Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-03-16 20:56:35 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

🛂 fix: Enforce Actions Capability Gate Across All Event-Driven Tool Loading Paths (#12252)

Browse source 
* fix: gate action tools by actions capability in all code paths

Extract resolveAgentCapabilities helper to eliminate 3x-duplicated
capability resolution. Apply early action-tool filtering in both
loadToolDefinitionsWrapper and loadAgentTools non-definitions path.
Gate loadActionToolsForExecution in loadToolsForExecution behind an
actionsEnabled parameter with a cache-based fallback. Replace the
late capability guard in loadAgentTools with a hasActionTools check
to avoid unnecessary loadActionSets DB calls and duplicate warnings.

* fix: thread actionsEnabled through InitializedAgent type

Add actionsEnabled to the loadTools callback return type,
InitializedAgent, and the initializeAgent destructuring/return
so callers can forward the resolved value to loadToolsForExecution
without redundant getEndpointsConfig cache lookups.

* fix: pass actionsEnabled from callers to loadToolsForExecution

Thread actionsEnabled through the agentToolContexts map in
initialize.js (primary and handoff agents) and through
primaryConfig in the openai.js and responses.js controllers,
avoiding per-tool-call capability re-resolution on the hot path.

* test: add regression tests for action capability gating

Test the real exported functions (resolveAgentCapabilities,
loadAgentTools, loadToolsForExecution) with mocked dependencies
instead of shadow re-implementations. Covers definition filtering,
execution gating, actionsEnabled param forwarding, and fallback
capability resolution.

* test: use Constants.EPHEMERAL_AGENT_ID in ephemeral fallback test

Replaces a string guess with the canonical constant to avoid
fragility if the ephemeral detection heuristic changes.

* fix: populate agentToolContexts for addedConvo parallel agents

After processAddedConvo returns, backfill agentToolContexts for
any agents in agentConfigs not already present, so ON_TOOL_EXECUTE
for added-convo agents receives actionsEnabled instead of falling
back to a per-call cache lookup.
This commit is contained in:
Danny Avila 2026-03-15 23:01:36 -04:00 • committed by GitHub
parent a26eeea592
commit 6f87b49df8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 372 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

16
api/server/services/Endpoints/agents/initialize.js
View file

@ -128,6 +128,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
toolRegistry: ctx.toolRegistry,
userMCPAuthMap: ctx.userMCPAuthMap,
tool_resources: ctx.tool_resources,
actionsEnabled: ctx.actionsEnabled,
});
logger.debug(`[ON_TOOL_EXECUTE] loaded ${result.loadedTools?.length ?? 0} tools`);
@ -214,6 +215,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
toolRegistry: primaryConfig.toolRegistry,
userMCPAuthMap: primaryConfig.userMCPAuthMap,
tool_resources: primaryConfig.tool_resources,
actionsEnabled: primaryConfig.actionsEnabled,
});
const agent_ids = primaryConfig.agent_ids;
@ -297,6 +299,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
toolRegistry: config.toolRegistry,
userMCPAuthMap: config.userMCPAuthMap,
tool_resources: config.tool_resources,
actionsEnabled: config.actionsEnabled,
});
agentConfigs.set(agentId, config);
@ -370,6 +373,19 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
userMCPAuthMap = updatedMCPAuthMap;
}
for (const [agentId, config] of agentConfigs) {
if (agentToolContexts.has(agentId)) {
continue;
}
agentToolContexts.set(agentId, {
agent: config,
toolRegistry: config.toolRegistry,
userMCPAuthMap: config.userMCPAuthMap,
tool_resources: config.tool_resources,
actionsEnabled: config.actionsEnabled,
});
}
// Ensure edges is an array when we have multiple agents (multi-agent mode)
// MultiAgentGraph.categorizeEdges requires edges to be iterable
if (agentConfigs.size > 0 && !edges) {