d627632874
Docs for parent release `v2026.1106.0` (`d69631b0`), up from `v2026.1023.0` (`1b4c8038`): 515 parent commits. ## How this branch was built The tag is 914 commits behind what `nightly` has drafted, so this branch isn't cut from `nightly` HEAD. It starts at nightly commit `1952052` (parent `043f2514`), 19 commits before the tag, then adds: - the `main` hotfix (#160) - the sync tooling from `nightly` - docs for those 19 commits Later nightly drafts stay on `nightly`, so no pages had to be removed. No `nightly-draft/*` PRs are open. ## What changed - **Runner by default:** new Claude, Codex, OpenCode and Pi agents start on Paperclip Runner on supported hosts, with **Legacy runner** and **Upgrade runner**. - **Workspaces:** cleanup of finished workspaces, optional Git expiration, and restore points for unsaved work. Restore points are off by default. - **New pages:** Prompt injection prevention, Google Workspace, GitHub Copilot, Speko, Braintrust, Daytona, Ditto and Unikraft. - **Breaking and upgrade notes:** the run history limit, Sentry run failures off by default and the DSN variables, the Docker start command for custom images, `--yes` on `instructions-file:delete`, and slower migrations on large instances. - **Also covered:** project repositories as skill sources, roster bulk edit, Artifacts V1 (experimental, off by default), composer dismissal, `expectedStatusVersion`, `unexecuted_review_stage`, and plugin workspace providers. - **Changelog:** a v2026.1106.0 entry in `reference/changelog.md`. ## Older text corrected These were wrong at the tag, and most are also wrong on the live site: - which permissions let an agent read a peer's configuration or change instructions (`api/agents.md`) - `decideNowCount`, which doesn't exist; the field is `deskBadgeCount` - `file-resources` routes, which are board-only - the **Create project** dialog fields, a CEO rule the code doesn't enforce, and where a terminated agent's reports appear - `instructions-file:put` and `:delete` examples that always failed (`cli/agent.md`) - a curl example that returned `422` (`api/cases.md`) - Google Workspace **Reconnect** instructions, which claimed it reopens the service picker - the `permissionKey` table, which listed 8 of 21 keys - drafting text at the end of `api/agents.md` ## ⚠ Please check these - **Product behaviour that may be a parent bug.** The docs now describe the tag's code, which you may prefer to fix upstream: - The project **Environment** dropdown saves a choice, but runs ignore it (`experimental/environments.md`). - `environments:manage` is granted by roles but no environment route checks it. - `suggest-changes` is documented as agent-only, because only agents have a consent path. Company skill policy decides skill edits. - **Reader-visible mismatches in the parent UI.** The docs follow the code. Upstream copy still mentions a "Built-in agents tab", says Copilot "awaits qualification", and tells people to "Reconnect Google Workspace to change access". ## ⚠ Post-tag leaks removed Nothing to remove from an already-drafted page: post-tag surfaces such as 1Password, Vercel, Supabase deploy, custom gateway onboarding and Artifacts V1 as default never came onto this branch. Authors left out post-tag hunks of the next nightly draft, and the reasons are in the run notes. ## ⚠ Drift None. Zero findings at the tag, from a full parent snapshot. ## ⚠ Verification Failures The tag-accuracy gate reports one leak and nine review entries. None is a real failure: - **Leak:** `reference/cli/service.md`, `paperclipai payload and`. This is a false positive; it's prose from a real message at `cli/src/commands/service.ts:184`. - **Review, 8 new connector pages:** the gate can't confirm new pages. Reviewers confirmed each surface exists at the tag. - **Review, `local_tools`:** an example value from the tag's Runner README. Not provable from code, and kept deliberately: - `sandbox-providers.md` uses `sandbox.yaml`. The tag's README says `install.yaml`, which returned 404 when checked. The upstream fix is post-tag. - The Google Workspace row about older OAuth brokers rests on release notes and a design doc. The broker isn't in this repo. - External claims about provider behaviour (for example Braintrust, Daytona, Unikraft and Google scopes). ## ↻ Renames detected None. The rename helper wasn't run: the 19-commit delta adds no new adapter, skill, or plugin directories that it would check. ## Verification All checks read a checkout pinned to the tag. - **First round:** authors, a release-notes audit, an audit of corrections stranded on `nightly`, an audit of 321 lines the last realign dropped from `main` (about 130 checked directly in code), and six fresh verifiers. - **Second round:** seven new verifiers re-checked every changed area, tracing behaviour rather than matching labels, and fixed about 50 more defects. That volume means more may remain. - **Limits of that second round:** - Each verifier reported what it only string-matched. That includes parts of Artifacts V1, the **Upgrade runner** notice, Copilot run behaviour, and some Plugin SDK contract text. - The second-round fixes themselves weren't reviewed by a third round. - **Gates:** `docs:build`, `docs:test` and `sync:check` pass. - **Nothing was run against a live instance.** All of this comes from reading code. ## Screenshots **196 of 278 screenshots are stale and none were recaptured.** The list is in `SCREENSHOTS_PENDING.md`. Some visibly differ from the text, such as the removed **Run with provider trace** button and the old roster tabs. ## After merge 1. Keep the PR title as is: `tag-docs-release.yml` reads the version from it. 2. Confirm the `docs/v2026.1106.0` tag exists. 3. Run `node scripts/sync/realign-nightly.mjs release/v2026.1106.0 --push`, then audit for dropped lines and duplicated paragraphs, and set `nightly` state back to `branch_mode: nightly`. 4. Check that `docs.paperclip.ing` serves the release: a new page, a new claim, and the changelog's top entry. 🤖 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]>
5.6 KiB
paperclip_version, seo_title, seo_description
| paperclip_version | seo_title | seo_description |
|---|---|---|
| v2026.1106.0 | Check AI Account Usage and Limits | Read provider-reported allowances for Claude, OpenAI, Grok, and OpenRouter accounts, understand missing values, and repair sign-in from a task. |
Check AI account usage
Before giving an agent a long task, check the allowance on the account it will use. Paperclip shows what the provider reports when you ask; it does not estimate a subscription balance from your task costs.
Usage checks and AI connection setup do not require an experimental setting.
Check a saved account
- Open Connectors and the saved AI account.
- Find Usage and select Check usage.
- Read the returned limits and reset times. Select Refresh when you need another observation.
| Account | Supported check |
|---|---|
| Anthropic subscription | Provider-reported Claude usage windows and overage when available |
| OpenAI subscription | Provider-reported allowance windows, reset times, and overage when available |
| Grok subscription | Provider-reported subscription limits and overage when available |
| OpenRouter API key | Key credit limits, reset cadence, and free-model limits when available |
| Other API-key methods | Unavailable for this sign-in method. |
The check uses the stored connection you selected. It does not probe an ambient CLI login. Opening an account page does not trigger the check automatically.
Read the result
A limit may show a percentage, a used amount and cap, or a remaining allowance. Limit reached means the provider reports the limit is exhausted. Blocked means it explicitly reports usage is not allowed. Reset time or cadence appears when supplied.
Missing fields show Not reported, never zero. Grok may omit included-plan usage, and some Claude credentials can run models without permission to read usage. Usage access denied. does not mean your allowance is exhausted.
Overage describes the provider's extra-usage state. On · Availability unknown means enabling overage alone has not established a funded usable balance. The observation timestamp tells you when the response was read.
Checking usage does not refresh your credential, buy credit, change the account selected for a task, or stop an active run. It is a provider observation, separate from Paperclip budgets and per-run cost accounting.
See quota on the Costs page
The Providers tab on the Costs page also shows a Subscription quota section for Anthropic and OpenAI subscription accounts. It lists each connected subscription account you're allowed to use, under its own name, and reads it with that account's stored credential — not a CLI login on the machine running Paperclip. Unlike Check usage, it refreshes on its own every few minutes while you're on the Providers tab.
If a refresh fails briefly, the last good reading stays on screen. If the account needs to be connected or reconnected, the reading is cleared and the section asks you to reconnect it here in AI connections.
See what a subscription costs per month
Usage checks tell you how much allowance is left; they don't tell you what the plan costs. For that, use the Subscriptions tile at the top of the Costs page. It lists the monthly fee for each subscription account your agents use, counts a shared seat once, and lets you enter the real price when Paperclip can only estimate it — or can't tell at all.
Repair sign-in from a task
When a task cannot start because its AI credential is missing or expired, it shows an authentication connection card. Open that card and connect your account or reconnect the existing one. After the card finishes successfully, the task resumes automatically through normal admission.
Only the account owner can reconnect it. If the task uses someone else's account, the card explains who must restore it. If that account is no longer available to you, ask its owner to restore access or choose another available connection in the agent's settings.
A reconnect retains the existing account's audience, agent access, and default selection. It does not broaden sharing. In agent settings, Reconnect account repairs your unavailable personal default; Connect an account… lets you establish another account.
Troubleshooting
| Message | What to do |
|---|---|
| Sign in again to check usage. | Reconnect the stored account. |
| Usage access denied. | The provider denied usage-read access for this credential. Check usage at the provider if necessary. |
| Too many checks. Try again later. | Wait before another usage check. This does not consume your model allowance. |
| Reconnect to check usage. | Restore the connection before checking again. |
| Provider unavailable. Try again. | Retry later; the provider did not supply a usable response. |
| Couldn’t read usage. Try again. | The response could not be read. Missing data is not treated as zero. |
API equivalent
Board-authenticated users with company access can request the same observation:
GET /api/companies/{companyId}/ai-connections/{connectionId}/usage
Pass ?grantId={grantId} when the connection has multiple eligible credential grants. The response includes checkedAt, status, provider-reported limits and overage, and an errorCode when unavailable. You can only read a credential you are allowed to use.