[Story]: Extend Muxing to Differentiate Between Chat and FIM Requests

[aponcedeleonch]

Description

We currently support routing logic based on filenames, and now we need to extend that functionality to differentiate between chat requests and Fill-In-Middle (FIM) requests.

Example

• A chat that references app.py → Model 1
• A FIM request within app.py → Model 2

Implementation Outline

• Extend the existing muxing rules to include a check for request type (chat or FIM).
• Allow users to configure which model should handle chat requests vs. FIM for specific filenames.

Additional Context

No response

[aponcedeleonch]

Closed by the tickets mentioned above