feature: langfuse thinking 及文本edit的问题修复( #371); 省略 diff 以减少内存峰值 (#376)

* 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> * fix: langfuse tracing 兼容 budget_tokens snake_case 格式 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix: 统一传递完整 thinking 配置而非仅 thinkingType Langfuse 追踪直接传递整个 thinking 对象（含 type 和 budget_tokens）， Analytics 日志同步补充 thinkingBudgetTokens 字段，logAPIQuery 改为接收 ThinkingConfig 类型参数。 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: 省略旧消息的代码 diff 展示，仅保留最新消息的完整 diff * fix: Edit 工具增加 Tab/空格规范化匹配，修复中文和缩进文件编辑失败 Read 工具输出将 Tab 渲染为空格，用户复制后 Edit 工具无法匹配。在 findActualString 中增加 Tab→空格规范化回退匹配，并精确映射回原始文件位置。 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * docs: README 添加安装/更新失败的解决方案提示 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-22 08:15:53 +00:00 · 2026-04-27 17:06:33 +08:00
parent b47731a3f3
commit c80e593212
16 changed files with 265 additions and 6 deletions
--- a/src/services/api/claude.ts
+++ b/src/services/api/claude.ts
@@ -1776,6 +1776,10 @@ 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.
+  // Pass the entire thinking config object so all fields (type, budget_tokens,
+  // and any future additions) flow through without cherry-picking.
+  let langfuseThinking: BetaMessageStreamParams['thinking'] | undefined
  {
    const queryParams = paramsFromContext({
      model: options.model,
@@ -1783,8 +1787,10 @@ async function* queryModel(
    })
    const logMessagesLength = queryParams.messages.length
    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 = queryParams.thinking
+    }
    void options.getToolPermissionContext().then(permissionContext => {
      logAPIQuery({
        model: options.model,
@@ -1794,7 +1800,7 @@ async function* queryModel(
        permissionMode: permissionContext.mode,
        querySource: options.querySource,
        queryTracking: options.queryTracking,
-        thinkingType: logThinkingType,
+        thinkingConfig,
        effortValue: logEffortValue,
        fastMode: isFastMode,
        previousRequestId,
@@ -2545,6 +2551,9 @@ async function* queryModel(
          maxOutputTokens,
          thinkingType:
            thinkingConfig.type as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+          ...(thinkingConfig.type === 'enabled' && {
+            thinkingBudgetTokens: thinkingConfig.budgetTokens,
+          }),
          fallback_disabled: true,
          request_id: (streamRequestId ??
            'unknown') as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
@@ -2577,6 +2586,9 @@ async function* queryModel(
        maxOutputTokens,
        thinkingType:
          thinkingConfig.type as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+        ...(thinkingConfig.type === 'enabled' && {
+          thinkingBudgetTokens: thinkingConfig.budgetTokens,
+        }),
        fallback_disabled: false,
        request_id: (streamRequestId ??
          'unknown') as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
@@ -2693,6 +2705,9 @@ async function* queryModel(
        maxOutputTokens,
        thinkingType:
          thinkingConfig.type as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+        ...(thinkingConfig.type === 'enabled' && {
+          thinkingBudgetTokens: thinkingConfig.budgetTokens,
+        }),
        request_id:
          failedRequestId as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
        fallback_cause:
@@ -2925,6 +2940,7 @@ 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 => {
--- a/src/services/api/gemini/index.ts
+++ b/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)
--- a/src/services/api/logging.ts
+++ b/src/services/api/logging.ts
@@ -23,6 +23,7 @@ import { getAPIProviderForStatsig } from 'src/utils/model/providers.js'
 import type { PermissionMode } from 'src/utils/permissions/PermissionMode.js'
 import { jsonStringify } from 'src/utils/slowOperations.js'
 import { logOTelEvent } from 'src/utils/telemetry/events.js'
+import type { ThinkingConfig } from 'src/utils/thinking.js'
 import {
  endLLMRequestSpan,
  isBetaTracingEnabled,
@@ -176,7 +177,7 @@ export function logAPIQuery({
  permissionMode,
  querySource,
  queryTracking,
-  thinkingType,
+  thinkingConfig,
  effortValue,
  fastMode,
  previousRequestId,
@@ -188,11 +189,13 @@ export function logAPIQuery({
  permissionMode?: PermissionMode
  querySource: string
  queryTracking?: QueryChainTracking
-  thinkingType?: 'adaptive' | 'enabled' | 'disabled'
+  thinkingConfig?: ThinkingConfig
  effortValue?: EffortLevel | null
  fastMode?: boolean
  previousRequestId?: string | null
 }): void {
+  const thinkingType = thinkingConfig?.type ?? 'disabled'
+  const thinkingBudgetTokens = thinkingConfig?.type === 'enabled' ? thinkingConfig.budgetTokens : undefined
  logEvent('tengu_api_query', {
    model: model as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
    messagesLength,
@@ -219,6 +222,9 @@ export function logAPIQuery({
      : {}),
    thinkingType:
      thinkingType as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    ...(thinkingBudgetTokens !== undefined && {
+      thinkingBudgetTokens,
+    }),
    effortValue:
      effortValue as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
    fastMode,
--- a/src/services/api/openai/index.ts
+++ b/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