Multi-Provider Model Routing for Agents#24
Merged
Conversation
- Introduced pluggable provider abstraction with `ModelProvider` interface. - Added concrete implementations for Claude, Gemini, Ollama, and OpenAI. - Created central `lib/providers.config.ts` for default model selection. - Refactored `runAgent` to support config-driven provider and model resolution. - Maintained legacy support for full agent loops with the Claude provider via SDK. - Enhanced logging to include `[provider:model]` prefix for all agent calls. - Updated stage-aware routing to correctly fallback to frontmatter-defined stages. - Verified all changes with comprehensive unit and E2E tests. Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Contributor
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
- Introduced pluggable provider abstraction for Claude, Gemini, Ollama, and OpenAI. - Added `lib/providers.config.ts` as the single point of configuration. - Refactored `runAgent` to use `resolveProvider` and respect config defaults. - Fixed stage-aware routing regression. - Improved logging to show resolved [provider:model]. - Fixed linting issues (converted static class to functions, fixed 'any' types). - Added `openai` to trustedPackages to satisfy CI checks. - Comprehensive unit and E2E testing. Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
- Introduced pluggable provider abstraction for Claude, Gemini, Ollama, and OpenAI. - Added `lib/providers.config.ts` as the single point of configuration. - Refactored `runAgent` to use `resolveProvider` and respect config defaults. - Fixed stage-aware routing regression in `runAgent`. - Improved logging to show resolved [provider:model]. - Converted `ProviderRegistry` class to `resolveProvider` function to satisfy linting. - Fixed TypeScript errors when mocking `global.fetch` in tests. - Added `openai` to trustedPackages in `package.json`. - Verified all 98 tests pass locally with full type checking. Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
- Introduced pluggable provider abstraction for Claude, Gemini, Ollama, and OpenAI. - Added central `lib/providers.config.ts` for unified model management. - Refactored `runAgent` to support config-driven provider and model resolution. - Fixed stage-aware routing regression. - Improved logging with `[provider:model]` prefix. - Converted `ProviderRegistry` to `resolveProvider` function for better lint compliance. - Fixed TypeScript errors in test mocks for `fetch`. - Pinned `@google/generative-ai` and `openai` versions and added `openai` to `trustedPackages`. - Verified all 98 tests pass locally with full type checking. Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR introduces a multi-provider model routing system to the agent-team project. Agents can now be configured to use different LLM providers (Claude, Gemini, Ollama, OpenAI) via their YAML frontmatter or through a central configuration file. The primary Claude provider maintains its full-featured agent loop using the Anthropic Agent SDK, while other providers use a standardized completion interface. The system includes robust resolution logic that prioritizes runtime options, then agent frontmatter, and finally central configuration defaults, with full support for stage-aware model overrides.
PR created automatically by Jules for task 1032649554769087595 started by @Mitriyweb