optimize user_goal_agent,next_action_agent#1386
Conversation
Qodo reviews are paused for this user.Troubleshooting steps vary by plan Learn more → On a Teams plan? Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center? |
|
reviewed |
There was a problem hiding this comment.
Pull request overview
Updates the routing reasoner prompt and function schema metadata to better align next_action_agent selection with the active user_goal_agent, improving agent routing consistency in BotSharp’s core agent infrastructure.
Changes:
- Refines the
reasoner.naive.liquidrouting instructions to prioritize continuity ofuser_goal_agentandnext_action_agentunless a new task starts. - Updates
route_to_agent.jsonparameter descriptions to reflect routing based on latest message + active goal.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| src/Infrastructure/BotSharp.Core/data/agents/01fcc3e5-9af7-49e6-ad7a-a760bd12dc4a/templates/reasoner.naive.liquid | Adjusts prompt guidance for inferring/retaining next_action_agent and user_goal_agent. |
| src/Infrastructure/BotSharp.Core/data/agents/01fcc3e5-9af7-49e6-ad7a-a760bd12dc4a/functions/route_to_agent.json | Clarifies schema descriptions for routing parameters (latest response + active goal). |
Comments suppressed due to low confidence (1)
src/Infrastructure/BotSharp.Core/data/agents/01fcc3e5-9af7-49e6-ad7a-a760bd12dc4a/templates/reasoner.naive.liquid:13
- Similar to the next-action guidance above, using snake_case variable names in the prose here can make the instruction less clear and may leak identifiers into the model output. Consider rewriting in natural language for consistency.
user_goal_agent is inferred from the user's active goal.
Keep the existing user_goal_agent unless the latest user message explicitly starts a different task or workflow.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
No description provided.