docs: update model lists for recent Go/Python/Dart plugin work#310
docs: update model lists for recent Go/Python/Dart plugin work#310cabljac wants to merge 3 commits into
Conversation
Bring the per-language "Available Models" lists in the Google AI, Vertex AI, and Anthropic integration docs up to date with models that recently landed in the Go, Python, and Dart plugins. Additive only - no existing entries removed, JS sections untouched. Every added model identifier was verified against the plugin source: - Go: googleAIModels / vertexAIModels arrays and embedderConfig in go/plugins/googlegenai/models.go; Anthropic lists models dynamically. - Python: GoogleAIGeminiVersion / VertexAIGeminiVersion enums in py/plugins/google-genai/.../models/gemini.py; anthropic model_info.py. - Dart: Vertex embedders (genkit_vertexai), public API vertexAI.textEmbedding. Changes: - anthropic: add claude-opus-4-7 to the Go and Python model lists. - google-genai: add enumerated Available Models lists to the Go section (Gemini + embedders) where only prose existed; refresh the Python Gemini list with the gemini-3.1 family and image models. - vertex-ai: add an Available Models list to the Go and Python sections; document the Vertex embedders for Dart (previously undocumented). Note: gemini-3.5-flash is registered for Vertex (not GoogleAI) in the Python plugin, so it is documented under the Vertex section accordingly.
There was a problem hiding this comment.
Code Review
This pull request updates the documentation for Anthropic, Google GenAI, and Vertex AI integrations to include newly supported models (such as Claude Opus 4.7, Gemini 3+ series, Gemini 2.5, Gemini 2.0, and new embedding models) along with updated code examples. The feedback suggests adding text-embedding-004 to the list of available embedding models in the Google GenAI documentation for completeness, as it was previously used in the code examples.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
Address review feedback: text-embedding-004 is a widely-used stable GoogleAI embedder (the prior example) and is registered as a GoogleAI gemini embedder in the Python plugin. Add it to the Go Available Models list for completeness.
Align the gemini-2.5-pro descriptor in the Go and Python model lists with
Google's own positioning ("our most advanced model for complex tasks,
featuring deep reasoning and coding"). It remains the most capable stable
model; the more capable gemini-3.1-pro is preview-only.
What
Brings the per-language Available Models lists in the Google AI, Vertex AI, and Anthropic integration docs up to date with models that recently landed in the Go, Python, and Dart plugins.
Scope / approach
Changes
anthropic.mdxclaude-opus-4-7google-genai.mdxAvailable Modelslists (Gemini + embedders); embedder example now usesgemini-embedding-2google-genai.mdxgemini-3.1family + image models to the Gemini listvertex-ai.mdxAvailable Modelslistsvertex-ai.mdxSource authority
googleAIModels/vertexAIModelsarrays andembedderConfigingo/plugins/googlegenai/models.go; Anthropic lists models dynamically from the API.GoogleAIGeminiVersion/VertexAIGeminiVersionenums inpy/plugins/google-genai/.../models/gemini.py;anthropic/model_info.py.genkit_vertexai; public APIvertexAI.textEmbedding(...).Note
gemini-3.5-flashis registered for Vertex (not GoogleAI) in the Python plugin, so it is documented under the Vertex section rather than GoogleAI.Verification
pnpm buildpasses (360 pages, all internal links valid).