## Summary Release docs for Paperclip **v2026.1005.0** (parent tag commit `467125fa`). - **Window:** `v2026.1001.0` → `v2026.1005.0`, 179 commits, 1,645 files, compare truncation 0. - **Branch:** cut from `nightly` (`c42305a`). Nightly had drafted against parent master up to `a6306ba6`, which is 159 commits past the tag. - **Review:** every changed page was checked by hand against a checkout of the tag. **Headline doc changes:** - **New pages:** - [Browser Use Cloud](docs/connectors/browser-use-cloud.md) - [Memory connectors](docs/connectors/memory-connectors.md), plus Cognee, Honcho, Supermemory and Zep - [Agent Chat](docs/experimental/agent-chat.md) - [Paperclip Runner](docs/reference/adapters/paperclip-runner.md) - **Breaking changes applied:** - @-mentions no longer start a run (#14577). Ten pages that still said they did are fixed. - Keyboard shortcuts are always on, and `/api/auth/preferences` is gone. - Connector setup is one screen (#14811). - Agent files that persist across tasks, a GitHub skill **Sources** tab, aggregators on by default, two-way Slack, Grok Build on the Runner, refreshed model catalogs, and the new env vars, including `PAPERCLIP_RUNNER_API_TOOLS_ENABLED` / `_COMPANY_IDS`. - A changelog entry, and 113 pages stamped `paperclip_version: v2026.1005.0`. ### ⚠ Post-tag leaks removed These document parent `master` features that are **not in v2026.1005.0**. They stay on `nightly` for the next release. - **Pages removed entirely (9):** - `connectors/ai-usage.md` (7d59de61) - `connectors/custom-model-providers.md` (9f7057e1) - `connectors/connection-instructions.md` (4857799a) - `administration/agent-commentary.md` (b508a05c) - `experimental/assistant-connections.md`, `reference/api/assistant-mcp.md` and `reference/cli/mcp.md` (e34abee6, 22a3ea34, 2d0c1381) - `guides/org/agent-identity.md` (a590ab76) - `reference/cli/runtime.md` (a6306ba6) - **Reverted to `main`:** - `agentmail.md` (6c1a75da) - `openrouter.md`; only the released access-line change was re-applied - `asana.md` (4ac37410); only the released access-line change was re-applied - `delegation.md` and `team-catalog.md` (862a5758, b17019e1) - `adapters/overview.md` (a6306ba6) - `api/tool-gateway.md`, the GET → 405 change - **Sections trimmed (~50 pages):** - AgentMail as a default connection - **Check usage** - aggregator account sync and grouping (b43073d1) - MCP `offline_access` (839cac13) and readable test results (6d654f63) - saved connection guidance - the **Update skill** tool (eb049aeb) and managed-checkout import roots (427e0484) - low-trust scoped work and owner-chat edits (0829d94a, 4039d4f0) - reduced default instructions (b17019e1) - Chat leading the nav and the combined inbox (1c07b590) - steer/interrupt recovery (cc67d4e1) - branch artifacts without a remote (db72ad4c) - Cursor on the Runner (a6306ba6) - Claude/Codex model ordering (92ad158c, d9b64ee2) - Daytona stalled-log polling (4e524632) - the agent identity env vars - the shared task composer for new tasks (2c43b391) ### ⚠ Drift Checked against the tag. **No real drift remains:** - **Env vars that exist at the tag but are read through helpers the checker doesn't scan (false positives):** - `PAPERCLIP_WORKSPACE_GIT_SCAN_*` - `PAPERCLIP_WORKSPACE_GIT_SNAPSHOT_TIMEOUT_MS` - `PAPERCLIP_RUNNER_API_COMPANY_CAPTURE_MAX_BYTES` - `PAPERCLIP_CLOUD_CONNECTOR_*` - `PAPERCLIP_ID_CONNECTOR_*` are documented as **retired**, which is correct. - Verify: `/api/companies/{companyId}/chats/{agentRef}` is registered dynamically (`router[method]`, `issues.ts:17185`). False positive. - Verify: `/api/agent-avatars/...png` and `/api/companies/import/transfers*` are known false positives from constant or param registration. ### ⚠ Verification Failures / review notes - **Asana:** `asana.md` keeps "register your own Asana OAuth app". The tag's `asana.json` advertises "Sign in with Asana" (DCR), but Asana's v2 MCP server needs a registered app, and sign-in only works after post-tag #14756. Confirm you're happy with that wording. - **Google Docs/Sheets/Slides/Calendar:** the "Reconnect after the scope change" paragraph isn't confirmed in code. - **`grok-local.md`:** "Intel Mac rejected" and "subscription sign-in, no automatic fallback" are only partly confirmed. - **`paperclip-runner.md`:** "Grok cannot automatically approve Paperclip tool calls under narrower ACP modes" isn't confirmed directly. - **`cognee.md`:** the tag's setup text says `uv` is required, which contradicts `tool-access.ts:3560`. The page follows the code. - **`work-modes.md`:** the per-reply mode chip was removed because it couldn't be found at the tag. - **`browser-use-cloud.md`:** the `frame-src` CSP advice is general advice, not code-backed. ### Screenshots **180 of 350 screenshots are stale**, across 41 routes (see `SCREENSHOTS_PENDING.md`). None were recaptured in this PR; refresh separately with `npm run screenshots:refresh`. ### Other open PRs - **#143** (Browser Use Cloud + Neon, targets `main`): Browser Use Cloud is covered here, and Neon is post-tag (5b8b2b38). Suggest closing it or retargeting it to `nightly`. ## Checks - `docs:build` passes. - `sync:check` passes, with no broken internal links. - `docs:test` passes in full: SEO metadata, crawlable links (275 routes), doc link resolution (2,198 checks), static routes, asset fingerprints, skills nav, and skill source blocks. ## After merge (Phase 9) - [ ] `docs/v2026.1005.0` tag is created by the workflow (keep the PR title as is). - [ ] `node scripts/sync/realign-nightly.mjs release/v2026.1005.0 --push`. The nine removed pages stay on `nightly`. - [ ] Flip `nightly`'s `.sync-state.json` back to `branch_mode: nightly`. - [ ] docs.paperclip.ing serves the release: the changelog's top entry reads v2026.1005.0, and `/connectors/browser-use-cloud/` returns 200. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.8 (1M context) <[email protected]> Co-authored-by: DevRel Gemini <[email protected]> Co-authored-by: Paperclip <[email protected]> Co-authored-by: Dotta <[email protected]> Co-authored-by: ClaudeCoder <[email protected]>
5.3 KiB
paperclip_version, seo_title, seo_description
| paperclip_version | seo_title | seo_description |
|---|---|---|
| v2026.1005.0 | PagerDuty Connector | Let agents read PagerDuty incidents, services, and schedules. Choosing the right service region, token scope, a safe read test, and troubleshooting. |
PagerDuty
Agents can work with PagerDuty incidents, services, schedules, and on-call information — useful for letting an agent summarize an incident or check who is on call.
Choose your region first
PagerDuty hosts accounts in separate service regions, and they are different endpoints with no cross-region access. Pick the one that hosts your account:
| Option | Use it when |
|---|---|
| US service region | The PagerDuty account is hosted in the US |
| EU service region | The PagerDuty account is hosted in the EU |
Choosing the wrong region is the most common setup failure, and it does not look like a region problem: authentication simply fails, or the account appears empty. If you are unsure, check the domain you use to sign in to PagerDuty.
Before you connect
- A PagerDuty account, and a user API token from it.
- Confirmation of which region hosts the account.
The token carries that user's permissions. If an agent should only read, issue the token from an account whose role is read-only — that is a stronger boundary than action settings alone.
Connect PagerDuty
- Open Connectors and select PagerDuty.
- Read the access line above the main button. It says who the connection signs in as and which agents can use it. To pick a different identity, narrow the agents, or use another sign-in method, select Change.
- Check the service region. To switch between US service region and EU service region, select Change.
- Paste the PagerDuty API key. Paperclip stores it as a secret.
Which PagerDuty token to create
Paperclip's field asks for a user API token, not a general REST API key. The two are different credentials in PagerDuty:
- A user API token acts as one person, and inherits that user's own PagerDuty role and team access. Create one under your PagerDuty user settings.
- A general REST API key is account-wide and is not what this field expects.
Because a user token inherits its user's permissions, the account you create it under is the access decision. A token made by a user with read-only PagerDuty permissions gives an agent read-only PagerDuty access, which is the cleanest way to bound this connector. Creating it under an account with broad permissions hands those to the agent.
PagerDuty's own reference is the PagerDuty MCP server documentation.
Choose access
Reach is the token's: the services, teams, and incidents the issuing user can see, subject to PagerDuty's own roles and team membership. There is no service or team picker in Paperclip.
Incident operations are consequential in a way that is easy to underestimate. Acknowledging or resolving an incident changes who gets paged and stops escalation — during a real outage that has immediate human consequences.
Warning: Keep incident mutations — acknowledge, resolve, reassign, and anything that creates or triggers an incident — on Ask first or Off. An agent resolving an incident it did not understand silently ends an escalation.
Reads are safe to leave Allowed. See Set action permissions.
Try it
Show me the most recent PagerDuty incident and tell me its status, service, and who it is assigned to. Do not acknowledge or resolve anything.
Compare against PagerDuty. Reading an existing incident confirms the token, the region, and the agent's permission without paging anyone or interfering with an escalation.
Do not verify by creating a test incident — that pages whoever is on call.
Note: Illustrative task, not a recorded test result.
Troubleshooting and limitations
| Problem | Likely cause | Fix |
|---|---|---|
| Authentication fails with a token you believe is valid | Often the wrong service region; also possible that a general REST API key was used instead of a user API token | Confirm the token is a user API token, then try the other region |
| It connects but no incidents or services appear | Wrong region, or the token's user has no team access | Sign in to PagerDuty as that user and check they can see the incidents themselves. If they can, try the other region |
| Some services are invisible | PagerDuty team membership and role restrict the token's user | Adjust the user's teams or role in PagerDuty |
| A write action is refused | The token's user role is read-only | Expected if you configured it that way |
| An incident was resolved unexpectedly | A mutation was set to Allowed | Re-open it in PagerDuty and tighten the action settings |
| Needs attention | The token was revoked | Issue a new token and reconnect |
Limitations: one account and one region per connection. No service or team filter inside Paperclip. PagerDuty's API rate limits apply.
Related guides
-
Sentry — error tracking, often used alongside incident response.