Per-task model configuration

### Problem Statement

I'm currently optimizing code review costs by selecting the cheaper model.

However, sometimes a lack of intelligence in the model can lead to higher token consumption or lower accuracy.

So I'm currently considering using different models for each sequence. Like the most recent [DoorDash research](https://careersatdoordash.com/blog/how-we-learned-to-trust-our-ai-code-reviewer-at-doordash/) splits the process into a scout agent and a deep review agent.

### Proposed Solution

Since OpenCodeReview has separate agents for each task, I think it can provide a configuration that allows selecting different models for them. For example, different models can be used for `PLAN_TASK` and `MAIN_TASK`, and a cheaper alternative model can be selected for `MEMORY_COMPRESSION_TASK`.

### Alternatives Considered

_No response_

### Affected Area

Configuration

### Additional Context

_No response_

Start by locating the configuration handling and the agent task definitions for PLAN_TASK, MAIN_TASK, and MEMORY_COMPRESSION_TASK. Trace how models are currently selected, then define task-specific configuration and verify that each task uses its configured model, including the cheaper compression option.

Written by the indexing model from the issue text.