Investigate API errors

[snopoke]

Review the LLM provider API errors that generate 400 response code and create tickets for the issues that are found which could be avoided through code changes or pipeline validation:

https://dimagi.sentry.io/issues/?environment=production&project=4505001320316928&query=BadRequestError&referrer=issue-list&statsPeriod=90d

E.g.:

Error code: 400 - {'error': {'message': "The following tools cannot be used with reasoning.effort 'minimal': file_search.", 'type': 'invalid_request_error', 'param': 'tools', 'code': None}}

Take-away: gpt-5 does not support 'file-search' when reasoning effort is 'minimal'.

We could add validation to handle this.

[coderabbitai]

📝 CodeRabbit Plan Mode

Generate an implementation plan and prompts that you can use with your favorite coding agent.

• Create Plan

Examples

• Example 1
• Example 2

🔗 Similar Issues

Possible Duplicates

• ISSUE-1799

Related Issues

• Validate file extensions for remote indexed collections #1799
• [Tool Functionality Update] Large SQL Query Outputs Causing Errors in ESPEN Gen AI Assistant #2428
• restrict image types being uploaded from chat widget #2339
• Remove previous tool call results from messages #2205
• KeyError: 'field' #2529

👤 Suggested Assignees

• sentry-io
• sentry
• jsingh0397

---

🧪 Issue enrichment is currently in early access.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false