fix: classifier shouldn't select custom agents

[nndn]

Summary by CodeRabbit

• New Features
  • Enhanced the agent selection process by filtering to exclusively consider system-level agents during query classification. This targeted adjustment directs queries to the most appropriate agents, potentially improving overall performance and consistency.
  • The core functionality remains stable while benefiting from a more precise routing approach.

[coderabbitai]

Walkthrough

The changes modify the SimplifiedAgentSupervisor in the conversation service by introducing a filtering mechanism. The new logic creates a filtered list of agents (only those with a "SYSTEM" status) and uses this list to build agent_descriptions for query classification. The overall control flow and error handling remain unchanged, with only comments updated to reflect the new filtering behavior.

Changes

File(s)	Summary of Changes
app/modules/…/conversation_service.py	Added a list comprehension in SimplifiedAgentSupervisor to filter self.available_agents for agents with "SYSTEM" status. Updated comments accordingly.

Sequence Diagram(s)

sequenceDiagram
    participant S as SimplifiedAgentSupervisor
    participant A as Available Agents
    participant F as System Agent Filter
    participant D as Agent Descriptions

    S ->> A: Retrieve available agents
    S ->> F: Filter agents (status == "SYSTEM")
    F -->> S: Return system_agents
    S ->> D: Build agent_descriptions from system_agents
    Note right of S: Classification now uses only system agents

Loading

Possibly related PRs

• Route directly to custom agents #227: Adjustments in available_agents handling and modifications to the classifier_node method create a direct relationship with the changes in filtering system agents in this PR.

Poem

I’m a rabbit, full of cheer,
Hopping through code without a fear,
Filtering agents with a clever trick 🐇,
Only system ones, now that’s slick!
Bugs hop away as clarity sticks.
CodeRabbit bounds ahead – oh so dear!

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between c7dc272 and c415165.

📒 Files selected for processing (1)

• app/modules/conversations/conversation/conversation_service.py (1 hunks)

🔇 Additional comments (3)

app/modules/conversations/conversation/conversation_service.py (3)

134-137: LGTM! Clear and effective filtering of system agents.

The list comprehension effectively filters out non-system agents, which aligns with the PR objective.

---

138-140: LGTM! Consistent use of filtered system agents.

The agent descriptions are now correctly built using only the filtered system agents.

---

158-175:

✅ Verification successful

Verify error handling for custom agent initialization.

The direct routing for custom agents looks good. However, let's verify that error handling for custom agent initialization is comprehensive.

Run this script to check for potential error handling improvements:

---

🏁 Script executed:

#!/bin/bash
# Description: Check error handling patterns in custom agent initialization

# Search for custom agent initialization patterns
ast-grep --pattern 'try {
  $$$
  agent = $$.get_agent($_, $_)
  $$$
} catch (Exception as $_) {
  $$$
}'

# Search for error logging patterns
rg -A 5 'Failed to create agent'

Length of output: 1448

---

Custom agent error handling verified is robust.

The error logging and response behavior for custom agent initialization checks out. The code consistently logs errors (e.g., "Failed to create agent ...") and returns a proper error Command when the initialization fails. No further changes are needed in this segment.

✨ Finishing Touches

• 📝 Generate Docstrings (Beta)

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud