## 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
> - 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 1/8 and focuses on fixture and demo MCP
servers
> - 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: Developers need deterministic local MCP fixtures and visible
demo servers without pulling in the governed production runtime.
- Proposed solution: Adds the Google Sheets and KV demo MCP packages,
fixture catalog/servers, smoke harness, guide, and the root
smoke/typecheck registration hunks.
- 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 `master`.
- 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: QA for fixture and smoke coverage; Greptile on every
PR.
## What Changed
- Adds the Google Sheets and KV demo MCP packages, fixture
catalog/servers, smoke harness, guide, and the root smoke/typecheck
registration hunks.
- 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`
- `pnpm --filter @paperclipai/google-sheets-mcp-server test` — 27 tests
passed
- `pnpm --filter @paperclipai/kv-demo-mcp-server test` — 12 tests passed
## Risks
- The new packages add dependencies that are intentionally not committed
to `pnpm-lock.yaml`, per repository policy.
- 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.
> - 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.
> - 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, distributed primarily via the `paperclipai` npm package and its
`@paperclipai/*` workspace packages.
> - The release subsystem (`scripts/release-package-*`) decides which
workspace packages CI republishes at the unified calver version each
release, and `replaceWorkspaceDeps()` rewrites every internal
`workspace:` dependency to that calver version at publish time.
> - The gap: a package that publishes from CI can declare a `workspace:`
dependency on a package that is NOT enrolled for CI publish. The
dependency spec gets rewritten to a calver version that is never
actually published, so the dependent becomes uninstallable.
> - This shipped for real: a recent change made `@paperclipai/server`
depend on `@paperclipai/skills-catalog`, but skills-catalog was not on
the calver release train — so canary builds after that merge failed to
resolve `@paperclipai/skills-catalog@<calver>` and `npx
paperclipai@canary run` broke.
> - This PR addresses it durably by (a) putting every remaining internal
package on the CI release train so no internal dependency can dangle,
and (b) adding a fail-fast guard so this class of break can never ship
again.
> - The benefit is that canary and stable installs resolve all internal
dependencies, and any future unpublishable workspace edge fails the
release build with a clear, named error instead of producing a broken
package.
## Linked Issues or Issue Description
Refs #8327 (introduced the `server -> skills-catalog` runtime dependency
that surfaced the gap).
No public issue tracks this; describing it in-PR:
- **Problem:** After #8327, `npx paperclipai@canary run` failed for
builds past the merge because `@paperclipai/skills-catalog` was
rewritten to a calver version that was never published (the package was
not enrolled for CI publish). Versions before the merge still ran.
- **Root cause:** A `publishFromCi:true` package can declare a
`workspace:` dependency on a package that is not `publishFromCi:true`;
the release-time version rewrite then points at a non-existent published
version.
## What Changed
- Enrolled every remaining internal package on the calver release train
by setting `publishFromCi: true` in
`scripts/release-package-manifest.json`: `skills-catalog`,
`teams-catalog`, `plugin-workspace-diff`, `plugin-kubernetes`,
`plugin-novita-sandbox`. There are now zero `publishFromCi:false`
entries.
- `skills-catalog`, `teams-catalog`, `plugin-workspace-diff` already
existed on npm — CI simply republishes them at calver.
- `plugin-kubernetes` and `plugin-novita-sandbox` were not on npm; their
one-time first publish was bootstrapped so the
`check-release-package-bootstrap` gate passes.
- Added `findUnpublishableWorkspaceEdges()` to
`scripts/release-package-map.mjs`, wired into
`buildReleasePackagePlan()`. The release map build now fails fast
(surfaced by the `check` CI already runs) whenever a
`publishFromCi:true` package declares a runtime `workspace:` dependency
(`dependencies`/`optionalDependencies`/`peerDependencies`) on a
non-`publishFromCi:true` `@paperclipai/*` package, naming the offending
edge.
- Added tests covering positive/negative detection, all three dependency
sections, unknown-package edges, off-train edges, and the live manifest.
## Verification
- `node --test scripts/release-package-map.test.mjs` → 9/9 pass
(includes a test asserting the live manifest has no unpublishable
edges).
- `node scripts/check-release-package-bootstrap.mjs
scripts/release-package-manifest.json` → passes, naming all five
newly-enabled packages (all confirmed present on npm).
- Confirmed via `npm view` that all five packages resolve on the public
registry.
## Risks
- Low risk. The change only enrolls already-existing (or
freshly-bootstrapped) packages onto the existing release train and adds
a build-time validation. No runtime code paths change. The new guard can
only *fail* a release that was already going to ship a broken package.
## Model Used
Claude Opus 4.7 (claude-opus-4-7), extended thinking, with tool use /
code execution.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change 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] If this change affects the UI, I have included before/after
screenshots (N/A — no UI changes)
- [x] I have updated relevant documentation to reflect my changes (N/A —
no doc-facing behavior change)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [ ] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip already separates agent adapters from execution
environments, so agents can run locally, over SSH, or through sandbox
providers.
> - Sandbox provider plugins let Paperclip add new cloud runtimes
without changing each agent adapter.
> - Novita Agent Sandbox is a cloud runtime for AI agent workloads with
isolated filesystems, command execution, templates, timeout controls,
and pause/resume behavior.
> - Paperclip currently has sandbox provider examples for Daytona and
Cloudflare, but not Novita.
> - This pull request adds a Novita sandbox provider plugin using the
existing provider-plugin lifecycle.
> - The benefit is that Paperclip users can run existing adapters such
as Codex, Claude, Gemini, OpenCode, Cursor, or ACPX inside Novita Agent
Sandbox environments.
## Linked Issues or Issue Description
Fixes#7596
## What Changed
- Added `packages/plugins/sandbox-providers/novita` as a standalone
sandbox provider plugin package.
- Registered provider key `novita` with `kind: "sandbox_provider"` and
`environment.drivers.register` capability.
- Implemented Novita environment lifecycle hooks: validate config,
probe, acquire lease, resume lease, release lease, destroy lease,
realize workspace, and execute commands.
- Added config support for `apiKey`, `domain`, `template`,
`requestedCwd`, `timeoutMs`, `requestTimeoutMs`, `secure`, `autoPause`,
and `reuseLease`.
- Added README documentation for setup, configuration, and lifecycle
behavior.
- Added tests for manifest shape, config parsing, safe shell command
wrapping, stdin delimiter safety, and env-key validation.
## Verification
From `packages/plugins/sandbox-providers/novita`:
- `pnpm typecheck`
- `pnpm test`
The tests avoid live Novita API calls and cover the provider's static
contract and command-wrapping behavior. Live end-to-end verification
requires a Paperclip instance with the plugin installed and a Novita API
key configured as either a Paperclip secret or `NOVITA_API_KEY` in the
worker environment.
## Risks
- This adds a new direct dependency on the Novita Sandbox JS SDK
(`novita-sandbox`). Socket/Snyk should review the package as part of
normal dependency checks.
- The implementation relies on Novita SDK command execution semantics;
live provider behavior should be verified with a real Novita sandbox
before marking the plugin production-ready.
- `reuseLease` maps Paperclip release behavior to Novita `betaPause()`.
If pause is unavailable for a selected template, the plugin falls back
to best-effort kill during release.
- Low migration risk for existing users because this is a new standalone
provider plugin and does not change existing adapters or built-in
providers.
> 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 Codex CLI, with repository file access, shell
command execution, GitHub CLI/API usage, and local TypeScript/Vitest
verification. Web and local documentation context were used for Novita
Sandbox SDK/API behavior.
## 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
- [ ] 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Devin Foley <devin@paperclip.ing>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - Sandbox providers are the seam that lets agent runs execute in
isolated environments; today the only first-party remote provider is
Daytona, a hosted third-party service
> - Self-hosters running Paperclip on their own infrastructure (often
Kubernetes already) have no first-party way to run agent sandboxes on a
cluster they control
> - That gap matters for teams with data-residency, sovereignty, or cost
constraints who cannot or will not send workloads to a hosted sandbox
service
> - This pull request adds a Kubernetes sandbox-provider plugin as a
standalone, workspace-excluded package: it implements every
SandboxProvider hook the Daytona provider does, on infrastructure the
operator owns
> - The benefit is that any Paperclip deployment with a Kubernetes
cluster gets multi-tenant, network-isolated, quota-bounded agent
sandboxes with zero new external dependencies
## Linked Issues or Issue Description
No existing issue. Following the feature template:
- **Problem:** Paperclip's remote sandbox execution requires a hosted
third-party provider. Self-hosters cannot run agent sandboxes on their
own Kubernetes clusters with a first-party provider.
- **Proposed solution:** A `@paperclipai/plugin-kubernetes`
sandbox-provider plugin with two backends: long-lived sandboxes via the
[kubernetes-sigs/agent-sandbox](https://github.com/kubernetes-sigs/agent-sandbox)
CRD (multi-command exec, adapter-install pattern) and one-shot
`batch/v1` Jobs (stable APIs only, no extra controllers).
- **Alternatives considered:** Driving kubectl from a generic shell
provider (no lifecycle/lease semantics), or requiring a hosted provider
(exactly the constraint this removes).
## What Changed
This is **stage 1 of 3** of a staged contribution (direction agreed with
maintainers): the plugin package alone. Stage 2 (server integration:
lease params, provider registration) and stage 3 (agent runtime images +
CI) are companion PRs that will be cross-linked from a comment here.
- New package `packages/plugins/sandbox-providers/kubernetes`
(workspace-excluded, like the path already carved out in
`pnpm-workspace.yaml`): src, unit + kind integration tests, operator
prerequisite manifests, README, smoke-test guide
- Implements the full SandboxProvider hook surface the Daytona provider
implements: `validateConfig`, `probe`, `acquireLease`, `resumeLease`,
`releaseLease`, `destroyLease`, `realizeWorkspace`, `execute`
- Two backends: `sandbox-cr` (default; long-lived pod via the
agent-sandbox `Sandbox` CR, supports multi-command exec) and `job`
(one-shot `batch/v1` Job; nothing beyond k8s 1.27+ required)
- Per-run adapter resolution: one environment serves mixed harnesses;
the per-run `adapterType` hint is read through a local optional type
extension, so the plugin typechecks and builds against the current
plugin SDK and simply falls back to the environment's configured default
adapter until stage 2 lands
- Exec-env wrapping: the Kubernetes exec API carries no environment, so
commands are wrapped to receive the run's env
- Fast-upload interception for workspace realization, scoped per lease
- Per-tenant isolation: derived namespace per company, RBAC,
ResourceQuota, restricted-PSS pod security (runAsNonRoot, drop ALL,
seccomp RuntimeDefault, no SA token automount)
- Network egress policy in two flavors: native `NetworkPolicy` and
`CiliumNetworkPolicy` (FQDN allowlists)
- Image allowlist with glob matching, registry override, and per-run
image override validation
- Per-run Kubernetes Secrets carrying agent credentials, ownerRef'd to
the Job or Sandbox CR for cascade GC
## Verification
- Standalone build, exactly as the README documents:
```bash
cd packages/plugins/sandbox-providers/kubernetes
pnpm install --ignore-workspace
pnpm test # 147 unit tests, 17 files, all green
pnpm typecheck # clean against the in-repo plugin SDK on master
pnpm build # dist/ emitted, manifest + worker entrypoints present
```
- A kind-cluster end-to-end integration test is included
(`RUN_K8S_INTEGRATION_TESTS=1 pnpm test
test/integration/end-to-end-run.test.ts`)
- Beyond CI: this provider has been verified in a production
multi-tenant deployment against five harnesses (opencode, pi, codex,
gemini, claude code) with real billed runs
## Risks
- **Zero behavior change for any existing deployment.** The package is
workspace-excluded; nothing in the server imports or loads it until
stage 2's integration lands. No existing code paths are touched.
- The default `sandbox-cr` backend depends on an alpha CRD
(`agents.x-k8s.io/v1alpha1`); the README flags this and the `job`
backend uses only stable APIs as a fallback.
- Risk surface is confined to deployments that explicitly install and
configure the plugin.
- The default runtime images (`ghcr.io/paperclipai/agent-runtime-*`) are
published by the stage 3 companion PR (#7934); until that lands,
deployments must point `runtimeImage` at their own images.
## Model Used
Claude Opus 4.8 (1M context), extended thinking, with tool use (Claude
Code).
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have 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 (no UI changes)
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (pending this push)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fixes#7551
## Thinking Path
> - Paperclip is the control plane for AI-agent companies, and reusable
company/team setup is part of making those companies faster to launch.
> - The teams catalog work introduces app-shipped team templates that
can be browsed, previewed, and installed into a company.
> - Catalog installation crosses several contracts: bundled package
contents, shared API types, server import/install behavior, CLI
workflows, and the board UI.
> - Agents also need a safe path through catalog installs: scoped
company selection, explicit source policy, approval fallback for agent
creation, and preserved catalog provenance.
> - This pull request extracts the completed teams catalog branch into
one reviewable PR on top of `public-gh/master`.
> - The benefit is a reusable teams catalog foundation with server, CLI,
package, docs, and hidden UI surfaces kept in sync.
## What Changed
- Added the `@paperclipai/teams-catalog` package with bundled/optional
team definitions, generated manifest, validators, catalog builder tests,
and migration notes.
- Added shared teams catalog types/validators plus server routes and
services for listing, previewing, and installing catalog teams.
- Integrated catalog install with company portability, skill/source
policy checks, provenance metadata, origin hashes, target-manager
reparenting, and installed/out-of-date detection.
- Added CLI `teams` commands and agent-safe company selection behavior,
including `company current` and approval fallback for forbidden
agent-run installs.
- Added hidden Team Catalog UI/API/query surfaces, Storybook fixtures,
and targeted UI tests while keeping the UI route out of primary
navigation.
- Added docs for CLI/company/teams catalog behavior and removed
generated screenshot artifacts from the PR diff.
## Verification
- `pnpm exec vitest run cli/src/__tests__/company.test.ts
cli/src/__tests__/teams.test.ts
packages/teams-catalog/src/catalog-builder.test.ts
packages/teams-catalog/src/shipped-catalog.test.ts
server/src/__tests__/agent-permissions-service.test.ts
server/src/__tests__/company-portability.test.ts
server/src/__tests__/company-skills-service.test.ts
server/src/__tests__/teams-catalog-routes.test.ts
server/src/__tests__/teams-catalog-service.test.ts
server/src/__tests__/teams-catalog-install-no-overrides.test.ts
ui/src/lib/company-routes.test.ts ui/src/pages/TeamCard.test.tsx
ui/src/pages/TeamCatalog.test.tsx
ui/src/pages/useInstallTeamCatalogEntry.test.tsx`
- `pnpm --filter @paperclipai/shared typecheck && pnpm --filter
@paperclipai/teams-catalog typecheck && pnpm --filter paperclipai
typecheck && pnpm --filter @paperclipai/server typecheck && pnpm
--filter @paperclipai/ui typecheck`
- Confirmed branch is rebased onto `public-gh/master` (`78dc3625a`) and
`public-gh/master` is an ancestor of `HEAD`.
- Confirmed PR diff excludes `pnpm-lock.yaml`, `.github/workflows/*`,
generated screenshot images, and screenshot helper scripts.
## Risks
- Medium review surface: this crosses package generation, shared
contracts, server install behavior, CLI, docs, and hidden UI code.
- Catalog install behavior creates agents/projects/tasks/skills and must
keep company scoping, permissions, source policy, and provenance checks
strict.
- `pnpm-lock.yaml` is intentionally excluded per repo policy;
CI/default-branch automation owns lockfile refresh.
- The Team Catalog UI is included but hidden from primary navigation, so
future enablement should re-check visual QA before exposure.
> 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`.
>
> ROADMAP checked: this aligns with reusable companies/templates and
plugin-adjacent onboarding work. This PR packages work already developed
on the Paperclip task branch for review.
## Model Used
- OpenAI Codex, GPT-5 series coding agent in this Paperclip session;
exact runtime context window was not exposed. Used shell, git, `gh`, and
local test/typecheck tooling.
## 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, or documented why screenshots are intentionally omitted
- [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 4.8 <noreply@anthropic.com>
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies through
company-scoped control-plane workflows.
> - Agents need reusable, inspectable skills that can be installed,
reset, audited, exported, and assigned without bespoke local setup.
> - The existing skill truth model needed cleanup so bundled skills,
optional catalog skills, runtime skills, and adapter-provided skills
have clear provenance.
> - Operators also need a practical CLI and board UI for discovering and
managing company skills.
> - This pull request adds the skills CLI, packaged skills catalog,
company skills APIs, and catalog-aware board UI.
> - The benefit is a more reusable Paperclip company setup where skills
are portable, auditable, and easier for operators and agents to manage.
## What Changed
- Added `paperclipai skills` CLI commands and coverage for catalog
listing, installing, resetting, and inspecting company skills.
- Added a packaged `@paperclipai/skills-catalog` workspace with bundled
and optional skill content plus validation/build tests.
- Added shared company-skill types and validators used across CLI,
server, and UI contracts.
- Added server catalog APIs/services for company skill catalog
operations, reset semantics, audit behavior, and portability provenance.
- Updated adapter skill handling so runtime/catalog provenance remains
explicit across local adapters.
- Added board UI support for browsing and managing catalog-backed
company skills.
- Updated docs for the skills CLI/catalog flow and the company skills
Paperclip skill reference.
- Rebased the branch onto current `paperclipai/paperclip:master`; no
`pnpm-lock.yaml`, `.github/workflows`, or migration files are included
in the final PR diff.
## Verification
- Passed: `pnpm run preflight:workspace-links && pnpm exec vitest run
cli/src/__tests__/skills.test.ts
packages/skills-catalog/src/catalog-builder.test.ts
packages/skills-catalog/src/shipped-catalog.test.ts
packages/shared/src/validators/company-skill.test.ts
packages/adapter-utils/src/server-utils.test.ts
packages/plugins/create-paperclip-plugin/src/entrypoints.test.ts
server/src/__tests__/company-skills-catalog-service.test.ts
server/src/__tests__/company-skills-routes.test.ts
server/src/__tests__/company-portability.test.ts`.
- Passed: `pnpm exec vitest run
server/src/__tests__/workspace-runtime.test.ts -t "default
branch|origin/master|symbolic-ref"`.
- Attempted: full `server/src/__tests__/workspace-runtime.test.ts`. Four
provisioning tests failed while seeding an isolated worktree database
from the local Paperclip instance because the local plugin schema dump
contains a duplicate-column foreign key
(`plugin_content_machine_18a7bc327b.content_case_signals`). The
default-branch tests touched by the rebase conflict passed in the
focused run above.
- Checked final diff: no `pnpm-lock.yaml`, no `.github/workflows`, and
no migration-file changes relative to `master`.
## Risks
- Medium: this is a broad skills/catalog change touching CLI, server
APIs, shared contracts, adapter skill sync, and UI.
- Catalog validation and reset semantics need careful reviewer attention
because they affect reusable company setup and portability.
- No database migrations are included in this PR, so there is no
migration ordering/idempotency risk in the final diff.
- No lockfile is included by design; dependency resolution will be
handled by the repository lockfile workflow.
## Model Used
- OpenAI Codex coding agent based on GPT-5, running in Paperclip via the
`codex_local` adapter with shell, git, GitHub CLI, and code-editing tool
access. Exact hosted model build/context-window metadata is not exposed
in this runtime.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run targeted tests locally and documented the local
workspace-runtime seed failure above
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, screenshots were intentionally
omitted per PAP-10124 instructions; UI behavior is covered by tests and
reviewer inspection
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip keeps its core release process declarative through
`scripts/release-package-manifest.json`, which decides which packages CI
is allowed to publish.
> - The Modal sandbox provider now exists as a first-party plugin
package under `packages/plugins/sandbox-providers/modal`.
> - The original Modal PR intentionally left `publishFromCi` disabled
until the package had been published and the registry bootstrap concern
was cleared.
> - The latest reviewer comment confirms that bootstrap step is
complete, so the remaining gap is only release automation configuration.
> - This pull request flips the Modal manifest entry to `publishFromCi:
true` so future CI-driven releases can publish
`@paperclipai/plugin-modal` the same way the other releasable packages
do.
> - The benefit is that Modal releases no longer require a manual
exception in the release pipeline.
## What Changed
- Updated the `@paperclipai/plugin-modal` entry in
`scripts/release-package-manifest.json` to set `publishFromCi` to
`true`.
## Verification
- Ran `node -e 'const
m=require("./scripts/release-package-manifest.json"); const
e=m.find(x=>x.name==="@paperclipai/plugin-modal");
if(!e||e.publishFromCi!==true){throw new Error("modal publishFromCi not
true")}; console.log(JSON.stringify(e))'`
## Risks
- Low risk. This only changes release-manifest metadata; the main
failure mode is CI attempting to publish the Modal package before
registry credentials or release conditions are ready.
## Model Used
- OpenAI Codex local agent, GPT-5-based coding model in the Codex
runtime (exact deployment model ID not exposed in this workspace), with
tool use and shell 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 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
## Thinking Path
> - Paperclip orchestrates AI agents through company-scoped
control-plane workflows and extensible runtime integrations.
> - Sandbox providers are part of that extension surface because they
let agents execute isolated work without baking each provider into the
core server.
> - Modal already offers managed sandboxes with filesystem, process,
timeout, and networking controls that map onto Paperclip's sandbox
provider contract.
> - The repo did not have a Modal provider plugin, so teams wanting
Modal-backed sandboxes had no first-party integration path.
> - This pull request adds a standalone
`packages/plugins/sandbox-providers/modal` plugin that implements the
provider contract, worker entrypoint, docs, and tests.
> - The benefit is that Modal can now be installed as a provider plugin
without expanding the core control-plane surface area.
## What Changed
- Added a new `packages/plugins/sandbox-providers/modal` package with
the plugin manifest, worker entrypoint, and exported plugin surface.
- Implemented Modal-backed sandbox lifecycle support for creation,
command execution, file operations, networking options, termination, and
metadata translation.
- Added focused Vitest coverage for config validation, env handling,
lifecycle flows, networking behavior, and error mapping.
- Documented installation, configuration, and usage requirements in the
plugin README.
- Removed misleading `MODAL_TOKEN_*` fallback behavior so authentication
relies on supported Modal credentials only.
## Verification
- `pnpm -r typecheck`
- `pnpm test:run`
- `pnpm build`
- `cd packages/plugins/sandbox-providers/modal && pnpm test`
## Risks
- Low to medium risk: this is isolated to a new plugin package, but
runtime behavior still depends on live Modal account credentials and
service-side sandbox semantics.
- Modal's current docs target a newer Node baseline than the repo
default, so the first live install should confirm credential loading and
sandbox startup behavior in a real Modal workspace.
- No UI or schema changes are included in this PR.
> 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 (GPT-5-class Codex
coding model; exact backend model ID is not exposed by the runtime),
with tool use, shell execution, and code-editing capabilities enabled.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [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.
> - Operators need to inspect what agents changed inside execution and
project workspaces.
> - The existing workspace detail views did not provide a first-party
rich diff surface for staged, unstaged, head, renamed, binary,
oversized, and untracked changes.
> - The plugin system is the intended extension point for optional rich
UI surfaces.
> - This pull request adds a workspace diff plugin plus host services
and shared contracts so Changes tabs can render workspace diffs through
plugin slots.
> - The diff-renderer dependency should stay owned by the plugin package
rather than the core UI app.
> - The dependency surface must stay aligned with repository PR policy,
including intentionally omitting `pnpm-lock.yaml` from the PR.
> - The benefit is a more reviewable workspace surface without
hard-coding the renderer into every page.
## What Changed
- Added `@paperclipai/plugin-workspace-diff`, including diff
normalization, plugin manifest/worker/UI entrypoints, and focused plugin
tests.
- Kept `@pierre/diffs` scoped to `@paperclipai/plugin-workspace-diff`;
removed the core UI lab diff-renderer surface and direct UI package
dependency.
- Added shared workspace diff types and validators, plus plugin SDK
surface for workspace diff host services.
- Added server workspace diff service support and route coverage for
execution/project workspace diff flows.
- Wired Execution Workspace and Project Workspace Changes tabs to load
the diff plugin, including loading/error fallback behavior.
- Added UI tests and fixtures for the Changes tabs and plugin bridge
behavior.
- Added the new plugin package manifest to the Docker deps stage so PR
policy can validate dependency coverage.
- Addressed review hardening around empty untracked patches, workspace
path exposure, project workspace read capability checks, and default
base refs.
## Verification
- `pnpm --filter @paperclipai/plugin-workspace-diff test`
- `pnpm exec vitest run
packages/shared/src/validators/workspace-diff.test.ts
server/src/__tests__/workspace-diff-service.test.ts
ui/src/pages/ProjectWorkspaceDetail.test.tsx
ui/src/pages/ExecutionWorkspaceDetail.test.tsx`
- `pnpm exec vitest run ui/src/plugins/bridge.test.ts
server/src/__tests__/workspace-runtime-routes-authz.test.ts`
- `pnpm --filter @paperclipai/shared typecheck`
- `pnpm --filter @paperclipai/plugin-workspace-diff typecheck`
- `pnpm --filter @paperclipai/server typecheck`
- `pnpm --filter @paperclipai/ui typecheck`
- `node ./scripts/check-docker-deps-stage.mjs`
- Browser screenshot captured from the local worktree dev server:
https://files.catbox.moe/ofdpsp.png
- Confirmed branch is rebased onto `public-gh/master`,
`.github/workflows/pr.yml` is not included in the PR diff,
`ui/package.json` is not included in the PR diff, and `pnpm-lock.yaml`
is not included in the PR diff.
## Risks
- Medium UI integration risk: the Changes tab depends on the plugin slot
and host diff service path.
- Medium dependency risk: this adds `@pierre/diffs` in the plugin
package, but `pnpm-lock.yaml` is intentionally omitted per packaging
instructions because repository automation manages lockfile updates.
- Current CI blocker: downstream frozen installs fail until the
repository policy path for new plugin package dependencies is chosen.
- Diff rendering edge cases are covered for common working-tree and head
diff states, but very large repositories may still expose performance
limits.
- No 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 class coding model, tool-enabled local execution
environment. Exact 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
- [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 publishes its CLI, server, UI, and adapter packages
through the shared release workflow.
> - Canary releases are driven by the GitHub release workflow on pushes
to `master`.
> - The release workflow does not publish every public package
automatically; it uses `scripts/release-package-manifest.json` as the CI
enrollment source of truth.
> - The Grok adapter is public and already present in the manifest, but
its `publishFromCi` flag was still disabled.
> - Because of that flag, normal canary publishes skipped
`@paperclipai/adapter-grok-local` even when the main package received a
canary.
> - This pull request enables Grok in the release manifest so future
canary runs include it.
> - The benefit is that Grok adapter canaries stay aligned with the rest
of the package release set.
## What Changed
- Set `packages/adapters/grok-local` / `@paperclipai/adapter-grok-local`
to `publishFromCi: true` in `scripts/release-package-manifest.json`.
## Verification
- `node ./scripts/release-package-map.mjs check`
- `node ./scripts/release-package-map.mjs list | grep
'@paperclipai/adapter-grok-local'`
- `pnpm test:release-registry`
## Risks
- Low risk: this is a release manifest-only change.
- Future canary releases will attempt to publish
`@paperclipai/adapter-grok-local`; this assumes the package remains
publishable and trusted publishing/package access are correctly
configured for the existing npm package.
> 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 shell, git, and GitHub
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, 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, and its release flow depends on
explicit package enrollment for automated publishing.
> - The release registry tooling uses
`scripts/release-package-manifest.json` as the source of truth for which
public packages CI is allowed to publish.
> - The cursor cloud adapter plus the Cloudflare and exe.dev sandbox
plugins are public packages that now need to ship through the normal CI
release path.
> - Leaving those entries at `publishFromCi: false` keeps release
automation and registry validation out of sync with the intended package
set.
> - This pull request updates only those three manifest entries and
leaves the release tooling itself unchanged.
> - The benefit is that CI release enrollment now matches the packages
we intend to publish, with the existing manifest checks continuing to
guard correctness.
## What Changed
- Enabled CI publishing for `@paperclipai/adapter-cursor-cloud` in
`scripts/release-package-manifest.json`.
- Enabled CI publishing for `@paperclipai/plugin-cloudflare-sandbox` in
`scripts/release-package-manifest.json`.
- Enabled CI publishing for `@paperclipai/plugin-exe-dev` in
`scripts/release-package-manifest.json`.
## Verification
- `node ./scripts/release-package-map.mjs check`
- `pnpm test:release-registry`
## Risks
- Low risk. This is a manifest-only change, but a wrong enrollment flag
would affect release automation, so the release-registry checks are the
main guardrail.
## Model Used
- OpenAI GPT-5.4 via Paperclip `codex_local` (`adapterConfig.model:
gpt-5.4`), high reasoning effort, with tool use and shell/code
execution. The adapter does not expose a separate context-window value
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
> _Stacked on top of #5685 → #5686 → #5687. Diff against master includes
commits from earlier PRs in the stack — review focuses on the two new
commits (`Add long-secret textarea variant to JsonSchemaForm
SecretField` + `Add exe.dev sandbox provider plugin`)._
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Each agent runs in a sandbox environment, and operators choose the
provider — today E2B, Daytona, and (in this stack) Cloudflare
> - exe.dev offers per-VM sandboxes via a small CLI / HTTP API — useful
for operators who want full Linux VMs (vs container/runtime-only
sandboxes)
> - The plugin shape mirrors the e2b plugin: lifecycle hooks (`new`,
`ls`, `rm`) drive exe.dev's CLI; SSH plumbing handles direct VM access
for adapters that need it
> - exe.dev VMs come up bare — `node` is not preinstalled, so the
Paperclip sandbox callback bridge (a Node script) needs Node 20
installed at VM init via `--setup-script`. The plugin defaults the setup
script to a Nodesource install
> - The auth field accepts long SSH private keys, which need a textarea
variant of the existing `SecretField` in `JsonSchemaForm` — added behind
a `maxLength > THRESHOLD` opt-in so other secret fields are unaffected
> - The benefit is that operators get exe.dev as a fully working sandbox
provider out of the box, with no manual VM provisioning required
## What Changed
**Shared UI support (`Add long-secret textarea variant to JsonSchemaForm
SecretField`):**
- `ui/src/components/JsonSchemaForm.tsx` + new
`JsonSchemaForm.test.tsx`: when a secret-formatted field declares
`maxLength` larger than the existing single-line threshold, render a
monospace textarea instead of the masked input. Short secrets (API keys,
tokens) keep the existing masked-input + show/hide toggle behavior.
**The exe.dev plugin (`Add exe.dev sandbox provider plugin`):**
- `packages/plugins/sandbox-providers/exe-dev/`: plugin entry, manifest,
plugin runtime, README, and 19-test Vitest suite.
- Manifest fields: API token (with `secret-ref` + `/exec` permission
notes — needs `new`, `ls`, `rm`), API URL override, optional SSH
username, optional SSH private key (uses the new `JsonSchemaForm`
textarea variant via `maxLength: 4096`), optional SSH identity-file
path, optional setup script.
- Default `--setup-script` is a Nodesource Node 20 install. exe.dev VMs
come up bare and the Paperclip sandbox callback bridge is a Node script,
so without Node preinstalled the bridge can't start. Operators can
override by supplying their own setup script.
- `runLifecycleCommand` redacts env values from the executed command
before surfacing it in error messages, so secrets passed via
`--env=KEY=VALUE` don't leak into operator-visible failures.
- The plugin distinguishes exe.dev's SSH onboarding failures (`Please
complete registration by running: ssh exe.dev`) from general SSH
failures and surfaces a clear remediation message.
- `scripts/release-package-manifest.json`: register the new plugin for
CI publish alongside the existing daytona / e2b providers.
## Verification
- `pnpm typecheck`
- `pnpm exec vitest run --no-coverage
ui/src/components/JsonSchemaForm.test.tsx`
- `(cd packages/plugins/sandbox-providers/exe-dev && pnpm test)` — 19
passing
For an operator-side smoke test:
1. Get an exe.dev API token with `/exec` permission for `new`, `ls`,
`rm`.
2. Register the plugin in your Paperclip instance, configure an
environment with the token.
3. Create a sandbox env whose provider is `exe-dev`, then run a Codex or
Claude job against it. The default Node 20 setup script should bring the
VM up automatically.
## Risks
- Adds a new sandbox provider plugin that follows the existing daytona /
e2b shape; behavior on existing providers is unchanged.
- The `JsonSchemaForm` textarea variant only engages for fields that opt
in via `maxLength` larger than the existing threshold. All existing
secret fields (which don't declare a `maxLength`) keep their current
rendering. Test coverage pins both paths.
- The redaction in `runLifecycleCommand` is a defense-in-depth measure;
the test suite exercises the redaction path. If the redaction misses a
future env-arg shape, the worst case is restored behavior (secrets in
error messages), which is what the existing daytona / e2b plugins also
do today.
- Default setup script downloads from `deb.nodesource.com` over HTTPS at
VM init. Operators on air-gapped networks or with a different package
strategy can override the setup script.
## Model Used
- Provider: Anthropic
- Model: Claude Opus 4.7 (1M context)
- Capabilities used: extended reasoning, tool use (Read/Edit/Bash/Grep)
## 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 — UI change is a textarea variant of an existing secret
field; will attach screenshots before requesting merge
- [x] I have updated relevant documentation to reflect my changes
(plugin README, manifest descriptions)
- [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>
> _Stacked on top of #5685 → #5686. Diff against master includes commits
from earlier PRs in the stack — review focuses on the two new commits
(`Extend sandbox callback bridge for Worker-hosted plugins` + `Add
Cloudflare sandbox provider plugin`)._
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Each agent runs in a sandbox environment, and operators choose which
provider backs that sandbox — today E2B and Daytona are bundled with the
platform
> - Cloudflare Workers + Durable Objects + the Sandbox SDK offer a
credible new option: globally distributed, cheap idle, and
operator-deployable as a single Worker
> - To plug it in, Paperclip needs (a) a provider plugin that speaks the
`PaperclipPluginManifestV1` lifecycle and (b) a small operator-deployed
Worker — the **bridge** — that adapts Paperclip's runtime RPCs to the
Cloudflare Sandbox SDK
> - The plugin extends the existing sandbox-callback-bridge with a
`bridge.transport: "worker"` discriminator so the platform routes
runtime RPCs through the Worker bridge instead of the in-process runner
> - This pull request adds the plugin, the bridge Worker template, and
the supporting adapter-utils + server hooks the new transport needs
> - The benefit is that operators can run sandboxes on Cloudflare's edge
with no new platform code beyond installing the plugin and deploying the
Worker
## What Changed
**Shared support (`Extend sandbox callback bridge for Worker-hosted
plugins`):**
- `packages/adapter-utils/src/sandbox-callback-bridge.{ts,test.ts}`:
expose `expectedHostHeader` so plugin-side bridge clients can verify the
canonical request envelope before forwarding.
- `packages/adapter-utils/src/command-managed-runtime.{ts,test.ts}`:
relax the always-fresh runner construction so callers can re-use a
runner across exec calls (Worker-hosted bridges hold the runner inside a
Durable Object).
- `server/src/services/environment-runtime.ts` +
`environment-runtime.test.ts`: route Worker-hosted bridges through the
same env-shaping path as E2B and pin the `requestEnv` contract.
- `server/src/services/plugin-environment-driver.ts`: thread an optional
`issueId` through the runtime descriptor so bridges can scope leases to
the originating issue (used by Cloudflare to map a sandbox to the
issue/workflow for billing and audit).
- `packages/plugins/sdk/src/protocol.ts`: add `issueId?` to
`PluginEnvironmentDriverBaseParams` and the new `bridge.transport:
"worker"` discriminator that the new plugin declares.
- `server/__tests__/heartbeat-plugin-environment.test.ts`: pin the
heartbeat path against the new runtime descriptor.
**The Cloudflare plugin itself (`Add Cloudflare sandbox provider
plugin`):**
- `packages/plugins/sandbox-providers/cloudflare/`: plugin entry,
manifest, plugin runtime (lifecycle + bridge client), config parsing,
and Vitest coverage. Manifest declares `bridge.transport: "worker"` so
the platform routes runtime RPCs through the bridge client.
- `bridge-template/`: a Worker template the operator deploys with
`wrangler`. Owns Durable Object-backed sessions (`sessions.ts`),
exec/stream routes (`exec.ts`, `routes.ts`), and an HMAC auth layer
(`auth.ts`) that pins the `Host` header surface. Includes the
SDK-contract-correct exec implementation, lease recovery, and chunked
stdout/stderr streaming.
- Tests cover lease/session handoff (`bridge-template/src/exec.test.ts`,
`routes.test.ts`), bridge client request shaping
(`src/bridge-client.test.ts`), and end-to-end plugin behavior
(`src/plugin.test.ts`) including streamed exec output. 27 tests in
total.
- `README.md` walks the operator through deploying the bridge Worker,
registering the plugin, and configuring the runtime.
## Verification
- `pnpm typecheck`
- `pnpm exec vitest run --no-coverage
packages/adapter-utils/src/sandbox-callback-bridge.test.ts
packages/adapter-utils/src/command-managed-runtime.test.ts
server/src/__tests__/environment-runtime.test.ts
server/src/__tests__/heartbeat-plugin-environment.test.ts`
- `(cd packages/plugins/sandbox-providers/cloudflare && pnpm test)` — 27
passing
For an operator-side smoke test:
1. Deploy the bridge: `cd
packages/plugins/sandbox-providers/cloudflare/bridge-template &&
wrangler deploy`
2. Register the plugin in your Paperclip instance, point its bridge URL
at the deployed Worker, set the HMAC shared secret.
3. Create a sandbox environment whose provider is `cloudflare`, then run
a Codex or Claude job against it.
## Risks
- Adds a new `bridge.transport: "worker"` code path, but the existing
E2B / Daytona transports go through the same shaped helpers and have
explicit test coverage that pins their behavior unchanged.
- The Worker bridge stores session state in a Durable Object; operator
instances must be aware of the corresponding Cloudflare costs (DO
requests, storage). Documented in the README.
- The `issueId` plumbing is optional throughout — existing plugins that
don't supply it continue to work.
## Model Used
- Provider: Anthropic
- Model: Claude Opus 4.7 (1M context)
- Capabilities used: extended reasoning, tool use (Read/Edit/Bash/Grep)
## 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
(plugin README, bridge-template README)
- [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 for zero-human companies
> - The release pipeline gates new public packages behind a bootstrap
policy: `scripts/check-release-package-bootstrap.mjs` requires every
package marked `publishFromCi: true` in
`scripts/release-package-manifest.json` to already exist on npm
> - PR #5580 added the new Daytona sandbox provider plugin but had to
land with `publishFromCi: false` because the package had never been
published, so CI's release plan would have failed bootstrap validation
otherwise
> - Now that `@paperclipai/plugin-daytona` has been bootstrap-published
to npm by hand, the temporary `false` flag is the only thing keeping it
out of the standard CI publish flow
> - This pull request flips the Daytona entry to `publishFromCi: true`,
matching every other release-enabled package in the manifest
> - The benefit is that future tagged releases will publish the Daytona
plugin automatically alongside the rest of the monorepo's public
packages
## What Changed
- Single-line flip in `scripts/release-package-manifest.json`:
`@paperclipai/plugin-daytona` is now `publishFromCi: true`
## Verification
- `node ./scripts/release-package-map.mjs check` → `Release package
manifest OK: 19 enabled for CI publish, 0 disabled pending bootstrap`
(was 18 + 1)
- `node ./scripts/check-release-package-bootstrap.mjs
scripts/release-package-manifest.json` against `origin/master` →
`Release bootstrap OK for changed manifests:
@paperclipai/plugin-daytona`, confirming npm sees the
bootstrap-published package
- No code changes; no tests required beyond the existing manifest
validators
## Risks
- Low risk. Only effect is that the next release run will include
`@paperclipai/plugin-daytona` in its publish set
- If the npm bootstrap was incomplete, CI's bootstrap check will fail
loudly before any release tag goes out — same safety net the policy is
designed to provide
## Model Used
- Claude Opus 4.7 (`claude-opus-4-7`), extended thinking, tool use
enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [ ] I have added or updated tests where applicable (N/A —
manifest-only flag flip, covered by existing validators)
- [ ] If this change affects the UI, I have included before/after
screenshots (N/A — release config)
- [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
> - Agents need isolated sandbox environments to execute work safely;
Paperclip already supports E2B as a sandbox provider plugin
> - Users want to use Daytona (https://www.daytona.io/) as an
alternative sandbox backend, but no plugin existed for it
> - Without a Daytona plugin, teams that prefer Daytona's
pricing/regions/runtime can't run Paperclip agents on it
> - This pull request adds a `@paperclip/sandbox-provider-daytona`
plugin that mirrors the existing E2B plugin shape and wires up Daytona's
`@daytonaio/sdk` for sandbox lifecycle, command execution, and shell
detection
> - The benefit is that operators can pick Daytona as a first-class
sandbox provider without touching core code, broadening Paperclip's
runtime options
## What Changed
- New plugin package `packages/plugins/sandbox-providers/daytona` with
manifest, worker entry, and provider implementation backed by
`@daytonaio/sdk`
- Implements sandbox create/destroy/exec/upload/download lifecycle,
shell command detection, and config/env wiring consistent with the E2B
plugin
- Adds unit tests under `src/plugin.test.ts` and a README documenting
setup and the `DAYTONA_API_KEY` requirement
- Minor adjustments in `scripts/paperclip-issue-update.sh`,
`packages/shared/src/issue-thread-interactions.test.ts`, and
`packages/shared/src/validators/issue.ts` to support the integration
## Verification
- Re-ran the full sandbox provider matrix on the QA Paperclip instance
using Daytona as the runtime — all 6 adapters executed inside the
Daytona sandbox with zero `environmentExecute` timeouts
- 5/6 adapters pass cleanly (or with informational warns); the only
failure is `codex_local`, which is an OpenAI quota/billing issue
unrelated to Daytona
- `pnpm --filter @paperclip/sandbox-provider-daytona test` runs the
plugin unit tests
## Risks
- New optional plugin; no behavior change for users who don't enable it
- Requires `DAYTONA_API_KEY` for runtime use — documented in the plugin
README
- Daytona SDK is a new external dependency; tracked in the plugin's own
package.json so it doesn't affect the core install footprint
## Model Used
- Claude Opus 4.7 (`claude-opus-4-7`), extended thinking, tool use
enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots (N/A — backend plugin)
- [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 agent companies, so its
release automation is part of the core operator trust boundary.
> - The affected subsystem is npm/GitHub Actions release publishing for
the public monorepo packages.
> - The concrete failure was that a newly added package reached
`master`, the canary workflow attempted its first publish, and npm
trusted publishing was not yet bootstrapped for that package.
> - That means the problem is not just one broken run; it is a missing
pre-merge guard that lets release-ineligible packages land and only fail
once `publish_canary` runs.
> - This pull request makes release enrollment explicit, validates that
enrollment in CI, and adds a PR-time bootstrap check against npm for
changed release-enabled package manifests.
> - The result is that we keep trusted publishing, avoid teaching CI to
`npm adduser`, and move this class of failure from post-merge canary
time to pre-merge review time.
## What Changed
- Added `scripts/release-package-manifest.json` so release-managed
public packages are explicitly enrolled instead of being inferred from
every non-private workspace package.
- Hardened `scripts/release-package-map.mjs` to validate the manifest
before release workflows rewrite versions or assemble publish payloads.
- Added `scripts/check-release-package-bootstrap.mjs` and wired it into
`.github/workflows/pr.yml` so PRs that change a release-enabled package
manifest fail if that package does not already exist on npm.
- Added release-package manifest coverage tests to
`scripts/release-package-map.test.mjs` and included them in `pnpm run
test:release-registry`.
- Wired manifest validation into `.github/workflows/release.yml` and
documented the first-publish bootstrap policy in `doc/PUBLISHING.md` and
`doc/RELEASE-AUTOMATION-SETUP.md`.
## Verification
- `pnpm run test:release-registry`
- `./scripts/release.sh canary --skip-verify --dry-run`
- Confirmed the committed diff contains no obvious PII/secrets via
targeted pattern scan before pushing.
## Risks
- Low risk overall: this is CI/release-policy code, not product runtime
logic.
- The new PR bootstrap check depends on npm metadata availability, so a
transient npm outage could block a PR that changes a release-enabled
package manifest.
- The manifest introduces a new source of truth that must stay aligned
with public package additions, but that is intentional and now enforced.
## Model Used
- OpenAI Codex via the `codex_local` Paperclip adapter; GPT-5-based
coding agent with tool use, terminal execution, git, and GitHub CLI.
Exact served model ID/context window are not exposed by the local
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
David V
Dotta
Devin Foley
Alex
Jannes Stubbemann
