Merge branch 'claude-code-best:main' into main

src/cli/print.ts

@@ -377,9 +377,6 @@ const cronJitterConfigModule =
   require('../utils/cronJitterConfig.js') as typeof import('../utils/cronJitterConfig.js')
 const cronGate =
   require('@claude-code-best/builtin-tools/tools/ScheduleCronTool/prompt.js') as typeof import('@claude-code-best/builtin-tools/tools/ScheduleCronTool/prompt.js')
-const extractMemoriesModule = feature('EXTRACT_MEMORIES')
-  ? (require('../services/extractMemories/extractMemories.js') as typeof import('../services/extractMemories/extractMemories.js'))
-  : null
 /* eslint-enable @typescript-eslint/no-require-imports */
 
 const SHUTDOWN_TEAM_PROMPT = `<system-reminder>
@@ -985,7 +982,14 @@ export async function runHeadless(
   // the forked agent mid-flight. Gated by isExtractModeActive so the
   // tengu_slate_thimble flag controls non-interactive extraction end-to-end.
   if (feature('EXTRACT_MEMORIES') && isExtractModeActive()) {
-    await extractMemoriesModule!.drainPendingExtraction()
+    try {
+      const { drainPendingExtraction } = await import(
+        '../services/extractMemories/extractMemories.js'
+      )
+      await drainPendingExtraction()
+    } catch {
+      // Module load failure — non-critical at shutdown
+    }
   }
 
   gracefulShutdownSync(

src/components/Spinner.tsx

@@ -23,6 +23,7 @@ import { getDefaultCharacters, type SpinnerMode } from './Spinner/index.js';
 import { SpinnerAnimationRow } from './Spinner/SpinnerAnimationRow.js';
 import { useSettings } from '../hooks/useSettings.js';
 import { isInProcessTeammateTask } from '../tasks/InProcessTeammateTask/types.js';
+import { isLocalAgentTask } from '../tasks/LocalAgentTask/LocalAgentTask.js';
 import { isBackgroundTask } from '../tasks/types.js';
 import { getAllInProcessTeammateTasks } from '../tasks/InProcessTeammateTask/InProcessTeammateTask.js';
 import { getEffortSuffix } from '../utils/effort.js';
@@ -209,15 +210,22 @@ function SpinnerWithVerbInner({
   const hasRunningTeammates = runningTeammates.length > 0;
   const allIdle = hasRunningTeammates && runningTeammates.every(t => t.isIdle);
 
-  // Gather aggregate token stats from all running swarm teammates
-  // In spinner-tree mode, skip aggregation (teammates have their own lines in the tree)
+  // Gather aggregate token stats from all running agents.
+  // In spinner-tree mode, skip in-process teammates (they have their own
+  // per-teammate lines in the tree) but still count local-agent tasks
+  // (background agents) which have no dedicated tree rows.
   let teammateTokens = 0;
-  if (!showSpinnerTree) {
-    for (const task of Object.values(tasks)) {
-      if (isInProcessTeammateTask(task) && task.status === 'running') {
-        if (task.progress?.tokenCount) {
-          teammateTokens += task.progress.tokenCount;
-        }
+  for (const task of Object.values(tasks)) {
+    if (task.status !== 'running') continue;
+    if (isInProcessTeammateTask(task)) {
+      if (!showSpinnerTree && task.progress?.tokenCount) {
+        teammateTokens += task.progress.tokenCount;
+      }
+      continue;
+    }
+    if (isLocalAgentTask(task)) {
+      if (task.progress?.tokenCount) {
+        teammateTokens += task.progress.tokenCount;
       }
     }
   }

src/query/stopHooks.ts

@@ -39,9 +39,6 @@ import { getTaskListId, listTasks } from '../utils/tasks.js'
 import { getAgentName, getTeamName, isTeammate } from '../utils/teammate.js'
 
 /* eslint-disable @typescript-eslint/no-require-imports */
-const extractMemoriesModule = feature('EXTRACT_MEMORIES')
-  ? (require('../services/extractMemories/extractMemories.js') as typeof import('../services/extractMemories/extractMemories.js'))
-  : null
 const jobClassifierModule = feature('TEMPLATES')
   ? (require('../jobs/classifier.js') as typeof import('../jobs/classifier.js'))
   : null
@@ -154,12 +151,16 @@ export async function* handleStopHooks(
       // Fire-and-forget in both interactive and non-interactive. For -p/SDK,
       // print.ts drains the in-flight promise after flushing the response
       // but before gracefulShutdownSync (see drainPendingExtraction).
-      void extractMemoriesModule!.executeExtractMemories(
-        stopHookContext,
-        toolUseContext.appendSystemMessage as
-          | ((msg: import('../types/message.js').SystemMessage) => void)
-          | undefined,
-      )
+      void import('../services/extractMemories/extractMemories.js')
+        .then(({ executeExtractMemories }) =>
+          executeExtractMemories(
+            stopHookContext,
+            toolUseContext.appendSystemMessage as
+              | ((msg: import('../types/message.js').SystemMessage) => void)
+              | undefined,
+          ),
+        )
+        .catch(() => {})
     }
     if (!toolUseContext.agentId && !poorMode) {
       void executeAutoDream(stopHookContext, toolUseContext.appendSystemMessage)

src/services/api/openai/__tests__/thinking.test.ts

@@ -147,6 +147,22 @@ describe('isOpenAIThinkingEnabled', () => {
       expect(isOpenAIThinkingEnabled('deepseek-coder')).toBe(true)
     })
 
+    test('returns true when model name is "mimo-v2-flash"', () => {
+      expect(isOpenAIThinkingEnabled('mimo-v2-flash')).toBe(true)
+    })
+
+    test('returns true when model name is "mimo-v2-pro"', () => {
+      expect(isOpenAIThinkingEnabled('mimo-v2-pro')).toBe(true)
+    })
+
+    test('returns true when model name is "mimo-v2.5-pro"', () => {
+      expect(isOpenAIThinkingEnabled('mimo-v2.5-pro')).toBe(true)
+    })
+
+    test('returns true when model name contains "mimo"', () => {
+      expect(isOpenAIThinkingEnabled('MiMo-V2-Omni')).toBe(true)
+    })
+
     test('returns false when model name is "gpt-4o"', () => {
       expect(isOpenAIThinkingEnabled('gpt-4o')).toBe(false)
     })
@@ -197,7 +213,10 @@ describe('buildOpenAIRequestBody — thinking params', () => {
   test('includes vLLM/self-hosted thinking format when enabled', () => {
     const body = buildOpenAIRequestBody({ ...baseParams, enableThinking: true })
     expect(body.enable_thinking).toBe(true)
-    expect(body.chat_template_kwargs).toEqual({ thinking: true })
+    expect(body.chat_template_kwargs).toEqual({
+      thinking: true,
+      enable_thinking: true,
+    })
   })
 
   test('includes both formats simultaneously when enabled', () => {

src/services/api/openai/requestBody.ts

@@ -7,11 +7,11 @@ import type { ChatCompletionCreateParamsStreaming } from 'openai/resources/chat/
 import { isEnvTruthy, isEnvDefinedFalsy } from '../../../utils/envUtils.js'
 
 /**
- * Detect whether DeepSeek-style thinking mode should be enabled.
+ * Detect whether thinking mode should be enabled for this model.
  *
  * Enabled when:
  * 1. OPENAI_ENABLE_THINKING=1 is set (explicit enable), OR
- * 2. Model name contains "deepseek-reasoner" OR "DeepSeek-V3.2" (auto-detect, case-insensitive)
+ * 2. Model name contains "deepseek" or "mimo" (auto-detect, case-insensitive)
  *
  * Disabled when:
  * - OPENAI_ENABLE_THINKING=0/false/no/off is explicitly set (overrides model detection)
@@ -23,9 +23,9 @@ export function isOpenAIThinkingEnabled(model: string): boolean {
   if (isEnvDefinedFalsy(process.env.OPENAI_ENABLE_THINKING)) return false
   // Explicit enable
   if (isEnvTruthy(process.env.OPENAI_ENABLE_THINKING)) return true
-  // Auto-detect from model name (all DeepSeek models support thinking mode)
+  // Auto-detect from model name (DeepSeek and MiMo models support thinking mode)
   const modelLower = model.toLowerCase()
-  return modelLower.includes('deepseek')
+  return modelLower.includes('deepseek') || modelLower.includes('mimo')
 }
 
 /**
@@ -58,12 +58,12 @@ export function resolveOpenAIMaxTokens(
  * Build the request body for OpenAI chat.completions.create().
  * Extracted for testability — the thinking mode params are injected here.
  *
- * DeepSeek thinking mode: inject thinking params via request body.
- * Two formats are added simultaneously to support different deployments:
- * - Official DeepSeek API: `thinking: { type: 'enabled' }`
- * - Self-hosted DeepSeek-V3.2: `enable_thinking: true` + `chat_template_kwargs: { thinking: true }`
+ * Three thinking-mode formats are sent simultaneously; each endpoint uses the
+ * format it recognizes and ignores the others:
+ * - Official DeepSeek API:    `thinking: { type: 'enabled' }`
+ * - Self-hosted DeepSeek:     `enable_thinking: true` + `chat_template_kwargs: { thinking: true }`
+ * - MiMo (Xiaomi):            `chat_template_kwargs: { enable_thinking: true }`
  * OpenAI SDK passes unknown keys through to the HTTP body.
- * Each endpoint will use the format it recognizes and ignore the others.
  */
 export function buildOpenAIRequestBody(params: {
   model: string
@@ -76,7 +76,7 @@ export function buildOpenAIRequestBody(params: {
 }): ChatCompletionCreateParamsStreaming & {
   thinking?: { type: string }
   enable_thinking?: boolean
-  chat_template_kwargs?: { thinking: boolean }
+  chat_template_kwargs?: { thinking: boolean; enable_thinking: boolean }
 } {
   const {
     model,
@@ -97,14 +97,15 @@ export function buildOpenAIRequestBody(params: {
     }),
     stream: true,
     stream_options: { include_usage: true },
-    // DeepSeek thinking mode: enable chain-of-thought output.
-    // When active, temperature/top_p/presence_penalty/frequency_penalty are ignored by DeepSeek.
+    // Enable chain-of-thought output for DeepSeek and MiMo models.
+    // When active, temperature/top_p/presence_penalty/frequency_penalty are ignored.
     ...(enableThinking && {
       // Official DeepSeek API format
       thinking: { type: 'enabled' },
       // Self-hosted DeepSeek-V3.2 format
       enable_thinking: true,
-      chat_template_kwargs: { thinking: true },
+      // Both DeepSeek self-hosted and MiMo formats in chat_template_kwargs
+      chat_template_kwargs: { thinking: true, enable_thinking: true },
     }),
     // Only send temperature when thinking mode is off (DeepSeek ignores it anyway,
     // but other providers may respect it)

src/utils/backgroundHousekeeping.ts

@@ -4,9 +4,6 @@ import { initMagicDocs } from '../services/MagicDocs/magicDocs.js'
 import { initSkillImprovement } from './hooks/skillImprovement.js'
 
 /* eslint-disable @typescript-eslint/no-require-imports */
-const extractMemoriesModule = feature('EXTRACT_MEMORIES')
-  ? (require('../services/extractMemories/extractMemories.js') as typeof import('../services/extractMemories/extractMemories.js'))
-  : null
 const registerProtocolModule = feature('LODESTONE')
   ? (require('./deepLink/registerProtocol.js') as typeof import('./deepLink/registerProtocol.js'))
   : null
@@ -32,7 +29,13 @@ export function startBackgroundHousekeeping(): void {
   void initMagicDocs()
   void initSkillImprovement()
   if (feature('EXTRACT_MEMORIES')) {
-    extractMemoriesModule!.initExtractMemories()
+    void import('../services/extractMemories/extractMemories.js')
+      .then(({ initExtractMemories }) => {
+        initExtractMemories()
+      })
+      .catch(() => {
+        // Module load failure — non-critical, memory extraction just won't run
+      })
   }
   initAutoDream()
   void autoUpdateMarketplacesAndPluginsInBackground()

src/utils/cacheWarning.ts

@@ -24,6 +24,12 @@ interface CacheWarningState {
 // 模块级状态，每个 querySource 独立跟踪
 const cacheWarningStateBySource = new Map<string, CacheWarningState>()
 
+// Limit the number of tracked sources to prevent unbounded Map growth.
+// querySource strings are effectively unbounded (typed as `any`), so a
+// long-running session that spawns many subagents could leak memory.
+// Evict the oldest entry (by insertion order) when the limit is exceeded.
+const MAX_SOURCE_ENTRIES = 50
+
 const DEFAULT_CACHE_THRESHOLD = 80
 
 /**
@@ -81,6 +87,13 @@ export function shouldShowCacheWarning(
   let state = cacheWarningStateBySource.get(querySource)
   if (!state) {
     state = { lastHitRate: null, lastTimestamp: null }
+    // Evict oldest entry when at capacity so the Map stays bounded
+    if (cacheWarningStateBySource.size >= MAX_SOURCE_ENTRIES) {
+      const oldestKey = cacheWarningStateBySource.keys().next().value
+      if (oldestKey !== undefined) {
+        cacheWarningStateBySource.delete(oldestKey)
+      }
+    }
     cacheWarningStateBySource.set(querySource, state)
   }
 
@@ -132,3 +145,10 @@ export function createCacheWarningMessage(info: CacheHitRateInfo): Message {
     isMeta: false,
   } as Message
 }
+
+/**
+ * Reset the per-source tracking state — only used in tests.
+ */
+export function _resetCacheWarningStateForTest(): void {
+  cacheWarningStateBySource.clear()
+}

src/utils/swarm/inProcessRunner.ts

@@ -47,6 +47,7 @@ import {
 import type { CustomAgentDefinition } from '@claude-code-best/builtin-tools/tools/AgentTool/loadAgentsDir.js'
 import { runAgent } from '@claude-code-best/builtin-tools/tools/AgentTool/runAgent.js'
 import { awaitClassifierAutoApproval } from '@claude-code-best/builtin-tools/tools/BashTool/bashPermissions.js'
+import type { AgentToolResult } from '@claude-code-best/builtin-tools/tools/AgentTool/agentToolUtils.js'
 import { BASH_TOOL_NAME } from '@claude-code-best/builtin-tools/tools/BashTool/toolName.js'
 import { SEND_MESSAGE_TOOL_NAME } from '@claude-code-best/builtin-tools/tools/SendMessageTool/constants.js'
 import { TASK_CREATE_TOOL_NAME } from '@claude-code-best/builtin-tools/tools/TaskCreateTool/constants.js'
@@ -63,7 +64,10 @@ import {
 } from '../../utils/messages.js'
 import { evictTaskOutput } from '../../utils/task/diskOutput.js'
 import { evictTerminalTask } from '../../utils/task/framework.js'
-import { tokenCountWithEstimation } from '../../utils/tokens.js'
+import {
+  tokenCountWithEstimation,
+  getTokenCountFromUsage,
+} from '../../utils/tokens.js'
 import { createAbortController } from '../abortController.js'
 import { type AgentContext, runWithAgentContext } from '../agentContext.js'
 import {
@@ -915,6 +919,7 @@ export async function runInProcessTeammate(
     invokingRequestId,
   } = config
   const { setAppState } = toolUseContext
+  const startTime = Date.now()
 
   logForDebugging(
     `[inProcessRunner] Starting agent loop for ${identity.agentId}`,
@@ -1463,6 +1468,48 @@ export async function runInProcessTeammate(
     // Mark as completed when exiting the loop
     let alreadyTerminal = false
     let toolUseId: string | undefined
+
+    // Compute result so the detail dialog can show token usage.
+    // Walk backwards for the last API usage (cumulative input_tokens from the
+    // Anthropic API already includes all prior context).
+    let completionTokens = 0
+    let completionToolUseCount = 0
+    let lastAssistantContent: AgentToolResult['content'] = []
+    let lastUsage: AgentToolResult['usage'] | undefined
+    for (let i = allMessages.length - 1; i >= 0; i--) {
+      const m = allMessages[i]!
+      if (m.type === 'assistant') {
+        const blocks = (m.message?.content ?? []) as any[]
+        for (const b of blocks) {
+          if (b?.type === 'tool_use') completionToolUseCount++
+        }
+        const textBlocks = blocks.filter((b: any) => b?.type === 'text')
+        if (textBlocks.length > 0 && lastAssistantContent.length === 0) {
+          lastAssistantContent = textBlocks.map((b: any) => ({
+            type: 'text' as const,
+            text: b.text,
+          }))
+        }
+        if (!lastUsage && m.message?.usage) {
+          lastUsage = m.message.usage as AgentToolResult['usage']
+          completionTokens = getTokenCountFromUsage(
+            m.message.usage as Parameters<typeof getTokenCountFromUsage>[0],
+          )
+        }
+        if (completionTokens > 0 && lastAssistantContent.length > 0) break
+      }
+    }
+
+    const teammateResult: AgentToolResult = {
+      agentId: identity.agentId,
+      agentType: 'teammate',
+      content: lastAssistantContent,
+      totalToolUseCount: completionToolUseCount,
+      totalDurationMs: Date.now() - startTime,
+      totalTokens: completionTokens,
+      usage: lastUsage as AgentToolResult['usage'],
+    } as unknown as AgentToolResult
+
     updateTaskState(
       taskId,
       task => {
@@ -1481,6 +1528,7 @@ export async function runInProcessTeammate(
           status: 'completed' as const,
           notified: true,
           endTime: Date.now(),
+          result: teammateResult,
           messages: task.messages?.length ? [task.messages.at(-1)!] : undefined,
           pendingUserMessages: [],
           inProgressToolUseIDs: undefined,