Fixture/langfuse record auto mode data error (#308)

* fix: 修复状态栏 context 计数器在 loading 时闪现为 0 的问题

第三方 API（如智谱）在 message_start 中可能不返回完整 usage 数据，
导致 getCurrentUsage 返回全零 usage 对象，使 ctx 显示为 0%。

双重保护：
- getCurrentUsage: 跳过全零 usage，继续往前找有真实数据的 message
- calculateContextPercentages: totalInputTokens 为 0 时返回 null

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 外部化 ESM 包使用 createRequire 替代裸 require

color-diff-napi、image-processor-napi、audio-capture-napi 声明
"type": "module" 但使用裸 require()，Node.js ESM 中 require
不可用。改用 createRequire(import.meta.url) 或顶层 import。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: getDefaultSonnetModel 优先使用用户配置的模型，修复第三方 provider 模型不存在错误

当用户通过 ANTHROPIC_MODEL 或 settings 配置了自定义 provider 支持的模型时，
getDefaultSonnetModel/Haiku/Opus 现在会优先使用该配置，而非硬编码 Anthropic 官方模型 ID。
同时改进 Langfuse 可观测性：sideQuery 失败时记录错误信息到 span，
optional 模式下标记 WARNING 而非 ERROR。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 将 auto_mode classifier 的 side-query span 绑定到父 trace

classifyYoloAction 及 classifyYoloActionXml 接收 parentSpan 参数，
透传给 sideQuery 调用，使 auto_mode 的 side-query span 嵌套在主 agent trace 下。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 穷鬼模式下跳过 memdir_relevance side-query

Poor mode 启用时不执行 findRelevantMemories 的预取调用，
避免额外的 API token 消耗。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: 添加 test:all 脚本用于完成任务后的全量检查

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: Vite 构建补齐缺失的 feature flags，修复 auto mode 不可见

Vite 构建插件的 DEFAULT_BUILD_FEATURES 缺少 BUDDY、TRANSCRIPT_CLASSIFIER、
BRIDGE_MODE、ACP、BG_SESSIONS、TEMPLATES，导致 feature('TRANSCRIPT_CLASSIFIER')
被替换为 false，auto mode 从 Shift+Tab 循环中消失。与 build.ts 对齐。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 统一 feature flags 到 defines.ts，修复 Vite 构建缺失 auto mode

将 DEFAULT_BUILD_FEATURES 列表从 build.ts、dev.ts、vite-plugin-feature-flags.ts
三处内联定义统一到 scripts/defines.ts 单一导出。之前的 Vite 插件缺少
TRANSCRIPT_CLASSIFIER 等 feature flag，导致 auto mode 在 Vite 构建中不可见。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/memdir/findRelevantMemories.ts

@@ -3,6 +3,7 @@ import { logForDebugging } from '../utils/debug.js'
 import { errorMessage } from '../utils/errors.js'
 import { getDefaultSonnetModel } from '../utils/model/model.js'
 import { sideQuery } from '../utils/sideQuery.js'
+import type { LangfuseSpan } from '../services/langfuse/index.js'
 import { jsonParse } from '../utils/slowOperations.js'
 import {
   formatMemoryManifest,
@@ -42,6 +43,7 @@ export async function findRelevantMemories(
   signal: AbortSignal,
   recentTools: readonly string[] = [],
   alreadySurfaced: ReadonlySet<string> = new Set(),
+  parentSpan?: LangfuseSpan | null,
 ): Promise<RelevantMemory[]> {
   const memories = (await scanMemoryFiles(memoryDir, signal)).filter(
     m => !alreadySurfaced.has(m.filePath),
@@ -55,6 +57,7 @@ export async function findRelevantMemories(
     memories,
     signal,
     recentTools,
+    parentSpan,
   )
   const byFilename = new Map(memories.map(m => [m.filename, m]))
   const selected = selectedFilenames
@@ -79,6 +82,7 @@ async function selectRelevantMemories(
   memories: MemoryHeader[],
   signal: AbortSignal,
   recentTools: readonly string[],
+  parentSpan?: LangfuseSpan | null,
 ): Promise<string[]> {
   const validFilenames = new Set(memories.map(m => m.filename))
 
@@ -119,6 +123,8 @@ async function selectRelevantMemories(
       },
       signal,
       querySource: 'memdir_relevance',
+      optional: true,
+      parentSpan,
     })
 
     const textBlock = result.content.find(block => block.type === 'text')

src/services/langfuse/index.ts

@@ -1,4 +1,4 @@
 export { initLangfuse, shutdownLangfuse, isLangfuseEnabled, getLangfuseProcessor } from './client.js'
-export { createTrace, createSubagentTrace, recordLLMObservation, recordToolObservation, endTrace, createToolBatchSpan, endToolBatchSpan } from './tracing.js'
+export { createTrace, createSubagentTrace, createChildSpan, recordLLMObservation, recordToolObservation, endTrace, createToolBatchSpan, endToolBatchSpan } from './tracing.js'
 export type { LangfuseSpan } from './tracing.js'
 export { sanitizeToolInput, sanitizeToolOutput, sanitizeGlobal } from './sanitize.js'

src/services/langfuse/tracing.ts

@@ -282,6 +282,60 @@ export function createSubagentTrace(params: {
   }
 }
 
+/**
+ * Create a child span under a parent trace — used for side queries
+ * that should be nested under the main agent trace in Langfuse.
+ */
+export function createChildSpan(
+  parentSpan: LangfuseSpan | null,
+  params: {
+    name: string
+    sessionId: string
+    model: string
+    provider: string
+    input?: unknown
+    querySource?: string
+    username?: string
+  },
+): LangfuseSpan | null {
+  if (!parentSpan || !isLangfuseEnabled()) return null
+  try {
+    const span = startObservation(
+      params.name,
+      {
+        input: params.input,
+        metadata: {
+          provider: params.provider,
+          model: params.model,
+          querySource: params.querySource,
+        },
+      },
+      {
+        asType: 'span',
+        parentSpanContext: parentSpan.otelSpan.spanContext(),
+      },
+    ) as LangfuseSpan
+
+    // Propagate session ID and user ID from parent
+    const parent = parentSpan as unknown as RootTrace
+    const sessionId = parent._sessionId ?? params.sessionId
+    if (sessionId) {
+      span.otelSpan.setAttribute(LangfuseOtelSpanAttributes.TRACE_SESSION_ID, sessionId)
+      ;(span as unknown as RootTrace)._sessionId = sessionId
+    }
+    const userId = parent._userId ?? resolveLangfuseUserId(params.username)
+    if (userId) {
+      span.otelSpan.setAttribute(LangfuseOtelSpanAttributes.TRACE_USER_ID, userId)
+      ;(span as unknown as RootTrace)._userId = userId
+    }
+    logForDebugging(`[langfuse] Child span created: ${span.id} (parent=${parentSpan.id})`)
+    return span
+  } catch (e) {
+    logForDebugging(`[langfuse] createChildSpan failed: ${e}`, { level: 'error' })
+    return null
+  }
+}
+
 export function endTrace(
   rootSpan: LangfuseSpan | null,
   output?: unknown,

src/utils/attachments.ts

@@ -2201,6 +2201,7 @@ async function getRelevantMemoryAttachments(
   recentTools: readonly string[],
   signal: AbortSignal,
   alreadySurfaced: ReadonlySet<string>,
+  parentSpan?: unknown,
 ): Promise<Attachment[]> {
   // If an agent is @-mentioned, search only its memory dir (isolation).
   // Otherwise search the auto-memory dir.
@@ -2221,6 +2222,7 @@ async function getRelevantMemoryAttachments(
         signal,
         recentTools,
         alreadySurfaced,
+        parentSpan as Parameters<typeof findRelevantMemories>[5],
       ).catch(() => []),
     ),
   )
@@ -2370,6 +2372,12 @@ export function startRelevantMemoryPrefetch(
     return undefined
   }
 
+  // Poor mode: skip the side-query to save tokens
+  const { isPoorModeActive } = require('../commands/poor/poorMode.js') as typeof import('../commands/poor/poorMode.js')
+  if (isPoorModeActive()) {
+    return undefined
+  }
+
   const lastUserMessage = messages.findLast(m => m.type === 'user' && !m.isMeta)
   if (!lastUserMessage) {
     return undefined
@@ -2397,6 +2405,7 @@ export function startRelevantMemoryPrefetch(
     collectRecentSuccessfulTools(messages, lastUserMessage),
     controller.signal,
     surfaced.paths,
+    toolUseContext.langfuseTrace,
   ).catch(e => {
     if (!isAbortError(e)) {
       logError(e)

src/utils/context.ts

@@ -133,6 +133,12 @@ export function calculateContextPercentages(
     currentUsage.cache_creation_input_tokens +
     currentUsage.cache_read_input_tokens
 
+  // Treat zero input tokens the same as no usage data — avoids flashing
+  // "ctx:0%" when a third-party API omits usage from message_start.
+  if (totalInputTokens === 0) {
+    return { used: null, remaining: null }
+  }
+
   const usedPercentage = Math.round(
     (totalInputTokens / contextWindowSize) * 100,
   )

src/utils/model/model.ts

@@ -126,6 +126,12 @@ export function getDefaultOpusModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_OPUS_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_OPUS_MODEL
   }
+  // Fall back to user's configured model — custom providers may not
+  // recognize hardcoded Anthropic model IDs.
+  const userSpecifiedOpus = getUserSpecifiedModelSetting()
+  if (userSpecifiedOpus) {
+    return parseUserSpecifiedModel(userSpecifiedOpus)
+  }
   // 3P providers (Bedrock, Vertex, Foundry) — kept as a separate branch
   // even when values match, since 3P availability lags firstParty and
   // these will diverge again at the next model launch.
@@ -153,6 +159,13 @@ export function getDefaultSonnetModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_SONNET_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_SONNET_MODEL
   }
+  // Fall back to user's configured model (ANTHROPIC_MODEL / settings) —
+  // custom providers (proxies, national clouds) may not recognize the
+  // hardcoded Anthropic model IDs.
+  const userSpecified = getUserSpecifiedModelSetting()
+  if (userSpecified) {
+    return parseUserSpecifiedModel(userSpecified)
+  }
   // Default to Sonnet 4.5 for 3P since they may not have 4.6 yet
   if (provider !== 'firstParty') {
     return getModelStrings().sonnet45
@@ -175,6 +188,12 @@ export function getDefaultHaikuModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_HAIKU_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_HAIKU_MODEL
   }
+  // Fall back to user's configured model — custom providers may not
+  // recognize hardcoded Anthropic model IDs.
+  const userSpecifiedHaiku = getUserSpecifiedModelSetting()
+  if (userSpecifiedHaiku) {
+    return parseUserSpecifiedModel(userSpecifiedHaiku)
+  }
 
   // Haiku 4.5 is available on all platforms (first-party, Foundry, Bedrock, Vertex)
   return getModelStrings().haiku45

src/utils/permissions/permissions.ts

@@ -696,6 +696,7 @@ export const hasPermissionsToUseTool: CanUseToolFn = async (
           context.options.tools,
           appState.toolPermissionContext,
           context.abortController.signal,
+          context.langfuseTrace,
         )
       } finally {
         clearClassifierChecking(toolUseID)

src/utils/permissions/yoloClassifier.ts

@@ -31,6 +31,7 @@ import { resolveAntModel } from '../model/antModels.js'
 import { getMainLoopModel } from '../model/model.js'
 import { getAutoModeConfig } from '../settings/settings.js'
 import { sideQuery } from '../sideQuery.js'
+import type { LangfuseSpan } from '../../services/langfuse/index.js'
 import { jsonStringify } from '../slowOperations.js'
 import { tokenCountWithEstimation } from '../tokens.js'
 import {
@@ -731,6 +732,7 @@ async function classifyYoloActionXml(
     action: string
   },
   mode: TwoStageMode,
+  parentSpan?: LangfuseSpan | null,
 ): Promise<YoloClassifierResult> {
   const classifierType =
     mode === 'both'
@@ -791,6 +793,7 @@ async function classifyYoloActionXml(
         signal,
         ...(mode !== 'fast' && { stop_sequences: ['</block>'] }),
         querySource: 'auto_mode',
+        parentSpan,
       }
       const stage1Raw = await sideQuery(stage1Opts)
       stage1DurationMs = Date.now() - stage1Start
@@ -877,6 +880,7 @@ async function classifyYoloActionXml(
       maxRetries: getDefaultMaxRetries(),
       signal,
       querySource: 'auto_mode' as const,
+      parentSpan,
     }
     const stage2Raw = await sideQuery(stage2Opts)
     const stage2DurationMs = Date.now() - stage2Start
@@ -1015,6 +1019,7 @@ export async function classifyYoloAction(
   tools: Tools,
   context: ToolPermissionContext,
   signal: AbortSignal,
+  parentSpan?: LangfuseSpan | null,
 ): Promise<YoloClassifierResult> {
   const lookup = buildToolLookup(tools)
   const actionCompact = toCompact(action, lookup)
@@ -1126,6 +1131,7 @@ export async function classifyYoloAction(
         action: actionCompact,
       },
       getTwoStageMode(),
+      parentSpan,
     )
   }
   const [disableThinking, thinkingPadding] = getClassifierThinkingConfig(model)
@@ -1156,6 +1162,7 @@ export async function classifyYoloAction(
       maxRetries: getDefaultMaxRetries(),
       signal,
       querySource: 'auto_mode' as const,
+      parentSpan,
     }
     const result = await sideQuery(sideQueryOpts)
     void maybeDumpAutoMode(sideQueryOpts, result, start)

src/utils/sideQuery.ts

@@ -15,8 +15,11 @@ import { logEvent } from '../services/analytics/index.js'
 import type { AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS } from '../services/analytics/metadata.js'
 import { getAPIMetadata } from '../services/api/claude.js'
 import { getAnthropicClient } from '../services/api/client.js'
-import { createTrace, endTrace, recordLLMObservation } from '../services/langfuse/index.js'
+import { createTrace, createChildSpan, endTrace, recordLLMObservation } from '../services/langfuse/index.js'
+import type { LangfuseSpan } from '../services/langfuse/index.js'
+import { convertMessagesToLangfuse, convertOutputToLangfuse, convertToolsToLangfuse } from '../services/langfuse/convert.js'
 import { getModelBetas, modelSupportsStructuredOutputs } from './betas.js'
+import { errorMessage } from './errors.js'
 import { computeFingerprint } from './fingerprint.js'
 import { getAPIProvider } from './model/providers.js'
 import { normalizeModelStringForAPI } from './model/model.js'
@@ -64,6 +67,11 @@ export type SideQueryOptions = {
   stop_sequences?: string[]
   /** Attributes this call in tengu_api_success for COGS joining against reporting.sampling_calls. */
   querySource: QuerySource
+  /** Parent Langfuse span to nest this side query under the main agent trace. */
+  parentSpan?: LangfuseSpan | null
+  /** When true, API failures are recorded as WARNING instead of ERROR in Langfuse.
+   *  Use for optional/best-effort queries where failure is expected and handled gracefully. */
+  optional?: boolean
 }
 
 /**
@@ -182,13 +190,25 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
   const normalizedModel = normalizeModelStringForAPI(model)
   const provider = getAPIProvider()
   const start = Date.now()
-  const langfuseTrace = createTrace({
-    sessionId: getSessionId(),
-    model: normalizedModel,
-    provider,
-    name: `side-query:${opts.querySource}`,
-    querySource: opts.querySource,
-  })
+  const traceName = `side-query:${opts.querySource}`
+
+  // When parentSpan is provided, create a child span nested under the
+  // main agent trace; otherwise create a standalone root trace.
+  const langfuseTrace = opts.parentSpan
+    ? createChildSpan(opts.parentSpan, {
+        name: traceName,
+        sessionId: getSessionId(),
+        model: normalizedModel,
+        provider,
+        querySource: opts.querySource,
+      })
+    : createTrace({
+        sessionId: getSessionId(),
+        model: normalizedModel,
+        provider,
+        name: traceName,
+        querySource: opts.querySource,
+      })
 
   let response: BetaMessage
   try {
@@ -210,7 +230,7 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
       { signal },
     )
   } catch (error) {
-    endTrace(langfuseTrace, undefined, 'error')
+    endTrace(langfuseTrace, { error: errorMessage(error) }, opts.optional ? 'interrupted' : 'error')
     throw error
   }
 
@@ -235,12 +255,21 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
   })
   setLastApiCompletionTimestamp(now)
 
-  // Record LLM observation in Langfuse (no-op if not configured)
+  // Record LLM observation in Langfuse (no-op if not configured).
+  // Wrap SDK types into the internal message format expected by converters.
+  const wrappedInput = messages.map(m => ({
+    type: m.role === 'assistant' ? 'assistant' as const : 'user' as const,
+    message: { role: m.role, content: m.content },
+  })) as unknown as Parameters<typeof convertMessagesToLangfuse>[0]
+  const wrappedOutput = [{
+    type: 'assistant' as const,
+    message: { role: 'assistant' as const, content: response.content },
+  }] as unknown as Parameters<typeof convertOutputToLangfuse>[0]
   recordLLMObservation(langfuseTrace, {
     model: normalizedModel,
     provider,
-    input: messages,
-    output: response.content,
+    input: convertMessagesToLangfuse(wrappedInput, systemBlocks.length > 0 ? systemBlocks.map(b => b.text) : undefined),
+    output: convertOutputToLangfuse(wrappedOutput),
     usage: {
       input_tokens: response.usage.input_tokens,
       output_tokens: response.usage.output_tokens,
@@ -249,6 +278,7 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
     },
     startTime: new Date(start),
     endTime: new Date(),
+    ...(tools && { tools: convertToolsToLangfuse(tools as unknown[]) }),
   })
   endTrace(langfuseTrace)
 

src/utils/tokens.ts

@@ -150,9 +150,17 @@ export function getCurrentUsage(messages: Message[]): {
     const message = messages[i]
     const usage = message ? getTokenUsage(message) : undefined
     if (usage) {
+      const inputTokens =
+        (usage.input_tokens ?? 0) +
+        (usage.cache_creation_input_tokens ?? 0) +
+        (usage.cache_read_input_tokens ?? 0)
+      // Skip placeholder usage (all zeros) — third-party APIs may emit
+      // message_start without real usage data, causing the context counter
+      // to flash to 0. Fall through to the previous message instead.
+      if (inputTokens === 0 && (usage.output_tokens ?? 0) === 0) continue
       return {
-        input_tokens: usage.input_tokens,
-        output_tokens: usage.output_tokens,
+        input_tokens: usage.input_tokens ?? 0,
+        output_tokens: usage.output_tokens ?? 0,
         cache_creation_input_tokens: usage.cache_creation_input_tokens ?? 0,
         cache_read_input_tokens: usage.cache_read_input_tokens ?? 0,
       }