Roo-Code/src/api/transform
Daniel afe51e0fe8
feat: migrate Gemini and Vertex providers to AI SDK (#11180)
* feat: migrate Gemini and Vertex providers to AI SDK

- Migrate GeminiHandler from @google/genai to @ai-sdk/google
- Create standalone VertexHandler using @ai-sdk/google-vertex
- Use shared AI SDK utilities (streamText, generateText, convertToAiSdkMessages)
- Support thinkingConfig via providerOptions.google.thinkingConfig
- Support Google Search and URL Context grounding tools
- Preserve cost calculation with tiered pricing
- Remove gemini-format.ts (AI SDK handles message conversion)

EXT-643

* fix: remove unused import and implement allowedFunctionNames tool filtering

- Remove unused handleAiSdkError import from gemini.ts
- Implement tool filtering based on allowedFunctionNames in both
  GeminiHandler and VertexHandler createMessage methods
- Filter tools before converting to AI SDK format to restrict
  model access to only allowed functions
2026-02-04 17:31:48 -07:00
..
__tests__ feat: migrate Gemini and Vertex providers to AI SDK (#11180) 2026-02-04 17:31:48 -07:00
cache-strategy Farewell jest (#4607) 2025-06-16 21:39:45 -07:00
caching feat: Add Vercel AI Gateway provider integration (#7396) 2025-08-26 13:41:02 -07:00
ai-sdk.ts feat: migrate SambaNova provider to AI SDK (#11153) 2026-02-02 23:02:32 -05:00
anthropic-filter.ts fix: filter non-Anthropic content blocks before sending to Vertex API (#9618) 2025-11-26 17:47:04 -05:00
bedrock-converse-format.ts fix: truncate AWS Bedrock toolUseId to 64 characters (#10902) 2026-01-24 00:49:33 -05:00
image-cleaning.ts perf: reduce excessive getModel() calls & implement disk cache fallback (#9410) 2025-11-19 23:13:39 -05:00
minimax-format.ts feat(minimax): move environment_details to system message for thinking models (#10284) 2025-12-22 19:59:42 -07:00
mistral-format.ts fix: normalize tool call IDs for cross-provider compatibility via OpenRouter (#10102) 2025-12-16 09:34:35 -08:00
model-params.ts chore: clean up XML legacy code and native-only comments (#10900) 2026-01-22 15:56:11 -05:00
openai-format.ts fix: Gemini thought signature validation errors (#10694) 2026-01-15 23:25:42 -05:00
r1-format.ts fix(deepseek): preserve reasoning_content during tool call sequences (#10141) 2025-12-17 11:05:55 -05:00
reasoning.ts feat(gemini): add minimal and medium reasoning effort levels (#9973) 2025-12-09 21:50:14 -08:00
stream.ts [feat] Claude Code Provider Native Tool Calling (#10077) 2025-12-17 12:57:27 -08:00
vscode-lm-format.ts Revert "feat(vscode-lm): add image support for VS Code LM API provider" (#11068) 2026-01-29 01:41:20 -05:00
zai-format.ts refactor(zai): merge environment_details into tool result instead of system message (#10289) 2025-12-22 20:20:29 -07:00