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

6.0 KiB

Raw Blame History

paperclip_version, seo_title, seo_description

paperclip_version	seo_title	seo_description
v2026.1106.0	Enterpret Connector	Let agents ask Enterpret about customer feedback and pull cited quotes. Connect with an org auth token or sign-in, and keep graph queries on Ask first.

Enterpret

You can let agents ask questions about your customer feedback in Enterpret — themes, sentiment, and verbatim quotes with citations back to the original records. It is useful when a task needs the customer's own words, not a guess about what customers think.

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

The connection uses Enterpret's official read-only MCP server. Enterpret runs a separate Agent MCP service that can make changes; this connector does not reach it.

Before you connect

Pick one of two ways in:

An organization auth token (recommended). Generate it in Enterpret under Settings → Enterpret MCP. One token belongs to one Enterpret organization, and the connection is shared by the people and agents you choose.
Your own Enterpret account, for browser sign-in. Each person connects separately, and Enterpret attributes their queries to them individually. The account needs access to your organization's feedback.

Customer feedback often contains names, accounts, and other personal details. Decide up front which agents should see it.

Connect Enterpret

Open Connectors and select Enterpret.
Read the access line above the main button. It says who the connection signs in as and which agents can use it. Select Change to narrow the agents or to switch the method.
Pick how to connect:
- Use an auth token — paste the token into the Your Enterpret key field. This is the default method.
- Sign in with Enterpret — complete browser sign-in. Paperclip registers its client automatically, so there is nothing to set up in a developer console. This method connects your own account only.
Finish setup and open Permissions to check the action list.

Paperclip stores the token as a secret and sends it to Enterpret on each call. Agents never see it.

Choose access

Almost every Enterpret action reads, and those start as Allowed. One does not:

run_graph_query starts as Ask first. It runs a graph query written by the agent. Enterpret labels it read-only, but Paperclip has not established that, so it treats the action as a write and asks a person before each call. Leave it there unless you are comfortable approving open-ended queries in bulk.

Two more things are worth knowing:

New actions are held for review. If Enterpret adds actions later, a Refresh actions puts them in front of you instead of switching them on. See What happens to a brand-new action.
Quotes land in task transcripts. Answers can include verbatim customer text with speaker attribution. Prefer Just agents I pick for a token connection, and keep the agent list short.

Try it

Start with a question you can check against Enterpret yourself:

Using Enterpret, tell me which organization this connection belongs to, then list the top three feedback themes from the last 30 days with one cited quote each.

Open the cited records in Enterpret and confirm the quotes match.

Note: Illustrative task, not a recorded test result.

Token expiry and sign-out

An auth token has an expiry date. Check it in Enterpret under Settings → Enterpret MCP and replace the token before it lapses: create a new one, then reconnect with it. See Reauthorize, revoke, or disconnect.

For browser sign-in, revoking access in Enterpret may not take effect straight away — Enterpret can keep treating the token as valid for up to 24 hours. To stop Paperclip's access immediately, disconnect the connection in Paperclip.

Troubleshooting and limitations

Problem	Likely cause	Fix
The token is rejected	It expired, was revoked, or was copied incompletely	Generate a new token under Settings → Enterpret MCP and reconnect
Answers come from the wrong organization	The token belongs to a different Enterpret organization	Reconnect with a token from the right organization
An agent is waiting on `run_graph_query`	It is on Ask first by default	Approve or decline the request — see Answer a connector review request
Sign-in shows more scopes than expected	Enterpret has reported broader scopes, including `mcp:write` and `email`, than Paperclip requests	Paperclip asks only for `mcp:read`; Enterpret is correcting the report. It does not grant this connector write actions
A new action does not appear as allowed	Actions Enterpret adds later are held for review	Select Refresh actions and review the new entries
Needs attention	The token expired or the sign-in was revoked	Select Reconnect

Limitations: one Enterpret organization per token connection. Browser sign-in is personal only; it cannot be shared as an organization connection.

PostHog and Mixpanel — product analytics connectors.
How connector access works
Set action permissions
Verify a connector and fix a broken one
Enterpret MCP server documentation

Sources

Enterpret definition — methods, labels, credential field, scopes, and warnings.
App defaults and tool connection service — Ask-first default for run_graph_query and held-back new actions.

6.0 KiB Raw Blame History