mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-01-24 19:26:14 +01:00
🧑🏫 fix: Multi-Agent Instructions Handling (#11484)
* 🧑🏫 fix: Multi-Agent Instructions Handling
* Refactored AgentClient to streamline the process of building messages by applying shared run context and agent-specific instructions.
* Introduced new utility functions in context.ts for extracting MCP server names, fetching MCP instructions, and building combined agent instructions.
* Updated the Agent type to make instructions optional, allowing for more flexible agent configurations.
* Improved the handling of context application to agents, ensuring that all relevant information is correctly integrated before execution.
* chore: Update EphemeralAgent Type in Context
* Enhanced the context.ts file by importing the TEphemeralAgent type from librechat-data-provider.
* Updated the applyContextToAgent function to use TEphemeralAgent for the ephemeralAgent parameter, improving type safety and clarity in agent context handling.
* ci: Update Agent Instructions in Tests for Clarity
* Revised test assertions in AgentClient to clarify the source of agent instructions, ensuring they are explicitly referenced as coming from agent configuration rather than build options.
* Updated comments in tests to enhance understanding of the expected behavior regarding base agent instructions and their handling in various scenarios.
* ci: Unit Tests for Agent Context Utilities
* Introduced comprehensive unit tests for agent context utilities, including functions for extracting MCP servers, fetching MCP instructions, and building agent instructions.
* Enhanced test coverage to ensure correct behavior across various scenarios, including handling of empty tools, mixed tool types, and error cases.
* Improved type definitions for AgentWithTools to clarify the structure and requirements for agent context operations.
This commit is contained in:
parent
7204e74390
commit
cfd5c793a9
6 changed files with 758 additions and 86 deletions
|
|
@ -217,7 +217,7 @@ export type Agent = {
|
|||
description: string | null;
|
||||
created_at: number;
|
||||
avatar: AgentAvatar | null;
|
||||
instructions: string | null;
|
||||
instructions?: string | null;
|
||||
additional_instructions?: string | null;
|
||||
tools?: string[];
|
||||
projectIds?: string[];
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue