Keep workspace and managed AI session metadata together, and load the renumbered work-folder migration in existing coverage.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Preserve measured operations and managed AI setup, and repair trust-order and synthetic Git transport test fixtures without importing later cancellation behavior.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Move the optional HOME helper and focused coverage ahead of its caller so the runtime hardening layer remains under the review file limit.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agent runs need credentials for a specific provider and sign-in
method.
> - Connections already owns accounts, grants, and access permissions.
> - AI authentication should use those same boundaries.
> - This pull request adds the storage, API, adoption, and runtime
foundation.
> - Legacy agents keep their authentication until they explicitly adopt
a managed connection.
## Linked Issues or Issue Description
**Problem or motivation**
AI credentials are configured separately from Connections. Agents cannot
consistently reuse a responsible user's account or a permitted shared
account.
**Proposed solution**
Manage AI accounts with the existing Connections grants and permissions.
Keep model and harness selection independent from credential selection.
Preserve legacy authentication until validated adoption.
**Alternatives considered**
A separate credential registry would duplicate ownership and access
policy. Automatic fallback would risk using the wrong account.
**Roadmap alignment**
This extends the shipped Apps, multi-user, secrets, and agent-runtime
capabilities. The maintainer requested the feature and reviewed the UI.
Related groundwork: #11899 (connection permissions), #10910 (connection
wizard), #11692 (Claude subscription profiles), and #11854 (Codex
account rotation).
## What Changed
- Add AI-purpose/runtime-auth contracts and an additive, idempotent
migration.
- Add Claude, OpenAI, OpenRouter, and Grok provider capabilities and
catalog entries.
- Store credentials on grants. Resolve responsible-user defaults or
explicit permitted grants.
- Isolate managed credentials and provider sessions across accounts.
Block missing credentials without ambient fallback.
- Keep imported legacy secrets unchanged during reconnect. Use
independent local Codex/Grok sign-in attempts for rotating credentials.
- Add authorization, migration, concurrent refresh, retry, cancellation,
and legacy-compatibility tests.
This is part 1 of a two-PR stack. The app UI follows in #13248. Merge
the foundation first.
## Verification
- Updated against master `04e364236`, preserving upstream provider login
and connector workflows.
- Full workspace typecheck, production build, Storybook build, and token
gates passed on the integrated branch. Final local-login changes passed
59 focused tests; new-agent and inbox regression suites passed 63 tests.
- Browser checks verified automatic local Claude account detection,
resumable Codex login commands, retry, focus restoration, and
desktop/phone layouts. Commands create their isolated directory before
invoking the CLI.
- All current-head CI checks passed on `2a996560a`, including all
server/workspace tests, browser shards, runner verification, typecheck,
build, and canary dry run. Greptile reviewed that commit at 5/5 with no
unresolved threads. Earlier local full-suite attempts hit the Mac
PostgreSQL shared-memory limit; the complete suites passed in CI.
- Renumbered the additive AI migration to `0276` after upstream
migrations and regenerated its snapshot. Existing legacy agents retain
their configuration.
- Added local login status checks, owner-scoped retry, managed OpenCode
remote homes, credential-aware model discovery, and task
connection-repair delivery.
## Risks
- Managed credential failures intentionally block execution. They do not
restore legacy fallback.
- Preview-era copied Codex/Grok subscriptions require independent
reconnect.
- The integrated branch has live provider acceptance coverage. This
update verifies local Claude detection and Codex API-key task repair; it
does not add a new subscription authorization/refresh or Daytona stress
pass.
- Runtime-auth connections must stay excluded from tool and channel
handling.
## Model Used
OpenAI GPT-6 through Codex, with reasoning, repository tools, code
execution, and browser testing. The exact runtime model identifier and
context-window size are not exposed in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## 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>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - A task can collect more messages while its agent works.
> - Legacy runners must stop the active process before they can receive
those messages.
> - The old Interrupt action cancelled the run but could leave the queue
idle and hidden.
> - Codex could also classify a cancelled run as successful or start a
fresh process after cancellation.
> - This pull request joins cancellation, preserves the provider
session, and dispatches the current queue after cleanup.
> - The benefit is reliable interruption with the saved message order,
edits, and deletions.
## Linked Issues or Issue Description
**What happened?**
Interrupt could strand a legacy message queue. The UI could hide pending
messages after the run stopped. A Codex signal exit could race the
cancellation write. A stale session warning could also trigger a fresh
process after an interrupted resume.
**Expected behavior**
Interrupt stops the active turn and sends the remaining messages once,
in their saved order. Deleted messages stay deleted. An interrupted
Codex turn keeps its session and does not restart itself.
**Steps to reproduce**
1. Assign a task to a legacy Codex agent that runs a long command.
2. Queue three messages. Edit one, discard another, and move the last
message first.
3. Click Interrupt in the queue.
4. Repeat the interruption while the resumed session runs another
command.
Related work: Refs #13160, which moves native queue steering into the
wake-queue module. This change fixes legacy interruption and keeps
native steering unchanged.
## What Changed
- Add a revision-checked, company-scoped endpoint for legacy queue
interruption.
- Promote only the requested queue after the provider stops and releases
its lease. Retry its persisted interrupt intent from the scheduler after
a promotion error or server restart.
- Keep pending legacy queues visible after a run stops. Use server state
for the interrupt result.
- Serialize owned process cancellation before classifying the adapter
result. Preserve late session and log metadata. Acknowledge cancellation
only when an actual process or process group was owned; scheduler
placeholders retain their normal release policy.
- Send Ctrl-C to legacy Codex. Prevent missing-session fallback once the
session has started.
- Add cancellation race, multi-actor queue order, durable retry, resume
fallback, and stale request regression tests. Document the behavior.
## Verification
- Real browser tests passed with legacy Codex CLI and ACP engines, using
Codex 0.153.4 and gpt-5.6-sol.
- All three automated ACP browser scenarios passed locally: immediate
Interrupt delivery, no replay of an unfinished write, and pause
requiring Resume. Updated the old test expectation that required a
separate “go” after Interrupt.
- Browser tests covered queued edits, deletion, reordering, deleting the
final message, and repeated interruption.
- Two consecutive CLI interrupts kept one provider session. Both stopped
processes exited. The final message arrived once.
- `pnpm -r typecheck` passed.
- `pnpm check:token-gates` passed.
- All 346 post-review scheduling, recovery, queue-route,
archived-company, worktree-suppression, and stale-queue regression tests
passed.
- All 318 process-recovery and durable-chat tests passed after the final
cancellation guard.
- Codex adapter, queue UI, issue-page, and OpenAPI contract tests
passed.
- `pnpm build` passed.
- Full local suite coverage completed with
`PAPERCLIP_IN_WORKTREE=false`, using the stable runner and its CI
shards: 618 general server suites, all 145 serialized server suites, and
all workspace groups. Every failing suite passed a targeted rerun after
the fixes, rebuilding the native test fixture, correcting macOS
temporary-path setup, or retrying setup/timing failures. Existing skips
remain.
- The original monolithic run reported failures before the final fixes;
its failed suites were rerun rather than rerunning all 618 suites again.
The final process-recovery/durable-chat regression run passed all 318
tests.
- All CI checks passed for `e30eaf787f23a5511a3cb3cdb5abbccab9ed001d`:
[run 34654820774, attempt
2](https://github.com/paperclipai/paperclip/actions/runs/34654820774/attempts/2),
including typecheck, build, all test shards, E2E, and canary. The
signoff and Cursor sandbox tests each hit a timeout in the initial
attempt; both suites passed locally, and both failed shards passed their
single CI rerun. All three corrected ACP browser scenarios passed in CI.
- Greptile reviewed `e30eaf787f23a5511a3cb3cdb5abbccab9ed001d`: 5/5, no
open review threads.
## Risks
Cancellation order affects local adapters. The tests cover signal exits,
graceful exits, adapter exceptions, termination errors, and cancellation
write errors. Embedded adapters keep their cancellation controls.
Ordinary run cancellation and task pause keep their distinct queue
policies. No database migration is required.
## Model Used
OpenAI Codex, GPT-6, with reasoning, tool use, browser testing, and code
execution. The exact serving model ID and context-window size are not
exposed in this session. The live test runner used OpenAI gpt-5.6-sol.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `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 controlled access to external services.
> - Experimental channels already map conversations to tasks and durable
work queues.
> - Email needs inbox ownership, recipient envelopes, delivery records,
and explicit sends.
> - This pull request adds AgentMail to that infrastructure and keeps
the provider key in the server vault.
> - Agents can receive and send email from local or sandbox execution
while the board follows each conversation in its task.
## Linked Issues or Issue Description
**Problem or motivation**
Agents need dedicated email addresses. Incoming email should become
assigned work. Internal task comments and progress must never become
outgoing email by accident.
**Proposed solution**
Add experimental AgentMail connections, an inbox assignment wizard,
durable email intake and publication, task email cards, and
authenticated API, CLI, and native runtime actions. Agents use Paperclip
credentials to request sends. Paperclip owns the provider key and
enforces access and task authority.
**Alternatives considered**
A general mailbox MCP connector does not provide durable task binding or
publication boundaries. A separate mailbox application duplicates task
collaboration. The board instead directs the agent through the normal
task conversation.
**Roadmap alignment**
This extends the existing experimental connections and task
infrastructure. Product scope and interaction design were reviewed with
the maintainer. Related connection authority work: #11831 and #11818.
The duplicate search found no competing task-based AgentMail
integration.
## What Changed
- Add AgentMail catalog data, shared contracts, company-scoped email
records, and an additive migration.
- Add vaulted setup, inbox assignment, access grants, trust guidance,
and provider-side allowlist guidance.
- Support WebSocket and signed-webhook intake through a shared durable
pipeline, deduplication, catch-up, and task wakeups.
- Queue explicit new conversations and replies with immutable send
intents, idempotency, delivery state, and uncertain-send resolution.
- Show inbound and outbound email cards in normal task conversations.
Keep internal messages internal.
- Add task-scoped CLI actions and the sandbox callback routes required
for Daytona execution.
- Provide a dedicated AgentMail skill automatically only to agents with
active authorized inbox assignments. Keep email instructions out of the
universal Paperclip skill.
- Advertise connector-owned `agentmail_inboxes`,
`agentmail_read_thread`, `agentmail_send`, and `agentmail_delivery`
tools only in eligible native sessions. Recheck live authority on
execution.
- Isolate Codex CLI connector skills by agent and skill revision.
Deliver the assigned skill in the run prompt for adapters that use
shared skill directories, including resumed turns. Keep automatic skills
out of manual persistent sync. Show them as read-only and document the
pattern in the connector playbook.
- Fix AgentMail health checks that entered local-stdio validation and
optional missing Codex credential cleanup in sandboxes.
- Add API, pipeline, authorization, sandbox, browser, and Storybook
coverage.
## Verification
- Live AgentMail testing covered WebSocket intake, signed webhooks,
restart catch-up, and a full receive → task → Daytona Codex CLI →
explicit reply → Delivered round trip. The reply was verified in the
other inbox. The normal task composer also initiated an outgoing email
child task.
- The connector-skill change was verified in the browser: AgentMail
appears once as an automatic, read-only skill with its assigned address.
Disabling experimental chat connections removes it; re-enabling restores
it. A regression test covers assignment data arriving after library
data.
- Connector regression coverage passed 178 runtime utility, email
integration, skill-route, and heartbeat tests. All 17 Codex execution
tests passed, including per-agent skill isolation, model identity,
revision changes, removal, and prompt delivery without shared skill
files.
- After rebasing onto master, all 44 focused email, heartbeat, and
native-authority tests passed. All 313 native-session executor tests
passed. The UI regression suite passed all 3 tests. These test sets
overlap earlier focused runs.
- Full workspace typecheck and build passed after the rebase. Token
gates passed. Earlier focused Playwright task/setup coverage and the
Storybook build also passed.
- Native connector tool execution uses deterministic integration tests.
Live Daytona qualification used the Codex CLI adapter; the new
shared-home prompt fallback has deterministic coverage.
- The full repository suite is run by CI. The earlier unsharded local
full-suite attempt was stopped after the equivalent CI suites passed and
is not reported as a completed local run. Greptile reviewed
`7e57dc267a8446d3c906e3cc5b8abc94fb8860eb` at 5/5 with no unresolved
threads. All server, workspace, serialized server, and browser suites
passed in CI. The build job hit a five-second timeout in a runner
transport test; both variants and the full 80-test file passed locally
with unchanged timeouts. The build passed on retry on the same commit
without code or timeout changes. All required CI gates, including the
final `ci / verify` and `ci / e2e` summaries, are green on
`7e57dc267a8446d3c906e3cc5b8abc94fb8860eb`.
## Risks
- Email from external senders can start normal agent work. Setup
recommends a low-trust agent and AgentMail sender controls. Sender
addresses never grant board membership.
- Provider timeouts can leave uncertain sends. Retries retain their
idempotency key; expired windows require reconciliation or operator
resolution.
- Connector skills and native tools are assignment-dependent and require
current access. Revocation denies retained calls; assignment changes
select a new runtime context.
- Activation remains behind the experimental-channel setting. The native
runner path has deterministic coverage; live Daytona qualification used
the Codex CLI adapter.
- Schema changes are additive. Inbox ownership is unique across
companies. Disconnect preserves provider inboxes and task history.
## Model Used
OpenAI GPT-6 (Codex). Used reasoning, repository tools, code execution,
and browser testing. The exact deployment model ID and context-window
size were not exposed in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
* codex/work-folders-remote-recovery-refresh:
Preserve upstream local sandbox defaults in environment regression test
Align provider selector tests with current configuration controls
* codex/work-folders-runtime-hardening-refresh:
Preserve upstream local sandbox defaults in environment regression test
Align provider selector tests with current configuration controls
Combine task-scoped workspace adoption with chat isolation, bounded shutdown draining, and provider identity handling. Preserve per-run capability rotation evidence and the new master warm-session transition coverage.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
Keep current task continuation, chat UI, provider security, and multi-architecture build behavior. Regenerate the work-folder schema after the published migration sequence and make it replay-safe for preview databases. Verify preserved file/trash/checkpoint references and company constraints on PostgreSQL.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - A user selects skills for an agent, and the host materializes those
skills into a bundle the agent reads
> - An agent can run in a remote sandbox, where the host must stage
every file the agent needs
> - On the Agent Client Protocol lane the host built that bundle and
then named its host path in the prompt, but it never staged the bundle
into the sandbox
> - The agent therefore read a path that does not exist inside the
sandbox, and the run failed on the missing skill file
> - The command-line lane of the same adapter already stages a `skills`
asset and reads the in-sandbox directory back from the staged runtime
> - This pull request carries that proven pattern to the Agent Client
Protocol lane, so a selected skill reaches the agent in a remote run
## Linked Issues or Issue Description
No public issue exists for this change. The description follows.
**What happened?**
A remote run of the Claude adapter on the Agent Client Protocol lane
could not read any selected
skill. The host builds the skill bundle in its own state directory, then
writes that host path into
the prompt as `Skill root: <path>`. The remote seam of that lane staged
one asset only, the
configuration seed. It staged no skills asset, so no skill file crossed
into the sandbox. The agent
then tried to read the skill file at the host path, and the read failed
with a missing-file error.
**Expected behavior**
A remote run receives the skills the user selected, and the prompt names
the directory that holds
those skills inside the sandbox.
**Steps to reproduce**
1. Select one or more skills for an agent that uses the Claude adapter.
2. Start a run for that agent in a remote sandbox on the Agent Client
Protocol lane.
3. Ask the agent to read the skill file at the path the prompt names.
The file is not there.
**Agent adapter(s) involved**
The Claude local adapter, on its Agent Client Protocol lane. The shared
engine in
`packages/adapter-utils` carries the prompt rewrite.
**Additional context**
The command-line lane of the same adapter already stages a `skills`
asset and remaps onto the staged
directory. This change reuses that mechanism instead of adding a new
transport. One other adapter
shows the same host-path shape on its own Agent Client Protocol lane.
That lane is tracked
separately and this pull request does not change it.
## What Changed
- Return the host skill bundle directory from the Claude skill runtime
step, and carry it through the
remote managed-home context to the staging seam. The value is null for a
non-Claude agent, for a
run that selects no skill, and for a run whose selected skills all fail
to materialize.
- Stage that bundle as a `skills` asset on the Claude Agent Client
Protocol remote seam, and only
when the run selected a skill.
- **Stage that asset with `followSymlinks: false`.** The bundle holds an
owned copy of each selected
skill, and the copy step never copies a symbolic link at the root or at
any depth. So the bundle
contains no symbolic link, and staging has none to follow. Refusing to
follow one also stops a link
planted in the bundle directory after the copy from pulling an unrelated
host file into the sandbox.
A regression test walks the real adapter sources and pins the reviewed
`followSymlinks` value at
every skills staging site, so a new or changed site fails the test.
- **Drop a skill whose staged copy has no usable `SKILL.md`** from the
prompt, the skill identity, the
command notes, and the bundle, and log which skill was dropped and why.
Without this, a skill whose
copy failed, or whose `SKILL.md` is a symbolic link the copy step skips,
stayed advertised in the
prompt while its file was absent — the same missing-file symptom this
change exists to fix.
- Rewrite the `Skill root:` prompt line, the skill identity, and the
command notes onto the
in-sandbox directory. The rewrite runs in the engine, after the
workspace placement returns the
staged runtime. A compatible session resume reuses the cached staged
runtime, so the rewrite runs
on that path too.
- Keep the session fingerprint on the host-independent skill identity. A
change to the selected skill
set still invalidates a warm session, and the volatile sandbox path
stays out of the hash.
- A local run, and a run with no selected skill, keep their current
behaviour.
## Verification
- `pnpm exec vitest run --project @paperclipai/adapter-claude-local
src/server/acp.test.ts` — 28 of 28
pass.
- `pnpm exec vitest run --project @paperclipai/adapter-utils
src/acpx-engine/execute.test.ts
src/skills-staging-follow-symlinks.test.ts`
— the new engine tests and the staging-site tests pass.
- `pnpm --filter @paperclipai/adapter-utils exec tsc --noEmit`, and the
same check on the adapter
package — both exit 0.
- The end-to-end test drives the lane against a local sandbox stand-in.
It reads the skill root out
of the prompt the runtime received, and then opens the skill file at
that path. That is the
reported symptom, proved closed.
- The new tests carry a sensitivity control. Restoring only the
production files to their previous
content fails 7 of the 9 new tests. The other 2 do not depend on
production code: one is a parser
unit test for the source scanner.
## Risks
Low risk, and the change is a two-way door. A revert restores the
previous behaviour exactly.
- **Scope.** The change touches one adapter lane. It does not change the
local lane, and it does not
change any other adapter. No existing staging site changes its
`followSymlinks` value.
- **The staged bundle and the workspace.** The staged skills land under
the runtime directory inside
the workspace. The workspace restore excludes that whole runtime
directory, so the staged skills
never return to the host worktree. A test proves the exclusion end to
end.
- **Session reuse.** The rewritten path never enters the session
fingerprint, so it cannot invalidate
a warm session, and a compatible resume applies the same staged path.
- **Direction of data.** Files move from the host into the sandbox only.
The change adds no path that
writes sandbox content onto the host.
- **A dropped skill.** A skill with no usable `SKILL.md` is now absent
from the prompt instead of
named but unreadable. The run logs the skill and the reason, so the
cause is visible.
## Model Used
Claude Opus 5 (`claude-opus-5`), with extended thinking and tool use,
through Paperclip agents.
## Test plan
- [x] `pnpm exec vitest run --project @paperclipai/adapter-claude-local
src/server/acp.test.ts` passes — 28 tests.
- [x] `pnpm exec vitest run --project @paperclipai/adapter-utils
src/acpx-engine/execute.test.ts
src/skills-staging-follow-symlinks.test.ts` passes.
- [x] `pnpm --filter @paperclipai/adapter-utils exec tsc --noEmit` exits
0.
- [x] All continuous-integration gates are green.
- [x] The automated review reports no open finding against the current
head.
## Required Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used with version and capability
details
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have described the issue in-PR following the relevant bug report
template
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [x] I have run the targeted tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect this change
- [x] I have considered and documented the risks above
- [x] All continuous-integration gates are green
- [x] The automated review score is 5/5 with no open current-head
findings
- [x] I have addressed every reviewer comment that applies to the
current head
**Note on the branch history.** This branch first carried a different
change: a filename-based admission filter that refused to stage files
such as `.env` from a skill directory, together with a switch from
symbolic-link bundles to copied bundles. That approach was rejected and
**reverted** on this branch. It does not match the documented trust
boundary, because the host already delivers credentials into the sandbox
on purpose, and replacing the symbolic-link bundles broke live editing
of a skill. The revert is in this branch's history. The file that work
changed, `packages/adapter-utils/src/server-utils.ts`, is byte-for-byte
identical to `master` here and is not part of this diff. Earlier review
findings that name that file target the reverted code. All of them are
resolved, and the automated review passes on the current head.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The `codex_local` adapter signs agents in to OpenAI, and a company
keeps one default Codex identity in its shared company home
> - A login with a DIFFERENT account than the company default is
deliberately kept out of the shared home — one agent's sign-in must not
switch every unbound agent's credentials — but that left the
cross-account login inert: nothing connected the agent the operator was
configuring to the credential the login stored
> - The stored credential and its company secret already exist; only the
last mile — an agent actually using them — was missing
> - This pull request reports a non-secret binding claim on the
authenticated login and lets the agent page bind that one agent's
`CODEX_HOME` to the account's secret, exactly and only when the
identities differ
> - The benefit is that multi-account Codex becomes one click on the
agent that needs it, with company-wide identity untouched
## Linked Issues or Issue Description
**What happened?**
On an agent's detail page, "Sign in with Codex" using a different OpenAI
account than the company default succeeds but changes nothing for that
agent. The credential lands in the per-identity store and a company
secret names it, but the agent keeps using the company default. The Test
keeps reporting that authentication is needed, and no repeat login
helps.
**Expected behavior**
When the operator deliberately signs an agent's page in with a different
account, that agent starts using that account. Agents that were not part
of the action keep the company default. A same-account login keeps
working through the shared company home with no per-agent pinning.
**Steps to reproduce**
1. Configure a company whose Codex home holds account A.
2. Open a `codex_local` agent's detail page with a sandbox environment
and complete "Sign in with Codex" using account B.
3. Press Test. Before this change the agent still resolves account A and
the authentication-needed check returns.
## What Changed
- `packages/adapters/codex-local` — the prerequisite shield:
`isCodexAuthCachePath` recognizes per-identity credential-store entries,
and `seedManagedCodexHome` refuses to symlink, heal, or
API-key-overwrite an entry's `auth.json`. The seeding pass runs before
every probe and execute; without the shield, an agent bound to an entry
would have its stored login silently swapped for the host credential.
Static shared config files still copy in. Rotation already survives
binding: the sandbox copy-back writes rotated credentials into the
identity-keyed store slot.
- `server` — the promotion records whether the company default home
ended on a different account than the login (any read failure degrades
to `false`, so the client can never be told to bind wrongly). After the
terminal commit, the routes layer remembers a non-secret claim — the
opaque account-home secret id plus that verdict — in a bounded in-memory
map, and merges it into the owner read of an `authenticated`
`codex_local` session. A restart drops the claim; the panel then shows
plain success.
- `packages/shared` — `CodexAccountBindingClaim` on the owner session
response. It carries no account identifier and no credential byte.
- `ui` — the login panel reports the claim upward once. The edit-mode
form binds the agent's `CODEX_HOME` to the secret and saves in one step,
only when `companyIdentityDiffers` is true. Same-account logins bind
nothing on purpose: the company-home refresh already carried them, and
an unbound agent keeps following the company default across rotations.
Create mode is unchanged.
## Verification
- Adapter suite: 381 passed, 1 skipped (includes the new store-entry
shield tests and the path-predicate cases).
- Server suites (8 files): 130 passed, 15 skipped — including two new
route tests that drive a login to `authenticated` and assert the claim
with both identity verdicts.
- UI render suite: 85 passed — including a panel test that the claim is
reported upward exactly once.
- `tsc --noEmit` clean in `packages/shared`, the adapter package, and
`ui`; `server` clean for the touched file.
## Risks
- The bind changes one agent's configuration through the normal
agent-update patch, initiated by the operator's own login on that
agent's page. The failure direction of every fallback is "offer
nothing": a missing claim, a restart, or an unreadable company home all
degrade to no bind.
- The seed shield narrows what the seeding pass may touch; homes outside
the credential store behave exactly as before, covered by the existing
seed tests.
- Builds on the sign-in credential-resolution fix (#13064), now merged;
this branch is rebased onto master and the diff contains only the
binding feature. Supersedes #13066, which GitHub auto-closed when its
stacked base branch was deleted on merge.
## Model Used
Claude (Anthropic) — Claude Fable 5 (`claude-fable-5`), extended
thinking, agentic tool use in Claude Code (terminal).
**Related PRs (searched; no duplicates found):** #12740, #12082, and
#9621 touch adjacent Codex credential sync paths; #8495 is the standing
hardening effort for probe auth seeding.
## 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 (no
standalone docs cover this flow; the behavioral contracts are documented
in-line at each changed site)
- [x] I have considered and documented any risks above
## Thinking Path
> - Paperclip manages agents that must write work and report task
outcomes through its API.
> - Local adapters select an execution engine and its permission
settings.
> - A higher ACP Node requirement can make an unchanged installation
lose access to its default engine.
> - The adapter then silently selects CLI, which can change permissions
and block API access.
> - This pull request keeps the engine choice fixed and reports missing
prerequisites before work starts.
> - It also gives explicit Codex CLI runs usable defaults and keeps
managed services on a supported Node runtime.
## Linked Issues or Issue Description
Refs #12215. Related changes: #11792 raised the Node requirement; #13094
addressed separate runner networking behavior. This change fixes the
engine-selection and managed-launcher paths.
**What happened?**
An unchanged agent could switch from ACP to CLI after an upgrade. Codex
CLI then used read-only permissions with networking disabled. The run
could finish without updating its task. Repeated recovery attempts used
the same unavailable setup. Managed updates also skipped the Node check
and did not refresh old launchers.
**Expected behavior**
An unavailable engine must fail with a clear setup error. It must not
silently select another engine. Explicit CLI runs must be able to write
workspace files and call the API unless the operator configures stricter
settings. Managed updates must validate Node and keep child tools on
that runtime.
**Steps to reproduce**
1. Run an ACP-default agent under Node 22 after the ACP minimum rises to
24.11.
2. Leave the engine unset and disable the approval/sandbox bypass.
3. Observe the old adapter select CLI and fail to write task disposition
through the API.
4. Start a managed service with an old launcher and a supervisor PATH
that selects a different Node for child tools.
## What Changed
- Remove automatic engine fallback for Codex, Claude, Gemini, and Kimi.
Check prerequisites for default and explicit ACP selections.
- Return a configuration error with proof that provider work did not
start. Stop automatic continuation retries for this error.
- Enable Codex ACP workspace networking at the actual turn boundary.
Upstream mode presets otherwise force it off even when config.toml
enables it. Preserve explicit network denial and read-only mode.
- Set workspace-write and network access defaults for explicit Codex CLI
runs. Preserve explicit sandbox modes, profiles, and network
restrictions.
- Pin the validated Node directory in managed launcher PATH. Refresh
legacy launchers during installs and npm/Git updates.
- Reject updates on unsupported Node. Keep update checks, dry runs, and
rollback available.
- Synchronize the qualified Codex ACP executable identity across server,
TypeScript runner, Rust runner, and provider-pack launch paths.
- Add regression tests and update engine and installation documentation.
## Verification
- [Full CI passed on the final
head](https://github.com/paperclipai/paperclip/actions/runs/34387099695):
typecheck, build/native runner verification, all general and serialized
test shards, all browser shards, release registry, canary dry run, and
policy checks.
- Greptile: 5/5 on `2c1d6e2815830a5cd39e36c8a082cc0c4441b6c0`, with no
unresolved review findings. Security gates are green.
- Full workspace typecheck and build also passed locally. The final
deployed Linux build passed.
- Full Codex, Claude, Gemini, and Kimi source test suites: 804 passed, 2
skipped. Installer, updater, and launcher tests: 47 passed. Installed
ACP turn-boundary tests: 3 passed. ACP packaging tests: 14 passed.
Focused recovery classification tests also passed.
- Real Linux Codex CLI runs, both fresh and resumed, wrote a workspace
file and reached the control-plane health API with the new defaults.
- Explicit read-only and network-disabled control probes retained those
restrictions.
- A real ACP run on the final deployed Linux build wrote a file and
reached the control-plane API with HTTP 200, without engine fallback.
The same probe failed DNS before the turn-policy patch.
- Executable-identity and installed-policy contracts: 12 passed.
Affected native server tests: 197 passed. Runner factory tests: 21
passed. Rust qualification and native provider integration tests: 11
passed.
- Deployed the production changes to a Linux service on Node 24.20 after
a verified database backup. Health, bootstrap readiness, static UI,
executable/cwd identity, and guarded restart checks passed. The restart
lost no runs.
- Corrected stale Kimi skill-default and Gemini remote-archive fixtures;
both suites pass.
## Risks
- Default or legacy auto engine settings now fail when ACP is
unavailable. Operators who intend to use CLI must select it explicitly.
- Codex CLI now permits workspace writes and networking by default, and
ACP workspace-write turns permit networking by default. Explicit
operator sandbox settings remain authoritative.
- Old managed launchers keep their pinned Node until they are
reinstalled under a supported runtime. An old updater cannot repair
itself; the documentation gives the current installer command.
- Custom service wrappers and global/source installations must configure
their runtime PATH. No database migration is required.
## Model Used
OpenAI Codex, based on GPT-6, with reasoning, repository inspection,
shell execution, and test tools. The exact serving model identifier and
context-window size are not exposed in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The `codex_local` adapter signs agents in to OpenAI with a
device-code login, and the agent page has a Test button that probes the
sandbox with the credentials a real run would use
> - The login stored its credential where the Test never looked: the
company Codex home kept an old shape-valid credential, so the Test
failed with "authentication needed" right after a successful sign-in
> - The Test also staged a different Codex home than a real run
resolves, so the Test and real runs could disagree in both directions
> - This pull request makes the login, the seeding pass, and the Test
probe agree on one credential resolution
> - The benefit is that a sign-in from the agent page fixes the Test on
the next click, and a green Test means the same thing a real run
experiences
## Linked Issues or Issue Description
**What happened?**
Sign in with Codex works during onboarding but not on the agent detail
page. The operator completes the device-code login. The panel reports
success. The Test button still reports that authentication is needed. No
number of repeat logins changes the result.
Three defects combine to cause this:
1. The device-login promotion only wrote the company default Codex home
when that home held no shape-valid credential. A stale credential (for
example a symlink to an old host login) blocked the write forever, so
the fresh login stayed invisible to the Test.
2. The seeding pass that runs before every probe and execute replaced a
same-identity regular-file `auth.json` with a symlink to the host
credential, with no freshness comparison. Even a freshly promoted
credential was deleted on the next Test.
3. The sandbox hello probe always staged the company default home. An
agent with a configured `CODEX_HOME` was tested against one credential
and ran with another.
**Expected behavior**
A completed sign-in updates the credential the Test probes. The Test
stages the same Codex home a real run resolves. A stale credential never
outranks a strictly newer one from an interactive login.
**Steps to reproduce**
1. Configure a company whose Codex home holds a shape-valid credential
that no longer authenticates (for example an old host login symlink).
2. Open a `codex_local` agent's detail page with a sandbox environment
and press Test. The result shows the authentication-needed check.
3. Complete the "Sign in with Codex" device-code flow from the panel.
4. Press Test again. Before this change the result still shows
authentication needed.
## What Changed
- `packages/adapters/codex-local/src/server/adapter-auth-promotion.ts`:
the promotion writes the company default home unconditionally. The
shared `last_refresh` merge predicate scopes the write. It seeds an
absent or unusable slot, refreshes a same-identity slot only with a
strictly newer credential, and keeps a slot a different account or an
API-key file holds. The atomic rename replaces a symlinked `auth.json`
at the link itself. It never writes through into the host home.
- `packages/adapters/codex-local/src/server/codex-home.ts`: the
same-identity heal in `seedManagedCodexHome` is freshness-aware. A
regular-file credential is swapped for the shared symlink only when the
shared source is strictly fresher by `last_refresh`. Ties and
unparseable timestamps keep the file, which matches the predicate's
fail-closed direction. A genuine stale copy still heals as soon as the
host credential rotates past it.
- `packages/adapters/codex-local/src/server/test.ts`: the sandbox hello
probe prepares and stages the same home a real run resolves. The
identity-anchored cache vend runs first. A configured managed
`CODEX_HOME` is seeded in place and staged. A genuine external override
is staged as-is and never seeded or mutated.
- Tests: new pins for the strictly-newer company-home refresh, the
different-account keep, the symlink-replaced-without-writing-its-target
property, the freshness-aware heal (newer kept, older healed, ties
kept), the configured-home staging, and the external-home no-mutation
proof. The remote-probe suite now pins `CODEX_HOME`/`PAPERCLIP_HOME` to
scratch directories so no test can touch a real `~/.codex`.
## Verification
- `pnpm exec vitest run packages/adapters/codex-local/src --root
packages/adapters/codex-local` — 378 passed, 1 skipped.
- Server suites for device login, reconciliation, and the codex adapter
(8 files) — 128 passed, 15 skipped.
- `tsc --noEmit` clean in the adapter package.
## Risks
- Behavioral shift is scoped by the shared merge predicate: only a
strictly newer same-identity login can displace a company-home
credential, so a second account still never takes over the company slot,
and API-key files are never displaced.
- The heal keeps ties and unparseable timestamps instead of swapping. A
kept file self-corrects on a later seed once the source is provably
fresher; deleting a promoted credential is irreversible, so the failure
direction is chosen deliberately.
- The probe change makes the Test exercise the credential a run uses. A
Test that previously passed against the company home while the agent's
configured home was broken now fails honestly.
## Model Used
Claude (Anthropic) — Claude Fable 5 (`claude-fable-5`), extended
thinking, agentic tool use in Claude Code (terminal). Diagnosis traced
through the live promotion locks, the on-disk Codex homes, and the
adapter's credential-resolution code paths.
**Related PRs (searched; no duplicates found):** #12740, #12082, and
#9621 touch adjacent Codex credential sync paths; #8495 is the standing
hardening effort for probe auth seeding.
## 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 (no
standalone docs cover this flow; the behavioral contracts are documented
in-line at each changed site)
- [x] I have considered and documented any risks above
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agent adapters select a provider, a model, and a runtime.
> - Runner conversion rejected existing Claude agents. The model list
mixed providers.
> - The native Claude runner rejected custom models and could not launch
on macOS.
> - This pull request fixes conversion, model selection, and verified
macOS execution.
> - It also groups configuration fields consistently across adapters and
opens artifact images in the task gallery.
> - Operators can change an agent configuration and run the selected
model on their Mac.
## Linked Issues or Issue Description
**What happened?**
Converting an existing Claude agent to Paperclip Runner failed with a
Codex-only restriction. ACPX Claude showed unrelated models and required
`claude-sonnet-5`. Its native runtime rejected macOS. Configuration
mixed common model settings with process controls. Artifact cards
labeled “Open gallery” navigated to attachment URLs instead of opening
the task gallery.
**Expected behavior**
Conversion keeps agent identity and compatible settings. ACPX Claude
uses the normal Claude catalog and accepts typed model IDs. Codex uses
the native runner. The verified Claude runtime can launch on macOS ARM64
and x64. Common configuration sections place the same fields together
across adapters. Artifact images open in the shared task gallery with
navigation and downloads.
**Steps to reproduce**
1. Open the configuration of an existing Claude agent.
2. Convert it to Paperclip Runner.
3. Select ACPX Claude and a different catalog model or a typed model ID.
4. Save the agent and run a disposable task on macOS.
5. Inspect configuration and advanced run-policy controls across
adapters.
**Paperclip version or commit**
The bugs were reproduced on `165ca56a22adb60e5fda56045442d9c8498116a8`.
This branch was rebased onto `7ed122911`.
**Deployment mode**
Built from source. Local test-drive instance on macOS ARM64 with an
isolated database.
Related work: #11798 addresses unsupported ACP session options in the
existing adapter path. #13048 addresses working-folder preservation.
This change fixes native runner configuration and launch behavior.
## What Changed
- Remove the Codex-only conversion restriction. Preserve agent identity,
instructions, directories, credentials, and compatible model settings.
Reset incompatible sessions while retaining history.
- Show ACPX Claude and native Codex as distinct provider choices. Remove
ACPX Codex from advertised configuration. Normalize legacy
configurations before fresh runs without rewriting historical run
descriptors.
- Select model catalogs and cache entries by provider. Support refresh
and typed model IDs. Pass exact Claude IDs through session creation,
model changes, and recovery.
- Add verified macOS ARM64 and x64 Claude SDK snapshots. Bound
executable allocation and total snapshot size. Preserve package checks,
dependency isolation, process ownership, cancellation, and Linux
descriptor loading.
- Probe local runtime readiness. Report remote platform checks as
incomplete until the remote runner verifies its runtime.
- Surface actual model rejection and allow correction and retry.
- Repair missing ACPX goal-capability helpers exposed by the post-rebase
live test. Persist and restore the optional capability without breaking
session startup.
- Put Agent identity first and intentionally remove the Capabilities
editor, as requested. This is removal of UI editing, not relocation:
preserve existing capability metadata and API compatibility without
adding another editor. Use the themed select for configurable permission
modes, with normal text instead of monospace.
- Put model and provider under Adapter. Give environment variables their
own section. Fold command and arguments under Configuration. Fold
lifecycle, timeout, and interrupt grace under Advanced Run Policy. Hide
single-option permission controls.
- Open image and video artifact cards in the existing task gallery,
including cards in the artifacts panel. Chat attachment images use the
same gallery. Preserve standalone media previews and download links.
## Verification
- Rebased focused UI/API/database suites: 293 tests passed.
- Rebased native runtime and ACPX suites: 242 passed, 7 skipped.
- Repository typecheck, build, and token gates passed for the runner
changes. Gallery follow-up UI typecheck, build, and token gates also
passed.
- Follow-up UI suites passed (86 tests), packaging checks passed (14
tests), and the final focused runtime suites passed (126 passed, 7
skipped).
- Linux container isolation and lifecycle fixtures passed before rebase
(57 passed, 2 skipped). Rust ACPX provider-session tests passed after
rebase (8 tests).
- Browser tests completed actual Claude and native Codex tasks on macOS
ARM64. They covered conversion, catalog refresh, a non-default catalog
model, a typed `haiku` ID, save/reload, cancel, follow-up session
continuity, invalid-model errors, and recovery.
- Final-revision live tests completed a typed Claude task, a follow-up
with the same provider session, and a native Codex task on macOS ARM64.
- Browser tests confirmed the moved interrupt-grace field saves and
survives reload. Cross-adapter tests cover Claude, Codex, Gemini,
process, gateway, and schema forms.
- Full local run: 7,080 passed, 30 skipped, and two timeouts. Both
timeout suites passed on isolated rerun (84 tests); the failures were
the plugin login-worker exit diagnostic and the runner real-server
vertical slice.
- Final follow-up checks: 50 registry tests and 45 snapshot/installation
tests passed (6 platform-specific skips). Oversized executable rejection
is covered before allocation or reading; unsupported-platform tests
invoke the real installation probe.
- Runner head `ddb5101c483a297f74875ab96b3c66035b002d50`: all CI gates
green, including full runner verification, repository build, typecheck,
general/serialized server suites, browser tests, and canary dry run. [CI
run](https://github.com/paperclipai/paperclip/actions/runs/34286178670).
- Greptile: 5/5 on that runner head. All four review threads resolved.
Superagent, Socket, and Snyk checks green.
- After snapshot hardening, another real Claude task completed on this
Mac using the rebuilt runtime.
- Gallery follow-up: 148 focused tests passed, covering artifact
selection, shared attachment collections, deduplication, image/video
cards, standalone previews, downloads, and closing. Live browser
verification completed on the settings follow-up: artifact selection,
6-image pagination with wrapping, download action, and closing all
stayed on the same task URL. All checks passed on gallery head
`96136da58ff195bf6ca00b281eb3022ad12d7bd8`: [CI
run](https://github.com/paperclipai/paperclip/actions/runs/34287987536).
Greptile returned 5/5 on that exact head with no unresolved threads.
- Final settings polish: 96 focused tests, UI typecheck/build, and token
gates passed. A real browser walkthrough verified readable permission
options, identity placement, Capabilities removal, and permission
save/reload. Original test-agent permission mode restored. All 31 checks
passed on final head `e46540d6bf32bfb0566dca16b2f4a75ba437618c`: [CI
run](https://github.com/paperclipai/paperclip/actions/runs/34292797886).
Greptile returned 5/5 with no unresolved threads.
## Risks
- Capabilities intentionally has no editable UI field after this change.
Existing values remain readable and API-compatible; removing the field
does not erase stored metadata.
- macOS launch now copies verified package files into private snapshots.
The implementation must retain isolation and clean up snapshots on exit.
- Runtime provider or model changes reset the current session.
Historical runs remain available.
- The macOS x64 SDK executable digest was verified, but a live Intel Mac
run was not available. Linux verification used container fixtures, not a
real Claude task.
- Remote environment tests report a warning when only the platform has
been checked. They do not claim package readiness from the server host.
## Model Used
OpenAI Codex, based on GPT-6. The exact served model identifier and
context-window limit are not exposed in this session. Used reasoning,
repository inspection, code execution, Rust and TypeScript tests, and
browser automation.
## 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 (focused suites and both
timeout suites on rerun; full-run counts above)
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Resolve unset Claude models to Opus 5 across CLI and ACP execution, preserve explicit and provider-specific overrides, and show the default in agent configuration.
Verified 212 focused tests after merging master, UI typecheck and token gates, and all CI checks. Greptile reviewed the final head at 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.
> - Operators create agents and configure their runtimes in the board
UI.
> - The old creation flow presents several choices and a large form
before an agent can start.
> - The existing onboarding controls already provide clear provider
connection steps.
> - This pull request uses those controls in a new-agent wizard and
organizes the full configuration pages.
> - Operators can connect, test, save, and assign a first task while
keeping the existing configuration tools.
## Linked Issues or Issue Description
Related: #10974. That earlier open PR also reorganizes agent
configuration. This PR follows the reviewed Storybook designs for agent
creation and the current configuration tabs.
**What existing behavior does this improve?**
Agent creation, provider connection, runtime tests, and full agent
configuration.
**Current behavior**
The creation dialog leads to a large manual configuration form. Provider
login controls differ from onboarding. Environment variables and secret
access appear in separate places.
**Proposed behavior**
Choose a name and adapter. Connect Claude or Codex through the existing
onboarding controls. Configure and test the runtime, save the agent, and
open a task dialog with that agent assigned. Use the same design on the
existing configuration tabs.
**Reason and benefit**
The first setup asks for fewer decisions. The full editor keeps
instructions, skills, runtime controls, secret access, permissions,
keys, and revisions available in clear sections.
**Breaking changes**
The board creation and configuration layouts change. The
test-environment API adds an optional, allowlisted `testCredentials`
field for one-shot probes. Database contracts stay the same. Native ACPX
tests now reject unsupported local platforms before a CLI login can mask
the runtime restriction.
## What Changed
- Added a new-agent wizard with numbered steps, adapter branding,
provider connections, editable model choices, runtime tests, and
confirmation.
- Added Codex app-server, Claude ACPX, and OpenCode runner choices.
- Stored API credentials through existing secret APIs and persisted
references in agent configuration. New setup keys are isolated from
credentials used by existing agents.
- Preserved external-agent invitations beside the wizard, including
optional messages, one-time prompts, and clipboard fallback.
- Added OpenRouter provider and secret bindings for Pi and OpenCode.
- Added adapter-specific prerequisite fields for Cursor, Gemini, Kimi,
and Hermes. Cursor Cloud keys are saved as new organization secrets.
- Fixed Cursor Cloud repository field mapping, omitted empty remote
environment values, and added useful model and repository error
messages.
- Preserved complete MCP assignments when multiple valid profiles
contain more than 250 tools in total. Generated profiles retain exact
tool selectors.
- Added service branding and deployment-aware adapter choices. Cloud
setup offers Claude, Codex, and OpenCode; local native runners require
the experimental setting.
- Made the agent list responsive at intermediate widths.
- Applied the reviewed design to the real agent configuration pages.
Kept the instruction editor, skills, and existing mutations.
- Combined secret access and environment variables under one Save and
Discard action.
- Added interactive Storybook screens for setup, configuration,
confirmation, authentication, and test results.
- Fixed Pi provider-error parsing and thinking-effort persistence.
Native ACPX validates Linux x64 on the actual local, SSH, or sandbox
target.
- Redacted the complete transient probe-credential field from HTTP error
logs, including rejected provider names.
## Verification
- Current head `df0292fe6` has a fresh Greptile 5/5 review with no
unresolved findings. All 31 executed CI checks passed, including the
aggregate verification gate and all browser E2E shards. Storybook visual
regression is skipped by its workflow; the local Storybook build passed.
- Browser tests completed real assigned tasks with direct Codex, Claude,
OpenCode, Pi, and native Codex.
- Verified external-agent invitation generation and automatic prompt
copying in the live browser.
- Pi and OpenCode used an existing OpenRouter secret. Browser checks
covered save and reload, instruction edits, skill selection,
environment-variable Save and Discard, and assigned task creation.
- Invalid Claude API credentials remained on the connection step with an
error. A live Pi/OpenRouter invalid-key probe returned a provider
failure and left the user-secret inventory unchanged (zero entries
before and after).
- Full workspace typecheck and build passed after rebasing onto current
master. After review fixes, server and UI typechecks, token gates, and
the full build passed again. Storybook built successfully.
- All 5,542 local UI tests passed. The Cursor Cloud and Pi adapter
regressions passed all 24 tests. Review regressions passed 69 server
tests and all 18 agent-list tests.
- The local full test command ran 6,971 general server tests
successfully. Editing review fixes during that long run caused nine
tests to use stale modules; fresh isolated runs passed. An unrelated
embedded-Postgres fixture hit the host shared-memory limit; its 15
affected tests passed when the fixture groups ran separately.
- Local workspace groups passed after rerunning 18 CLI tests
sequentially to avoid host database limits and parallel-load timeouts.
The local full command stopped at the general server phase, so
serialized server verification comes from the five passing CI shards.
- Browser testing at 390px confirmed that the agent action menu opens
and the page has no horizontal overflow. CI browser E2E shards passed.
- Review the `Onboarding / New agent` and `Agents / Configuration
refresh` Storybook groups. In the real app, create an agent, run its
connection test, save it, assign a task, and reload its configuration.
## Risks
- This changes the main agent setup and configuration UI. Regression
tests cover routing, persistence, secret bindings, and form actions.
- Native Claude ACPX requires Linux x64. Direct Claude works on macOS.
Remote checks execute a bounded platform probe and reject unsupported or
unverified targets.
- A native OpenCode task reached the provider context limit because of
its tool payload. Its provider connection test passed. Direct OpenCode
completed a task. This existing native execution limit is not fixed
here.
- Claude and Codex connection keys use the existing user-secret store.
Other runtime setup keys use distinct organization secrets. Existing
credentials are never rotated. Probes do not store entered keys. Failed
agent creation removes newly staged credentials.
- Cursor Cloud has not completed a live task. Its authenticated account
still needs GitHub repository access. The live run passed MCP
provisioning, remote environment validation, and explicit Auto model
selection before the repository prerequisite blocked execution.
- Generated runtime MCP profiles can exceed the public profile-edit
request limit. They still contain exact catalog selectors and preserve
permission boundaries.
- No database migration, dependency, lockfile, or workflow changes are
included.
## Model Used
OpenAI Codex, based on GPT-6, with reasoning, repository tools, shell
execution, and browser automation. The runtime did not expose the exact
model ID 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 `#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 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 is the open source app that people use to manage AI agents
for work.
> - The Codex local adapter supplies model metadata to the server and
the user interface.
> - OpenAI now lists `gpt-6-astra` as a supported Codex model.
> - Paperclip did not list this model or its model-specific controls.
> - This pull request adds the model through the existing adapter
metadata path.
> - The benefit is that agents and task overrides can use the exact
model ID and supported controls.
## Linked Issues or Issue Description
**Subsystem affected**
`packages/adapters` and `ui`
**Problem or motivation**
Paperclip does not expose `gpt-6-astra` in Codex model selectors.
Operators cannot select and save the model through the normal agent and
task forms.
**Proposed solution**
Register the exact model ID in the Codex local adapter. Use the adapter
as the source for the model-specific reasoning options. Preserve the
current default model. Forward the saved model, reasoning effort, and
fast-mode controls through both Codex execution lanes.
**Alternatives considered**
A user-interface-only model list would duplicate adapter metadata. A
model alias would not match the official model ID. Both options were
rejected.
**Roadmap alignment**
This is a small adapter compatibility update. It does not duplicate a
planned item in `ROADMAP.md`.
## What Changed
- Added `gpt-6-astra` to the Codex local adapter model registry and
fast-mode support list.
- Added the official Astra reasoning efforts: `low`, `medium`, `high`,
`xhigh`, `max`, and `ultra`.
- Used the adapter metadata in agent and task model selectors.
- Preserved supported effort choices when the model changes. Cleared an
effort only when the new model does not support it.
- Added tests for registration, user-interface selection, configuration
persistence, and CLI and ACP forwarding.
## Verification
- `pnpm exec vitest run packages/adapters/codex-local/src/index.test.ts
packages/adapters/codex-local/src/server/acp.test.ts
packages/adapters/codex-local/src/server/codex-args.test.ts
packages/adapters/codex-local/src/ui/build-config.test.ts
ui/src/lib/codex-reasoning-effort.test.ts
ui/src/components/AgentConfigForm.render.test.tsx
ui/src/components/IssueProperties.test.tsx
ui/src/components/NewIssueDialog.test.tsx
ui/src/lib/issue-assignee-overrides.test.ts` passed 245 tests.
- `pnpm -r typecheck` passed.
- `pnpm check:token-gates` passed all four gates across 939 files.
- `pnpm --filter @paperclipai/ui build` passed and supplied isolated
user-interface build proof.
- `pnpm build` passed.
- `pnpm test:run` passed 5,812 tests and failed 24 workspace-runtime
tests in this isolated host. The failures use invalid generated ports
above 65,535, incomplete nested-worktree fixture configuration, or
`/tmp` path aliases. The focused tests for this change all pass. GitHub
CI must pass before review handoff.
- GitHub CI run `33918372718` passed all required checks and the
aggregate verify gate on exact head
`6ac6be2cee0a5996c82bdf674fcb7f46cb4c5fde`.
- Independent engineering review approved the exact remediation head
after 170/170 reviewer tests passed.
- Greptile reported 5/5 with no open review threads on exact head
`6ac6be2cee0a5996c82bdf674fcb7f46cb4c5fde`.
- The model ID and capabilities were checked against the [official
OpenAI Codex model list](https://developers.openai.com/codex/models).
## Risks
- Low risk. The change adds one model and model-specific selector
options. It does not change the default model.
- OpenAI can change model capabilities later. The adapter metadata must
stay aligned with the official Codex metadata.
> 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 model ID `gpt-5.6-sol`, a 272,000-token context
window, 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
- [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 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 companies that use AI agents for
work
> - Local adapters connect Paperclip agents to provider command line
tools
> - The Codex adapter stores login data in a shared company home
> - A shared home cannot keep credentials for more than one Codex
account
> - This pull request gives each account a safe home and a matching
company secret
> - The benefit is that one company can use multiple Codex accounts at
the same time
## Linked Issues or Issue Description
**Problem or motivation**
A company can hold only one Codex subscription credential because device
login uses one shared home. A second account cannot log in without
replacing or conflicting with the first credential.
**Proposed solution**
This change validates the vendor account identifier, stores each
credential in its own home, and creates a company secret that points to
that home. Repeat login calls return success when the matching secret
already exists.
**Roadmap alignment**
The change supports the roadmap goal for centrally managed secrets with
scoped access and audited resolution.
**Additional context**
The security review returned approve with no blocking finding. The
branch adds shared account-handle validation and tests for device login
and the Codex local adapter.
## What Changed
- Add strict allowlist validation for Codex account handles.
- Store each Codex account credential in a separate home under the Codex
cache root.
- Verify that the resolved account home stays inside the cache root.
- Create the `CODEX_HOME_<handle>` company secret for each account.
- Keep repeat and concurrent login calls safe and idempotent.
- Add shared helper and route, adapter, and validation tests.
## Verification
- `pnpm --filter @paperclipai/adapter-codex-local test` passes with 343
tests.
- `pnpm --filter @paperclipai/server test
src/__tests__/agent-device-login-routes.test.ts` passes with 25 tests.
- The adapter suite passes with 23 tests.
- The shared package and Codex adapter typechecks pass.
- Continuous integration must pass on every check before merge.
## Risks
The account handle becomes part of a directory path and secret name. The
strict allowlist and root containment check reduce path traversal risk.
Existing single-account homes remain unchanged unless a new device login
creates an account-specific home.
## Model Used
OpenAI GPT-5 (exact runtime model ID: gpt-5), with tool use and code
execution. The runtime context window is not exposed in 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)
- [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
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Claude local adapter lets operators select a Claude model for an
agent.
> - Claude Fable 5.1 was absent from the adapter model lists.
> - The adapter runtime also used a Claude Code build that rejected
Fable 5.1.
> - This pull request adds the direct Anthropic ID and the AWS Bedrock
inference profile ID.
> - It also updates the Claude ACP runtime and keeps the Paperclip usage
and isolation patches.
> - The benefit is that operators can select and run Claude Fable 5.1
through the Claude adapter.
## Linked Issues or Issue Description
Refs #8810. That issue covers related model ID handling. This change
does not change provider-prefixed model IDs.
**Agent or provider**
Claude Code through the built-in `claude_local` adapter. The requested
model is Claude Fable 5.1.
**Why this adapter is useful**
Operators can use Fable 5.1 without entering an undocumented model ID.
The configured model also reaches both supported Claude execution lanes.
**How the agent is invoked**
The CLI lane sends `--model claude-fable-5-1`. The ACP lane sends
`ANTHROPIC_MODEL=claude-fable-5-1` to
`@agentclientprotocol/claude-agent-acp`.
**Are you willing to implement it?**
Yes. This pull request includes the implementation and tests.
**Additional context**
Claude Code 2.1.232 rejected Fable 5.1 and required version 2.1.251 or
newer. ACP package 0.73.0 includes Claude Code 2.1.257. The update keeps
Paperclip's usage metadata and isolated-context behavior.
## What Changed
- Added `claude-fable-5-1` to the direct Claude fallback list.
- Added `us.anthropic.claude-fable-5-1` to the AWS Bedrock list.
- Kept the existing default model at the first position in each list.
- Updated the Claude ACP dependency from 0.70 to 0.73.
- Carried the Paperclip usage and isolated-context changes into the 0.73
patch.
- Added a Claude Code 2.1.251 minimum-version preflight for Fable 5.1
when using the standard `claude` executable, surfaced in both adapter
Test and execution. Explicit custom wrappers retain their existing
compatibility contract.
- Kept local adapter Tests from executing caller-selected binaries: when
runtime `PATH` selects a different Claude executable than the trusted
probe, the Test warns and defers the authoritative version check to
execution instead of approving or rejecting the alternate installation.
- Added tests for model listing, discovery deduplication, Bedrock
filtering, model pass-through in both execution lanes, old-CLI rejection
before launch, custom-wrapper compatibility, and local runtime-PATH
mismatch handling.
## Verification
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm exec vitest run
packages/adapters/claude-local/src/server/execute.remote.test.ts
packages/adapters/claude-local/src/server/test.remote.test.ts
packages/adapters/claude-local/src/server/test.probe.test.ts
packages/adapters/claude-local/src/server/acp.test.ts
server/src/__tests__/adapter-models.test.ts` (72 tests passed)
- `node --test scripts/acpx-patch-packaging.test.mjs` (13 tests passed)
- `pnpm -r typecheck`
- `pnpm build`
- A local Paperclip agent run completed with `usageJson.model` set to
`claude-fable-5-1` through ACP 0.73.0 and its bundled Claude Code
2.1.257.
- `pnpm test:run` completed 5,638 passing tests and 24 skipped tests. It
also found 24 failures in unrelated workspace-runtime,
path-canonicalization, and runtime-exposure tests on macOS with Node 26.
These failures do not touch this diff. Clean pull request CI is the
final full-suite gate.
## Risks
- The ACP dependency update can change Claude runtime behavior outside
model selection. Focused ACP tests, the full typecheck, the production
build, and a real local Fable run reduce this risk.
- The 0.73 patch must stay aligned with the installed ACP version.
Dependency-resolution CI verifies the manifest and patch pair.
- Fable 5.1 adds a short `claude --version` preflight to standard
CLI-lane Tests and runs. The result is intentionally not cached so an
in-place Claude Code upgrade takes effect without restarting Paperclip.
Explicit custom wrappers are not version-probed because their output and
compatibility contract can differ from the standard executable.
- Local Tests preserve the existing deny-by-default probe boundary and
do not execute a binary selected by caller-controlled `PATH`. A
mismatched runtime binary produces an explicit warning without blocking
an otherwise valid setup; execution independently validates the actual
runtime-selected CLI before launch.
- The AWS Bedrock identifier differs from earlier IDs because Fable 5.1
has no `-v1` suffix. The model-list test locks this exact value.
- There is no schema change or migration.
> 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
Provider: OpenAI. Model: GPT-5 Codex. The host did not expose a more
specific model ID or context-window size. Capabilities used: agentic
reasoning, repository editing, shell execution, web research, and local
runtime verification.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the 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 Paperclip Runner provides durable, provider-neutral agent
execution.
> - The current stack supports qualified local providers but omits the
managed provider paths from the integration branch.
> - Claude Managed Agents and AWS AgentCore need explicit profile
qualification, durable recovery, usage accounting, and cleanup controls.
> - This pull request adds those managed backends as the third part of
the Runner parity stack.
> - The benefit is managed execution without weakening the default-off
Runner rollout gate.
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting: Runner, server orchestration, database profiles, CLI, and
adapter configuration UI.
**Problem or motivation**
The current Runner stack cannot select or execute the managed Claude
Agents API or AWS Bedrock AgentCore Harness backends. It also lacks
qualified profile storage and recovery checks for those remote
resources.
**Proposed solution**
Add qualified managed and remote profiles, API and CLI management, exact
provider selection, durable lifecycle handling, cumulative usage
accounting, bounded cleanup, and retention acknowledgement. Keep
`enableNativeRunner` default-off.
**Alternatives considered**
A direct copy of the old integration branch was rejected because its
provider contracts, model values, credential flow, and migration history
no longer match the current base. A single large parity pull request was
also rejected because stacked review keeps each subsystem bounded.
**Roadmap alignment**
This continues the existing Runner architecture and rollout work. It
does not introduce a separate execution system.
**Additional context**
This pull request is based on the merged #12691 and #12685 stack. It
also closes the delayed security-review findings reported on #12691 by
binding qualified ACPX and OpenCode launch artifacts to the bytes
actually executed. A GitHub search for managed agent, AgentCore, and
Claude managed work found no duplicate public issue or pull request.
## What Changed
- Add Claude Managed Agents and AWS AgentCore provider executors to
runnerd.
- Add qualified managed and remote profile storage, routes, OpenAPI
contracts, CLI commands, and migration 0237.
- Validate profile ownership, enabled state, exact qualified revision,
model, agent version, and secret binding before persistence and
recovery.
- Persist durable provider session and owned skill state for
restart-safe cleanup.
- Reconcile uncertain create responses and delete remote sessions before
owned skills.
- Track cumulative provider usage and enforce positive session spend
caps.
- Recover interrupted AgentCore usage at the next turn boundary by
charging the prior invocation ceiling exactly once; keep the session
gated until an explicit monotonic budget raise.
- Isolate AgentCore AWS configuration from host profiles and
credential-process/SSO configuration while preserving workload identity.
- Require OpenCode 1.18.17 and fixed build-owned provider-pack artifact
paths; remove the ambient executable override.
- Snapshot and content-verify ACPX and OpenCode commands, scripts, and
provider executables before launch. Linux executes sealed inherited
descriptors; macOS uses authenticated private snapshots with retry-safe
rematerialization at the spawn boundary.
- Persist canonical ACPX and OpenCode launch-profile digests, reject
drift across fresh recovery, and make recovery failures sticky.
- Close and journal unsafe ACPX active-turn recovery before any provider
bootstrap or reconnect.
- Add managed provider fields to the Runner configuration UI and
permission projection.
- Preserve the default-off `enableNativeRunner` experimental flag.
## Verification
- `pnpm -r typecheck`
- `pnpm build`
- Focused managed server, database, CLI, Runner TypeScript, Rust,
Claude, AgentCore, ACPX, OpenCode, process-supervisor, and
durable-recovery tests passed.
- `cargo test -p paperclip-runner-core --lib --locked` (160 tests)
- `cargo check --workspace --all-targets --locked`
- Native Codex integration tests passed (60 tests); native provider
tests passed (7 tests); server native-runtime tests passed (87 tests).
- Verified-launch replacement, nested-spawn retry, exact-version,
profile-drift, sticky-failure, and no-bootstrap active-recovery tests
passed.
- `git diff --check`
- The PR changes 91 files. `pnpm-lock.yaml` is unchanged. The Rust
workspace lockfile adds the approved `rustix` dependency used for safe
descriptor handling while `#![forbid(unsafe_code)]` remains enabled.
## Risks
- The provider APIs can change while they are in beta. Exact
qualification and fail-closed recovery checks limit drift.
- Remote cleanup can fail after a partial create. Durable ownership
inventories and retry-safe deletion preserve recovery state.
- Migration 0237 adds profile tables. The generated migration and
snapshot pass the repository migration checks.
- Managed execution can incur provider cost. Positive default spend caps
and explicit retention acknowledgement limit accidental use.
- An interrupted AgentCore invocation without final metadata is
conservatively charged to its active session ceiling. This can overstate
cost, but cannot undercount it; later work requires an explicit budget
increase.
- Linux qualified launches use sealed memory descriptors. macOS lacks
executable-descriptor APIs, so the runner uses owner-only private
snapshots and minimizes linked-path lifetime; hostile same-UID processes
remain outside the documented local-host trust boundary.
- The global Runner feature remains default-off.
> 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, GPT-5, with tool use, code execution, and subagent review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip Runner is the experimental native runtime for governed
agent work.
> - The runtime contracts already describe Codex, OpenCode, and ACPX
providers.
> - The merged control plane still rejected OpenCode and ACPX for new
runner agents.
> - Runnerd also selected only the Codex provider implementation.
> - This pull request activates the qualified OpenCode and ACPX paths
from the form to runnerd.
> - The benefit is one durable runner path with provider-specific
permissions and recovery.
## Linked Issues or Issue Description
Refs #12685
**Subsystem affected**
This change affects the runner package, server orchestration, adapter
configuration, and UI configuration.
**Problem or motivation**
Paperclip Runner stores provider contracts for OpenCode and ACPX. New
agents cannot select those providers. Runnerd cannot execute those
stored provider descriptors. The UI also shows only Codex.
**Proposed solution**
Accept the qualified OpenCode 1.18.17 profile and the fixed ACPX Claude
and Codex profiles. Route them through runnerd. Keep provider selection,
model selection, permissions, credentials, events, and recovery inside
closed provider-specific boundaries.
**Alternatives considered**
One option was to keep the contracts dormant. That option leaves stored
configuration and runtime behavior out of sync. Another option was to
enable every ACPX agent. That option is not safe because Pi does not yet
have the same verified launch path.
**Roadmap alignment**
This change supports the completed cloud and sandbox agent milestone. It
also supports self-healing runs and governed agent execution. It does
not add a new roadmap surface.
## What Changed
- Add one server profile resolver for Codex, OpenCode, and qualified
ACPX descriptors.
- Keep `adapterConfig` as the provider and permission authority for
fresh runs.
- Add Paperclip Runner provider, ACPX agent, and provider-specific
permission controls to the UI.
- Reset the model to a compatible qualified value when the provider
changes.
- Route Codex, OpenCode, and ACPX through the durable runnerd provider
selector.
- Add a durable ACPX executor with bounded state, recovery, events, tool
receipts, and identity checks.
- Remove Codex labels from OpenCode events, results, evidence, and
recovery diagnostics.
- Pass only provider-specific credential names to child processes.
- Keep ACPX Pi unavailable and reject it before process launch.
- Keep the existing Paperclip Runner experimental flag unchanged.
## Verification
- `pnpm exec vitest run
packages/paperclip-runner/src/backends/native-backend-factory.test.ts
packages/paperclip-runner/src/live/runnerd-codex-transport.test.ts
packages/adapters/codex-local/src/ui/build-config.test.ts
ui/src/adapters/codex-local/config-fields.test.tsx
server/src/__tests__/adapter-registry.test.ts
server/src/__tests__/adapter-routes.test.ts
server/src/__tests__/agent-adapter-validation-routes.test.ts
server/src/__tests__/company-portability.test.ts
server/src/services/native-runtime/runtime-mode.test.ts
server/src/services/native-runtime/native-session-executor.test.ts
server/src/services/heartbeat-runner-provider-config.test.ts`
- The focused TypeScript, server, and UI suites passed 274 tests.
- `cargo test -p paperclip-runner-core --test native_provider_backend`
- The executable native provider integration suite passed 4 tests.
- `cargo test -p paperclip-runner-core --lib`
- The Rust unit suite passed 91 tests.
- `pnpm -r typecheck`
- `pnpm check:token-gates`
- `pnpm build`
- `git diff --check codex/runner-parity-task-runtime...HEAD`
## Risks
- This changes provider process selection and durable recovery. The
experimental flag still gates every fresh Paperclip Runner run.
- OpenCode requires a model in `provider/model` form and stays pinned to
version 1.18.17.
- ACPX accepts only exact Claude and Codex profile versions and models.
Pi stays unavailable.
- ACPX steering stays unavailable and reports that limit through the
driver capabilities.
- Child processes receive explicit environment allowlists. They do not
inherit the full server environment.
- This pull request has no database migration.
## Model Used
OpenAI Codex, GPT-5, with tool use, code execution, and subagent review.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [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
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Paperclip runs agents through provider-specific adapters in local
and remote environments
> - A remote Grok run can refresh its credential inside its sandbox
> - The host copy can become stale when teardown discards that refreshed
credential
> - This pull request copies the refreshed credential back through a
locked, fail-closed teardown path
> - The benefit is that later Grok runs can use the refreshed host
credential without another login
## Linked Issues or Issue Description
Refs: #12618
**Agent or provider**
Grok local adapter.
**Why this adapter is useful**
A remote Grok run can refresh its access token during a run. Copying the
refreshed credential back to the host keeps later runs ready to use.
**How the agent is invoked**
Paperclip invokes the Grok local adapter through its remote subscription
run path. The adapter stages the company Grok home as a sandbox asset.
The change adds a copy-out step on the teardown path.
## What Changed
- `grok-auth-merge-decision.cjs` adds a host predicate in its own
process. It compares the whole `<issuer>::<uuid>` identity key of the
two files. It reads `expires_at` as an ISO-8601 string, an epoch-seconds
number, or an epoch-milliseconds number. It exits 10 to use the source,
20 to keep the destination, 21 when the expiry shape is unreadable, and
22 when the source expiry sits more than 400 days after the host clock.
It fails closed in every unclear case: an unusable side, a different
identity, an absent expiry, a tie, an unreadable expiry, and an
implausible expiry all keep the destination.
- `grok-auth-merge-decision.ts` adds a wrapper that runs the predicate
and maps the exit code to a typed result.
- `grok-auth-copyback.ts` adds `copyBackGrokAuth({ hostHomeDir,
readSandboxAuth, log, env })`. It locks on `hostHomeDir` with
`withDirectoryMergeLock`, stages the sandbox bytes into a private `0600`
temporary file, runs the predicate, and installs the file with an atomic
rename in the same directory. It keeps no backup of the displaced
credential. It leaves no temporary file on the success path, the keep
path, or an error path. On an error it logs the `errno` code only, then
re-throws.
- `execute.ts` adds a `restore` callback to the Grok `home` asset. The
callback takes the destination from
`resolveManagedGrokHomeDir(process.env, agent.companyId)`, never from
`env.GROK_HOME`. A copy-out failure does not fail the run.
- `package.json` updates the `build` script to copy
`grok-auth-merge-decision.cjs` into `dist/server/`, because `tsc` does
not copy a `.cjs` file.
**The credential shape this predicate reads**
A redacted sample of a real vendor credential answered four structural
questions. The answers hold no credential bytes, no account identifier,
no file path, and no timestamp value.
1. `expires_at` is present.
2. `expires_at` sits inside the value object, under the
`<issuer>::<uuid>` key. It is not a top-level field.
3. `expires_at` is an ISO-8601 string. It carries UTC time with a
trailing `Z` and six fractional-second digits.
4. A normal run rewrites `auth.json`. The value object carries a
`refresh_token` next to `expires_at`, so the client refreshes the access
token and rewrites the file.
## Verification
- [x] `pnpm vitest run packages/adapters/grok-local` — 114 tests in 12
files pass.
- [x] `pnpm --filter @paperclipai/adapter-grok-local typecheck` — clean.
- [x] `pnpm --filter @paperclipai/adapter-grok-local build` — succeeds,
and `dist/server/grok-auth-merge-decision.cjs` exists after the build.
- [x] Continuous integration is green on every check.
## Risks
The predicate keeps the host credential when identity, expiry, file
access, or freshness data is unclear. The copy-out path can log an error
and leave the run successful when it cannot install the refreshed
credential. The atomic rename and directory lock protect the host file
from partial writes and concurrent copy-out actions.
## Model Used
OpenAI GPT-5, current deployment. The exact runtime version and context
window are not exposed to this agent. The model used tool calls and code
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 (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>
Dotta
Dotta
Nicky Leach
Devin Foley
Michael Nguyen
dependabot[bot]