DottaandPaperclip
370fb50ad4
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents use remote MCP tools through a governed gateway. > - The gateway lists tools only while their shared connection is healthy. > - One failed call currently marks the whole connection as unhealthy. > - Later calls to healthy sibling tools then fail with `tool_not_found`. > - This pull request keeps non-authentication call failures on their invocation. > - Agents can continue their work while credential and access gates remain in force. ## Linked Issues or Issue Description Refs #10147. Related work: #15462 fixed oversized and malformed response handling. #15448 covers timeout and JSON-RPC health handling together with separate SSE and catalog discovery changes. Its patch still marks fetch failures and HTTP failures as connection errors. #15325 proposed a transport failure counter; it has merge conflicts and has not changed since October 6. #11910 is an older timeout fix with merge conflicts. This PR covers the remaining fetch and HTTP failure paths on current master, with the same narrow call-health rule for timeouts and JSON-RPC failures. It does not include the SSE or discovery changes from #15448. The timeout session-reset check follows the recovery case discussed in #15448. **What happened?** A shared remote MCP connection works until one call has a network failure, timeout, HTTP 503, or JSON-RPC error. Every later call on that connection returns `tool_not_found`, including healthy sibling tools. Connection setup then asks for user attention even though the failure did not prove that credentials need repair. **Expected behavior** The original invocation retains its failure. Authorized sibling tools remain callable. The gateway does not replay an ambiguous action. HTTP 401/403, missing credentials, and explicit insufficient scope keep their access gates. **Steps to reproduce** 1. Give an agent access to two read tools on one remote MCP connection. 2. Make one tool fail with a network error or HTTP 503. 3. Call the other tool in the same gateway session. 4. Before this fix, the second call fails with `tool_not_found` before provider dispatch. **Paperclip version or commit** `master` at `e6dcd1e8e9`. The regression runs against source with synthetic data. **Deployment mode** Any deployment that uses a shared remote MCP connection. This is a core gateway issue. ## What Changed - Preserve connection health after a network failure, timeout, non-authentication HTTP error, or JSON-RPC error from one tool call. - Retain HTTP 401/403 and insufficient-scope health gates. - Retain HTTP 401/403 gates during MCP initialization and its initialized notification, with HTTP 503 controls for both stages. - Discard only the upstream session used by a network failure or timeout. Let the next explicit call initialize again. - Add sibling-tool regression cases, authentication controls, and real HTTP header/body timeout checks. - Update runtime recovery guidance and the feature and access maps. ## Verification - Red: the four new sibling-tool cases failed on the original implementation. Each second call returned HTTP 404 with `tool_not_found`. HTTP 401/403 control cases passed. - Green: the same six-case selection passed after the production change: `pnpm --filter @paperclipai/server exec vitest run src/__tests__/tool-gateway-service.test.ts -t 'keeps sibling MCP tools usable|keeps the connection blocked' --maxWorkers=1`. - The regression checks the actual gateway and embedded PostgreSQL. The injected provider fault preserves the call boundary. It checks failure recording, no automatic replay, catalog retention, and successful sibling dispatch. - The real local HTTP fixture checks cancellation before headers and during a body, then a successful explicit call with a fresh MCP session. - `node scripts/check-maps.mjs` and `git diff --check` pass. - Complete nearby suites pass: 166 tests across `tool-gateway-service.test.ts`, `tool-gateway.test.ts`, `remote-mcp-protocol.test.ts`, and `mcp-http.test.ts`, with one test worker. - `pnpm --filter @paperclipai/server exec tsc --noEmit` passes after refreshing Runner TypeScript declarations. The first package typecheck used declarations from before the rebase and failed two unchanged native-session call sites; rebuilding that dependency resolved both errors. - The rebased head also passes all 11 selected sibling/authentication/session regressions. - Review regression red: setup-stage HTTP 401/403 controls failed because connection health stayed `ok`; the two setup-stage HTTP 503 controls passed. Green: all six setup controls and the complete 166-test nearby run pass. The fix separately handles typed initialization authentication failures and preserves the existing caller error. The server compiler also passes after this change. - Full repository CI passes on `256a65ccc302c1c31a80e87f1f91411d955028de`: typecheck, build, test shards, Runner checks, browser checks, Canary dry run, and aggregate gates. All checks are terminal: 55 successful, 2 expected skips, and the separate Paperclip Review check is neutral. Greptile is 5/5 on this exact head, with no open findings. - Full repository checks were run in CI. Local verification in this worktree used the focused suites and server compiler to keep parallel work bounded. - This change has no live provider or staging deployment proof. ## Risks - A provider that remains unavailable can stay listed until a health check detects the outage. Each call still fails with its original controlled reason code. - No automatic retry occurs because a failed remote action may already have run. - Already unhealthy connections still need a successful health check after an upgrade. - No schema, credential policy, or permission contract changes. ## Model Used - OpenAI Codex, GPT-6 family, with tool use and code execution. The runtime does not expose the exact serving model ID or context window. ## 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>
4.6 KiB
navigation
| navigation | ||||||
|---|---|---|---|---|---|---|
|
Tool gateways and access profiles
Administrators expose selected tools through gateways and reusable access profiles, connect clients, manage tokens, and inspect gateway activity.
Implementation: gateways, gateway detail, profiles.
Agent access: companion.
Sub-features
gateway: create/edit an endpoint backed by a tool access profile.profiles: define reusable tool access configuration and inspect draft/detail state.client-connect: copy the intended endpoint/configuration to an authorized test client.tokens: create/revoke client credentials and verify their scope.activity: inspect tool discovery/calls and explicit errors.
How to get to it (user POV)
gateway-client
Open /apps/gateways, then a gateway’s Overview, Apps/Tools, Tokens, and Activity tabs.
access-profile
Open /apps/advanced/profiles, create a profile, or follow its detail/edit route.
Driving it with Playwright and an MCP client
Preconditions: follow the baseline. Use a fixture tool connection and test client. Record gateway/profile, token owner, transport, and selected company.
Gateway creation selects a profile. Maintain that profile's app/action selection through the Apps/Tools links; the gateway form is not a separate tool picker. Use an active organization member for human-scoped access, and check the actual endpoint authorization independently of whether the admin UI is visible.
gateway-client
Automated: gateway service, connect client dialog, and token panel cover service/UI contracts.
Gateway regressions also cover a failed remote call followed by a successful sibling tool call. Transient failures preserve the catalog. Authentication failures retain their access gates. Real HTTP timeout fixtures verify an explicit retry starts a fresh MCP session without replaying the failed action. These checks do not establish a live provider journey.
Manual: Create a disposable gateway with one harmless tool, connect a client using its provided configuration, discover/call that tool, and inspect activity. Revoke the client token and confirm the same call fails. Test a tool outside the allowed set.
access-profile
Automated: profile wizard and profile detail cover component behavior with mocks.
Backend: profile entry validation uses isolated PostgreSQL to create and replace a 518-selector assignment with bounded reference reads. It checks exact selector retention, company boundaries, invalid input order, and fresh validation after deletion. This does not establish live client latency.
Manual: Create a bounded profile, choose its offered tools and options, save or resume its draft, and reload the detail. Apply/connect it through the offered flow and inspect the actual client-visible tool set. Verify cancellation and invalid selections retain an understandable draft.
Gotchas
- A copied endpoint is not proof of client authentication or tool discovery.
- Gateway access cannot replace underlying connection/action permission checks.
- Advanced tool routes require the appropriate admin gate; legacy tool URLs may redirect.
Storybook verification
tokens
Scope: ui Storybook: Mount current TokensPanel with issue controls, once-only token reveal, expiry/actions, revocation confirmation and failures. Old GatewaysTab fixtures and assistant OAuth revocation are insufficient. Production: Issue bounded token via POST /tool-gateway/gateways/{id}/tokens; call allowed and excluded tools; revoke via /tool-gateway/gateway-tokens/{id}/revoke and verify denial using same client. Sources: Source: TokensPanel.tsx, tool-gateway.ts, tools.ts. Tests: TokensPanel.test.tsx, tool-gateway-service.test.ts, tool-gateway.test.ts