime can select
or execute ACPX yet.
**Steps to reproduce**
1. Change the protocol version, command inventory, or event inventory in
the schema.
2. Run the runner protocol type check without regenerating the language
inventories.
3. Observe the drift gate fail.
**Paperclip version or commit**
Stacked on `runner-server-semantic-codex` at `ebd7f9df7`.
## What Changed
- Add the internal ACPX sidecar v2 JSON Schema outside the public PRP v1
schema catalog.
- Generate one TypeScript inventory and one Rust inventory from that
schema.
- Add generate and check hooks to the existing runner protocol-type
workflow.
- Add fail-closed AJV tests for all three message families, version
drift, unknown commands, and extra properties.
- Keep the generated Rust module unregistered until the Rust ACPX
transport exists.
## Compatibility Boundary
- Codex remains the only production runner provider.
- `paperclip_runner` selection and the default-off rollout flag are
unchanged.
- No ACPX package, patch, lockfile, binary entry point, root export,
server file, UI file, workflow, or dependency is added.
- The schema is shipped with the existing `protocol` directory but is
not added to the public PRP manifest.
- Existing direct adapters continue through their current paths.
- Diff against the actual stacked base: 6 files.
## Verification
- Runner TypeScript typecheck and both generated-contract drift gates —
passed.
- Runner TypeScript tests — 37 files and 355 Vitest tests passed; 11
Node contract tests passed.
- Rust provider-bridge regression suite after restacking — 14/14 passed.
- `pnpm -r typecheck` — passed for all applicable workspaces.
- `pnpm build` — passed, including runner binary, server, UI, and
workspace packages.
- `pnpm test:run` — attempted; the local host reproduced unrelated
workspace/Postgres and port-exposure failures in unchanged server
suites. The changed runner contract suites pass, and the repository's
serialized/sharded GitHub checks remain authoritative for those
host-sensitive suites.
- Prettier, rustfmt, generated-source drift checks, and `git diff
--check` — passed.
- `pnpm-lock.yaml` is unchanged.
## Risks
The main risk is allowing schema and generated language inventories to
diverge. Build and typecheck now fail on any drift. The sidecar
implementation and third-party ACPX packages are deliberately absent, so
this PR cannot alter runtime behavior or expand the production attack
surface.
## Model Used
OpenAI Codex with GPT-5 and repository tool use.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs
- [x] I have described the issue and expected behavior in this PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal task
identifier
- [x] I have run the affected tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have documented the compatibility and security boundary
- [ ] All applicable GitHub Actions are green
- [ ] Greptile is 5/5 with every actionable comment resolved
- [x] I will address all review findings before requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Paperclip Runner now has protocol, provider, tool, package,
persistence, and hidden server boundaries.
> - The server still cannot select that path for a real agent heartbeat.
> - A new runtime must not change any existing direct adapter.
> - An experimental runtime must fail closed when its rollout flag is
off.
> - This pull request adds one guarded Codex vertical slice through
runnerd.
> - The benefit is a production-built runner path that users cannot
start by default.
## Linked Issues or Issue Description
Refs #11962
Refs #12111
Refs #12169
Refs #12176
**Subsystem affected**
Cross-cutting. The change affects the runner package, server
orchestration, shared settings, and adapter configuration UI.
**Problem or motivation**
The hidden PRP coordinator cannot execute a real heartbeat. The
application also needs an explicit rollout boundary before it can expose
the experimental runner. Existing direct adapters must keep their
current execution and finalization behavior.
**Proposed solution**
Add `paperclip_runner` as a Codex-only adapter behind the default-off
`enableNativeRunner` instance flag. Select the native runtime only for
that adapter. Persist the run binding before runnerd starts. Wait for
the durable PRP result and terminal event. Resume the real Codex
provider thread on later heartbeats. Keep persisted native runs readable
and recoverable after the flag changes.
**Alternatives considered**
The server could route `codex_local` through runnerd. That option would
change an existing adapter and weaken rollback safety. The server could
expose all providers now. That option would add unreviewed provider
behavior. The build could depend on a prebuilt runner binary. That
option would make source builds architecture-dependent and difficult to
verify.
**Roadmap alignment**
This work supports the shipped enforced-outcomes, governed-tool, and
self-healing-run milestones. It does not add a new roadmap surface. It
is the guarded execution step after the merged hidden runner boundaries.
**Additional context**
This is the next replacement for the closed large runner pull request.
Task-thread presentation remains a separate follow-up so this change can
preserve the current direct-adapter UI.
## What Changed
- Add `paperclip_runner` as an explicit Codex-only adapter.
- Add the default-off `enableNativeRunner` instance flag.
- Reject fresh create, hire, import, switch, and execution requests
while the flag is off.
- Allow edits to persisted runner agents while the flag is off.
- Recover an already persisted native run even after the flag is
disabled.
- Keep every built-in direct adapter on its existing runtime path.
- Persist an immutable native run binding and revisioned completion
contract before runnerd starts.
- Execute server to PRP to runnerd to Codex to server through the hidden
coordinator.
- Validate the durable result against the terminal event and exact
completion criteria before finalization.
- Preserve the Codex provider thread ID and use `thread/resume` on the
next heartbeat.
- Strip unsupported Codex configuration fields from the experimental
adapter.
- Build a target-native release runner binary from source and vendor it
into the server distribution.
- Install Rust only in the Docker build stage. Do not add a workflow or
lockfile change.
- Stop the runner process group on completion, cancellation, and forced
shutdown.
## Verification
- Run `pnpm --filter @paperclipai/paperclip-runner check:all`. All 69
TypeScript tests and 58 Rust tests pass. Protocol, conformance, replay,
formatting, and generated-file checks pass.
- Run the 12 focused adapter, settings, runtime-selection, coordinator,
direct-isolation, and real Codex integration test files. All 186 tests
pass.
- The real integration test uses PostgreSQL, HTTP, WebSocket, runnerd,
and a fake Codex app server. It proves one `thread/start` followed by
one `thread/resume`.
- Run `pnpm -r typecheck`.
- Run `pnpm build`.
- Run `pnpm check:token-gates`.
- Build the Docker `build` target from a clean context. Confirm that the
server distribution contains an executable `paperclip-runnerd` built
with Debian Rust 1.85.
- Start the server through the source-mode tsx entry point with the
package `dist` directory absent. Confirm the vendor shim resolves source
exports and the server boots.
- Run `pnpm test:run` twice. On this macOS host, 405 files pass and 1
file skips. Eight untouched workspace and loopback tests fail because
macOS resolves `/tmp` and `/var` through `/private` and because
PID-derived test ports exceed 65535. Linux CI must pass the full suite.
- Confirm that the diff contains 52 files. Confirm that it contains no
`.github` or `pnpm-lock.yaml` change.
## Risks
- The feature flag is off by default. A fresh native start fails with a
stable error while the flag is off.
- A persisted native run remains recoverable after the flag changes.
This prevents rollout changes from corrupting recorded work.
- Only local Codex execution is accepted. Other providers and remote
work modes fail closed.
- Existing direct adapters do not start runnerd, create native rows, use
native status arbitration, or enter native finalization.
- The runner receives its one-use bootstrap ticket through the child
environment. The server does not put the ticket in command arguments or
logs.
- The server validates the company, task, agent, run, runner, session,
completion contract, result, and terminal binding before it accepts
completion.
- The build compiles a target-native Rust binary. Cross-platform release
packaging remains a later concern. Source builds and Docker builds
compile for their current target.
- Docker needs enough build memory for the existing server TypeScript
compile. The Docker build stage sets a 4 GB V8 heap limit.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex with GPT-5. The exact deployment ID and context-window
size are not exposed. The model used agentic reasoning, repository
tools, code execution, and test execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and applicable tests pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner package now has protocol, transport, provider, catalog,
and authorization foundations.
> - Its first upstream package boundary should expose only the
implemented runtime and test-helper surfaces.
> - Rust correctness belongs in the repository existing build
verification, without introducing a parallel release process.
> - Direct package creation must build the files declared by the package
manifest.
> - This pull request defines the minimal package API and verifies the
optimized runner binaries in the existing PR and release Build jobs.
> - The benefit is a production-ready runner package boundary with
minimal build-process change.
## Linked Issues or Issue Description
Refs #11962
This pull request replaces one bounded part of the archived large runner
change. It follows the package-local authorization change in #12126.
## What Changed
- Export only `@paperclipai/paperclip-runner` and
`@paperclipai/paperclip-runner/testing`.
- Keep Node-only fixture loading and semantic conformance helpers out of
the runtime root.
- Add a provider-neutral semantic conformance kit with stable JSON
comparison and fail-closed input checks.
- Keep deferred SDK, eval, browser, React, lab, and command surfaces
private.
- Pin the runner Rust toolchain to 1.97.1 with the minimal profile and
`rustfmt`.
- Run the Rust workspace tests in release mode.
- Launch the optimized `paperclip-runnerd` and fake-harness binaries in
process-level integration coverage.
- Add one `pnpm --filter @paperclipai/paperclip-runner check:all` step
to each existing PR and release Build job.
- Make the existing server `prepack` lifecycle run its existing build
after it prepares UI assets.
- Document that no production adapter starts runnerd yet.
This revision adds no standalone GitHub Actions job. It adds no server
runner dependency or runner vendoring. It adds no Docker bootstrap or
clean-consumer harness. It does not change `pnpm-lock.yaml`.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner check:all`
- 66 TypeScript tests
- 8 protocol contract tests
- 56 Rust unit and integration tests
- Release-mode integration coverage launches the optimized runnerd and
fake-harness binaries.
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/server-package-build-script.test.ts` (2 tests)
- Clean `pnpm pack` from `server/` rebuilt the server and produced both
`package/dist/index.js` and `package/dist/index.d.ts`.
- `node --test scripts/__tests__/release-verify-workflow.test.mjs` (8
tests)
- `pnpm -r typecheck`
- `pnpm build`
- `pnpm check:token-gates`
- `git diff --check`
- No `pnpm-lock.yaml` diff.
- The diff changes 12 files.
## Risks
The runner adds Rust work to the existing Build jobs. These jobs can
take longer on a cold cache. The pinned toolchain makes contributor and
CI behavior reproducible. Cargo tests use `--release` to verify
optimized executables. The server prepack lifecycle now performs the
build that its published entry points require. This can make direct
server packing slower. This pull request does not wire runnerd into the
server. It does not select runnerd for any adapter. Existing application
execution and finalization paths remain unchanged.
## Model Used
OpenAI Codex with GPT-5. Agentic coding mode used repository tools, code
execution, and automated tests.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner now has a durable PRP transport and a Codex
provider bridge.
> - Codex must use stable, provider-neutral action contracts before
Paperclip can grant run-scoped tool access.
> - A catalog must describe actions without granting permission to
discover or invoke them.
> - Generated inventory must stay synchronized with its TypeScript
source.
> - This pull request adds the canonical Codex-spine semantic action
catalog inside the runner package.
> - The benefit is a small review unit for schemas and inventory before
authorization and dispatch land.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This pull request extends private runner infrastructure
in `packages/paperclip-runner`.
**Problem or motivation**
The Codex provider bridge has no canonical description of the Paperclip
actions that a later authorization layer can project into a run.
Independent operation lists can drift in names, claims, task modes,
effects, and input bounds.
**Proposed solution**
Add one immutable v1 catalog for the first 27 Codex-spine actions. Give
each action a stable identifier, placement, effect, required claims,
supported task modes, and JSON Schema input and output contracts.
Generate a deterministic JSON inventory from that source and fail
package checks on drift.
**Alternatives considered**
The combined runner branch contains larger live and scenario catalogs
with authorization, bindings, labs, and other providers. That change is
too large for this review unit. A generic API escape hatch would also
bypass the operation-level boundary, so this catalog excludes it.
**Roadmap alignment**
This work supports the governed tool access direction in `ROADMAP.md`.
It does not add a tool gateway, application binding, server endpoint, or
production authorization decision.
**Additional context**
Refs #12111 and #11962. Pull request #12111 was squash-merged first.
This branch starts at the resulting `master` commit. Its delta is 10
files.
## What Changed
- Added 27 versioned, provider-neutral semantic action declarations for
the Codex spine.
- Added bounded JSON Schema input contracts and normalized operation
receipt output contracts.
- Added placement, effect, claim, mode, and role metadata.
- Added a deeply frozen public catalog and an operation lookup helper.
- Added a deterministic checked-in JSON inventory and generation
commands.
- Added a byte-for-byte drift gate to the package build.
- Added AJV schema compilation, mutation-bound, forged-field,
immutability, inventory, and non-executable-boundary tests.
- Exported only the catalog types and declarations from the existing
package root.
- Documented that catalog membership does not grant discovery,
authorization, dispatch, or application binding.
- Kept server code, UI code, other providers, scenario-only actions,
labs, generic API access, authorization, dispatch, and receipts
processing out of this pull request.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner check:all` passes.
- TypeScript protocol tests pass: 8 Node tests and 49 Vitest tests.
- All package Rust tests and conformance and replay parity checks pass.
- `pnpm --filter @paperclipai/paperclip-runner
check:semantic-action-catalog` passes.
- `pnpm -r typecheck` passes.
- `pnpm build` passes.
- `pnpm check:token-gates` passes.
- Prettier and `git diff --check` pass for the changed source and
documentation files.
- The generated catalog matches its source byte for byte.
- The secret scan is clean.
- The delta against `master` is 10 files. `pnpm-lock.yaml` is unchanged.
- `pnpm test:run` completed locally with 4,692 passing tests, 19 skipped
tests, and 24 failures in 8 unchanged server test files. The failures
reproduce the established local macOS path-alias, listener, and
workspace-runtime baseline. No changed-file test failed. Linux CI
remains the repository handoff authority.
- The full Linux PR workflow passes, including the aggregate `verify`
gate.
- Snyk, Socket, Superagent security, and supply-chain checks pass.
- Greptile is 5/5 with no actionable comments, recommendations, or
follow-ups.
- Storybook visual regression skipped by design because this pull
request changes no UI file.
- Browser and migration tests are not applicable because this pull
request changes no server, UI, database, or migration file.
## Risks
Production behavior is unchanged because no consumer projects this
catalog into a provider run. The main risks are contract drift,
unbounded mutation input, forged scope fields, accidental executable
authority, and generated inventory drift. Closed input schemas, explicit
bounds, a frozen catalog, tests, and the byte drift gate cover these
risks. The later authorization layer must still bind every action to the
active run and company before discovery or invocation.
I checked `ROADMAP.md`. This change is private contract infrastructure
for the governed tool access direction. It does not duplicate a shipped
or public product surface.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The package-local runner now has a durable PRP transport, but it
cannot execute a real provider.
> - The first provider must preserve PRP identities while using Codex
native thread and turn identities.
> - Recovery must resume the same Codex thread without starting a
duplicate turn.
> - Provider output must become bounded and provider-neutral before it
crosses PRP.
> - Semantic tools must remain unavailable until the catalog and
authorization layers exist.
> - This pull request adds the Codex provider bridge inside the runner
package only.
> - The benefit is a reviewable provider slice with no server or
user-facing behavior change.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This pull request extends private provider infrastructure
in `packages/paperclip-runner`.
**Problem or motivation**
The durable runner from #12100 has no production provider. It cannot
start Codex app-server, map its events, cancel or steer a turn, deliver
a structured question, or recover a native thread after process restart.
**Proposed solution**
Add a supervised Codex app-server transport and a normalized runner
backend. Persist the Codex thread and active turn identities. Resume and
inspect the exact thread after restart. Convert supported notifications
into bounded PRP events. Keep the dynamic tool inventory empty.
**Alternatives considered**
The combined runner branch implements several providers, semantic tools,
server coordination, and UI integration together. That change is too
large for one review unit. Reusing the direct `codex_local` adapter
would also couple this package layer to the existing server execution
path.
**Roadmap alignment**
This work supports the governed tools and self-healing run direction in
`ROADMAP.md`. It does not add a server endpoint, runtime adapter,
rollout flag, or user-facing behavior.
**Additional context**
Refs #12100 and #11962. Pull request #12100 was squash-merged first.
This branch starts at the resulting `master` commit. Its current delta
is 16 files.
## What Changed
- Added a Codex-only app-server process transport with bounded JSONL
frames and buffered notifications.
- Added strict provider descriptor validation for the Codex driver,
working directory, launch arguments, model, instructions, and
non-interactive approval policy.
- Started new Codex threads with an empty dynamic tool inventory and the
named workspace-only permission profile.
- Added native turn start, steering, interruption, cancellation, thread
reads, and structured question responses.
- Added thread and active-turn binding checks for provider requests and
notifications.
- Added provider-neutral normalization for session, turn, item, plan,
usage, tool execution, notice, and structured input events.
- Bounded and redacted provider text and process output before durable
persistence.
- Added private atomic provider state for the descriptor, thread ID,
account session ID, active turn ID, and unacknowledged normalized
events.
- Added exact-thread recovery through `thread/resume` and `thread/read`.
Recovery does not issue another `turn/start` for an active turn.
- Preserved active native turn identity across unexpected provider exit
and reconciled it before later start, interrupt, or snapshot commands.
- Added stable provider-event identities, per-event durable commit and
acknowledgement, and a bounded fingerprint receipt journal that prevents
duplicate delivery across outbox and provider-ack crash windows.
- Extended the durable command executor with provider event polling and
explicit process shutdown on stop, suspend, revocation, lease expiry,
and runtime expiry.
- Preserved completed shutdown behavior when the command result is
replayed after a disconnect.
- Added a fake Codex app-server and integration tests for response
buffering, structured questions, interruption, provider exit,
unacknowledged-event recovery, durable resume, and duplicate-turn
prevention.
- Added a focused `test:codex` package command for the provider
integration suite.
- Kept server code, UI code, other providers, semantic catalogs, tool
authorization, and production runtime selection out of this pull
request.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner check:all` passes.
- TypeScript contract tests pass: 8 Node tests and 44 Vitest tests.
- Rust tests pass: 43 unit tests, 5 Codex integration tests, 3 public
durable-recovery tests, 2 local-runner tests, and 3 process-supervisor
tests.
- Rust conformance and replay parity checks pass against the shared PRP
fixtures.
- `cargo clippy --workspace --all-targets -- -A
clippy::filter-map-bool-then -D warnings` passes. The narrow allow
covers an unchanged replay implementation from the preceding contract
pull request.
- `pnpm -r typecheck` passes.
- `pnpm build` passes.
- `pnpm check:token-gates` passes.
- `git diff --check` passes.
- The delta against `master` is 16 files. The package lockfile is
unchanged. The PR workflow generates its temporary lockfile artifact
from the changed package manifest.
- `pnpm test:run` completed locally with 4,690 passing tests, 19 skipped
tests, and 26 failures in 8 unchanged server test files. The failures
reproduce the established local macOS path-alias, listener, port-range,
and workspace-runtime baseline. No changed-file test failed. Linux CI
remains the repository handoff authority.
- Browser and migration tests are not applicable because this pull
request changes no server, UI, database, or migration file.
- The full Linux PR workflow passes. One unchanged heartbeat recovery
test timed out on the first pass and passed on the failed-only rerun;
the aggregate `verify` gate is green.
- Greptile is 5/5 on the final commit. All four review threads are
resolved.
## Risks
Production behavior is unchanged because no server code starts this
provider. The main risks are a provider process escape, cross-thread
event confusion, secret leakage, duplicated turns, duplicated or lost
provider events, lost questions, and unsafe recovery. Process-group
supervision, identity binding, private bounded state, redaction, durable
command replay, retained event acknowledgements, bounded durable
receipts, exact-thread reconciliation, and integration tests cover these
risks. Semantic tools remain undiscoverable in this layer.
I checked `ROADMAP.md`. This change is private provider infrastructure
for planned control-plane work. It does not duplicate a shipped or
public product surface.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The package-local runner can supervise a local process, but it
cannot yet survive a broken controller connection.
> - A production transport must authenticate both peers without putting
the bootstrap secret on the wire.
> - Commands and events must remain bounded, ordered, and recoverable
across reconnects and crashes.
> - Retrying an uncertain side effect is unsafe, so indeterminate
outcomes must fail closed instead of running twice.
> - This pull request adds those transport and recovery guarantees
inside the runner package only.
> - The benefit is a durable PRP boundary that can be reviewed before
any provider or server integration exists.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This pull request extends private transport
infrastructure in `packages/paperclip-runner`.
**Problem or motivation**
The local runner introduced by #12095 has no authenticated network
handshake, durable outbox, reconnect lease, cumulative acknowledgement,
or crash-safe command journal. A dropped connection could otherwise lose
an event or tempt a controller to repeat a side effect whose outcome is
unknown.
**Proposed solution**
Add an authenticated PRP v1 WebSocket transport, encrypted frames,
lease-based reconnects, a bounded durable event outbox, cumulative
acknowledgements, and an idempotent command journal. Preserve pending
commands before execution and classify the crash window as indeterminate
so an uncertain side effect is never repeated automatically.
**Alternatives considered**
The combined runner branch implements transport together with Codex,
semantic tools, and server coordination. That change is too large for
one review unit. Keeping transport in memory would make reconnect and
crash recovery unverifiable. Re-running a pending command after restart
would weaken the at-most-once side-effect boundary.
**Roadmap alignment**
This work supports the governed tools and self-healing run direction in
`ROADMAP.md`. It does not add a production provider, server endpoint,
adapter, feature flag, or user-facing behavior.
**Additional context**
Refs #12095 and #11962. Pull request #12095 was squash-merged first.
This branch has been rebased onto the resulting `master` commit, and its
current delta is 13 files.
## What Changed
- Added a loopback-only WebSocket connection policy with one-time DNS
resolution and pinned reconnect addresses.
- Added an HMAC mutual-authentication handshake that never sends the
bootstrap ticket over the socket.
- Added AES-256-GCM secure frames with per-direction keys, monotonic
counters, and session-bound authenticated data.
- Added one-use bootstrap-ticket handling and lease-based reconnect
validation with expiry, revocation, and epoch checks.
- Added a private, symlink-resistant state directory with atomic,
synchronized state replacement.
- Added a bounded durable event outbox, priority-zero reserve,
cumulative acknowledgements, and reconnect replay of only the
unacknowledged suffix.
- Added a bounded command journal with contiguous sequence enforcement,
persistent results, and deterministic duplicate responses. Duplicate
replay requires a SHA-256 match over the complete canonical command.
- Persisted commands before their effects. A crash after persistence but
before result storage returns an indeterminate terminal result and does
not execute the command again.
- Migrated pre-fingerprint command journals by compacting through their
persisted controller cursor. Legacy redelivery fails closed instead of
reconstructing an incomplete identity or repeating an uncertain effect.
- Added strict limits and validation for frames, state, results, outbox
entries, command history, and redacted diagnostics.
- Added a transport-only `paperclip-runnerd --connect-url` mode. It
handles lifecycle commands and rejects provider commands because no
provider is present in this pull request.
- Added a full disconnect-before-ack fault test that reconnects with the
lease, replays identical command and event state, and proves the effect
ran once.
- Kept provider transports, semantic tools, server integration, and
production runtime selection out of this pull request.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner check:all` passes.
- TypeScript contract tests pass: 8 Node tests and 44 Vitest tests.
- Rust tests pass: 33 unit tests, 3 public durable-recovery integration
tests, plus the existing 2 local-runner and 3 process-supervisor tests.
- The disconnect-before-ack, lease reconnect, duplicate command,
malformed state, unknown command, bounds, and crash-window tests pass.
- Rust conformance and replay parity checks pass against the shared PRP
fixtures.
- `cargo clippy --workspace --all-targets -- -A
clippy::filter-map-bool-then -D warnings` passes. The narrow allow
covers an unchanged replay implementation from the preceding contract
pull request.
- `pnpm -r typecheck` passes.
- `pnpm build` passes.
- `pnpm check:token-gates` passes.
- `git diff --check` passes.
- The delta against `master` is 13 files. The package lockfile is
unchanged.
- `pnpm test:run` completed locally with 4,686 passing tests, 19 skipped
tests, and 30 failures in 8 unchanged server test files. The failures
reproduce the established local macOS path-alias, listener, port-range,
and workspace-runtime baseline. No changed-file test failed; Linux CI
remains the repository handoff authority.
- Storybook visual regression is not applicable because this pull
request changes no UI or story files.
## Risks
Production behavior is unchanged because no server code starts or
connects to this transport. The main risks are secret disclosure, forged
or replayed frames, state corruption, unbounded disk growth, duplicated
side effects, and incorrect recovery. Mutual authentication, encrypted
counter-bound frames, private atomic state, explicit bounds, cumulative
acknowledgements, a durable command journal, fail-closed indeterminate
recovery, and fault-injection tests cover these risks.
I checked `ROADMAP.md`. This change is private transport infrastructure
for planned control-plane work. It does not duplicate a shipped or
public product surface.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner needs a small local process model before it can
connect to a production provider or server.
> - The TypeScript PRP contracts now define the expected replay
behavior.
> - A second language implementation must produce the same result from
the same fixtures.
> - Local child processes also need bounded input, bounded output, and
complete descendant cleanup.
> - This pull request adds a package-local Rust runner, a scripted fake
harness, and deterministic parity checks.
> - The benefit is a testable process boundary with no production
Paperclip behavior change.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This pull request adds private test infrastructure to
`packages/paperclip-runner`.
**Problem or motivation**
The PRP contracts have no second implementation on `master`. There is
also no small harness that can prove process cleanup, command
idempotency, terminal reconciliation, or bounded JSONL handling without
a production provider.
**Proposed solution**
Add a minimal Rust workspace. Add a local runner process, a scripted
fake harness, a bounded process supervisor, and Rust conformance and
replay checks. Keep all binaries package-local. Do not connect them to
the Paperclip server.
**Alternatives considered**
The combined runner branch includes provider transports, durable
networking, SDKs, labs, and server behavior. That change is too large
for this review unit. A TypeScript-only harness would not test
cross-language contract parity.
**Roadmap alignment**
This work supports the governed tools and self-healing run direction in
`ROADMAP.md`. It does not add a user-facing runtime, adapter, endpoint,
or rollout flag.
**Additional context**
Refs #12091 and #11962. Pull request #12091 was merged before this
branch opened. This branch is based on the current `master`. Its delta
is 25 files.
## What Changed
- Added a minimal locked Rust workspace with only `serde` and
`serde_json` dependencies.
- Added a package-local `paperclip-runnerd` local mode and a scripted
fake harness.
- Added bounded controller input, harness input, subprocess output
queues, line sizes, log retention, script sizes, script steps, and
command history.
- Added contiguous controller and harness sequence checks and
equivalent-command replay handling.
- Added process-group supervision that cleans up child processes and
remaining descendants after forced or natural harness exit.
- Added runner-owned terminal reconciliation for success, failure,
interruption, cancellation, controller closure, and protocol failure.
- Added Rust conformance output and deterministic replay summaries for
the shared PRP fixtures.
- Added fake scripts for success, failure, interruption, interaction,
duplicate terminal output, process cleanup, and oversized output.
- Added package scripts and documentation for the Rust and
cross-language checks.
- Kept provider transport, server integration, semantic tools, and
production runtime selection out of this pull request.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner check:all` passes.
- TypeScript contract tests pass: 8 Node tests and 44 Vitest tests.
- Rust tests pass: 20 unit tests, 2 local-runner tests, and 3
process-supervisor tests.
- The Rust conformance and replay parity checks pass against the shared
fixtures.
- The natural-exit and forced-exit tests confirm that the harness and
its worker process are stopped.
- The oversized-frame test confirms that a harness frame above the
configured limit is rejected.
- `pnpm -r typecheck` passes after the final rebase to `master`.
- `pnpm build` passes after the final rebase to `master`.
- `pnpm check:token-gates` passes.
- `git diff --check` passes.
- The delta against `master` is 25 files. The package lockfile is
unchanged.
- `pnpm test:run` completed locally with 4,686 passing tests, 19 skipped
tests, and 30 failures in 8 unchanged server test files. The failures
are local macOS path-alias, listener, port-range, and workspace-runtime
baseline failures. No changed-file test failed, and every applicable
Linux CI shard passes.
- Storybook visual regression skipped intentionally because this pull
request changes no UI or story files.
## Risks
Low production risk. No server code invokes the new binaries. The
package remains private. The main risks are process leaks, unbounded
local input, and cross-language drift. Bounded queues and sizes,
process-group cleanup tests, fixture manifests, and parity checks cover
these risks.
I checked `ROADMAP.md`. This change is private test infrastructure for
planned control-plane work. It does not duplicate a shipped or public
product surface.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner needs one typed interpretation of the
language-neutral PRP contract.
> - The JSON Schemas and fixtures now exist, but TypeScript consumers
cannot validate or replay them yet.
> - A deterministic reducer must define how duplicate delivery and
source gaps affect the projected session.
> - Result and question contracts must also validate untrusted provider
and user input before later runtime code uses it.
> - This pull request adds those TypeScript contracts and replay oracles
without adding a process, provider, endpoint, or production behavior.
> - The benefit is a reviewable and testable TypeScript foundation for
the local runner and transport pull requests.
## Linked Issues or Issue Description
**Subsystem affected**
This change affects the private `@paperclipai/paperclip-runner` package.
It does not change an existing server or adapter execution path.
**Problem or motivation**
The PRP v1 schemas do not yet provide TypeScript types, runtime
validators, normalized result handling, or a deterministic session
projection. Later Rust, transport, provider, and server work needs one
tested TypeScript oracle instead of separate interpretations.
**Proposed solution**
Generate a checked-in TypeScript schema bundle from the PRP v1 sources.
Add derived types, AJV validation, result and question validation,
deterministic replay, a reducer, and generated golden snapshots. Export
only these implemented root-package surfaces.
**Alternatives considered**
The combined runner branch adds the TypeScript contracts together with
Rust, providers, semantic authorization, SDKs, labs, and server
behavior. That delta is too large for normal review. Handwritten
duplicate protocol types would also create a drift risk.
**Roadmap alignment**
This work supports the governed tool and control-plane direction in
`ROADMAP.md`. It does not enable a new production adapter or endpoint.
**Additional context**
Refs #12087 and #11962. This pull request was prepared on #12087, then
rebased onto its squash merge before opening. The current delta against
`master` is 37 files.
## What Changed
- Added JSON-Schema-derived PRP v1 types and AJV runtime validation.
- Added fail-closed required-version checks and cross-envelope binding
checks.
- Added provider-neutral completion-result and structured-question
contracts.
- Added normalization for accepted legacy provider result aliases before
strict validation.
- Added a deterministic session reducer for replay, duplicate delivery,
source gaps, requests, items, results, and terminal state.
- Added generated replay snapshots and compact parity summaries for six
accepted fixtures.
- Added schema-bundle, manifest, and replay-golden drift gates.
- Added only the root package export. Deferred testing, SDK, evaluation,
lab, provider, and browser entry points remain unavailable.
## Verification
- `pnpm --filter @paperclipai/paperclip-runner test` passed with 8
protocol tests and 44 TypeScript tests.
- `pnpm --filter @paperclipai/paperclip-runner typecheck` passed.
- `pnpm --filter @paperclipai/paperclip-runner check:replay-goldens`
passed.
- `pnpm -r typecheck` passed.
- `pnpm build` passed.
- `pnpm check:token-gates` passed.
- `git diff --check` passed.
- The delta against its declared base is 37 files.
- `pnpm test:run` was executed locally. The package tests pass, while
the macOS repository run retains the unchanged local-environment
failures documented on #12087. The complete Linux CI matrix must pass on
this commit.
- A scoped scan found no secret-like values, internal references, or
deferred-provider file names.
- Greptile found an unbounded sequence-gap allocation. Commit `4a405c17`
caps detailed missing IDs at 256, records the full missing count and
truncation state, and rejects sequence values above the exact JavaScript
integer range. The focused tests, workspace typecheck, build, and token
gates pass after this fix.
## Risks
Low production risk. The package remains private. This change adds no
process, network endpoint, provider bridge, server integration, database
change, or execution selection. The main risk is protocol interpretation
drift. Generated schema and replay gates detect that drift. Browser and
CSP-specific validator packaging remains deferred to its later package
boundary.
I checked `ROADMAP.md`. This change defines contracts for planned
control-plane work and does not add overlapping product behavior.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner needs a language-neutral contract between the
server and the runner process.
> - A shared contract must exist before TypeScript, Rust, transport, or
provider implementations can depend on it.
> - Required protocol versions must fail closed, while safe optional
fields must remain compatible.
> - The contract also needs deterministic fixtures and a drift gate for
later cross-language work.
> - This pull request adds that contract without adding runtime
behavior.
> - The benefit is a small, reviewable source of truth for the next
implementation pull requests.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This pull request adds a private package contract for
later server, TypeScript, and Rust work.
**Problem or motivation**
Paperclip Runner does not have a small language-neutral protocol
boundary on `master`. A runtime implementation without this boundary can
drift between languages, accept unsupported required versions, or
silently change canonical fixtures.
**Proposed solution**
Add PRP v1 JSON Schemas, accepted and rejected fixtures, a Codex
structured-question fixture, and a generated SHA-256 manifest. Run
compatibility and manifest checks during the package build. Keep the
package private and export nothing in this pull request.
**Alternatives considered**
The combined runner branch contains schemas together with providers,
SDKs, labs, and server behavior. That change is too large for normal
review. Generating TypeScript validators in this pull request would also
cross into the next review unit.
**Roadmap alignment**
This contract supports the governed tool and control-plane direction in
`ROADMAP.md`. It does not enable a new production adapter or endpoint.
**Additional context**
Refs #12084 and #11962. This pull request was reviewed as a stack on
#12084, then rebased and retargeted to `master` after #12084 merged. The
current delta is 38 files.
## What Changed
- Added 20 PRP v1 JSON Schemas with stable identifiers and resolved
references, including explicit cross-language conformance input and
output schemas.
- Added canonical replay, cross-language, and Codex question fixtures.
- Added accepted cases for additive optional fields and a rejected case
for an unsupported required protocol version.
- Added a deterministic manifest with SHA-256 digests for every schema
and fixture.
- Added package-local schema-instance, schema-reference, compatibility,
question-ID, conformance-pair, and drift checks.
- Added a private workspace package with no public exports and no
production runtime behavior.
- Added the package manifest to the Docker dependency-stage inventory
required for every workspace package. This does not copy or build runner
runtime code into the production image.
- Kept the provider descriptor and question fixture Codex-only. No
deferred provider package or dependency is present.
## Verification
- `pnpm install --frozen-lockfile` passed with Node 24.19.0 and pnpm
9.15.4. No lockfile change is committed.
- `pnpm --filter @paperclipai/paperclip-runner check:protocol` passed
with 8 tests.
- The committed AJV 2020-12 gate accepted every canonical v1 replay,
question, and cross-language conformance fixture. It rejected the
required v2 fixture, a replay fixture with a missing required command
ID, and conformance output with a missing session ID.
- `pnpm -r typecheck` passed.
- `pnpm build` passed and ran the protocol manifest drift check.
- `pnpm check:token-gates` passed.
- `node ./scripts/check-docker-deps-stage.mjs` passed.
- `git diff --check` passed.
- The delta against its declared base is 38 files.
- `pnpm test:run` completed with 4,687 passing tests, 19 skipped tests,
and 29 failures across 9 unchanged server files. The failures reproduce
macOS path aliases, local listener probes, workspace-runtime
assumptions, and one connection-retry timeout. No changed-file test
failed. Linux CI must pass before this pull request is ready.
- `pnpm check:tokens` reports existing personal-name references outside
this pull request. A scoped scan of `packages/paperclip-runner` found no
secret-like values, internal references, or deferred-provider names.
- PR #12084 was squash-merged, and this branch was rebased onto that
merge and retargeted to `master`. The first master-base policy run
correctly caught the missing Docker dependency-stage manifest copy;
commit `4fa1ea7c` fixes that gate, and the complete Linux matrix is
green.
- Serialized server shard 1 initially hit an unchanged heartbeat
test-harness timeout and a later assertion in the same file. Its
isolated rerun passed in 3m57s. All other shards passed on their first
attempt.
- Greptile reviewed the final commit at 5/5 with no blocking failure.
Both earlier actionable validation threads are resolved, and no review
thread remains open.
## Risks
Low production risk. The package is private and has no exports, server
adapter, endpoint, or process. AJV is a package-only development
dependency that the server workspace already uses. The main risk is
contract churn before the TypeScript and Rust consumers land. The
generated manifest and compatibility fixtures make that churn explicit.
I checked `ROADMAP.md`. This change defines a contract for planned
control-plane work and does not add overlapping product behavior.
## Model Used
OpenAI Codex with GPT-5 was used. The exact serving model ID and context
size were not exposed. The model used high reasoning, repository tools,
GitHub tools, and local code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Dotta
Nicky Leach
dependabot[bot]
