## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Sandbox agents need a safe login path for each supported adapter
> - Codex device login and Claude setup-token login used separate
session stores and route logic
> - Separate stores made session lookup, expiry, and login capability
checks harder to keep consistent
> - This pull request unifies both flows on one session table and one
capability contract
> - The benefit is one company-scoped login model with public session
identifiers and shared lifecycle rules
## Linked Issues or Issue Description
**Subsystem affected**
Cross-cutting (multiple of the above)
**Problem or motivation**
Codex and Claude sandbox login used separate session stores and
different route paths. This split increased the risk of inconsistent
company scoping, session lookup, and cleanup.
**Proposed solution**
Use `adapter_auth_sessions` for both login flows. Use public session
identifiers for API access. Select login behavior from projected adapter
capability data. Share the route spine, lease arguments, runner
lifecycle, and reaper rules.
**Alternatives considered**
Keep two session tables and add matching fixes to both routes. This
keeps duplicate logic and does not provide one capability contract, so
this pull request uses shared infrastructure.
**Roadmap alignment**
This change supports the shipped Cloud / Sandbox agents milestone in
`ROADMAP.md`.
## What Changed
- Unify Codex device login and Claude setup-token login on
`adapter_auth_sessions`.
- Return and look up sessions with company-scoped public session
identifiers.
- Enforce one active session for each company, owner, and adapter.
- Share the login route spine, sandbox lease arguments, runner
lifecycle, and missing-auth check.
- Add a standalone setup-token reaper with adapter-specific row
selection.
- Add optional login capability projection for adapters and drive route
and UI selection from that data.
- Rename the provider flag to `supportsLoginPty` and validate its
deprecated alias.
- Remove the old Claude setup-token session table and add the required
migrations.
## Verification
- Server typecheck passed with `tsc`.
- Database typecheck passed.
- UI typecheck passed with `tsc -b`.
- Codex login service and route suites passed.
- Setup-token session, route, and reaper suites passed.
- Adapter session schema, plugin validator, capability projection, UI
render, and Daytona suites passed.
- GitHub Actions must confirm the complete CI gate after pull request
creation.
## Risks
- The migrations remove short-lived in-flight login rows during
deployment. A login that spans the migration can continue until its
provider lease expires.
- The Codex credential store remains company-scoped. A cross-owner
credential race remains a documented, board-accepted risk.
- API clients that use internal session row identifiers no longer work.
The API accepts only public session identifiers.
## Model Used
Codex, GPT-5, exact runtime model ID not exposed in this handoff, large
context window, reasoning, and repository tool use. The implementing
engineer produced the code with AI assistance.
## 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.
> - Managed worktree services run isolated Paperclip instances with
cloned databases.
> - A reachable service was reported as ready even when its database,
runtime identity, or login path was not usable.
> - The first candidate added verified database seeding and managed
repair in #11665.
> - This pull request consolidates that candidate with signed login
handoff and a complete readiness contract.
> - Post-QA fixes close five defects in repair identity, repair
responses, UI retry, seed journal handling, and seed-source trust.
> - The benefit is a workspace that either opens safely or reports one
accurate recovery action.
## Linked Issues or Issue Description
No public GitHub issue exists for this work, so the problem is described
here.
**What happened**
Managed workspace URLs could return HTTP 200 and report ready while
login failed. QA also found cases where repair used the wrong instance
identity, returned a generic error, left the UI stuck, rejected a safe
journal lag, or trusted a mutable workspace manifest.
**Expected behavior**
Opening a ready workspace signs the board user in to the correct
isolated instance. Provisioning and repair use a registered source and
report a structured recovery state.
**Actual behavior**
Entry depended on a password copied into the clone. Several failure
paths could publish stale readiness, hide the repair precondition, or
trust state that the workspace could modify.
**Additional context**
This pull request includes the commits first published in #11665. That
pull request keeps the original base head for review history. This
consolidated pull request is the merge candidate. Related open readiness
work includes #11575 and #11621.
## What Changed
- Adds a short-lived, signed, single-use login ticket. It binds the
user, workspace, instance, and runtime origin.
- Exchanges the ticket through Better Auth. It creates the session and
cookie through the supported adapter path.
- Adds protected workspace readiness fields for the database, clone
data, login handoff, seed phase, and runtime identity.
- Fails readiness closed when the guest has no company or
execution-workspace binding.
- Binds ticket issuance to the exact cloned user and active company
membership selected for the handoff.
- Verifies every current active board identity through the exact-user
handoff before publication or reuse.
- Gates managed runtime publication on the readiness contract and the
recorded worktree instance identity.
- Refreshes runtime work products from the live runtime row after a port
change.
- Adds one workspace access card with ready, degraded, repairing, and
failed states.
- Uses the runtime response identity for repair. It returns structured
repair precondition errors.
- Lets a valid source journal lag converge during provisioning.
- Binds seed and repair manifests to a source registered outside the
agent-writable worktree.
- Clears recovered UI errors so a successful retry can open the
workspace.
- Makes runtime tests register canonical sources and avoid ports owned
by live host listeners.
- Keeps Vitest on source suites when compiled `dist` trees exist.
- Isolates CLI and adapter tests from ambient AWS and runtime API
environment variables.
- Preserves a 404 response for cross-company workspace ID lookups before
runtime authorization.
- Makes concurrent single-flight coverage independent of
path-canonicalization scheduling order.
## Verification
The following checks passed on the integrated head:
```sh
pnpm -r typecheck
pnpm build
pnpm check:token-gates
pnpm --filter @paperclipai/db check:migrations
```
- The server source lane passed 420 files and 4,953 tests. Five tests
were skipped.
- The CLI lane passed 57 files and 385 tests.
- The database lane passed 26 files and 97 tests.
- The shared package passed 58 files and 506 tests.
- The adapter utility lane passed 640 tests. Four tests were skipped.
- The Claude adapter passed 220 tests. One test was skipped.
- The Codex adapter passed 323 tests.
- The OpenClaw adapter passed 13 tests.
- The OpenCode adapter passed 42 tests.
- The plugin SDK passed 45 tests.
- The workspace runtime suite passed 124 tests.
- The caller-scoped readiness and handoff suite passed 52 tests.
- The workspace provisioning shell suite passed 7 tests.
- The runtime exposure suite passed 17 tests while live host mappings
occupied fixed test ports.
- `git diff --check` passed and the worktree is clean.
The serialized route lane will run in GitHub CI with its normal shards.
No deployment or active-workspace migration was performed.
## Risks
- This is a medium-risk authentication and runtime-readiness change.
- The login ticket uses exact origin, workspace, instance, and user
binding. It has a short expiry and a one-time nonce.
- Runtime publication is stricter. A real readiness, identity, per-user
handoff, or control-plane database disagreement now blocks publication.
- This pull request supersedes #11665 as the merge candidate. Close
#11665 after this pull request merges.
- No new database migration is included. The lockfile and workflow files
are unchanged.
- Deployment and active-workspace migration are intentionally outside
this pull request.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
Claude Opus 5 (`claude-opus-5[1m]`), 1M context, extended thinking, tool
use, and code execution produced the main candidate. OpenAI GPT-5
(`gpt-5`) through Codex, with agentic reasoning, tool use, and code
execution, integrated the post-QA fixes and hardened the test gates. The
Codex context-window size was not exposed.
## 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 Claude local adapter supports subscription login through a
sandbox
> - The new-agent page must show login before the user creates an agent
> - Test results must not expose raw sandbox diagnostics or secret
values
> - This pull request adds the login UI to both Test lanes and closes
the diagnostic boundary
> - The branch also adds durable cleanup recovery for failed sandbox
teardown
> - Reusable sandboxes must retain both their recorded teardown
configuration and a valid lifecycle path until destruction succeeds
> - The benefit is a usable login flow with fixed public checks,
redacted server logs, and recoverable sandbox cleanup
## Linked Issues or Issue Description
Related public work:
[#9488](https://github.com/paperclipai/paperclip/pull/9488) adds
first-class recognition for `CLAUDE_CODE_OAUTH_TOKEN` in headless and
remote runs. Related public issue:
[#2681](https://github.com/paperclipai/paperclip/issues/2681) requests
Claude Code subscription support. This pull request adds the login
transport and new-agent UI flow that those changes do not provide.
**Subsystem affected:** Claude local adapter, server login probes,
sandbox provider setup, cleanup recovery, and the new-agent UI.
**Problem or motivation:** The Test lanes did not show the sandbox login
panel in all supported cases. Test results also exposed raw probe
diagnostics, and JSON escapes could end secret redaction early.
**Proposed solution:** Surface the login capability through the bundled
provider manifest. Prepare the same probe runtime in the ACP lane. Send
diagnostics only to redacted server logs. Keep Test checks on fixed
public messages. Normalize login URL hints to allowlisted HTTPS Claude
and Anthropic hosts. Consume JSON escapes during redaction. Preserve
failed sandbox cleanup state across retries and restarts, and prevent
deletion from severing the lifecycle context of a live reusable sandbox.
**Alternatives considered:** Keep raw diagnostics in Test checks or
trust login URL text from the sandbox. Both choices increase information
exposure. Keep separate probe behavior in the ACP lane. That choice
would leave the two Test lanes inconsistent.
## What Changed
- Surface the sandbox login panel on both Test lanes.
- Reconcile the bundled Daytona plugin manifest so
`supportsSetupTokenLogin` reaches the UI capability gate.
- Prepare the ACP Test lane with the same probe runtime as the CLI Test
lane.
- Add the `claude_acp_login_probe_unavailable` warning when the ACP
probe cannot run.
- Send raw sandbox diagnostics only to redacted server logs.
- Keep Test checks on fixed public messages in the ACP, managed-config,
and CLI paths.
- Normalize login URL hints to allowlisted HTTPS Claude and Anthropic
hosts.
- Redact JSON and escaped-JSON secret values, including escaped quotes
and backslashes.
- Preserve orphan cleanup records across provider failures, restarts,
and unavailable plugins.
- Atomically block environment deletion while a live reusable sandbox
lease still depends on it.
- Verify pending cleanup destroys plugin sandboxes with the provider
configuration recorded on the lease, even after the current environment
configuration changes.
## Verification
- Head under review: `506b7fa2d83c36bfa5fd722ee9d95b0c7431c241`.
- Focused environment route/service/runtime coverage passes: 196 tests
across 3 files.
- `pnpm -r typecheck` passes.
- `pnpm build` passes.
- The full Vitest run completed with 4,754 passing and 28 failing tests.
All 23 source-test failures reproduce unchanged on parent head
`58cfe61a33191ce03d965d65085d26064b4888ba`; the other 5 are duplicate
executions from stale `server/dist` output. The failures are unrelated
macOS path/listener and scheduler-fixture failures, so there is no new
bad commit for bisect to localize.
- All required CI checks pass for the current head, including build,
typecheck/release registry, all server and workspace shards, serialized
server suites, canary, and e2e.
- A fresh Greptile review for `506b7fa2d83c36bfa5fd722ee9d95b0c7431c241`
reports 5/5, “safe to merge,” with no blocking failure remaining.
## Risks
- A probe or redaction change could hide useful server diagnostics.
- An allowlist change could reject a valid Claude login URL.
- Cleanup recovery changes could affect provider teardown ordering.
- An environment with a live reusable sandbox can no longer be deleted
until the owning issue or execution workspace completes teardown.
- The implementation keeps public Test messages fixed and sends detail
to redacted server logs.
## Model Used
OpenAI GPT-5 via Codex — exact model ID: GPT-5; tool use and code
execution enabled; extended reasoning enabled. The implementation author
used AI-assisted development.
## 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 documented the result
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation or confirmed no separate
documentation change is needed
- [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.
> - Agent adapters run ACP sessions and manage runtime, workspace, and
lease resources.
> - Several failure paths left runtime bridges, staged workspaces, or
environment leases active after an error.
> - These leaks reduce run reliability and can leave later runs without
clean resources.
> - This pull request closes the failure paths, applies one teardown
policy, and adds regression tests.
> - The benefit is consistent failure settlement and safer reuse of
agent workspaces and leases.
## Linked Issues or Issue Description
**What happened?**
ACP runs could leave runtime bridges, staged workspaces, or environment
leases active after failures. Claude and Gemini ACP runs did not restore
the sandbox workspace on teardown. Lease release stopped when one lease
returned an error.
**Expected behavior**
Each ACP failure must return an error result and settle its resources.
Teardown must run each step, release leases independently, and restore
the host workspace when the sandbox ends. Pending cleanup leases must
receive bounded retry attempts.
**Steps to reproduce**
1. Run an ACP session that fails after runtime creation or during turn
preparation.
2. Run an ACP session that fails during a warm hit or staged runtime
handoff.
3. Run lease cleanup with more than one lease when the first release
returns an error.
4. Inspect the result phase, teardown calls, workspace state, and lease
metadata.
5. Run the regression suites listed in the Verification section.
## What Changed
- Settle every ACP failure after runtime creation with an error result
and one sandbox.startup span closure.
- Close the ACP runtime and remove warm entries after every pre-turn
failure.
- Run all teardown steps, record teardown errors, release staging leases
in finally, and prevent duplicate teardown.
- Dispose staged runtimes after seam failures and remove borrowed staged
entries with identity guards.
- Add fail-open workspace sync-back teardown for Claude and Gemini ACP
adapters.
- Isolate lease release errors and add bounded retry sweeps for stranded
pending_cleanup leases.
- Atomically claim pending_cleanup retries and clamp attempt readers to
keep the five-attempt bound.
- Default absent provider reusableLeases values to false and align the
fake provider with its runtime declaration.
- Add regression tests for engine, adapter, server, and shared
environment behavior.
## Verification
- [x] `npx vitest run
packages/adapter-utils/src/acpx-engine/execute.test.ts` — 124 tests
passed.
- [x] `npx vitest run
packages/adapters/codex-local/src/server/acp.test.ts
packages/adapters/claude-local/src/server/acp.test.ts
packages/adapters/gemini-local/src/server/acp.test.ts` — 61 tests
passed.
- [x] `npx vitest run server/src/__tests__/environment-runtime.test.ts
server/src/__tests__/heartbeat-pending-cleanup-sweep.test.ts
server/src/__tests__/reusable-leases-default.test.ts
server/src/__tests__/environment-routes.test.ts
packages/shared/src/environment-support.test.ts` — passed.
- [x] All listed suites ran from the repository root.
- [x] GitHub CI completed successfully for
`cfc349c9f232711433897915112a1c52c0e462ca`.
- [x] Greptile completed with a 5/5 confidence score and no blocking
finding.
## Risks
The engine changes affect failure settlement and teardown order across
ACP runs. The server changes add retry state to existing lease metadata
without a schema migration. The adapter changes restore workspaces after
sandbox execution. Regression tests cover the changed paths. GitHub CI
and Greptile passed for the current head.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. This change fixes runtime
reliability and does not duplicate a roadmap feature.
## Model Used
OpenAI GPT-5 Codex. The model used tool-based repository inspection,
GitHub operations, and code review support. The runtime does not expose
a context-window value.
## 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 (for example, `docs/...` or
`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>
Fixes#2444.
Refs #4947.
The `claude_local` adapter launched Claude Code as
`claude --print - --output-format stream-json --verbose`. Paperclip writes
the rendered task prompt to Claude's stdin, but current Claude Code releases
can treat the stale `-` positional marker as the prompt itself, so Claude
received the literal string `"-"` instead of the issue body. The customer's
task ran against no content at all.
The fix keeps `--print` mode and stdin delivery, and removes the stale `-`.
Adds regression coverage on both sides of the delivery path: a `claude_local`
assertion that `--print` is present, `"-"` is absent and the prompt still
reaches stdin, and an adapter-utils case proving the sandbox run-log command
wrapper preserves stdin while streaming logs.
Authored by @elJayAdvisor, whose commit is included unchanged with their
authorship. The branch had gone stale and was showing CONFLICTING; the
conflict was in `execution-target-sandbox.test.ts`, where their new test was
added at the same point as master's `creates the process session directories
only in the launch exec` case and git interleaved the two into one hunk.
Resolved by taking master's file and re-inserting their test whole, after
checking every helper it needs still exists there.
Verified: the bug was still live on master at `execute.ts:838`; the
regression test genuinely catches it — restoring the stale `-` fails
`expect(captured.argv).not.toContain("-")`; `@paperclipai/adapter-claude-local`
and `@paperclipai/adapter-utils` typecheck clean; 67 pass across the two test
files. All CI gates green; Greptile 5/5.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Claude local is one of the adapter paths that lets operators run
Claude Code through a local Paperclip runtime.
> - Claude Code rejects `--dangerously-skip-permissions` when the
process is running as root or through sudo.
> - Local/self-hosted Paperclip deployments may run inside root-owned
Docker/runtime processes, so the Claude local adapter can fail before it
reaches the actual runtime/auth condition.
> - Paperclip already uses a curated `--allowedTools` list instead of
`--dangerously-skip-permissions` for remote Claude targets.
> - This pull request applies the same safer permission strategy to
local root processes while preserving existing local non-root and remote
behavior.
> - The benefit is clearer, safer Claude local diagnostics/execution in
containerized setups without widening permissions beyond the existing
explicit tool allowlist.
## Linked Issues or Issue Description
No directly matching public issue or PR found.
Bug description:
- **Problem:** `claude_local` can fail its local probe/execution path
when Paperclip runs from a root-owned local container/runtime because
Claude Code refuses `--dangerously-skip-permissions` under root/sudo.
- **Actual behavior:** The adapter may fail immediately with Claude's
root/sudo guard before validating the real Claude runtime/auth state.
- **Expected behavior:** Local root processes should use the same
explicit allowlist strategy Paperclip already uses for remote targets,
while local non-root behavior remains unchanged.
- **Environment:** Local/self-hosted Docker or container-style Paperclip
runtime where the app process UID is `0`.
Related but different: #4926 covers MCP config propagation for the
Claude local adapter, not the root/sudo permission flag behavior fixed
here.
## What Changed
- Added root-aware permission argument selection for the Claude local
adapter.
- Preserved current local non-root behavior:
`--dangerously-skip-permissions` is still used when allowed.
- Preserved current remote behavior: remote targets continue using
explicit `--allowedTools`.
- Changed local root behavior to use the explicit `--allowedTools` list
instead of `--dangerously-skip-permissions`.
- Threaded process UID awareness through Claude local probe and
execution paths.
- Added unit coverage for skip-disabled, remote, local non-root, local
root, and UID-unavailable behavior.
## Verification
```sh
./node_modules/.bin/vitest run --config g15-vitest-claude-local.config.mjs \
packages/adapters/claude-local/src/server/permissions.test.ts
```
Result:
```text
1 file passed
8 tests passed
```
```sh
pnpm --filter @paperclipai/adapter-claude-local typecheck
```
Result:
```text
@paperclipai/adapter-claude-local typecheck passed
```
Additional local smoke:
- Ran a disposable root-container Claude adapter diagnostic against this
patch.
- The diagnostic no longer fails with Claude's root/sudo
`--dangerously-skip-permissions` error.
- It proceeds to the actual environment-specific Claude auth/runtime
result.
- No credentials, tokens, hostnames, private paths, or internal
Paperclip issue references are included in this PR.
Public duplicate checks performed:
```sh
gh pr list --repo paperclipai/paperclip --state open --search 'claude local root permissions dangerously skip permissions allowedTools'
gh issue list --repo paperclipai/paperclip --state open --search 'claude local root permissions dangerously skip permissions allowedTools'
```
## Risks
Low-to-medium risk adapter behavior change:
- Local root Claude runs will now use explicit `--allowedTools` rather
than broad skip-permissions behavior.
- That is intentionally safer, but an environment depending on broader
implicit tool access under root may now need the adapter allowlist to
include any required tools.
- Local non-root behavior is unchanged.
- Remote behavior is unchanged.
- No database migrations, API contract changes, or UI changes.
> 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-5.5` via Hermes Agent, with shell/file/tool use for
repository inspection, patching, local verification, and GitHub CLI
operations.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: LeeJ <elJayAdvisor@users.noreply.github.com>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Claude agents that run in a remote sandbox need a safe in-product
login path
> - The existing host login route cannot open a pseudo-terminal inside
that sandbox
> - The login flow must protect the browser code, the login URL, and the
OAuth token at every step
> - This pull request adds the parser, the runner, a Daytona
pseudo-terminal transport, and a guarded, owner-bound session route
behind an injectable transport
> - The route stays inert in the default build and fails closed until a
sandbox provider binds the live transport
> - The benefit is a company-scoped setup-token flow with one-time
secret delivery, redaction, and fail-closed transport checks, ready for
a later staged production rollout
## Linked Issues or Issue Description
**Agent or provider**
Claude Code setup-token login for sandbox agents.
**Why this adapter is useful**
Sandbox agents need a supported way to sign in without host credentials.
An authorized owner completes the browser step and receives the token
one time.
**How the agent is invoked**
When a sandbox provider binds the injectable transport, the server
starts `claude setup-token` through a sandbox pseudo-terminal, sends the
browser code to the matched prompt, and returns the token through the
guarded session route. The default build does not bind the transport. In
that state the start route fails closed with a fixed no-secret `503`. It
does not start a process and it does not hold a sandbox lease.
**Additional context**
The transport is injectable, so each sandbox provider binds its own
pseudo-terminal. This pull request adds the Daytona transport but does
not bind it in the production server. A production wiring needs a lease
manager, a live pseudo-terminal factory, a durable token store, and its
own security review. The route keeps secrets out of logs, activity
details, errors, telemetry, and non-owner responses.
## What Changed
- Add strict parsers for the setup-token URL, the prompt, and the
success token.
- Add a login runner that drives the `claude setup-token` command
through a pseudo-terminal.
- Add the Daytona pseudo-terminal transport and the sandbox plugin
wiring.
- Add a company-scoped, owner-bound login session service with rate
limits, a reaper, cleanup, and one-time token delivery.
- Add the guarded session routes at
`/agents/:id/setup-token-login-sessions/*` behind an injectable
transport. The routes become the live login path only when a provider
binds the transport.
- Keep the start route fail-closed in the default build. It returns a
fixed no-secret `503` and it does not bind `setupTokenLogin`.
- Keep the existing host route `POST /agents/:id/claude-login` in place.
This pull request does not replace it.
- Keep confidential responses behind a fail-closed TLS transport guard
with `Cache-Control: no-store`, and extend redaction for the new fields.
- Export the parser and the runner from the Claude local server entry,
and document the new session routes in the OpenAPI spec.
## Verification
- `pnpm --filter @paperclipai/server exec vitest run setup-token-route
setup-token-session`
- `pnpm --filter @paperclipai/adapter-claude-local exec vitest run`
- `pnpm --filter @paperclipai/server run typecheck`
- Confirm that the pull request checks pass on GitHub.
## Risks
- Low user-facing risk on merge. The default build does not bind the
transport, so the production start route stays fail-closed with a `503`.
The merge does not change the production login behavior.
- When a provider later binds the transport, the flow starts a live
sandbox process and holds a short-lived in-memory secret. Cleanup must
stop the child before it releases the sandbox lease.
- The transport guard fails closed when the deployment does not provide
a trusted TLS path. A wrong proxy allowlist can block a valid request.
- The production wiring is out of scope. It needs a lease manager, a
live pseudo-terminal factory, a durable token store, and its own
security review before the server binds `setupTokenLogin`.
## Model Used
Anthropic Claude Opus 4.8 assisted the implementation. It used extended
reasoning, code execution, repository tool use, and a 200,000-token
context window.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` /
`Closes: #` / `Refs: #` OR (b) described the issue in-PR following the
relevant issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes (the
OpenAPI spec covers the new session routes; no user-facing documentation
needs changes)
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The agent Test action builds adapter config from the form.
> - The build-config parser kept plain and secret_ref bindings.
> - It dropped user_secret_ref bindings on the create path.
> - This PR shares one parser that keeps every binding shape.
> - The test path now sends the same env binding set that a real run
sees.
> - The benefit is one fix across every adapter build-config path.
## Linked Issues or Issue Description
**What happened?**
The agent Test action dropped a user-scoped env binding in create mode.
The same agent config worked in a real run. Related public PRs: #10115,
#9321, #9921, #8825.
**Expected behavior**
The Test action should keep user-scoped env bindings and resolve them
like a real run.
**Steps to reproduce**
1. Set a user-scoped env binding on an agent config form.
2. Run Test in create mode.
3. The probe runs without the variable.
**Paperclip version or commit**
c09d2509e3
**Deployment mode**
Local dev (pnpm dev)
**Agent adapter(s) involved**
Not adapter-specific (core bug)
**Database mode**
Embedded PGlite (default — DATABASE_URL unset)
**Additional context**
This change is not Claude-specific.
## What Changed
- Added a shared env binding parser in `@paperclipai/adapter-utils`.
- Replaced the eight adapter build-config copies with the shared helper.
- Kept `plain`, `secret_ref`, and `user_secret_ref` bindings intact in
create mode and edit mode.
- Preserved the runtime merge behavior from the earlier env merge
change.
## Verification
- Author-recorded test run:
`packages/adapter-utils/src/env-bindings.test.ts`
- Author-recorded test run:
`packages/adapters/claude-local/src/ui/build-config.test.ts`
- Author-recorded test run: six adapter build-config test files
- Author-recorded typecheck: `tsc --noEmit` for adapter-utils and the
eight adapter packages
- GitHub checks: all required PR checks pass on PR #10926.
- Greptile review: 5/5 with no open comments.
## Risks
- The change touches adapter config assembly.
- A wrong binding shape would change test-time probe input.
- Tests cover the binding types and the create-mode path.
> 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 GPT-5, code execution and repo inspection.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` /
`Closes: #` / `Refs: #` OR (b) described the issue in-PR following the
relevant issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change and contains no internal
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 or
confirmed no documentation update is needed
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The claude_local adapter runs Claude Code on sandbox execution
targets, and operators verify an agent's configuration with the
test-environment probe before running it
> - Real runs merge the selected environment's env vars (secret refs
included) under the agent's adapter config env, but the probe built its
config from the adapter config alone — so environment-level auth worked
in runs while the Test button reported missing auth, and a dropped
secret binding passed silently
> - The claude env-test hints also did not recognize
`CLAUDE_CODE_OAUTH_TOKEN` even though the CLI accepts it, and a hello
probe that hit the subscription usage limit reported a hard failure
although authentication worked
> - Separately, the claude-local package test suites were absent from
the CI project list, so two suites drifted broken without notice
> - This pull request makes the probe resolve the same layered env as a
real run, adds the missing auth hint, classifies usage-limit probe
results as a warning, repairs the drifted suites, and turns the
claude-local project on in CI
> - The benefit is a Test button that tells the truth about
environment-level configuration, and a test suite that actually gates
the claude-local adapter
## Linked Issues or Issue Description
No public issue exists; related open PRs: Refs #9488 (recognizes
CLAUDE_CODE_OAUTH_TOKEN in environment checks — overlaps with the
auth-hint portion of this PR via a differently named check; it does not
cover the environment-envVars probe merge, the usage-limit
classification, or the CI coverage), Refs #9933 (live credential
validation in environment checks — complementary, no file-level conflict
with the route change).
The underlying problem, following the enhancement template:
**Current behavior**
The test-environment route builds the probe config from the agent's
adapterConfig only. Real runs merge the selected environment's envVars
under the agent env, so environment-level env vars (including auth such
as `ANTHROPIC_API_KEY` or `CLAUDE_CODE_OAUTH_TOKEN` bound as environment
secrets) work in runs while "Test environment" cannot see them, and a
missing secret binding passes silently. The claude env-test hints do not
recognize `CLAUDE_CODE_OAUTH_TOKEN`. A hello probe that hits the
subscription usage limit reports a hard `claude_hello_probe_failed`. The
claude-local package test suites do not run in CI, and two of them are
stale.
**Proposed behavior**
The probe resolves the selected environment's envVars
(environment-consumer secret bindings included) and merges them under
the agent config env with the run-path precedence; missing bindings
surface as an explicit error check that fails the test. The env-test
emits a `claude_oauth_token_configured` info check when that variable is
set. Usage-limit probe results classify as a
`claude_hello_probe_usage_limited` warning because auth works and only
the usage window is spent. The claude-local suites run in CI. Docs state
the resulting facts.
**Reason and benefit**
The Test button should tell the truth: it previously contradicted run
behavior for environment-level configuration and hid broken secret
bindings. Enabling the package suites in CI prevents further silent
drift — two suites were already broken on master without anyone
noticing.
**Breaking changes**
None. Runs are unchanged. The probe route only adds env layers and
checks; setups without environment envVars behave exactly as before.
## What Changed
- `server/src/routes/agents.ts`: the test-environment route resolves the
selected environment's envVars (forbidden keys stripped,
environment-consumer secret context) and merges them under the agent
adapterConfig env, mirroring `resolveExecutionRunAdapterConfig`
precedence. Missing secret bindings are skipped, reported as an
`environment_env_binding_missing` error check, and fail the test —
matching the `ConfigurationIncompleteFailure` a real dispatch would
raise.
- `packages/adapters/claude-local/src/server/test.ts`: new
`claude_oauth_token_configured` info hint between the API-key warning
and the subscription fallback; hello-probe classification gains a
`claude_hello_probe_usage_limited` warning for provider-quota results
(previously a hard `claude_hello_probe_failed`).
- `scripts/run-vitest-stable.mjs`: add
`@paperclipai/adapter-claude-local` to `nonServerProjects` so CI runs
the package suites.
- `packages/adapters/claude-local/src/server/execute.remote.test.ts`:
assert both runtime asset syncs (skills and mcp-config); the suite
predated the mcp-config asset.
- `packages/adapters/claude-local/src/server/test.probe.test.ts`:
usage-limit fixture now expects the usage-limited warning; new fixture
covers the genuine transient path (529 overloaded); new tests cover the
token hint and API-key precedence.
- `server/src/__tests__/agent-test-environment-routes.test.ts`: new
tests for the env merge (agent wins on conflict, forbidden key
filtered), missing-binding reporting, and the no-execution-target
fallback path.
- `docs/adapters/claude-local.md`, `docs/adapters/overview.md`: state
the auth-input facts (API key or oauth token wins over stored logins;
snapshot-owns-auth applies when neither is configured) and describe the
environment-aware Test behavior.
## Verification
- `npx vitest run --project @paperclipai/adapter-claude-local` — 131
tests pass (both drifted suites repaired; they fail on master today).
- `npx vitest run
server/src/__tests__/agent-test-environment-routes.test.ts` — 7 tests
pass.
- `node --test ./scripts/__tests__/run-vitest-stable-shard.test.mjs` —
passes with the added project.
- `pnpm typecheck` in `server/` and `packages/adapters/claude-local/` —
clean.
## Risks
- Low risk. The run path is untouched; the probe route change is
additive and inert when the environment has no envVars.
- The probe now performs environment-consumer secret resolution at test
time; access is authorized per binding exactly as at run time, and the
audit consumer is the environment (as before for adapter-config
resolution).
- Enabling the claude-local project in CI adds about 2 seconds of vitest
wall time to the general workspaces group and could surface future
regressions in that package — which is the point.
## Model Used
Claude Fable 5 (`claude-fable-5`), extended thinking enabled, agentic
tool use via Claude Code (CLI).
## 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
> - Agents pick their model from a dropdown in agent config, populated
per-adapter by `listAdapterModels()` → each adapter's live provider
catalog merged over a static fallback list
> - For `claude_local`, newer model ids only reach the dropdown via the
live Anthropic `/v1/models` fetch, which needs a server
`ANTHROPIC_API_KEY`, a <5s round-trip, non-Bedrock mode, and account
entitlement; on any miss it silently falls back to the static `models`
array
> - Claude Sonnet 5 (`claude-sonnet-5`) is a current flagship but was
absent from that static fallback, so it appeared only when live
discovery happened to succeed — i.e. "the newest model doesn't
consistently show up"
> - This pull request adds `claude-sonnet-5` to the `claude_local`
static model list so it is selectable regardless of the live-discovery
path
> - The benefit is a consistent, reliable dropdown that no longer
depends on a flaky live fetch to surface a shipped flagship model
## Linked Issues or Issue Description
No public GitHub issue. The bug is described inline following the
bug-report template:
**What happened**
The `claude_local` agent-config model dropdown intermittently omitted
Claude Sonnet 5. `claude-sonnet-5` was missing from the adapter's static
fallback `models` array (`packages/adapters/claude-local/src/index.ts`),
so it only surfaced when the live Anthropic `/v1/models` discovery
happened to succeed.
**Expected behavior**
Claude Sonnet 5 is a shipped flagship model and should always be
selectable in the dropdown, independent of whether live discovery
succeeds.
**Steps to reproduce**
1. Run the server without a working live Anthropic `/v1/models` path (no
`ANTHROPIC_API_KEY`, Bedrock mode, a discovery timeout, or a cache
miss).
2. Open agent config for a `claude_local` agent and inspect the model
dropdown.
3. Observe that `claude-sonnet-5` is absent because the static fallback
list omitted it.
**Deployment mode**
Self-hosted / local adapter (`claude_local`); the server process reads
`ANTHROPIC_API_KEY` from its environment.
## What Changed
- Added `{ id: "claude-sonnet-5", label: "Claude Sonnet 5" }` to the
`claude_local` static `models` fallback, immediately after
`claude-opus-4-8` (so Opus 4.8 stays the default first option).
- Added an explicit regression assertion in
`server/src/__tests__/adapter-models.test.ts` that `claude-sonnet-5` is
present in the `claude_local` fallback when live discovery is
unavailable.
## Verification
- `pnpm -C server exec vitest run src/__tests__/adapter-models.test.ts
-t "claude fallback"` — **passes** (the new `claude-sonnet-5` assertion
included).
- Reviewed the consuming tests: the fallback test also asserts
`models[0]?.id === "claude-opus-4-8"` (still index 0 — Sonnet 5 is index
1, unaffected); `adapter-registry.test.ts` reads `builtIn?.models`
dynamically, so no exact-array snapshot breaks.
- Change is a single static-data addition plus a test assertion; no
control-flow change.
## Risks
- Low risk. Pure additive change to a fallback list; no control-flow
change. Worst case is an id that a given account isn't entitled to,
which the existing "current"/manual-model UI paths already tolerate.
## Model Used
Claude (Anthropic), model id `claude-opus-4-8` (Opus 4.8), extended
thinking + tool use, run as the Paperclip CTO agent.
## 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)
- [ ] My branch name describes the change (branch is the assigned
execution-workspace branch and cannot be renamed this run)
- [x] I have run tests locally and they pass (server adapter-models
"claude fallback" case)
- [x] I have added or updated tests where applicable (explicit
`claude-sonnet-5` fallback assertion)
- [x] I have updated relevant documentation to reflect my changes (n/a —
no docs reference this list)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (pending CI)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(pending review)
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Local adapters can confine agent processes with filesystem and
network sandbox policies
> - Allowlist confinement must still let an agent reach Paperclip's own
control plane and managed MCP servers
> - The Codex local adapter already marks those runtime-owned endpoints
as trusted, but the Claude local adapter did not
> - As a result, allowlisted Claude runs could not call their own
Paperclip API unless operators duplicated runtime URLs manually
> - This pull request mirrors the trusted-URL wiring in the Claude local
adapter and adds a regression test at the process-execution boundary
> - The benefit is that confined Claude agents retain their required
control-plane access without broadening the operator-managed network
allowlist
## Linked Issues or Issue Description
Refs #447
No exact public issue was found. The underlying bug is:
- **Observed:** with `claude_local` configured for local-process
`networkScope: "allowlist"`, the sandbox options omitted the
runtime-owned Paperclip API and MCP server URLs. Requests to those
endpoints could therefore be denied by confinement.
- **Expected:** Paperclip's own API URL and managed MCP server URLs are
passed as trusted sandbox targets, matching `codex_local` behavior.
- **Steps to reproduce:** configure a local Claude agent with allowlist
network confinement, omit the runtime Paperclip API URL from the
operator allowlist, and have the agent call its injected
`PAPERCLIP_API_URL`.
- **Version:** `ca92f727c5` (`origin/master` at branch creation).
- **Deployment mode:** local-process sandbox confinement in a local
deployment.
## What Changed
- Added the injected Paperclip API URL and runtime MCP server URLs to
`claude_local` sandbox `networkTrustedUrls`, filtering empty values.
- Added a unit test proving allowlist sandbox construction trusts
`PAPERCLIP_API_URL`.
## Verification
- `pnpm exec vitest run
packages/adapters/claude-local/src/server/execute.acp-fallback.test.ts`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
## Risks
- Low risk. The change only affects confined local Claude processes and
trusts runtime-owned endpoints already injected by Paperclip.
- Operator-configured `networkAllowlist` behavior is unchanged; the
added URLs use the sandbox's separate trusted-target path.
> 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 (exact serving snapshot and context-window
size are not exposed), with reasoning, repository inspection, shell tool
use, code editing, and test execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes (not
applicable: behavior parity fix with no user-facing configuration
change)
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Agents pick their model from a dropdown in agent config, populated
per-adapter by `listAdapterModels()` → each adapter's live provider
catalog merged over a static fallback list
> - For `claude_local`, newer model ids only reach the dropdown via the
live Anthropic `/v1/models` fetch, which needs a server
`ANTHROPIC_API_KEY`, a <5s round-trip, non-Bedrock mode, and account
entitlement; on any miss it silently falls back to the static `models`
array
> - Claude Opus 5 (`claude-opus-5`) is generally available — Anthropic
lists it as the recommended model for complex agentic coding and
enterprise work — but it was absent from that static fallback, so it
appeared only when live discovery happened to succeed
> - This pull request adds `claude-opus-5` to the `claude_local` static
model list so it is selectable regardless of the live-discovery path
> - The benefit is a consistent, reliable dropdown that surfaces the
current GA Opus flagship without depending on a flaky live fetch
## Linked Issues or Issue Description
No public GitHub issue. The bug is described inline following the
bug-report template:
**What happened**
The `claude_local` agent-config model dropdown omitted Claude Opus 5.
`claude-opus-5` was missing from the adapter's static fallback `models`
array (`packages/adapters/claude-local/src/index.ts`), so it only
surfaced when the live Anthropic `/v1/models` discovery happened to
succeed.
**Expected behavior**
Claude Opus 5 is a shipped, generally-available flagship (Anthropic's
recommended model for agentic coding) and should always be selectable in
the dropdown, independent of whether live discovery succeeds.
**Steps to reproduce**
1. Run the server without a working live Anthropic `/v1/models` path (no
`ANTHROPIC_API_KEY`, Bedrock mode, a discovery timeout, or a cache
miss).
2. Open agent config for a `claude_local` agent and inspect the model
dropdown.
3. Observe that `claude-opus-5` is absent because the static fallback
list omitted it.
**Deployment mode**
Self-hosted / local adapter (`claude_local`); the server process reads
`ANTHROPIC_API_KEY` from its environment.
## What Changed
- Added `{ id: "claude-opus-5", label: "Claude Opus 5" }` to the
`claude_local` static `models` fallback. Placed after the current
5-family entries and above the legacy `claude-opus-4-7`, so
`claude-opus-4-8` stays the default (index 0) option.
- Added an explicit regression assertion in
`server/src/__tests__/adapter-models.test.ts` that `claude-opus-5` is
present in the `claude_local` fallback when live discovery is
unavailable.
## Verification
- `pnpm -C server exec vitest run src/__tests__/adapter-models.test.ts`
— **17/17 pass**, including the new `claude-opus-5` assertion and the
existing `models[0] === "claude-opus-4-8"` default invariant (unaffected
— Opus 5 is inserted lower in the list).
- Change is a single static-data addition plus a test assertion; no
control-flow change.
## Risks
- Low risk. Pure additive change to a fallback list; no control-flow
change. Worst case is an id a given account isn't entitled to, which the
existing "current"/manual-model UI paths already tolerate.
- Note for reviewers: a sibling PR adds `claude-sonnet-5` to the same
static array (near `claude-opus-4-8`). Both are complementary "refresh
the static list to current GA" changes; whichever merges second may need
a one-line merge resolution in
`packages/adapters/claude-local/src/index.ts` and the matching test
assertion block.
## Model Used
Claude (Anthropic), model id `claude-opus-4-8` (Opus 4.8), extended
thinking + tool use, run as the Paperclip CTO agent.
## 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)
- [ ] My branch name describes the change (branch is the assigned
execution-workspace branch and cannot be renamed this run)
- [x] I have run tests locally and they pass (server adapter-models
suite, 17/17)
- [x] I have added or updated tests where applicable (explicit
`claude-opus-5` fallback assertion)
- [x] I have updated relevant documentation to reflect my changes (n/a —
no docs reference this list)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (pending CI)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(pending review)
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Heartbeat wake payloads and the task-context markdown are the two
channels that deliver an issue's brief into an agent's prompt
> - #10151 fixed wake-prompt-only adapter lanes waking without the issue
description by adding it to the structured wake payload
> - That left the description delivered twice per prompt on lanes that
also inject the task-context markdown, and re-delivered in full on every
resume wake, permanently bloating persistent-session context
> - This pull request makes the task markdown the single description
carrier on lanes that use it, and omits the description from
non-assignment resume deltas on all lanes while keeping it for
assignment-shaped and recovery wakes
> - The benefit is that every lane receives the brief exactly once when
it needs it, and long-lived sessions stop re-paying the full brief in
tokens on every wake
## Linked Issues or Issue Description
Refs #10151
Related prior work: #2883, #8402 (earlier description-delivery attempts
referenced by #10151). I searched the PR list for open work on
wake-payload description handling and found none besides the merged
#10151.
**Bug:** After #10151, adapters that inject the `Paperclip task context`
markdown (ACPX engine lanes, claude-local CLI, hermes server and
gateway) receive the issue description twice in a single prompt — once
in the wake prompt's `Issue description:` block and once in the task
markdown. Separately, resume deltas re-send the full description (up to
12k characters) on every wake even though the persistent session already
received it.
**Expected behavior:** The description appears exactly once per prompt
on every lane, and resume deltas only carry it when the resuming session
may not have seen the brief (assignment-shaped or recovery wakes),
leaving an explicit fetch breadcrumb otherwise.
**Reproduction:** Wake a claude-local or ACPX agent on an issue with a
description and inspect the assembled prompt: the description text
appears in both the wake-payload block and the task-context block. Wake
the same session again via a comment: the full description is present
again in the resume delta.
**Affected version:** Current `master` (with #10151 merged).
**Deployment mode:** Adapter-backed heartbeat execution, local and
sandboxed lanes.
## What Changed
- `renderPaperclipWakePrompt` accepts `suppressIssueDescription`; the
four task-markdown lanes pass it so the task markdown stays the single,
uncapped description carrier there.
- Non-assignment resume deltas omit the description and emit `- issue
description: omitted from this resume delta; fetch the issue if you need
the latest brief`. Assignment-shaped reasons (`issue_assigned`,
`issue_reopened_via_comment`, `issue_recovery_action_restored`,
`issue_tree_restored`) and recovery wakes still deliver the full brief.
- `buildPaperclipTaskMarkdown` gains `includeDescription`; the server
now also publishes `context.paperclipTaskMarkdownCompact` (description
stripped, directives and wake comment kept), and the new
`selectPaperclipTaskMarkdown` helper picks the right variant under the
same resume rules, falling back to the full markdown when no compact
variant exists (version skew safety).
- The wake prompt's description block now carries the same user-authored
trust framing the task markdown already had.
## Verification
- `npx vitest run packages/adapter-utils/src/server-utils.test.ts
packages/adapters/claude-local/src/server/acp.test.ts
packages/adapters/codex-local/src/server/acp.test.ts
server/src/__tests__/heartbeat-context-summary.test.ts` — 137 tests
passed, including new coverage for suppression, resume omission plus
breadcrumb, assignment-shaped resume inclusion, compact-variant
building, variant selection, and an end-to-end ACPX prompt-assembly test
asserting the description appears exactly once on fresh wakes and not at
all on comment resumes.
- `npx vitest run` in `packages/adapters/hermes` — 59 tests passed,
including a gateway execute-level test asserting the brief is sent
exactly once on fresh runs and not re-sent on stable-session resumes.
- `tsc --noEmit` in `packages/adapter-utils`,
`packages/adapters/claude-local`, `packages/adapters/hermes` — clean;
`server` matches the `master` baseline exactly (pre-existing plugin-sdk
resolution errors only, none in touched files).
- Pre-existing failures confirmed identical on clean `master`:
claude-local `execute.remote.test.ts` / `test.probe.test.ts`,
adapter-utils `mcp-isolation.integration.test.ts` (requires a newer
local Claude CLI).
## Risks
- Behavioral shift, prompt-only: a resumed session woken by a comment on
an issue it never handled (rare — assignment wakes normally precede
comment wakes) would not get the inline description; the breadcrumb plus
the standard issue-fetch path covers it.
- Additive context key (`paperclipTaskMarkdownCompact`); older adapters
ignore it and newer adapters fall back to the full markdown when it is
absent, so mixed-version deployments degrade to current behavior.
- No schema, migration, or API changes; the structured wake-payload JSON
shape is unchanged.
- Known follow-up deliberately out of scope: openclaw embeds the raw
wake-payload JSON (which still contains the description) in prompt text
for machine parsing. The hermes-gateway lane is handled: it detects
stable-session resumes (issue/agent session-key strategy plus a stored
prior session id), compacts the task markdown, and omits the description
from its prompt-embedded JSON copy.
> This is a focused correctness/efficiency fix to existing wake plumbing
and does not overlap with planned roadmap feature work.
## Model Used
- Anthropic Claude Fable 5 (`claude-fable-5`), extended thinking
enabled, with repository tool use, shell execution, and local test
execution via Claude Code.
## 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)
- [ ] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
(execution-workspace branch, same convention as merged #10202)
- [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
(code-level docs; no user-facing docs affected)
- [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
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is a control plane that orchestrates AI agents and adapter
execution for human operators.
> - Agents run across local and remote execution contexts, and
reliability in remote sessions depends on consistent adapter
bootstrapping.
> - The ACP path must prepare per-adapter runtime homes so managed
credentials and config are available in sandboxed runner environments.
> - Before this change, the new remote ACP lane did not yet consistently
stage managed-home paths for all affected adapters or restore Codex auth
state on teardown.
> - We added a shared per-adapter seam in the ACP engine, then wired
Codex, Claude, and Gemini remote lanes to seed managed homes and remap
to in-sandbox locations.
> - Codex additionally reuses the existing atomic auth restore flow to
copy auth back on teardown, matching CLI behavior.
> - This improves remote runner parity with existing CLI behavior and
avoids credential drift in shared-code-path executions.
## Linked Issues or Issue Description
- This change continues the ACP remote managed-home work by completing
per-adapter remote bootstrapping and Codex auth restore behavior for the
remote ACP lane.
- It specifically covers: `acpx-engine`, `codex-local`, `claude-local`,
and `gemini-local`.
- Related prior work in this repo: PR #10070.
## What Changed
- Add a per-adapter remote managed-home seam
(`prepareRemoteManagedHome`) in `acpx-engine` and thread it through ACP
execution options.
- Implement Codex ACP preparation to:
- stage `CODEX_HOME` (auth/config/skills) into a sandboxed remote home,
- repoint `CODEX_HOME` to the in-sandbox path,
- and wire teardown copy-back through the existing managed-auth restore
path.
- Implement Claude ACP preparation to seed a sanitized `config-seed`
into `CLAUDE_CONFIG_DIR` and remap that directory to the sandbox root.
- Implement Gemini ACP preparation to seed `~/.gemini/skills`, set
`HOME` to managed runtime root, and preselect API-key auth in
`settings.json`.
- Keep local and runner-less ACP→CLI behavior unchanged by only invoking
the remote managed-home seam when running in remote ACP mode.
- Preserve existing authorization and activity boundaries in the shared
engine and adapter layers.
## Verification
- `git log --oneline
origin/master..origin/feat/acp-remote-managed-home-seed` confirms only
the expected 4 commits.
- `tsc --noEmit` is clean in `adapter-utils`, `codex-local`,
`claude-local`, and `gemini-local`.
- Vitest selection used during validation passed (120 tests across the
ACP-related suites).
## Risks
- If remote sandbox teardown occurs after token rotation but before
restore timing, Codex credentials can become stale and require re-auth
on next startup.
- Partial provisioning of managed-home assets would cause adapter
bootstrap failures in runner-backed ACP sessions.
- This change is scoped to execution-path behavior; it should not affect
CLI behavior.
## Model Used
None — human-authored.
## 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: Harold Kim <harold@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The shared ACP engine
(`packages/adapter-utils/src/acpx-engine/execute.ts`) is responsible for
launching local and remote agent processes via the ACP protocol
> - On runner-backed remote sandbox (Daytona) targets, `buildRuntime`
never crossed the CLI's staging seam: it never called
`prepareAdapterExecutionTargetRuntime`, left `runtimeRootDir: null` in
both the paperclip and process-session bridges, and handed the agent the
**HOST filesystem path** as the `session/new` cwd — meaning
Claude/Gemini silently operated on a path that does not exist inside the
sandbox (Codex additionally crashes on its HOST home path, addressed in
a follow-up PR)
> - The fix must cross the staging seam for remote sandboxes, thread the
real `runtimeRootDir` through both bridges, and bind the in-sandbox
workspace path as the session cwd — without touching local ACP runs or
the runner-less ACP→CLI fallback
> - This pull request introduces a `stageAcpRemoteRuntime` helper that
calls `prepareAdapterExecutionTargetRuntime` for runner-backed remote
runs, captures `{ workspaceRemoteDir, runtimeRootDir, assetDirs,
restoreWorkspace }`, and reuses the in-sandbox `workspaceRemoteDir` as
the single `sessionCwd` across `session/new`, the fingerprint,
compatibility check, persistence, `ensureSession`, the process-session
bridge cwd, and the error path
> - The benefit is that remote ACP runs now operate in the correct
in-sandbox cwd and receive a non-null `runtimeRootDir` in both bridges —
fixing silent wrong-cwd degradation for Claude/Gemini on Daytona
targets; this is PR 1 of 3 and seeds no credential material
## Linked Issues or Issue Description
No public GitHub issue exists for this change. Inline description
follows the feature request template:
### Subsystem affected
packages/adapters — agent adapter implementations
### Problem or motivation
The shared ACP engine
(`packages/adapter-utils/src/acpx-engine/execute.ts`) never crossed the
CLI's staging seam on runner-backed remote sandbox targets. It never
called `prepareAdapterExecutionTargetRuntime`, always passed
`runtimeRootDir: null` to both the paperclip and process-session
bridges, and handed the agent the **HOST filesystem path** as the ACP
`session/new` cwd. As a result, Claude and Gemini silently operated on a
cwd that does not exist inside the sandbox; Codex crashed with a fatal
error on the HOST `CODEX_HOME` path (that crash is in a follow-up PR).
### Proposed solution
Gate on `usesRunnerBackedSandbox` (`kind === "remote" && transport ===
"sandbox" && runner`). For runs that pass the gate, call
`prepareAdapterExecutionTargetRuntime` via a new `stageAcpRemoteRuntime`
helper that ships the workspace into the sandbox and captures `{
workspaceRemoteDir, runtimeRootDir, assetDirs, restoreWorkspace }`.
Thread the real `runtimeRootDir` into both bridges. Bind a single
`sessionCwd` (the in-sandbox `workspaceRemoteDir`) and use it at every
cwd-keyed session site (`session/new`, fingerprint, compat, persist,
`ensureSession`, process-session bridge, error path) so a warm/resumable
session is reused rather than invalidated. For local runs and the
runner-less ACP→CLI fallback, `sessionCwd` resolves to the HOST cwd —
byte-identical to the previous behavior.
### Alternatives considered
Patching each per-adapter bridge individually — rejected because the bug
is in the shared engine layer and the fix belongs there so all three
adapters (Codex, Claude, Gemini) benefit without per-adapter
duplication.
### Roadmap alignment
Internal correctness fix enabling remote ACP to work as designed; no new
user-facing features. This is PR 1 of 3 in a sequential chain: PR 1
(this PR) stages the workspace and routes the cwd; PR 2 adds per-adapter
home seeding and copy-back; PR 3 wires session-lifecycle restore.
## What Changed
- **`packages/adapter-utils/src/acpx-engine/execute.ts`** — added
`stageAcpRemoteRuntime` helper that calls
`prepareAdapterExecutionTargetRuntime` for runner-backed remote
sandboxes and returns `{ sessionCwd, runtimeRootDir, stagedRuntime }`;
`buildRuntime` now uses this helper to derive `sessionCwd` (in-sandbox
`workspaceRemoteDir` for remote; HOST cwd unchanged for
local/runner-less) and threads the real `runtimeRootDir` to both the
paperclip bridge and process-session bridge; `stagedRuntime` is stashed
for the follow-up credential PR
- **`packages/adapter-utils/src/acpx-engine/execute.test.ts`** — new
engine-level unit tests: staging seam crossed with no credential asset,
non-null `runtimeRootDir` in both bridges, in-sandbox `session/new` cwd,
warm-handle reuse after the cwd change, local-unchanged; 60 tests green
- **`packages/adapters/codex-local/src/server/acp.test.ts`** — new
per-adapter test: runner-backed remote asserts `ensureSession` cwd ==
`workspaceRemoteDir`; runner-less sandbox falls back to CLI
- **`packages/adapters/claude-local/src/server/acp.test.ts`** — same
per-adapter coverage for Claude
- **`packages/adapters/gemini-local/src/server/acp.test.ts`** — same
per-adapter coverage for Gemini
## Verification
- `adapter-utils` typecheck clean; `codex/claude/gemini-local` typecheck
clean
- Engine units (`acpx-engine/execute.test.ts`): 60/60 green — staging
seam crossed with no credential asset, non-null `runtimeRootDir` to both
bridges, in-sandbox `session/new` cwd, warm-handle reuse after cwd
change, local unchanged
- Per-adapter ACP test suites (`codex/claude/gemini-local`
`acp.test.ts`): 103 tests green — runner-backed remote asserts
`ensureSession` cwd == `workspaceRemoteDir`; runner-less sandbox falls
back to CLI
- CI green on PR (in progress)
## Risks
This is PR 1 of 3 in a strictly sequential chain; it seeds **no
credential material** (no `assets`, no `installCommand`). The
per-adapter home seeding is deferred to PR 2, which consumes the
`stagedRuntime` object stashed here. The `restoreWorkspace` callback is
carried on `stagedRuntime` for PR 3's session-lifecycle wiring (see the
`stageAcpRemoteRuntime` function comment). Local ACP runs and the
runner-less ACP→CLI fallback are untouched — `sessionCwd` resolves to
the HOST cwd for those paths, preserving existing behavior. The
`stageAcpRemoteRuntime` helper is gated on `usesRunnerBackedSandbox`, so
there is no regression risk for local or CLI-lane runs.
## Model Used
Claude Sonnet 4.6 (`claude-sonnet-4-6`) via Paperclip ACPX engine —
extended context, tool use enabled, co-authored with Paperclip agent
orchestration.
## 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/...`,
`feat/...`) and contains no internal Paperclip ticket id or
instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Harold Kim <harold@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Agent runs get their environment from user/adapter/project/routine
env bindings resolved by the server heartbeat, plus `PAPERCLIP_*`
runtime vars (identity, wake, workspace, API access) injected by the
harness
> - The heartbeat stripped **every** `PAPERCLIP_`-prefixed binding
before resolution, so legitimately user-named keys (e.g. cloud provider
token bindings like `PAPERCLIP_CLOUD_PROD_PROVIDER_RAILWAY_*`) were
silently dropped and never reached the run env
> - At the same time, several adapters honored an explicitly configured
`PAPERCLIP_API_KEY` over the harness-minted run token, which is exactly
the one key config must never control
> - This pull request replaces the blanket prefix strip with a precise
three-rule policy: never accept `PAPERCLIP_API_KEY` from config, always
let harness-assigned runtime vars win, and let every other
`PAPERCLIP_*`-named user binding flow through
> - The benefit is that user secrets with a `PAPERCLIP_`-style name work
like any other binding, while runtime identity and API credentials stay
fully harness-controlled
## Linked Issues or Issue Description
**Bug description** (no public issue exists):
- **What happened:** Env bindings whose key starts with `PAPERCLIP_`
(e.g. a cloud provider token a user deliberately named
`PAPERCLIP_CLOUD_PROD_PROVIDER_RAILWAY_TOKEN`) were silently stripped by
the server before secret resolution, so the spawned agent never received
them. No error, no access event — the variable just never appeared.
- **Expected behavior:** A user-named `PAPERCLIP_*` binding should reach
the run env unless the harness itself uses that key. Only
`PAPERCLIP_API_KEY` should be categorically rejected, and
harness-assigned runtime vars (`PAPERCLIP_RUN_ID`, `PAPERCLIP_AGENT_ID`,
wake/workspace vars, …) should always win over config.
- **Steps to reproduce:** Configure an agent/project env binding named
`PAPERCLIP_<ANYTHING>` (plain or secret_ref), run a heartbeat, and
inspect the spawned process env — the key is absent.
- **Deployment mode:** local server, any local adapter.
Related prior PRs (different, save-time/API-layer blanket-ban approach;
this PR supersedes that direction with a runtime allow-except-reserved
policy): Refs #8239, Refs #8439.
## What Changed
- `server/src/services/heartbeat.ts`: the pre-resolution strip now
removes only `PAPERCLIP_API_KEY` (hard denylist) instead of every
`PAPERCLIP_`-prefixed binding; other `PAPERCLIP_*` keys flow into
binding resolution. Low-trust inline-sensitive-env checks now also cover
those keys.
- `packages/adapter-utils/src/server-utils.ts`: new
`isForbiddenConfigEnvKey()` helper; the shared
`refreshPaperclipWorkspaceEnvForExecution` merge drops
`PAPERCLIP_API_KEY` from config and keeps harness-assigned `PAPERCLIP_*`
keys authoritative.
- `packages/adapter-utils/src/acpx-engine/execute.ts`: removed the
explicit-`PAPERCLIP_API_KEY`-from-config allowance; the run token
(`authToken`) is now always applied; config `PAPERCLIP_API_KEY` is
ignored.
- All local adapters (`claude-local`, `codex-local`, `cursor-local`,
`gemini-local`, `grok-local`, `opencode-local`, `pi-local`) plus
`cursor-cloud`, `hermes`, and the server `process` adapter: removed
`hasExplicitApiKey`-style allowances so the harness token always wins,
and guarded the remaining unguarded env-merge loops (claude-local inline
loop, process adapter) with the same policy.
- Tests updated/added: heartbeat binding-strip test now asserts the
three-rule policy; adapter-utils merge tests assert the
`PAPERCLIP_API_KEY` ban and `PAPERCLIP_*` pass-through; acpx engine
tests moved credential fixtures to `authToken` and assert config
`PAPERCLIP_API_KEY` is ignored while other `PAPERCLIP_*` config keys
forward and still bust the session fingerprint on rotation.
## Verification
- `pnpm vitest run packages/adapter-utils/src/server-utils.test.ts
packages/adapter-utils/src/acpx-engine/execute.test.ts` — 127 passed
- `pnpm vitest run server/src/__tests__/heartbeat-project-env.test.ts
server/src/__tests__/heartbeat-local-environment.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/codex-local-execute.test.ts
server/src/__tests__/cursor-local-execute.test.ts
server/src/__tests__/gemini-local-execute.test.ts` — 68 passed
- Adapter package execute suites and the server tests touching API-key
fixtures (`heartbeat-run-log`, `redaction`,
`effective-run-config-fingerprints`, `agent-permissions-routes`) —
green. Three pre-existing sandbox/SSH fixture failures reproduce
identically on clean `master` on this host and are unrelated.
- `pnpm --filter <pkg> typecheck` for server, adapter-utils, and all
nine touched adapter packages — all pass.
## Risks
- Behavioral change: a deployment that relied on configuring a static
`PAPERCLIP_API_KEY` in adapter config env loses that override — by
design; the harness-minted run token is now the only source. When no run
token exists, no API key is injected at all.
- `PAPERCLIP_*`-named user bindings now reach binding resolution and run
envs; a key that collides with a harness runtime var is still discarded
at merge time, so runtime identity/wake/workspace vars cannot be
spoofed.
- Low risk otherwise: no migrations, no API surface changes.
## Model Used
- Claude Fable 5 (`claude-fable-5`, Anthropic Claude 5 family,
Mythos-class tier), extended thinking enabled, agentic tool use (file
edits, shell, test runner) via Claude Agent SDK.
## 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
- [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
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is the open source control plane people use to organize,
govern, and understand AI-agent work
> - Operators need concise, current status views across projects and
execution workspaces without manually reading every issue and run
> - Paperclip already has auditable issues, documents, built-in agents,
routines, and live run events, but no first-class summary-slot workflow
connecting those systems
> - A built-in Summarizer can generate status prose through ordinary
governed tasks while summary slots provide stable, revisioned
destinations for that output
> - The UI needs to show current summaries, generation progress,
failures, revisions, and streaming draft status in the places operators
already work
> - This pull request adds the end-to-end summary-slot data, API, agent,
orchestration, and UI surfaces behind an experimental setting
> - The benefit is decision-oriented status context that remains
company-scoped, auditable, retryable, and inexpensive by default
## Linked Issues or Issue Description
No public GitHub issue exists for this feature.
**Problem**
Operators currently have to reconstruct project and workspace status by
reading many issues, runs, and comments. This makes it hard to identify
decisions, review queues, recent work, and the next event worth
watching.
**Proposed capability**
Add an experimental summary system with revisioned summary slots for
projects and workspaces, a paused-by-default built-in Summarizer agent,
governed generation tasks, live draft status, and reusable UI cards.
**Expected behavior**
- Summary data remains company-scoped and revisions remain auditable.
- Generation runs through normal issue/agent orchestration and
deduplicates active requests.
- Only the linked built-in Summarizer generation task can author a slot
revision.
- Operators can generate, retry, inspect revisions, and follow draft
progress from project and workspace views.
- The feature remains opt-in and background generation remains paused by
default.
## What Changed
- Added summary-slot schema, idempotent migrations, shared contracts,
validators, API paths, and service tests.
- Added company-scoped summary-slot routes for reading revisions,
requesting generation, and guarded Summarizer writes with activity
logging.
- Added terminal generation finalization, failure reasons, assignment
wakeups, and orchestration integration.
- Added the paused-by-default built-in Summarizer bundle, low-cost
runtime defaults, status-summarization skill, and stale-summary routine.
- Added summary cards, revision selection, retry/configuration states,
live draft streaming, transcript chunk handling, and project/workspace
integrations.
- Updated Claude local parsing for streamed status output and expanded
server, adapter, shared, database, catalog, and UI coverage.
## Verification
- `pnpm -r typecheck`
- `pnpm exec vitest run packages/db/src/summary-slots-schema.test.ts
packages/shared/src/summary-slot.test.ts
server/src/__tests__/summary-slot-routes.test.ts
server/src/__tests__/summary-slots.test.ts
server/src/__tests__/built-in-agents.test.ts
ui/src/components/SummarySlotCard.test.tsx
ui/src/components/SummarySlotCard.status.test.tsx
ui/src/components/useSummaryDraftStream.test.tsx
ui/src/lib/summary-draft-stream.test.ts
ui/src/lib/run-log-chunks.test.ts
ui/src/context/LiveUpdatesProvider.hook.test.tsx` — 113 tests passed
- `pnpm test:run` — server and UI suites passed; one CLI AWS doctor test
was affected by inherited `AWS_ACCESS_KEY_ID`/`AWS_SECRET_ACCESS_KEY`,
and passed when those host credentials were removed
- `pnpm exec vitest run cli/src/__tests__/secrets.test.ts` with
inherited AWS credential variables removed — 8 tests passed
- `pnpm build`
- `pnpm check:token-gates` currently reports nine `#9627` comment
references introduced by current `master`; none are in this PR diff
## Risks
- Database risk is limited by incrementally ordered, idempotent
migrations and migration safety checks.
- Summary generation creates normal issues/runs, so misconfiguration can
produce failed slots; the UI exposes retryable failure reasons and agent
configuration entry points.
- Streaming draft parsing depends on the documented `STATUS:` protocol;
final persisted revisions remain the source of truth.
- The feature is experimental, opt-in, and its built-in routine is
paused with no background token spend by default.
> 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 GPT-5.3 Codex with reasoning, repository tool use, code
execution, GitHub CLI, and Paperclip control-plane integration. Earlier
branch commits also record Claude model co-authorship where applicable.
## 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>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is the open source control plane people use to coordinate
AI-agent companies and their work.
> - Its recovery subsystem detects stranded issue execution and decides
whether to retry, escalate, or request operator intervention.
> - The existing recovery path used a mostly generic owner ladder and
generic execution contract, so transient failures could wake a manager
who then performed the deliverable instead of repairing and returning
the task.
> - Provider quota failures also entered the same takeover path even
when the correct action was to wait for capacity and retry the original
assignee.
> - Recovery actions already retain the source owner and evidence needed
to choose a cause-specific route, render a scoped contract, and measure
whether work was handed back.
> - This pull request adds a cause-keyed recovery playbook, propagates
its contract through every built-in adapter, and makes resolved recovery
actions return work to the original owner by default.
> - The benefit is bounded self-recovery that preserves task ownership,
avoids needless management takeover, and makes recovery outcomes
observable.
## Linked Issues or Issue Description
No matching public GitHub issue was found.
Related recovery work was reviewed but is not duplicated here: #9630
restores bounded recovery continuations, #8807 changes one
assignee-ranking case, and #9404 records runtime-failure transition
evidence. This change instead introduces cause-specific routing and
recovery contracts across the recovery lifecycle.
### What happened?
When an issue became stranded, recovery generally selected an owner
through the same fallback ladder and rendered the normal execution
contract. That made the recovery wake look like ordinary deliverable
work, even when the correct action was to retry the original agent,
repair its runtime, or wait for a provider quota reset.
### Expected behavior
Recovery should select a response by failure cause, tell the recipient
to recover rather than complete the deliverable, suppress takeover wakes
for provider quota waits, and return repaired work to its original
assignee unless the recovery owner explicitly completes it.
### Actual behavior
Recovery could escalate transient failures to management, omit the
cause-specific next action from the wake, and leave the recovery owner
assigned after the runtime problem was resolved.
### Impact
The generic path creates avoidable management work, ownership churn, and
budget consumption while obscuring whether recovery successfully
returned work to the responsible agent.
## What Changed
- Added cause-keyed routing for process loss, missing disposition,
provider quota limits, Codex output inactivity, workspace validation
failures, and fallback recovery causes.
- Added recovery-scoped wake rendering that replaces the generic
execution contract with the failure summary, original assignee, attempt
count, next action, and cause-specific playbook instruction.
- Propagated the structured recovery contract through all built-in
adapter execution paths, including Hermes local and gateway adapters.
- Added provider-quota wait monitoring so capacity failures schedule the
original assignee instead of enqueueing a takeover wake.
- Added hand-back behavior and `handed_back` / `owner_completed` outcome
accounting when recovery actions are resolved.
- Added focused routing, renderer, quota-monitor, and hand-back
regression coverage plus implementation-spec documentation.
## Verification
- `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-workspace-branch-containment.test.ts
server/src/__tests__/issue-recovery-actions.test.ts`
- 4 test files passed; 194 tests passed.
- Targeted `pnpm --filter ... typecheck` across
`@paperclipai/adapter-utils`, `@paperclipai/shared`,
`@paperclipai/server`, `@paperclipai/ui`, and all nine changed adapter
packages.
- 13 affected workspace packages passed typecheck.
- `pnpm check:token-gates`
- All UI token gates passed.
## Risks
- Recovery routing behavior changes for stranded work, so an incorrectly
classified cause could select a different recipient than before;
fallback causes retain the existing management ladder.
- Provider quota detection depends on structured failure evidence and
conservative text matching; unmatched failures continue through fallback
recovery.
- Adapter prompt plumbing changes across built-ins, covered by shared
renderer tests and compile-time call signatures.
> 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 exact model ID `gpt-5.6-sol`, using reasoning, tool
use, and code execution. The runtime does not expose its configured
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 is the open source app people use to manage AI agents for
work
> - Governed MCP access spans contracts, runtime enforcement, adapters,
UI surfaces, and operator verification
> - The parity reference PR #9534 is too large for effective automated
or human review
> - The feature therefore needs a linear stack whose individual diffs
stay below the 100-file review limit
> - This pull request is split 4/8 and focuses on gateway runtime, Smoke
Lab, plugins, and server wiring
> - The benefit is a standalone, testable review boundary while
preserving byte-for-byte parity at the top of the stack
## Linked Issues or Issue Description
- Related parity reference: #9534
- Problem: The policy core needs runtime execution, endpoint guards,
route registration, heartbeat integration, and adapter MCP injection to
become operational.
- Proposed solution: Adds the remaining server routes/wiring/consumers,
runtime tests, adapter-utils MCP contracts, and Claude/Codex injection
implementations required by the server layer.
- Alternatives considered: keeping #9534 as one 403-file review, or
rewriting the feature to manufacture seams; both were rejected in favor
of path extraction plus compile-driven boundary moves.
- Roadmap alignment: this advances the existing governed MCP/tool-access
work already represented by #9534; it does not introduce a separate
roadmap initiative.
- Stack position: base branch is `pap10341-split/03-server-tool-access`.
- Merge policy: merge bottom-up, in order, only after the complete
eight-PR stack has been reviewed and the top-of-stack parity gate
remains empty.
- Requested review: SecurityEngineer for gateway, endpoint guard, token
issuance, and runtime wiring; Greptile on every PR.
## What Changed
- Adds the remaining server routes/wiring/consumers, runtime tests,
adapter-utils MCP contracts, and Claude/Codex injection implementations
required by the server layer.
- Keeps this PR below 100 changed files and independently typecheckable.
- Preserves the final tree from #9534 when combined with the other seven
stack levels.
## Verification
- `pnpm typecheck`
- Changed server test set — 26 files, 382 tests passed
- Affected server adapter tests — 38 tests passed after concrete adapter
boundary move
- Adapter-utils and Codex focused tests — 76 tests passed
## Risks
- Remote endpoint validation, token handling, and runtime supervision
are security-sensitive and can fail closed or deny legitimate access if
misconfigured.
- Stack risk: merging out of order can expose incomplete layers;
mitigate by following the documented bottom-up merge policy.
- Parity risk: later edits to an intermediate branch can drift from
#9534; mitigate by re-running the empty top-of-stack diff before merge.
> 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, exact model ID `gpt-5.4`; runtime-managed context
window; medium reasoning with repository, shell, Git, GitHub CLI, and
code-execution tools enabled.
## 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] Internal references are omitted except the execution-plan link
explicitly required for this coordinated split stack
- [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
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Stack Coordination
- Internal execution plan:
[PAP-13874](/PAP/issues/PAP-13874#document-plan)
- Parity reference: #9534
- Stack: #9556 → #9557 → #9558 → #9559 → #9560 → #9561 → #9562 → #9563
- Merge bottom-up only after full-stack review and an empty parity diff
at #9563.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source control plane people use to manage AI
agents for work.
> - Local coding adapters currently spawn their CLI processes directly
on the Paperclip host.
> - CLI-native approval and sandbox flags do not provide a reliable host
filesystem or network boundary.
> - An agent can therefore inspect unrelated host files or fetch
external material when an operator needs stronger isolation.
> - The confinement must stay opt-in so existing local adapter behavior
does not change unexpectedly.
> - This pull request adds a shared Linux Bubblewrap spawn layer for
workspace filesystem and deny/allowlist network scopes.
> - The benefit is enforceable defense in depth around Codex and Claude
local runs while preserving explicit provider connectivity.
## Linked Issues or Issue Description
### What happened?
`codex_local` and `claude_local` processes could read arbitrary host
paths and make unrestricted outbound network requests because Paperclip
did not impose a spawn-level boundary.
### Expected behavior
Operators can opt into a workspace-only filesystem view and either deny
network egress or allow exact provider/API hosts, independently of CLI
approval flags.
### Steps to reproduce
1. Run current `master` on Linux and configure a Codex or Claude local
adapter.
2. Ask the agent to read a canary file outside its active workspace.
3. Ask the agent to `curl` a public host.
4. Observe that both operations succeed without a Paperclip-level
confinement option.
### Environment
- Paperclip commit: `c36f1a4af` / current `master` base.
- Deployment mode: Linux local dev or self-hosted server.
- Installation: built from source.
- Adapters: Codex and Claude Code.
- Database: not related.
## What Changed
- Added a shared Bubblewrap process wrapper with opt-in
`filesystemScope: "workspace"`, managed/extra path mounts, private
`/tmp`, and Linux-only validation.
- Added `networkScope: "deny" | "allowlist"`; both use a private network
namespace, while allowlist mode exposes an exact-host HTTP(S) proxy over
a Unix-socket bridge.
- Wired Codex and Claude local CLI execution through the wrapper and
forced scoped auto runs onto the CLI lane because ACP processes are not
covered.
- Added unit and gated Bubblewrap canaries for outside-file denial,
workspace writes, direct network denial, allowlisted forwarding, and
rejected destinations.
- Documented both scopes, provider allowlist examples, Bubblewrap
requirements, and default-off behavior.
## Verification
- `pnpm exec vitest run
packages/adapter-utils/src/local-process-sandbox.test.ts
packages/adapters/codex-local/src/server/acp.test.ts
packages/adapters/claude-local/src/server/acp.test.ts` — 34 passed, 4
gated Bubblewrap tests skipped by default.
- `pnpm --filter @paperclipai/adapter-utils typecheck`
- `pnpm --filter @paperclipai/adapter-codex-local typecheck`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/adapter-utils build`
- `pnpm --filter @paperclipai/adapter-codex-local build`
- `pnpm --filter @paperclipai/adapter-claude-local build`
- Attempted the gated tests with a vendored Bubblewrap binary; this
container blocks unprivileged namespace setup (`setting up uid map:
Permission denied` / loopback `RTM_NEWADDR: Operation not permitted`),
so kernel-level execution remains for CI or a namespace-enabled Linux
host.
## Risks
- Bubblewrap must be installed and unprivileged user/mount/network
namespaces must be enabled on the host; scoped runs fail clearly if the
prerequisite is missing.
- Allowlist mode depends on the coding CLI honoring standard
`HTTP_PROXY` / `HTTPS_PROXY` variables; custom providers must list every
required exact hostname and port.
- Exact-host allowlists intentionally reject wildcards, which is safer
but may require operators to enumerate multi-host provider setups.
- No behavior changes unless an operator enables `filesystemScope` or
`networkScope`.
> This aligns with the ROADMAP direction toward safer remote and
sandboxed agent environments and does not duplicate an open PR or issue
found in the repository search.
## Model Used
- OpenAI GPT-5.5 (`gpt-5.5`) via Codex CLI, with reasoning, repository
tool use, shell execution, code editing, and test execution. The serving
context-window size is not exposed to the agent.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source control plane people use to manage
AI-agent companies
> - Budgets and spend telemetry are control-plane safety features, not
just reporting
> - Local Codex and Claude adapters can execute through either ACP or
their native CLI engines
> - The ACP lane records usage and reported cost, but CLI JSON output
often reports tokens without a price
> - The CLI lane was either losing per-run usage semantics or coercing
missing cost to zero, making real usage indistinguishable from a
genuinely free run
> - This pull request preserves CLI usage as per-run totals and records
token-bearing runs without a reported price as explicitly unpriced
ledger events
> - The benefit is accurate usage accounting and a visible pricing gap
instead of silently misleading zero-cost telemetry
## Linked Issues or Issue Description
Refs #9471
Refs #9230
**Bug description**
A `codex_local` run using the CLI engine can emit a final
`turn.completed` event with millions of input tokens and tens of
thousands of output tokens while the agent's spend ledger remains
indistinguishable from a true zero-usage, zero-cost run. Claude CLI
output has the same missing-price edge case.
**Expected behavior**
Token-bearing CLI runs should persist their usage. If the adapter
reports a price, the ledger should record it as reported; if the CLI
reports usage but no price, the ledger should explicitly mark the event
as unpriced rather than silently treating missing price data as a
reported `$0` cost.
**Reproduction shape**
1. Configure `codex_local` with `engine: cli`.
2. Run a task that produces a `turn.completed` usage payload.
3. Observe token usage in the run stream.
4. Before this change, missing price data is represented as ordinary
zero-cost spend and the CLI usage basis is not consistently propagated.
## What Changed
- Mark Codex and Claude native CLI usage totals as `per_run` and
propagate that basis through success and failure results.
- Stop coercing missing Claude CLI cost to `0`.
- Add `cost_status` to cost events with `reported` and `unpriced`
values, including an idempotent migration and shared validation/types.
- Persist token-bearing runs without a reported price as `unpriced`
ledger events while retaining zero cents until an authoritative price
exists.
- Add parser, execute-path, heartbeat-accounting, and cost-service
regression coverage for both local CLI adapters.
- Document the cost-status invariant and CLI accounting behavior.
## Verification
- `pnpm exec vitest run
packages/adapters/codex-local/src/server/parse.test.ts
packages/adapters/claude-local/src/server/parse.test.ts
server/src/__tests__/codex-local-execute.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/heartbeat-cost-accounting.test.ts
server/src/__tests__/costs-service.test.ts` — 6 files / 102 tests
passed.
- `pnpm --filter @paperclipai/shared typecheck`
- `pnpm --filter @paperclipai/db typecheck` — includes migration
numbering and safety checks.
- `pnpm --filter @paperclipai/adapter-codex-local typecheck`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/server typecheck`
## Risks
- Existing cost rows default to `reported`, preserving current
interpretation; only new token-bearing events with absent cost are
marked `unpriced`.
- This change does not invent model pricing. Budget hard stops still
cannot charge an unknown amount, but operators and evals can now
distinguish missing pricing from a genuinely reported zero cost.
- Consumers that enumerate cost-event fields should tolerate the
additive `costStatus` field.
> 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, exact model `gpt-5.3-codex`, with repository tool use
and code execution; default reasoning mode.
## 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 control plane for running and governing
AI-agent companies.
> - Adapter executions feed token usage, billing identity, and run cost
into the control plane's spend telemetry.
> - The default ACP execution lane for local Claude and Codex adapters
did not propagate per-turn usage or cost, so paid runs could be recorded
with zero spend and no tokens.
> - Claude CLI result events could also undercount output tokens by
reading only the main-loop usage block instead of the complete per-model
ledger.
> - The shared executor needs to distinguish per-run usage from
session-cumulative usage so the server does not apply the wrong delta
heuristic.
> - This pull request captures ACP usage and cumulative-cost deltas,
resolves adapter billing identity, uses Claude's complete model-usage
ledger, and preserves per-run usage in server normalization.
> - The benefit is accurate token and cost accounting across the default
paid Claude and Codex execution paths.
## Linked Issues or Issue Description
### What happened?
Paid `claude_local` and `codex_local` runs using the default ACP engine
can complete successfully while the control plane records zero or null
cost and missing token usage. Claude CLI result parsing can additionally
undercount output tokens when subagent or sidechain usage is present.
### Steps to reproduce
1. Run a paid Claude or Codex local adapter through the ACP engine.
2. Complete a turn that reports usage and cumulative cost through ACP
status/events.
3. Inspect the execution result and normalized run telemetry.
### Expected behavior
The execution result contains per-turn token usage, a per-run USD cost
delta, and the correct billing identity. Server normalization records
those per-run values without applying a session-cumulative delta a
second time.
### Actual behavior before this change
ACP execution results returned no usage and `costUsd: null` with unknown
billing. The server therefore recorded zero spend and no tokens for paid
runs. Claude CLI parsing could use an incomplete usage block.
## What Changed
- Capture ACP usage from runtime status and `usage_update` events,
reporting it as `usageBasis: per_run`.
- Convert agent-reported cumulative ACP cost into a per-turn delta,
including counter-reset and no-report safeguards.
- Add a shared billing-identity resolver and map Claude and Codex
authentication/provider modes to control-plane billing types.
- Prefer Claude result-event `modelUsage` totals so subagent and
sidechain tokens are included.
- Skip the server's session-cumulative usage delta when an adapter
explicitly reports per-run usage.
- Add regression coverage for usage capture, event fallback, cost
resets, stale reports, billing identities, model-usage totals, and
server spend normalization.
## Verification
- `pnpm exec vitest run
packages/adapter-utils/src/acpx-engine/execute.test.ts
packages/adapters/claude-local/src/server/parse.test.ts
packages/adapters/claude-local/src/server/acp.test.ts
packages/adapters/codex-local/src/server/acp.test.ts
server/src/__tests__/costs-service.test.ts
server/src/__tests__/monthly-spend-service.test.ts` — 6 files, 126 tests
passed.
- `pnpm --filter @paperclipai/adapter-utils typecheck` — passed.
- `pnpm --filter @paperclipai/adapter-claude-local typecheck` — passed.
- `pnpm --filter @paperclipai/adapter-codex-local typecheck` — passed.
- `pnpm --filter @paperclipai/server typecheck` — passed.
- A broader Claude-local suite has a pre-existing rate-limit
classification failure in `test.probe.test.ts`; it also fails on clean
`master` and is unrelated to this change.
## Risks
- Cost reporting depends on the agent's cumulative counter semantics;
reset handling falls back to the post-turn amount and is covered by
regression tests.
- Incorrect billing-mode inference could misclassify spend;
provider/auth mappings mirror each adapter's existing CLI behavior and
have focused tests.
- The new `usageBasis` contract changes server normalization only when
adapters explicitly opt into `per_run`; existing adapters retain prior
behavior.
- No database migration, workflow, lockfile, or UI changes are included.
> 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
- Implementation commit: Anthropic Claude Fable 5, tool-enabled coding
workflow (exact context window and runtime configuration were not
recorded in the commit metadata).
- PR preparation and verification: OpenAI Codex, tool-enabled coding
agent (runtime model ID and context window are not exposed to 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: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Agent adapters (Claude, Codex, Gemini) default to the ACP engine
lane, which needs a live bidirectional stdio session with the agent
process
> - Sandbox execution targets only exposed one-shot command execution,
so every ACP-capable adapter refused remote targets and fell back to the
CLI lane with a "supports only the local Paperclip host" warning
> - Running agents in sandboxes is a core deployment mode, and losing
ACP there means losing streaming updates, structured events, and
default-lane parity with local runs
> - This pull request adds a provider-agnostic process-session bridge
that relays the ACP stdio session into the sandbox over the existing
sandbox runner contract, and updates the adapters to use it
> - The benefit is that the default ACP lane now behaves the same on the
local host and in any sandbox provider, with CLI fallback reserved for
targets that genuinely cannot host a bidirectional session
## Linked Issues or Issue Description
No existing public issue covers this; inline description following the
feature request template:
**Problem or motivation**
Configuring an ACP-capable adapter (e.g. Claude) with a sandbox
environment made every run fall back to the CLI lane with the warning
"Claude ACP currently supports only the local Paperclip host, but this
run targets a remote environment." The ACP engine only knew how to spawn
a local subprocess, while sandbox providers only expose one-shot command
execution — so there was no way to hold the bidirectional stdio session
ACP requires.
**Proposed solution**
Add a process-session bridge in `adapter-utils`: a local ACPX-spawnable
proxy script connects to a token-authenticated loopback TCP server,
which relays JSON-framed stdin/stdout/stderr events to and from a small
relay script executed inside the sandbox via the provider's ordinary
runner. Claude/Codex/Gemini adapters now treat sandbox targets with a
runner as ACP-capable, resolve agent commands against the remote target,
and fall back to CLI only when the sandbox exposes no bidirectional
path. The sandbox callback bridge injects a run-scoped API endpoint and
bridge token so the agent inside the sandbox can reach Paperclip
(including work-product handoffs) without ever receiving the host run
JWT.
**Alternatives considered**
A provider-specific lane was prototyped first: Daytona minting SSH
access metadata at lease time, converted into an SSH execution target.
It was dropped because it only worked for providers able to advertise
SSH, added per-provider surface area, and left every other sandbox
provider on the CLI fallback. The merged design rides the one-shot
runner contract all providers already implement; a regression test pins
that sandbox targets stay on the bridge lane even when lease metadata
advertises SSH access.
**Roadmap alignment**
Directly advances the "Cloud / Sandbox agents" roadmap item — agents
running in remote and sandboxed environments keep the same control-plane
behavior as local ones. No overlap with other planned core work.
## What Changed
- `packages/adapter-utils/src/execution-target.ts`: new
`startAdapterExecutionTargetProcessSessionBridge()` plus helpers —
writes a token-authenticated local proxy script (spawnable by ACPX) and
a remote relay script synced into the sandbox, with a loopback TCP
server streaming JSON-framed stdio between them; events emitted before
the ACP client attaches are buffered so none are lost.
- `packages/adapter-utils/src/acpx-engine/execute.ts`: the ACP engine
can execute against remote sandbox targets through the bridge instead of
requiring a local subprocess, including remote cwd/env shaping.
- `packages/adapter-utils/src/sandbox-callback-bridge.ts`:
sandbox-scoped API bridging extended to allow work-product handoffs; the
sandbox payload env carries a bridge token, never the host run JWT.
- `packages/adapters/claude-local`, `codex-local`, `gemini-local`
(`src/server/acp.ts`): default-lane selection no longer rejects all
remote targets; command resolution is remote-aware
(`ensureAdapterExecutionTargetCommandResolvable`,
`resolveAdapterExecutionTargetCwd`); the fallback reason is now scoped
to sandboxes that expose only one-shot execution.
- `server/src/__tests__/environment-execution-target.test.ts`: pins that
sandbox targets resolve to the bridge lane, including when lease
metadata advertises SSH access.
- Non-sandbox remote targets (e.g. SSH) keep the CLI lane: the ACP
engine's remote transport is sandbox-only, so default-lane selection
falls back for those targets across all three adapters, and tests
covering CLI-specific remote behavior pin `engine: "cli"` explicitly.
- The bridge authenticates loopback connections before they can own the
session or receive buffered output (token required, idle unauthenticated
peers dropped), and remote event writes are serialized so the exit event
always lands after stdout/stderr have drained.
- Daytona plugin: formatting-only residue from the earlier iteration; no
functional change.
## Verification
- `vitest run` over the touched suites —
`packages/adapter-utils/src/acpx-engine/execute.test.ts`,
`packages/adapter-utils/src/execution-target-sandbox.test.ts`,
`packages/adapter-utils/src/sandbox-callback-bridge.test.ts`, the three
adapter `acp.test.ts` files, and
`server/src/__tests__/environment-execution-target.test.ts` — 102 tests
pass.
- End to end: with a Claude agent configured on a Daytona sandbox
environment, the primary-model test now selects the default ACP lane (no
fallback warning), and the full round trip (wake → sandbox execution →
API bridge → comment post) was exercised twice from inside a live
sandbox.
## Risks
- Behavioral shift: adapters that previously always fell back to CLI on
sandbox targets now default to ACP there; `engine=cli` still pins the
CLI lane explicitly.
- The bridge relays stdio as JSON lines over loopback TCP guarded by a
per-session random token; the remote relay runs inside the sandbox under
the provider's runner. Providers with slow one-shot execution will see
higher session startup latency — the CLI fallback remains for genuinely
incapable targets.
- No schema or migration changes.
## Model Used
- Claude Fable 5 (`claude-fable-5`, Anthropic) — extended thinking
enabled, agentic tool use via the Claude Agent SDK harness;
implementation iterated with local Vitest 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 (no
shipped docs describe the old local-only ACP limitation)
- [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: Cody <noreply@paperclip.ing>
Co-authored-by: Cody <cody@paperclip.local>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The heartbeat/recovery subsystem decides whether an agent run has a
durable continuation path after the process stops.
> - External waits need stricter semantics than local background
watchers: a killed local process is not durable, while a first-class
blocker/monitor/scheduled wake is.
> - Without that distinction, recovery can repeatedly treat
adapter-failed continuations as live work and obscure the real reason a
task stopped.
> - This pull request adds explicit durable external-wait liveness
handling and documents the expected execution semantics.
> - It also improves operator-visible recovery evidence so invalid
external-wait paths explain why they were rejected.
> - The benefit is clearer recovery behavior, fewer duplicate
continuation recoveries, and a safer contract for monitor-backed
external waits.
## Linked Issues or Issue Description
- Refs #5978
- Related PRs: #4988, #7495, #8502
## What Changed
- Added durable external-wait liveness classification so
local/background watchers are not accepted as durable live paths after
the owning process exits.
- Preserved first-class blocker/monitor/scheduled wake paths as valid
external-wait continuations.
- Added backend regression coverage for killed watcher failure,
monitor-backed durable wait resumption, normal completion, blocker
behavior, and no duplicate recovery.
- Added adapter utility coverage for terminal cleanup behavior used by
local process adapters.
- Surfaced invalid external-wait recovery evidence in the recovery
action card and run ledger.
- Updated execution semantics documentation and the V1 implementation
contract.
## Verification
- `pnpm check:token-gates` passed.
- `pnpm -r typecheck` passed.
- `node scripts/run-vitest-stable.mjs --mode general --group
general-server` equivalent lane passed in CI-clean env: 238 files, 2164
tests passed, 1 skipped.
- `node scripts/run-vitest-stable.mjs --mode general --group
general-workspaces-a` passed in fully Paperclip-env-clean env: UI 305
files / 2430 tests; CLI 43 files / 230 tests.
- `node scripts/run-vitest-stable.mjs --mode general --group
general-workspaces-b` passed in fully Paperclip-env-clean env:
shared/db/adapters/plugin packages all green.
- `node scripts/run-vitest-stable.mjs --mode serialized` passed in fully
Paperclip-env-clean env: 107 serialized server suites green, including
84/84 heartbeat-process-recovery tests.
- `pnpm build` passed in fully Paperclip-env-clean env.
Notes: running `pnpm test:run` directly inside the Paperclip heartbeat
environment exposed local harness env contamination in existing tests
(`PAPERCLIP_CONFIG`, `PAPERCLIP_DB_BACKUP_DIR`, and
`PAPERCLIP_WORKTREE_START_POINT`). Re-running the same lanes with
inherited `PAPERCLIP_*` and port env removed produced the CI-equivalent
green results above.
## Risks
- Medium behavioral risk: this changes recovery classification for
stopped local external-wait processes, so adapters relying on unmanaged
background watchers must use blockers, monitors, scheduled wakes, or
explicit durable handoff instead.
- Low UI risk: recovery-card copy changes are covered by component tests
and Storybook screenshot QA.
- No database migration is included.
> 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-based coding agent, tool-enabled terminal/code
execution. Exact context-window metadata was not exposed in the runtime.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Adapter packages are the bridge between the control plane and local
agent harnesses such as Claude Code, Codex, and Gemini CLI.
> - ACP support was concentrated in a separate `acpx_local` adapter,
which made ACP feel like a separate agent choice instead of an execution
capability of the harness adapters.
> - Claude, Codex, and Gemini now have ACP-capable harnesses, so the
native adapter should own ACP selection, fallback, config, transcript
parsing, and environment diagnostics.
> - The standalone ACPX adapter still needs a compatibility path for
existing rows, but it should not be offered as an active adapter for new
agents.
> - This pull request moves the shared ACP runtime into
`@paperclipai/acpx-engine`, wires Claude/Codex/Gemini local adapters to
prefer ACP when prerequisites are available, and retires `acpx_local` to
a tombstone.
> - The benefit is one adapter per harness, richer ACP transcripts by
default where possible, and a migration path for existing Claude/Codex
ACPX agents.
## Linked Issues or Issue Description
Closes#5932 — the broken default `acpx_local` Claude path is replaced
by native `claude_local` ACP support, existing Claude/Codex ACPX rows
migrate to native adapters, and new agents no longer choose the
standalone ACPX adapter.
Refs #4893 — original merged ACPX local adapter runtime that this PR
replaces with native per-harness ACP engines.
Refs #6590 — prior ACPX-Claude seamlessness work folded into the new
native Claude ACP path.
Refs #197 — related open generic ACP/Kiro adapter work; this PR does not
close it because Kiro/custom generic ACP remains a separate adapter
decision.
Refs #7018 — related Kimi-specific `acpx_local` shell failure; this PR
retires the built-in standalone adapter but does not add a native Kimi
adapter.
Refs #8864 — related ACPX prompt/API guidance PR; this PR moves runtime
guidance into the shared/native ACP engine path instead of the old
standalone adapter.
Refs #8881 — related `acpx_local` POSIX shell failure from the old
`acpx` pin; this PR updates ACP dependencies but does not claim
custom/OMP ACP support as a first-class native adapter.
Refs #8964 — related open `acpx_local` stderr cleanup PR; this PR makes
the old runtime path obsolete for new agents but keeps it as a
non-closing reference.
Problem description:
- The standalone `acpx_local` adapter duplicates Claude/Codex agent
choices that already have first-class local adapters.
- ACP should be an execution engine capability of each harness adapter
when the underlying harness supports ACP.
- Existing `acpx_local` agents should either migrate to native harness
adapters or fail with an explicit retirement message instead of silently
falling back to the process adapter.
## What Changed
- Added `@paperclipai/acpx-engine` as the shared ACP execution,
session-codec, CLI formatter, and UI parser package.
- Wired `claude_local`, `codex_local`, and `gemini_local` to auto-select
ACP by default when prerequisites pass, with `engine=cli` opt-out and
`engine=acp` strict mode.
- Added ACP config schema/UI fields, environment checks, session-codec
preservation, transcript parsing, and adapter capability metadata for
the native adapters.
- Retired `acpx_local` to a server tombstone, removed its
UI/package/runtime image surface, and added a migration for existing
Claude/Codex ACPX agents.
- Updated package manifests, lockfile, release tooling, docs, Kubernetes
sandbox defaults, and tests.
## Verification
- `corepack pnpm --filter @paperclipai/acpx-engine typecheck`
- `corepack pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `corepack pnpm --filter @paperclipai/adapter-codex-local typecheck`
- `corepack pnpm --filter @paperclipai/adapter-gemini-local typecheck`
- `corepack pnpm --filter @paperclipai/acpx-engine exec vitest run`
- `corepack pnpm --filter @paperclipai/adapter-claude-local exec vitest
run src/server/acp.test.ts src/server/execute.acp-fallback.test.ts
src/ui/build-config.test.ts`
- `corepack pnpm --filter @paperclipai/adapter-codex-local exec vitest
run src/server/acp.test.ts src/ui/build-config.test.ts`
- `corepack pnpm --filter @paperclipai/adapter-gemini-local exec vitest
run src/server/acp.test.ts src/ui/build-config.test.ts
src/ui/parse-stdout.test.ts`
- `corepack pnpm --filter @paperclipai/plugin-sdk ensure-build-deps &&
corepack pnpm --filter @paperclipai/server exec tsc --noEmit`
- `corepack pnpm --filter @paperclipai/server exec vitest run
src/__tests__/adapter-routes.test.ts
src/__tests__/adapter-session-codecs.test.ts
src/__tests__/adapter-models.test.ts`
- `corepack pnpm --filter @paperclipai/ui typecheck`
- `corepack pnpm --filter @paperclipai/ui exec vitest run
src/adapters/metadata.test.ts
src/adapters/adapter-display-registry.test.ts
src/components/AgentConfigForm.test.ts
src/components/AgentConfigForm.render.test.tsx
src/components/transcript/RunTranscriptView.test.tsx`
- `node --test scripts/bootstrap-npm-package.test.mjs
scripts/release-package-map.test.mjs
scripts/verify-release-registry-state.test.mjs`
Note: the server typecheck script calls `pnpm` internally; this dev
shell exposes pnpm through Corepack only, so I ran the two script steps
manually with `corepack pnpm`.
## Risks
- Migration changes existing `acpx_local` Claude/Codex agents to native
adapter types and clears old ACPX task sessions/runtime state.
- Custom ACP commands remain on the retired tombstone and will need a
separate future adapter/plugin path.
- ACP auto-selection depends on local Node and ACP server command
prerequisites; remote and unsupported environments fall back to CLI
unless `engine=acp` is explicit.
- `@paperclipai/acpx-engine` is a new public package and needs npm
trusted-publishing bootstrap before release automation can publish it.
> 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 GPT-5 via Codex coding agent. Exact hosted model build and
context-window size are not exposed in this runtime. Tool use included
shell execution, repository editing, GitHub CLI operations, and local
test/typecheck 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 is the open source app people use to manage AI agents for
work
> - Agents run in heartbeat runs orchestrated by the server; run
lifecycle, retry scheduling, and the dashboard's run-activity metrics
are the subsystems involved
> - A spike in "failed" tasks traced to three causes: server restarts
killing in-flight runs and mislabeling them as failures, deterministic
workspace-validation loops when a worktree's branch diverged, and
provider quota/usage-limit errors being classified as generic transient
failures (putting agents into error state and polluting metrics)
> - Killed-then-recovered runs and quota waits are not product failures,
so both the runtime behavior and the reporting needed to distinguish
them
> - This pull request drains runs gracefully on shutdown with idempotent
restart retries, self-heals workspace branch mismatches, adds a
quota-aware failure class with reset-time retry, separates recovered
restart kills from true failures on the dashboard, and documents restart
hygiene for operators
> - The benefit is fewer spurious failures, automatic recovery instead
of manual repair, and dashboard metrics that reflect real failure rates
## Linked Issues or Issue Description
No public GitHub issue exists; describing the bug inline per the
bug-report template:
**What happened?**
In-flight heartbeat runs are marked `failed` when the server restarts,
even though a retry later succeeds. Worktrees whose checked-out branch
diverges from the issue branch fail workspace validation on every
subsequent run with no recovery path. Provider quota/usage-limit
responses are treated as generic transient upstream errors, putting
agents into an error state and retrying before the quota window resets.
The dashboard counts all of these as true failures, inflating failure
metrics.
**Expected behavior**
Graceful shutdown should interrupt (not fail) running runs and chain
exactly one recovery retry. Workspace validation should repair
recoverable branch mismatches automatically. Quota errors should get
their own error class with the retry scheduled at the provider reset
time and the agent left idle. The dashboard should report recovered
restart kills separately from true failures.
**Steps to reproduce**
1. Start a heartbeat run, then restart the server (SIGTERM) while it is
in flight — the run lands as `failed` with a process-loss error code
even when its retry succeeds
2. Check out an issue whose worktree branch has diverged (e.g. after a
force-moved branch) — every subsequent run fails
`workspace_validation_failed` deterministically
3. Drive an agent into a provider usage-limit window — the run fails as
a generic transient upstream error and the agent enters an error state
instead of idling until the reset time
**Paperclip version or commit**
master (base c07e650cd)
**Deployment mode**
Self-hosted dev plane (Linux, node server + embedded Postgres)
## What Changed
- Graceful shutdown (SIGTERM hook) now marks in-flight runs
`interrupted` instead of `failed` and enqueues an idempotent
process-loss retry (pre-insert existence check on `retryOfRunId`
prevents duplicates; bursts chain exactly one retry per interrupted run)
- Run-liveness classification routes `interrupted` to `needs_followup`
rather than `failed`
- Workspace validation self-heals branch mismatch / missing-branch
states instead of failing deterministically on every run
- New `provider_quota` error class: session/usage-limit responses
schedule the retry at the provider reset time and leave the agent idle
(not errored); fixes a case where a quota-terminated run with subtype
`success` was misclassified as failed; HTTP 529 remains transient
- Dashboard run-activity query separates recovered restart kills from
true failures via a recursive CTE over `retry_of_run_id` (ancestors of a
succeeded retry count as recovered), adds a per-day failed-by-error-code
breakdown, and binds the window start as a timestamptz string
- Activity charts UI: amber "Recovered" segment with legend and per-day
error-code tooltip; success-rate chart counts recovered runs as
successes
- New ops runbook: `docs/deploy/dev-plane-restart-hygiene.md`
## Verification
- Greptile follow-up fixes on `992705edd`: `pnpm exec vitest run
server/src/__tests__/server-startup-feedback-export.test.ts
server/src/__tests__/heartbeat-workspace-branch-containment.test.ts
server/src/__tests__/heartbeat-workspace-session.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-workspace-finalize-branch.test.ts` (209
tests); `pnpm --filter @paperclipai/server typecheck`; `git diff
--check`
- Post-rebase CI fixes: `pnpm exec vitest run
server/src/__tests__/heartbeat-retry-scheduling.test.ts`; `pnpm exec
vitest run server/src/__tests__/heartbeat-retry-scheduling.test.ts
server/src/__tests__/workspace-runtime.test.ts
server/src/__tests__/heartbeat-workspace-branch-containment.test.ts
server/src/__tests__/heartbeat-workspace-finalize-branch.test.ts
server/src/__tests__/heartbeat-workspace-session.test.ts` (227 tests);
`pnpm --filter @paperclipai/server typecheck`
- `npm test` server suites covering the changes:
`heartbeat-process-recovery`, `heartbeat-stop-metadata`,
`heartbeat-retry-scheduling` (95 tests), quota parse +
execute/retry-scheduling suites (100 tests), workspace self-heal suites
(200 tests), dashboard run-activity tests (3 tests) — all green,
typecheck exit 0
- Dashboard CTE cross-checked against a real development database: two
restart-burst days moved from 17 to 8 and 19 to 6 true failures once
recovered kills were separated, matching manual retry-chain inspection
- Screenshot verification of the real ActivityCharts component
(recovered segment + tooltip) during QA
## Risks
- Behavioral shift: runs killed by a restart no longer surface as
`failed`; anyone consuming raw run statuses will see `interrupted` (new
status value) — dashboards/queries in this repo were updated accordingly
- Retry chaining on repeated restarts is bounded (one chained retry per
interruption) but a pathological restart loop still delays work rather
than failing it; the runbook covers operator hygiene for that case
- Dashboard query adds a recursive CTE; cost is bounded by the
day-window row count and was verified against production-sized data
- No schema migrations; low migration risk
## Model Used
- Claude (Anthropic) — claude-fable-5 via Claude Code / Paperclip agent
harness, extended thinking with tool use; implementation commits also
produced with Codex CLI (GPT-5 class) agents under the same harness
## 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)
- [ ] 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 core part of that experience is watching active agent runs without
dropping into raw logs first
> - Local and sandbox-backed adapters already record useful run output,
progress, and tool activity
> - But active issue threads could sit visually stale while the agent
was syncing workspaces, tailing sandbox output, or emitting incremental
tool-call updates
> - Operators need timely, human-readable progress while preserving the
raw transcript underneath
> - This pull request streams sandbox run-log progress into runtime
status, keeps visible issue threads refreshed, and folds repeated ACPX
tool updates into stable transcript cards
> - The benefit is that long-running agent work becomes easier to
supervise without changing the task/comment control-plane model
## Linked Issues or Issue Description
No public GitHub issue exists for this exact change.
Problem/motivation:
- During long-running sandboxed agent work, the issue UI can appear idle
even though the agent is actively syncing, running tools, or producing
incremental output.
- Operators need realtime feedback at the issue-thread layer, not only
after opening raw logs or waiting for the final heartbeat result.
- Related public context: #1808 previously added live-run status dots to
Projects; #4362 touches heartbeat wakeup behavior but is not a duplicate
of this runtime/UI feedback change.
## What Changed
- Added sandbox run-log streaming support and defaulted sandbox-capable
local adapters into the richer live-feedback path.
- Surfaced environment/sandbox sync progress through heartbeat runtime
status with bounded, redacted snippets.
- Added live issue-thread cache patching so visible active runs update
as progress events arrive.
- Folded repeated ACPX `tool_call` updates into one transcript card
instead of stacking duplicate cards.
- Updated adapter docs and added focused regression coverage for sandbox
log streaming, runtime status, ACPX parsing, live updates, transcript
rendering, and issue chat messages.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run ui/src/context/LiveUpdatesProvider.test.ts`
- `pnpm exec vitest run
server/src/services/heartbeat-run-runtime-status.test.ts
server/src/__tests__/heartbeat-runtime-state.test.ts
ui/src/context/LiveUpdatesProvider.test.ts`
- `pnpm exec vitest run
packages/adapter-utils/src/execution-target-sandbox.test.ts
packages/adapter-utils/src/sandbox-managed-runtime.test.ts
server/src/services/heartbeat-run-runtime-status.test.ts
server/src/__tests__/agent-live-run-routes.test.ts
server/src/__tests__/heartbeat-runtime-state.test.ts
packages/adapters/acpx-local/src/ui/parse-stdout.test.ts
ui/src/context/LiveUpdatesProvider.test.ts
ui/src/components/transcript/RunTranscriptView.test.tsx
ui/src/lib/issue-chat-messages.test.ts
ui/src/components/IssueChatThread.test.tsx`
- GitHub PR workflow on head `8397953e7b41ccd42e5d9457ee7e4dfb996e4ec5`:
`verify`, build, typecheck/release-registry, e2e, general shards,
serialized server shards, and canary dry run passed.
- Greptile Review on head `8397953e7b41ccd42e5d9457ee7e4dfb996e4ec5`:
Confidence Score 5/5, no unresolved review threads.
## Risks
- Live issue-thread cache patching could miss an edge case for a route
shape not covered by tests.
- Surfacing active-run snippets needs continued care around redaction;
this PR keeps snippets bounded and adds redaction-focused coverage.
- More frequent active-run UI refreshes could expose performance issues
on very large issue threads, though updates are scoped to visible
run/query caches.
## Model Used
OpenAI GPT-5 via Codex, operating as a tool-enabled coding agent with
shell, git, and repository-editing capabilities. Context window size is
not exposed in this runtime.
## 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.
> - Adapter names are part of the board-facing agent setup and
management experience.
> - The product now treats adapters as harnesses, while execution
environments are modeled separately.
> - Several built-in adapter labels still carried legacy local wording
from the older harness-by-environment model.
> - That wording makes the UI noisier and implies a distinction users no
longer need to reason about.
> - This pull request normalizes adapter display labels while keeping
persisted adapter type identifiers unchanged.
> - The benefit is clearer adapter selection and management copy without
a database migration.
## Linked Issues or Issue Description
No public GitHub issue was found for this exact cleanup.
Related public PRs:
- Supersedes #8910, an earlier branch for the same cleanup that did not
include the later docs/gateway/Cursor alignment.
- Refs #8819, which is related display-registry work for external
multi-segment adapter labels, but not a duplicate of this built-in label
cleanup.
Feature request details:
- Subsystem affected: Cross-cutting (`ui/`, `packages/adapters`, and
docs).
- Problem or motivation: user-facing adapter names include legacy local
qualifiers even though adapters map to harnesses and environments are
first-class elsewhere.
- Proposed solution: remove the legacy local wording from built-in
display labels, keep machine-readable adapter type ids unchanged, and
keep gateway disambiguation where it is useful.
- Alternatives considered: changing persisted adapter type ids was ruled
out because it would create migration and compatibility risk; one-off UI
replacements were ruled out because the display registry is already the
correct central label boundary.
- Roadmap alignment: this is small adapter UX polish, not a new
roadmap-level core feature.
## What Changed
- Updated the adapter display registry so known adapter labels are final
and no built-in local adapter renders a legacy local suffix.
- Preserved clean derived labels for unknown plugin local types while
keeping gateway disambiguation for unknown gateway types.
- Updated `AdapterManager` to prefer registry labels when the server
reports raw adapter type ids for built-ins.
- Removed legacy local wording from built-in adapter metadata labels in
UI and adapter packages.
- Aligned Cursor adapter metadata with the central display registry
label.
- Updated adapter docs and Storybook fixtures to match the new display
names.
- Added focused registry coverage for built-in labels and unknown plugin
suffix behavior.
## Verification
- `pnpm check:tokens`
- `git diff --check origin/master...fix/adapter-display-labels`
- Patch-addition scan for added secrets, private paths, and internal
links: no matches.
- GitHub duplicate search for open adapter-label/local-suffix issues and
PRs; #8910 was identified as the older superseded public PR.
- `pnpm exec vitest run
ui/src/adapters/adapter-display-registry.test.ts`
- `pnpm --filter @paperclipai/ui typecheck`
- Stale-label scan found no remaining user-facing display-label
suffixes; remaining local wording is operational/test terminology such
as adapter ids, docs about running locally, and test descriptions.
## Risks
Low risk. The change is display-label and documentation focused, and
adapter type ids remain unchanged. The main risk is ambiguous gateway
naming, mitigated by keeping explicit gateway labels where variants need
disambiguation.
## Model Used
OpenAI GPT-5 via Codex, tool-enabled coding agent in a local repository
workspace. Context window size is not exposed by this environment.
## 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.
> - Local adapters are the bridge between Paperclip's control plane and
provider CLIs such as Claude Code and Codex.
> - Those adapters can run either on the host machine or inside a
remote/sandbox execution target.
> - Sandbox probes need to validate the same auth/config path that real
sandbox execution will use.
> - The previous probe paths could surface misleading Claude errors,
rely on host-only Codex state, or upload far more Codex home state than
the probe needed.
> - This pull request fixes the Claude and Codex sandbox probe/runtime
behavior together while keeping provider-specific sandbox image work out
of scope.
> - The benefit is faster, clearer adapter health checks that better
match real sandbox execution.
## Linked Issues or Issue Description
No public GitHub issue was found for this exact bug during duplicate
search.
Bug report:
**What happened?**
Sandboxed Claude/Codex adapter tests could diverge from real runtime
auth/config behavior. Claude sandbox probes could show the leading
stream init line instead of the real final error, and Codex sandbox
probes could upload full managed home state or mask a sandbox-local
login with an empty uploaded `CODEX_HOME`.
**Expected behavior**
Sandbox probes should exercise the remote runtime contract, preserve
useful sandbox credentials, avoid relying on unrelated host state, and
report actionable probe failures.
**Steps to reproduce**
1. Configure a remote/sandbox execution target for `claude_local` or
`codex_local`.
2. Run the environment Test/probe path where host credentials differ
from the sandbox's runtime credentials or the managed Codex home
contains session history.
3. Observe that probe behavior can differ from the actual sandbox
runtime path or surface an unhelpful Claude stream initialization line.
**Paperclip version or commit**
Current `master` before this PR, based on `4a2447da3`.
**Deployment mode**
Local development/control-plane deployment with remote sandbox execution
targets.
Related search performed:
- Public issues: `Claude sandbox probe`, `Codex CODEX_HOME sandbox`
returned no matches.
- Public PRs: `Claude Codex sandbox probe`, `codex home sandbox`,
`claude auth sandbox` returned no matches.
## What Changed
- Made Claude sandbox Test probes materialize the same Paperclip-managed
Claude config seed path used by sandbox execution.
- Preserved sandbox-local Claude credentials when materializing remote
Claude config and expanded auth-required detection for `/login` API-key
failures.
- Improved Claude hello-probe diagnostics so the final result/error is
surfaced instead of the unhelpful stream init event, with transient
upstream failures downgraded to warnings.
- Changed Codex probe behavior to upload only minimal auth/config files
instead of the full managed `CODEX_HOME`.
- Let Codex sandbox probes leave `CODEX_HOME` unset when the host has no
credentials, so pre-authenticated sandbox images can be tested directly.
- Excluded bulky host-local Codex session/shell state from sandbox
runtime home uploads.
- Switched the Codex local default model away from the
ChatGPT-unsupported `gpt-5.3-codex` option.
- Added regression coverage for Claude parsing/probe paths, Codex
adapter metadata/argument/probe behavior, and server-level Claude
sandbox environment behavior.
## Verification
Passed locally:
- `pnpm install --frozen-lockfile`
- `pnpm vitest run
packages/adapters/claude-local/src/server/parse.test.ts
packages/adapters/claude-local/src/server/test.probe.test.ts
server/src/__tests__/claude-local-adapter-environment.test.ts`
- `pnpm vitest run packages/adapters/codex-local/src/index.test.ts
packages/adapters/codex-local/src/server/codex-args.test.ts
packages/adapters/codex-local/src/server/test.remote.test.ts`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/adapter-codex-local typecheck`
- `pnpm --filter @paperclipai/server typecheck`
- `git diff --check`
## Risks
- Adapter configuration behavior is sensitive to local vs sandboxed
execution mode, so review should focus on environment detection,
argument construction, and any state written during probe/test runs.
- The Codex default-model change may affect newly created agents that
rely on the adapter default instead of an explicit model.
- Excluding Codex session/shell state from sandbox uploads should be
safe for fresh sandbox runs, but reviewers should confirm no runtime
resume path depends on that host-local state.
- Provider-specific setup/capture behavior is intentionally left to
separate work.
## Model Used
OpenAI GPT-5 Codex via Paperclip `codex_local`; tool-enabled local
coding session with terminal access. Context window size was not exposed
by the runtime.
## 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 orchestrates AI agents for zero-human companies.
> - The `claude_local` adapter is the control-plane surface that turns
Paperclip agent settings into concrete Claude CLI invocations.
> - Issue #3777 reports that selecting Claude Haiku 4.5 from the
Paperclip UI causes Claude Code to request `claude-haiku-4-5-20251001`,
which some enterprise-scoped keys are not allowed to access.
> - In the current adapter model list, the direct Anthropic 4.5 entries
are version-pinned IDs, unlike the 4.6 entries which already use the
stable short aliases.
> - This pull request switches the direct 4.5 `claude_local` model
options to the short aliases Claude Code account access expects, while
leaving Bedrock-native IDs unchanged in the Bedrock-specific model list.
> - The benefit is that selecting Claude Sonnet 4.5 or Claude Haiku 4.5
from Paperclip no longer forces the CLI onto a more restrictive
versioned direct model name.
## What Changed
- Updated the direct `claude_local` adapter model list to use
`claude-sonnet-4-5` instead of `claude-sonnet-4-5-20250929`.
- Updated the direct `claude_local` adapter model list to use
`claude-haiku-4-5` instead of `claude-haiku-4-5-20251001`.
- Left the Bedrock-specific model IDs in `src/server/models.ts`
unchanged so AWS Bedrock routing still uses region-qualified native IDs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- Confirmed the only source change is
`packages/adapters/claude-local/src/index.ts`.
## Risks
- Low risk. This only changes the direct `claude_local` model IDs
advertised by Paperclip for the two 4.5 options.
- Bedrock behavior is unchanged because the Bedrock-native identifiers
are defined separately and were not modified in this PR.
- Existing 4.6 model options are untouched.
## Model Used
- OpenAI Codex on a GPT-5-class coding model with terminal tool use and
local code execution in this workspace.
## 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 run tests locally and they pass
- [ ] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
Fixes#3777
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Sandboxed agent runs can spend meaningful time preparing a remote
workspace before the agent transcript shows useful output.
> - Operators need short, current progress text for those setup phases,
but that text should not become durable run history.
> - The existing live-run websocket path already carries run updates to
the UI, so the backend can reuse that channel instead of adding polling.
> - This pull request adds an ephemeral runtime-progress contract, a
process-local status store, and heartbeat integration for
sandbox-managed runs.
> - The benefit is a clearer active-run experience without database
migrations or persistent progress rows.
## Linked Issues or Issue Description
Refs #248
No exact public GitHub issue was found for this status-message plumbing.
The underlying problem is that active sandboxed runs currently have
setup phases, such as workspace sync and restore, where the operator
cannot see concise current progress through the live run state. This PR
addresses that gap for the backend/runtime layer while keeping progress
messages ephemeral.
GitHub search performed for related or duplicate work: `sandbox runtime
status`, `sandbox restore index`, and `runtime progress`. No direct
duplicate PR was found.
## What Changed
- Added shared runtime-progress types and the `heartbeat.run.progress`
live event type.
- Added a process-local heartbeat run runtime-status store with TTL,
bounded/redacted messages, and terminal cleanup.
- Threaded runtime progress callbacks through heartbeat execution and
active/live run serialization.
- Emitted sandbox-managed runtime phase updates for sync, adapter
startup, restore/export, and finalization paths.
- Added backend and adapter-utils tests for ephemeral status behavior,
terminal cleanup, live serialization, and sandbox progress callbacks.
## Verification
- `pnpm install --frozen-lockfile`
- Local PII scan before push: high-confidence secret patterns, internal
issue links, local user paths, and private URL patterns checked across
all three split diffs; no real secrets or internal links found. The only
secret-like text is an intentional fake test fixture (`sk-test-secret`).
- `git diff --check origin/master..feat/sandbox-runtime-status`
- `pnpm exec vitest run
server/src/services/heartbeat-run-runtime-status.test.ts
server/src/__tests__/heartbeat-runtime-state.test.ts
server/src/__tests__/agent-live-run-routes.test.ts
packages/adapter-utils/src/sandbox-managed-runtime.test.ts` — 4 files,
23 tests passed.
- `pnpm run typecheck` passed on both top stacks that include this
branch: `feat/sandbox-status-ui` and `fix/sandbox-restore-index-sync`.
- `pnpm run build` passed on both top stacks that include this branch;
Vite reported existing CSS `::highlight` and chunk-size warnings.
- `pnpm run test:run` was attempted on `fix/sandbox-restore-index-sync`;
it failed in two unrelated broad-suite tests. One depends on this host's
Git default branch behavior, and one depends on local Claude
model-discovery environment. The changed focused suites above pass.
## Risks
- Runtime progress is process-local by design, so status disappears
after TTL, terminal cleanup, or server restart.
- Clients that do not consume `heartbeat.run.progress` simply keep
existing behavior.
- Message redaction is intentionally generic; overly specific phase
details should stay out of runtime-progress payloads.
> 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 GPT-5 via Codex coding agent, with shell/tool execution in a
local worktree. Exact context-window metadata is not exposed by the
runtime.
## 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 CTO <cto@paperclip.local>
Co-authored-by: Paperclip CTO <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The claude-local adapter launches the Claude CLI inside execution
environments (local, SSH, and ephemeral sandboxes such as Daytona)
> - Newer adapter code passes `--effort` to the CLI, but the Claude
binary baked into some sandbox images is older and rejects it with
`error: unknown option '--effort'`, so every run in those environments
fails
> - This needs addressing because the failure is environment-dependent
and silent from the operator's perspective — the run just dies with a
CLI usage error
> - This pull request probes the in-sandbox CLI for `--effort` support
once, caches the result per environment, and strips the flag (with a
warning) when the CLI does not support it
> - The benefit is that sandboxes with older Claude CLIs keep working
instead of failing, with negligible probe overhead because the
capability check is cached and reused across ephemeral leases
## Linked Issues or Issue Description
No public GitHub issue exists. Describing the bug inline following the
bug report template:
### What happened?
Runs using the `claude-local` adapter inside certain sandbox/execution
environments fail with `error: unknown option '--effort'`. The adapter
unconditionally appends `--effort` to the Claude CLI invocation, but the
Claude CLI version present in some sandbox base images predates that
flag, so the process exits with a usage error and the run dies.
### Expected behavior
The adapter should detect that the target environment's Claude CLI does
not support `--effort` and degrade gracefully — drop the flag and emit a
warning — rather than failing the run.
### Steps to reproduce
1. Configure an execution environment (e.g. a sandbox image) whose
bundled Claude CLI is old enough to predate the `--effort` option.
2. Run any claude-local task that resolves to an effort level (so
`--effort` is appended).
3. Observe the run fail immediately with `error: unknown option
'--effort'`.
### Paperclip version or commit
`master` at the time of this PR (branch forked from current `master`).
### Deployment mode
Self-hosted / local instance using execution environments (reproducible
with ephemeral sandbox providers such as Daytona where `reuseLease:
false`).
### Agent adapter(s) involved
Claude Code (`claude-local`).
## What Changed
- Add a CLI capability probe (`cli-capabilities.ts`) that runs the
target Claude binary's `--help` inside the execution environment to
detect `--effort` support.
- Strip `--effort` from the CLI args (emitting a warning) when the probe
reports the flag is unsupported; keep it otherwise.
- Cache probe results keyed by
`sandbox:providerKey:environmentId:command` (no lease id) so the probe
is reused across ephemeral leases — important for `reuseLease: false`
sandbox configs like Daytona, which would otherwise re-probe on every
run.
- Conservative fallback: if the probe itself can't run/parse, assume the
flag is supported (preserves prior behavior).
## Verification
- `node_modules/.bin/vitest run
src/__tests__/claude-local-execute.test.ts
src/__tests__/claude-local-adapter-environment.test.ts` → **2 files, 30
tests passed**.
- Regression test issues two `execute()` calls with distinct lease ids
and asserts the in-sandbox `--help` probe runs exactly once (cache reuse
across leases).
- Added tests covering: flag stripped when unsupported, flag retained
when supported, warning emitted, and conservative fallback when the
probe fails.
## Risks
Low risk. The change is additive and gated behind a probe with a
conservative default (assume supported on probe failure), so existing
environments that support `--effort` are unaffected. Worst case for an
environment where the probe is unreliable is the prior behavior (flag
passed through).
## Model Used
Claude Opus 4.8 (claude-opus-4-8), extended thinking, with tool use /
code execution via Claude Code.
## 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
- [ ] If this change affects the UI, I have included before/after
screenshots (N/A — no UI change)
- [ ] I have updated relevant documentation to reflect my changes (N/A —
no doc-facing behavior change)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (pending CI)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(pending review)
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the control plane for running AI-agent companies, so
long-running remote work needs to stay observable to human operators.
> - Cloud / sandbox agents are an active roadmap area, and their
workspace sync path is part of the runtime substrate every remote coding
run depends on.
> - In the sandbox and SSH execution-target flows, Paperclip logged that
sync had started, then often went silent for the full transfer window.
> - That made large remote syncs feel stalled and also hid a real
performance problem in the command-managed sandbox upload path.
> - The first part of this pull request threads a throttled
progress-reporting surface through the adapter execution-target stack so
sync and restore work can emit meaningful updates.
> - The second part fixes the command-managed sandbox transport itself:
it removes the old serial 32KB append bottleneck, but also falls back
away from the single-stream path when a provider-backed sandbox runner
cannot surface mid-flight stdin progress.
> - The result is that sandbox and SSH transfers are both faster and
more observable, including the live Daytona-style sandbox case that
previously only emitted `0%` and `100%`.
## Linked Issues or Issue Description
No public GitHub issue exists for this bug, so it is described inline
below following the bug report template.
### What happened
- Remote sandbox and SSH workspace syncs could spend a long time
transferring data while only logging a start line (`Syncing workspace
and runtime assets to sandbox environment`) and, at best, a terminal
line.
- In the command-managed sandbox path, the original upload
implementation also paid a large performance cost by appending base64
data in many small sequential remote writes (thousands of serial 32KB
round-trips on a large workspace).
- After the initial transport rewrite, live provider-backed sandbox runs
still only emitted `0%` and `100%` because the single-stream stdin RPC
buffered progress until completion.
### Expected behavior
- Long-running sandbox and SSH syncs should periodically report how much
of the transfer is complete (a percentage and/or MB transferred) so an
operator can tell the run is healthy and making progress rather than
stuck.
- The main sandbox upload path should not be artificially slow.
- A transfer that fails partway should leave an explicit failure marker
in the log rather than a dangling intermediate percentage.
### Steps to reproduce
1. Run an agent against a sandbox (command-managed) or SSH
(remote-managed) execution target with a non-trivial workspace.
2. Watch the run log during the workspace/runtime asset sync phase.
3. Observe that the log shows the sync start line and then stays silent
for the full transfer (live provider-backed sandbox runs only show `0%`
then `100%`).
### Paperclip version or commit
- Branch `PAPA-825-provide-status-updates-when-syncing-sandboxes` off
`master`.
### Deployment mode
- Self-hosted / local instance using sandbox (command-managed) and SSH
(remote-managed) execution targets, including provider-backed sandbox
runners.
## What Changed
- Added shared throttled runtime progress reporting and threaded
`onProgress` through the adapter execution-target surface and adapter
`execute.ts` entrypoints.
- Added sync and restore progress reporting for the command-managed
sandbox path and the SSH/remote-managed path, including git
import/export progress where totals are known.
- Reworked command-managed sandbox transfer behavior so uploads use the
faster single-stream path when appropriate, but fall back to chunked
progress-emitting writes when the runner cannot expose mid-stream stdin
progress.
- Marked provider-backed environment sandbox runners as not supporting
single-stream stdin progress so live sandbox runs emit meaningful
intermediate updates instead of only `0%` and `100%`.
- Emit an explicit terminal failure marker (`failed at NN% (x/y MB)`)
when an SSH/tar transfer rejects, so a failed sync no longer leaves a
dangling intermediate percentage in the log.
- Run the SSH sync/restore size estimate (local directory walk / remote
`du` probe) concurrently with the transfer instead of awaiting it before
opening the pipe, so progress instrumentation no longer adds startup
latency proportional to workspace file count.
- Added and extended focused regression coverage for runtime progress
throttling and the new failure marker, command-managed sandbox
transfers, sandbox orchestration, SSH transfer progress, and environment
execution-target wiring.
## Verification
- `pnpm exec vitest run
packages/adapter-utils/src/runtime-progress.test.ts
packages/adapter-utils/src/ssh-fixture.test.ts
packages/adapter-utils/src/command-managed-runtime.test.ts
packages/adapter-utils/src/sandbox-managed-runtime.test.ts`
- `pnpm exec vitest run
packages/adapter-utils/src/command-managed-runtime.test.ts
server/src/__tests__/environment-execution-target.test.ts`
- `npx tsc --noEmit` for `packages/adapter-utils`
## Risks
- The provider-backed sandbox fallback now prefers chunked
command-managed writes when progress hooks are active, so
small-to-medium uploads may trade some raw throughput for observable
intermediate progress on runtimes that cannot surface true mid-stream
stdin progress.
- Progress percentages on tar-based transfers still depend on estimates
in some cases, so operators may briefly see MB-only lines before the
estimate resolves, then near-final clamping before the terminal `100%`
line.
- This PR changes shared execution-target behavior used by multiple
adapters, so regressions would most likely appear in remote runtime
setup/teardown flows rather than in a single adapter.
## Model Used
- Initial implementation: OpenAI GPT-5.4 via Codex local agent
(`codex_local`), high reasoning mode.
- Observability follow-ups (failure marker, concurrent size estimate,
added tests): Claude Opus 4.8 via Claude Code (`claude_local`).
## 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] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [ ] 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
- [ ] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Agents run through adapters; `@paperclipai/adapter-claude-local`
shells out to the Claude CLI and maps its result JSON into Paperclip's
run outcome (`errorCode` / `errorFamily`)
> - A Fable 5 policy refusal exits the CLI cleanly (`exitCode=0`,
`is_error=false`) with `stop_reason: "refusal"`, which the adapter
mapped to `errorCode: null`
> - Paperclip therefore recorded the run as a silent success, so the
agent's heartbeat stalled with no signal for operators and no hook to
retry or alert
> - This pull request adds a refusal detector to the adapter so a
refusal resolves to a distinct `errorCode: "claude_refusal"`
(`errorFamily: "model_refusal"`)
> - The benefit is that policy refusals become observable: the server
persists the code, operators can see it on the run, and downstream
retry/alert policy can key off it
## Linked Issues or Issue Description
No public GitHub issue exists. Describing the underlying bug in-PR,
following `.github/ISSUE_TEMPLATE/bug_report.yml`:
**What happened?**
When the Claude CLI returns `stop_reason: "refusal"` (a model policy
refusal), it still exits cleanly (`exitCode=0`, `is_error=false`).
`@paperclipai/adapter-claude-local` keyed refusal detection off the
failure flag during error-code resolution, so it returned `errorCode:
null` — a refused run was indistinguishable from a successful one,
recorded by Paperclip as a silent success with no signal to retry or
alert.
**Expected behavior**
A refusal should resolve to a distinct, non-null error code (`errorCode:
"claude_refusal"`, `errorFamily: "model_refusal"`) so the server can
surface it to operators and downstream policy can react.
**Steps to reproduce**
1. Run any agent on the `claude-local` adapter with a prompt the model
refuses on policy grounds.
2. The Claude CLI exits `0` with `is_error=false` and `stop_reason:
"refusal"`.
3. Observe the run resolves `errorCode: null` (pre-fix) instead of a
refusal-specific code.
**Paperclip version or commit**
`adapter-claude-local` v2026.609.0 (`dist/server/execute.js` error-code
resolution block); reproduced on `master`.
**Deployment mode**
Local / self-hosted.
**Agent adapter(s) involved**
`@paperclipai/adapter-claude-local` (Claude Code, local).
## What Changed
- **`packages/adapters/claude-local/src/server/parse.ts`** — new
`isClaudeRefusalResult()` helper, parallel to
`isClaudeMaxTurnsResult()`. Detects `stop_reason` / `stopReason` /
`error_code` / `errorCode` == `refusal` and `subtype` ==
`model_refusal`, case/whitespace tolerant.
- **`packages/adapters/claude-local/src/server/execute.ts`** — compute
the refusal flag independent of the `failed` flag (a refusal exits
cleanly, so keying off `failed` would miss it); resolve `errorCode:
"claude_refusal"` and `errorFamily: "model_refusal"`; surface
`stopReason: "refusal"` in `resultJson`.
- **`packages/adapter-utils/src/types.ts`** — widen
`AdapterExecutionErrorFamily` with `"model_refusal"`.
- **`packages/adapters/claude-local/src/server/index.ts`** — export the
new helper.
- **`packages/adapters/claude-local/src/server/parse.test.ts`** — 7 new
unit tests.
## Verification
```
npx vitest run packages/adapters/claude-local # 35 passed (7 new)
npx tsc --noEmit -p packages/adapter-utils # clean
npx tsc --noEmit -p packages/adapters/claude-local # clean
```
Manual: a result JSON with `stop_reason: "refusal"` on a clean exit now
resolves `errorCode: "claude_refusal"` and `errorFamily:
"model_refusal"`; non-refusal results are unaffected.
## Risks
Low risk. Additive only — it introduces a new error code on a path that
previously returned `null`; no existing error code or success path
changes. `claude_refusal` is deliberately **not** added to the
transient-upstream retry set: a refusal is deterministic, so retrying
the same prompt yields the same refusal. It surfaces as a distinct
non-transient code for operators; downstream retry/alert policy can key
off `claude_refusal` / `errorFamily: model_refusal` later.
## Model Used
Claude Opus 4.8 (`claude-opus-4-8`), extended-thinking mode, run via
Claude Code with tool use.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above (no related PRs found)
- [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] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots (N/A — no UI changes)
- [x] I have updated relevant documentation to reflect my changes (N/A —
internal adapter error-code addition; no user-facing docs)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (this push re-runs the gates;
will confirm once green)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(prior run was 4/5 on a PR-description note now addressed; will confirm
on re-run)
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Full-Stack Engineer <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The Claude-local adapter resumes prior sessions via `claude --resume
<session-id>` so work continues across heartbeats.
> - When a resumed session contains an image whose content is no longer
accessible, Claude returns a 400 "Could not process image" — but the
session itself is poisoned and will keep returning the same error on
every resume.
> - The existing retry path only catches the "unknown session" 400 case;
image-processing 400s on resume fall through and the run fails for the
user.
> - This PR adds an `isClaudeImageProcessingError` detector mirroring
`isClaudeUnknownSessionError` and wires it into the same fresh-session
retry branch in `execute.ts`.
> - The benefit is that a poisoned-image resume self-recovers by
retrying once with a fresh session, exactly like the existing
unknown-session path.
## Linked Issues or Issue Description
Fixes#3275
Refs #3123
## What Changed
- Added `isClaudeImageProcessingError()` in
`packages/adapters/claude-local/src/server/parse.ts` that matches `Could
not process image` in 400 error messages.
- Wired the new detector into the existing session-resume retry branch
in `packages/adapters/claude-local/src/server/execute.ts` alongside
`isClaudeUnknownSessionError`.
- Retry only fires when `sessionId` is present (i.e. we were resuming),
so fresh-session runs that hit the same error are not retried (no
infinite loop).
## Verification
- `pnpm --filter @paperclipai/adapter-claude-local test` covers
`parse.ts` patterns and the resume-retry decision branch.
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
## Risks
Low. Behavior change is narrowly additive: a previously-fatal 400 on
resume now triggers a single fresh-session retry. No effect on
fresh-session runs, unknown-session retries, or non-image 400s.
## Model Used
Claude (Opus 4.6) — used to mirror the existing unknown-session pattern
and verify the guard against infinite loops.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots (N/A — no UI changes)
- [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 (in progress)
- [ ] 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: Devin Foley <devin@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents on pluggable adapters
(`claude_local`, `opencode_local`, `codex_local`, …); each adapter wraps
an external CLI.
> - The heartbeat service stores a session ID per agent and replays it
back to the adapter via `--resume` so within-task continuity is
preserved.
> - Session IDs are adapter-specific in format: claude expects a UUID,
opencode emits `ses_…`, etc. They cannot be cross-replayed.
> - When the cross-adapter session ID does slip through (operator
changes `adapterType`, edge cases in the resume path, foreign-format ID
in stored task sessions), the claude CLI hard-fails with a validation
error and every subsequent heartbeat loops on the same error until the
stored ID is manually cleared.
> - Master now ships a canonical-session-ID guard at `heartbeat.ts:8450`
(via #5972) that prevents most of this at the source, and
`isClaudePoisonedPreviousMessageIdError` recovers from the 400-class API
error.
> - This PR adds defense-in-depth at the adapter layer: the `--resume
requires a valid session ID … not a UUID …` validation error from the
claude CLI is now classified as an unknown-session signal, so the
existing fresh-session retry recovers instead of hard-failing.
## Linked Issues or Issue Description
Refs #5972 — sibling fix on the same cluster (recovers from poisoned
`previous_message_id` 400). This PR complements it by handling the
CLI-layer `--resume` validation error class.
## What Changed
- `packages/adapters/claude-local/src/server/parse.ts` — broaden
`isClaudeUnknownSessionError` regex to also match `--resume requires a
valid session`, `is not a UUID`, and `does not match any session title`.
The existing fresh-session retry at `execute.ts:612-625` now fires for
this error class.
- `packages/adapters/claude-local/src/server/parse.test.ts` — adds 4 new
test cases for `isClaudeUnknownSessionError` covering the legacy and new
patterns plus a negative case.
**Dropped from the original PR on rebase** (already on master, would
conflict):
- `server/src/services/heartbeat.ts` runtimeSessionFallback gate —
superseded by the stricter `isCanonicalSessionIdForAdapter` check on
master (#5972 lineage).
- `packages/adapters/claude-local/vitest.config.ts` and
`vitest.config.ts` projects entry — both already in master.
## Verification
```sh
pnpm --filter @paperclipai/adapter-claude-local vitest run
# 19/19 passed (3 files, includes 4 new isClaudeUnknownSessionError cases)
```
Pre-existing failure on
`server/src/__tests__/heartbeat-process-recovery.test.ts > queues
exactly one retry when the recorded local pid is dead` reproduces on
`origin/master` — unrelated to this PR.
## Risks
- **Low-to-medium.** The added regex fragments are narrow. `--resume
requires a valid session` and `does not match any session title` are
unambiguously session-related. `is not a UUID` is more generic; worst
case is one extra retry on an unrelated CLI validation error that would
also fail on the same root issue. Happy to drop `is not a UUID` if
reviewers prefer.
- **No DB migration; no schema change; no behavior change when adapter
types match (the common path).**
## Model Used
- Provider: Anthropic (Claude)
- Model: `claude-opus-4-7` (Opus 4.7), 1M context window
- Tool: Claude Code CLI with extended thinking + tool use; human review
on the rebase and the regex narrowing tradeoffs
## Checklist
- [x] I searched the GitHub PR list for similar PRs and confirmed this
is not a duplicate (related: #5972 already merged, complementary scope)
- [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 run tests locally and they pass (19/19 claude-local)
- [x] I have added or updated tests where applicable
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Devin Foley <devin@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The Claude-local adapter uses `claude --resume <session-id>` to
continue prior sessions; the `--resume` value MUST be a UUID per
Claude's CLI contract.
> - Paperclip internally uses session IDs prefixed with `ses_` (not
UUIDs); these get passed straight through to `--resume` and crash the
run.
> - On top of the crash, when the underlying error path triggers a
secret-decryption failure or heartbeat setup failure, the diagnostics
are too thin to tell key-mismatch from other failures, and the heartbeat
error code is mis-classified as `adapter_failed` instead of
`setup_failed`.
> - This PR validates `runtimeSessionId` against a UUID regex before
letting `canResumeSession` become true, adds `not a valid UUID` to
Claude's own retry-error regex, improves AES-256-GCM decryption
diagnostics in the local encrypted provider, and re-classifies
pre-adapter setup failures.
> - The benefit is that Paperclip session IDs are detected and skipped
gracefully (logged, no crash), legitimate Claude UUID-rejection errors
are treated as retriable, and operators can diagnose decryption/setup
failures from the run log.
## Linked Issues or Issue Description
**What happened?**
The `claude-local` adapter passes Paperclip's internal session
identifiers (e.g. `ses_…`) straight to `claude --resume <session-id>`.
Because Claude's CLI requires the `--resume` argument to be a UUID, the
run crashes with a `not a valid UUID` error. When the surrounding code
path also hits a secret-decryption failure, the heartbeat reports it as
`adapter_failed`, hiding the real `setup_failed` cause and making
diagnosis hard.
**Expected behavior**
Non-UUID session IDs should be detected before `--resume` is called, the
run should fall back to a fresh session with a clear log line, and any
decryption / setup failure should be reported with enough detail (and
the correct error code) for an operator to tell what failed.
**Steps to reproduce**
1. Have a persisted task session whose ID is not a UUID
(Paperclip-issued `ses_…` form).
2. Trigger a heartbeat that resumes that session via the `claude-local`
adapter.
3. Observe: the adapter crashes with a UUID-validation error; if the
path also involves a decryption failure, the heartbeat surfaces
`adapter_failed` instead of `setup_failed`.
## What Changed
- `packages/adapters/claude-local/src/server/execute.ts`: Validates
`runtimeSessionId` against a UUID regex before setting
`canResumeSession`; non-UUID IDs are logged and skipped gracefully.
Guards the cwd-mismatch log block on `isValidUuid` so it does not fire
for non-UUID session IDs.
- `packages/adapters/claude-local/src/server/parse.ts`: Adds `not a
valid UUID` to the session-error retry regex so Claude's own UUID
rejection is treated as a retriable error.
- `server/src/services/secrets/local-encrypted-provider.ts`: Wraps
AES-256-GCM decryption in try/catch and re-throws with a key fingerprint
hint to aid key-mismatch diagnosis.
- `server/src/services/heartbeat.ts`: Corrects the outer-catch
`errorCode` from `adapter_failed` to `setup_failed` for pre-adapter
setup failures.
- `AGENTS.md`: Adds task/PR/CI governance sections (10–13) and expands
the Definition of Done.
## Verification
- `pnpm --filter @paperclipai/adapter-claude-local test` covers UUID
validation and the parse retry regex.
- `pnpm --filter @paperclipai/server test src/services/secrets` covers
decryption diagnostics.
- `pnpm --filter @paperclipai/server typecheck`
## Risks
Low. UUID validation is strictly additive (non-UUIDs that previously
crashed now log and skip). Decryption diagnostics only fire on failure
paths. The `setup_failed` error code change is a clearer classification,
not a behavior change.
## Model Used
Claude (Opus 4.6) — used to identify the UUID-validation root cause,
mirror existing parse patterns, and re-classify the heartbeat setup
error code.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots (N/A — no UI changes)
- [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 (in progress)
- [ ] 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: CTO Agent <cto@paperclip.ing>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## Thinking Path
> - Paperclip's `claude_local` adapter persists Claude Code session
jsonls under `~/.claude/projects/…/{sessionId}.jsonl` and resumes them
on the next heartbeat
> - When Claude Code injects `<synthetic>` placeholder assistant
messages (after rate-limit, max-turn exhaustion, or transient-upstream
failures) those placeholders get UUID-format `message.id`s rather than
`msg_…`-format ids
> - On the next `--resume`, Claude Code passes that UUID as
`previous_message_id` and Anthropic's API rejects it with a 400:
``diagnostics.previous_message_id: must be the `id` from a prior
/v1/messages response (starts with `msg_`)``
> - The adapter had a session-rotation fallback only for "unknown
session" errors, so the poisoned session was `--resume`-d indefinitely
and the agent flipped between `idle` and `error` every heartbeat
> - Even worse, the *result* event of the failing run still carried a
`session_id`, and the adapter was persisting that id into the
issue-scoped session store (`agentTaskSessions`). So even after we
detected the 400, every subsequent continuation re-loaded the same
poisoned id and hit the same 400 again — the issue was permanently
stranded
> - We observed this on multiple agents in our deployment; the only
manual fix was to rename the `.jsonl`, which is not a viable long-term
workaround
> - This PR detects the 400, runs the same session-rotation fallback the
unknown-session path uses **and** stops persisting the poisoned id, so
the next attempt starts genuinely fresh
## Linked Issues or Issue Description
No external GitHub issue is linked. Describing the problem inline
following the bug-report template:
**What happened:** `claude_local` agents flipped between `idle` and
`error` on every heartbeat because the persisted session jsonl carried a
synthetic UUID `previous_message_id` (from `<synthetic>` assistant
placeholders injected after rate-limit/max-turn/upstream errors).
Anthropic's API rejected every `--resume` with a 400:
``diagnostics.previous_message_id: must be the `id` from a prior
/v1/messages response (starts with `msg_`)``.
**Expected behavior:** When the persisted session is poisoned and
unrecoverable, the adapter should rotate to a fresh session — the same
fallback path already used for unknown-session errors — and stop
re-persisting the poisoned `session_id`.
**Actual behavior:** The session-rotation fallback only matched the
"unknown session" pattern, so the poisoned session was `--resume`-d
forever. The result event of the failing run still carried `session_id`,
which was being persisted into `agentTaskSessions`, so every subsequent
continuation reloaded the same poisoned id and hit the same 400.
**Reproduction:** Inject any flow that causes Claude Code to emit a
`<synthetic>` placeholder (rate-limit, max-turn exhaustion, transient
upstream failure). The next `--resume` will fail with the 400 and the
agent will not self-recover.
**Scope of fix:** Add a `previous_message_id` 400 detector; route it
through the existing unknown-session fallback; drop the poisoned
`sessionId` and emit `clearSession: true` so the heartbeat service wipes
the persisted row; best-effort delete the local poisoned `.jsonl`.
## What Changed
Two commits:
1. **`adapter-claude-local: auto-rotate session on previous_message_id
400 (synthetic-msg poisoning)`** — detector + execute-time rotation
2. **`adapter-claude-local: guard against persisting poisoned
sessionId`** — validate-before-persist + `clearSession`
Combined diff:
- `parse.ts`: new `isClaudePoisonedPreviousMessageIdError(parsed)`
matching ``/diagnostics\.previous_message_id.*starts with `msg_`/i``
against `parsed.result` and `extractClaudeErrorMessages(parsed)`
- `parse.ts`: `isClaudeTransientUpstreamError()` excludes the new error
from transient classification so it isn't masked as retryable upstream
noise
- `execute.ts`: expand the resume-fallback branch so it triggers on both
`isClaudeUnknownSessionError` and the new
`isClaudePoisonedPreviousMessageIdError`, with a distinct log line
(`"returned a poisoned message-id"` vs `"is unavailable"`)
- `execute.ts`: for local (non-remote) execution targets, best-effort
delete the poisoned `~/.claude/projects/.../{sessionId}.jsonl` before
retrying so the file can't be accidentally resumed by an out-of-band
caller. The `fs.unlink` and follow-up log call are in separate try/catch
blocks so a closed log stream cannot mask a successful unlink (and vice
versa)
- `execute.ts` / `toAdapterResult`: when a result carries the poisoned
400, **drop** `sessionId`/`sessionParams`/`sessionDisplayId` (return
`null`) and emit `clearSession: true` so the heartbeat service's
`resolveNextSessionState` wipes the persisted row. The result also
surfaces `errorCode: "claude_poisoned_previous_message_id"` for
observability
- `docs/adapters/claude-local.md`: runbook entry — symptom,
auto-recovery flow, on-call checklist
- Tests:
- 4 new `parse.test.ts` cases covering positive detection in `result`
and `errors[]`, negative cases, and non-transient classification
- 3 new `claude-local-execute.test.ts` cases: (a) fresh run reports the
poisoned error → sessionId dropped + `clearSession: true`; (b) recovery
retry also reports the poisoned error → same guards apply; (c)
session-rotation success on retry
## Verification
```bash
pnpm --filter @paperclipai/adapter-claude-local exec vitest run src/server/parse.test.ts
pnpm --filter @paperclipai/server exec vitest run src/__tests__/claude-local-execute.test.ts
```
Both suites green locally. This patch is also currently running as a
hot-patch over the published `2026.513.0` adapter on the reporting
deployment — sessions that previously looped indefinitely now
self-recover on the first heartbeat after the 400 surfaces.
## Risks
- Low risk. The detector is conservative (regex over `result` +
`errors[]` only) and the rotation reuses the existing unknown-session
fallback path
- The local-only `fs.unlink` of the poisoned `.jsonl` is wrapped in
`try/catch` and ignored on failure — strictly an optimization; the
server-side session clear is the authoritative reset
- Remote execution targets (`executionTargetIsRemote`) skip the disk
cleanup because the file lives on a remote host that we can't safely
reach from the adapter
- The `clearSession: true` + nulled session fields path is a no-op on
healthy runs; it only fires when the new detector matches, so existing
successful continuations are unaffected
- No DB schema changes, no public API changes, no new dependencies
## Model Used
- Provider: Anthropic Claude
- Model: `claude-opus-4-7` (Opus 4.7)
- Context window: 1M
- Capabilities: extended reasoning, tool use, code execution
- Role: implemented the detector, expanded the fallback branch, added
the persist-guard + `clearSession`, wrote the unit + integration tests,
validated locally, and applied the equivalent hot-patch to the deployed
`2026.513.0` install while this PR is in 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 similar or duplicate PRs and linked
them — closed#2295, #2361, #3572, #5438 as duplicates of this canonical
fix; complementary fixes#4838 (heartbeat_timer reset) and #4932 (gemini
context-overflow rotation) target different code paths
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots — N/A, adapter-only change
- [x] I have updated relevant documentation
(`docs/adapters/claude-local.md` runbook entry)
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Danial Jawaid <danial.jawaid@gmail.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## Summary
Adds the newly released Claude models from the [models
overview](https://platform.claude.com/docs/en/about-claude/models/overview)
to the `claude_local` adapter's model selector:
- **Claude Fable 5** (`claude-fable-5`) — generally available as of
2026-06-09, Anthropic's most capable widely-released model.
- **Claude Mythos 5** (`claude-mythos-5`) — limited availability
(Project Glasswing).
**Opus 4.8 stays first in the list so it remains the default selection**
— per the request, the new flagship models are *offered* but not
defaulted (not Fable, not Mythos).
## Changes
- `packages/adapters/claude-local/src/index.ts` — add `claude-fable-5`
and `claude-mythos-5` to the adapter model list, right after
`claude-opus-4-8`.
- `packages/adapters/claude-local/src/server/models.ts` — add the Fable
5 Bedrock identifier (`us.anthropic.claude-fable-5-v1`) to the Bedrock
fallback list. Mythos 5 is limited-availability on Bedrock, so it's
intentionally left out of that fallback.
- `server/src/__tests__/adapter-models.test.ts` — assert the new models
are present and that `claude-opus-4-8` remains first (the default).
These flow through the single `claudeModels` source, so they also appear
in the ACPX combined list (`registry.ts` prefixes them with `Claude:`)
and are recognized by the ACPX Claude model filter. The UI selector
reads models dynamically from the adapter, so no UI changes are needed.
## Testing
- `npx vitest run src/__tests__/adapter-models.test.ts` — 13 passed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Thinking Path
> - Paperclip orchestrates AI-agent companies through adapter-backed
local and external runtimes.
> - The agent configuration UI lets operators choose adapter models and
refresh model lists when adapters support live discovery.
> - Codex already had a live refresh path, but Claude Local only exposed
static fallback models and the UI hid the refresh action for Claude.
> - A newly available Claude Opus model should not require a code
release every time the model catalog changes.
> - This pull request adds Anthropic model discovery for Claude Local,
keeps the static fallback current with Claude Opus 4.8, and exposes the
existing refresh button in the Claude Local dropdown.
> - The benefit is that operators can refresh Claude models from the
same model selector flow they already use for Codex.
## What Changed
- Added `claude-opus-4-8` to the Claude Local fallback model list.
- Added Claude model discovery through Anthropic-compatible `GET
/v1/models` when `ANTHROPIC_API_KEY` is available.
- Added normal cache reuse, forced refresh support, a SHA-256-based
API-key fingerprint for cache keys, and warning logging for discovery
errors before fallback.
- Wired `claude_local.refreshModels` into the server adapter registry.
- Enabled the existing `Refresh models` dropdown action for
`claude_local` in `AgentConfigForm`.
- Added tests for Claude fallback, live discovery, API-failure fallback,
forced refresh, and the UI refresh-button gate.
## Verification
- `pnpm exec vitest run server/src/__tests__/adapter-models.test.ts`
- `pnpm exec vitest run ui/src/components/AgentConfigForm.test.ts`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/server typecheck`
- `pnpm --filter @paperclipai/ui typecheck`
- Greptile review reached Confidence Score: 5/5 on commit `b796cf4f1`
with addressed threads resolved.
UI note: the visible change is a conditional action row inside the
existing model dropdown; the regression test covers that `claude_local`
now receives the refresh action.
## Risks
- Low risk. Without `ANTHROPIC_API_KEY`, Claude Local still uses the
static fallback list.
- If Anthropic model discovery fails or times out, Paperclip falls back
to the existing cached or static list.
- Bedrock environments remain on Bedrock-native model IDs.
## Model Used
OpenAI GPT-5 via Codex local coding agent, with repository file access,
shell command execution, git operations, and targeted test/typecheck
verification. Exact context window is not exposed by the runtime.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies through
company-scoped control-plane workflows.
> - Agents need reusable, inspectable skills that can be installed,
reset, audited, exported, and assigned without bespoke local setup.
> - The existing skill truth model needed cleanup so bundled skills,
optional catalog skills, runtime skills, and adapter-provided skills
have clear provenance.
> - Operators also need a practical CLI and board UI for discovering and
managing company skills.
> - This pull request adds the skills CLI, packaged skills catalog,
company skills APIs, and catalog-aware board UI.
> - The benefit is a more reusable Paperclip company setup where skills
are portable, auditable, and easier for operators and agents to manage.
## What Changed
- Added `paperclipai skills` CLI commands and coverage for catalog
listing, installing, resetting, and inspecting company skills.
- Added a packaged `@paperclipai/skills-catalog` workspace with bundled
and optional skill content plus validation/build tests.
- Added shared company-skill types and validators used across CLI,
server, and UI contracts.
- Added server catalog APIs/services for company skill catalog
operations, reset semantics, audit behavior, and portability provenance.
- Updated adapter skill handling so runtime/catalog provenance remains
explicit across local adapters.
- Added board UI support for browsing and managing catalog-backed
company skills.
- Updated docs for the skills CLI/catalog flow and the company skills
Paperclip skill reference.
- Rebased the branch onto current `paperclipai/paperclip:master`; no
`pnpm-lock.yaml`, `.github/workflows`, or migration files are included
in the final PR diff.
## Verification
- Passed: `pnpm run preflight:workspace-links && pnpm exec vitest run
cli/src/__tests__/skills.test.ts
packages/skills-catalog/src/catalog-builder.test.ts
packages/skills-catalog/src/shipped-catalog.test.ts
packages/shared/src/validators/company-skill.test.ts
packages/adapter-utils/src/server-utils.test.ts
packages/plugins/create-paperclip-plugin/src/entrypoints.test.ts
server/src/__tests__/company-skills-catalog-service.test.ts
server/src/__tests__/company-skills-routes.test.ts
server/src/__tests__/company-portability.test.ts`.
- Passed: `pnpm exec vitest run
server/src/__tests__/workspace-runtime.test.ts -t "default
branch|origin/master|symbolic-ref"`.
- Attempted: full `server/src/__tests__/workspace-runtime.test.ts`. Four
provisioning tests failed while seeding an isolated worktree database
from the local Paperclip instance because the local plugin schema dump
contains a duplicate-column foreign key
(`plugin_content_machine_18a7bc327b.content_case_signals`). The
default-branch tests touched by the rebase conflict passed in the
focused run above.
- Checked final diff: no `pnpm-lock.yaml`, no `.github/workflows`, and
no migration-file changes relative to `master`.
## Risks
- Medium: this is a broad skills/catalog change touching CLI, server
APIs, shared contracts, adapter skill sync, and UI.
- Catalog validation and reset semantics need careful reviewer attention
because they affect reusable company setup and portability.
- No database migrations are included in this PR, so there is no
migration ordering/idempotency risk in the final diff.
- No lockfile is included by design; dependency resolution will be
handled by the repository lockfile workflow.
## Model Used
- OpenAI Codex coding agent based on GPT-5, running in Paperclip via the
`codex_local` adapter with shell, git, GitHub CLI, and code-editing tool
access. Exact hosted model build/context-window metadata is not exposed
in this runtime.
## 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 run targeted tests locally and documented the local
workspace-runtime seed failure above
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, screenshots were intentionally
omitted per PAP-10124 instructions; UI behavior is covered by tests and
reviewer inspection
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Remote-managed adapters need sandbox/environment execution to behave
like real agent runs, not just local host probes.
> - The Cloudflare sandbox path was the weakest leg in the SSH +
Cloudflare QA matrix because bridge execution could truncate output,
time out long-running installs, and under-provision the worker instance.
> - That made several adapters fail for reasons unrelated to their
actual business logic, which blocks confidence in Paperclip's non-local
environment model.
> - This pull request hardens the Cloudflare bridge/runtime path and
adjusts sandbox probe budgets so adapter verification matches the
measured behavior of the fixed environment.
> - It also corrects the Pi sandbox install command so the QA matrix
exercises a real, supported install path.
> - The benefit is a materially more reliable SSH + Cloudflare adapter
matrix with fewer false negatives and clearer failure boundaries.
## What Changed
- Switched the Cloudflare bridge worker instance type to `standard-2`
for the QA-matrix execution path.
- Raised Cloudflare bridge/plugin-worker timeout budgets and added SSE
keepalives so long-running install/exec calls can complete instead of
dying at the transport layer.
- Fixed Cloudflare bridge-channel command handling to avoid dropped
final stdout chunks on short-lived execs.
- Made Claude, OpenCode, and Cursor sandbox probe timeouts
configurable/sandbox-aware, then tightened the defaults to the measured
post-fix range.
- Updated the Pi sandbox install command to use the package currently
installed by the official `pi.dev` installer, pinned to a specific npm
version.
- Added/updated tests around Cloudflare bridge behavior and adapter
sandbox probe paths.
## Verification
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/adapter-opencode-local typecheck`
- `pnpm --filter @paperclipai/adapter-cursor-local typecheck`
- `pnpm vitest run packages/adapters/cursor-local
packages/adapters/claude-local packages/adapters/opencode-local
packages/adapters/pi-local packages/plugins/sandbox-providers/cloudflare
server/src/services/__tests__/plugin-worker-manager.test.ts`
- Manual QA on the dedicated dev instance using the SSH + Cloudflare
environment matrix (`ENV-29` through `ENV-40`). Clean end-to-end passes:
SSH `claude_local`, `codex_local`, `cursor`, `gemini_local`; Cloudflare
`claude_local`, `codex_local`, `cursor`, `gemini_local`.
## Risks
- Cloudflare sandbox cost increases because the bridge worker now runs
on `standard-2` instead of `lite`.
- Higher timeout ceilings can delay surfacing truly hung Cloudflare
bridge calls, even though they remove transport-level false negatives.
- The manual heartbeat matrix still exposed follow-on
execution/sync/disposition bugs in `opencode_local` and `pi_local`;
those are not fixed by this PR.
## Model Used
- OpenAI `gpt-5.4` via Paperclip `codex_local`, reasoning effort `high`,
tool use enabled, repo search enabled.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots (not applicable)
- [x] I have updated relevant documentation to reflect my changes (not
applicable)
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
dependabot[bot]
Nicky Leach
Dotta
LeeJ
scotttong
Devin Foley
Michael Nguyen
LeonSGP
Lennie Sliwinski
uky333
nullEFFORT
kengraversen
NyDamon
Danial Jawaid