Commit Graph
3 Commits
Author SHA1 Message Date
DottaandPaperclip c67909cb0f fix: keep tool approvals valid through OAuth refresh and delayed review (#20340)
## Thinking Path

> - Paperclip lets people manage agent work and approve app actions.
> - An approval must bind the action that the person reviewed.
> - OAuth access tokens can expire while that person is away.
> - The old target snapshot treated each token refresh as a new
authorization. It also imposed a one-hour review deadline.
> - This pull request separates token renewal from authorization
identity and keeps the human decision durable.
> - Current access, the reviewed arguments, meaningful target changes,
task closure, and execution receipts still control dispatch.
> - People can approve later without repeating a decision after routine
connection maintenance.

## Linked Issues or Issue Description

**What happened?**

A pending app action returned `approved_tool_target_changed` after its
OAuth tokens refreshed. The tool and connection settings were unchanged.
The same card also expired after one hour. A sign-in problem could
discard an accepted decision before provider dispatch.

**Expected behavior**

The original card remains reviewable after routine OAuth refresh and a
server restart. A later approval runs the exact reviewed action once. A
connection repair preserves the decision while Paperclip verifies the
same authorization. Meaningful changes require a new review.

**Steps to reproduce**

1. Connect an OAuth MCP app and configure an action to require approval.
2. Request the action, then refresh its access and refresh tokens before
approving.
3. Approve the original card. Before this change, it returns HTTP 409
even when the authorization is unchanged.
4. Wait more than one hour. Before this change, the card expires without
a task-specific deadline.

**Paperclip version or commit**

Reproduced from master at `76254ead2229`. The final branch is rebased
onto current master.

## What Changed

- Add versioned approval target comparison. New snapshots bind
credential identity epochs, consent, permissions, ownership, connection
configuration, tool contracts, and credential references. Authenticated
OAuth refresh preserves identity. Manual credential replacement does
not.
- Remove the implicit one-hour deadline from ordinary app action
reviews. Keep explicit deadlines and terminal-task expiry. Synchronize
the nullable interaction deadline in shared contracts and UI.
- Keep accepted, undispatched actions when sign-in is required. Show a
saved-approval repair state. Resume on committed connection changes
after target and access revalidation, without an idle retry loop.
- Preserve the existing execution claim, result receipt, and
uncertain-outcome no-replay rules.
- Explain meaningful target changes without inviting the person to retry
the stale card.
- Add a production task-thread Storybook example and document
compatibility and recovery behavior.

## Verification

- Red: production-refresher invalid-grant handling and formal-approval
withdrawal during a sign-in wait also reproduced as failing regressions
before their fixes.
- Red: before implementation, the local OAuth HTTP fixture failed for
both public and confidential clients with `approved_tool_target_changed`
after token refresh.
- Green: the extended fixture passes for public and confidential clients
with personal and shared grants. It covers actual local HTTP token
exchanges, multiple refreshes, a rebuilt gateway, an ended originating
run, approval after 25 hours, duplicate approval, preserved sharing
arguments, sign-in waiting, and event-driven repair. The gateways use
the production OAuth refresher; an invalid refresh preserves the
accepted decision before provider dispatch. Omitted-scope responses
cover equivalent scope-reporting changes. The provider is an isolated
local fixture, not a deployed Notebook service.
- Negative controls refuse changed consent, scopes, tool definition,
destination, and manual credential replacement before provider
execution.
- Existing gateway service, connected-tool acceptance, secret owner,
secret service, unsigned-review queue, and connection-health suites
passed. Explicit-deadline fixtures still prove expiry behavior,
including deadlines on accepted sign-in waits. A withdrawn formal
approval cancels a waiting action before connection recovery.
- Approval card, task-chat, error-copy and target-comparison tests
passed. Server and UI typechecks passed. Token gates and Storybook
catalog checks passed.
- Inspected the new saved-approval repair card in local Storybook using
the production task thread. It shows a reconnect link and no second
approval button or false running state.
- `pnpm verify --explain` returned exit 2 and requested broad CI
coverage. [Full
CI](https://github.com/paperclipai/paperclip/actions/runs/42677855507)
passed on `eb4f1c7caa9ee6e802c314ffc5eadec475a5de0c`, including build,
typecheck/release registry, general and serialized tests, and all eight
browser shards.
- Greptile reviewed the same final head at 5/5. Both findings from the
first review are fixed and their threads resolved; no open follow-ups
remain.

## Risks

- No database migration is needed. The new comparison reuses the vault
identity epoch. Only authenticated OAuth refresh code can preserve that
epoch; HTTP credential-write schemas cannot select that behavior.
- Earlier signed requests keep their original exact-version checks and
saved deadlines. Already-expired cards are not revived. A historical
card whose credentials already changed needs a fresh review.
- A new consent, account, permission set, destination, or manually
replaced credential must not inherit the old authorization. Reconnection
continues automatically only when revalidation proves the same saved
authorization.
- The interaction enrichment now permits a null deadline. Existing
string deadlines remain valid. The web client and shared validator
change together.
- This PR does not deploy to staging or perform a live Notebook
publication.

## Model Used

OpenAI Codex, GPT-6 family, with repository tools, code execution, and
browser inspection. The runtime does not expose the exact model ID,
context-window limit, or reasoning-mode label; those values are not
asserted.

## 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>
2026-11-09 13:46:28 -06:00
DottaandPaperclip f187de99aa Preserve domain deadlines across owned idle sleep (#18656)
Reviewed and verified at 9b4acc456d.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-11-03 15:40:56 -06:00
DottaandPaperclip ad55d0a281 fix(connections): repair personal credentials and request write access (#14739)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agents use Apps through a gateway that checks identity, company
access, and action policies.
> - Personal pasted credentials can point to company secrets. Setup can
show success while the gateway rejects every call.
> - Several OAuth methods also omit the scopes needed for their
supported write actions.
> - This pull request gives setup, health checks, and invocation the
same credential rules. Owners repair existing connections by
reconnecting.
> - New connections request reviewed permissions for their supported
actions. Read-only choices remain available under Advanced.
> - Agents can use the connections people give them, while existing
consent, identity boundaries, and action restrictions remain enforced.

## Linked Issues or Issue Description

Refs #14009 and #14008. This addresses the personal-credential defect.
The separate GitHub organization-identity selection defect is outside
this change.

Related work: #13942 fixed part of new personal-key setup. #14200
independently fixes legacy personal reconnect and protects managed-agent
profile credentials during removal. This PR covers that ownership
invariant across key and secret-URL setup, reconnect, health, discovery,
and invocation, and keeps owner reconnect as the repair path. #14059
tracks requested versus provider-asserted OAuth scopes; it remains
separate work. I searched open PRs and issues for Zapier, Airtable
scopes, connector writes, and personal credential failures.

**What happened?**

A Zapier secret URL saved through personal setup can become a company
secret referenced by a user grant. Health checks bypass the gateway's
ownership check, so the connection appears healthy but calls fail with
`grant_credential_invalid`. Custom-header paths can also receive a
duplicate `credentials.` prefix. Omitted OAuth scopes make write access
depend on provider defaults.

**Expected behavior**

Personal invocation credentials belong to the selected user. Setup,
health, and actual calls enforce the same rule. New connections request
documented permissions for supported read and write actions. Existing
tokens gain no permissions without provider consent.

**Steps to reproduce**

1. Connect Zapier or a generic secret URL with the personal identity.
2. Allow an agent to use the connection and complete setup.
3. Invoke a tool through a run-scoped gateway. The legacy layout fails
ownership validation despite successful setup.

**Paperclip version or commit**

The implementation started from
`44736c9c7c67b7b646ead9d51721db10f5b83835` and was rebased onto master
at `94e8dec56`.

**Deployment mode**

Built from source. Regression tests use isolated PostgreSQL fixtures and
controlled MCP transports.

## What Changed

- Share credential writing, ownership validation, and canonical paths
across initial setup, resume, reconnect, rotation, health, discovery,
and gateway calls. Keep OAuth client-registration secrets separate from
invocation credentials.
- Existing personal connections with company-scoped credentials require
owner reconnect with a fresh key or secret URL. Reconnect creates a
correctly owned value and updates the existing grant and declarations.
There is no automatic ownership backfill or new startup hook.
- Preserve PostgreSQL timestamp precision when reconnect checks whether
a grant changed. Previously, converting the timestamp to a JavaScript
Date could reject reconnect with a false concurrent-change error.
- Protect credentials used by other grants, connections, bindings,
managed-agent profiles, routine triggers, or secret proposals from
connection removal.
- Review all 117 tool methods, including 84 OAuth methods. Record
explicit scopes or documented provider-default exceptions with official
evidence. Add Airtable's seven scopes, Hugging Face repository/job
scopes, and other documented MCP permissions.
- Prefer available write-capable methods. Put explicit read-only choices
under Advanced. Explain pasted-key permissions and offer reconnect for
missing OAuth consent. Preserve existing grants, policies, Google
availability gates, and curated scope allowlists.
- Reconnect generic secret URLs and custom headers using their stored
credential fields. Refresh the catalog after setup, correct reconnect
feedback and error guidance, and let Cancel exit invalid setup while
Save & exit retains draft-saving behavior.
- Apply ownership checks to the new GitHub repository/skill connection
picker. Align the permission audit with the Google scope reductions
merged on master.
- Add run-scoped gateway, ownership, owner-reconnect, OAuth URL,
insufficient-scope, UI, and catalog-wide regression coverage. Update the
connector playbook and permission audit.

## Verification

Latest commit `97bc0b86e0eae0ec892e4ac44beff1a66164b20e` passes all
CI/status gates (55 completed check runs, no failures or pending checks)
and has a completed Greptile review at **5/5 with no outstanding
findings**. GitHub reports the PR as mergeable/CLEAN.

- **Embedded browser:** used the actual server and built UI from this
worktree, a fresh isolated database, and local HTTP MCP fixtures.
Completed personal bearer-key, secret-URL, and custom-header setup;
reproduced the legacy ownership failure; reconnected through the owner’s
form; and completed writes afterward. Read-back was verified for
bearer-key and secret-URL connections. Public organization-wide setup
appeared immediately in Browse without reload. Zapier URL
validation/Cancel and Google’s enrollment gate were also exercised.
- **Persistence and invocation:** verified user ownership, canonical
`credentials.authorization` / `remote.url` / `headers.X-Api-Key`
declarations, and unchanged connection/grant identity. The old company
secrets retain their ownership. Separate HTTP calls through an actual
run-scoped gateway session completed a write and read-back.
- **Backend coverage:** the final gateway suite passes all 82 cases,
including catalog Zapier and generic inline reconnect. It checks
company/user isolation, canonical declarations, same-endpoint URL
validation, fresh credentials, retained restrictions, and real gateway
read/write execution using fixture transport. A timestamp with
PostgreSQL microseconds covers the former false reconnect conflict.
- **Local checks:** 368 catalog, gateway, repository, and UI tests
passed before the final extra Zapier case; 49 GitHub skill access tests
also passed. All three Apps browser regressions pass, including
reconnect through the actual form and catalog visibility without reload.
Full `pnpm -r typecheck`, `pnpm build`, server typecheck after the final
patch, and token gates passed. Full tool-access service runs hit varying
15-second Google fixture timeouts; both affected cases and the updated
reconnect assertion pass in isolation (3 tests). The complete test
matrix passes in CI on this head.
- **Verification limits:** no live provider account was available for
Zapier/Airtable/OAuth consent or account-bound write proof. Public
metadata and local fixtures do not establish provider consent. The
original development database clone failed on a pre-existing missing
`tool_connections_transport_check` constraint; browser acceptance used a
fresh isolated database created by the normal CLI onboarding flow.

## Risks

- Existing broken personal connections stay unusable until their owner
reconnects. Health, discovery, and invocation return an actionable
ownership error; startup does not rewrite credential ownership.
- Scope changes affect new authorization requests. Providers may still
require resource selection, account roles, paid plans, or app
verification. Existing consent and action restrictions remain unchanged.
- Shared credentials are retained rather than reassigned or revoked.
Provider-default exceptions and unavailable live checks are documented
in `doc/connections/CONNECTOR-PERMISSION-AUDIT.md`.
- No new endpoint, database table, lockfile change, or CI workflow
change is included.

## Model Used

OpenAI Codex, based on GPT-6, with reasoning, code editing, shell
execution, web research, and browser tools. The exact deployment model
ID and context window were not exposed in this 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 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>
2026-09-30 14:32:34 -05:00