Fix issue where thinking param was being sent with non-claude 3.7 models

This commit is contained in:
Saoud Rizwan 2025-03-02 17:12:51 -08:00
parent 6baac79138
commit 542ce36a80
3 changed files with 8 additions and 5 deletions

View file

@ -19,11 +19,13 @@ export class AnthropicHandler implements ApiHandler {
@withRetry()
async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
let budget_tokens = this.options.thinkingBudgetTokens || 0
const reasoningOn = budget_tokens !== 0 ? true : false
const model = this.getModel()
let stream: AnthropicStream<Anthropic.RawMessageStreamEvent>
const modelId = model.id
let budget_tokens = this.options.thinkingBudgetTokens || 0
const reasoningOn = modelId.includes("3-7") && budget_tokens !== 0 ? true : false
switch (modelId) {
// 'latest' alias does not support cache_control
case "claude-3-7-sonnet-20250219":

View file

@ -16,11 +16,12 @@ export class AwsBedrockHandler implements ApiHandler {
@withRetry()
async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
let budget_tokens = this.options.thinkingBudgetTokens || 0
const reasoningOn = budget_tokens !== 0 ? true : false
// cross region inference requires prefixing the model id with the region
let modelId = await this.getModelId()
let budget_tokens = this.options.thinkingBudgetTokens || 0
const reasoningOn = modelId.includes("3-7") && budget_tokens !== 0 ? true : false
// Get model info and message indices for caching
const model = this.getModel()
const userMsgIndices = messages.reduce((acc, msg, index) => (msg.role === "user" ? [...acc, index] : acc), [] as number[])

View file

@ -32,7 +32,7 @@ export class VertexHandler implements ApiHandler {
if (modelId.includes("claude")) {
let budget_tokens = this.options.thinkingBudgetTokens || 0
const reasoningOn = budget_tokens !== 0 ? true : false
const reasoningOn = modelId.includes("3-7") && budget_tokens !== 0 ? true : false
let stream
switch (modelId) {