mirror of
https://github.com/LibreChat-AI/librechat.ai.git
synced 2026-03-27 10:48:32 +07:00
df2fa1bd4b
* 📝 feat: Update agent capabilities to include 'artifacts' and 'chain' * 📝 feat: Add Agent Chain capability and Advanced Settings documentation * 📝 feat: Add maxRecursionLimit option to agents configuration and update documentation * 📝 feat: Update agents configuration with maxRecursionLimit and enhance capabilities documentation * feat: Update Agent Chain documentation to include beta status and maximum agent limit
18 lines
1.5 KiB
Plaintext
18 lines
1.5 KiB
Plaintext
- Added `maxRecursionLimit` to [Agents Endpoint](/docs/configuration/librechat_yaml/object_structure/agents#maxrecursionlimit)
|
|
- Sets the absolute maximum number of steps an agent can take in a run
|
|
- Defines the upper limit for `recursionLimit` that can be set from the UI
|
|
- If omitted, defaults to the value of `recursionLimit` or 25 if `recursionLimit` is also omitted
|
|
- For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps)
|
|
- Updated `recursionLimit` in [Agents Endpoint](/docs/configuration/librechat_yaml/object_structure/agents#recursionlimit)
|
|
- Now represents the default number of steps an agent can take in a run
|
|
- This value can be configured from the UI up to the `maxRecursionLimit` (if one is provided)
|
|
- For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps)
|
|
- Added `artifacts` to [Agent Capabilities](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
|
|
- Enables agents to generate and display interactive content, such as React components, HTML code, and Mermaid diagrams
|
|
- For more information, see [Artifacts](/docs/features/artifacts)
|
|
- Added `chain` to [Agent Capabilities](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
|
|
- Enables a Mixture-of-Agents (MoA) approach for complex tasks
|
|
- Allows creation of chains of specialized agents that work together
|
|
- Each agent in the chain can access outputs from previous agents
|
|
- For more information, see [Agent Chain](/docs/features/agents#agent-chain)
|