## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agents need a governed way to request app connections during issue
work.
> - The catalog now describes the available providers and setup methods.
> - A request must become a durable, company-scoped intent before an
operator acts on it.
> - This pull request adds that intent runtime across server, agent,
CLI, and shared contracts.
> - The benefit is a safe bridge from agent need to operator-approved
setup.
## Linked Issues or Issue Description
Refs #11965
This is stack 7 of 11. It depends on stack 6 and replaces another
reviewable part of #11965.
## What Changed
- Add connection intent types, validation, service logic, and routes.
- Add agent runtime tools and CLI support for connection requests.
- Add issue-thread interaction support for connection intents.
- Add runtime, route, adapter, and contract tests.
- Hold the final resolved-continuation row lock through asynchronous
adapter preparation until an actual process spawn, so parking or
reassignment cannot cross that boundary.
- Report Hermes Gateway's first remote run request through the shared
dispatch hook so the resolved-intent lock is released at the true
dispatch boundary.
- Revalidate the addressed user's live non-viewer membership and
connection-management authority for every intent mutation, including
OAuth completion.
## Verification
- `pnpm --filter @paperclipai/server typecheck`
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/tool-access-service.test.ts`
- Result: 176 tests passed.
- `pnpm build`
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/heartbeat-stale-queue-invalidation.test.ts` (32 passed;
includes non-process dispatch lock-release coverage)
- `pnpm exec vitest run --project @paperclipai/server
server/src/__tests__/connection-intents-service.test.ts -t
"addressed-user mutation"` (1 passed)
- `pnpm exec vitest run --project @paperclipai/server
server/src/__tests__/tool-access-service.test.ts -t "binds OAuth
callback completion to the initiating board session"` (1 passed)
- `pnpm --filter @paperclipai/hermes-paperclip-adapter test --
src/gateway/server/execute.test.ts` (23 passed; includes dispatch-hook
ordering and exactly-once coverage)
- `pnpm --filter @paperclipai/hermes-paperclip-adapter typecheck`
## Risks
- A malformed intent could create an unusable operator request.
- Validators and company checks reject invalid or cross-company
requests.
- The final continuation gate holds the issue row lock through adapter
preparation until process or remote dispatch; later operator changes use
the normal active-run interruption path.
- The change does not add a database migration.
> I checked `ROADMAP.md`. This stack continues the existing app
connection work from #11965 and does not duplicate another planned item.
## Model Used
OpenAI Codex, GPT-5. The runtime model ID and context window were not
exposed. The model used reasoning, tool use, and code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have linked the public source pull request with `Refs #`
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id 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
> - Paperclip uses adapters to connect agents and model providers to its
control plane
> - The sandbox login panel supports displayed-code login for selected
adapters
> - Grok users need the same login path and a private credential home
for later runs
> - This pull request adds Grok support to the shared device-login path
and preserves the existing Codex path
> - The benefit is one secure login flow for both adapters with
company-scoped credential storage
## Linked Issues or Issue Description
**Agent or provider**
Grok Local needs displayed-code login support in the sandbox login
panel.
**Why this adapter is useful**
This change lets users sign in to Grok from the sandbox login panel. It
also gives later Grok runs access to the stored credential.
**How the agent is invoked**
The Grok local adapter uses its login command through the shared
displayed-code login flow. Later runs receive the managed home through
`GROK_HOME`.
**Additional context**
The change uses adapter-scoped login lifecycle handling. It stores the
credential in a company-scoped directory with mode `0700`, and it stores
the credential file with mode `0600`.
## What Changed
- Rename the shared device-login modules to adapter-neutral names.
- Scope the shared login lifecycle to a closed adapter set.
- Return the device-login URL that the provider prints.
- Add the Grok prompt parser, login command, capability, and login panel
entry.
- Store the Grok credential in a private, company-scoped home directory.
- Pass `GROK_HOME` to later Grok runs.
- Add tests for the Grok adapter, the Daytona sandbox provider, the
server login path, and the user interface.
## Verification
- Run `pnpm vitest run
packages/adapters/grok-local/src/server/adapter-auth-promotion.test.ts`.
- Run the Grok adapter package suite.
- Run the Daytona sandbox provider suite.
- Run the server device-login suites.
- Run the user interface suite.
- Confirm the full CI suite passes.
## Risks
The change extends shared login lifecycle code to another adapter. A
regression could affect Codex login. The credential path uses explicit
`chmod` calls to keep the directory at mode `0700` and the file at mode
`0600`.
## Model Used
OpenAI Codex, GPT-5. The runtime used tool calls and code review
support. The runtime did not provide 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 (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Paperclip Runner now has protocol, provider, tool, package,
persistence, and hidden server boundaries.
> - The server still cannot select that path for a real agent heartbeat.
> - A new runtime must not change any existing direct adapter.
> - An experimental runtime must fail closed when its rollout flag is
off.
> - This pull request adds one guarded Codex vertical slice through
runnerd.
> - The benefit is a production-built runner path that users cannot
start by default.
## Linked Issues or Issue Description
Refs #11962
Refs #12111
Refs #12169
Refs #12176
**Subsystem affected**
Cross-cutting. The change affects the runner package, server
orchestration, shared settings, and adapter configuration UI.
**Problem or motivation**
The hidden PRP coordinator cannot execute a real heartbeat. The
application also needs an explicit rollout boundary before it can expose
the experimental runner. Existing direct adapters must keep their
current execution and finalization behavior.
**Proposed solution**
Add `paperclip_runner` as a Codex-only adapter behind the default-off
`enableNativeRunner` instance flag. Select the native runtime only for
that adapter. Persist the run binding before runnerd starts. Wait for
the durable PRP result and terminal event. Resume the real Codex
provider thread on later heartbeats. Keep persisted native runs readable
and recoverable after the flag changes.
**Alternatives considered**
The server could route `codex_local` through runnerd. That option would
change an existing adapter and weaken rollback safety. The server could
expose all providers now. That option would add unreviewed provider
behavior. The build could depend on a prebuilt runner binary. That
option would make source builds architecture-dependent and difficult to
verify.
**Roadmap alignment**
This work supports the shipped enforced-outcomes, governed-tool, and
self-healing-run milestones. It does not add a new roadmap surface. It
is the guarded execution step after the merged hidden runner boundaries.
**Additional context**
This is the next replacement for the closed large runner pull request.
Task-thread presentation remains a separate follow-up so this change can
preserve the current direct-adapter UI.
## What Changed
- Add `paperclip_runner` as an explicit Codex-only adapter.
- Add the default-off `enableNativeRunner` instance flag.
- Reject fresh create, hire, import, switch, and execution requests
while the flag is off.
- Allow edits to persisted runner agents while the flag is off.
- Recover an already persisted native run even after the flag is
disabled.
- Keep every built-in direct adapter on its existing runtime path.
- Persist an immutable native run binding and revisioned completion
contract before runnerd starts.
- Execute server to PRP to runnerd to Codex to server through the hidden
coordinator.
- Validate the durable result against the terminal event and exact
completion criteria before finalization.
- Preserve the Codex provider thread ID and use `thread/resume` on the
next heartbeat.
- Strip unsupported Codex configuration fields from the experimental
adapter.
- Build a target-native release runner binary from source and vendor it
into the server distribution.
- Install Rust only in the Docker build stage. Do not add a workflow or
lockfile change.
- Stop the runner process group on completion, cancellation, and forced
shutdown.
## Verification
- Run `pnpm --filter @paperclipai/paperclip-runner check:all`. All 69
TypeScript tests and 58 Rust tests pass. Protocol, conformance, replay,
formatting, and generated-file checks pass.
- Run the 12 focused adapter, settings, runtime-selection, coordinator,
direct-isolation, and real Codex integration test files. All 186 tests
pass.
- The real integration test uses PostgreSQL, HTTP, WebSocket, runnerd,
and a fake Codex app server. It proves one `thread/start` followed by
one `thread/resume`.
- Run `pnpm -r typecheck`.
- Run `pnpm build`.
- Run `pnpm check:token-gates`.
- Build the Docker `build` target from a clean context. Confirm that the
server distribution contains an executable `paperclip-runnerd` built
with Debian Rust 1.85.
- Start the server through the source-mode tsx entry point with the
package `dist` directory absent. Confirm the vendor shim resolves source
exports and the server boots.
- Run `pnpm test:run` twice. On this macOS host, 405 files pass and 1
file skips. Eight untouched workspace and loopback tests fail because
macOS resolves `/tmp` and `/var` through `/private` and because
PID-derived test ports exceed 65535. Linux CI must pass the full suite.
- Confirm that the diff contains 52 files. Confirm that it contains no
`.github` or `pnpm-lock.yaml` change.
## Risks
- The feature flag is off by default. A fresh native start fails with a
stable error while the flag is off.
- A persisted native run remains recoverable after the flag changes.
This prevents rollout changes from corrupting recorded work.
- Only local Codex execution is accepted. Other providers and remote
work modes fail closed.
- Existing direct adapters do not start runnerd, create native rows, use
native status arbitration, or enter native finalization.
- The runner receives its one-use bootstrap ticket through the child
environment. The server does not put the ticket in command arguments or
logs.
- The server validates the company, task, agent, run, runner, session,
completion contract, result, and terminal binding before it accepts
completion.
- The build compiles a target-native Rust binary. Cross-platform release
packaging remains a later concern. Source builds and Docker builds
compile for their current target.
- Docker needs enough build memory for the existing server TypeScript
compile. The Docker build stage sets a 4 GB V8 heap limit.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex with GPT-5. The exact deployment ID and context-window
size are not exposed. The model used agentic reasoning, repository
tools, code execution, 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 applicable tests pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Agent adapters use provider-specific login flows
> - Codex device login needs a live pseudo-terminal (PTY), while the
shared channel still uses Claude-specific names
> - The old streamed-exec path does not provide the prompt transport
that Codex needs
> - This pull request moves Codex device login to the shared login PTY
and removes the dead streamed-exec path
> - The benefit is one controlled login transport with fail-closed
capability checks and safer credential reads
## Linked Issues or Issue Description
**Problem or motivation**
Codex device login used a streamed-exec path that did not provide the
required prompt transport. The shared login channel also exposed
Claude-specific names outside Claude code.
**Expected behavior**
The host selects a fixed login command from trusted adapter data. Codex
login uses the provider login PTY. Providers without that capability
fail closed.
**Proposed solution**
Use a server-controlled session home, create and validate it as a fresh
0700 directory, read credentials from one validated descriptor, and
rename shared channel names to the neutral login PTY family.
**Alternatives considered**
Keep the shared login PTY as the single transport. Do not keep the
removed streamed-exec path because it cannot provide the required prompt
transport.
**Roadmap alignment**
This change supports the planned login transport work. It does not add a
separate roadmap item.
## What Changed
- Route Codex device login through the shared login PTY transport.
- Select the login command from a closed internal command key.
- Carry a server-controlled session home through the launch contract.
- Create and validate the session home as a fresh 0700 directory owned
by the login user.
- Read the credential file with descriptor-relative, no-follow path
walking and final descriptor checks.
- Gate the login route and run lease on the provider login PTY
capability.
- Rename shared channel names to the neutral login PTY family.
- Remove the streamed-exec transport value, selector field, driver
branch, and related tests.
- Hide Codex login in the user interface when the provider lacks the
login PTY capability.
## Verification
- Server unit suites pass: 89/89.
- Adapter-utils suites pass: 262/262.
- Codex-local suites pass: 326/326.
- Credential-read reader suite passes: 20/20.
- Daytona login PTY suite passes: 30/30.
- Device-login suites pass: 56/56.
- TypeScript checks pass for server, adapter-utils, and UI.
- GitHub Actions must pass after pull request creation.
- Greptile review must reach 5/5 with no open P2 findings,
recommendations, or follow-ups.
## Risks
- Providers without a login PTY capability lose Codex login support by
design.
- The credential read rejects invalid ownership, mode, type, path, and
size.
- The launch-time sandbox directory race remains outside the threat
model because the login runs inside the sandbox and a hostile sandbox
already controls its credential.
## Model Used
OpenAI Codex, GPT-5, tool use and code review assistance. The exact
context window and reasoning mode are 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 is the open source app people use to manage AI agents for
work.
> - Paperclip runs across the CLI, server, adapters, plugins, CI, and
container images.
> - These surfaces declared different Node.js versions from 20 through
24.
> - A newer `@types/node` major can expose APIs that the supported
runtime does not provide.
> - Node.js 20 is no longer a suitable project baseline, and Node.js 24
is the current LTS line.
> - This pull request sets Node.js 24.11.0 as one repository-wide
baseline, adds a drift check, and gives users actionable startup
guidance when their runtime is too old.
> - The benefit is one clear runtime contract for development, release,
installation, and published packages.
## Linked Issues or Issue Description
Refs #2734
Refs #11727
Refs #739
## What Changed
- Require Node.js 24.11.0 or newer in all 42 package manifests and
runtime checks.
- Use Node.js 24 in GitHub Actions, Docker images, smoke images, sandbox
setup, portable installs, and esbuild targets.
- Align every direct `@types/node` declaration on `^24.0.0`.
- Prevent Dependabot from opening major `@types/node` upgrades without a
matching runtime decision.
- Add `.nvmrc` and a CI policy check for Node version drift.
- Update ACP version gates, tests, and user documentation for the new
minimum.
- Print a non-blocking warning on CLI and server startup when Node is
unsupported, with remediation through a version manager or the
documented downloaded `install.sh` workflow.
- Deduplicate that warning when `paperclipai run` boots the CLI and
server in the same process.
## Verification
- `node scripts/check-node-version-policy.mjs`
- `node --check scripts/check-node-version-policy.mjs`
- `node --check cli/esbuild.config.mjs`
- `node --check scripts/generate-npm-package-json.mjs`
- `bash -n scripts/install.sh scripts/test-install-sh-docker.sh
scripts/e2e-install-lifecycle.sh`
- Parsed all 42 package manifests and confirmed `engines.node` is
`>=24.11.0`.
- `git diff --check`
- `vitest run
packages/adapter-utils/src/sandbox-install-command.test.ts` passed with
3 tests.
- `vitest run cli/src/node-version.test.ts` passed with 4 tests.
- Directly exercised the shared warning helper for unsupported-version
messaging and same-process deduplication.
- The focused exe.dev suite could not resolve the locally unbuilt plugin
SDK from this isolated worktree. A full offline workspace install was
also blocked because the package-manager signature verifier requires
registry access. The full suite was not run locally; draft CI performs a
clean install and evaluates the wider impact.
## Risks
- This is a breaking runtime change for users, plugins, and deployments
that still use Node.js 20 or 22.
- Published workspace packages will now produce an engine warning or
failure in strict package managers on older Node.js releases.
- Node.js 24 can reveal dependency, native module, Playwright, or agent
CLI compatibility issues in CI.
- The bootstrap installer now installs Node.js 24 when the current
runtime is older than 24.11.0.
- The portable sandbox fallback is pinned to Node.js 24.11.0 and depends
on that upstream tarball remaining available.
- Unsupported runtimes continue booting after a warning, so a later
incompatibility can still fail at its point of use.
- The CLI and server share the warning policy through the published
`@paperclipai/shared` package; packaging checks must keep that subpath
export available.
- This PR does not commit `pnpm-lock.yaml` because repository policy
assigns lockfile generation to CI.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex based on GPT-5. The exact deployment ID and context
window are not exposed in this session. Reasoning, repository tools,
shell execution, and GitHub tools were 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] 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 agent adapters (`claude_local`, `gemini_local`, `grok_local`,
…) are the integration surface that lets Paperclip run coding CLIs on
the host machine
> - The Kimi Code CLI (`kimi`, Moonshot AI) has a documented
non-interactive mode, `kimi -p --output-format stream-json` with session
resume via `kimi -r`, but Paperclip has no built-in adapter for it
> - So Kimi users (especially Kimi membership / OAuth subscribers)
cannot onboard their CLI to Paperclip agent teams
> - This pull request adds a complete built-in `kimi_local` adapter
(both execution engines, session management, instructions + skills
delivery, thinking-effort control, environment test, UI and CLI modules,
docs) following the established `gemini_local`/`grok_local` package
pattern
> - Kimi Code ships an ACP server (`kimi acp`), so the adapter runs on
Paperclip's shared acpx engine by default (streaming transcript with
live tool status, like `claude_local`/`gemini_local`) and falls back to
a headless CLI lane (`kimi -p --output-format stream-json`) when ACP
prerequisites are unavailable
> - The benefit is that Kimi Code becomes a first-class Paperclip agent
lane: selectable in the UI, resumable across heartbeats, with the same
operating context (instruction bundle, skills, effort) and streaming
transcript the other local adapters get
## Linked Issues or Issue Description
- Supersedes #9880 (same branch; expanded from the CLI-only lane into a
complete adapter with the default ACP engine lane, control-plane skill
install, and live transcript wiring)
- Refs #9879 (adapter request for Kimi Code CLI, filed with this PR)
- Refs #163 (original Kimi support request)
Duplicate/related prior PRs, per the dedup search (both appear stale: no
updates or maintainer review since May 2026, and both target an older
Kimi CLI interface; calling them out for reviewer context per
CONTRIBUTING.md):
- Refs #6276 (`feat: add kimi-local adapter`): targets an older
array-based content format (`{type: think}`/`{type: text}` blocks), not
the current documented stream-json schema
- Refs #5202 (`feat(adapter): add Kimi CLI local adapter with Wire
protocol support`): builds on a `--wire` JSON-RPC interface that current
Kimi Code CLI (0.27.0) no longer documents; the current documented
headless interface is `-p --output-format stream-json`
This PR is a fresh implementation against current master and the
currently documented/verified Kimi CLI behavior (see Verification).
Happy to fold in anything useful from the earlier attempts if a reviewer
prefers.
## What Changed
- **New adapter package** `packages/adapters/kimi-local`
(`@paperclipai/adapter-kimi-local`), modeled on
`gemini-local`/`grok-local`:
- `src/server/execute.ts`: spawns `kimi -p <prompt> --output-format
stream-json` (argv array, no shell), `-m <model>` only when configured,
`-r <sessionId>` when the stored session cwd matches the run cwd,
automatic fresh-session retry on unrecoverable-session errors,
headless-safe env (`CI=1`, `NO_COLOR=1`, `KIMI_CODE_NO_AUTO_UPDATE=1`,
`TERM=dumb`; user-configured values win), full remote (ssh/sandbox)
execution lane with runtime install via `@moonshot-ai/kimi-code`
- **Instruction bundle delivery**: the prompt path directive now names
the sibling instruction files (`./HEARTBEAT.md`, `./SOUL.md`,
`./TOOLS.md`) alongside the prepended entry file, and local runs pass
`--add-dir <instructions-dir>` so Kimi can actually open them (matching
`claude_local`). Without this, only the entry file reached Kimi and
agents improvised the operating workflow that `HEARTBEAT.md` documents
- **Thinking effort**: a configured `effort` is forwarded as the
`KIMI_MODEL_THINKING_EFFORT` operational override (Kimi has no
per-invocation effort flag). It is only sent for models that advertise
`support_efforts` (currently `kimi-code/k3`) to avoid provider
rejections, and `medium` maps to `high` since Kimi has no medium tier
(`low`/`high`/`max` pass through)
- **Skills delivery**: desired Paperclip skills are delivered via Kimi's
`--skills-dir` flag from a dedicated per-run directory (a local
snapshot, or the synced snapshot on remote targets), so skills load
reliably and in isolation. Paperclip never overwrites the shared
`$KIMI_CODE_HOME/skills` home, so skills installed by the operator or
other agents are left intact. `--skills-dir` is only passed when at
least one skill is desired, so unconfigured agents keep Kimi's default
skill discovery
- **Live run status**: the adapter now forwards each streamed
stream-json line to `onEvent` (assistant `content` as an assistant
snippet, `tool_calls` as tool-name events), which drives the
issue-thread activity indicator (`currentToolName` /
`lastAssistantSnippet` / `lastEventAt`). Previously the adapter only
wrote the raw run log, so the issue thread showed a stale "no output for
N s" line with no tool or reasoning context while Kimi worked. Tool
results are omitted so the last meaningful "Using X" / snippet is not
overwritten by a generic label
- `src/server/parse.ts`: parses the verified Kimi stream-json event
shapes (`assistant` text, `assistant.tool_calls` with JSON-string
arguments, `tool` results, trailing `meta.session.resume_hint` for
session-id capture) plus failure classifiers (`kimi_auth_required`,
transient network, unrecoverable session). A signaled exit (null exit
code, not a timeout) is now reported as a failure rather than coalesced
to success, and the error message names the terminating signal
- `src/server/skills.ts`: lists/syncs Paperclip skills for the adapter's
skill-management surface
- `src/server/test.ts`: environment test covering CLI resolution + `kimi
--version`, cwd check, auth detection (OAuth credential dirs, keyed
`[providers.*]` in config.toml, or the `KIMI_MODEL_NAME` +
`KIMI_MODEL_API_KEY` env pair), and a live hello probe
- `src/ui/` (stdout-line parser for transcripts, config builder) and
`src/cli/` (stream event formatter) modules
- Root metadata: three managed model aliases
(`kimi-code/kimi-for-coding`, `kimi-code/kimi-for-coding-highspeed`,
`kimi-code/k3`), effort-capable-model metadata (`EFFORT_CAPABLE_MODELS`,
effort mapping helpers), `agentConfigurationDoc`
- Tests: 101 tests across parse, execute (args building, resume gating,
retry, auth error code, timeout, signaled-exit failure, effort
forwarding/gating/mapping, `--add-dir` instructions directive,
`--skills-dir` gating, `onEvent` runtime-event forwarding), ACP engine
(engine resolution, acpx config build, node-version gate), ACP
transcript delegation, environment test, UI parse/build-config
- **ACP engine lane (default)** (`src/server/acp.ts` + shared
`adapter-utils/acpx-engine`): Kimi Code ships an ACP server (`kimi
acp`), so `kimi_local` now runs on Paperclip's shared acpx engine by
default, matching `claude_local`/`codex_local`/`gemini_local`. The
issue-thread transcript streams live (assistant text deltas, tool calls
with a `pending`->`completed` status lifecycle) instead of the CLI
lane's bursty complete-message output. Registered `kimi_local -> "kimi"`
in `ACPX_ADAPTER_AGENT_IDS` and resolved the built-in agent command to
`kimi acp`; `execute.ts` dispatches to the ACP executor first with an
automatic CLI fallback when ACP prerequisites fail (`engine=acp`
requires ACP, `engine=cli` pins the headless lane); `index.ts` falls
back to the shared acpx session codec; the UI/CLI delegate `acpx.*`
events to the shared acpx transcript parser and event formatter. The
headless CLI lane (above) remains as the fallback
- **Registration** (one entry each, mirroring existing adapters): server
adapter registry + `BUILTIN_ADAPTER_TYPES`, `AGENT_ADAPTER_TYPES`
(shared), UI adapter registry + display registry (`Kimi Code`, Moon
icon) + capabilities defaults, CLI adapter registry, `Dockerfile`
(package copy + `npm install --global @moonshot-ai/kimi-code@latest`),
`vitest.config.ts` workspace, `scripts/release-package-manifest.json`
- **Behavioral sets** mirroring `gemini_local` (Kimi resumes sessions
the same way): `GIT_SENSITIVE_LOCAL_ADAPTER_TYPES`,
`SESSIONED_LOCAL_ADAPTERS` (heartbeat + recovery),
`REMOTE_MANAGED_ADAPTERS`, ssh/sandbox execution-target allow-lists,
`ADAPTER_DEFAULT_RULES_BY_TYPE` (`timeoutSec: 0`, `graceSec: 15`), and
`LEGACY_SESSIONED_ADAPTER_TYPES` + `ADAPTER_SESSION_MANAGEMENT` in
adapter-utils
- **UI touch-points**: New Agent default-model branch, AgentConfigForm
command map (`kimi_local: "kimi"`) + model defaults + a Kimi-specific
thinking-effort option list (`Low`/`High`/`Max`, reflecting Kimi's tiers
rather than borrowing Claude's), OnboardingWizard (command map, model
default, `kimi login` / `KIMI_MODEL_NAME + KIMI_MODEL_API_KEY` auth
hints, manual-debug command line), InviteLanding enabled adapters
- **Control-plane skill install** (`cli/src/commands/client/agent.ts`):
`paperclipai agent local-cli` seeded the Paperclip control-plane skills
into `~/.codex/skills` and `~/.claude/skills` so Codex/Claude agents
auto-discover the API reference every run. Kimi had no equivalent
target, so `kimi_local` agents began each session without the
control-plane skill and rediscovered routes (e.g. the company-scoped
`POST /api/companies/{companyId}/issues`) by trial and error. Added
`~/.kimi-code/skills` (honoring `KIMI_CODE_HOME`) as a third install
target for parity. Independent of the per-run `--skills-dir` delivery,
which only applies to explicitly configured skills.
- **Docs**: `docs/adapters/kimi-local.md` (prerequisites, auth options,
config fields including `effort`, session resume, instruction bundle,
skills delivery, control-plane skill install) + a row in
`docs/adapters/overview.md`
Out of scope (deliberately): model profiles, built-in agent
`allowedAdapterTypes` additions.
## Verification\n\nCurrent-master rebase verification (OpenAI Codex,
2026-08-03): 13 focused files / 231 tests pass; adapter-utils, server,
UI, CLI, and Kimi adapter typechecks pass; full repository build and UI
token gates pass. The branch is conflict-free against master at head
`1249df117c5e12e5771b9a570a6340866450619e`.\n\nAutomated (all from repo
root, pnpm 9.15.4, Node 22):
- `vitest run packages/adapters/kimi-local`: 89/89 pass (includes
coverage for the instruction `--add-dir` directive, effort
forwarding/gating/mapping, `--skills-dir` gating, the signaled-exit
failure path, and `onEvent` runtime-event forwarding with cross-chunk
line buffering)
- `vitest run server/src/__tests__/adapter-registry.test.ts
server/src/__tests__/adapter-routes.test.ts
server/src/services/heartbeat-stop-metadata.test.ts
ui/src/adapters/adapter-display-registry.test.ts`: 37/37 pass
- `vitest run cli/src/__tests__/skills.test.ts`: 13/13 pass (the
control-plane skill install target follows the existing Codex/Claude
install path, whose symlink logic is unchanged)
- `vitest run packages/shared`: 307/307 pass; `vitest run
packages/adapter-utils`: pass except one pre-existing, unrelated failure
(`mcp-isolation.integration.test.ts` requires Claude CLI ≥ 2.1.207; host
has 2.1.185, fails identically on unmodified master)
- `pnpm --filter @paperclipai/adapter-kimi-local typecheck|build`, plus
typecheck of `server`, `ui`, `cli`, `adapter-utils`: all clean
- `pnpm install --frozen-lockfile`: passes (the PR diff itself contains
no lockfile changes, per repo policy; verified against a locally
regenerated lockfile)
- `node scripts/check-no-git-push.mjs` and `node
scripts/check-forbidden-tokens.mjs`: pass
- CI note: the `policy` job's release-bootstrap step is expected to stay
red until a maintainer bootstraps the first npm publish of
`@paperclipai/adapter-kimi-local`; see the CI Note for Maintainers
comment. All other contributor-actionable checks are green.
Manual end-to-end (real Kimi CLI 0.27.0, OAuth login, dev server on an
isolated instance):
1. Server `GET /api/adapters` lists `kimi_local` as builtin with correct
capability flags; models endpoint returns the three Kimi models
2. `POST .../adapters/kimi_local/test-environment`: all checks pass,
including a live `kimi -p` hello probe
3. Created a `kimi_local` agent and invoked two heartbeats: run 1
spawned `kimi -p ... --output-format stream-json`, Kimi used its `Read`
tool, produced the expected answer, and the session id was captured from
the `session.resume_hint` meta event; run 2 resumed the **same** Kimi
session (`sessionIdBefore == sessionIdAfter`) via `-r`
4. UI: adapter appears in the New Agent dropdown; selecting it shows the
Kimi command placeholder, the three models, and the Kimi config fields;
the run transcript renders Kimi tool calls via the adapter's stdout
parser
The instruction-bundle, thinking-effort, and `--skills-dir` changes
landed after the manual run above. They are covered by the unit tests
listed under Automated, and the Kimi CLI flags they rely on
(`--add-dir`, `--skills-dir`, `KIMI_MODEL_THINKING_EFFORT`) were
confirmed against the installed Kimi Code CLI 0.27.0 (`kimi --help`,
config-file thinking-effort docs).
Screenshots (assets branch on the fork, not part of the diff):
## Risks
- Low risk to existing behavior: the change is additive, one new
workspace package plus single-entry registrations alongside existing
adapters; no existing adapter code paths are modified.
- The adapter invokes the locally installed `kimi` CLI; like other local
adapters, run behavior depends on the host's Kimi version. The parser is
written against the documented/verified 0.27.0 stream-json schema and
degrades gracefully (malformed lines are skipped, failures surface as
run errors).
- `--skills-dir` overrides Kimi's auto-discovery of user and project
skills for the run. This is intentional (paperclip-managed agents get a
reproducible, isolated skill set), and it is only passed when at least
one Paperclip skill is desired, so unconfigured agents keep default
discovery.
- Thinking effort is only forwarded to models that advertise
`support_efforts` (currently `kimi-code/k3`); `EFFORT_CAPABLE_MODELS`
must be extended when more Kimi models gain support, otherwise a
configured effort is silently ignored for them.
- `Dockerfile` now installs `@moonshot-ai/kimi-code@latest` globally
alongside the other agent CLIs, so image size increases slightly.
- Maintainer action needed for the npm bootstrap gate: the `policy`
job's release-bootstrap step fails until the first npm publish of
`@paperclipai/adapter-kimi-local` (the gate from #5146 that every new
adapter package has passed through). Enrollment with `publishFromCi:
true` is required by the manifest validator (dropping the entry,
`false`, or `private` are all rejected), so this is intentionally left
to a maintainer. Remaining CI lanes are expected to run once it is done.
## Model Used\n\n- **Current-master rebase, conflict adaptation, and
registry-parity coverage:** OpenAI, **GPT-5 Codex** (Codex agent; exact
serving model ID and context-window size were not exposed to the
runtime), with repository, shell, Git, and GitHub tooling. It preserved
Hawik’s commit authorship, reconciled ACPX and environment-capability
changes, added current registry tests, and ran the verification
above.\n- **Adapter implementation and initial review:** Moonshot AI,
**Kimi K3 Coding** (latest), via **Kimi Code CLI v0.27.0**
(`kimi-code/k3` alias, 1M-token context window, thinking mode, agentic
tool use). The CLI agent explored the repo, wrote the adapter
implementation (delegated to a coder sub-agent of the same model), ran
tests, and drafted the first version of this PR body. A second
model-driven review pass (read-only, same model) audited the diff for
security/correctness before submission; its findings (shell-quoting
hardening, auth-detection false positive, session-compaction
registration, test gaps) were fixed and are included.
- **Harness-context fixes and review responses:** Anthropic, **Claude
Opus 4.8** (`claude-opus-4-8`) via Claude Code. Diagnosed from run logs
that Kimi received only the entry instructions file (not the
`HEARTBEAT.md`/`SOUL.md`/`TOOLS.md` bundle) and that `effort` was never
wired, then implemented the instruction `--add-dir` delivery,
`KIMI_MODEL_THINKING_EFFORT` forwarding, and `--skills-dir` skill
delivery, added the accompanying tests and docs, and addressed the
automated review comments (preserving external skills on remote sync,
treating a signaled exit as a failure). Also extended the `paperclipai
agent local-cli` installer to seed the control-plane skills into
`~/.kimi-code/skills` for Codex/Claude parity, wired `onEvent` runtime
events so the issue-thread activity indicator reflects Kimi's tool and
reasoning output live, and built the ACP engine lane (`kimi acp` via the
shared acpx engine, default) so the transcript streams with live tool
status like the other ACP adapters. The Kimi CLI flags, subcommand, and
env var relied on here were verified against the installed Kimi Code CLI
0.27.0.
- All CLI behaviors claimed here (`-p`, `--output-format stream-json`,
`-r` resume, event shapes, `--add-dir`, `--skills-dir`,
`KIMI_MODEL_THINKING_EFFORT`) were verified empirically against the
installed Kimi CLI, not assumed.
## 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 *(only the release-bootstrap step
remains red, pending the maintainer npm publish described in Risks)*
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
*(will address all Greptile comments as they arrive)*
- [x] I will address all Greptile and reviewer comments before
requesting merge
---
## Maintainer Addendum (2026-08-20)
The shared acpx-engine and issue-chat changes (run-summary segmentation,
placeholder tool-event coalescing,
`ISSUE_CHAT_TRANSCRIPT_MAX_VISIBLE_ENTRIES` 30 → 400, live-reasoning UI)
have been **extracted to #11761** so the cross-adapter behavior changes
review and revert independently — both commits there preserve @hawikk's
authorship. This PR is now the kimi-specific adapter only (60 files,
+3,793/−8, essentially pure addition); the only shared-engine touch left
is the `kimi acp` command resolution. `publishFromCi` is `true` — the
package name is bootstrapped on npm.
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Dotta <bippadotta@protonmail.com>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## 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
> - Paperclip provides CLI commands and guidance for operators and
agents
> - The `pnpm paperclipai` script can pass argument values through a
shell
> - Shell re-parsing can execute command substitutions inside quoted
values
> - This pull request routes guidance through inert-argv `npx
paperclipai` commands and adds regression coverage
> - The benefit is safer operator guidance across documentation and
runtime hints
## Linked Issues or Issue Description
This pull request fixes a command-injection-class defect in Paperclip
CLI guidance.
**What happened?**
The `pnpm paperclipai <sub> --flag "$VALUE"` form can re-parse argument
values through a shell. A command substitution inside a quoted value can
execute on the host.
**Expected behavior**
Paperclip guidance must pass CLI values as inert argument values.
Host-derived values must not appear in copyable commands.
**Steps to reproduce**
1. Run a Paperclip guidance command that uses the `pnpm paperclipai`
script.
2. Provide a quoted value that contains a command substitution.
3. Observe that the shell can evaluate the substitution before the CLI
starts.
4. Compare the result with the `npx paperclipai` form.
**Paperclip version or commit**
`5670984b75d109950c968542a0111ebb6967f4da`
**Deployment mode**
All deployment modes that show or use the affected CLI guidance.
**Installation method**
Built from source and installed CLI guidance.
**Agent adapter(s) involved**
Not adapter-specific (core bug).
**Database mode**
Not database-related.
**Access context**
Both.
**Additional context**
The earlier merged PR
[#11343](https://github.com/paperclipai/paperclip/pull/11343) used the
unsafe `pnpm exec paperclipai` form. This fresh PR replaces that
guidance with the safe `npx paperclipai` form.
## What Changed
- Standardize documentation and runtime hints on `npx paperclipai`.
- Remove the broken `pnpm exec paperclipai` guidance.
- Use a static `<host>` placeholder in private-hostname guidance.
- Add regression tests for unsafe forms, continued lines, static hosts,
and offline guidance.
## Verification
- `git diff --check
origin/master...origin/fix/paperclipai-cli-npx-safe-invocation` passes.
- The branch adds `server/src/__tests__/cli-invocation-safety.test.ts`
and updates private-hostname tests.
- CI must run the new tests, typecheck, lint, and build checks.
- Local Vitest execution was not available because this worktree has no
installed Vitest binary.
## Risks
- The change affects operator and agent documentation text.
- The runtime hints now show `<host>` instead of a request-derived host
value.
- No database schema or migration changes exist.
- CI will detect any missed unsafe invocation or type error.
## Model Used
OpenAI GPT-5, exact model ID `gpt-5`, with tool use and code-review
assistance. The model used repository inspection, Git operations, and PR
preparation.
## 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] CI ran the test suites and they pass; local test execution was
unavailable in this worktree
- [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 addressed 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.
> - Paperclip provides CLI guidance to agents and operators through
documentation and runtime messages.
> - Content-bearing `pnpm paperclipai` examples send arguments through a
shell.
> - Shell evaluation can execute command substitutions in untrusted
argument content.
> - Runtime hostname guidance can also place request-derived content
inside a shell command.
> - This pull request uses `npx paperclipai` for content-bearing
guidance and uses a static hostname placeholder.
> - The benefit is safer copy-paste guidance for agents and operators.
## Linked Issues or Issue Description
**Issue type**
Incorrect information
**Where is the issue?**
CLI guidance in `doc/CLI.md`, `skills/paperclip/SKILL.md`,
documentation, and runtime-generated hints.
**What's wrong?**
Content-bearing `pnpm paperclipai` commands can pass argument text
through `/bin/sh`. Shell command substitution in an argument can execute
before the CLI receives the value.
**Suggested fix**
Use `npx paperclipai` for content-bearing commands. Use a static
`<host>` placeholder when runtime guidance displays the allowed-hostname
command.
## What Changed
- Replace content-bearing `pnpm paperclipai` examples with `npx
paperclipai` across the documentation and agent-facing guidance.
- Update runtime-generated CLI hints to use a static `<host>`
placeholder.
- Add safety notes to `doc/CLI.md` and `skills/paperclip/SKILL.md`.
- Add scans and regression tests for unsafe invocation and hostile
hostname headers.
- Keep fixed lifecycle commands and `pnpm --filter @paperclipai/*` build
commands unchanged.
## Verification
- Run `tsc --noEmit` for the changed server files.
- Run `cli-invocation-safety.test.ts`.
- Run `private-hostname-guard.test.ts`.
- Confirm that hostile hostname headers do not enter shown shell
commands.
- Confirm that the three commits contain the required Paperclip
co-author trailer.
## Risks
- This change updates documentation and diagnostic text across many
surfaces.
- Fixed lifecycle and setup commands remain unchanged.
- The tests fail if content-bearing `pnpm paperclipai` guidance returns.
- The change does not alter the CLI argument parser.
## Model Used
OpenAI Codex, GPT-5, tool use, code execution, and repository review
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 orchestrates AI agents for zero-human companies
> - One of its pluggability surfaces is external adapter packages,
loaded at startup by `server/src/adapters/plugin-loader.ts` and routed
through the adapter registry so third parties can override built-in
adapters like `claude_local`
> - `loadExternalAdapterPackage` calls `await import(modulePath)` where
`modulePath` is an absolute filesystem path
> - On Windows that path begins with a drive letter (`C:\…`), which
Node's ESM loader parses as a URL scheme and rejects with
`ERR_UNSUPPORTED_ESM_URL_SCHEME`; the defensive `try/catch` around the
call masks the failure and the builtin adapter silently keeps serving
traffic, so the override never activates
> - `reloadExternalAdapter` in the same file already tries to build a
`file://` URL, but does it via template-string concatenation
(`file://${modulePath}`) which produces a malformed URL on Windows
(`file://C:\…` instead of `file:///C:/…`) — so dev hot-reload of
adapters is broken on Windows even after initial load works on POSIX
> - This pull request swaps both paths to `pathToFileURL()` from
`node:url`, the idiomatic cross-platform conversion
> - The benefit is external adapter packages load reliably on Windows
with no changes required to existing adapters, and the two sibling paths
in the same file stop diverging in their URL-handling discipline
Closes#4286.
## What Changed
- `server/src/adapters/plugin-loader.ts`:
- Import `pathToFileURL` from `node:url`.
- `loadExternalAdapterPackage`: wrap `modulePath` in
`pathToFileURL(modulePath).href` before passing to `import()`.
- `reloadExternalAdapter`: replace `` `file://${modulePath}` `` string
concatenation with `pathToFileURL(modulePath).href` so the cache-bust
URL is well-formed on Windows too (drive letter, UNC, percent-encoding).
Three lines changed + one import. No behavior change on POSIX:
`pathToFileURL("/foo/bar.js").href === "file:///foo/bar.js"`, which
Node's ESM loader accepts identically to the bare path.
## Verification
**Runtime, Windows 11, Node v24, `@paperclipai/server@2026.416.0`:**
Before (installed dist, vanilla):
```
INFO: Loading external adapter package {packageName: "@reforged/adapter-claude-local", modulePath: "C:\\Users\\…\\index.js"}
WARN: Failed to dynamically load external adapter; skipping
err: ERR_UNSUPPORTED_ESM_URL_SCHEME … Received protocol 'c:'
```
After (same dist with the equivalent two-line patch applied):
```
INFO: Loading external adapter package {packageName: "@reforged/adapter-claude-local"}
INFO: Loaded external adapters from plugin store {count: 1, adapters: ["claude_local"]}
```
End-to-end: the override actually services execute calls and its
telemetry fields (e.g. `errorCode: "rate_limited"` on 429) surface into
heartbeat-run records — I've been running this heartbeat through the
override on a vendor-patched copy while drafting this PR.
**Static / logic review:**
- `pathToFileURL` is part of Node's stdlib since v10.12.0, no new dep.
- On POSIX, `path.resolve("/a", "b") → "/a/b"` and
`pathToFileURL("/a/b").href → "file:///a/b"`. `await
import("file:///a/b")` and `await import("/a/b")` both resolve to the
same ESM module — no double-load risk.
- Reload path: the existing cache-bust query (`?t=${Date.now()}`) still
appends cleanly because `pathToFileURL(...).href` returns a normalized
`file:///…` URL with no pre-existing query string.
**Local test suite:** I did not run the full `pnpm test` suite in this
fork — the monorepo test infrastructure (embedded Postgres, pnpm
workspace install) is a significant local-setup cost and this change is
surgical enough that CI should be the source of truth. Happy to iterate
based on CI signal. No existing test directly exercises
`plugin-loader.ts`'s initial-load path.
## Risks
**Low.** This aligns the initial-load path with the already-existing
intent of the reload path (which tried, but imperfectly, to use a
`file://` URL). POSIX behavior is unchanged. The only runtime difference
is that Windows stops throwing and starts loading the adapter — which is
exactly the bug being fixed.
Edge cases worth naming:
- **UNC paths** (`\\server\share\…`): previously broken the same way on
the load path, still broken with `file://` string concat on the reload
path. `pathToFileURL` handles UNC correctly (→
`file:////server/share/…`), so this change also quietly fixes UNC-path
adapter installs on Windows.
- **Bun**: the reload path has a Bun cache-eviction block that keys off
`modulePath` and the old `fileUrl`. Bun accepts both `file://` URLs and
bare paths in its module cache keys, so changing the URL form is
consistent with the existing evict-both pattern (we still evict both
`fileUrl` and `modulePath` after the change).
## Model Used
Claude Opus 4.7 (`claude-opus-4-7`, provider: Anthropic) via Claude
Code, running as the CTO agent in a Paperclip-orchestrated company. 200k
context, tool use. No extended thinking mode. Model authored the patch,
the issue body, and this PR description; human review by the company's
principal (fronc) is pending.
## 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
- [ ] I have run tests locally and they pass — *deferred to CI, see
Verification note*
- [ ] I have added or updated tests where applicable — *no existing
tests for this file; adding one would require stubbing
`adapter-plugin-store` + filesystem, which seemed out of scope for a
3-line fix. Happy to add one on request.*
- [x] If this change affects the UI, I have included before/after
screenshots — *not UI, N/A*
- [x] I have updated relevant documentation to reflect my changes — *no
user-facing docs affected; behavior unchanged on POSIX and now-working
on Windows*
- [x] I have considered and documented any risks above
- [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
> - 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 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 app people use to manage AI agents for
work
> - The adapter layer (hermes-local, process adapters) delegates agent
execution to child processes via `runChildProcess()`
> - `runChildProcess()` accepts an `onSpawn` callback to report child
PID and process group info, but the hermes and process adapters were not
forwarding `ctx.onSpawn` to this call
> - Without PID persistence, the orphan reaper cannot distinguish live
runs from abandoned processes, causing false-positive reaps and 5-minute
timeout errors for active runs
> - This pull request adds `onSpawn: ctx.onSpawn` to both adapter call
sites and declares the option in the `runChildProcess` wrapper type
> - The benefit is that the orphan reaper can now correctly track live
child processes, eliminating false-positive reaps
## Linked Issues or Issue Description
Fixes#8723
Fixes false-positive orphan reaps in hermes-local and process adapters
by forwarding the `onSpawn` callback to `runChildProcess()`. All other
adapters (claude-local, codex-local, cursor-local, gemini-local,
grok-local, opencode-local, pi-local) already forward `ctx.onSpawn` —
these two were the only ones missing it.
## What Changed
- `server/src/adapters/utils.ts`: Added `onSpawn?` to the
`runChildProcess()` options type so callers can forward the callback
- `server/src/adapters/process/execute.ts`: Forward `ctx.onSpawn` to
`runChildProcess()`
- `packages/adapters/hermes/src/server/execute.ts`: Forward
`ctx.onSpawn` to `runChildProcess()`
## Verification
- `pnpm -r typecheck` passes across all packages
- Confirmed all other adapters already forward `ctx.onSpawn` (12 grep
matches across 9 adapter files)
- The 3-line diff is additive only — no existing behavior is changed,
only a previously-ignored callback is now forwarded
## Risks
Low risk. This is a 3-line additive change. The `onSpawn` parameter is
optional (`?`) so existing callers are unaffected. The callback is
already well-established across all other adapters.
## Model Used
Hermes Agent (by Nous Research) — xiaomi/mimo-v2.5-pro via OpenRouter,
with tool use (file editing, git, GitHub API).
## 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
- [x] My branch name describes the change and contains no internal
ticket id
- [x] I have run tests locally and they pass (typecheck passes)
- [x] I have added or updated tests where applicable (N/A — type-level
fix only, no behavioral change)
- [x] I have updated relevant documentation to reflect my changes (N/A —
internal fix)
- [x] I have considered and documented any risks above
---------
Co-authored-by: Zephyr <zephyr@motoyuki.dev>
## 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.
> - Paperclip runs agents through adapters, including built-in local and
gateway-style adapters.
> - Hermes gateway users need to connect Paperclip to an already-running
Hermes API server.
> - The gateway setup flow was missing clear non-local adapter
configuration fields and accepted fewer URL shapes than operators
naturally paste from Hermes.
> - It also surfaced sparse diagnostics when the gateway was unreachable
or when Paperclip generated onboarding prompts for gateway agents.
> - This pull request tightens Hermes gateway configuration, URL
normalization, diagnostics, and onboarding defaults.
> - The benefit is that Hermes gateway setup is easier to complete and
easier to debug without affecting unrelated adapters.
## Linked Issues or Issue Description
No public issue found for this exact follow-up. Related prior/in-flight
Hermes work:
- Refs #2363
- Refs #4359
- Refs #6473
Problem statement:
- **Type:** Adapter follow-up / setup reliability
- **Adapter:** `hermes_gateway`
- **Motivation:** Operators configure `hermes_gateway` against a running
Hermes API server, but the UI and onboarding flow did not expose enough
gateway-specific configuration or diagnostics.
- **Expected behavior:** Paperclip should render the gateway fields,
normalize common Hermes dashboard/API URL inputs, preserve sensible
gateway onboarding defaults, and report reachability failures with
actionable detail.
- **Deployment mode:** Built-in adapter package in the Paperclip
monorepo.
## What Changed
- Added UI config fields for non-local Hermes gateway settings,
including tests for rendering and field behavior.
- Accepted Hermes dashboard URLs by normalizing them to gateway API URLs
for execution.
- Improved gateway reachability and run URL diagnostics.
- Updated Hermes gateway onboarding text/default behavior so join
prompts preserve gateway configuration.
- Added focused server, UI, and adapter tests for the gateway
configuration and onboarding paths.
## Verification
- `pnpm install --frozen-lockfile --prefer-offline`
- `pnpm --filter @paperclipai/hermes-paperclip-adapter exec vitest run
src/gateway/server/execute.test.ts` — 20 passed
- `pnpm exec vitest run
server/src/__tests__/invite-accept-gateway-defaults.test.ts
server/src/__tests__/invite-onboarding-text.test.ts
ui/src/adapters/hermes-gateway/config-fields.test.tsx
ui/src/components/AgentConfigForm.render.test.tsx
ui/src/lib/agent-onboarding-prompt.test.ts` — 23 passed across 5 files
- Confirmed the PR diff excludes `pnpm-lock.yaml` and
`.github/workflows`.
## Risks
Low to moderate risk. The changes are scoped to Hermes gateway
configuration/onboarding and generic non-local adapter field rendering.
The main risk is rejecting an unusual Hermes URL shape that should be
accepted; the normalization tests cover dashboard and API URL variants
added here.
> 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 in a tool-enabled local CLI
environment, with shell/GitHub/Paperclip API access. Exact runtime model
identifier was not exposed in this session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agent adapters are the boundary between the control plane and the
runtimes that actually do work.
> - Hermes support needs to be available as first-class local and
gateway adapters while still preserving the adapter-manager override
path for external packages.
> - The adapter work touches runtime execution, UI adapter metadata,
onboarding prompts, scoped credentials, release packaging, and smoke
coverage, so the handoff needs concrete verification rather than only
unit tests.
> - This pull request adds built-in Hermes local and Hermes gateway
support, keeps external adapter overrides compatible, and
documents/tests the gateway flow end to end.
> - The benefit is that operators can hire Hermes-backed agents without
a manual plugin install, while self-hosted installs can still
override/shadow the built-ins through Adapter manager packages.
## Linked Issues or Issue Description
No public GitHub issue exists for this exact Hermes built-in adapter,
gateway onboarding, and release-source work.
Problem description:
- Hermes local and gateway adapters need a public, reviewable source
path in the monorepo so package artifacts and built-in adapter behavior
match the application source.
- Operators need built-in `hermes_local` and `hermes_gateway` adapter
choices without losing the ability to install external Hermes packages
as overrides.
- Gateway onboarding needs secure defaults for API server URLs, API
keys, and generated agent setup text.
- Hermes-originated task bridge credentials need narrower API-key scope
configuration.
- Related public PRs found during duplicate search include #3027, #2363,
#7544, #7950, #8095, and #8543.
## What Changed
- Added the unified Hermes adapter package with local and gateway
server/UI/CLI exports, config schemas, transcript parsing, model
detection, and package metadata.
- Registered `hermes_local` and `hermes_gateway` as built-in adapters
across shared constants, server registries, CLI packaging, and UI
adapter registries.
- Kept the external adapter override path compatible so installed Hermes
packages can shadow built-ins and restore the built-in parser when
disabled.
- Added Hermes gateway onboarding docs, board-operator docs, Docker
smoke assets, and shell smoke harnesses for join/e2e validation.
- Added scoped task-bridge API-key support, authorization checks,
issue-origin handling, and tests for Hermes-created Paperclip tasks.
- Hardened gateway transport and redaction behavior for API keys,
headers, session data, and smoke diagnostics.
- Updated release packaging/bootstrap checks for the Hermes packages
while leaving `pnpm-lock.yaml` out of the PR per repository policy.
## Verification
Targeted local verification recorded before PR handoff:
- `pnpm --filter @paperclipai/hermes-paperclip-adapter exec vitest run
src/gateway/server/execute.test.ts` — 14/14 passed.
- `pnpm test:hermes-gateway-smoke` — 6/6 passed.
- Hermes package typecheck/build checks passed.
- Focused server/UI adapter tests passed — 31/31.
- Release helper Node tests passed — 18/18.
- `git diff --check origin/master..HEAD` passed.
Fresh Docker E2E smoke evidence:
- Ran `pnpm smoke:hermes-gateway-e2e` on 2026-06-26 with a fresh state
directory and fresh Docker container against a live Paperclip dev
server.
- Hermes direct execution reached `completed`.
- Hermes stop/cancel path reached `cancelled`.
- Hermes gateway created a Paperclip task, Paperclip ran the Hermes
agent, and the task reached `done` with the expected marker response.
- Temporary board auth keys, token files, smoke state, and Docker
containers were cleaned up after the run.
PR checks on head `b5eae40ce`:
- GitHub Actions passed: `policy`, `review`, `Typecheck + Release
Registry`, all general test shards, all serialized server shards,
`Build`, `Canary Dry Run`, `e2e`, and aggregate `verify`.
- External checks passed: Snyk and Socket Project Report.
- External Socket Pull Request Alerts remained pending after the
first-party CI matrix completed.
## Risks
- Medium risk: this spans adapter registration, package publishing,
gateway execution, onboarding docs, API-key scoping, and UI adapter
metadata.
- Migration risk is low: the scope-config migration adds a nullable
column and does not rewrite existing keys.
- Gateway execution depends on operator-provided Hermes API
configuration; the smoke covers the Docker gateway path but real
deployments may differ by network/auth setup.
- Direct Greptile review on the latest expanded diff is file-count
limited, although the commitperclip review gate passed.
> 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 coding agent, tool use enabled in a local repository
workspace. Context window size is not exposed in 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] Commitperclip review gate is green; direct Greptile review is
file-count limited on the latest expanded diff
- [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 (Claude, Codex, Cursor, Gemini, Grok, OpenCode, Pi,
ACPX) ship bundled "skills" — opinionated Markdown prompt bundles
materialized into the agent's runtime
> - One of those bundled skills, `paperclip-dev`, existed to let agents
develop Paperclip itself; it has now moved to its own external repo and
no longer belongs in the core tree
> - The adapter skill model also carried a `required` / `requiredReason`
attribute plus a `paperclip_required` `AdapterSkillOrigin` variant, all
of which only existed to mark bundled skills as non-optional in the UI
and adapter sync logic
> - With `paperclip-dev` gone, no bundled skill is "required" anymore,
and the type / runtime surface for `required` is dead weight — but it is
computed at request time and never persisted, so a clean removal is safe
(no compatibility shim needed)
> - This pull request deletes `skills/paperclip-dev/` and removes every
trace of the `required` / `requiredReason` field and the
`paperclip_required` origin across shared types, validators,
adapter-utils, all eight local adapters, server routes, the
company-skills service, the UI, the storybook fixtures, and the test
suite
> - The benefit is a smaller, simpler adapter-skill surface: one origin
(`company_managed`) for managed bundled skills,
`resolvePaperclipDesiredSkillNames` collapses to "just the configured
desired set", and the AgentDetail skills tab no longer renders a
"Required by Paperclip" section that no longer applies
## Linked Issues or Issue Description
<!-- No existing public GitHub issue; describing the underlying work
inline (feature_request template fields). -->
**Summary**
Remove the bundled `paperclip-dev` skill (now maintained in its own
external repo) and retire the `required` / `requiredReason` skill
attribute and the `paperclip_required` skill origin, which only existed
to support it.
**Problem or motivation**
`paperclip-dev` is the only bundled skill that was ever marked
"required". Now that it lives in a separate repository, shipping it
inside the core tree is wrong, and the entire `required` surface (a type
field, a validator field, a synthesized `paperclip_required` origin, UI
"Required by Paperclip" section, and required-skill merging in the
desired-skills calculation) becomes dead weight. The `required` value is
computed at request time and never persisted, so it can be removed
cleanly without a migration or compatibility shim.
**Proposed solution**
Delete `skills/paperclip-dev/`, drop the `required` / `requiredReason`
fields and `paperclip_required` origin everywhere they are produced or
consumed, collapse managed-skill origin to a single `company_managed`
value, and simplify `resolvePaperclipDesiredSkillNames` to return only
the configured desired set.
**Alternatives considered**
Keeping the `required` attribute as a no-op for forward compatibility —
rejected because it is request-time only (nothing persists it), so
leaving it in place is pure dead surface area with no callers.
**Roadmap alignment**
Internal cleanup / dead-code removal that simplifies the adapter-skill
surface; it does not introduce or duplicate any planned core feature in
ROADMAP.md.
## What Changed
- Deleted bundled `skills/paperclip-dev/` (moved to a separate repo).
- Dropped `required`, `requiredReason`, and the `paperclip_required`
origin from `packages/shared/src/types/adapter-skills.ts`,
`packages/shared/src/validators/adapter-skills.ts`, and
`packages/adapter-utils/src/types.ts`.
- In `packages/adapter-utils/src/server-utils.ts`: removed
`readSkillRequired()`; dropped `required`/`requiredReason` from
`listPaperclipSkillEntries()`,
`normalizeConfiguredPaperclipRuntimeSkills()`,
`buildPersistentSkillSnapshot()`, and `PaperclipSkillEntry`; collapsed
`buildManagedSkillOrigin()` to always return `company_managed`;
simplified `resolvePaperclipDesiredSkillNames()` to return only the
configured desired set (signature preserved so adapter call sites are
untouched).
- Walked all eight local adapters (`acpx-local`, `claude-local`,
`codex-local`, `cursor-local`, `gemini-local`, `grok-local`,
`opencode-local`, `pi-local`) and removed every remaining
`requiredReason` / `paperclip_required` reference.
- `server/src/services/company-skills.ts`: dropped the `required =
sourceKind === "paperclip_bundled"` synthesis when listing runtime skill
entries.
- `server/src/routes/agents.ts`: removed required-skill merging from the
desired-skills calculation in the persist-config path and the
unsupported-snapshot path (keeping the current version-aware
`desiredSkillEntries` structure).
- `ui/src/pages/AgentDetail.tsx`: dropped required-based filters, the
required tooltip, and the entire "Required by Paperclip" section from
the agent skills tab; storybook fixtures in
`ui/storybook/stories/acpx-local.stories.tsx` cleaned up to match.
- Tests: deleted the `required: false` case in
`paperclip-skill-utils.test.ts` and the "keeps required bundled skills
installed" case in every `*-local-skill-sync.test.ts`;
`acpx-local-execute.test.ts`, `cursor-local-execute.test.ts`,
`cursor-local-skill-sync.test.ts`, `agent-skills-routes.test.ts`, and
`packages/adapter-utils/src/server-utils.test.ts` were updated to drop
removed fields and map `origin: "paperclip_required"` →
`"company_managed"`.
- `server/src/adapters/registry.ts`: two `as unknown as
ServerAdapterModule["..."]` casts on `hermesListSkills` /
`hermesSyncSkills` (matching the existing `executeHermesLocal` pattern).
`hermes-paperclip-adapter@0.2.0` still depends on the published
`@paperclipai/adapter-utils` which keeps the retired
`paperclip_required` variant; the cast bridges the
workspace-vs-published type mismatch at the registry seam and can drop
once hermes upgrades.
## Verification
Run from the workspace root:
```sh
grep -rn "skills/paperclip-dev" .
grep -rn "paperclip_required" --include="*.ts" --include="*.tsx" .
grep -rn "requiredReason" --include="*.ts" --include="*.tsx" .
pnpm -w typecheck
pnpm --filter @paperclipai/server exec vitest run paperclip-skill-utils
pnpm --filter @paperclipai/server exec vitest run skill-sync
```
The first three greps return only the explanatory comment in
`server/src/adapters/registry.ts` (no live `paperclip_required` /
`requiredReason` usage) and zero `skills/paperclip-dev` source hits.
Locally:
- `pnpm -w typecheck` → all packages this PR touches pass
(adapter-utils, shared, server, ui, cli, and the
cursor/gemini/opencode/pi adapters).
- Affected vitest suites pass: `paperclip-skill-utils`, `server-utils`,
all eight `*-local-skill-sync`, `agent-skills-routes`, and the
`acpx`/`cursor`/`pi` execute suites.
## Risks
- Behavioral shift in the agent skills UI: the "Required by Paperclip"
section disappears. No bundled skill is required anymore, so this only
affects environments that previously surfaced `paperclip-dev` as a
forced-on row; those installs will see the skill move into the regular
"company-managed" list (and be uninstalled on next sync unless
explicitly listed as desired).
- Existing agents may still have the string `"paperclip-dev"` in their
persisted `desiredSkills`. That entry is inert (no source for it to
install from); a one-time DB cleanup is out of scope. Low risk.
- Hermes adapter type bridge: two casts in `registry.ts` paper over a
type-only divergence between the workspace `@paperclipai/adapter-utils`
and the published version still pinned by
`hermes-paperclip-adapter@0.2.0`. Runtime behavior is unaffected because
the retired `paperclip_required` value is no longer produced by anything
in this tree. The casts can be removed once hermes upgrades its
dependency.
## Model Used
- Provider: Anthropic
- Model: Claude Opus 4.7 (`claude-opus-4-7`)
- Capability: agent tool use via Paperclip's `claude_local` adapter
## 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
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Local agents run through the `claude_local` adapter, which spawns
Claude Code and routes its Anthropic API traffic through a shared proxy
(e.g. better-ccflare).
> - That proxy's request log feeds observability dashboards that break
down cost and token usage.
> - But requests from local agents arrive without an agent identifier,
so all traffic collapses into a single unattributed bucket and per-agent
telemetry is impossible.
> - Anthropic's CLI forwards `ANTHROPIC_CUSTOM_HEADERS` onto each API
request, and better-ccflare now reads an `X-Anthropic-Agent-Id` header
to attribute requests per agent.
> - This pull request stamps the agent's id into
`ANTHROPIC_CUSTOM_HEADERS` as `X-Anthropic-Agent-Id`, injected into the
env the adapter actually forwards to the spawned process.
> - The benefit is per-agent cost/token attribution in proxy-backed
dashboards, with zero impact on agents that don't run behind such a
proxy.
## Linked Issues or Issue Description
No public GitHub issue exists; describing inline per CONTRIBUTING.md
(feature template).
**Problem or motivation**
When several `claude_local` agents share a proxy (better-ccflare) in
front of the Anthropic API, the proxy cannot tell which agent issued a
given request. Per-agent cost and token dashboards therefore can't be
built — every request is attributed to one undifferentiated bucket.
**Proposed solution**
Have the `claude_local` adapter stamp each spawned Claude Code process
with `ANTHROPIC_CUSTOM_HEADERS: X-Anthropic-Agent-Id: <agentId>`. The
Anthropic CLI forwards that header on every API call, so the proxy can
attribute requests to the specific agent.
**Alternatives considered**
Parsing per-agent identity from workspace paths or session ids in the
proxy — brittle and proxy-specific. A first-class request header is the
stable contract; it pairs with better-ccflare's `X-Anthropic-Agent-Id`
support
([tombii/better-ccflare#260](https://github.com/tombii/better-ccflare/pull/260))
and dashboards like
[danieltamas/axon](https://github.com/danieltamas/axon).
**Roadmap alignment**
Additive observability glue for an existing adapter; no overlap with
planned core work.
## What Changed
- Added `server/src/adapters/claude-agent-id-header.ts` exporting
`stampClaudeAgentIdHeader`, which wraps the `claude_local` execute and
merges `X-Anthropic-Agent-Id: <agentId>` into the run's
`config.env.ANTHROPIC_CUSTOM_HEADERS`.
- `server/src/adapters/registry.ts`: the `claude_local` adapter now uses
the wrapped execute (`stampClaudeAgentIdHeader(claudeExecute)`).
- The header is merged into **`config.env`** — the env the Claude
adapter actually forwards into the spawned process — rather than
`agent.adapterConfig.env`, which is resolved upstream before `execute`
runs and is never read by the Claude adapter.
- `agentId` is sanitized (CR/LF stripped, capped at 256 chars) before
interpolation to prevent HTTP header injection.
- Passthrough when no agent id is available; a pre-existing
`X-Anthropic-Agent-Id` (manual override) is respected and not
duplicated.
- Added `server/src/adapters/claude-agent-id-header.test.ts` covering
injection into `config.env`, append-to-existing
`ANTHROPIC_CUSTOM_HEADERS`, CR/LF sanitization, length bounding,
no-agent-id passthrough, and the duplicate-header guard.
## Verification
- Unit tests: `cd server && npx vitest run
src/adapters/claude-agent-id-header.test.ts` → 6 passing.
- CI: typecheck, build, server suites, and Greptile gates run on this
PR.
- Manual: configure a `claude_local` agent behind better-ccflare, run a
heartbeat, and confirm the proxy log shows `X-Anthropic-Agent-Id:
<agentId>` on that agent's requests. An agent that already sets
`X-Anthropic-Agent-Id` in its adapter config keeps its override (no
duplicate line).
## Risks
Low risk. The change is additive and non-breaking:
- When no agent id is present, or when an `X-Anthropic-Agent-Id` is
already configured, execution is byte-for-byte unchanged (the original
`ctx` is passed straight through).
- The header only has an effect for deployments whose proxy reads it;
agents without such a proxy are unaffected.
- The agent id is sanitized (CR/LF removed, length-bounded) before it is
interpolated into a header value, preventing header injection.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. This is additive
observability glue for an existing adapter and does not overlap planned
core work.
## Model Used
Claude (Anthropic) — Claude Opus 4.8 (`claude-opus-4-8`), via the Claude
Code CLI with extended reasoning and 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
- [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 (N/A — no UI 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: zenprocess <zenprocess@users.noreply.github.com>
Co-authored-by: Devin Foley <devin@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 adapters translate Paperclip configuration into the
CLI/runtime flags needed by each provider.
> - Hermes custom providers are represented as `custom:*` values, but
the adapter registry was not passing that provider value through as
Hermes CLI arguments.
> - The fix is isolated to adapter argument construction and its
regression tests.
> - This pull request extracts only the Hermes custom-provider
pass-through fix onto `origin/master`.
> - The benefit is a small adapter PR that can merge independently from
UI, skills catalog, and migration work.
## Linked Issues or Issue Description
No GitHub issue exists for this branch split. Internal source task:
[PAP-11234](/PAP/issues/PAP-11234).
Problem/motivation:
- Hermes `custom:*` providers need to reach the Hermes process as
`--provider <value>`.
- The adapter should preserve existing auth injection and avoid adding
duplicate provider flags when the user already supplied one.
Proposed solution:
- Detect Hermes `custom:*` provider values in adapter registry argument
construction.
- Add `--provider <custom value>` unless an explicit provider arg
already exists.
- Cover both spaced and equals-style existing provider args in
regression tests.
Related PR search:
- Found related Hermes adapter PRs such as #7544 and #3027, but none
duplicates this specific custom-provider arg pass-through behavior.
Roadmap alignment:
- Checked `ROADMAP.md`; no duplicate planned item was found for this
adapter fix.
## What Changed
- Updated Hermes adapter registration argument construction to pass
`custom:*` providers through `extraArgs` as `--provider <value>`.
- Preserved existing auth injection behavior.
- Avoided duplicate provider arguments when `--provider value` or
`--provider=value` is already present.
- Added adapter registry regression coverage.
## Verification
- `CI=true NODE_ENV=development pnpm install --frozen-lockfile
--prefer-offline`
- `pnpm exec vitest server/src/__tests__/adapter-registry.test.ts --run`
— 1 file, 20 tests passed.
## Risks
- Low risk; change is scoped to Hermes adapter argument construction.
- Review should confirm the provider flag syntax matches current Hermes
CLI expectations.
> 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 Codex via Paperclip `codex_local` / CodexCoder, GPT-5-class
coding model with tool use and shell execution. Exact runtime snapshot
and context-window setting were not exposed by the Paperclip run
context.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details available from the run context)
- [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 change)
- [x] I have updated relevant documentation to reflect my changes (N/A;
no docs behavior changed)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (pending on draft PR)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(pending follow-up loop)
- [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 execution subsystem runs those agents in environments (local,
ssh, sandbox), and sandbox-provider plugins let an environment
materialize per-run sandboxes
> - Stage 1 (#5790) contributed a first-party Kubernetes
sandbox-provider plugin, but the server core has no way to adopt it
operationally: no per-run adapter selection, no way to force an instance
onto sandboxed execution, no declarative adapter/model configuration,
and the plugin must be installed by hand
> - Without this, a multi-tenant or security-conscious deployment cannot
guarantee that agent runs never execute on the host, and a single
environment cannot serve agents with different harnesses
> - This pull request adds the server + SDK integration: per-run
adapterType on the lease protocol, an env-gated forced-Kubernetes
execution policy with provisioning and a per-run allowlist guard, a
declarative adapter registry and model list, in-cluster env passthrough
for sandbox plugin workers, fail-safe auto-install of the bundled
plugin, and the matching UI affordance
> - The benefit is that sandbox-provider plugins become fully usable for
Kubernetes execution: operators configure everything via environment
variables and GitOps, while self-hosters who set none of the variables
see exactly the behavior they have today
## Linked Issues or Issue Description
Refs #5790 (stage 1 of 3: the Kubernetes sandbox-provider plugin
package).
No existing issue. Feature description: the server core lacks the
integration seams to operate a sandbox-provider plugin as the mandatory
execution path of an instance. This PR is stage 2 of 3 of the staged
Kubernetes contribution; stage 3 will contribute the agent runtime
images and their build pipeline.
## What Changed
One line per piece:
- `packages/plugins/sdk/protocol.ts`: optional `adapterType` on
`PluginEnvironmentAcquireLeaseParams` so a provider can select the
runtime image per run; existing providers simply ignore it
- `server/services/environment-runtime.ts` +
`environment-run-orchestrator.ts`: thread the agent's adapter type into
both lease-acquiring drivers, including the heartbeat path (the two call
sites have historically drifted, hence the pinned test)
- `server/services/environments.ts`: `ensureKubernetesEnvironment` /
`findKubernetesEnvironment`, an idempotent managed Kubernetes
environment per company, identified by a metadata marker and refreshed
(not recreated) on config change; `timeoutMs` rides on the config for
slow cold-start leases
- `server/services/execution-allowlist.ts`: pure (driver, provider,
policy) -> allow/deny guard; `executionMode=kubernetes` only allows the
kubernetes sandbox provider
- `server/services/execution-policy-bootstrap.ts` + startup hook in
`server/index.ts`: parse `PAPERCLIP_EXECUTION_MODE` / `PAPERCLIP_K8S_*`,
persist `executionMode` into instance general settings, and provision
the managed environment for every company; fails loud on
misconfiguration
- `server/services/heartbeat.ts`: when the policy forces Kubernetes, pin
run selection to the managed environment (also overriding any persisted
workspace environment id), refuse to fall back to local, and re-check
the actually acquired environment against the allowlist as defense in
depth
- `server/services/adapter-registry-bootstrap.ts` + shared
`AdapterRegistryEntry` type/validator: declarative `PAPERCLIP_ADAPTERS`
registry (inline JSON or file) that reconciles adapter availability at
startup and rides on the Kubernetes environment config
- `server/services/adapter-models-env.ts` + `adapters/registry.ts`:
`PAPERCLIP_ADAPTER_MODELS` lets an operator declare picker model lists
the server cannot CLI-discover
- `server/services/plugin-loader.ts`: pass
`KUBERNETES_SERVICE_HOST/PORT(_HTTPS)` through to plugin workers that
register environment drivers, so in-cluster API clients can be
constructed; all other host env stays stripped
- `server/app.ts`: fail-safe auto-install of the bundled kubernetes
plugin at boot; no-ops when the bundle is absent and never blocks
startup on error
- `packages/shared` types/validators: `InstanceExecutionMode` on general
settings (optional, strict schema)
- `ui/lib/forced-kubernetes-environment.ts` + `AgentConfigForm`: when
the policy is active, show a read-only Kubernetes environment instead of
the environment picker and default new agents onto the managed
environment
- Tests for every new module plus the adapterType pin in
`heartbeat-plugin-environment` and the managed-environment lifecycle in
`environment-service`
Everything is gated: with `PAPERCLIP_EXECUTION_MODE`,
`PAPERCLIP_ADAPTERS`, and `PAPERCLIP_ADAPTER_MODELS` unset (and no
bundled plugin present), every code path reduces to current behavior.
The per-run `adapterType` is an optional SDK parameter that existing
providers ignore.
## Verification
- `cd server && npx tsc --noEmit`: clean (0 errors); `ui` typecheck also
clean
- Targeted suites all green (11 files, 90 tests): `npx vitest run
server/src/__tests__/heartbeat-plugin-environment.test.ts
server/src/__tests__/environment-service.test.ts
server/src/__tests__/environment-runtime.test.ts
server/src/__tests__/environment-run-orchestrator.test.ts
server/src/__tests__/plugin-database.test.ts
server/src/services/execution-policy-bootstrap.test.ts
server/src/services/execution-allowlist.test.ts
server/src/services/adapter-registry-bootstrap.test.ts
server/src/services/adapter-registry-bootstrap.reconcile.test.ts
server/src/services/adapter-models-env.test.ts
packages/shared/src/validators/adapter-registry.test.ts`
- `npx vitest run ui/src/components/AgentConfigForm.test.ts`: green (6
tests)
- Full `npx vitest run server/src/__tests__`: 2323 passed, 1 skipped;
the only failures (heartbeat-process-recovery pid-retry,
workspace-runtime symbolic-ref/git tests) reproduce identically on
pristine `master` in the same environment, so they are
machine-environment issues unrelated to this change;
`server-startup-feedback-export` needed its `services/index.js` mock
extended with the new export and is green
- This integration has been running in production on a hosted
multi-tenant deployment, where it executes agent runs across five
different harnesses through the stage 1 plugin
## Risks
- Low for existing deployments: every behavior is env-gated and the
defaults preserve current semantics; the auto-install block is wrapped
fail-safe and skips silently when the plugin bundle is absent
- `executionMode` is a new optional field on a strict zod schema; absent
input normalizes exactly as before
- The forced policy intentionally fails runs loudly (rather than falling
back to local) when no managed Kubernetes environment exists; this only
affects instances that explicitly set
`PAPERCLIP_EXECUTION_MODE=kubernetes`
## Model Used
Claude Opus 4.8 (claude-opus-4-8, 1M context), extended thinking,
agentic tool use via Claude Code.
## UI screenshots
The UI change is a new read-only "Execution" section in
`AgentConfigForm`, shown only when the instance execution policy forces
Kubernetes (`executionMode=kubernetes`); there is no "before" state for
it (the section did not exist, and instances without the forced policy
render the existing picker unchanged). Captured from the new Storybook
stories added in this PR (`Product/Agent Management`):
Managed Kubernetes environment present (read-only display, no local/SSH
picker):
No managed environment available yet (warning notice, no silent local
fallback):
## 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
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.8 (1M context) <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, so
adapter quality directly affects what runtimes the control plane can
supervise.
> - Local CLI adapters are one of the core execution surfaces because
they turn real coding tools into Paperclip-managed employees with
heartbeats, transcripts, and reviewability.
> - Grok Build was installed on the Paperclip host, but Paperclip had no
built-in `grok_local` adapter, so the runtime could not be configured
through the normal server/UI/CLI adapter path.
> - That gap needed to be closed with the same built-in registry,
environment diagnostics, transcript parsing, and skill/instructions
behavior that the other local adapters already rely on.
> - After the initial adapter landed, a real follow-up run showed that
Grok streaming text was being rendered one fragment per line, which made
transcripts harder to read even though the runtime itself was working.
> - This pull request adds the built-in `grok_local` adapter end-to-end
and then fixes the transcript parser so streamed Grok output is
coalesced into readable assistant/thinking blocks.
> - The benefit is that Grok Build becomes a first-class Paperclip
runtime with a usable operator experience instead of a partially wired
runtime with noisy transcript output.
## What Changed
- Added a new built-in `@paperclipai/adapter-grok-local` package with
server, UI, and CLI entrypoints.
- Implemented Grok execution, session handling, environment diagnostics,
config building, skill syncing, and parser coverage inside the new
adapter package.
- Registered `grok_local` across the built-in adapter inventories and
capability/display metadata in server, UI, CLI, and shared constants.
- Added adapter route coverage for the new built-in type.
- Fixed Grok transcript readability by emitting streamed `text` and
`thought` fragments as deltas so the shared transcript builder coalesces
them into readable message blocks.
- Added regression tests for the Grok parser and transcript coalescing
behavior.
## Verification
- `pnpm vitest run
packages/adapters/grok-local/src/ui/parse-stdout.test.ts
ui/src/adapters/transcript.test.ts`
- `pnpm --filter @paperclipai/adapter-grok-local build`
- Manual runtime verification on the Paperclip host during
implementation and follow-up review:
- confirmed the Grok CLI was installed and authenticated
- confirmed the worktree dev server could be restarted cleanly and
health-checked after the parser follow-up
- No screenshots attached. This change is primarily adapter plumbing
plus transcript formatting behavior; reviewers can verify via the
Grok-backed run surfaces directly.
## Risks
- This adds a new built-in adapter, so any missed registration surface
could create inconsistencies between server, UI, and CLI behavior.
- The adapter depends on Grok Build's current event/output shape; if
upstream Grok streaming JSON changes, transcript parsing or session
extraction may need follow-up updates.
- The transcript readability fix intentionally changes how Grok
fragments are grouped, so any downstream code that implicitly expected
one entry per fragment would behave differently.
> 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 via Paperclip `codex_local` agent runtime.
- GPT-5-class coding model with tool use, shell execution, file editing,
and repo inspection enabled.
- Exact backend model ID/context window were not surfaced to the agent
in this Paperclip 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 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
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Each agent runs inside a sandbox environment so its CLI is isolated
from the host
> - Sandbox-backed adapter runs go through a small set of shared helpers
— `ensureAdapterExecutionTargetCommandResolvable`, the sandbox callback
bridge runner, and per-adapter `SANDBOX_INSTALL_COMMAND` strings
> - When standing up new sandbox provider plugins, the existing helpers
timed out, missed install fallbacks, or leaned on assumptions that only
held for E2B
> - Local adapters (`claude-local`, `codex-local`, `gemini-local`,
`opencode-local`) needed slightly hardened probes so they could install
themselves and validate inside *any* remote sandbox transport, not just
E2B
> - This pull request bundles those runtime fixes so future sandbox
provider plugins inherit a working baseline
> - The benefit is that adding a new sandbox provider plugin no longer
requires touching adapter-utils or each local-adapter probe — the
supporting infra is already correct
## What Changed
- `packages/adapter-utils/src/execution-target.ts`: introduce
`DEFAULT_REMOTE_SANDBOX_ADAPTER_TIMEOUT_SEC = 1800` and
`resolveAdapterExecutionTargetTimeoutSec(...)`. Local and SSH adapters
keep the historical "0 means no adapter timeout" behavior;
sandbox-backed runs without an explicit `timeoutSec` get an explicit
30-minute default so remote installs and warm-up don't time out at the
per-RPC default. Plumbed `timeoutSec` through
`ensureAdapterExecutionTargetCommandResolvable` so install probes inside
a sandbox honor adapter-level overrides instead of the bridge's 5-minute
default.
- `packages/adapters/opencode-local/src/index.ts`: switch
`SANDBOX_INSTALL_COMMAND` from `npm install -g opencode-ai` to `curl
-fsSL https://opencode.ai/install | bash`. The npm package reifies four
large prebuilt-binary subpackages in parallel even though only one
matches the host arch; on bandwidth-constrained sandboxes that blew
through the 240s install budget. The official installer fetches one
arch-specific binary and adds `$HOME/.opencode/bin` to PATH via
`~/.bashrc`, which the sandbox-callback-bridge login-shell script
already sources.
- `packages/adapters/{claude,codex,gemini,opencode}-local/`: harden
remote-target probes — pass `--skip-git-repo-check` for Codex when
probing outside a repo, normalize permission flags for Claude, and add
`*.remote.test.ts` coverage that exercises the remote-sandbox path
explicitly for each adapter.
- `packages/adapter-utils/src/sandbox-install-command.{ts,test.ts}`
(new): add `buildSandboxNpmInstallCommand` helper.
`server/src/adapters/registry.ts` + new
`server/src/__tests__/adapter-registry.test.ts`: wire adapter install
commands so they fall back to a writable `$HOME/.local` prefix when
global install isn't available.
- `server/src/__tests__/plugin-worker-manager.test.ts` + new
`server/src/__tests__/fixtures/plugin-worker-delayed.cjs`: pin per-call
timeout overrides so plugin worker exec calls honor the caller's timeout
instead of the worker's default.
## Verification
- `pnpm typecheck`
- `pnpm exec vitest run --no-coverage
packages/adapter-utils/src/execution-target-sandbox.test.ts
packages/adapter-utils/src/sandbox-install-command.test.ts`
- `pnpm exec vitest run --no-coverage
server/src/__tests__/plugin-worker-manager.test.ts
server/src/__tests__/adapter-registry.test.ts
server/src/__tests__/claude-local-adapter-environment.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/gemini-local-adapter-environment.test.ts`
- `pnpm exec vitest run --no-coverage
packages/adapters/codex-local/src/server/test.remote.test.ts
packages/adapters/opencode-local/src/server/test.remote.test.ts
packages/adapters/codex-local/src/server/codex-args.test.ts
packages/adapters/codex-local/src/server/execute.remote.test.ts
packages/adapters/gemini-local/src/server/execute.remote.test.ts`
All passing locally.
## Risks
- Touches shared `adapter-utils` and several `*-local` adapters. The
30-minute default applies only when both (a) the target is
`remote+sandbox` and (b) no `timeoutSec` is configured — local + SSH
paths are unchanged. New test coverage was added alongside each behavior
change to pin the contracts.
- Switching OpenCode's install command to the official installer is a
behavior change for any operator running OpenCode inside a remote
sandbox. Local installs are unaffected (the `SANDBOX_INSTALL_COMMAND`
only runs when an adapter is being installed inside a sandbox).
- Low risk overall — no migrations, no API surface change.
## Model Used
- Provider: Anthropic
- Model: Claude Opus 4.7 (1M context)
- Capabilities used: extended reasoning, tool use (Read/Edit/Bash/Grep),
no code execution beyond local repo commands
## 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
- [ ] If this change affects the UI, I have included before/after
screenshots — N/A, no UI change
- [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
> - There are many adapter types, one per agent-runtime product (Claude,
Codex, OpenCode, Cursor local CLI, etc.)
> - Cursor shipped a public TypeScript SDK on 2026-04-29 that exposes
Cursor's full hosted-agent platform (cloud VMs, harness, MCP, skills,
hooks)
> - Paperclip had no first-class adapter for this — agents that wanted
to use Cursor's managed cloud runtime had to fall back to the local CLI
adapter, which loses the cloud session, streaming, and durable run model
> - This PR adds a new `cursor_cloud` adapter built directly on
`@cursor/sdk`, with Paperclip's heartbeat mapped to Cursor's
durable-agent + per-run model
> - The benefit is that any Paperclip agent can now drive a Cursor cloud
agent across heartbeats with native session reuse, streaming, and
cancellation, while Paperclip remains the source of truth for issue/task
state
## What Changed
- New built-in adapter package `packages/adapters/cursor-cloud` (15
files, ~1.7k LOC) backed by `@cursor/sdk` ^1.0.12
- `src/server/execute.ts` — SDK-first lifecycle: `Agent.create` /
`Agent.resume` / `Agent.getRun` / `agent.send` / `run.stream` /
`run.wait`, with session reuse keyed on the (runtime env type, env name,
repo set) tuple
- `src/server/session.ts` — codec for `cursorAgentId` + `latestRunId` +
repo metadata, persisted in `runtime.sessionParams`
- `src/server/test.ts` — environment probe via `Cursor.me()` and
optional model validation via `Cursor.models.list()`
- `src/ui/parse-stdout.ts` + `src/cli/format-event.ts` — normalize
Cursor SDK message types (`status`, `thinking`, `assistant`, `user`,
`tool_call`, `tool_result`, `result`) into Paperclip transcript events
for the UI and CLI
- Registrations: `packages/shared/src/constants.ts`,
`packages/adapter-utils/src/session-compaction.ts`,
`server/src/adapters/{registry,builtin-adapter-types}.ts`,
`ui/src/adapters/{registry,adapter-display-registry}.ts` +
`ui/src/adapters/cursor-cloud/index.ts`, `cli/src/adapters/registry.ts`,
plus workspace deps in `cli`/`server`/`ui` `package.json`
- `ui/src/components/AgentConfigForm.tsx` — hide local-Cursor
`mode`/thinking-effort field for `cursor_cloud` (different config
surface)
- 11 vitest tests covering execute paths (fresh create, matching-resume,
active-run reattach, non-finished result), session codec round-trip,
transcript parsing, and config building
## Verification
Reviewer steps:
```bash
pnpm install
pnpm --filter @paperclipai/adapter-cursor-cloud typecheck # → clean
pnpm vitest run packages/adapters/cursor-cloud # → 11/11 passing
```
End-to-end check against a real Cursor cloud agent (requires
`CURSOR_API_KEY` and Cursor GitHub-app install on the target repo):
1. Create a `cursor_cloud` agent in Paperclip with `repoUrl` set to the
test repo, `repoStartingRef: main`, and `env.CURSOR_API_KEY` set
2. Trigger a heartbeat → adapter calls `Agent.create({ cloud: { env: {
type: "cloud" }, repos: [...] } })`, streams events, terminates on
`finished`
3. Trigger a second heartbeat → adapter calls `Agent.resume` or
`agent.send` follow-up depending on prior-run state, reusing
`cursorAgentId`
4. The Paperclip UI/CLI transcript reflects Cursor `status` / `thinking`
/ `assistant` events as they stream
5. Cancellation from Paperclip maps to `run.cancel()` or Cloud API v1
`cancelRun` for cross-heartbeat cancellation
A direct-SDK smoke run against a real repo (devinfoley/my_test_project @
main) confirmed: `Cursor.me()` ok → `Agent.create` → `agent.send` →
`run.stream()` (30 events) → terminal status `finished` in ~11s.
## Risks
- **New adapter, additive only.** No existing adapter or registry is
replaced; current `cursor` local-CLI adapter is untouched. Default
behavior of any existing agent is unchanged.
- **External dependency on `@cursor/sdk`.** Cursor's SDK is v1.0.x and
may evolve. Mocked unit tests cover the public surface used here; if the
SDK breaks compatibility we update the adapter independently.
- **Cost/budget.** `cursor_cloud` runs on Cursor's billed cloud VMs;
operators must understand they are spending money outside Paperclip's
budget controls when they enable this adapter. Same shape as other
API-billed adapters.
- **No webhook support in V1.** The SDK already provides
stream/wait/cancel/reattach, so V1 does not require a public callback
URL. If a future use case needs out-of-band wakes, we add a Cloud API v1
webhook bridge as a separate change. This is called out in the issue
plan document.
- **Lockfile.** Per repo policy, `pnpm-lock.yaml` is intentionally not
in this PR — CI's lockfile workflow will update it on merge given the
manifest changes.
## Model Used
- Provider: Anthropic Claude (via Claude Code / Paperclip `claude_local`
adapter)
- Model: `claude-opus-4-7` (Claude Opus 4.7), knowledge cutoff January
2026
- Mode: standard tool-use with extended reasoning
- Context: ~200k token window
- Capabilities used: code generation, multi-file edits, shell/test
execution, GitHub PR workflow
## 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 (11/11 in
`packages/adapters/cursor-cloud`)
- [x] I have added or updated tests where applicable (4 new test files,
11 cases)
- [ ] If this change affects the UI, I have included before/after
screenshots (the only UI change is hiding the local-Cursor mode field on
the `cursor_cloud` adapter — happy to attach a screenshot if the
reviewer wants one)
- [x] I have updated relevant documentation to reflect my changes (issue
plan document supersedes the pre-SDK design; tracked in PAPA-203)
- [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 across several adapter
implementations.
> - ACPX is a local adapter path that can proxy Claude and Codex-style
execution.
> - Its configuration needed stronger schema defaults, provider-aware
model handling, and better UI support.
> - Plugin authors also need clear docs for managed resources.
> - This pull request improves ACPX adapter configuration and documents
plugin-managed resources.
> - The benefit is a more predictable adapter setup path without
changing unrelated control-plane behavior.
## What Changed
- Improved ACPX config schema, execution config handling, UI build
config, and route coverage.
- Added ACPX model filtering support and tests.
- Updated the agent config form and storybook coverage for ACPX
model/provider behavior.
- Expanded plugin authoring documentation for managed resources.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/acpx-local-execute.test.ts
server/src/__tests__/adapter-routes.test.ts
ui/src/lib/acpx-model-filter.test.ts`
## Risks
- Low-to-medium risk: adapter configuration behavior changes can affect
ACPX users, but the change is isolated to ACPX/plugin-doc surfaces and
covered by targeted adapter tests.
## Model Used
- OpenAI GPT-5 Codex via Paperclip `codex_local` adapter, with
shell/git/GitHub CLI 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 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies, running
adapter
> commands like `claude`, `codex`, `pi` either locally or on remote
runtimes
> (SSH hosts, sandboxes, etc.)
> - On a fresh remote runtime — particularly an ephemeral sandbox — the
> adapter's CLI may not be installed yet. Today operators handle this
via
> external configuration (e.g. a project-level `provisionCommand` shell
> script) that has to know about every adapter the operator might want
to use
> - This means every adapter has its own well-known npm package, but
operators
> end up writing duplicate provision shell scripts that paste together
> `npm install -g @anthropic-ai/claude-code`, `npm install -g
@openai/codex`,
> etc. — knowledge the adapter itself already has
> - This PR moves that knowledge into the adapter modules: each adapter
declares
> how its runtime command should be detected and (if applicable)
installed
> via `getRuntimeCommandSpec(config)`. The execution path runs the
adapter's
> own install command on remote sandbox targets before launching, so a
fresh
> sandbox bootstraps itself instead of requiring a hand-written
provision script
> - The benefit is fewer footguns for operators provisioning remote
runtimes,
> and a clean place for new adapters to plug in their install recipe
## What Changed
- New types in `packages/adapter-utils/src/types.ts`:
- `AdapterRuntimeCommandSpec` describing `command`, optional
`detectCommand`, and optional `installCommand`
- Optional `getRuntimeCommandSpec(config)` on `ServerAdapterModule`
- Optional `runtimeCommandSpec` on `AdapterExecutionContext` so adapters
receive the resolved spec at execute time
- New helper `ensureAdapterExecutionTargetRuntimeCommandInstalled(...)`
in
`packages/adapter-utils/src/execution-target.ts` that runs the install
command
on remote targets when `transport === "sandbox"`. SSH and local targets
are
no-ops. Throws on timeout or non-zero exit so failures surface early.
- Each of `claude-local`, `codex-local`, `cursor-local`, `gemini-local`,
`opencode-local`, `pi-local`'s `execute.ts` now reads
`ctx.runtimeCommandSpec?.installCommand` and calls the helper before
launching
the adapter command.
- `server/src/adapters/registry.ts` declares `getRuntimeCommandSpec` for
each
adapter:
- claude/codex/gemini/opencode/pi-local: `npm install -g <package>`
recipe via
a shared `buildNpmRuntimeCommandSpec` helper, with a defensive guard
that
only auto-installs when the configured `command` matches the well-known
fallback (custom binaries are left alone).
- cursor-local: declares `command` only; no auto-install (no public npm
package), preserving the existing manual setup.
- `server/src/services/heartbeat.ts` resolves the spec via
`adapter.getRuntimeCommandSpec?.(runtimeConfig)` and passes it through
to
`AdapterExecutionContext`.
- Tests added in `execution-target.test.ts` (~75 lines), e2b
`plugin.test.ts` (~32 lines), and `environment-run-orchestrator.test.ts`
(~76 lines).
## Verification
- `pnpm --filter @paperclipai/adapter-utils test`
- `pnpm --filter @paperclipai/server test --
environment-run-orchestrator`
- `pnpm --filter @paperclipai/sandbox-providers-e2b test`
- Manual QA: run an adapter (claude/codex/etc.) against a fresh
sandbox-backed
environment that does NOT have the adapter CLI pre-installed. Confirm
the
install runs once at the start of the agent run and the adapter then
launches
successfully. Re-run on the same sandbox; confirm the install command is
idempotent and the second run starts faster.
- Confirm SSH and local execution paths are unaffected (gated by
`transport === "sandbox"`).
## Risks
- Behavioural shift on sandbox runs: a new install step now runs at the
start
of every sandbox agent run for adapters with `installCommand` set. The
install commands are idempotent (`if ! command -v X >/dev/null 2>&1;
then
npm install -g <pkg>; fi`), so this is fast on warm sandboxes. On a cold
sandbox, the first run takes longer.
- Operators who used the legacy project-level `provisionCommand` to
install
adapter CLIs can drop that part of their script; the adapter handles it
now.
Existing scripts continue to work — installs are idempotent.
- The cursor-local adapter has no auto-install (no public npm package).
Behaviour for cursor-local on sandboxes is unchanged.
- New optional surface on `ServerAdapterModule`. Plugins that don't
implement
`getRuntimeCommandSpec` retain previous behaviour (no auto-install).
## Model Used
- OpenAI GPT-5.4 (reasoning effort: high) via Codex CLI
- Provider: OpenAI
- Used to author the code changes in this PR
## 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
- [ ] If this change affects the UI, I have included before/after
screenshots — N/A
- [ ] I have updated relevant documentation to reflect my changes — N/A
- [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-agent companies through a control plane
that can start, supervise, and recover agent runs.
> - Local adapters are the bridge between Paperclip issues and concrete
agent runtimes such as Claude, Codex, and other ACP-compatible tools.
> - The roadmap calls out broader “bring your own agent” and claw-style
agent support, and ACPX gives Paperclip one path to normalize multiple
ACP agents behind a single adapter.
> - The branch needed to become one reviewable PR against current
`paperclipai/paperclip:master`, without carrying stale base conflicts or
generated lockfile churn.
> - This pull request adds an experimental built-in `acpx_local`
adapter, integrates it through the server/CLI/UI adapter surfaces, and
adds regression coverage for runtime execution, skill sync, stream
parsing, diagnostics, and log redaction.
> - The benefit is that Paperclip can run Claude/Codex/custom ACP agents
through ACPX while keeping operator configuration, skills, logging, and
transcript rendering inside the existing adapter model.
## What Changed
- Added `@paperclipai/adapter-acpx-local` with server execution, config
schema, ACPX session handling, CLI formatting, UI config helpers, and
stdout parsing.
- Registered `acpx_local` across CLI, server, shared constants, UI
adapter metadata, adapter capabilities, and agent creation/editing
surfaces.
- Added ACPX runtime execution support with persistent sessions,
local-agent JWT environment handling, skill snapshots, runtime skill
materialization, and isolation/security regressions.
- Added ACPX adapter diagnostics and marked the adapter experimental in
the UI.
- Added command/env secret redaction for resolved command metadata in
adapter-utils, server event storage, and the Agent Detail invocation UI.
- Added Storybook coverage for ACPX config, transcript rendering, and
skill states, plus PR screenshots under `docs/pr-screenshots/pap-2944/`.
- Rebased the branch onto current `public-gh/master`; `pnpm-lock.yaml`
is intentionally not included and there are no migration/schema changes.
## Verification
- `pnpm exec vitest run
packages/adapters/acpx-local/src/server/execute.test.ts
packages/adapters/acpx-local/src/server/test.test.ts
packages/adapters/acpx-local/src/cli/format-event.test.ts
packages/adapters/acpx-local/src/ui/parse-stdout.test.ts
packages/adapter-utils/src/server-utils.test.ts
server/src/__tests__/redaction.test.ts
server/src/__tests__/acpx-local-execute.test.ts
server/src/__tests__/acpx-local-skill-sync.test.ts
server/src/__tests__/acpx-local-adapter-environment.test.ts
server/src/__tests__/adapter-routes.test.ts
server/src/__tests__/agent-skills-routes.test.ts
ui/src/adapters/metadata.test.ts` — 12 files, 87 tests passed.
- `pnpm --filter @paperclipai/adapter-acpx-local typecheck` — passed.
- `pnpm --filter @paperclipai/server typecheck` — passed.
- `pnpm --filter @paperclipai/ui typecheck` — passed.
- Confirmed PR diff does not include `pnpm-lock.yaml`, database schema
files, or migrations.
Screenshots:
## Risks
- Medium risk: this introduces a new built-in adapter package and
touches runtime execution, adapter registration, agent config, skills,
and transcript rendering.
- ACPX and ACP agent behavior can vary by installed tool versions; the
adapter is marked experimental to set operator expectations.
- `pnpm-lock.yaml` is excluded per repository PR policy, so dependency
lock refresh must be handled by the repo’s automation or maintainers.
- No database migration risk: no schema or migration files changed.
> 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 coding agent based on GPT-5, with repository tool use,
shell execution, git operations, and local verification. Exact hosted
context window was not exposed in 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 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is a control plane for autonomous AI companies, where
adapters are the boundary between the board, agents, and execution
runtimes.
> - Local adapters currently expose a primary runtime configuration, but
operators often need a cheaper model lane for routine or low-risk work.
> - That cheap lane has to stay adapter-owned: runtime profile settings
should not mutate the primary adapter config or bypass existing
auth/secret mediation.
> - Issue creation also needs an ergonomic way to request primary,
cheap, or custom model behavior for a selected assignee.
> - This pull request adds a first-class `cheap` model profile contract
across adapter capabilities, heartbeat config resolution, agent
configuration, and issue creation.
> - The benefit is cheaper task execution can be configured and
requested explicitly while preserving adapter boundaries, secret
handling, and audit visibility.
## What Changed
- Added adapter model-profile capability metadata and a `cheap` profile
contract for supported local adapters.
- Applied `runtimeConfig.modelProfiles.cheap.adapterConfig` during
heartbeat config resolution, including requested/applied/fallback run
metadata.
- Added agent configuration UI for cheap model profile settings without
writing those settings into primary `adapterConfig`.
- Added New Issue assignee model lane controls for Primary / Cheap /
Custom and request payload handling.
- Added run ledger profile badges and Storybook stories for the new
cheap-lane UI states.
- Added tests for validators, heartbeat model profile application,
permission/secret mediation, UI payload helpers, and run ledger
rendering.
- Added committed UI verification screenshots under
`docs/pr-screenshots/pap-2837/`.
- Addressed Greptile review feedback around cheap-profile defaults,
shared profile types, and fallback test data.
## Verification
Local:
- `pnpm exec vitest run packages/shared/src/validators/issue.test.ts
server/src/__tests__/adapter-registry.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
server/src/__tests__/heartbeat-model-profile.test.ts
ui/src/components/IssueRunLedger.test.tsx
ui/src/lib/agent-config-patch.test.ts
ui/src/lib/issue-assignee-overrides.test.ts
ui/src/lib/new-agent-runtime-config.test.ts` — passed, 8 files / 103
tests.
- `pnpm exec vitest run ui/src/lib/new-agent-runtime-config.test.ts
ui/src/components/IssueRunLedger.test.tsx` — passed after
Greptile/rebase follow-up, 2 files / 17 tests.
- `pnpm --filter @paperclipai/ui typecheck` — passed after
Greptile/rebase follow-up.
- `pnpm -r typecheck` — passed.
- `pnpm build` — passed.
- `pnpm test:run` — did not complete successfully in this local
worktree: it stopped in pre-existing `@paperclipai/adapter-utils`
sandbox/SSH fixture suites outside this PR diff. Failures were 5s local
timeouts plus `git init -b` unsupported by this machine's Git 2.21.0.
The branch-specific targeted suites above passed.
- Branch was fetched/rebased onto `public-gh/master`; `git rev-list
--left-right --count public-gh/master...HEAD` reports `0 9`.
Remote PR checks on latest head
`e30bf399146451c86cee98ed528d51d33fa5af5a`:
- `policy` — passed.
- `verify` — passed.
- `e2e` — passed.
- `Greptile Review` — passed, confidence score 5/5; Greptile review
threads resolved.
- `security/snyk (cryppadotta)` — passed.
Screenshots:
- [New issue cheap lane
desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-cheap-desktop.png)
- [New issue custom lane
desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-custom-desktop.png)
- [New issue unsupported adapter
desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-unsupported-desktop.png)
- [Run ledger model profile badges
desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/runledger-profile-badges-desktop.png)
- Mobile variants are also in `docs/pr-screenshots/pap-2837/`.
## Risks
- Medium: heartbeat config mediation now merges runtime model profiles
into adapter configs, so adapter secret normalization and host-command
restrictions must keep covering nested config paths.
- Medium: the UI adds another issue creation choice; unsupported
adapters must keep hiding the cheap lane and preserve primary behavior.
- Low migration risk: 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 coding agent using GPT-5-class reasoning with repo tool use
and command execution. Exact served model/context window 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
- [ ] 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Adapter execution and retry classification decide whether agent work
pauses, retries, or recovers automatically
> - Transient provider failures need to be classified precisely so
Paperclip does not convert retryable upstream conditions into false hard
failures
> - At the same time, operators need an up-to-date model list for
Codex-backed agents and prompts should nudge agents toward targeted
verification instead of repo-wide sweeps
> - This pull request tightens transient recovery classification for
Claude and Codex, updates the agent prompt guidance, and adds Codex
model refresh support end-to-end
> - The benefit is better automatic retry behavior plus fresher
operator-facing model configuration
## What Changed
- added Codex usage-limit retry-window parsing and Claude extra-usage
transient classification
- normalized the heartbeat transient-recovery contract across adapter
executions and heartbeat scheduling
- documented that deferred comment wakes only reopen completed issues
for human/comment-reopen interactions, while system follow-ups leave
closed work closed
- updated adapter-utils prompt guidance to prefer targeted verification
- added Codex model refresh support in the server route, registry,
shared types, and agent config form
- added adapter/server tests covering the new parsing, retry scheduling,
and model-refresh behavior
## Verification
- `pnpm exec vitest run --project @paperclipai/adapter-utils
packages/adapter-utils/src/server-utils.test.ts`
- `pnpm exec vitest run --project @paperclipai/adapter-claude-local
packages/adapters/claude-local/src/server/parse.test.ts`
- `pnpm exec vitest run --project @paperclipai/adapter-codex-local
packages/adapters/codex-local/src/server/parse.test.ts`
- `pnpm exec vitest run --project @paperclipai/server
server/src/__tests__/adapter-model-refresh-routes.test.ts
server/src/__tests__/adapter-models.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/codex-local-execute.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-retry-scheduling.test.ts`
## Risks
- Moderate behavior risk: retry classification affects whether runs
auto-recover or block, so mistakes here could either suppress needed
retries or over-retry real failures
- Low workflow risk: deferred comment wake reopening is intentionally
scoped to human/comment-reopen interactions so system follow-ups do not
revive completed issues unexpectedly
> 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 with tool use and code execution
in the Codex CLI 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 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
- [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 external adapter plugin system (#2218) lets adapters ship as npm
modules loaded via `server/src/adapters/plugin-loader.ts`; since #4296
merged, each `ServerAdapterModule` can declare `sessionManagement`
(`supportsSessionResume`, `nativeContextManagement`,
`defaultSessionCompaction`) and have it preserved through the init-time
load via the new `resolveExternalAdapterRegistration` helper
> - #4296 fixed the init-time IIFE path at
`server/src/adapters/registry.ts:363-369` but noted that the hot-install
path at `server/src/routes/adapters.ts:174
registerWithSessionManagement` still unconditionally overwrites
module-provided `sessionManagement` during `POST /api/adapters/install`
> - Practical impact today: an external adapter installed via the API
needs a Paperclip restart before its declared `sessionManagement` takes
effect — the IIFE runs on next boot and preserves it, but until then the
hot-install overwrite wins
> - This PR closes that parity gap: `registerWithSessionManagement`
delegates to the same `resolveExternalAdapterRegistration` helper
introduced by #4296, unifying both load paths behind one resolver
> - The benefit is consistent behaviour between cold-start and
hot-install: no "install then restart" ritual; declared
`sessionManagement` on an external module is honoured the moment `POST
/api/adapters/install` returns 201
## What Changed
- `server/src/routes/adapters.ts`: `registerWithSessionManagement`
delegates to the exported `resolveExternalAdapterRegistration` helper
(added in #4296). Honours module-provided `sessionManagement` first,
falls back to host registry lookup, defaults `undefined`. Updated the
section comment to document the parity-with-IIFE intent.
- `server/src/routes/adapters.ts`: dropped the now-unused
`getAdapterSessionManagement` import.
- `server/src/adapters/registry.ts`: updated the JSDoc on
`resolveExternalAdapterRegistration` — previously said "Exported for
unit tests; runtime callers use the IIFE below", now says the helper is
used by both the init-time IIFE and the hot-install path in
`routes/adapters.ts`. Addresses Greptile C1.
- `server/src/__tests__/adapter-routes.test.ts`: new integration test —
installs a mocked external adapter module carrying a non-trivial
`sessionManagement` declaration and asserts
`findServerAdapter(type).sessionManagement` preserves it after `POST
/api/adapters/install` returns 201.
- `server/src/__tests__/adapter-routes.test.ts`: added
`findServerAdapter` to the shared test-scope variable set so the new
test can inspect post-install registry state.
## Verification
Targeted test runs from a clean tree on
`fix/external-session-management-hot-install` (rebased onto current
`upstream/master` now that #4296 has merged):
- `pnpm test server/src/__tests__/adapter-routes.test.ts` — 6 passed
(new test + 5 pre-existing)
- `pnpm test server/src/__tests__/adapter-registry.test.ts` — 15 passed
(ensures the IIFE path from #4296 continues to behave correctly)
- `pnpm -w run test` full workspace suite — 1923 passed / 1 skipped
(unrelated skip)
End-to-end smoke on file:
[`@superbiche/cline-paperclip-adapter@0.1.1`](https://www.npmjs.com/package/@superbiche/cline-paperclip-adapter)
and
[`@superbiche/qwen-paperclip-adapter@0.1.1`](https://www.npmjs.com/package/@superbiche/qwen-paperclip-adapter),
both public on npm, both declare `sessionManagement`. With this PR in
place, the "restart after install" step disappears — the declared
compaction policy is active immediately after the install response.
## Risks
- Low risk. The change replaces an inline mutation with a call to a
helper that already has dedicated unit coverage (#4296 added three tests
for `resolveExternalAdapterRegistration` covering module-provided,
registry-fallback, and undefined paths). Behaviour is a strict superset
of the prior path — externals that did not declare `sessionManagement`
continue to get the hardcoded-registry lookup; externals that did
declare it now have those values preserved instead of overwritten.
- No migration impact. The stored plugin records
(`~/.paperclip/adapter-plugins.json`) are unchanged. Existing
hot-installed adapters behave correctly before and after.
- No behavioural change for builtin adapters; they hit
`registerServerAdapter` directly and never flow through
`registerWithSessionManagement`.
## Model Used
- Provider and model: Claude (Anthropic) via Claude Code
- Model ID: `claude-opus-4-7` (1M context)
- Reasoning mode: standard (no extended thinking on this PR)
- Tool use: yes — file edits, subprocess invocations for
builds/tests/git via the Claude Code 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 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 — server-only change)
- [x] I have updated relevant documentation to reflect my changes (the
JSDoc on `resolveExternalAdapterRegistration` and the section comment
above `registerWithSessionManagement` now document the parity-with-IIFE
intent)
- [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
> - Adapters are how paperclip hands work off to specific agent
runtimes; since #2218, external adapter packages can ship as npm modules
loaded via `server/src/adapters/plugin-loader.ts`
> - Each `ServerAdapterModule` can declare `sessionManagement`
(`supportsSessionResume`, `nativeContextManagement`,
`defaultSessionCompaction`) — but the init-time load at
`registry.ts:363-369` hard-overwrote it with a hardcoded-registry lookup
that has no entries for external types, so modules could not actually
set these fields
> - The hot-install path at `routes/adapters.ts:179` →
`registerServerAdapter` preserves module-provided `sessionManagement`,
so externals worked after `POST /api/adapters/install` — *until the next
server restart*, when the init-time IIFE wiped it back to `undefined`
> - #2218 explicitly deferred this: *"Adapter execution model, heartbeat
protocol, and session management are untouched."* This PR is the natural
follow-up for session management on the plugin-loader path
> - This PR aligns init-time registration with the hot-install path:
honor module-provided `sessionManagement` first, fall back to the
hardcoded registry when absent (so externals overriding a built-in type
still inherit its policy). Extracted as a testable helper with three
unit tests
> - The benefit is external adapters can declare session-resume
capabilities consistently across cold-start and hot-install, without
requiring upstream additions to the hardcoded registry for each new
plugin
## What Changed
- `server/src/adapters/registry.ts`: extracted the merge logic into a
new exported helper `resolveExternalAdapterRegistration()` — honors
module-provided `sessionManagement` first, falls back to
`getAdapterSessionManagement(type)`, else `undefined`. The init-time
IIFE calls the helper instead of inlining an overwrite.
- `server/src/adapters/registry.ts`: updated the section comment (lines
331–340) to reflect the new semantics and cross-reference the
hot-install path's behavior.
- `server/src/__tests__/adapter-registry.test.ts`: new
`describe("resolveExternalAdapterRegistration")` block with three tests
— module-provided value preserved, registry fallback when module omits,
`undefined` when neither provides.
## Verification
Targeted test run from a clean tree on
`fix/external-session-management`:
```
cd server && pnpm exec vitest run src/__tests__/adapter-registry.test.ts
# 1 test file, 15 tests passed, 0 failed (12 pre-existing + 3 new)
```
Full server suite via the independent review pass noted under Model
Used: **1,156 tests passed, 0 failed**.
Typecheck note: `pnpm --filter @paperclipai/server exec tsc --noEmit`
surfaces two errors in `src/services/plugin-host-services.ts:1510`
(`createInteraction` + implicit-any). Verified by `git stash` + re-run
on clean `upstream/master` — they reproduce without this PR's changes.
Pre-existing, out of scope.
## Risks
- **Low behavioral risk.** Strictly additive: externals that do NOT
provide `sessionManagement` continue to receive exactly the same value
as before (registry lookup → `undefined` for pure externals, or the
builtin's entry for externals overriding a built-in type). Only a new
capability is unlocked; no existing behavior changes for existing
adapters.
- **No breaking change.** `ServerAdapterModule.sessionManagement` was
already optional at the type level. Externals that never set it see no
difference on either path.
- **Consistency verified.** Init-time IIFE now matches the post-`POST
/api/adapters/install` behavior — a server restart no longer regresses
the field.
## Note
This is part of a broader effort to close the parity gap between
external and built-in adapters. Once externals reach 1:1 capability
coverage with internals, new-adapter contributions can increasingly be
steered toward the external-plugin path instead of the core product — a
trajectory CONTRIBUTING.md already encourages ("*If the idea fits as an
extension, prefer building it with the plugin system*").
## Model Used
- **Provider**: Anthropic
- **Model**: Claude Opus 4.7
- **Exact model ID**: `claude-opus-4-7` (1M-context variant:
`claude-opus-4-7[1m]`)
- **Context window**: 1,000,000 tokens
- **Harness**: Claude Code (Anthropic's official CLI), orchestrated by
@superbiche as human-in-the-loop. Full file-editing, shell, and `gh`
tool use, plus parallel research subagents for fact-finding against
paperclip internals (plugin-loader contract, sessionCodec reachability,
UI parser surface, Cline CLI JSON schema).
- **Independent local review**: Gemini 3.1 Pro (Google) performed a
separate verification pass on the committed branch — confirmed the
approach & necessity, ran the full workspace build, and executed the
complete server test suite (1,156 tests, all passing). Not used for
authoring; second-opinion pass only.
- **Authoring split**: @superbiche identified the gap (while mapping the
external-adapter surface for a downstream adapter build) and shaped the
plan — categorising the surface into `works / acceptable /
needs-upstream` buckets, directing the surgical-diff approach on a fresh
branch from `upstream/master`, and calling the framing ("alignment bug
between init-time IIFE and hot-install path" rather than "missing
capability"). Opus 4.7 executed the fact-finding, the diff, the tests,
and drafted this PR body — all under direct 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 (convention-aligned bug fix on the external-adapter
plugin path introduced by #2218)
- [x] I have run tests locally and they pass (15/15 in the touched file;
1,156/1,156 full server suite via the independent Gemini 3.1 Pro review)
- [x] I have added tests where applicable (3 new for the extracted
helper)
- [x] If this change affects the UI, I have included before/after
screenshots (no UI touched)
- [x] I have updated relevant documentation to reflect my changes
(in-file comment reflects new semantics)
- [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 and records their actions through
auditable issue comments and API writes.
> - The local adapter registry is responsible for adapting each agent
runtime to Paperclip's server-side execution context.
> - The Hermes local adapter delegated directly to
`hermes-paperclip-adapter`, whose current execution context type
predates the server `authToken` field.
> - Without explicitly passing the run-scoped agent token and run id
into Hermes, Hermes could inherit a server or board-user
`PAPERCLIP_API_KEY` and lack a usable `PAPERCLIP_RUN_ID` for mutating
API calls.
> - That made Paperclip writes from Hermes agents risk appearing under
the wrong identity or without the correct run-scoped attribution.
> - This pull request wraps the Hermes execution call so Hermes receives
the agent run JWT as `PAPERCLIP_API_KEY` and the current execution id as
`PAPERCLIP_RUN_ID` while preserving explicit adapter configuration where
appropriate.
> - Follow-up review fixes preserve Hermes' built-in prompt when no
custom prompt template exists and document the intentional type cast.
> - The benefit is reliable agent attribution for the covered local
Hermes path without clobbering Hermes' default heartbeat/task
instructions.
## What Changed
- Wrapped `hermesLocalAdapter.execute` so `ctx.authToken` is injected
into `adapterConfig.env.PAPERCLIP_API_KEY` when no explicit Paperclip
API key is already configured.
- Injected `ctx.runId` into `adapterConfig.env.PAPERCLIP_RUN_ID` so the
auth guard's `X-Paperclip-Run-Id: $PAPERCLIP_RUN_ID` instruction
resolves to the current run id.
- Added a Paperclip API auth guard to existing custom Hermes
`promptTemplate` values without creating a replacement prompt when no
custom template exists.
- Documented the intentional `as unknown as` cast needed until
`hermes-paperclip-adapter` ships an `AdapterExecutionContext` type that
includes `authToken`.
- Added registry tests for JWT injection, run-id injection, explicit key
preservation, default prompt preservation, and the no-`authToken`
early-return path.
## Verification
- [x] `pnpm --filter "./server" exec vitest run adapter-registry` - 8
tests passed.
- [x] `pnpm --filter "./server" typecheck` - passed.
- [x] Trigger a Hermes agent heartbeat and verify Paperclip writes
appear under the agent identity rather than a shared board-user
identity, with the correct run id on mutating requests.
## Risks
- Low migration risk: this changes only the Hermes local adapter wrapper
and tests.
- Existing explicit `adapterConfig.env.PAPERCLIP_API_KEY` values are
preserved to avoid breaking intentionally configured agents.
- `PAPERCLIP_RUN_ID` is set from `ctx.runId` for each execution so
mutating API calls use the current run id instead of a stale or literal
placeholder value.
- Prompt behavior is intentionally conservative: the auth guard is only
prepended when a custom prompt template already exists, so Hermes'
built-in default prompt remains intact for unconfigured agents.
- Remaining operational risk: the identity and run-id behavior should
still be verified with a live Hermes heartbeat before relying on it in
production.
## Model Used
- OpenAI Codex, GPT-5 family coding agent, tool use enabled for local
shell, GitHub CLI, 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 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: backend-only change)
- [x] I have updated relevant documentation to reflect my changes (not
applicable: no product docs changed; PR description updated)
- [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>
Co-authored-by: Dotta <bippadotta@protonmail.com>
## Summary
This fixes the Hermes local adapter so that a configured command
override is respected during both environment tests and execution.
## Problem
The Hermes adapter expects `adapterConfig.hermesCommand`, but the
generic local command path in the UI was storing
`adapterConfig.command`.
As a result, changing the command in the UI did not reliably affect
runtime behavior. In real use, the adapter could still fall back to the
default `hermes` binary.
This showed up clearly in setups where Hermes is launched through a
wrapper command rather than installed directly on the host.
## What changed
- switched the Hermes local UI adapter to the Hermes-specific config
builder
- updated the configuration form to read and write `hermesCommand` for
`hermes_local`
- preserved the override correctly in the test-environment path
- added server-side normalization from legacy `command` to
`hermesCommand`
## Compatibility
The server-side normalization keeps older saved agent configs working,
including configs that still store the value under `command`.
## Validation
Validated against a Docker-based Hermes workflow using a local wrapper
exposed through a symlinked command:
- `Command = hermes-docker`
- environment test respects the override
- runs no longer fall back to `hermes`
Typecheck also passed for both UI and server.
Co-authored-by: NoronhaH <NoronhaH@users.noreply.github.com>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Local adapter capability flags decide which configuration surfaces
the UI and server expose for each adapter.
> - `hermes_local` currently advertises managed instructions bundle
support, so Paperclip exposes the AGENTS.md bundle flow for Hermes
agents.
> - The bundled `hermes-paperclip-adapter` only consumes
`promptTemplate` at runtime and does not read `instructionsFilePath`, so
that advertised bundle path silently does nothing.
> - Issue #3833 reports exactly that mismatch: users configure AGENTS.md
instructions, but Hermes only receives the built-in heartbeat prompt.
> - This pull request stops advertising managed instructions bundles for
`hermes_local` until the adapter actually consumes bundle files at
runtime.
## What Changed
- Changed the built-in `hermes_local` server adapter registration to
report `supportsInstructionsBundle: false`.
- Updated the UI's synchronous built-in capability fallback so Hermes no
longer shows the managed instructions bundle affordance on first render.
- Added regression coverage in
`server/src/__tests__/adapter-routes.test.ts` to assert that
`hermes_local` still reports skills + local JWT support, but not
instructions bundle support.
## Verification
- `git diff --check`
- `node --experimental-strip-types --input-type=module -e "import {
findActiveServerAdapter } from './server/src/adapters/index.ts'; const
adapter = findActiveServerAdapter('hermes_local');
console.log(JSON.stringify({ type: adapter?.type,
supportsInstructionsBundle: adapter?.supportsInstructionsBundle,
supportsLocalAgentJwt: adapter?.supportsLocalAgentJwt, supportsSkills:
Boolean(adapter?.listSkills || adapter?.syncSkills) }));"`
- Observed
`{"type":"hermes_local","supportsInstructionsBundle":false,"supportsLocalAgentJwt":true,"supportsSkills":true}`
- Added adapter-routes regression assertions for the Hermes capability
contract; CI should validate the full route path in a clean workspace.
## Risks
- Low risk: this only changes the advertised capability surface for
`hermes_local`.
- Behavior change: Hermes agents will no longer show the broken managed
instructions bundle UI until the underlying adapter actually supports
`instructionsFilePath`.
- Existing Hermes skill sync and local JWT behavior are unchanged.
## Model Used
- OpenAI Codex, GPT-5.4 class coding agent, medium reasoning,
terminal/git/gh 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
- [ ] 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
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations 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
- OpenAI Codex, GPT-5.4 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
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 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Heartbeat runs are the control-plane record of each agent execution
window.
> - Long-running local agents can exhaust context or stop while still
holding useful next-step state.
> - Operators need that stop reason, next action, and continuation path
to be durable and visible.
> - This pull request adds run liveness metadata, continuation
summaries, and UI surfaces for issue run ledgers.
> - The benefit is that interrupted or long-running work can resume with
clearer context instead of losing the agent's last useful handoff.
## What Changed
- Added heartbeat-run liveness fields, continuation attempt tracking,
and an idempotent `0058` migration.
- Added server services and tests for run liveness, continuation
summaries, stop metadata, and activity backfill.
- Wired local and HTTP adapters to surface continuation/liveness context
through shared adapter utilities.
- Added shared constants, validators, and heartbeat types for liveness
continuation state.
- Added issue-detail UI surfaces for continuation handoffs and the run
ledger, with component tests.
- Updated agent runtime docs, heartbeat protocol docs, prompt guidance,
onboarding assets, and skills instructions to explain continuation
behavior.
- Addressed Greptile feedback by scoping document evidence by run,
excluding system continuation-summary documents from liveness evidence,
importing shared liveness types, surfacing hidden ledger run counts,
documenting bounded retry behavior, and moving run-ledger liveness
backfill off the request path.
## Verification
- `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts
server/src/__tests__/run-continuations.test.ts
server/src/__tests__/run-liveness.test.ts
server/src/__tests__/activity-service.test.ts
server/src/__tests__/documents-service.test.ts
server/src/__tests__/issue-continuation-summary.test.ts
server/src/services/heartbeat-stop-metadata.test.ts
ui/src/components/IssueRunLedger.test.tsx
ui/src/components/IssueContinuationHandoff.test.tsx
ui/src/components/IssueDocumentsSection.test.tsx`
- `pnpm --filter @paperclipai/db build`
- `pnpm exec vitest run server/src/__tests__/activity-service.test.ts
ui/src/components/IssueRunLedger.test.tsx`
- `pnpm --filter @paperclipai/ui typecheck`
- `pnpm --filter @paperclipai/server typecheck`
- `pnpm exec vitest run server/src/__tests__/activity-service.test.ts
server/src/__tests__/run-continuations.test.ts
ui/src/components/IssueRunLedger.test.tsx`
- `pnpm exec vitest run
server/src/__tests__/heartbeat-process-recovery.test.ts -t "treats a
plan document update"`
- `pnpm exec vitest run server/src/__tests__/activity-service.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts -t "activity
service|treats a plan document update"`
- Remote PR checks on head `e53b1a1d`: `verify`, `e2e`, `policy`, and
Snyk all passed.
- Confirmed `public-gh/master` is an ancestor of this branch after
fetching `public-gh master`.
- Confirmed `pnpm-lock.yaml` is not included in the branch diff.
- Confirmed migration `0058_wealthy_starbolt.sql` is ordered after
`0057` and uses `IF NOT EXISTS` guards for repeat application.
- Greptile inline review threads are resolved.
## Risks
- Medium risk: this touches heartbeat execution, liveness recovery,
activity rendering, issue routes, shared contracts, docs, and UI.
- Migration risk is mitigated by additive columns/indexes and idempotent
guards.
- Run-ledger liveness backfill is now asynchronous, so the first ledger
response can briefly show historical missing liveness until the
background backfill completes.
- UI screenshot coverage is not included in this packaging pass;
validation is currently through focused component tests.
> 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-5.4, local tool-use coding agent with terminal, git,
GitHub connector, GitHub CLI, and Paperclip API access.
## 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
Screenshot note: no before/after screenshots were captured in this PR
packaging pass; the UI changes are covered by focused component tests
listed above.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip is the control plane for autonomous AI companies.
> - V1 needs to stay local-first while also supporting shared,
authenticated deployments.
> - Human operators need real identities, company membership, invite
flows, profile surfaces, and company-scoped access controls.
> - Agents and operators also need the existing issue, inbox, workspace,
approval, and plugin flows to keep working under those authenticated
boundaries.
> - This branch accumulated the multi-user implementation, follow-up QA
fixes, workspace/runtime refinements, invite UX improvements,
release-branch conflict resolution, and review hardening.
> - This pull request consolidates that branch onto the current `master`
branch as a single reviewable PR.
> - The benefit is a complete multi-user implementation path with tests
and docs carried forward without dropping existing branch work.
## What Changed
- Added authenticated human-user access surfaces: auth/session routes,
company user directory, profile settings, company access/member
management, join requests, and invite management.
- Added invite creation, invite landing, onboarding, logo/branding,
invite grants, deduped join requests, and authenticated multi-user E2E
coverage.
- Tightened company-scoped and instance-admin authorization across
board, plugin, adapter, access, issue, and workspace routes.
- Added profile-image URL validation hardening, avatar preservation on
name-only profile updates, and join-request uniqueness migration cleanup
for pending human requests.
- Added an atomic member role/status/grants update path so Company
Access saves no longer leave partially updated permissions.
- Improved issue chat, inbox, assignee identity rendering,
sidebar/account/company navigation, workspace routing, and execution
workspace reuse behavior for multi-user operation.
- Added and updated server/UI tests covering auth, invites, membership,
issue workspace inheritance, plugin authz, inbox/chat behavior, and
multi-user flows.
- Merged current `public-gh/master` into this branch, resolved all
conflicts, and verified no `pnpm-lock.yaml` change is included in this
PR diff.
## Verification
- `pnpm exec vitest run server/src/__tests__/issues-service.test.ts
ui/src/components/IssueChatThread.test.tsx ui/src/pages/Inbox.test.tsx`
- `pnpm run preflight:workspace-links && pnpm exec vitest run
server/src/__tests__/plugin-routes-authz.test.ts`
- `pnpm exec vitest run server/src/__tests__/plugin-routes-authz.test.ts
server/src/__tests__/workspace-runtime-service-authz.test.ts
server/src/__tests__/access-validators.test.ts`
- `pnpm exec vitest run
server/src/__tests__/authz-company-access.test.ts
server/src/__tests__/routines-routes.test.ts
server/src/__tests__/sidebar-preferences-routes.test.ts
server/src/__tests__/approval-routes-idempotency.test.ts
server/src/__tests__/openclaw-invite-prompt-route.test.ts
server/src/__tests__/agent-cross-tenant-authz-routes.test.ts
server/src/__tests__/routines-e2e.test.ts`
- `pnpm exec vitest run server/src/__tests__/auth-routes.test.ts
ui/src/pages/CompanyAccess.test.tsx`
- `pnpm --filter @paperclipai/shared typecheck && pnpm --filter
@paperclipai/db typecheck && pnpm --filter @paperclipai/server
typecheck`
- `pnpm --filter @paperclipai/shared typecheck && pnpm --filter
@paperclipai/server typecheck`
- `pnpm --filter @paperclipai/ui typecheck`
- `pnpm db:generate`
- `npx playwright test --config tests/e2e/playwright.config.ts --list`
- Confirmed branch has no uncommitted changes and is `0` commits behind
`public-gh/master` before PR creation.
- Confirmed no `pnpm-lock.yaml` change is staged or present in the PR
diff.
## Risks
- High review surface area: this PR contains the accumulated multi-user
branch plus follow-up fixes, so reviewers should focus especially on
company-boundary enforcement and authenticated-vs-local deployment
behavior.
- UI behavior changed across invites, inbox, issue chat, access
settings, and sidebar navigation; no browser screenshots are included in
this branch-consolidation PR.
- Plugin install, upgrade, and lifecycle/config mutations now require
instance-admin access, which is intentional but may change expectations
for non-admin board users.
- A join-request dedupe migration rejects duplicate pending human
requests before creating unique indexes; deployments with unusual
historical duplicates should review the migration behavior.
- Company member role/status/grant saves now use a new combined
endpoint; older separate endpoints remain for compatibility.
- Full production build was not run locally in this heartbeat; CI should
cover the full matrix.
## Model Used
- OpenAI Codex coding agent, GPT-5-based model, CLI/tool-use
environment. Exact deployed model identifier and context window were 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 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
Note on screenshots: this is a branch-consolidation PR for an
already-developed multi-user branch, and no browser screenshots were
captured during this heartbeat.
---------
Co-authored-by: dotta <dotta@example.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Thinking Path
> - Paperclip orchestrates AI agents via adapters (`claude_local`,
`codex_local`, etc.)
> - Each adapter type has different capabilities — instructions bundles,
skill materialization, local JWT — but these were gated by 5 hardcoded
type lists scattered across server routes and UI components
> - External adapter plugins (e.g. a future `opencode_k8s`) cannot add
themselves to those hardcoded lists without patching Paperclip source
> - The existing `supportsLocalAgentJwt` field on `ServerAdapterModule`
proves the right pattern already exists; it just wasn't applied to the
other capability gates
> - This pull request replaces the 4 remaining hardcoded lists with
declarative capability flags on `ServerAdapterModule`, exposed through
the adapter listing API
> - The benefit is that external adapter plugins can now declare their
own capabilities without any changes to Paperclip source code
## What Changed
- **`packages/adapter-utils/src/types.ts`** — added optional capability
fields to `ServerAdapterModule`: `supportsInstructionsBundle`,
`instructionsPathKey`, `requiresMaterializedRuntimeSkills`
- **`server/src/routes/agents.ts`** — replaced
`DEFAULT_MANAGED_INSTRUCTIONS_ADAPTER_TYPES` and
`ADAPTERS_REQUIRING_MATERIALIZED_RUNTIME_SKILLS` hardcoded sets with
capability-aware helper functions that fall back to the legacy sets for
adapters that don't set flags
- **`server/src/routes/adapters.ts`** — `GET /api/adapters` now includes
a `capabilities` object per adapter (all four flags + derived
`supportsSkills`)
- **`server/src/adapters/registry.ts`** — all built-in adapters
(`claude_local`, `codex_local`, `process`, `cursor`) now declare flags
explicitly
- **`ui/src/adapters/use-adapter-capabilities.ts`** — new hook that
fetches adapter capabilities from the API
- **`ui/src/pages/AgentDetail.tsx`** — replaced hardcoded `isLocal`
allowlist with `capabilities.supportsInstructionsBundle` from the API
- **`ui/src/components/AgentConfigForm.tsx`** /
**`OnboardingWizard.tsx`** — replaced `NONLOCAL_TYPES` denylist with
capability-based checks
- **`server/src/__tests__/adapter-registry.test.ts`** /
**`adapter-routes.test.ts`** — tests covering flag exposure,
undefined-when-unset, and per-adapter values
- **`docs/adapters/creating-an-adapter.md`** — new "Capability Flags"
section documenting all flags and an example for external plugin authors
## Verification
- Run `pnpm test --filter=@paperclip/server -- adapter-registry
adapter-routes` — all new tests pass
- Run `pnpm test --filter=@paperclip/adapter-utils` — existing tests
still pass
- Spin up dev server, open an agent with `claude_local` type —
instructions bundle tab still visible
- Create/open an agent with a non-local type — instructions bundle tab
still hidden
- Call `GET /api/adapters` and verify each adapter includes a
`capabilities` object with the correct flags
## Risks
- **Low risk overall** — all new flags are optional with
backwards-compatible fallbacks to the existing hardcoded sets; no
adapter behaviour changes unless a flag is explicitly set
- Adapters that do not declare flags continue to use the legacy lists,
so there is no regression risk for built-in adapters
- The UI capability hook adds one API call to AgentDetail mount; this is
a pre-existing endpoint, so no new latency path is introduced
## Model Used
- Provider: Anthropic
- Model: Claude Sonnet 4.6 (`claude-sonnet-4-6`)
- Context: 200k token context window
- Mode: Agentic tool use (code editing, bash, grep, file reads)
## 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
- [x] I have added or updated tests where applicable
- [ ] 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
---------
Co-authored-by: Pawla Abdul (Bot) <pawla@groombook.dev>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Previously, --model was completely skipped for Bedrock users, so the
model dropdown selection was silently ignored and the CLI always used
its default model. Selecting Haiku would still run Opus.
- Add listClaudeModels() that returns Bedrock-native model IDs
(us.anthropic.*) when Bedrock env is detected
- Register listModels on claude_local adapter so the UI dropdown
shows Bedrock models instead of Anthropic API names
- Allow --model to pass through when the ID is a Bedrock-native
identifier (us.anthropic.* or ARN)
- Add isBedrockModelId() helper shared by execute.ts and test.ts
Follows up on #2793 which added basic Bedrock auth detection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the client-side-only override store with a real server-side
toggle. When a developer pauses the external override, the server swaps
ALL adapter behavior back to the builtin — execute handler, model listing,
config schema, detection — not just the UI parser.
Server changes:
- registry.ts: builtinFallbacks map + pausedOverrides set + setOverridePaused()
- routes/adapters.ts: PATCH /api/adapters/:type/override endpoint + overridePaused in list
UI changes:
- adapters.ts: setOverridePaused API method + overridePaused on AdapterInfo
- AdapterManager: overrideMutation calls server, instant feedback via invalidate()
- use-disabled-adapters.ts: reads adapter.overridePaused from server response
Removed:
- disabled-overrides-store.ts: no longer needed (server is the source of truth)
Note: already-running agent sessions keep the adapter they started with.
Only new sessions use the swapped adapter.
Previously external adapters matching a built-in type were skipped with
a warning. Now they override the built-in, so plugin developers can ship
improved versions of existing adapters (e.g. hermes-paperclip-adapter)
without removing the built-in fallback for users who haven't installed
the plugin.
- Fix external adapters (hermes, droid) not auto-selected when
navigating with ?adapterType= param — was using a stale
module-level Set built before async adapter registration
- Move SchemaConfigFields to render after thinking effort (same
visual area as Claude's chrome toggle) instead of bottom of
config section
- Extract SelectField into its own component to fix React hooks
order violation when schema fields change between renders
- Add onAdapterChange() subscription in registry.ts so
registerUIAdapter() notifies components when dynamic parsers
load, fixing stale parser for old runs
- Add parserTick to both RunTranscriptView and
useLiveRunTranscripts to force recomputation on parser change
Re-align phase1 with upstream: hermes_local ships via hermes-paperclip-adapter on the server and UI (hermes-local module). Fixes ERR_PNPM_OUTDATED_LOCKFILE from server/package.json missing a dep still present in the lockfile.
Add shared BUILTIN_ADAPTER_TYPES and skip external plugin registration when it would override a built-in type. Docs list Hermes as built-in; Droid remains the primary external example.
Made-with: Cursor
- Plugin loader: install/reload/remove/reinstall external adapters
from npm packages or local directories
- Plugin store persisted at ~/.paperclip/adapter-plugins.json
- Self-healing UI parser resolution with version caching
- UI: Adapter Manager page, dynamic loader, display registry
with humanized names for unknown adapter types
- Dev watch: exclude adapter-plugins dir from tsx watcher
to prevent mid-request server restarts during reinstall
- All consumer fallbacks use getAdapterLabel() for consistent display
- AdapterTypeDropdown uses controlled open state for proper close behavior
- Remove hermes-local from built-in UI (externalized to plugin)
- Add docs for external adapters and UI parser contract
Dotta
Nicky Leach
David V
Frank Gonnello
machjesusmoto
Devin Foley
Zen Process
Jannes Stubbemann
Michel Tomas
Michel Tomas
Robin van Duiven
Hiuri Noronha
LeonSGP
Chris Farhood
Dotta
kimnamu
dotta
HenkDz
