What specific problem does this solve?

Currently, a Roo Code mode can be configured to use a single API Configuration Profile. If the selected API provider for that profile experiences an outage or a connection failure, any task in that mode halts and requires manual user intervention to switch to a different API profile. This disrupts the workflow and reduces the tool's resilience, especially during long-running automated tasks.

Additional context (optional)

No response

Roo Code Task Links (Optional)

No response

Request checklist

• I've searched existing Issues and Discussions for duplicates
• This describes a specific problem with clear impact and context

Interested in implementing this?

• Yes, I'd like to help implement this feature

Implementation requirements

• I understand this needs approval before implementation begins

How should this be solved? (REQUIRED if contributing, optional otherwise)

I would like to be able to configure a prioritized list of API Configuration Profiles for each mode. If the primary (first) profile in the list fails to get a response, Roo Code should automatically and sequentially try the next profile in the list until it succeeds.

For example, for the "Code" mode, I'd like to configure the following fallback chain:

1. Primary: Anthropic (Claude 4 Sonnet)

2. Secondary: OpenAI (GPT-5)

3. Tertiary: Ollama (Local qwen3 models)

If a request using the Anthropic profile fails, Roo Code should automatically retry the same request with the OpenAI profile without requiring me to manually change the settings. If that also fails, it should then try the local Ollama model.

How will we know it works? (Acceptance Criteria - REQUIRED if contributing, optional otherwise)

No response

Technical considerations (REQUIRED if contributing, optional otherwise)

No response

Trade-offs and risks (REQUIRED if contributing, optional otherwise)

No response