feat: langfuse tracing 增加 thinking 参数记录

在 recordLLMObservation 中添加 thinking 配置（type/budgetTokens），
所有 provider（claude/gemini/openai）及 tokenEstimation、sideQuery
调用处同步传递 thinking 信息，便于 Langfuse 面板观察 thinking 使用情况。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/services/api/claude.ts

@@ -1776,6 +1776,8 @@ async function* queryModel(
   // captures only primitives instead of paramsFromContext's full closure scope
   // (messagesForAPI, system, allTools, betas — the entire request-building
   // context), which would otherwise be pinned until the promise resolves.
+  // Also capture thinking params for Langfuse observability.
+  let langfuseThinking: { type: string; budgetTokens?: number } | undefined
   {
     const queryParams = paramsFromContext({
       model: options.model,
@@ -1785,6 +1787,15 @@ async function* queryModel(
     const logBetas = useBetas ? (queryParams.betas ?? []) : []
     const logThinkingType = queryParams.thinking?.type ?? 'disabled'
     const logEffortValue = queryParams.output_config?.effort
+    if (queryParams.thinking && queryParams.thinking.type !== 'disabled') {
+      langfuseThinking = {
+        type: queryParams.thinking.type,
+        ...('budget_tokens' in queryParams.thinking &&
+          typeof queryParams.thinking.budget_tokens === 'number' && {
+            budgetTokens: queryParams.thinking.budget_tokens,
+          }),
+      }
+    }
     void options.getToolPermissionContext().then(permissionContext => {
       logAPIQuery({
         model: options.model,
@@ -2925,6 +2936,7 @@ async function* queryModel(
     endTime: new Date(),
     completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
     tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+    thinking: langfuseThinking,
   })
 
   void options.getToolPermissionContext().then(permissionContext => {

src/services/api/gemini/index.ts

@@ -193,6 +193,15 @@ export async function* queryModelGemini(
       endTime: new Date(),
       completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
       tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+      thinking:
+        thinkingConfig.type !== 'disabled'
+          ? {
+              type: thinkingConfig.type,
+              ...(thinkingConfig.type === 'enabled' && {
+                budgetTokens: thinkingConfig.budgetTokens,
+              }),
+            }
+          : undefined,
     })
   } catch (error) {
     const errorMessage = error instanceof Error ? error.message : String(error)

src/services/api/openai/index.ts

@@ -418,6 +418,7 @@ export async function* queryModelOpenAI(
       endTime: new Date(),
       completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
       tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+      ...(enableThinking && { thinking: { type: 'enabled' } }),
     })
 
     // Safety: if stream ended without message_stop, assemble and yield whatever we have

src/services/langfuse/tracing.ts

@@ -78,6 +78,11 @@ export function recordLLMObservation(
     endTime?: Date
     completionStartTime?: Date
     tools?: unknown
+    /** Thinking depth configuration used for this request */
+    thinking?: {
+      type: string
+      budgetTokens?: number
+    }
   },
 ): void {
   if (!rootSpan || !isLangfuseEnabled()) return
@@ -97,6 +102,10 @@ export function recordLLMObservation(
         metadata: {
           provider: params.provider,
           model: params.model,
+          ...(params.thinking && { thinkingType: params.thinking.type }),
+          ...(params.thinking?.budgetTokens !== undefined && {
+            thinkingBudgetTokens: params.thinking.budgetTokens,
+          }),
         },
         ...(params.completionStartTime && { completionStartTime: params.completionStartTime }),
       },

src/services/tokenEstimation.ts

@@ -354,6 +354,7 @@ export async function countTokensViaHaikuFallback(
     },
     startTime: new Date(apiStart),
     endTime: new Date(),
+    ...(containsThinking && { thinking: { type: 'enabled', budgetTokens: TOKEN_COUNT_THINKING_BUDGET } }),
   })
   endTrace(langfuseTrace)
 

src/utils/sideQuery.ts

@@ -294,6 +294,12 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
     startTime: new Date(start),
     endTime: new Date(),
     ...(tools && { tools: convertToolsToLangfuse(tools as unknown[]) }),
+    ...(thinkingConfig && thinkingConfig.type !== 'disabled' && {
+      thinking: {
+        type: thinkingConfig.type,
+        ...(thinkingConfig.type === 'enabled' && { budgetTokens: thinkingConfig.budget_tokens }),
+      },
+    }),
   })
   endTrace(langfuseTrace)