feat: implement Unified Model Selection Configuration

[Leoyzen]

Unified Model Selection Configuration

Summary

This PR implements unified model selection support across AgentPool's protocol servers. Users can now define custom model variants in their manifest configuration, which will be exposed through both OpenCode and ACP server endpoints.

What's New

Shared Model Utilities (src/agentpool_server/shared/)

• New shared module for model-related helper functions
• extract_provider(): Extract provider names from any model configuration type (OpenAI, Anthropic, Gemini, etc.)
• build_providers_from_tokonomics(): Convert tokonomics discovery results into server-compatible provider objects
• apply_configured_variants(): Merge user-defined model variants with auto-discovered models

OpenCode Server Updates (opencode_server/routes/config_routes.py)

• Implements intelligent fallback hierarchy for model discovery:
  1. User-defined model_variants from manifest (preferred)
  2. Dynamic discovery via tokonomics
  3. Agent-specific modes (Codex/Claude thought levels)
  4. Empty list with warning (last resort)
• Removed hardcoded dummy provider fallback
• Configured variants take precedence over discovered models with identical IDs

ACP Server Updates (acp_server/acp_agent.py)

• get_session_model_state(): Now includes configured variants in session state responses
• set_session_model(): Validates model IDs against both tokonomics discovery and configured variants
• User-defined variants override auto-discovered models with matching IDs

Example Configuration

agents:
  my_agent:
    type: native
    model: "openai:gpt-4o"

model_variants:
  fast:
    type: string
    identifier: "openai:gpt-4o-mini"
  creative:
    type: anthropic
    identifier: "claude-sonnet-4"
  reliable:
    type: fallback
    models:
      - type: openai
        identifier: "gpt-4o"
      - type: anthropic  
        identifier: "claude-opus-4"

Key Behaviors

• Precedence: Configured variants override discovered models with the same ID
• Fallback: When no variants are configured, servers gracefully fall back to automatic discovery
• Backward Compatible: Existing configurations continue to work without changes
• Type-Safe: Full pattern matching implementation without runtime attribute access

Testing

• 29 comprehensive unit tests covering all model configuration types
• Tests for provider extraction, provider building, and variant merging
• Integration tests for end-to-end workflows

---

Files Changed: 5
Additions: 788 lines
Deletions: 71 lines

[gemini-code-assist]

Summary of Changes

Hello @Leoyzen, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the AgentPool's model selection capabilities by introducing a unified configuration system. It allows users to define and prioritize custom model variants through manifest files, which are then seamlessly integrated and respected across both OpenCode and ACP server endpoints. This change streamlines model management, improves flexibility, and ensures that user-defined preferences take precedence over dynamically discovered models, all while maintaining backward compatibility.

Highlights

• Unified Model Selection: Implemented a unified system for model selection across AgentPool's protocol servers (OpenCode and ACP), allowing users to define custom model variants in their manifest configurations.
• Precedence Logic: Established a clear precedence hierarchy where user-defined model variants override auto-discovered models with identical IDs, ensuring custom configurations are respected.
• Shared Model Utilities: Introduced a new shared module (src/agentpool_server/shared/model_utils.py) containing reusable functions for model provider extraction, tokonomics integration, and variant merging, promoting code reuse and consistency.
• OpenCode Server Enhancements: Updated the OpenCode server to use an intelligent fallback mechanism for model discovery, prioritizing configured variants, then tokonomics, and finally agent-specific modes, removing previous hardcoded dummy providers.
• ACP Server Integration: Modified the ACP server to incorporate configured variants into session model state retrieval and validation during model setting, ensuring consistency with the new unified model selection.
• Backward Compatibility: Ensured that existing configurations continue to function without requiring any changes, minimizing disruption for current users.
• Comprehensive Testing: Added 29 unit tests covering the new model configuration types and logic, ensuring robustness and correctness of the unified model selection system.

Changelog

• src/agentpool_server/acp_server/acp_agent.py
  • Updated get_session_model_state to fetch and merge configured model variants from the manifest, giving them precedence over tokonomics-discovered models.
  • Modified set_session_model to validate requested model IDs against both dynamically discovered models and user-defined variants in the manifest.
• src/agentpool_server/opencode_server/routes/config_routes.py
  • Imported logging, Any, AgentsManifest, and new shared model utility functions.
  • Added new asynchronous functions (_get_configured_variants, _build_providers_from_configured, _build_providers_from_variants, _build_providers_with_fallback) to implement the model discovery fallback hierarchy.
  • Refactored get_providers and list_providers endpoints to utilize the new _build_providers_with_fallback logic, removing the previous dummy provider fallback.
  • Removed the _get_dummy_providers function.
• src/agentpool_server/shared/init.py
  • Created an __init__.py file to define the shared directory as a Python package.
• src/agentpool_server/shared/model_utils.py
  • Introduced helper functions: _extract_provider_from_identifier to parse provider names from model IDs, _extract_provider to determine provider from various model config types, _build_providers_from_tokonomics to convert tokonomics data into provider objects, and _apply_configured_variants to merge user-defined variants into provider lists.
• tests/agentpool_server/shared/test_model_utils.py
  • Added new test file with comprehensive unit tests for _extract_provider_from_identifier, _extract_provider, _build_providers_from_tokonomics, and _apply_configured_variants functions.

Activity

• No human activity (comments, reviews, etc.) has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a unified model selection configuration, which is a significant and well-executed feature. The introduction of a shared model_utils module is a great step towards better code organization and reuse. The new fallback hierarchy for model discovery in the OpenCode server is a robust improvement over the previous implementation that relied on dummy data. The changes in the ACP server are consistent and correctly apply the new unified logic. The comprehensive test suite for the new utilities is also commendable.

I have a couple of suggestions regarding hardcoded values that are duplicated across files. Addressing these would further improve the maintainability of the new code. Additionally, the refactoring seems to have left the _apply_variants_to_providers function in config_routes.py unused, which could be removed.