scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-09-07 08:26:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Hard cap max tokens for 3-7 models in lieu of extended thinking

Browse source
This commit is contained in:
slytechnical 2025-05-16 18:53:09 -05:00
parent 88de5b26cd
commit 8eb9c28bb2
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/api/providers/fetchers/litellm.ts
View file

@ -32,11 +32,17 @@ export async function getLiteLLMModels(apiKey: string, baseUrl: string): Promise
if (!modelName || !modelInfo || !litellmModelName) continue
let determinedMaxTokens = modelInfo.max_tokens || modelInfo.max_output_tokens || 8192
if (modelName.includes("claude-3-7-sonnet")) {
// due to https://github.com/BerriAI/litellm/issues/8984 until proper extended thinking support is added
determinedMaxTokens = 64000
}
models[modelName] = {
maxTokens: modelInfo.max_tokens || 8192,
maxTokens: determinedMaxTokens,
contextWindow: modelInfo.max_input_tokens || 200000,
supportsImages: Boolean(modelInfo.supports_vision),
// litellm_params.model may have a prefix like openrouter/
supportsComputerUse: Boolean(modelInfo.supports_computer_use),
supportsPromptCache: Boolean(modelInfo.supports_prompt_caching),
inputPrice: modelInfo.input_cost_per_token ? modelInfo.input_cost_per_token * 1000000 : undefined,