paperclipai/paperclip-docs

0 Fork 0

mirror of https://github.com/paperclipai/paperclip-docs.git synced 2026-11-07 06:16:07 -10:00

Files

T

d627632874 Release docs for paperclip v2026.1106.0 (#172 )

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]>

2026-11-07 13:02:42 +01:00

5.0 KiB

Raw Blame History

paperclip_version, seo_title, seo_description

paperclip_version	seo_title	seo_description
v2026.1106.0	Telem.AI Web Search Connector	Give agents web search and page reading across many search providers with one Telem.AI API key. Optional routing, tier, and provider include lists.

Telem.AI

Agents can search the web and read pages through Telem.AI — useful when a task needs current information from outside your company. Telem.AI sends each search to many search providers behind one API key, so you do not have to sign up for each one.

Telem.AI appears in the catalog on every instance; no experimental setting is needed.

Before you connect

A Telem API key. Create one in the Telem console at app.telem.ai. Keys start with tlm_.

There is no browser sign-in and no free profile; the key is the only way in. Usage is billed to the Telem account that owns the key.

Connect Telem.AI

Open Connectors and select Telem.AI.
Read the access line above the main button. It says who the connection belongs to and which agents can use it. Select Change to narrow the agents or to reach the optional settings below.
Paste the key into the Your Telem.AI key field and select Connect.

Paperclip stores the key as a secret and sends it to Telem.AI on each call; agents never see it.

Optional settings

You can leave all of these empty. Whatever you choose applies to every agent using this connection.

Setting	Choices	What it does
Auto routing	Off, Accuracy	Accuracy lets Telem pick the search providers for each query. Off, or no selection, keeps auto routing off.
Tier	Minimalist, Default, Extended, Max	How much search work Telem does per query. No selection uses Default.
Providers to include	Comma-separated provider names	Telem searches only these providers. Leave it empty to allow all.
Providers to exclude	Comma-separated provider names	Telem skips these providers.

Once you pick a value from a list, you cannot clear it back to empty. To turn auto routing off again, choose Off.

Choose access

This connector reads from the public web; it does not reach into your own data. That makes it one of the lower-stakes connectors to share, and its actions start as Allowed.

Three things are still worth deciding:

Who pays. Every agent with access draws on the same Telem account. A higher tier means more search work per query. If one busy agent runs up usage, give it its own connection with a separate key.
What Telem sees. Paperclip tells Telem which company, project, task, agent, and run each search came from, so you can trace usage on the Telem side. Search terms themselves go to the search providers, so keep private details out of queries.
What agents do with results. Search results are outside content. An agent should treat them as information to check, not instructions to follow. See Set action permissions for keeping follow-on actions in other connectors behind Ask first.

Try it

Search the web with Telem.AI for the latest release notes of a tool we use, and summarise the top three results with their links.

Open the links the agent returns. A search with sources you can check confirms the connection and the agent's permission.

Note: Illustrative task, not a recorded test result.

Troubleshooting and limitations

Problem	Likely cause	Fix
The key is rejected	The key was revoked or copied incompletely	Create a new key at app.telem.ai and reconnect
A provider name is refused	The list contains spaces or other characters	Use comma-separated names with letters, numbers, `.`, `_`, or `-` only
Results never come from a provider you expected	It is excluded, or missing from Providers to include	Check both lists under Change
Usage is higher than expected	A high Tier, or many agents sharing one key	Lower the tier or split the connection
Needs attention	The key was revoked	Select Reconnect with a valid key

Limitations: one Telem account per connection. The available actions are whatever Telem.AI's hosted server exposes.

You.com — another web search connector, with a keyless free profile.
How connector access works
Set action permissions
Telem.AI documentation

Sources

Telem.AI definition — method, credential field, and optional settings.
Connection setup — where optional settings appear and how list choices behave.
Tool connection service — context forwarded to Telem.AI with each call.

5.0 KiB Raw Blame History