scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-09-06 08:18:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Roo-Code/src/api/providers
History
Hannes Rudolph 47bba1c2f7
feat: add Claude Opus 4.6 support across all providers (#11224) 
* feat: add Claude Opus 4.6 support across all providers

Add Claude Opus 4.6 (claude-opus-4-6) model definitions and 1M context
support across Anthropic, Bedrock, Vertex AI, OpenRouter, and Vercel AI
Gateway providers.

- Anthropic: 128K max output, /5 pricing, 1M context tiers
- Bedrock: anthropic.claude-opus-4-6-v1:0 with 1M context + global inference
- Vertex: claude-opus-4-6 with 1M context tiers
- OpenRouter: prompt caching + reasoning budget sets
- Vercel AI Gateway: Opus 4.5 and 4.6 added to capability sets
- UI: 1M context checkbox for Opus 4.6 on all providers
- i18n: Updated 1M context descriptions across 18 locales

Also adds Opus 4.5 to Vercel AI Gateway (previously missing) and
OpenRouter maxTokens overrides for Opus 4.5/4.6.

Closes #11223

* fix: apply tier pricing when 1M context is enabled on Bedrock

When awsBedrock1MContext is enabled for tiered models like Opus 4.6,
also apply the 1M tier pricing (inputPrice, outputPrice, cache prices)
instead of only updating contextWindow. This ensures cost calculations
and UI display use the correct >200K rates.
2026-02-05 13:18:40 -07:00
..
__tests__ feat: migrate Gemini and Vertex providers to AI SDK (#11180) 2026-02-04 17:31:48 -07:00
fetchers feat: add Claude Opus 4.6 support across all providers (#11224) 2026-02-05 13:18:40 -07:00
utils chore: disable edit_file tool for Gemini/Vertex (#10594) 2026-01-09 21:24:15 -05:00
anthropic-vertex.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
anthropic.ts feat: add Claude Opus 4.6 support across all providers (#11224) 2026-02-05 13:18:40 -07:00
base-openai-compatible-provider.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
base-provider.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
baseten.ts (feat): Add Baseten Provider (#9461) 2025-11-21 17:49:15 -05:00
bedrock.ts feat: add Claude Opus 4.6 support across all providers (#11224) 2026-02-05 13:18:40 -07:00
cerebras.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
chutes.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
constants.ts feat: add User-Agent header to API providers (#5492) 2025-07-08 23:19:56 -04:00
deepinfra.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
deepseek.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
doubao.ts Support new LLM provider: Doubao (#6345) 2025-07-30 16:54:16 -04:00
fake-ai.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
featherless.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
fireworks.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
gemini.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
groq.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
huggingface.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
index.ts feat: Add OpenAI-compatible base provider and migrate Moonshot to AI SDK (#11063) 2026-01-29 01:29:33 -05:00
io-intelligence.ts Get the model id property for a given provider (#8009) 2025-09-17 15:24:27 -07:00
lite-llm.ts Fix LiteLLM tool ID validation errors for Bedrock proxy (#10990) 2026-01-26 23:54:48 -05:00
lm-studio.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
minimax.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
mistral.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
moonshot.ts feat: Add OpenAI-compatible base provider and migrate Moonshot to AI SDK (#11063) 2026-01-29 01:29:33 -05:00
native-ollama.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
openai-codex.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
openai-compatible.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
openai-native.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
openai.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
openrouter.ts chore: clean up XML legacy code and native-only comments (#10900) 2026-01-22 15:56:11 -05:00
qwen-code.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
requesty.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
roo.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
router-provider.ts chore: remove XML tool calling support (#10841) 2026-01-20 20:25:08 -05:00
sambanova.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
unbound.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
vercel-ai-gateway.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
vertex.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
vscode-lm.ts Revert "feat(vscode-lm): add image support for VS Code LM API provider" (#11068) 2026-01-29 01:41:20 -05:00
xai.ts fix(ai-sdk): preserve reasoning parts in message conversion (#11217) 2026-02-05 10:48:21 -07:00
zai.ts Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00