Persist generic stop intent before provider dispatch, use the exact pinned StopLease capability for release and restart recovery, and retain saved allocations when capability or stop confirmation is unavailable.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Version new plugin-pinned intents and recover v1 from the exact lease recorded plugin without driver-key fallback or accepting mismatched explicit pins.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Refuse a duplicate driver key or unavailable original plugin during stop-only recovery; preserve the pending intent and fence later provider rebinding.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Exercise a 190 MiB journal made of individually bounded event frames and document off-thread proof quotas, retained evidence, and nonblocking file admission.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Stream proof reads through a fixed buffer, retain only authority evidence, and preserve full-file digests and warm-transition fingerprints. Fail closed when essential evidence exceeds the bounded projection budget.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve terminal unsafe-archive repairs and future retry delays when an earlier reconciler snapshot enters after the live owner releases copyback.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Add native read, update, history, and restore operations with server-bound identity and revision compare-and-swap safety. Register the default catalog and API discovery paths; cover real authority authorization and exact revision restore.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Implement PAP-66 foundation: exact content history, transactional compare-and-swap saves, current responsible-user authorization, recoverable materialization, and editor history. Keep run staging and cleanup integration with PAP-63.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Keep Markdown review documents available alongside explicit attachment tabs. Preserve direct card downloads and separate the preview action. Regressions fail with the text context enabled before the fix; 199 focused tests and both desktop/mobile browser cases pass afterward.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve the accepted result and retained sandbox, distinguish repairable unsafe paths from missing sandboxes, and keep transient copy-back failures retryable.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Keep large response artifacts inspectable through the existing authenticated API route. Preserve company and run authority, UTF-8 boundaries, and transfer limits. Reproduce the artifact loop through real HTTP and add an explicit full-stack fixture.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Restore the recovered PAP-61 viewer, use accessible icon controls for rendered/raw Markdown and downloads, and keep explicit mobile file requests on the visible panel. Verify uploads, rendering, tab selection, and exact original downloads on desktop and mobile.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip manages AI agents and their work.
> - Remote runs need a snapshot of the task workspace before the agent
starts.
> - The snapshot lists untracked filenames through the shared Git scan
scheduler.
> - A generated directory with a few thousand long filenames can exceed
the 1 MiB output limit.
> - This stops setup and prevents the agent from continuing its task.
> - This change gives that listing a 32 MiB bound and keeps the explicit
file snapshot.
> - Normal generated trees can now pass setup, while larger snapshots
still fail at a finite limit.
## Linked Issues or Issue Description
Refs #11572 and #12214 for the existing bounded scan and ignore-scan
protections.
**What happened?**
An agent continuation failed during workspace setup with `Workspace Git
scan exceeded its output limit`. A real Git fixture reproduces the
untracked-file path: 5,000 long filenames in one generated directory
exceed its 1 MiB output limit.
**Expected behavior**
The workspace snapshot must support ordinary generated trees with
thousands of files. It must keep a finite output bound and select
explicit files before staging.
**Steps to reproduce**
1. Commit a base file in a Git repository.
2. Add 5,000 untracked files with long names in one new directory.
3. Call `readGitWorkspaceSnapshot` with the normal scan limits.
4. Observe the output-limit error before this change.
**Paperclip version or commit**
Base commit: `640dee1`.
**Deployment mode**
Remote sandbox execution from source.
## What Changed
- Increase the untracked-file snapshot output bound from 1 MiB to 32
MiB.
- Keep explicit file selection, the shared scheduler, the timeout, and
the other scan bounds.
- Test that 40,000 long filenames above the old 8 MiB bound reach the
snapshot. Reuse those files with deeper paths to prove that output above
32 MiB still fails.
- Test that files created after the snapshot, including an ignored
secret, stay out of the overlay archive.
- Check the workspace root identity and reject selected paths with
symlinked parent directories before upload.
- Test root replacement after path resolution, including root-level
selected files.
- Preserve existing workspace root aliases by capturing the resolved
root before snapshot selection. Test that later alias retargeting cannot
change the archive contents.
- Stop staging on permission and I/O errors; continue to allow missing
files.
- Test these failures and preserve selected symlink entries.
- Accept valid case-renamed directories by checking ancestor file types.
A modeled case-insensitive regression failed before this correction and
now passes.
- Give the 40,000-file fixture enough time to remove its files.
- Document the larger bound and staging behavior.
## Verification
- Red: the 5,000-file regression failed with `stdout maxBuffer length
exceeded` before the fix.
- A separate check through the real server scheduler reproduced
`workspace_git_scan_output_limit` on the original code. The revised code
selected all 5,000 files.
- The late-file regression failed against the first PR revision because
the archive contained `drafts/late.secret`. It passes with the final
explicit-file approach.
- The staging regressions failed before the review fix: a substituted
parent directory and permission/I/O errors were accepted. All three
cases now stop before upload.
- Green: 134 tests passed across `git-workspace-sync.test.ts` and
`sandbox-managed-runtime.test.ts` with Vitest 4.1.11. This includes
complete selection above 8 MiB and rejection above 32 MiB.
- `pnpm --filter @paperclipai/adapter-utils... typecheck` passed after
the revision.
- The module-boundary check and `git diff --check` passed.
- `pnpm -r typecheck` and `pnpm build` stopped in the Rust runner steps
because this environment has no `cargo` executable.
- The full `pnpm test:run` attempt ended with `SIGKILL` during the
general server suite. It did not finish. That full-suite result belongs
to the earlier revision. Fresh checks are required for this revision.
- The new regression fails at the old 8 MiB bound with `stdout maxBuffer
length exceeded`. All 134 focused tests pass with the 32 MiB change.
- The affected typechecks and module-boundary check pass. The full local
typecheck requires Cargo, which is absent in this environment.
- Final verification for `b43e9bc95e55382c6a9bfe200487c164770c8be8`: 54
successful checks/statuses and two skipped Storybook checks. No checks
remain pending or failed.
- The [CI
run](https://github.com/paperclipai/paperclip/actions/runs/36315569674)
passes on attempt 2. The first attempt had one unrelated preview-fixture
readiness timeout. That exact test passed locally; its CI shard passed
on the single rerun.
- [Greptile reports
5/5](https://github.com/paperclipai/paperclip/pull/14194#issuecomment-5852045501)
on this revision. All review threads are resolved.
- [Security review accepts the documented memory
tradeoff](https://github.com/paperclipai/paperclip/pull/14194#discussion_r4115149465)
for this finite mitigation. The separate streaming follow-up will remove
full-list buffering.
- This revision also passes affected local typechecks and the
module-boundary check. Full local typecheck/build stop because Cargo is
absent. The full local Vitest attempt was stopped after about 18 minutes
once all remote gates passed; it did not complete locally.
## Risks
- Each untracked-file scan can buffer up to 32 MiB instead of 1 MiB. The
scheduler still limits concurrent scans and execution time.
- Snapshots above 32 MiB still fail with the existing error. Tracked and
ignored-file scan bounds stay unchanged.
- A workspace that replaces a selected path’s parent with a symlink now
fails staging.
- Detailed logs from the reported host were unavailable. The exact
command that exceeded its limit on that host is unconfirmed.
## Model Used
OpenAI GPT-6 through Codex, with reasoning, tool use, and code
execution. The runtime does not expose a more specific model build or
context window size.
## 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 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>
Preserve native coordinator ownership while accepted results await workspace
copy-back, assessment, or arbitration. Check that ownership in the terminal
update so a coordinator recorded after the liveness read is also protected.
Keep terminal task authority and exhausted-retry cleanup unchanged.
Validation: 28 focused recovery tests, local typecheck/build, 52 passing CI
checks, and Greptile 5/5 with no open findings.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip coordinates agent work across task turns.
> - Warm runners need reusable sandbox leases.
> - Lease acquisition read only the environment reuse setting.
> - Startup then read the agent's new warm setting and rejected the
ephemeral lease.
> - This fix requests reuse before acquisition, with provider checks
intact.
## Linked Issues or Issue Description
**What happened?**
Switching an existing native runner task from per-turn to warm fails
with `runner_warm_environment_requires_reusable_lease`. Environment
`reuseLease` defaults to false. Acquisition therefore creates an
ephemeral lease, and capability narrowing correctly denies reuse.
**Expected behavior**
Changing lifecycle between turns requests a compatible lease without
replacing the task workspace or changing the shared environment.
**Steps to reproduce**
1. Start a native runner task with inherited lifecycle and environment
reuse disabled.
2. Change the agent from per-turn to warm.
3. Continue the task on a reusable-capable sandbox provider.
**Paperclip version or commit**
Reproduced on `a6c4e7a`. Related: #12904 established warm workspace
continuity; this fixes the earlier lease-selection mismatch.
## What Changed
- Pass agent settings into acquisition and derive a run-scoped reuse
request.
- Respect explicit environment lifecycle overrides; leave other adapters
unchanged.
- Keep provider capability, ownership, cleanup and restore gates intact.
- Add orchestration and database-backed transition tests; document the
contract.
## Verification
- Red: three new assertions failed before the fix.
- Green: 156 tests pass in environment-run-orchestrator,
environment-runtime, native-sandbox-lifecycle, and
environment-execution-target-capabilities.
- Database-backed regression proves ephemeral → reusable → resumed
lease, same workspace, and unchanged stored environment. Provider RPCs
are mocked, not live Daytona.
- `git diff --check` passes.
- Latest-head CI passes typecheck, build, tests, runner checks, E2E, and
canary dry run. Greptile: 5/5; no open threads.
- Recovery uses the persisted lifecycle. Direct regression: red before,
six cases green after. CI runs the added Vitest cases.
- Full local checks were unavailable (missing dependencies and earlier
memory limits).
## Risks
Warm mode now requests retained resources despite an environment's
default `reuseLease:false`. Existing idle timeout and cleanup still
apply. Unsupported providers remain denied. No migration, credential
[REDACTED], or shared-environment mutation.
## Model Used
OpenAI Codex agent; reasoning, code editing and test execution. Exact
model ID and context size were not exposed to this run.
## 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 available)
- [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 relevant issue
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 [REDACTED] 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 native runner exposes tools for company tasks.
> - API search and call tools cover operations without a dedicated tool.
> - The current default hides these tools unless an operator sets an
environment variable.
> - This pull request enables the tools when that variable is absent.
> - Operators can still disable the tools or restrict them to selected
companies.
## Linked Issues or Issue Description
Refs #13003, which added the guarded API tools.
**What happened?**
The native runner does not advertise `search_api` or `call_api` with the
default server configuration.
**Expected behavior**
The tools are available without a special environment variable. Existing
authorization checks still apply.
**Steps to reproduce**
Remove `PAPERCLIP_RUNNER_API_TOOLS_ENABLED` and
`PAPERCLIP_RUNNER_API_TOOLS_COMPANY_IDS`. Create a normal runner
authority. Inspect its tool definitions.
**Paperclip version or commit**
a6c4e7a.
## What Changed
- Enable API tools when the server flag is absent.
- Keep explicit disable, invalid-value rejection, company restrictions,
and binding restrictions.
- Test default tool definitions and run HTTP integration tests without
the enabling flag.
- Update operator and hiring documentation. The existing shared gate
also controls `hire_agent`.
- Use the same policy in the E2E evidence summary so an unset flag is
not reported as disabled.
- Isolate default-availability tests from operator environment
variables.
## Verification
- Red test: two new rollout policy assertions failed before the fix.
- Focused policy, authority, and HTTP tests: 3 files passed; 41 tests
passed, 2 skipped. The two runnerd transport cases require a Rust-built
binary absent from this workspace.
- Command: `pnpm exec vitest run
server/src/services/native-runtime/runner-api-rollout.test.ts
server/src/services/native-runtime/paperclip-runner-tool-authority.test.ts
server/src/services/native-runtime/runner-api.integration.test.ts`.
- Attempted `pnpm -r typecheck`: blocked by missing `cargo` in this
workspace.
- Attempted `pnpm build`: terminated at the 4 GiB memory limit.
- Attempted `pnpm test:run`: stopped after memory pressure to run
focused tests alone.
- Repeated the 41 passing focused tests with an inherited disabled flag
and a foreign-company restriction; test isolation passed.
- `pnpm test:e2e:runner:unit`: 44 files and 543 tests passed.
- `pnpm test:e2e:runner:typecheck` exceeded the workspace memory limit,
including a retry with bounded Go memory settings.
- CI results will be recorded before handoff.
## Risks
- More native runs can discover API tools and the existing `hire_agent`
tool by default.
- The change does not remove company, run, mode, credential, lifecycle,
or approval checks.
- Explicit operator restrictions still take precedence. No database
migration is required.
## Model Used
OpenAI Codex agent. The runtime does not expose the exact model ID or
context-window size. Used reasoning, repository tools, shell execution,
and 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
- [ ] 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.
> - A comment can queue execution before the task changes state.
> - The task may be completed, cancelled, deleted, or reassigned before
setup checks ownership.
> - The ownership guard must prevent that obsolete execution from
starting.
> - This pull request records that guard outcome as cancellation and
settles the wake request.
> - Missing history and authorization errors remain failures that
operators can investigate.
## Linked Issues or Issue Description
**What happened?**
A comment can queue a run just before a user marks its task Done. The
ownership guard stops setup before adapter dispatch, but the run becomes
a setup failure and can put the agent into an error state.
**Expected behavior**
Cancel obsolete work when the typed task ownership guard rejects it.
Keep genuine setup errors visible. Do not change the task's terminal
state or current owner.
**Steps to reproduce**
Queue a task continuation, then mark the task Done or Cancelled before
continuation setup. The run should settle as cancelled without invoking
the adapter. Deleting or reassigning the task must also prevent
dispatch. Missing source history or explicit user authorization must
still fail.
**Paperclip version or commit**
Refreshed against master `b2e9e82f053af14777fd68e8834fff6bb64c84c4`.
Related: #13546 covers lost issue-lock claims, and #13888 covers
persisted continuation decisions and retry budgets. This change handles
the final continuation ownership guard during setup.
Thanks to @MrBlackTongue for the original typed cancellation
implementation and regression coverage. This update preserves the
contributor's commits, resolves the master conflict, and narrows
cancellation to task ownership invalidation.
## What Changed
- Add a typed `StaleExecutionContinuationError` for
`continuation_task_ownership_changed`.
- Use existing cancellation settlement for that typed guard, including
the run, wake request, issue execution ownership, and agent state.
Suppress immediate recovery of obsolete work.
- Preserve failure classification for missing source context, missing
user authorization, and untyped errors, including an untyped error with
identical text.
- Cover Done and Cancelled tasks with real database checks. Retain
company and assignment guard coverage. Verify cancellation performs no
adapter dispatch or automatic replay.
- Document the cancellation event and its error classification in the
run-log guide.
## Verification
Current head: `b875486e81`.
- `pnpm -r typecheck`: passed.
- `pnpm build`: passed.
- `pnpm exec vitest run
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/services/execution-continuation.test.ts --maxWorkers=1
--no-file-parallelism -t 'authorized continuation context|obsolete
continuation setup|untyped continuation setup failures'`: 17 passed; 316
unrelated tests excluded by the name filter.
- `pnpm test:run`: local full run is still finishing. It is not a clean
pass: the observed failures are three company-skills cache checks
(`EACCES` while renaming read-only cache directories on macOS), one
tool-access assertion, and one comment-wake timeout. The three cache
failures reproduce in isolation in unchanged code. The tool-access check
passes in isolation, and the entire comment-wake file passes (29 tests),
including explicit feedback after completion. Final full-run totals will
be added when available.
-
[CI](https://github.com/paperclipai/paperclip/actions/runs/36282532652):
all gates green on this head. An unchanged Runner workspace-diff test
initially returned no diff; an isolated check passed, and the failed job
plus its dependent gate passed on retry with no code change. Original
failed job: 108517010989.
- Greptile: 5/5 on the full current head, with no unresolved review
threads. Branch is current with master and conflict-free.
- Diff check and local secret/PII scan passed. No customer data or
private deployment identifiers are included.
## Risks
The classification change is limited to the typed ownership guard. A
task with missing history remains a failure rather than being treated as
an expected cancellation. Existing company, task-owner, terminal-state,
and authorization checks still prevent dispatch. Cancellation retains
its specific reason in the run log and does not grant a retry. No
schema, dependency, or API changes; no migration is required.
## Model Used
OpenAI GPT-6 via Codex assisted investigation, implementation, code
review, and test 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
- [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 bug issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name describes the change and contains no internal
ticket id
- [x] I have run the focused regression tests locally and they pass;
full-suite results are tracked above
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation
- [x] I have considered and documented the risks
- [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 merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The execution service owns each run and saves messages sent while it
runs.
> - Interrupt must stop the current executor before it delivers those
messages.
> - Remote Grok commands did not register the host cancellation control.
> - A cancelled task run could still write Done and prevent queue
recovery.
> - This pull request connects remote cancellation and revokes cancelled
run writes.
> - Saved input can use the existing queue admission rules after
verified cleanup.
## Linked Issues or Issue Description
**What happened?**
Interrupting a queued message marked a remote Grok run cancelled before
its sandbox stopped. The old run could still post a reply and mark the
task Done. Its saved follow-up remained deferred behind execution
recovery.
**Expected behavior**
Stop revokes run write authority and waits for verified termination.
Saved messages remain durable and enter one successor through normal
admission after cleanup.
**Steps to reproduce**
1. Run a task with `grok_local` in a remote sandbox.
2. Send a follow-up and use Interrupt while the command runs.
3. Let the old command attempt a task status update after cancellation.
4. Observe the task disposition and the saved message queue.
**Paperclip version or commit**
The gap is present in master at `d3e0f0a238`.
**Deployment mode**
Authenticated server with a Daytona sandbox.
Related work: #14028 and #14046 handle bounded continuation. #13291
covers infrastructure interruption and verified remote cleanup. #13332
addresses atomic recovery holds. This change handles direct Grok
operator cancellation and stale task writes.
## What Changed
- Register remote Grok cancellation before preparation. Keep command
ownership until the host confirms sandbox termination.
- Reuse the sandbox cancellation boundary for the direct CLI invocation.
Reject fresh attempts after cancellation and preserve workspace restore
failure evidence.
- Reject writes from cancelled task JWTs and runs with a pending stop.
Preserve diagnostic reads and existing conversation error codes.
- Recheck run authority under a database lock before task updates and
interaction responses commit.
- Preserve authorized handoffs that stop their own run. Only the
server-issued stop receipt for that request permits the final task
update.
- Add tests for hung commands, unverified stops, early cancellation,
copy-back failures, late Done, late interaction responses, authorized
handoffs, exact lease receipts, and one queue successor across
concurrent restart sweeps.
- Document the cancellation and write-authority contract.
## Verification
- Targeted adapter, cancellation-boundary, authentication,
queued-message, interaction-service, and activity-route tests passed.
The expanded run passed 214 tests; one new test had an incomplete
fixture. After correcting the fixture, all 8 selected follow-up cases
passed.
- `pnpm -r typecheck`: passed on
`179c86caf1bf0d89914a503d46e24af7e4b8c557`.
- `pnpm build`: passed on the same commit.
- `pnpm test:run`: the general-server group completed with 13,521
passed, 99 skipped, and 18 failed tests. It then stopped, so the
remaining local groups did not run. Five Slack, email, and wake-batching
failures passed on focused reruns after correcting the local
environment. The remaining 13 failures reproduce as `EACCES` on rename
in unchanged skill-cache code on macOS. Two custom-image suite setup
hooks also failed to start embedded PostgreSQL after the machine
exhausted shared-memory slots; all 31 tests in that file passed on rerun
after the local resource issue was resolved. CI covers all test groups.
- CI: 53 checks passed and 2 were skipped on the latest commit,
including the aggregate verification gate. The last server shard passed
on its single rerun after a preview-server startup timeout. The affected
file also passed locally with 28 passed and 3 skipped.
- Greptile: 5/5 on the latest commit. Both review threads are resolved.
- No live deployment or staging task mutation has been performed.
## Risks
- Stopping the sandbox can prevent file copy-back. The result preserves
workspace restore failure evidence; termination does not imply restored
files.
- If provider termination fails, the adapter keeps ownership of its
outstanding command and does not acknowledge Stop.
- The write restriction now applies to ordinary cancelled tasks. Reads
remain allowed. Task and interaction checks add a shared run-row lock to
agent mutations. An exact server-issued receipt permits the task request
that stopped its own run to complete its handoff.
- Existing terminal tasks are not reopened automatically. An operator
must correct a historical late Done before its saved queue can continue.
- No schema migration or UI change.
## Model Used
OpenAI GPT-6 through Codex, with reasoning, repository inspection, code
execution, and test tools. The precise 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
#` 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>
Reject malformed CLI challenge UUIDs before database access while preserving secret and authentication precedence. Document the HTTP responses and pin the supervisor test fixture to the CI-selected Node executable.
Validated by 21 focused tests, root typecheck/build, and full CI. Mac broad-suite baseline limitations are documented in the PR. Greptile 5/5.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve fixed broker rejection reason codes within strict size/time limits while retaining public error codes and status. Unknown bodies remain generic; no raw response or credential material enters the error.
Validated by 33 consumer tests, a synthetic producer HTTP contract fixture, root typecheck/build, and full CI. Greptile 5/5.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Declare provider acquisition budgets so slow Daytona creation does not hit the host’s 30-second fallback. Bound creation and setup to one deadline and preserve scoped cleanup ownership after timeout. Legacy drivers retain their original call shape.
Validated by 238 provider/manifest tests, focused database and heartbeat regressions, root and standalone provider typecheck/build, and full CI. Local broad tests also expose recorded Mac baseline limitations. Greptile 5/5.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Its sidebar provides navigation between organizations.
> - The generic organization switcher slot lets installed plugins own
that navigation.
> - Both Core UI shells still contain the old Cloud portfolio menu.
> - Cloud now uses its private Account plugin for this menu.
> - This pull request removes the duplicate Cloud menu and keeps the
built-in company menu.
> - This reduces Cloud-specific code without changing the plugin host
contract.
## Linked Issues or Issue Description
Refs #13832 and #13854. Related #14060 changes the account popup, not
this organization switcher.
**What existing behavior does this improve?**
Organization navigation in both sidebar shells.
**Current behavior**
Core retains Cloud portfolio fetching, stack rows and stack-entry links
behind the plugin replacement slot.
**Proposed behavior**
The installed switcher plugin owns Cloud navigation. Core lists local
companies when no usable replacement exists. The Members-page Cloud
invitation action keeps its existing portfolio API; it is a live caller,
not an old-image fallback.
## What Changed
- Remove Cloud portfolio queries, stack rendering and Cloud
creation/entry branches from both built-in menus.
- Remove the unused stack-entry URL helper.
- Keep company selection, ordering, invitations, logout and plugin error
handling. Hide local company creation on managed hosts, where the server
forbids it.
- Update switcher tests and the navigation contract.
## Verification
- `pnpm -r typecheck` passed, including Rust checks with the installed
Cargo toolchain on PATH.
- `pnpm exec vitest run --project @paperclipai/ui`: 637 files and 6,727
tests passed.
- Focused switcher, plugin host and Cloud link tests: 26 passed after
the managed-host creation guard.
- `pnpm check:token-gates` passed.
- Full `pnpm test:run` was attempted, then stopped after failures in
unchanged server tests. Targeted reproduction found an ancestor
skills-directory collision for Slack and macOS EACCES errors renaming
the company skills cache. Other local failures appeared in email
connector skill setup and a process-turn test. This is not a local
full-suite pass; clean Linux CI covers the complete suite.
- Full `pnpm build`, UI production build and Storybook build passed. All
[latest-head CI
checks](https://github.com/paperclipai/paperclip/actions/runs/36201814444)
passed, including the full Linux test matrix, browser tests, typecheck,
build and release checks. Greptile is 5/5 with no unresolved comments.
## Risks
- A managed host without a usable switcher plugin now gets the ordinary
company menu. It no longer gets the old Cloud portfolio menu, and local
company creation remains unavailable there.
- The Cloud portfolio endpoint remains required by the Members-page
invitation action. This PR does not remove that live endpoint or change
its authorization.
- No database, authentication, plugin protocol or deployment changes.
## Model Used
OpenAI Codex, GPT-6, with reasoning, repository inspection and code
execution. The exact deployment identifier and context-window size are
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
- [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 a bounded diagnostic for failed workspace and staged-asset restores.
Preserve the original error, retry policy, and archive safety checks. Never
copy raw provider messages, credentials, paths, or asset names into the log.
Nested failures log once; safe fields survive throwing property getters.
Verified 129 focused restore/Claude tests, typecheck/build, and green full
PR CI. Greptile 5/5 with all review threads resolved.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Reject invalid and cross-company execution workspace references with a useful
422 before changing the work product. Hold the validated reference through
the transaction so concurrent deletion cannot turn validation into a 500.
Verified 13 focused tests, full typecheck/build, and green PR CI. Greptile
5/5 with no unresolved comments. The known UI copy-toast flake passed on an
unchanged-commit retry and in a focused local run.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Its control plane decides when a task can continue, wait, stop, or
complete.
> - Legacy continuation could change when an agent changed its wording
without changing task state.
> - Shared attempt counts also let repair and infrastructure retries
affect each other's limits.
> - This pull request uses persisted state and separate, bounded
allowances for these decisions.
> - If automatic repair stops, the task explains what happened and
offers a guarded retry.
> - Paired tests and real-provider evaluations verify that Stop,
approvals, ownership, and spending limits remain authoritative.
## Linked Issues or Issue Description
Related work: Refs #13761, Refs #11126, Refs #13610. These cover
obsolete continuation dispatch and retry storms. Open and closed issues
and PRs were searched for related lifecycle, continuation, and retry
work.
**What happened?**
Legacy continuation depended on English wording and progress heuristics.
Repair, failure retry, and productive continuation could consume shared
counts. When bounded repair stopped, the task showed a technical
recovery message without a clear next action.
**Expected behavior**
Persisted disposition and owned execution paths determine the next
action. Missing disposition prompts bounded agent repair. Explicit work
mode determines planning mode. Narrative changes and raw activity counts
cannot replenish allowances. An exhausted repair shows a readable
notice. An explicit retry checks current controls and preserves the
assigned agent.
**Steps to reproduce**
Run `pnpm test:lifecycle-baseline`. The paired probes keep structured
state constant while varying completion, planning, blocker, and progress
prose. Run the explicit `lifecycle-baseline` and
`continuation-accounting` Product E2E suites for real-provider coverage.
In Storybook, open **Design previews / Recovery notice** to inspect the
production component's normal, pending, acknowledged, unavailable,
failure, and mobile states.
## What Changed
- Hide the image attachment button, icon, and drop/paste hint in answer
composers. Image paste and drop support remains available.
- Merge current master and retain both browser regression sets. Use a
production-stamped service worker in the offline recovery browser
fixture.
- Share one state-based legacy continuation decision across immediate,
delayed, and recovered dispatch. Bind bounded repairs to their source
run and episode.
- Remove title and description wording from work-mode authority. Agents
can still write requested plans in execution mode.
- Persist separate failure-retry and productive-continuation counters.
Disposition repair and resource waits cannot consume or reset those
allowances.
- Validate delayed repair identity, then recheck current gates before
provider dispatch. Fence native startup cancellation.
- Show **Agent needs attention**, a plain-language explanation, **Retry
agent**, and expandable details in both task interfaces. Report request
progress, acknowledgement, and errors inline.
- Store typed recovery notice metadata. Recognize older active notices
only through exact stored action and run IDs. Notice text never grants
retry authority.
- Use the existing recovery-action endpoint for retry. Recheck current
action, status, owner, agent availability, dependencies, active runs,
pending questions and confirmations, approvals, pause controls, and
budget. Duplicate requests do not wake twice.
- Add component, page, route, database, contract, and Storybook
coverage. Keep the scenario inventory and executable evals here.
Historical reports and snapshots live in the [commit-pinned
paperclip-evals
archive](https://github.com/paperclipai/paperclip-evals/blob/ce3e5afcd4a1184650f586a2b5b8be5874c66c8b/experiments/2026-09-lifecycle-authority/README.md).
- Preserve unsaved project fields while the same project URL changes to
its canonical alias. Do not reuse data across projects or companies.
This separate fix addresses the repeated repository-editor browser
failure without changing the browser test.
- Keep the development service worker from intercepting Vite module
reloads. Update the connection-intent browser fixture to record progress
and completion through the agent API.
## Verification
Merge preparation on September 25, commit
`c1e8e4b7ddd9fbc4913ed55ce21b8e12906c2f97`:
- Merged master `bd2030932` and resolved the browser test-list conflict
by keeping both sets of regressions.
- Deterministic lifecycle baseline: 1,090/1,090 assertions passed; no
failures, skips, or missing selected evidence. Unit 423, runner 184,
database integration 397, grading 86.
- Browser support: 17/17 passed. The offline recovery test first failed
with an unstamped development worker, then passed with the production
stamp. Its assertions are unchanged.
- Focused interaction UI and offline fallback tests: 19/19 passed.
Verified the custom-answer composer in Storybook: no attachment controls
or hint; entering an answer enables Next.
- Recursive typecheck, production build, token gates, and diff checks
passed. The worktree is clean. No new real-provider campaign was run.
- Current CI and review: [Current PR CI
passed](https://github.com/paperclipai/paperclip/actions/runs/36166011243):
55 successful checks and two optional Storybook skips. Greptile scored
this exact commit 5/5. Hiding the question attachment controls is an
intentional UI change; paste/drop remains available.
Earlier recovery UI verification, commit
`21be0fec0e90e86b6d662b8ee4831847cd041cdb`:
- Recursive typecheck, production build, token gates, and diff checks
passed.
- Focused UI coverage: 338 tests passed across six suites (336 before
the interaction guard, with the two affected suites rerun at 149 passed
after it). Covers both task interfaces, the real page mutation,
pending/error acknowledgement, stale state, and unavailable controls.
- Recovery database integration: 352 tests passed before the interaction
guard. The complete recovery-action and mutation-route suites passed 181
tests after it. The two new pending question/confirmation regressions
failed before the fix and passed afterward, including
resolved-interaction controls. Shared validator suite: 31 passed. E2E
catalog suites: 34 passed.
- Browser inspection passed for light/dark themes, mobile layout,
expandable details, pending retry, acknowledgement, failure, and
disabled retry. Storybook renders the production component; its request
is simulated.
- The broad local run hit two chat callback-order wait failures and was
stopped after all CI unit/database/runner shards passed. Both local
failures passed when rerun without the competing full-suite process.
- CI exposed a repeated project-repository draft-loss race during
canonical redirects. A new unit regression failed before the fix; all
nine project-page tests now pass, including controls for other projects
and companies. Both unchanged repository browser tests passed against a
fresh local server. UI typecheck, production UI build, and token gates
passed after this fix.
- [Earlier PR CI
passed](https://github.com/paperclipai/paperclip/actions/runs/36072486798)
on `21be0fec0e90e86b6d662b8ee4831847cd041cdb`: 55 successful checks, two
optional Storybook skips, and no failed or pending checks. The
repository browser shard passed with the production fix. Greptile is 5/5
on this exact commit with no unresolved review threads. The PR is
mergeable.
Historical, source-qualified lifecycle evidence:
- Lifecycle baseline: 1,074 assertions. Native session coverage: 447
tests. Product E2E support: 515 tests. Browser support: 11 tests. Full
earlier verification is retained in the archive.
- [Real-provider campaign: 8/8 passed, zero
retries](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35881382080-1/index.html),
source `e88d210417280140b44a36449027290adcb1aeaa`. Evidence and cleanup
checks passed. This includes deliberately exhausted repair cases that
correctly remain blocked; it does not mean every task finished Done.
This campaign predates the recovery UI change.
- Archive migration verified all 16 original JSON files byte-for-byte
and all 24 checksum entries. App tests do not need private archive
access. [Archive PR
#27](https://github.com/paperclipai/paperclip-evals/pull/27) is merged.
## Risks
- Agents that omit durable disposition receive at most two repair
attempts by default. Prose-only completion exposes missing state rather
than silently changing scheduling.
- A retry is an explicit board action. The server rechecks current
controls. A successful response confirms the task returned to To do; it
does not claim that the provider has already started.
- Existing notice metadata remains valid. Only older active notices with
matching structured evidence receive the new UI. Historical notices
without that evidence keep their existing rendering. No schema migration
is required.
- Old run records require conservative retry accounting. Tests cover old
counters, alternating retry lanes, restarts, and exhausted repairs.
- Historical snapshots require private `paperclip-evals` access. The app
index retains public campaign links. Live campaigns qualify specific
sources and scenarios; no new real-provider campaign has run for the
recovery UI commit.
> This fixes existing lifecycle and recovery behavior and does not
duplicate planned core work.
## Model Used
OpenAI GPT-6 through Codex assisted implementation, reasoning, code
execution, and review. The exact serving model ID and context window are
not exposed in this task. Historical real-provider evaluations used
Codex model `gpt-5.6-sol`, separately from the implementation assistant.
## 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 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>
Preserve agent output and earlier execution errors when workspace restore fails. Report the restore phase and confirmed saved-plan links. Require verified repair before retrying unsafe archives, while preserving approval states and the retry budget.
Verified with full CI, 506 focused regression tests, and Greptile 5/5 with all review threads resolved.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip helps people manage AI agents for work.
> - Connections let those agents use external services with explicit
access rules.
> - Zapier, Arcade, Composio Connect, and Executor already have setup
and runtime support.
> - Their experimental switch still blocks discovery and setup by
default.
> - This pull request removes those gates and the Settings toggle.
> - Users can connect these providers without enabling an experiment.
## Linked Issues or Issue Description
Refs #13755. Refs #13941.
**What existing behavior does this improve?**
Apps browsing, inline setup, and agent connection search for the four
MCP aggregators.
**Current behavior**
An instance must enable the MCP aggregators experiment before users or
agents can start setup.
**Proposed behavior**
All four providers are available by default on local and managed
instances. Old stored and managed values still parse but cannot disable
them.
## What Changed
- Remove the aggregator gates from Apps, inline setup, server setup, and
agent search.
- Remove the Settings toggle and its UI hook.
- Retain the old setting key only for upgrade compatibility. Normalize
it to true and ignore managed overrides, as Apps already does.
- Replace opt-in fixtures with default-on coverage. Test old false
values, all four setup flows, provider choice, and the removed toggle.
- Update current connector guidance and remove the opt-in from the
runner acceptance fixture.
## Verification
- 306 focused tests passed across eight files: shared remote MCP
contracts; server remote MCP lifecycle, aggregator fallback, settings
normalization, and managed overlay; UI Apps browsing, setup, and
experimental settings.
- Server and UI TypeScript checks passed.
- UI token gates and `git diff --check` passed.
- The full local suite was not run, per the maintainer's instruction.
All 54 CI checks passed; two checks were skipped. One unrelated
workspace-preview readiness timeout passed on one failed-shard retry.
- The setup fixtures use simulated MCP responses. This change does not
claim new live provider acceptance.
## Risks
- Existing instances now show all four providers, even if the old flag
was false. This is intentional.
- External provider choice, credentials, company isolation, agent
grants, and tool policies still apply. Showing a connector does not
authorize an external account.
- No data migration is required. The compatibility key keeps old managed
configuration documents valid.
- Historical Zapier live acceptance remains incomplete in the existing
evidence report. The maintainer explicitly requested the default-on
rollout for all four existing providers; the report records that scoped
exception.
## Model Used
OpenAI GPT-6 (`gpt-6-astra`) through Codex, with reasoning, repository
tools, and test execution. The context window size is 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.
> - Connections give agents governed access to external services.
> - Native connections should remain the first choice for a supported
app.
> - Other apps may be available through an external MCP provider.
> - The user must know which external provider handles the connection
and choose it before setup.
> - This pull request adds ranked alternatives and server-authored
instructions to connection search.
> - Agents can follow the returned instructions while Paperclip
validates saved choices and access.
## Linked Issues or Issue Description
Related: #13879, which fixed inline MCP provider setup. This PR adds
discovery and provider selection on top of that work.
**Subsystem affected**
Cross-cutting: shared connection contracts, server search and intent
services, native runtime, CLI, inline setup UI, and evals.
**Problem or motivation**
An agent cannot offer a clear external-provider choice when Paperclip
has no native connection for an app. Adding provider-specific branches
to the core prompt would make those instructions harder to maintain.
**Proposed solution**
Prefer a native connection. Otherwise return verified alternatives in
Composio, Arcade, Executor, Zapier order. Include an external-service
disclosure, a question with None, and the next instruction in the search
result. Validate the saved human choice before creating a selected
fallback setup card. Reuse existing provider accounts and verify
underlying app access separately.
**Alternatives considered**
Do not silently choose a provider. Do not claim that broad execution
tools prove support for every app. Reuse existing questions and
connection intents rather than add another connection model.
**Roadmap alignment**
Extends the existing MCP Tool Gateway & Apps and Agent evals & feedback
capabilities. The MCP aggregators experiment remains the gate. No
duplicate provider-routing PR was found in the public search.
## What Changed
- Add a dated support index and authorized cached-tool evidence for
external routes.
- Return provider questions and next-step instructions from
`connections_search`.
- Preserve pending choices and declines across continuation. Validate
company, task, agent, human, app, and current route eligibility.
- Carry the selected app into new setup and account reuse, validate
explicit provider requests against persisted human messages, and
distinguish provider readiness from app authorization.
- Sync native, MCP, REST, and CLI contracts. Keep core agent
instructions provider-neutral.
- Add production-component Storybooks, focused database tests, and three
real-agent browser eval cases.
- Record the plan, observed failures, fixes, passing evidence, and
acceptance limits.
## Verification
- Latest head `586f0e6cd`: 54 checks passed, 2 skipped; Greptile 5/5 and
all review threads resolved.
- After rebasing on master `18dac1e1e`: 64 focused shared, validator,
route-contract, and database tests passed; server typecheck passed.
- Embedded-browser test drive on the rebased head: native Jira card,
HubSpot external-provider question, Arcade account reuse, one actual MCP
read against a local synthetic fixture, reload persistence, and None
preventing further calls. A real OpenAI-backed agent performed discovery
and continuation.
- UX observation: the agent initially combined mutually exclusive
request fields; the server rejected it and the agent recovered without
changing access. This extra retry remains visible in the transcript.
- After rebase: 23 focused eval grader/catalog tests, affected
TypeScript checks, token gates, production UI build, and Storybook build
passed. Full local tests are intentionally excluded at the maintainer's
request.
- Before rebase: four browser/real-agent attempts passed: native Jira,
None, and reuse of the second provider on two Codex profiles.
- Browser evals used an isolated deterministic MCP fixture through the
real Paperclip gateway. They do not prove production compatibility with
all four providers.
- Review `Apps / Connections / Provider choice` in Storybook. Choose
Arcade, continue through Access, and verify the app name,
external-service disclosure, and URL configuration.
- The detailed verification report is
`doc/connections/2026-09-23-aggregator-routing-verification.md`.
## Risks
- The public support index is finite and can age. Account capability and
app authorization still require verification after selection.
- Existing installed-tool permissions remain in effect. Provider choice
is not a new execution permission boundary. An early Mini attempt
skipped search; clearer provider-neutral instructions made the targeted
rerun pass. This is not a measured reliability rate.
- Explicit requests skip provider confirmation only when a clear
persisted human message or saved provider choice supports them. Other
phrasing falls back to confirmation; the agent query alone is not
consent. These routes do not add tool permissions.
- No database migration or legacy Composio broker is added.
Real-provider acceptance remains separate from fixture proof.
## Model Used
OpenAI GPT-6 through Codex, with reasoning, repository tools, code
execution, and browser tools. The exact deployment variant and
context-window size are not exposed in this session. Product evals
separately used the repository's primary Codex and Codex Mini profiles;
those agents supplied test behavior, not independent provider
compatibility proof.
## 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>
