## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The native Runner keeps provider sessions under company authority,
approvals, budgets and durable recovery.
> - Cursor work was spread across candidate branches. The published
branch lacked later plan, permission and cleanup fixes.
> - Production also needs public installation and matching runtime
assets for local and Daytona execution.
> - This pull request consolidates Cursor onto current mainline recovery
behavior and completes that installation path.
> - The installed v11 release passed focused local and Daytona
qualification after the generic mode and lifecycle cleanup. The later
model-selection correction and current mainline merge produce v14
artifacts that need matching release qualification.
> - Cursor admission is enabled in source; publish only an artifact
combination with matching qualification. Native AskQuestion and complete
per-run dollar accounting remain excluded.
## Linked Issues or Issue Description
Refs: #14435, #14631, #14669, #14699, #14724.
This completes the Cursor implementation by @cryppadotta from combined
source `22c78242a4e0c2369fecf0c2dc4e7600fbad6706`. It preserves newer
mainline recovery, completion and warm-directory behavior. Pi and
Copilot remain gated.
## What Changed
- Generate named Rust and TypeScript ACPX release profiles from one
manifest. Share runtime pins with packaging and server verification.
Preserve vendor runtime versions; bind the updated ACPX patch to Cursor
profile v14 and reject stale generated declarations at build/typecheck.
- Remove ACPX model allowlists, including the former Codex and Pi
restrictions and the duplicate developer test-drive gate. Send any
explicit model ID unchanged to its provider and verify the effective
selection before prompting. The bundled ACPX package forwards unlisted
IDs, rejects mismatched acknowledgements, and restores the exact
selection after session load. It does not expand Cursor model aliases.
Provider rejection, mismatch, or missing model controls fails without a
fallback. Model examples live in evaluation fixtures, outside runtime
declarations.
- Add pinned Cursor execution, contained instructions, exact model
verification and Agent/Plan/Ask modes.
- Carry an opaque generic `mode` identifier in shared native execution,
sidecar, Rust and recovery contracts. The provider adapter owns
supported modes, defaults, native translation and acknowledgement.
- Keep native RPC recognition, accepted-plan interpretation and
permission evidence behind provider adapters. Shared settlement and
recovery verify normalized facts and their committed evidence.
- Replace the Cursor-only warm-attachment branch with a runner-owned
capability. Only Cursor opts into it. Move profile compatibility and
optional usage parsing into provider metadata and adapters.
- Write generic plan-wait receipts. Read exact historical Cursor
receipts through a separate compatibility decoder. Reject mixed formats
and preserve existing authority checks.
- Carry native plans, semantic questions, todos, child activity,
permission identities and partial usage diagnostics through the Runner.
- Preserve durable response delivery, cancellation, warm ownership and
process retirement.
- Finish accepted planning runs successfully. Keep their tasks open for
explicit direction. Acceptance does not start implementation.
- Ship `paperclipai runtime setup cursor` and its provisioner through
the public package. npm installation does not download Cursor. Setup
uses the OS account's closure-keyed cache so system-wide npm packages
can remain read-only. Run it as the Paperclip service account.
- Include Cursor in normal provider packs and Daytona images for macOS
ARM64/x64 and Linux x64.
- Reject stale release packs by source revision and current ACPX/Cursor
pins before assembly writes files. Verify current Cursor
version/profile/closure again at runtime.
- Ship all three daemon targets and the expected Linux image-pack
identity. A macOS controller uses its packaged Linux daemon for Daytona.
Image mismatches fail before provider launch.
- Use the vendored Runner boundary for installed readiness probes.
Verify the actual installed Cursor probe.
- Verify compiled public Daytona plugins and their release versions in
installed smokes.
- Record exact artifacts, the acceptance matrix, retained failures,
supported capabilities and rollback behavior in the [readiness
report](https://github.com/paperclipai/paperclip/blob/codex/cursor-production-readiness/doc/plans/2026-10-03-cursor-production-readiness.md).
## Verification
- Current head `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037` merges
mainline `faa8e452c73bae5e044dd6379179a00106abb131`. It keeps Cursor
plan and cancellation guards alongside mainline historical-question
filtering. The evaluation catalog includes both Cursor and expanded
adapter accounting cases (683 total). Recursive typecheck, full build,
696 lifecycle/recovery tests, 45 fixture tests and fixture typecheck
passed. Current-head CI passed: 56 successful checks, one neutral and
four skipped. [Complete
CI](https://github.com/paperclipai/paperclip/actions/runs/37557996535).
The fresh Base Greptile review is 5/5 on this exact head, with 304 files
reviewed, zero new comments and zero unresolved threads. The user
authorized overriding the CODEOWNER review gate after checks passed; no
failing checks are overridden. Prior results below retain their own head
identities.
- Corrective head `3d2b168366258036f6b6a6fccb382c49138cc601` fixes the
post-merge Apex finding. Automatic-review and new-evidence
reconciliation preserve pending child results and recheck delivery under
the status lock before completing. Account repair now excludes unrelated
secret consumers and requires the failed agent's identity. Regression
coverage includes the commit race, delivery statuses,
current-run/current-intent exclusions, repeated reconciliation, both
database reconciliation paths, and credential consumer boundaries. All
184 affected tests, server typecheck and server build passed.
Current-head Base Greptile review is 5/5, with 304 files reviewed, zero
new comments and zero unresolved threads. Current-head CI passed: 56
successful checks, one neutral and four skipped. [Complete
CI](https://github.com/paperclipai/paperclip/actions/runs/37535994724).
This Base review is distinct from the earlier Apex review.
- Merge head `5957c257a` reconciles mainline `b508a05c4`. It preserves
both accepted-plan waits and pending-child-completion checks, current
provider selectors, task-creation response identities, and mainline ACPX
missing-file handling. The combined patch is bound to Cursor profile
v14; historical records keep their original identities.
- Merge head `5957c257a` passed recursive typecheck, full build, 43
installed ACPX/package contracts, 107 provider UI and plan/recovery
tests, 593 database-backed lifecycle tests, 49 profile/native contract
tests, 45 Product E2E fixture tests, fixture typecheck, token gates,
three provider-free browser task-creation cases, and Runner
conformance/replay checks. Its complete CI passed (55 successful checks,
one neutral and four skipped), while Apex returned 2/5 with a
child-delivery finding addressed below.
- The local full-suite attempt again failed the unchanged Git streaming
test (360-second timeout) and was stopped. The concurrent local Rust
attempt failed four unchanged Codex process/deadline tests; all four
passed serially without code changes in 7.29 seconds after removing the
competing test load. These failed commands are retained and are not
reported as full-suite passes; the fresh Linux CI runs are tracked
separately.
- The previous head `907bdb2a2778c7ffeb4a662a91460c9d1ddfc9c5` earned
Apex 5/5 with zero comments after fixing all three findings: per-user
install cache, stale release-pack rejection, and public Linux smoke
account/home handling. Its real built installer passed from read-only
public packages on macOS ARM64 and Linux x64. All 137 release-registry
checks and 64 ACPX package contracts passed. That review does not cover
this mainline reconciliation.
- Prior `beadd3654` passed the full CI matrix; its one unchanged chat
test failure and successful single retry remain in the [CI
history](https://github.com/paperclipai/paperclip/actions/runs/37521449327).
Historical results below remain attributed to their original builds.
- Fixture follow-up `dd59d7e82b103a88b7cbd7d2c38b612c0fbbff7a` removes
provider-specific model choices from generic offline ACPX tests. The
fake sidecar preserves the model and session identity selected at open
through suspension. Affected verification passed: 106 Rust tests and 73
TypeScript tests. This commit changes test code only; the
production-code checks below retain their recorded identities. Its CI
and Greptile review later passed; those results belong to that
historical head.
- Model-selection cleanup `9a070808b48960a41fdfd369ae0636b95af82459`:
252 focused Runner tests passed (six platform skips), covering all six
ACPX agents, native model acknowledgement, rejected selections,
installation integrity and recovery identity. The merged branch passed
recursive typecheck, full build, token gates, server admission (19
tests), and the Product E2E catalog (45 tests). The acceptance catalog
passed all four tests. The full Rust suite passed: 643 tests, 2 ignored.
It verifies sidecar acknowledgement of unlisted models and rejection of
model mismatches. The final commits only update Rust tests; production
sources match the verified build at
`65ec3279ac50185e3cda109b5cfd9b4f56105de0`. No new paid provider calls
were made.
- The merge preserves both Cursor and the new mainline public-MCP
fixture cases. Auto-merge remains disabled; the latest follow-up status
is recorded above. The local `pnpm test:run` attempt hit the unchanged
Git streaming test's 300-second timeout and was interrupted before
merging mainline. The broad Runner attempt found obsolete single-model
assertions plus three macOS fixture-path failures caused by a
`/private/tmp` override. The assertions are corrected; affected
TypeScript checks passed with the standard macOS temporary directory,
and the complete Rust suite passed. Neither interrupted command is a
full-suite pass.
- Earlier declaration-cleanup head `6f4a5e9e2` passed recursive
typecheck, build, Rust and focused tests. Its CI later exposed a test
expecting duplicated Grok digest literals. The current source fixes that
assertion to compare launcher bytes with the shared manifest. Historical
successes and failed attempts are retained; no new live provider
qualification is claimed.
- Previous head `e75fde6098b0ddd8cec765bfb6ecaeecb88a26a6` passed
complete CI (56 successful checks, one neutral, four skipped) and
Greptile 5/5. [Historical complete
CI](https://github.com/paperclipai/paperclip/actions/runs/37489112305).
Those results are not claimed for the cleanup head.
- Frozen live application: `d7b696f9b8f79095233e9e3d56d23e6a6018dd48`.
Public package version: `0.0.0-cursor-verify.3d0c9b7761c6`. The
declaration cleanup preserves release pins and does not relabel that
tested artifact as a build of the new source. Mainline through
`e34abee670` was reconciled while preserving accepted-plan waits,
provider-capacity handling, and both Cursor and public-MCP fixtures.
- Clean normal installation, explicit Cursor setup and daemon resolution
passed on macOS ARM64, macOS x64 under Rosetta, and Linux x64. npm
lifecycle hooks ran without silently downloading Cursor.
- Historical v11 live matrix: **18/18 passed with cleanup** (nine local,
nine Daytona) after the generic mode and lifecycle cleanup. The campaign
has 23 attempts; all five failures and their diagnoses remain recorded.
Exact case identities, hashes and limits are in the readiness report.
All provider calls are real, use the explicit Luna model and
company-bound credentials, and run without qualification or
runtime-asset overrides.
- The immutable Daytona image is
`ghcr.io/paperclipai/paperclip-daytona-runner@sha256:d6259b6bba094702c13fc2283bd85550849c1c53145b656fb2746778f9fa1747`.
The public Daytona plugin is installed independently and its version is
checked.
- Recursive typecheck, full build, token gates and Runner
contract/conformance/replay checks passed on the frozen application. Its
complete Linux CI suite passed. The duplicate local full-suite command
was incomplete after timing failures; affected repeats passed, but that
command is not reported as a clean pass.
- Qualification fixtures passed typecheck, 1,675 Vitest tests (one
skip), 128 Node checks, three provider-free browser tests, and 150
focused lifecycle tests after the final diagnostic correction. The
affected legacy Cursor command file also passed all five tests after
removing its shorter 10-second override; it now inherits the suite’s
standard 15-second timeout. Greptile is 5/5 on `e75fde609` with no
unresolved review threads. CI results above are recorded separately from
historical build results.
## Risks
- Cursor v14 includes the updated ACPX dependency patch and release
identity. The v11 live matrix and image below remain historical
evidence. They do not certify new v14 package/image artifacts.
- ACPX accepts models beyond the qualification fixtures. Availability
and entitlement depend on the provider. Successful configuration is not
a claim of live qualification for every model.
- Shared mode is an opaque identifier. Provider adapters own its
meaning. Incompatible historical sessions remain fenced; exact committed
plan waits and task history remain inspectable.
- Native AskQuestion is excluded. Paperclip semantic questions are
supported. Authoritative per-run dollar accounting is unavailable;
partial counters remain diagnostics and unknown cost is not zero.
- Image input, detailed native diffs, deeper child transcripts and
native plan-file export remain follow-ups.
- macOS x64 has clean-install and daemon-startup proof under Rosetta,
not a separate live campaign on Intel hardware.
- Release only the tested package/image combination. Merging this PR
does not publish npm packages or deploy that image. Later builds need
their own release verification. Rollback disables new Cursor admission
while preserving records and recovery inspection.
- A model can fail an exact instruction: one cancelled-plan attempt
returned the wrong summary marker despite correct cancellation. The
unchanged repeat passed; both results remain in the report.
> ROADMAP.md was checked. This completes existing native Runner/Cursor
work; it does not add an independent core feature proposal.
## Model Used
OpenAI Codex, GPT-6. The exact serving variant and context window are
not exposed in this session. The agent used reasoning, repository
inspection, code execution, protocol tests and browser-backed Product
E2E tools. Cursor acceptance uses the explicit
`gpt-5.6-luna[context=272k,reasoning=medium,fast=false]` model. That is
the evaluated provider model.
## 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 — affected suites passed;
full CI and the retained local failed attempts are recorded separately
above.
- [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 — 56 successful checks, one
neutral and four skipped on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037`
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups —
fresh Base review passed on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037`;
zero new comments and no unresolved threads. The earlier Apex finding
remains fixed.
- [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.
> - Users connect accounts and choose an agent harness and model.
> - The runtime change in #14970 supports custom providers on those
connections.
> - Normal setup must stay simple while advanced users can choose a
compatible gateway.
> - Shared connector rows and access controls keep these choices
consistent.
> - This pull request refines the agent setup UI and adds review stories
and repeatable browser qualification.
> - The qualification checks real tools and downloaded outputs, not only
a successful run status.
## Linked Issues or Issue Description
Refs #14970, #37, #13083, #14104, #14565, #12692.
The core implementation in #14970 is merged. This branch incorporates
its squash commit and targets `master`. Both PRs contain our
implementation. #14016 is a reference only and is not a dependency. This
PR has 96 changed files.
## What Changed
- Complete model-provider connector presentation beside other
connectors. Each row uses the existing Connect action and connection
list. Tags are stored without category UI. The base PR includes the
provider forms and routes.
- Show persistent Subscription, API Key, and Advanced choices. Label
Advanced as Custom Gateway. Reuse provider logos, connection lists, and
permissions controls. Default access to the organization and all agents
when permitted; keep narrowing controls under Advanced.
- Keep Configure reachable before subscription sign-in, so users can
select a supported environment when the default cannot sign in. Testing
and saving still require a connection. Show the execution environment in
Configure. Preserve the confirmed Connect choice. Editing a method,
credential, saved account, or advanced choice requires that current
choice to connect before testing or saving. Use matching model and
thinking-effort dropdowns and retain connection icons in selected
values.
- Preserve the new harness model default when switching an existing
OpenCode agent to Codex or Claude, and resolve user-selected model names
with the effective harness.
- Load popular OpenRouter models through the shared connection-model
discovery path. Keep explicit model lists and manual model entry
available.
- Group onboarding, connection setup, agent runtime, management,
recovery, and production-component stories under AI Connections /
Provider routing.
- Add an explicit-only provider-connections browser suite for managed
local or existing local/staging targets. Use private browser profiles
and credential handoffs. Support human-assisted subscription sign-in
without sharing passwords or tokens in reports.
- Verify persisted connection identity, runtime probes, tool execution,
exact artifact bytes, completion, and context-dependent follow-up.
Retain source/model provenance, cost bounds, closed error diagnostics,
original failures, and cleanup evidence.
- Add Gemini startup-model and skill-root fixes, Grok private-history
detection, ACP filesystem regression fixtures, selected-workspace
handling for local Hermes, and artifact-helper workspace fallback.
- Keep managed Grok runtime homes disposable. Remove host-side
transcript retention/restoration because private file modes do not
isolate same-user agent processes. Ignore earlier development archives
and use a fresh task handoff when history is unavailable. Verify the
absence of restored transcripts with a separate same-user process.
- Capture stopped-run diagnostics before deleting an attached-company
fixture agent. Track creation and owned sign-in receipts; revoke only
this attempt's accounts and never adopt a concurrent campaign's newly
created account. Preserve failure signals and final status through
cleanup.
- Require the requested environment in the saved agent and every run,
including follow-ups. Reject a forced incompatible target. Keep one
cancellation state through startup, every cell, reporting, and teardown
for SIGINT, SIGTERM, and SIGHUP. Stop further paid cells after
interruption. Document qualification limits.
## Verification
- Current head `b3bb3e94d577d43d9965a6b9daba039f599b2e49` includes
master `d9f600043`. The security fix in `a758fde31` passes full
workspace typecheck, production build, and 119 connection/Grok
regressions. The unchanged UI passes all 126
configuration/model-discovery tests and token gates. The final
published-guide correction passes Grok adapter typecheck. Earlier head
`eebd8225c` passed the complete deterministic runner suite (1,404 Vitest
tests and 128 Node tests) and all CI jobs. Current-head CI run
`37520147514` passed all 47 jobs, including the full sharded Vitest and
browser matrix, production build, and canary dry run. All 55 checks
completed: 53 successes and two expected skips. The current-head
security scan passed, Greptile is 5/5, and no review threads remain
open.
- A separate same-user process reproduced reading a restored Grok
transcript before the security fix. The regression now finds no
transcript. Existing fresh-session fallback and ordinary session
metadata behavior pass.
- The final account-choice and cleanup fixes pass 85 setup tests and 26
qualification-harness tests. Regressions verify that editing a
connection invalidates confirmation, Configure remains reachable before
sign-in, diagnostics are captured before fixture deletion, and
concurrent campaigns cannot adopt or revoke each other's accounts. UI
and E2E typechecks pass.
- The Storybook build and actual Chromium production-component stories
passed during this change. Review the neighboring AI Connections /
Provider routing stories, regular connector rows, three connection
modes, model discovery, and the single execution-environment control in
Configure.
- Cancellation smoke verified authenticated cleanup before browser close
for SIGINT, SIGTERM, and SIGHUP. Regressions cover interruption during
startup and reporting, missing-file ACP resource errors, and preserved
permission denials. Both ACP runtime versions and 54 ACPX/Grok
regressions passed. The deterministic connection-intent browser suite
passed two tests.
- Historical local qualification retained 43 passing API/gateway cells
out of 46, with downloaded outputs and follow-up receipts. These
attempts span earlier builds; they do not qualify this exact commit or
staging. Subscription combinations, Gemini overloads, and the unresolved
follow-up failure remain recorded rather than counted as passing.
- Use `pnpm test:e2e:runner -- --list --suite provider-connections` to
inspect the matrix. Follow `tests/runner-e2e/PROVIDER-CONNECTIONS.md`
for credentials, target URL, sign-in assistance, budget, evidence, and
cleanup. Paid live tests remain opt-in.
## Risks
- The core implementation in #14970 is merged. This PR adds no database
migration of its own.
- Subscription login needs an interactive provider session. Dedicated
accounts and staging qualification remain follow-up work; this PR does
not certify every login combination for production.
- Managed Grok transcript resume is deferred until provider history has
an OS isolation or authorized broker solution. Follow-ups start fresh
with Paperclip task context; earlier live Grok results do not qualify
this behavior.
- Gemini CLI 0.58.0 has an upstream ACP new-file error conversion
defect. Live overloads and one unresolved follow-up timeout remain
recorded. The stock CLI is unchanged, and those cases are not marked as
passing.
- Real-provider tests spend credits and use private credential/evidence
directories. The launcher requires explicit selection and checks target
ownership. It must not attach to a developer's database by accident.
- OpenClaw Gateway, Hermes Gateway, Claude Managed, AWS AgentCore,
Process, HTTP, and legacy ACPX local remain outside custom provider
setup.
## Model Used
OpenAI GPT-6 through Codex, with reasoning, repository tools, code
execution, and browser testing. The exact deployment model ID and
context window size were 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
- [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.
> - Agents run through coding-agent adapters and the native runner. Both
use the same installed provider CLIs, model catalogs, and reasoning
controls.
> - OpenAI released GPT-6.1 Sol (`gpt-6.1-sol`) in Codex. Anthropic
released Claude Sonnet 5.5. The static Codex, Bedrock, and OpenCode
catalogs do not list these IDs.
> - The shared provider pack pins Codex 0.156.0 and OpenCode 1.18.32.
The evaluation image pins older Grok, Gemini, Kimi, Cursor, and GitHub
CLI releases. Codex 0.156.0 has no bundled metadata for GPT-6.1 Sol.
> - A model entry without a current harness, or a harness pin without
its runner integrity checks, fails at run time.
> - This pull request adds the verified model IDs and moves the harness
pins, executable digests, controller checks, and image pins together.
> - The benefit is that operators can select the current models, and the
native and local adapters share one current CLI installation.
## Linked Issues or Issue Description
Refs #13829 and #13838 (the September 22, 2026 model and harness
refresh). Related pull requests: #14993 (merged October 5, 2026,
superseding #14816) added the direct Claude Sonnet 5.5 entry and
refreshed the Claude runtime to Agent SDK 0.3.286 / Claude Code 2.1.286.
This pull request does not change the Claude runtime or the direct
Claude model list; it keeps the #14993 pins and adds only the Bedrock
Sonnet 5.5 ID. After #14993 merged, this branch was rebased onto
`master` (October 5, 2026). The six overlapping pin regions
(`docker/daytona-runner/Dockerfile`, `docker/daytona-runner/README.md`,
`package.json`, `pnpm-workspace.yaml`,
`packages/adapters/claude-local/src/index.test.ts`,
`packages/paperclip-runner/src/backends/native-backend-factory.test.ts`)
were resolved by keeping this pull request's Codex 0.160.0 and OpenCode
1.18.34 pins next to #14993's Claude 0.3.286 / 2.1.286 pins, taking the
union of the Sonnet 5.5 model IDs in the Claude test, and merging both
README paragraphs. The Sonnet 5.5 effort and CLI-gate lines in the
Claude adapter were identical in both pull requests and merged without a
diff. #14917 and #14918 reordered the Claude and Codex model lists
earlier; the new entries sit where those ordering rules put them.
Sources checked on 2026-10-02:
- [OpenAI Codex models](https://learn.chatgpt.com/docs/models): GPT-6.1
Sol uses `gpt-6.1-sol`, supports reasoning efforts from Light to Ultra,
and has Standard and Fast modes at launch. The page also records that
`gpt-5.4` and `gpt-5.4-mini` retired from Codex with ChatGPT sign-in on
August 31, 2026, and that `gpt-5.5` retires on October 14, 2026. Neither
retirement applies to the OpenAI API.
- [Codex CLI releases](https://github.com/openai/codex/releases) 0.157.0
through 0.160.0. The bundled model metadata in the 0.160.0 Linux binary
contains `gpt-6.1-sol`.
- [Claude Sonnet
5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview):
Bedrock ID `anthropic.claude-sonnet-5-5`, released September 28, 2026.
- [OpenCode releases](https://github.com/anomalyco/opencode/releases)
1.18.33 and 1.18.34 (fixes only). The OpenCode model registry lists both
added provider-qualified IDs.
- npm `latest` tags for `@xai-official/grok` 1.0.46,
`@google/gemini-cli` 0.62.0, and `@moonshot-ai/kimi-code` 2.1.1.
[xAI](https://docs.x.ai/docs/models),
[Google](https://ai.google.dev/gemini-api/docs/models), and
[Kimi](https://www.kimi.com/code/docs/en/kimi-code/models.html) list no
newer coding models.
- Cursor CLI 2026.10.01-e373342 is the version the official installer
resolves. The pinned digest is the SHA-256 of the versioned Linux x64
archive.
- [GitHub CLI 2.102.0](https://github.com/cli/cli/releases/tag/v2.102.0)
(security fixes). The pinned digest matches the release `checksums.txt`.
## What Changed
- Codex adapter: add `gpt-6.1-sol` to the model list, the Fast mode
list, and the Ultra effort set. It is the first entry: #14918 orders the
list newest version first, and its description notes the ChatGPT app
lists GPT-6.1 Sol first. Update the adapter documentation text.
- Claude adapter: add `us.anthropic.claude-sonnet-5-5` (Bedrock Sonnet
5.5) to the Bedrock catalog in the newest-Sonnet slot after Opus 5.5;
`us.anthropic.claude-sonnet-5` moves into the older-Sonnet group,
matching what `sortClaudeModels` from #14917 produces at runtime. Any
Sonnet 5.5 ID (direct or Bedrock-qualified) now gets the documented
`xhigh` and `max` efforts and requires Claude Code 2.1.284 or later on
the CLI lane (the Claude Code changelog entry for 2.1.284 adds
`claude-sonnet-5-5`). These two lines are identical to the ones #14993
merged, so the branch carries no diff for them.
- OpenCode adapter: add `openai/gpt-6.1-sol` and
`anthropic/claude-sonnet-5-5` to the static fallback catalog.
- Codex runtime pin 0.156.0 → 0.160.0 in the root and workspace
overrides, the runner package, the Codex ACP package patch, the
qualified ACPX profiles, the Linux x64 executable digest, the Rust
provider backend and its tests, the provider-pack manifest pins, the
remote controller pins, the sandbox npm install spec, and the opt-in
qualification scripts.
- Remote Codex compatibility window: upper bound 0.157.0 → 0.161.0. The
minimum stays at 0.149.0.
- OpenCode runtime pin 1.18.32 → 1.18.34 in the runner package, the
materialization script, the server and Rust qualified versions, the eval
and live-session labels, fixtures, and the configuration label.
- Evaluation image (`docker/daytona-runner/Dockerfile`): Grok CLI
1.0.46, Gemini CLI 0.62.0, Kimi Code 2.1.1, Cursor CLI
2026.10.01-e373342 with its digest, GitHub CLI 2.102.0 with its digest,
Codex and OpenCode version probes, and the refreshed lockfile digest.
The Claude Code 2.1.286 probe comes from #14993 and is unchanged here.
- `pnpm-lock.yaml` is not part of this pull request. The repository's
pull request gate rejects lockfile edits, and the refresh bot
regenerates the lockfile on master (the same flow #13838 used). The
Dockerfile `PAPERCLIP_RUNNER_LOCK_SHA256` default is the digest of the
lockfile that `pnpm install --resolution-only --ignore-scripts
--no-frozen-lockfile` (the refresh workflow's command) produces for the
combined pins on the rebased branch (`e1856797…`); that lockfile differs
from master only in the `@openai/codex` 0.160.0 platform packages, the
`@anthropic-ai/claude-agent-sdk` 0.3.286 override that #14993 introduced
(the open refresh-bot pull request #14872 carries that part),
`opencode-ai` 1.18.34 with its Linux x64 baseline, and the `codex-acp`
patch hash.
- Documentation: runner README, runner compatibility doc, environment
variable example, and a new `doc/adapter-model-audit-2026-10-02.md` with
sources and deferred items.
- Tests: Codex adapter catalog, server adapter models, Codex
compatibility window, native session executor pins, runner package
contract, OpenCode materialization, and UI effort options.
Unchanged on purpose: Claude Agent SDK 0.3.286 / Claude Code 2.1.286
(already on `master` from #14993), ACP bridges (`acpx` 0.13.1,
`claude-agent-acp` 0.73.0, `codex-acp` 1.6.2; newer upstream releases
need a separate qualification), the native Grok runtime 1.0.13, Pi
0.84.2 / 0.87.1 (the Pi 1.0 runner stack covers it), and Hermes 0.19.0
(current). `gpt-5.4` and `gpt-5.4-mini` stay in the picker because the
OpenAI API still serves them.
## Verification
Run on Linux x64 with Node 25.9.0 and pnpm 9.15.4 after `pnpm install
--no-frozen-lockfile` (the refreshed lockfile stays local; see above).
The results below were re-run on the rebased head (October 5, 2026) for
the suites the conflict resolution touches; the other rows are from the
original run and are covered by CI on every push:
- Rebased head: `packages/adapters/codex-local` 482 passed;
`packages/adapters/claude-local` 340 passed, 4 failed (`execute.remote`,
`test.probe`, `execute.acp-fallback`, `acp` spawn/env-hardening cases
that fail identically on unchanged `master` in this host environment);
`server` adapter-models + codex-runtime-compatibility +
native-session-executor + adapter-registry 607 passed, 1 failed (the
same adapter-registry override-pause case as before, also failing on
`master` here); `packages/paperclip-runner` native-backend-factory +
qualified-profiles 36 passed; `ui` codex-reasoning-effort +
config-fields + model-utils 19 passed. Rust, full typecheck, build, and
the Docker image are left to CI as before.
- `vitest run` in `packages/adapters/codex-local`: 13 passed. `vitest
run` in `packages/adapters/claude-local` (whole package, including the
new Sonnet 5.5 gate and effort tests): see the latest CI run and the
comment below. `vitest run` in `packages/adapters/opencode-local`: 48
passed, 1 failed (`runtime-config.test.ts` reads the host
`PAPERCLIP_OPENCODE_PROVIDERS` variable; it fails the same way on the
unchanged base).
- `vitest run src/__tests__/adapter-models.test.ts
src/services/native-runtime/codex-runtime-compatibility.test.ts
src/__tests__/adapter-registry.test.ts` in `server`: 84 passed, 1 failed
(`adapter-registry.test.ts` override pause test; it fails the same way
on the unchanged base).
- `vitest run` in `ui` for `codex-reasoning-effort`,
`agent-setup-fields`, `config-fields`, and `ComposerRunSettingsPicker`:
25 passed.
- `node --test test/acpx-codex-package-contract.test.mjs
scripts/materialize-opencode-binary.test.mjs
scripts/runner-protocol-eval-campaign.test.mjs` in
`packages/paperclip-runner`: 23 passed. The package contract test
verifies the installed Codex ACP executable digest and the 0.160.0 patch
pin.
- `vitest run src/drivers/acpx src/backends src/drivers/opencode
src/live/live-session.test.ts` in `packages/paperclip-runner`: 626
passed, 5 failed, 1 skipped. The 5 failures
(`installation-integrity.test.ts` `/proc/self/fd` module loading and one
OpenCode answer-selection test) also fail on the unchanged base under
Node 25; Linux CI runs Node 24.
- `pnpm run test:opencode:qualification` in `packages/paperclip-runner`
against the installed OpenCode 1.18.34 executable: passed.
- `codex --version` from the installed pack prints `codex-cli 0.160.0`.
The Linux x64 executable digest `12eb3e81…652aad` was computed from the
`@openai/codex@0.160.0-linux-x64` archive after checking its registry
`dist.integrity`.
- `pnpm check:token-gates`: all gates clean.
- `pnpm run typecheck:typescript` in `packages/paperclip-runner`:
passed. Package typechecks ran one at a time; see the comment below for
the server and UI results.
Not run here, and needed from CI:
- Rust tests and `pnpm -r typecheck` / `pnpm build` for the server (no
`cargo` in this environment; the server typecheck prepares the runner
vendor build).
- The Docker evaluation image build and the real-binary Codex startup
and session-resume probes (no Docker; the probes need the compiled
`paperclip-runnerd`). The trusted CI runner workflow covers them.
- Authenticated inference with any new model. This change is metadata
and startup validation only.
## Risks
- Codex 0.160.0 changes the bundled model catalog and app-server
behaviour (authoritative provider catalogs, incremental running-turn
tracking). The patched `codex-acp` 1.6.2 bridge is unchanged and
declares `^0.148.0`; it worked with 0.156.0 under the same override. If
CI probes show a protocol change, the pin can return to 0.156.0 by
reverting this pull request.
- The compatibility window upper bound moves to `<0.161.0`. Remote
images with Codex 0.157 to 0.160 become accepted. Older images stay
accepted down to 0.149.0.
- Until the refresh bot lands the regenerated lockfile on master, the
Dockerfile lockfile digest default does not match the committed
lockfile. The trusted CI workflow computes the digest from its own
resolution at build time, so this affects only a local build that passes
no digest.
- Existing saved model selections and effort settings are not changed.
Agents on `gpt-5.4` or `gpt-5.5` with ChatGPT sign-in need a model
change before the OpenAI retirement dates; that is documented, not
enforced.
- Rollout order: deploy the controller and runner from this change
before promoting a sandbox image that carries these pins. Older
controllers reject the new provider-pack pins.
## Model Used
- Claude Fable 5.1 (Anthropic, model ID `claude-fable-5-1`), 1M context
window, adaptive thinking, tool use. The model ran as a Paperclip agent
through the Claude Code harness, performed the web research, edited the
code, and ran the tests listed above.
## 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
- [ ] 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
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Bender (Fable) <noreply@paperclip.ing>
Co-authored-by: devinfoley <139239+devinfoley@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Require explicit native-effective thinking modes, reject drift across reconnects, and retain observed settings in qualification artifacts. Version the profile and pinned wrapper closure for the new contract.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Pin Pi profile 8 to native message provenance, preserve explicit empty starts and ends, and keep replay/history and native notices out of final assistant aggregation. Validate fresh, warm and loaded SDK sessions and exact native closure bytes.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve Pi v6 and bounded startup pools, admit current Cursor and Copilot v4 identities, and combine additive Product flows and catalog assertions.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The shared ACP adapter engine records agent failures for operators.
> - ACP providers can report a failure category, title, and detailed
cause.
> - Our patch kept only the category in the saved error, so an operator
could not diagnose a failure when tracing was off.
> - This pull request preserves redacted provider diagnostics in the run
error, transcript, and structured run result.
> - Operators can now inspect the provider message and any supplied
request ID or stack trace after the run ends.
## Linked Issues or Issue Description
Refs #13889 (the diagnostic gap; this PR does not update the bundled
Claude version).
Refs #14484 (related model-refusal classification; this PR retains
diagnostics for all terminal failure categories).
**What happened?**
An ACP turn failed with only `ACP agent reported a terminal service
failure.` The provider's title and details were available in memory but
absent from the saved error and transcript.
**Expected behavior**
The run retains useful provider diagnostics even when raw tracing is
disabled. Credentials remain redacted. A size limit must report
truncation instead of silently removing the cause.
**Steps to reproduce**
1. Run an ACP agent that returns an error-severity typed session
failure.
2. Include an HTTP error, request ID, and stack text in its title and
details.
3. Inspect the failed run with tracing disabled. Before this change,
only the category survives.
## What Changed
- Both pinned ACPX patches pass complete error text to the in-memory
callback, so redaction happens before truncation.
- The shared engine retains the sanitized category, title, and details
in `resultJson.terminalSessionFailure` and includes the text in the run
error and error transcript.
- Diagnostics redact configured environment values even under arbitrary
names, unknown launch-environment values, connection URL passwords, run
credentials, and common credential syntax. Known boolean settings remain
readable, while credential values are redacted even when embedded in
other text. Diagnostics remove control characters and invalid Unicode.
- Title and detail limits keep escaped transcript JSON below the
server's chunk limit. Truncated fields include an omission count. The
safe run-result projection preserves a byte-bounded diagnostic preview
when the result exceeds its byte budget, with an explicit pointer to the
full adapter-bounded run error and transcript.
- The existing UI and CLI display the error. Diagnostics do not become
assistant output. Issue continuation summaries and session-compaction
prompts receive only the generic category, preventing provider text from
becoming handoff instructions. Existing quota classification, warnings,
timeout precedence, and control-channel failure precedence remain in
place.
- Regression tests cover real ACP child processes with both pinned
versions in one-shot and persistent modes, credential redaction, request
IDs after the old 4 KiB cutoff, transcript parsing, storage bounds, and
database retrieval of oversized multibyte diagnostics.
## Verification
- Full CI on `20ad4f5f1f66c46d2c260e6ad0339cbea607b4cf`: **54 passed, 2
intentionally skipped, no pending or failing checks**. Includes
typechecking, build, all Vitest shards, Runner checks, browser E2E, and
the canary packaging/public-install dry run.
- Greptile: **5/5** on this commit. Superagent security scan passes. All
review threads are resolved.
- Local verification passed: shared ACP engine suite (395 tests); real
Claude ACP child-process and diagnostic regressions across both pinned
runtimes and both execution modes; run retrieval and model-handoff
regressions (59 tests); ACPX patch packaging (16 tests); full typecheck
and build. Affected package typechecks and focused tests were rerun
after review fixes.
- The broad local `pnpm test:run` was stopped after review edits made
its cached imports stale. Fresh targeted runs pass, including both
affected server suites. Cold-build import failures were also rerun after
dependency builds: chat integration (1,063 tests) and tool access (351
tests) pass. The final commit's complete CI matrix is green.
## Risks
- Provider diagnostic text is untrusted. This change retains more of it
in company-scoped run records. Redaction and size bounds apply before
persistence.
- Diagnostics are limited to fields the provider supplies. Old runs
cannot recover discarded error text.
- No schema migration, recovery-policy change, or new Telemetry or
OpenTelemetry export.
## Model Used
- OpenAI GPT-6 through Codex, with reasoning, repository inspection,
code editing, and test execution. The exact serving 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
- [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>
Add shared rich ACP transport, durable questions and permissions, verified provider packaging, and bounded activity and plan presentation. Keep Cursor, Copilot, and Pi pending their separate provider qualification.
Persist interaction settlement before publication, fence failed writes until fresh recovery, and preserve owned-process cleanup. Incorporate reviewed mainline integration with extended harness coverage.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve exact delivery retries while separating reused native IDs across warm prompts. Add pinned SDK ordering, real semantic bridge, lifecycle and history regressions, and bump the verified Pi profile to v4.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Retain each native builder, profile installer, extension adapter and image-content input. Update the pack dispatch test now that Pi is installed alongside Cursor and Copilot. Combined ACP tests pass 616 cases; actual distribution/wrapper package checks pass 34 cases.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Bump the immutable Pi profile to version 3 and reject prior warm snapshots. Bound and redact authenticated MCP validation errors while retaining failure status; preserve standard ACP tool values alongside terminal metadata.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
The actual patched wrapper now distinguishes successful, failed, and missing retry outcomes. Regressions fail on the previous wrapper and preserve terminal provider failure. Regenerate the wrapper, target closure and profile pins; the previous pack evidence remains historical until rebuilt after the foundation rebase.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip manages AI agents and governs their work.
> - Its native runner uses structured provider protocols for sessions
and tools.
> - Grok Build supports ACP over stdio, but the runner did not expose
it.
> - Native execution requires company-scoped credentials, verified
identities, and permission gates.
> - This change adds Grok through ACPX for local and Daytona execution.
> - Subscription login and explicit API-key execution have separate
credential paths.
> - Qualification grades real tool outcomes, durable state, and browser
workflows.
## Linked Issues or Issue Description
Refs #13845, #13847, #13850, #13878, #13901, #13973, #13977, #13979.
Add **Grok Build** to `paperclip_runner` with `provider: "acpx"`,
`acpxAgent: "grok"`, and model `grok-4.7`. Existing legacy Grok agents
keep their adapter. Merge the three companion fixes (#13973, #13977,
#13979) before treating the integrated Product qualification as deployed
behavior.
## What Changed
- Synchronize shared, TypeScript, Rust, server, validation, and UI
provider contracts.
- Run Grok native ACP stdio through ACPX and the authenticated Paperclip
MCP bridge. Verify the pinned executable and exact ACP model identity.
- Prefer company subscription login. Support an explicit company-secret
API key without automatic paid fallback. Fence refresh and copyback to
the same account and remove private runtime credentials after
containment.
- Preserve selected permissions, cancellation, durable session identity,
resume, and restart recovery. Keep unsupported steering and goals
unavailable. Preserve missing usage and cost as unknown.
- Package checksum-verified Grok Build 1.0.13 for Daytona with an
immutable, signed image built on EC2.
- Add deterministic admission, protocol, permissions, identity,
credential, failure, and cleanup checks. Add the maintained 39-case
protocol roster and separate subscription/API Product profiles.
- Fix live-test findings in reasoning events, reloads, idle-owner
retirement, credential-home cleanup, expired-login model discovery,
launcher pinning, and rerun evidence selection.
- Align control-plane state readers with the transport's 64 MiB bound
while retaining identity, ownership, lifecycle, and size rejection
checks.
- Stabilize two asynchronous CI assertions while retaining actual
outcome and filesystem-evidence checks.
## Verification
Current integration head `f114948376056fe0b6b34c1496ae8667b59daa63`
includes master `3447609d2247e75e55d91493dda91a608364f672` (2026-09-28).
Two master advances during verification overlapped the eval catalog; the
final merge preserves Grok qualification, completion updates, and
bounded API-response reading in all 348 cells. All 77 focused
catalog/eval/workflow tests pass. Both native stack layers (#14397) are
mergeable, and both exact-head Greptile reviews are 5/5 with successful
security scans and no unresolved review threads. All current-head CI is
green: 56 successful checks/statuses and four intentional skips ([CI
run](https://github.com/paperclipai/paperclip/actions/runs/36447097232)).
Trunk code-owner requirements remain enforced. The review summary’s
non-blocking saved-asset offset classification note concerns code
already merged in #14301; those runtime files are identical to master
and outside this stack’s diff. Historical live evidence below retains
its original source revisions.
Earlier integration checkpoint:
`24fc9b94ca0afb21ccdc8d26dbb2e4b258ad72cb`. Refreshed against master
`0f14d2612`, preserving Grok qualification alongside the new accounting
and lifecycle suites. All 124 focused catalog, evidence, and
service-worker checks pass. The current base workflow includes the
explicitly selected public-install verification lane; follow-up #14024
supplies its verifier script. CI at that earlier checkpoint was green
(56 successful checks/statuses, four intentional skips), and the review
is 5/5 with no unresolved findings. Prior feature CI at
`fd73f0a9b1ecdf4094685054028df71739ddc3e1` passed ([run
36148259902](https://github.com/paperclipai/paperclip/actions/runs/36148259902));
that is historical evidence, not a current-head result.
Paid Product measurements use frozen integrated source
`2d939a92b21dcaf5c77c88b54d96784d2ddd0699`, which combines the feature
with #13973, #13977, and #13979. That source passed all 52 CI checks and
clean 5/5 review. Later master syncs incorporate upstream changes. Their
checks remain separate from these pinned live measurements.
| Check | Result and source-pinned report |
| --- | --- |
| Subscription protocol roster | [39/39 first attempts; 206
assertions](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-36046839612-1/index.html),
runtime `bc6833f7`, evals `92bb4b8c` |
| API protocol roster | [39/39 first attempts; 206
assertions](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-35926577007-1/index.html),
runtime `4a1061c8`, evals `3213dbec` |
| Subscription full Product matrix | [16/16 first attempts; 144
assertions; cleanup
passed](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36096908572-1/index.html),
source `2d939a92` |
| Subscription core repetitions | 18/18: tool use, planning approval,
and Stop/resume each passed three times in local and Daytona profiles.
The full matrix contains repetition one; [repeat
two](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36104551060-1/index.html)
and [repeat
three](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36108100404-1/index.html)
each passed 6/6. Total: 28 unique subscription attempts at `2d939a92`. |
| API smoke and question continuation | [4/4 first attempts; cleanup
passed](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36147315401-1/index.html),
both environments at `2d939a92` |
| Historical API Product coverage | [16/16 full
matrix](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35875144860-1/index.html)
and 18/18 core repetitions at `4a1061c8`; retained as measurements of
that revision |
| Native Daytona proof | Three subscription and three API
MCP/permissions/resume runs passed at `bc6833f7`. Three expired-login
admission and fenced refresh checks passed without inference. All test
sandboxes were removed. |
| Inspectable artifacts and UI | Current-source screenshots verify
planning approval, direct Ask completion, question continuation after
controller restart, and two downloadable project revisions. The project
downloads pass 12 and 18 tests; all 40 independent artifact oracle
checks pass. |
| Provider-free checks | 116 eval-validator tests, 39 Grok definitions,
and 359 enabled/external campaign cells pass. Continuation regressions
above 2 MiB and 16 MiB failed before their fixes; 32 focused
recovery/ownership/size checks pass. |
The 32 unique current-source Product attempts have no failures, retries,
or skipped cells, and all cleanup checks pass. Whole-workflow timing,
model identity, image and provider-pack provenance, attempts, and
accounting coverage are retained in the canonical reports. The report
publisher's conservative `complete=false` flag is preserved; independent
audits verify the exact selected source catalog and immutable result
rows.
Pins: Grok Build `1.0.13 (5e9a58528b76)`, ACPX `0.13.1`, ACP model
`grok-4.7`. Linux binary SHA-256:
`edf79521581bb5e6b95abef848491a6a742e860da3e237ebe86a280d30dce4c1`.
Launcher SHA-256:
`f0b698395a3704ed2ffaf84ea19bdb20c36c8a0a70b7c629c7b6ffe144e59e55`.
Image:
`ghcr.io/paperclipai/paperclip-daytona-runner@sha256:76b24edfd850219e949418b19e4ceba690e84d51d199ade426e484953329b5e9`.
Image build source is `4196a4cd`, recorded separately from application
source `2d939a92`; each campaign verifies the image signature and
provider pack.
Original failed campaigns remain available: [continuation
bound](https://github.com/paperclipai/paperclip/actions/runs/36057718059),
[scheduler/event
capture](https://github.com/paperclipai/paperclip/actions/runs/36071063537),
and [startup cleanup plus EC2
interruption](https://github.com/paperclipai/paperclip/actions/runs/36080870743).
They retain their original grades. No Docker or Rust builds ran on the
developer laptop for these follow-ups.
## Risks
Merge packaging follow-up #14024 with this base before public release.
The follow-up replaces the private Grok bridge package with a built-in
launcher and makes the native binary an explicit sandbox prerequisite.
Three separate, reviewed fixes are part of the tested integrated
behavior: #13973 serializes task-run admission; #13977 captures complete
event evidence; #13979 durably reconciles failed Daytona creation. Each
has green CI and clean 5/5 review. Failed-create recovery has 277 plugin
tests, 92 SDK tests, host-runtime recovery tests, and a real Daytona
lost-deletion-receipt proof. The live proof uses a private file for
journal persistence; database durability is covered by host tests.
Worker death before delivery of a failure envelope remains outside that
recovery mechanism.
Subscription fixtures stage an authorized company login; interactive
browser sign-in is not qualified. Local Product profiles ran on EC2
Linux. The temporary subscription credential was removed from the
protected GitHub environment after all subscription audits, with absence
verified. Runtime homes and refresh copyback remain ownership-fenced.
Protocol results remain pinned to their original revisions; they are not
relabeled as tests of the latest feature commit. New binary/model
versions require qualification. Missing token usage and model cost
remain unknown; runtime estimates do not establish a full bill.
Automatic paid Grok scheduling remains disabled pending separate
reviewed enablement. The 64 MiB bound can increase memory use for
verbose sessions, and larger files still fail closed. No automatic
legacy-agent migration occurs.
## Model Used
OpenAI GPT-6 through Codex, with tool use and code execution. The exact
serving model identifier 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
- [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>
Record terminal usage before classifying or throwing a provider-reported failure. Failed Pi turns retain their exact request token counts and source-proven USD receipt, including across canonical disk serialization, while the failure remains terminal.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Synchronize with master 14795136f5 while retaining the recorded implementation base. Regenerate protocol contracts and preserve both input-presence and permission-scope checks.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Bind response receipts to the active stream, request and prompt; reject cancellation, disconnect, write failure and mismatched responses before acknowledging durable delivery.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip runs agents through local adapters and the native runner.
> - Both paths must use the same installed provider CLI.
> - New models require current harness releases.
> - The runner still pins Codex 0.153.4, Claude SDK 0.3.263, and
OpenCode 1.18.29.
> - Changing the image alone would fail the runner's exact version and
executable checks.
> - This pull request updates those dependencies, integrity checks,
controller checks, and image pins together.
> - Shared installations can then run the current models without a
task-time download.
## Linked Issues or Issue Description
Refs #13829, which updates model choices and reasoning controls.
Searches found no open PR that updates these runtime pins.
**Current behavior**
The shared provider pack ships old CLIs. Claude Code 2.1.263 cannot run
Opus 5.5, which requires 2.1.280. Remote controllers reject provider
packs whose versions differ from their declared pins.
**Proposed behavior**
Use Codex 0.156.0, Claude Agent SDK 0.3.280 / Claude Code 2.1.280, and
OpenCode 1.18.32 throughout the runner. Keep the reviewed ACP bridge
patches and one shared CLI installation per provider.
**Reason and benefit**
Current harnesses support the new model IDs while preserving executable
verification and remote provider-pack compatibility checks.
## What Changed
- Update dependency overrides, the Codex ACP package patch, runtime
profiles, and remote controller pins.
- Verify the new Claude Linux x64 and macOS arm64/x64 executables and
Codex Linux x64 executable against integrity-verified npm archives.
- Refresh OpenCode version checks, fixtures, and the runner
configuration label.
- Refresh the eval image's Grok, Gemini, Kimi, Cursor, and GitHub CLI
pins and archive hashes. Hermes remains current at 0.19.0.
- Refresh the build-time lock digest from clean pnpm 9.15.4 resolution.
Leave lockfile commits to repository automation.
- Document model compatibility and the separation between CLI runtimes
and patched ACP bridges.
## Verification
- `pnpm -r typecheck` and `pnpm build` passed.
- Rust workspace release tests passed.
- Package/patch and OpenCode binary-materialization contract tests: 11
passed.
- Real Codex 0.156.0 startup-ownership and paginated session-resume
probes passed with isolated synthetic homes and no model turn.
- Codex app-server `thread/start` preserved `gpt-6-sol` and
`gpt-6-luna`; no `turn/start` was sent. An unauthenticated built-in
catalog does not include those account-served entries.
- Installed Claude integrity probes passed for `claude-opus-5-5` and
`claude-fable-5-1`.
- `pnpm --filter @paperclipai/paperclip-runner
test:opencode:qualification` passed with the actual OpenCode 1.18.32
executable under Node 24 and Node 25. The loopback provider exercise
covers health/version, session creation/read/delete, SSE, and a
completed async prompt.
- `pnpm check:token-gates` passed.
- The targeted runner suite passed 130 tests. Three macOS failures in
snapshot module lookup and OpenCode final-message selection also
reproduce on the unchanged base; Linux CI will provide the platform
check.
- [Final Linux
CI](https://github.com/paperclipai/paperclip/actions/runs/35798076399):
all gates passed. Four jobs needed one retry after their CI workers
received shutdown signals. The PR has 55 successful checks, two skipped
checks, Greptile 5/5, and no unresolved review threads.
- Changed runner configuration UI tests: 5 passed.
- Full macOS `pnpm test:run` reached 13,094 passing server tests, 84
skipped, and 18 failures before the wrapper stopped. Failures involved
skill-cache publication permissions, missing bundled connector skills in
the worktree, and a conversation-reset timing case. The 10 cache
permission failures reproduce on the unchanged base; both
conversation-reset cases passed on a targeted retry. The wrapper did not
reach its later workspace/serialized groups locally; Linux CI covers
those groups.
- The local Docker daemon did not respond, so no local Docker build was
run. No billable model requests were made.
## Risks
- Deploy the matching controller and provider pack together. Older
controllers enforce their previous exact pins.
- Current upstream CLIs can change behavior. Existing protocol tests and
isolated real Codex probes cover the integration boundaries;
authenticated model inference is not part of these checks.
- ACP bridge package versions and executable digests stay unchanged
because their executable bytes are unchanged. Only the underlying
CLI/SDK dependencies move.
- No schema migration. Revert the runtime and image pins together to
roll back.
## Model Used
OpenAI GPT-6 via Codex, with repository tools, code execution, and web
research. The exact serving model ID and context window were not exposed
by 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 for the changed surfaces
and real-executable probes; full macOS-suite limitations are listed
above
- [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>
Typed Claude ACP quota failures lost their recovery classification and reset
time when the runtime reduced provider metadata to a generic category error.
Inspect terminal metadata in memory and retain only safe recovery labels and
a parsed reset timestamp. Preserve the existing handling of other limits.
Verified real child processes on both pinned ACPX runtimes, adapter and
server recovery regressions, all PR CI gates, and Greptile 5/5. Also isolate
a pre-existing chat regression from unrelated fixtures’ retry work.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Dotta