mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-11-16 13:00:55 +00:00
|
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Backend Unit Tests / backend (push) Blocked by required conditions
Codegraph E2E Vote Gate / Gate (push) Waiting to run
Codegraph E2E Votes / vote (shard 1/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 10/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 2/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 3/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 4/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 5/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 6/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 7/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 8/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 9/10) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Playwright E2E Tests / Codegraph select (push) Waiting to run
Playwright E2E Tests / e2e () (push) Blocked by required conditions
Playwright E2E Tests / MCP list_changed (replica count 1) (push) Blocked by required conditions
Playwright E2E Tests / MCP list_changed (replica count 2) (push) Blocked by required conditions
Playwright E2E Tests / MCP Apps (browser and server) (push) Waiting to run
Playwright E2E Tests / e2e (push) Blocked by required conditions
* 🚪 fix: Refuse Interactive MCP Sign-in on Remote Agent API Runs A run started through the remote agent API (API key or OIDC bearer) has no signed-in browser reading its response. When one of the agent's MCP servers needed OAuth, the run still published LibreChat's sign-in prompt into the OpenAI-compatible response and waited up to two minutes for a sign-in the caller could not complete. The remote auth middleware now marks the response it admits. The prompt emitters refuse to write to a marked response, and tool loading skips the turn-start wait when no reader exists. Background Responses keep their prompts: those go to the generation stream the owner follows in LibreChat. * 🧭 refactor: Pass the Unattended Fact Explicitly and Release Unattended Callers From Shared Sign-in Review feedback on the first commit: - The response registry coupled the auth middleware to MCP through module state. The remote controllers now supply `unattended` as an argument (chat completions always; Responses through the runtime's tool context, foreground only) and it is passed through tool loading to the manager and the prompt transports. The registry and the middleware side effect are gone. - A remote run that reached a server while its owner had a sign-in open in a browser joined that recovery and waited for the person. The manager now guards an unattended caller at its two entry points: the first sign-in prompt, from the caller's own flow or from a recovery it waits on, ends that caller's wait with a typed error and leaves a shared recovery running for its other waiters. A recovery announces a sign-in request so waiters that registered no prompt handler are released too. * 🧪 test: Cover Unattended Sign-in Through the Real MCP SDK The shared-sign-in tests replaced the production OAuth handler with a synthetic listener, so they did not exercise the SDK lifecycle whose cancellation and shared-recovery behaviour the change depends on. They now run against the real Streamable HTTP test server, the real connection factory handler and the real flow manager: an unattended tool call alone, alongside the owner's open sign-in, joining a recovery that then stops being silent, recovering through a silent refresh, and opening a connection that needs sign-in. The synthetic-handler versions are removed. |
||
|---|---|---|
| .. | ||
| credentials.js | ||
| credentials.spec.js | ||
| mcp.js | ||
| mcp.spec.js | ||
| search.js | ||
| search.spec.js | ||