Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-04-03 06:17:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

🔁 fix: Pass recursionLimit to OpenAI-Compatible Agents API Endpoint (#12510)

Browse source 
* fix: pass recursionLimit to processStream in OpenAI-compatible agents API

The OpenAI-compatible endpoint never passed recursionLimit to LangGraph's
processStream(), silently capping all API-based agent calls at the default
25 steps. Mirror the 3-step cascade already used by the UI path (client.js):
yaml config default → per-agent DB override → max cap.

* refactor: extract resolveRecursionLimit into shared utility

Extract the 3-step recursion limit cascade into a shared
resolveRecursionLimit() function in @librechat/api. Both openai.js and
client.js now call this single source of truth.

Also fixes falsy-guard edge cases where recursion_limit=0 or
maxRecursionLimit=0 would silently misbehave, by using explicit
typeof + positive checks.

Includes unit tests covering all cascade branches and edge cases.

* refactor: use resolveRecursionLimit in openai.js and client.js

Replace duplicated cascade logic in both controllers with the shared
resolveRecursionLimit() utility from @librechat/api.

In openai.js: hoist agentsEConfig to avoid double property walk,
remove displaced comment, add integration test assertions.

In client.js: remove inline cascade that was overriding config
after initial assignment.

* fix: hoist processStream mock for test accessibility

The processStream mock was created inline inside mockResolvedValue,
making it inaccessible via createRun.mock.results (which returns
the Promise, not the resolved value). Hoist it to a module-level
variable so tests can assert on it directly.

* test: improve test isolation and boundary coverage

Use mockReturnValueOnce instead of mockReturnValue to prevent mock
leaking across test boundaries. Add boundary tests for downward
agent override and exact-match maxRecursionLimit.
This commit is contained in:
Danny Avila 2026-04-01 21:13:07 -04:00 • committed by GitHub
parent aa575b274b
commit cb41ba14b2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 134 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

9
api/server/controllers/agents/openai.js
View file

@ -15,6 +15,7 @@ const {
createErrorResponse,
recordCollectedUsage,
getTransactionsConfig,
resolveRecursionLimit,
createToolExecuteHandler,
buildNonStreamingResponse,
createOpenAIStreamTracker,
@ -194,10 +195,8 @@ const OpenAIChatCompletionController = async (req, res) => {
const conversationId = request.conversation_id ?? nanoid();
const parentMessageId = request.parent_message_id ?? null;
// Build allowed providers set
const allowedProviders = new Set(
appConfig?.endpoints?.[EModelEndpoint.agents]?.allowedProviders,
);
const agentsEConfig = appConfig?.endpoints?.[EModelEndpoint.agents];
const allowedProviders = new Set(agentsEConfig?.allowedProviders);
// Create tool loader
const loadTools = createToolLoader(abortController.signal);
@ -491,7 +490,6 @@ const OpenAIChatCompletionController = async (req, res) => {
throw new Error('Failed to create agent run');
}
// Process the stream
const config = {
runName: 'AgentRun',
configurable: {
@ -504,6 +502,7 @@ const OpenAIChatCompletionController = async (req, res) => {
},
...(userMCPAuthMap != null && { userMCPAuthMap }),
},
recursionLimit: resolveRecursionLimit(agentsEConfig, agent),
signal: abortController.signal,
streamMode: 'values',
version: 'v2',