## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Conversations must use the same tasks, controls, and execution
history.
> - Users need an ongoing chat with an agent without managing task
properties.
> - Agents should clarify and plan work, then hand execution to assigned
project tasks.
> - This pull request combines the reviewed Agent Chat stack for one
squash merge.
> - The benefit is persistent conversation with normal task governance
and shared UI.
## Linked Issues or Issue Description
**Subsystem affected**
Task lifecycle, agent runtime tools, shared task UI, and browser/paid
runner tests.
**Problem or motivation**
Users need one persistent conversation with each agent. A separate chat
store or renderer would duplicate task behavior and bypass existing
controls.
**Proposed solution**
Use a task-backed chat per company, user, and agent. Reuse the task
composer and transcript. Clarify and plan in chat, then create assigned
project tasks with the relevant plan. Keep Agent Chat behind its own
disabled-by-default experimental setting.
**Roadmap alignment**
This implements the task-backed direction in [CEO
Chat](https://github.com/paperclipai/paperclip/blob/master/ROADMAP.md#-ceo-chat).
Related proposals: #2504 and #9693. Related request: #7981. The
maintainer requested one squash merge of the complete stack.
Consolidates the reviewed runtime
[#13281](https://github.com/paperclipai/paperclip/pull/13281), backend
[#13282](https://github.com/paperclipai/paperclip/pull/13282), and UI
[#13283](https://github.com/paperclipai/paperclip/pull/13283) layers
with this PR's E2E coverage. All four layers passed CI and received
Greptile 5/5 before consolidation. This PR targets master and includes
the complete feature.
## What Changed
- Add personal canonical chat tasks with ordinary company visibility,
immutable identity, idempotent first sends, and an idle waiting state.
- Process `/new` in queue order. Preserve history, release a chat pause,
and fence old provider context and delayed writes.
- Keep chat lifecycle rules across recovery, finalization, assignment,
task lists, and rollups.
- Support research and plan revision in chat. Hand plans to ordinary
assigned project tasks before execution starts. Reject new chat
subtasks.
- Add repository-aware project creation and discovery tools, including
multiple repository IDs and GitHub URLs, authorization, idempotency, and
durable project-created cards.
- Reuse task UI components for chat, with starred/recent agent
navigation and a separate `enableAgentChat` experimental flag.
- Add deterministic browser tests and 24 paid chat cells across four
Codex/Claude profiles, with validated reports and screenshots.
- Integrate current master recovery, controller lease, queued-message,
and task UI changes. Gate chat interruption and deferred promotion on
ownership/feature policy. Guarantee lease renewal and active controls
are stopped even if teardown fails.
- Preserve master's migration 0273 and generate chat migration 0274 with
idempotent replay for development databases.
## Verification
- Prior exact heads of all four PRs passed Linux CI, including build,
typecheck, general/serialized tests, and browser E2E. Each had Greptile
5/5 and no unresolved findings.
- Integrated local verification passed: full repository typecheck and
production build, Storybook build, token gates, 340 focused UI tests,
all 20 deterministic chat browser tests, two migration replay tests, 88
focused chat/queue/native/controller tests, and provider/session
regressions including real lease expiry. These include the three
lifecycle regressions for the final admission/teardown fixes; server
typecheck also passes. Current head
`1268eda16cc2af892055917e7292f068820be135` has Greptile 5/5 with no
unresolved findings and passing security scans. All final-head CI gates
passed: build, full Runner verification, typecheck/release registry,
canary, all general/serialized test shards, and all browser E2E shards
([CI
run](https://github.com/paperclipai/paperclip/actions/runs/34696739927)).
Local PostgreSQL startup contention required serialized retries; skipped
fixtures do not count as passing coverage.
- The earlier paid campaign passed all 24 chat cells and retained 32
screenshots:
[report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-34648511170-1/index.html?report=agent-chat#suite-agent-chat).
It tested `abacbdfd2f660709ec37312cdb758284c8399d04`; it is prior
evidence, not a paid run of this integrated head.
- Manual check: enable Agent Chat in Experimental settings, open an
agent, clarify and revise a plan, then hand off to an assigned project
task. Stop a reply, send `/new`, and verify fresh context with retained
history. Disable the setting and verify agent shortcuts/new chat turns
are blocked.
## Risks
- Queue/session integration can affect retries and delayed writes. Tests
cover ownership, cancellation, reset boundaries, idle recovery, and
ordinary task behavior.
- Migration 0274 adds conversation fields and constraints. Replay is
idempotent and preserves existing development chat history.
- This combines the previously reviewed stack at the maintainer's
request. Agent Chat remains off by default and is separate from
Conference Room.
## Model Used
OpenAI Codex, GPT-6 Astra (`gpt-6-astra`), with reasoning, code
execution, browser tools, and parallel review. The exact context-window
size is not exposed in this session. Codex and Claude also ran as test
subjects in the linked paid campaign.
## 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>
Bring governed connection reviews into task history and composer approvals. Share resolution with Connections, add scoped remembered permissions, and resume agents through durable outcome receipts.
Keep cards compact, collapse raw results, isolate untrusted provider output, bound continuation payloads, and reconcile missed live events. Add Storybook coverage, browser journeys, and service regression tests.
Verification: all PR CI gates passed, Greptile 5/5, security scans passed, five connection-review browser journeys passed, and real native Codex approval/continuation was verified against the local MCP fixture.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Task interactions let an operator approve completion or ask an agent
to continue.
> - The server stores the continue choice as a rejected completion
request so it can resume the same task.
> - The task feed ignored the configured action label and showed the
generic text `Declined request`.
> - The generic text made a successful three-turn continuation look like
a failed request.
> - This pull request keeps the server state and shows the action that
the operator selected.
> - The benefit is an accurate task feed for legacy Codex and Runner
Codex.
## Linked Issues or Issue Description
**What happened?**
A rejected confirmation always appeared as `Declined request`. The feed
did not use a custom rejection action such as `Continue work`.
**Expected behavior**
The resolved receipt and success toast must show the selected custom
action. Confirmations without a custom action must keep the current
fallback text.
**Steps to reproduce**
1. Create a completion confirmation with `rejectLabel` set to `Continue
work`.
2. Select `Continue work` and enter a continuation note.
3. Open the completed task feed.
4. Observe that the old UI says `Declined request` instead of the
selected action.
**Paperclip version or commit**
`539c9212f4b98e37643f5a8e3b603f1b5845b5d7`
**Deployment mode**
GitHub Actions Runner E2E with warm Daytona sandboxes.
## What Changed
- Show `Selected “Continue work”` when a rejected confirmation has that
custom action label.
- Use the same action-aware text in the success toast.
- Keep `Declined request` as the fallback for confirmations without a
custom rejection label.
- Make the legacy warm-turn prompt ask if the task is ready to complete.
- Require both warm Daytona matrix cells to show two continuation
receipts and no generic decline receipt.
## Verification
- `pnpm exec vitest run ui/src/pages/IssueDetail.test.tsx
ui/src/lib/issue-thread-interactions.test.ts
ui/src/components/task-chat/TaskChatInteractionCard.test.tsx`
- `pnpm test:e2e:runner:unit`
- `pnpm test:e2e:runner:typecheck`
- `pnpm --filter @paperclipai/ui typecheck`
- `pnpm --filter @paperclipai/ui build`
- `pnpm check:token-gates`
- Paid `daytona-warm-continuity` campaign: both three-turn cells passed
on attempt 1 ([workflow
run](https://github.com/paperclipai/paperclip/actions/runs/34052047946));
the downloaded evidence aggregates locally as 2/2. The trusted report
job did not publish because default branch `pnpm-lock.yaml` was
transiently behind its manifest.
- `pnpm typecheck` reached an unrelated `plugin-workspace-diff`
dependency type error after the current master manifest and lockfile
resolved different versions. The focused UI and runner checks pass.
## Risks
- Low risk. The database state and continuation behavior do not change.
- A custom rejection label now appears in resolved receipts and success
toasts.
- The paid warm Daytona suite has a stricter browser assertion.
## Model Used
- OpenAI Codex, GPT-5, with reasoning, tool use, and code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used with version and capability
details
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked existing issues or described the issue in
this PR with the bug template fields
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal task
identifier
- [x] I have run focused tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated the relevant E2E fixture and assertions
- [x] I have considered and documented the risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Daytona preserves a stopped sandbox filesystem, but deleting or
replacing a sandbox removes its only remote copy.
> - Warm reuse therefore improves latency but cannot be Paperclip's
durability boundary.
> - The host execution workspace must remain authoritative after every
successful turn, while same-run recovery must avoid overwriting
unexported remote work.
> - Result proposal, workspace export/merge, and terminal completion
need a durable, replayable ordering so a crash never starts a duplicate
provider turn.
> - A paid browser acceptance suite must exercise both legacy Codex and
Runner Codex for three real turns on one continuously warm Daytona
sandbox.
## Linked Issues or Issue Description
Refs #12901.
Runner Codex did not previously export successful Daytona workspace
changes back to the authoritative host workspace. That made warm reuse
depend on Daytona's remote filesystem and left deleted/replacement
sandboxes without a reliable reconstruction path. The existing paid
fixture also lacked a focused three-turn continuity case for both Codex
adapters.
## What Changed
- Persist versioned, atomic native workspace-sync descriptors and
durable seeds in `PAPERCLIP_HOME`, without credentials or a database
migration.
- Classify fresh, warm, replacement, and same-run-recovery workspace
preparation explicitly; ambiguous lease/root/digest evidence fails
closed.
- Finalize native workspace export/merge after semantic result proposal
and before run completion, with idempotent replay that never submits a
second provider turn.
- Surface legacy Codex workspace restoration failures instead of masking
them, while preserving an earlier provider error when both fail.
- Keep healthy reusable Daytona leases warm for legacy and native
adapters, stamp finalized workspace generations, and retain existing
cleanup behavior for per-turn or unhealthy leases.
- Preserve Runner Codex's provider process/session across warm turns,
including bounded post-terminal tail draining and exact authority
rotation.
- Add the exact paid `daytona-warm-continuity` matrix:
- `legacy-codex × daytona × warm-three-turn`
- `runner-codex × daytona × warm-three-turn`
- Drive all three turns through the browser, verify ordered file
continuity and stable lease/workspace/runtime identities, capture
per-turn timings, and delete the sandbox immediately after assertions.
- Document `pnpm test:e2e:runner -- --suite daytona-warm-continuity`; no
package script was added.
## Verification
- `pnpm typecheck` — passed, including migration safety (no migration
added)
- Focused server/runner Vitest coverage — 144 passed
- `pnpm test:e2e:runner:unit` — 114 passed
- `pnpm test:e2e:runner:typecheck` — passed
- `pnpm --filter @paperclipai/paperclip-runner test:codex` — 66 passed,
1 helper ignored
- `native-session-executor.test.ts` — 139 passed, including safe
fail-closed cleanup after remote runner identity capture failure
- Paid local browser acceptance, exact post-rebase Linux/amd64 runner
binary:
- Runner Codex — passed in 1.7m; 3 runs; lease outcomes `created,
resumed, resumed`; 10/10 matchers; cleanup passed
- Legacy Codex — passed in 2.7m; 3 runs; lease outcomes `created,
resumed, resumed`; 10/10 matchers; cleanup passed
- [Protected paid GitHub Actions
campaign](https://github.com/paperclipai/paperclip/actions/runs/34026735033)
against `7da42a91b95fa7fb2df126668ef7e37afb3b2b9d` — passed 2/2:
- Runner Codex — 3 runs; lease outcomes `created, resumed, resumed`;
evidence and cleanup passed
- Legacy Codex — 3 runs; lease outcomes `created, resumed, resumed`;
evidence and cleanup passed
- Merge/enforcement, S3 history, and Pages publication jobs passed
- Paid result artifacts were scanned for both provider credentials;
neither secret was present.
- Current PR checks — 31 passed, 1 expected Storybook skip; Greptile
5/5; Superagent security scan passed
- `git diff --check origin/master...HEAD` — passed
- Confirmed no `package.json`, lockfile, migration, or SQL changes.
## Risks
- Workspace synchronization now sits on the terminal-success path, so a
remote export failure deliberately prevents false success. Retryable
state retains its lease/seed; loss of the only unexported remote copy
fails closed.
- Warm provider reuse has strict identity and quiescence checks.
Mismatched or ambiguous evidence blocks reuse rather than risking
concurrent provider work.
- The paid suite incurs Daytona and Codex cost only in the existing
protected scheduled/manual workflow and explicitly destroys its sandbox
after each cell.
## Model Used
OpenAI Codex with GPT-5 agentic reasoning, repository inspection, real
browser E2E execution, Rust/TypeScript test execution, and GitHub
Actions diagnostics.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked an existing issue or described the issue
in-PR
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name contains no internal ticket id
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have documented the dedicated suite invocation without adding a
package script
- [x] I have considered and documented risks above
- [x] All Paperclip CI gates are green on the current revision
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
on the current revision
- [x] I will address all reviewer comments before requesting merge
## Thinking Path
> - Paperclip manages AI agent work and the execution state for each
task.
> - Remote agents run in sandbox environments such as Daytona.
> - Daytona keeps files while a sandbox is stopped, but deletion removes
those files.
> - Runner Codex did not copy successful remote workspace changes back
to the host workspace.
> - A warm sandbox could therefore hide data loss until Daytona replaced
or deleted the sandbox.
> - This pull request makes the host workspace durable after every
successful turn and keeps verified reusable sandboxes warm.
> - The benefit is reliable multi-turn work across warm reuse, restart,
stop, and sandbox replacement.
## Linked Issues or Issue Description
**What happened?**
A successful native Codex turn in Daytona could leave workspace changes
only in the remote sandbox. A later warm turn appeared to work because
it reused that filesystem. A replacement sandbox could start from stale
host data and lose the successful changes.
**Expected behavior**
Paperclip must merge each successful remote turn into the authoritative
host workspace before it completes the run. A verified warm lease may
reuse its remote files. A replacement lease must reconstruct the exact
durable workspace seed.
**Steps to reproduce**
1. Run Codex in a reusable Daytona environment.
2. Write a file during one successful turn.
3. Replace the Daytona sandbox before the next turn.
4. Observe that the next turn can start without the prior file on the
unpatched code.
Related remote workspace foundation: #10070.
## What Changed
- Added explicit `host_current`, `durable_seed`, and `adopt_remote`
workspace preparation modes.
- Added atomic, versioned native workspace descriptors and seed archives
under `PAPERCLIP_HOME`.
- Added real native sandbox export and three-way host merge before
terminal result completion.
- Added workspace-only recovery after a proposed result. Recovery does
not submit another provider turn or consume the provider retry budget.
- Added fail-closed handling when a sandbox with unexported changes is
gone.
- Kept healthy reusable Daytona sandboxes started for legacy Codex and
Runner Codex.
- Kept the Runner Codex process and provider session across verified
warm turns.
- Added the paid `daytona-warm-continuity` browser suite. It contains
exactly the legacy Codex and Runner Codex cells. Each cell performs
three measured turns.
- Documented `pnpm test:e2e:runner -- --suite daytona-warm-continuity`.
No package script was added.
- Added no database migration. The metadata format is backward
compatible and idempotent.
## Verification
- `pnpm typecheck`
- `pnpm test:e2e:runner:unit` — 114 passed
- Native workspace, finalizer, session, and environment tests — 232
passed
- Daytona provider tests — 150 passed
- Workspace staging and merge tests — 98 passed
- Runner transport tests — 63 passed
- Legacy Codex restore tests — 5 passed
- Rust format and compile checks pass through root typecheck
- The paid Daytona suite was not run locally because the required
Daytona, OpenAI, and immutable image credentials are not present.
## Risks
- The main risk is an incorrect workspace identity or merge after a
crash. Durable descriptors bind the run, workspace, lease, provider
lease, local root, remote root, and baseline digest. Ambiguous evidence
fails closed.
- The host merge may conflict with concurrent host edits. The existing
three-way merge and exclusion rules handle this case and surface
failures.
- A deleted sandbox cannot recover unexported bytes. Paperclip now
blocks with `workspace_sync_out_unrecoverable` instead of reporting
success or rerunning the provider.
- There is no database migration. Descriptor writes and recovery are
atomic and idempotent.
## Model Used
OpenAI Codex with GPT-5. The run used agentic reasoning, repository
inspection, code execution, test execution, Git, and GitHub CLI tools.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip uses runner end-to-end reports to compare agent profiles
and execution environments
> - The report dashboard shows each reviewed final-state screenshot as a
thumbnail and gallery item
> - The public history publisher removed all per-attempt images before
it regenerated the dashboard
> - Therefore the public dashboard had the new layout but could not show
the screenshots from the run
> - The publisher needs a narrow rule that keeps only screenshots from
the exact live fixture issue route
> - This pull request keeps those trusted PNG files in every future
public S3 and GitHub Pages report
> - The benefit is that each future report can show its screenshot
gallery without exposing logs, traces, videos, archives, arbitrary
images, or generated report trees
## Linked Issues or Issue Description
**What happened?**
The runner E2E job captured final-state screenshots in its private
artifact. The public S3 and GitHub Pages publication step removed those
screenshots before it regenerated the dashboard. As a result, the public
report showed the new dashboard controls but no screenshot thumbnails or
gallery items.
**Expected behavior**
Each future public runner E2E report must include reviewed PNG
screenshots from the live fixture issue. Other captures and active or
unsafe evidence must stay private.
**Steps to reproduce**
1. Run the runner full-stack E2E workflow on `master` before this
change.
2. Open the private `runner-e2e-report-*` artifact and confirm that it
contains per-attempt PNG screenshots.
3. Open the public campaign URL and confirm that the dashboard has no
screenshot gallery items.
**Paperclip version or commit**
The issue was reproduced on commit `64d8929`, after the report design
change in PR #12889.
**Deployment mode**
GitHub Actions with the public S3 and GitHub Pages report publishers.
Related design work: Refs #12889.
## What Changed
- Mark screenshots from the exact server-created live fixture issue
route with `public-runner-fixture`.
- Keep marked PNG files in both the S3 history bundle and the GitHub
Pages bundle.
- Keep captures from other issue routes, sensitive routes, and external
origins private.
- Bind public files to the normalized execution ID, attempt, and safe
PNG base name.
- Validate every retained image with the existing PNG signature and 12
MiB size checks.
- Skip missing-artifact sentinel results with attempt `0` when they have
no public screenshots.
- Continue to remove unmarked images, videos, traces, archives,
generated HTML reports, and other private evidence.
- Update publisher tests, workflow checks, report copy, and the
public-evidence security documentation.
## Verification
- `pnpm exec vitest run --config tests/runner-e2e/vitest.config.ts
tests/runner-e2e/history.test.ts tests/runner-e2e/report.test.ts`
- `pnpm exec vitest run --config tests/runner-e2e/vitest.config.ts
tests/runner-e2e/workflow-security.test.ts -t "uses environment-scoped
OIDC"`
- `pnpm test:e2e:runner:typecheck`
- `PAPERCLIP_PLAYWRIGHT_CHANNEL=chrome pnpm exec playwright test
--config tests/e2e/playwright.config.ts
tests/e2e/runner-e2e-dashboard.spec.ts`
- `pnpm -r typecheck`
- `pnpm build`
- Regenerated the dashboard from retained evidence for Actions run
`33968240659` without a paid matrix rerun. The public-stage proof
contained 121 screenshot gallery items and thumbnail frames, with zero
generated HTML report files. The trusted-fixture marker and route gate
have separate focused tests.
- All pull request CI checks pass on commit `ccd2b49e1`.
## Risks
- This change intentionally makes marked fixture screenshots public at
the campaign URL. A screenshot can show data that a raw-byte secret scan
cannot detect.
- The capture helper marks a screenshot only on the exact loopback issue
route for the fixture that the harness created. A different issue,
sensitive page, or external origin stays private.
- The publisher also requires the marker, a safe normalized path, a
valid PNG signature, and the size limit.
- The change does not publish videos, logs, traces, archives, arbitrary
images, or generated browser report trees.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex, model `gpt-5.6-sol`, with high reasoning, repository
tool use, shell execution, browser inspection, and GitHub CLI access.
The working context was the Codex desktop task context.
## 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 manages AI agents and their work.
> - The runner executes agent turns on local and remote providers.
> - A remote per-turn session must save its state before Paperclip
releases its sandbox.
> - The session runtime returned after 100 milliseconds while the remote
checkpoint still ran.
> - The next turn also checked the local state path instead of the
verified remote backup.
> - This pull request waits for the bounded remote close and accepts
only a verified suspended backup.
> - The benefit is reliable multi-turn execution without weaker identity
checks.
## Linked Issues or Issue Description
**What happened?**
A successful remote agent turn released its sandbox before the runner
saved the verified continuation backup. The next turn failed with
`runner_state_identity_mismatch`.
**Expected behavior**
Paperclip must finish the bounded remote checkpoint before it releases
the sandbox. A later turn must validate and restore the digest-matched
suspended backup.
**Steps to reproduce**
1. Run a native ACPX Claude Plan test in a non-reusable Daytona sandbox.
2. Reject the first plan to start a second turn.
3. Observe that the second turn fails before provider execution.
**Paperclip version or commit**
The failure reproduced at `13775a90b078ff64872f50961ea1b83d575e7bc6`.
**Deployment mode**
GitHub Actions with a Daytona sandbox.
## What Changed
- Wait for the internally bounded remote runner close and checkpoint
before the host returns.
- Preserve the existing short cleanup bound for other providers.
- Validate remote continuation lifecycle from a complete digest-verified
backup when local runner state is absent.
- Keep corrupt, non-suspended, mismatched, and unverified state
fail-closed.
- Make native Plan completion and accepted-Plan wake prompts
deterministic.
## Verification
- A prior 45-cell local campaign passed 44 cells. The only failure was
the OpenCode Plan prompt variance fixed here.
- A focused OpenCode local Plan rerun passed.
- ACPX Claude Daytona message and question cells passed.
- Focused regressions cover delayed checkpoint close and verified remote
backup lifecycle.
- GitHub Build and the focused ACPX Claude Daytona Plan cell will
validate this exact head.
## Risks
Remote runnerd sessions now wait for their internally bounded
close/checkpoint path before returning; generic provider cleanup retains
the existing 100 millisecond bound. Durable run success still cannot be
reversed. The environment release guard still blocks sandbox destruction
when no verified backup stamp exists.
## Model Used
OpenAI Codex, GPT-5.6, extended reasoning, with code execution and
GitHub Actions inspection.
## 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 task
id
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] 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 findings
- [ ] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paid runner E2E tests verify the complete runner, control-plane, and
UI path.
> - A server restart could load a fresh task page while Playwright still
waited on an unsettled Vite navigation lifecycle.
> - The current server also ignored the isolated Vite cache path and
skipped Vite's per-request HTML transform from the known-green runner
snapshot.
> - A one-cell paid run then exposed that download-artifact v8 removes
the artifact-name directory for one pattern match.
> - This pull request restores the Vite contract, proves a fresh
document after restart, and accepts only the exact singleton artifact
layout.
> - The benefit is reliable local runner qualification without weaker
UI, source, or artifact checks.
## Linked Issues or Issue Description
Refs #12769
Refs #12828
Refs #12829
Refs #12833
**What happened?**
The structured-question restart test could time out after the
replacement server returned the task route and rendered the durable
pending interaction. A focused one-cell rerun passed the paid test but
failed aggregation because download-artifact v8 flattened its single
artifact.
**Expected behavior**
The test must prove that a new document loaded after the server restart
and that the same pending interaction survived. The aggregate must
accept the exact documented singleton download layout while it continues
to reject ambiguous or foreign artifacts.
**Steps to reproduce**
1. Run the local ACPX-Codex structured-question restart-resume cell.
2. Restart the isolated server while the question waits for an answer.
3. Observe that the route and task UI can reload before Playwright
settles the navigation promise.
4. Run a paid campaign with one selected cell.
5. Observe download-artifact v8 extract the sole campaign directory
directly into the requested path.
**Paperclip version or commit**
The local campaign reproduced the navigation failure at
`3586956a1b794b3cb4a9c5f57ffb7355e2b0c46d`. The one-cell aggregate
reproduced the singleton layout at
`f487660c0a06ba06ca140b57386f21ed39f13120`. This fix is
`de4ccceff453a4b39436bf9a2eb8f03924151af7`.
**Deployment mode**
Local development and paid GitHub Actions.
**Installation method**
Built from source.
**Agent adapter(s) involved**
ACPX-Codex. The Vite and aggregate fixes are provider-neutral.
## What Changed
- Prove a new post-restart browser document with an in-memory sentinel.
- Tolerate only Playwright's navigation timeout before the exact UI and
API checks run.
- Honor `PAPERCLIP_VITE_CACHE_DIR` in the embedded Vite server.
- Limit dependency optimization to the real UI entry.
- Run `vite.transformIndexHtml` for each request while caching only the
branded source template.
- Accept download-artifact v8's flattened layout only for one expected
cell with one unique recognized campaign.
- Keep source SHA, source ref, workflow URL, execution ID, attempt, and
unexpected-entry validation.
- Add focused positive and negative regressions for Vite rendering and
singleton artifact selection.
## Verification
- Exact 45-cell local campaign
https://github.com/paperclipai/paperclip/actions/runs/33888939013 passed
44/45. Its only failure was the post-restart navigation false negative
fixed here.
- Exact focused rerun
https://github.com/paperclipai/paperclip/actions/runs/33891207957 passed
the ACPX-Codex restart cell first attempt with the same session, two
durable runs, the terminal marker once, and cleanup complete.
- The focused Vite renderer suite passed 2/2 tests.
- The focused rerun-artifact selector suite passed 12/12 tests.
- Prettier and `git diff --check` passed.
- An exact-head 45-cell confirmation is pending.
## Risks
Low to medium risk. The Vite change restores known-green per-request
transforms and isolated cache behavior. It can affect all development UI
loads. The paid matrix and ordinary CI will verify that behavior. The
singleton selector remains fail-closed for ambiguous layouts and
validates every result source.
## Model Used
OpenAI Codex, `gpt-5.6-sol`, extended reasoning, tool use, code
execution, and parallel focused agents.
## 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
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paid runner E2E tests verify the full control-plane path for
supported providers.
> - Native OpenCode could write the reserved terminal marker through
progress and final output.
> - The restart fixture also waited for all development assets after the
recovered UI was already usable.
> - These behaviors made two valid local runner paths fail
qualification.
> - This pull request makes the OpenCode write contract explicit and
uses the visible UI as the restart readiness gate.
> - The benefit is reliable local OpenCode qualification without weaker
duplicate detection.
## Linked Issues or Issue Description
Refs #12769
Refs #12829
Refs #12828
**What happened?**
The native OpenCode ask fixture allowed a progress tool call before the
final response. OpenCode could write the reserved terminal marker in
both places. The structured restart fixture could also time out while it
waited for `DOMContentLoaded` after the recovered UI was visible and
usable.
**Expected behavior**
The ask fixture must write the reserved marker once. The restart fixture
must continue when the recovered UI and interaction API prove that the
application is ready.
**Steps to reproduce**
1. Run the local native OpenCode ask-question paid cell.
2. Observe a run that calls `report_progress`, calls `paperclip_finish`,
and then emits the exact marker.
3. Run the local native OpenCode structured-question restart-resume cell
with a fresh Vite graph.
4. Observe that the page is usable before the navigation lifecycle event
completes.
**Paperclip version or commit**
The failures reproduced at `06cdf88bd9ac0fad82588025d23a68e810b20fd0`.
The fixes are at `f7e044e71df11a0582eafe28d2fd52ea7cd07948`.
**Deployment mode**
Local dev.
**Installation method**
Built from source.
**Agent adapter(s) involved**
OpenCode through the native runner.
## What Changed
- Require `paperclip_finish` to be the only tool call in the native ask
fixture.
- Forbid `report_progress` and other tool calls in that fixture.
- Wait for navigation commit after a server restart.
- Keep the explicit recovered UI and interaction API readiness checks.
- Add prompt contract assertions.
## Verification
- The exact two-cell paid run passed both affected cells on the AWS
runner fleet:
https://github.com/paperclipai/paperclip/actions/runs/33883334853
- Native OpenCode ask-question passed in job
https://github.com/paperclipai/paperclip/actions/runs/33883334853/job/101058952662
- Native OpenCode structured restart-resume passed in job
https://github.com/paperclipai/paperclip/actions/runs/33883334853/job/101058952823
- Prettier passed for all three changed files.
- `git diff --check` passed.
- The run-level aggregate failed only because the workflow source still
used the pre-repair lockfile on `master`. PR #12828 repairs that
lockfile.
## Risks
Low risk. The prompt change affects native ask fixtures across provider
profiles. The navigation change remains guarded by explicit UI and API
assertions.
## Model Used
OpenAI Codex, `gpt-5.6-sol`, extended reasoning, tool use, and code
execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip manages AI agents that perform work.
> - Paperclip Runner connects durable task runs to local provider
processes.
> - The full-stack paid matrix exposed failures after the runner
integrity repair.
> - Verified JavaScript entrypoints lost their relative module graph
when Linux executed them through descriptor paths.
> - Returned provider startup errors also remained pending and became
indeterminate after recovery.
> - Sparse Codex tool lifecycle events lost the `write_document`
identity before task transcript projection.
> - This pull request repairs those three boundaries and makes the
structured-question fixture deterministic.
> - The benefit is repeatable provider startup, exact failure replay,
and correct inline Plan placement.
## Linked Issues or Issue Description
Refs #12721 and #12700.
**What happened?**
The paid runner matrix failed ACPX and OpenCode startup before provider
session creation. The runner journal then replaced the original startup
error with an indeterminate recovery result. Native Codex saved a Plan
but rendered it only as a fallback card. A legacy Claude waiting reply
could also echo the reserved terminal marker before the answer arrived.
**Expected behavior**
Verified JavaScript providers must start from immutable
descriptor-backed artifacts. Returned startup failures must persist as
terminal failed command results. Native tool lifecycle updates must
preserve the `write_document` boundary. Pre-answer fixture output must
not contain the reserved terminal marker.
**Steps to reproduce**
1. Run the local provider cells in the Runner Full-Stack E2E workflow.
2. Observe ACPX and OpenCode fail during `session.open` before provider
execution.
3. Observe recovery report `execution_indeterminate` instead of the
original startup error.
4. Run the native Codex Plan cell and observe the fallback Plan card
after the tool activity row.
5. Run the legacy Claude structured-question resume cell and observe an
early marker echo in waiting prose.
**Paperclip version or commit**
`0f9452101740835ce0b1488a204bf48acd5bafc3`
**Deployment mode**
Local development with the paid GitHub Actions acceptance workflow.
## What Changed
- Bundle the ACPX sidecar and OpenCode proxy as self-contained Node ESM
entrypoints before hashing and verified descriptor launch.
- Anchor ACPX dynamic provider package resolution at a
controller-derived provider-pack root and keep that root out of the
provider child environment.
- Persist executor-returned startup errors as redacted durable failed
command results while retaining indeterminate recovery for true process
death.
- Coalesce sparse native tool items by stable ID so a late
`write_document` name, input, and result reach the transcript boundary
once.
- Forbid the structured-question fixture from spelling or announcing its
reserved terminal marker before the user answers.
## Verification
- Rust and TypeScript regression tests cover durable failed replay, true
crash ambiguity, bundle closure, package-root derivation, environment
filtering, exact Codex tool lifecycle coalescing, and prompt
determinism.
- Local execution is intentionally limited to formatters and static diff
checks. GitHub Actions will run tests, type checks, builds, and security
checks.
- After ordinary CI is green, scoped paid cells will validate one ACPX
launch, one OpenCode launch, native Codex Plan projection, and legacy
Claude structured resume before a complete matrix rerun.
- Prior failing matrix:
https://github.com/paperclipai/paperclip/actions/runs/33682434315
## Risks
- Bundling changes the bytes covered by provider launch hashes.
Provider-pack generation already hashes the final built files.
- ACPX still loads qualified provider packages dynamically. The
controller supplies a normalized package root, while existing version,
digest, path, and descriptor checks remain active.
- Durable `failed` is terminal. Replays return the same redacted result
and do not execute the provider effect twice.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex based on GPT-5 with agentic reasoning, repository
inspection, code editing, Git, parallel subagents, and GitHub Actions
coordination. The exact deployed snapshot and context-window size are
not exposed to this task.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either linked related public work or described the bug in
this PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
ticket id
- [ ] I have run tests locally and they pass (intentionally deferred to
GitHub Actions)
- [x] I have added or updated tests where applicable
- [x] No documentation change is required for this runtime repair
- [x] I have considered and documented the risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the control plane for agents that perform work.
> - Paperclip Runner connects durable provider sessions to individual
task runs through PRP.
> - Provider continuity and per-run authority are different lifetimes.
> - The existing implementation mixed those lifetimes and lost event
metadata between provider frames, runnerd, persistence, API
sanitization, and the task thread.
> - That caused failed continuation, missing progress and Plans,
duplicate replies, hidden failures, and unsafe recovery.
> - This repair gives every heartbeat fresh authority, preserves
qualified provider-session continuity, and restores one lossless
presentation path without changing direct adapters.
## Linked Issues or Issue Description
**What happened?**
A second native heartbeat could reuse tickets, leases, command receipts,
sequence state, and run identity from the first heartbeat. Provider
phase and item identity could be lost before the UI read them. Redaction
could corrupt protocol discriminators while still missing malformed
credential tails. The task thread could fold progress into the final
response, hide failures, or show more than one final answer. Native
Codex also exposed approval modes that do not yet have a durable
approval bridge.
**Expected behavior**
Each heartbeat uses a new PRP authority epoch. Codex and OpenCode
preserve exact qualified provider sessions; ACPX emits an explicit
continuity event when its qualified process-replacement policy is used.
Every accepted provider event is presented, classified as internal, or
surfaced as unsupported. The task page shows chronological progress,
reasoning summaries, activity, Plans, interactions, terminal failures,
and exactly one final reply. Direct adapters retain their existing path.
**Steps to reproduce**
1. Enable the unified experimental Paperclip Runner setting.
2. Create a local native Codex, OpenCode, ACPX Claude, or ACPX Codex
agent.
3. Run response, Plan, structured-question/resume, restart,
cancellation, and failure scenarios.
4. Reload the task while active, waiting, failed, and settled.
5. On the old implementation, observe stale run authority, missing
classifications, incomplete output, or duplicated/folded replies.
**Paperclip version or commit**
The repair is based directly on `master` at
`87d05e194b643810d16d20612115acd01d735d43`.
**Deployment mode**
Local development with the embedded database.
Related work: Refs #12616, #12646, #12666, #12685, and #12700.
## What Changed
- Rotates PRP control-plane, outbox, ticket, lease, command, receipt,
and sequence authority for each heartbeat while carrying forward only a
validated provider-session identity.
- Reads `control-plane-state.json`, validates both durable schemas and
lifecycle values, resumes coherent current runs, archives qualified
settled authority, and quarantines malformed or mismatched scoped state
without moving ambiguous live legacy state.
- Preserves Codex provider phase and stable item identities so
commentary remains progress and only `final_answer` becomes final.
- Adds raw OpenCode HTTP/SSE boundary coverage and canonical reasoning
lifecycle mapping.
- Makes ACPX normalization lossless for visible reasoning, tool
lifecycle metadata, stable bounded identities, Plan revisions,
structured requests, failures, and qualified process replacement. Only
the compatible terminal assistant message is promoted as final.
- Applies schema-aware redaction before generic JWT-shaped detection and
scans every diagnostic string leaf. Malformed raw/escaped quoted
credential tails are redacted in both server and durable Rust state.
- Restores snapshot-style chronological task presentation, expandable
tool activity, inline Plan cards, visible waiting/resume/cancel/failure
states, and exactly one final answer.
- Makes `never` the only qualified native Codex permission mode and
rejects unsupported persisted native modes with remediation. OpenCode
and ACPX policies remain intact.
- Keeps the unified experimental Runner setting as the only enablement
flag. Onboarding and direct Codex, Claude, and OpenCode stay on their
legacy execution/finalization paths.
- Adds cross-language goldens, authority/recovery/fault coverage, exact
response/count assertions, and native plus legacy acceptance scenarios.
## Verification
- Pull-request GitHub Actions run Rust formatting/tests, TypeScript
checks, server/UI tests, builds, protocol drift checks, browser E2E, and
security scans.
- A separate workflow-only validation ref is pinned directly on this PR
head and runs the 35-cell paid local matrix: three core scenarios plus
structured-question resume and restart/resume for native Codex, native
OpenCode, ACPX Claude, ACPX Codex, and direct Codex/Claude/OpenCode.
Run: https://github.com/paperclipai/paperclip/actions/runs/33682434315
- Acceptance requires exact single visible replies, monotonic sequences,
matching envelope discriminators, one semantic terminal, one run
terminal, no unresolved interaction, no duplicate mutation, no secret
leakage, provider continuity, and zero native rows for direct adapters.
- Per maintainer direction, tests are running in GitHub Actions rather
than on the slower local host. Only formatters and static diff checks
were run locally.
## Risks
- Recovery from old or partial filesystem state is sensitive. The repair
fails closed, preserves active or unverifiable authority, and
quarantines only state whose scoped ownership is safe to move.
- Provider event formats can change. Closed validators and boundary
goldens turn new or malformed events into visible diagnostics instead of
silent drops.
- Shared task presentation could affect direct adapters. Runtime-fact
gating plus the direct-adapter matrix protect the existing path.
- Managed and remote providers are not qualified here. Shared code
continues to compile and fail safely, but live qualification is
deferred.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex based on GPT-5. The exact deployed snapshot and
context-window size are not exposed to this task. It used agentic
reasoning, repository inspection, code editing, Git, parallel subagents,
and GitHub Actions.
## 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
- [ ] I have run tests locally and they pass (intentionally deferred to
GitHub Actions)
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented risks above
- [ ] All Paperclip CI gates are green
- [ ] The paid local-provider matrix is green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner subsystem executes agent work across local and managed
provider backends.
> - The lower pull requests restore the task runtime, provider backends,
and managed-provider control plane.
> - The restored system needs repeatable full-stack checks before it can
ship safely.
> - Paid live checks also need clear access, cost, and secret controls.
> - This pull request adds acceptance, live evaluation, chaos, and
release gates for the restored runner stack.
> - The benefit is measurable runner parity with safer release
decisions.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting. This change covers runner tests, release workflows,
server contracts, and evaluation tools.
**Problem or motivation**
The runner stack did not have one complete acceptance surface for native
Codex, ACPX, Claude Managed, and AWS AgentCore. Release checks could
miss provider drift, task-view regressions, cost-policy errors, and
destructive cleanup errors.
**Proposed solution**
Add a 57-cell full-stack catalog, a Daytona image, and opt-in paid
workflows. Add live evaluation, chaos, cost-limit, redaction, and
release contract checks. Add AWS AgentCore infrastructure and guarded
provisioning tools. Keep the native runner experimental flag off by
default.
**Alternatives considered**
We considered manual smoke tests only. They do not give repeatable
evidence and they do not protect release branches. We also considered
one large pull request. The stacked pull requests keep each review below
the Greptile file limit.
**Roadmap alignment**
This work supports the shipped Cloud / Sandbox agents milestone and the
shipped Agent evals & feedback milestone in `ROADMAP.md`.
Related stack:
- #12699 adds managed provider backends and lifecycle support.
- #12691 adds qualified OpenCode and ACPX provider backends.
- #12685 restores task runtime rendering and steering.
## What Changed
- Add the runner full-stack harness with 57 catalog cells and 60 unit
tests.
- Add a Daytona runner image with digest-pinned base images and
base-aware image-content checks.
- Add guarded live evaluation and chaos workflows with a fixed
40-execution matrix; live and full-stack paid schedules now run only on
Sundays or by manual dispatch.
- Add in-flight reported-usage cost stops, post-turn cost caps,
exact-threshold failure classification, secret redaction, retry
classification, and actor authorization.
- Reattach stream and hard-budget listeners before restart-recovery
continuations so restored paid sessions cannot bypass in-flight
interruption.
- Preserve OpenCode usage and cost across tool-loop messages and turns
while exposing an explicit current-run delta to durable accounting.
- Keep PNG/WebM evidence in access-controlled artifacts only, reject
SVG, and publish only pruned inert structured per-attempt evidence.
- Add AWS AgentCore infrastructure, provisioning checks, and smoke
tools; reject unsafe model identifiers, require exact stack ownership
markers, and make failed-stack replacement explicit.
- Add evaluation-session contracts and capability reports.
- Add release workflow checks for immutable action pins, frozen
dependency installs, exact weekly cron shape, paid-run guards,
provider-secret isolation, and chaos test paths.
- Reauthorize the original and triggering numeric actor IDs as the first
step of every provider-secret job, including partial reruns, before
checkout or provider access.
- Give each full-stack matrix cell only its matching provider
credential, expose Daytona only to Daytona cells, and disable shared
dependency caches anywhere paid credentials or OIDC write access are
present.
- Protect the legacy manual E2E workflow with the same default-branch,
allowlist, environment, and per-job authorization boundary.
- Rotate live-eval candidates by week and retain 120 days of compatible
history so the seven-week trend window remains viable.
- Restore the root runner-acceptance commands and reconcile reported
snapshots,
raw receipts, and terminal usage without double counting or losing late
usage.
- Mark ACPX token deltas exact only when every budget field is present,
keep
cumulative cost/request authority separate, reject non-USD cost
labeling,
and include thought tokens in output-token budgets.
- Keep `enableNativeRunner` off by default. The acceptance harness
enables it only in its isolated test instance.
## Verification
Passed locally:
- `pnpm --filter @paperclipai/paperclip-runner typecheck`
- `pnpm test:runner-acceptance:typecheck`
- `pnpm test:runner-acceptance` (19 tests)
- focused OpenCode proxy, driver, runnerd transport, live-session, and
turn-stream tests (106 tests)
- `pnpm --filter @paperclipai/paperclip-runner exec vitest run
src/live/clean-room-server.test.ts` (22 tests)
- `pnpm test:e2e:runner:typecheck`
- `pnpm test:e2e:runner:unit` (62 tests)
- `node --test scripts/__tests__/release-verify-workflow.test.mjs`
- `pnpm --filter @paperclipai/paperclip-runner
test:runner-workflow-evals` (22 tests)
- `pnpm -r typecheck`
- `pnpm build`
- `node --test
packages/paperclip-runner/scripts/aws-agentcore-provisioning.test.mjs`
(6 tests)
- `git diff --check`
- `cargo test --manifest-path
packages/paperclip-runner/runner/Cargo.toml -p paperclip-runner-core
--lib --locked` (161 tests)
- focused ACPX provider-event tests (10 tests)
- The rebased PR changes 92 files. `pnpm-lock.yaml` is unchanged.
I did not run paid live provider jobs or provision AWS resources. Those
checks need credentials and can create cost.
## Risks
The paid workflows can create provider cost. They require an allowlisted
original and triggering actor, the protected `runner-e2e-paid`
environment, explicit opt-in variables, and cost limits. The four
provider credentials exist only in that master-only environment, which
requires allowlisted reviewer approval and disables administrator
bypass; repository and organization Actions scopes contain no copies.
Provider usage arrives after a billable request, so the live guard
cannot prevent one request from crossing a threshold. It interrupts
immediately on the first reported threshold hit and permits no
continuation.
Visual evidence can contain secrets rendered as pixels. PNG/WebM remain
only in access-controlled workflow artifacts; SVG and per-attempt XML
are excluded, and S3/Pages receive a pruned structured dashboard.
The AWS scripts can create cloud resources. They use explicit commands,
least-privilege roles, KMS encryption, saved nonsecret metadata, and
explicit teardown.
This pull request does not enable the experimental native runner for
existing instances.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
OpenAI Codex with GPT-5. The model used extended reasoning, tool use,
code execution, and parallel subagents.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Dotta