chore: 1.10.8

evidence 数组和追加块缺少大小限制，导致 skill 文件（如
sdd-brainstorming）在短时间内膨胀至 21K+ 行/78 个 evidence 块。

三处修复：
- instinctParser: evidence 数组 cap 10 条, observationIds cap 20 条
- skillGenerator: 追加块每次最多 20 行, 文件总大小上限 50KB,
  生成 skill 的 evidence 段限制 20 行
- agentGenerator: 生成 agent 的 evidence 段限制 20 行

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

README.md

@@ -55,6 +55,8 @@ ccb update # 更新到最新版本
 CLAUDE_BRIDGE_BASE_URL=https://remote-control.claude-code-best.win/ CLAUDE_BRIDGE_OAUTH_TOKEN=test-my-key ccb --remote-control # 我们有自部署的远程控制
 ```
 
+> **安装/更新失败？** 先 `npm rm -g claude-code-best` 清理旧版本，再 `npm i -g claude-code-best@latest`。仍失败则指定版本号：`npm i -g claude-code-best@<版本号>`
+
 ## ⚡ 快速开始(源码版)
 
 ### ⚙️ 环境要求

package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-best",
-  "version": "1.10.4",
+  "version": "1.10.8",
   "description": "Reverse-engineered Anthropic Claude Code CLI — interactive AI coding assistant in the terminal",
   "type": "module",
   "author": "claude-code-best <claude-code-best@proton.me>",

packages/builtin-tools/src/tools/FileEditTool/__tests__/utils.test.ts

@@ -106,6 +106,84 @@ describe("findActualString", () => {
     const result = findActualString("hello", "");
     expect(result).toBe("");
   });
+
+  // ── Tab/space normalization (Bug #2 reproduction) ──
+
+  test("finds match when search uses spaces but file uses tabs", () => {
+    // File content uses Tab indentation
+    const fileContent = "\tif (x) {\n\t\treturn 1;\n\t}";
+    // User copies from Read output which renders tabs as spaces
+    const searchWithSpaces = "    if (x) {\n        return 1;\n    }";
+    const result = findActualString(fileContent, searchWithSpaces);
+    expect(result).not.toBeNull();
+    expect(result).toBe(fileContent);
+  });
+
+  test("finds match when search mixes tabs and spaces inconsistently", () => {
+    const fileContent = "\tconst x = 1; // comment";
+    const searchMixed = "    const x = 1; // comment";
+    const result = findActualString(fileContent, searchMixed);
+    expect(result).not.toBeNull();
+  });
+
+  test("finds match for single-line tab-to-space mismatch", () => {
+    const fileContent = "\t\torder_price = NormalizeDouble(ask, digits);";
+    const searchSpaces = "        order_price = NormalizeDouble(ask, digits);";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+  });
+
+  // ── CJK / UTF-8 characters (Bug #1 reproduction) ──
+
+  test("finds match with CJK characters in content", () => {
+    const fileContent = "input int x = 620; // 止盈点数(点) — 32个pip=320点";
+    const result = findActualString(fileContent, fileContent);
+    expect(result).toBe(fileContent);
+  });
+
+  test("finds match with CJK characters when tab/space differs", () => {
+    const fileContent = "\t// 向上突破 → Sell Limit (逆方向做空)";
+    const searchSpaces = "    // 向上突破 → Sell Limit (逆方向做空)";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+    expect(result).toBe(fileContent);
+  });
+
+  // ── Multiline with tabs + CJK (combined Bug #1 + #2) ──
+
+  test("finds multiline match with tabs and CJK characters", () => {
+    const fileContent = "\tif(effective_dir == BREAKOUT_UP)\n\t\t{\n\t\t\t// 向上突破\n\t\t}";
+    const searchSpaces = "    if(effective_dir == BREAKOUT_UP)\n        {\n            // 向上突破\n        }";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+    expect(result).toBe(fileContent);
+  });
+
+  // ── Returned string must be a valid substring of fileContent ──
+
+  test("returned string from tab match is a real substring of fileContent", () => {
+    const fileContent = "prefix\n\t\tindented code\nsuffix";
+    const searchSpaces = "prefix\n        indented code\nsuffix";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+    expect(fileContent.includes(result!)).toBe(true);
+  });
+
+  test("returned string from partial tab match is a real substring", () => {
+    const fileContent = "line1\n\tif (x) {\n\t\tdoStuff();\n\t}\nline5";
+    const searchSpaces = "    if (x) {\n        doStuff();\n    }";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+    expect(fileContent.includes(result!)).toBe(true);
+  });
+
+  test("tab match with mixed indentation levels", () => {
+    const fileContent = "class Foo {\n\t\tmethod1() {\n\t\t\treturn 42;\n\t\t}\n}";
+    const searchSpaces = "class Foo {\n        method1() {\n            return 42;\n        }\n}";
+    const result = findActualString(fileContent, searchSpaces);
+    expect(result).not.toBeNull();
+    expect(fileContent.includes(result!)).toBe(true);
+  });
 });
 
 // ─── preserveQuoteStyle ─────────────────────────────────────────────────

packages/builtin-tools/src/tools/FileEditTool/utils.ts

@@ -63,9 +63,26 @@ export function stripTrailingWhitespace(str: string): string {
   return result
 }
 
+/**
+ * Normalizes whitespace for fuzzy matching by converting tabs to spaces
+ * and collapsing leading whitespace on each line to a canonical form.
+ * This handles the case where Read tool output renders tabs as spaces,
+ * so users copy spaces from the output but the file actually has tabs.
+ */
+function normalizeWhitespace(str: string): string {
+  return str.replace(/\t/g, '    ')
+}
+
 /**
  * Finds the actual string in the file content that matches the search string,
- * accounting for quote normalization
+ * accounting for quote normalization and tab/space differences.
+ *
+ * Matching cascade:
+ * 1. Exact match
+ * 2. Quote normalization (curly → straight quotes)
+ * 3. Tab/space normalization (tabs ↔ spaces in leading whitespace)
+ * 4. Quote + tab/space normalization combined
+ *
  * @param fileContent The file content to search in
  * @param searchString The string to search for
  * @returns The actual string found in the file, or null if not found
@@ -89,9 +106,92 @@ export function findActualString(
     return fileContent.substring(searchIndex, searchIndex + searchString.length)
   }
 
+  // Try with tab/space normalization — handles the case where Read output
+  // renders tabs as spaces and the user copies the rendered version
+  const wsNormalizedFile = normalizeWhitespace(fileContent)
+  const wsNormalizedSearch = normalizeWhitespace(searchString)
+
+  const wsSearchIndex = wsNormalizedFile.indexOf(wsNormalizedSearch)
+  if (wsSearchIndex !== -1) {
+    // Map the match position back to the original file content.
+    // We need to find the corresponding range in the original string.
+    return mapNormalizedMatchBackToFile(fileContent, wsNormalizedFile, wsSearchIndex, wsNormalizedSearch.length)
+  }
+
+  // Try combined: quote normalization + tab/space normalization
+  const combinedFile = normalizeWhitespace(normalizedFile)
+  const combinedSearch = normalizeWhitespace(normalizedSearch)
+
+  const combinedIndex = combinedFile.indexOf(combinedSearch)
+  if (combinedIndex !== -1) {
+    return mapNormalizedMatchBackToFile(fileContent, combinedFile, combinedIndex, combinedSearch.length)
+  }
+
   return null
 }
 
+/**
+ * Given a match found in a normalized version of fileContent, map the match
+ * position back to the original fileContent and extract the corresponding
+ * substring.
+ *
+ * Strategy: walk through both strings character by character, building a
+ * mapping from normalized offset to original offset. When a tab is expanded
+ * to 4 spaces in the normalized version, the normalized offset advances by 4
+ * while the original offset advances by 1.
+ */
+function mapNormalizedMatchBackToFile(
+  fileContent: string,
+  normalizedFile: string,
+  normalizedStart: number,
+  normalizedLength: number,
+): string {
+  // Build a sparse mapping from normalized position → original position.
+  // We only need to map the range [normalizedStart, normalizedStart + normalizedLength].
+  let normPos = 0
+  let origPos = 0
+  let origStart = -1
+  let origEnd = -1
+
+  while (origPos < fileContent.length && normPos <= normalizedStart + normalizedLength) {
+    if (normPos === normalizedStart) {
+      origStart = origPos
+    }
+    if (normPos === normalizedStart + normalizedLength) {
+      origEnd = origPos
+      break
+    }
+
+    const origChar = fileContent[origPos]!
+    if (origChar === '\t') {
+      // Tab expands to 4 spaces in normalized version
+      const nextNormPos = normPos + 4
+      // If normalizedStart falls within this expanded tab, snap to origPos
+      if (normPos < normalizedStart && nextNormPos > normalizedStart && origStart === -1) {
+        origStart = origPos
+      }
+      if (normPos < normalizedStart + normalizedLength && nextNormPos > normalizedStart + normalizedLength && origEnd === -1) {
+        origEnd = origPos + 1
+      }
+      normPos = nextNormPos
+      origPos++
+    } else {
+      normPos++
+      origPos++
+    }
+  }
+
+  // Fallback: if we couldn't map precisely, use character-count heuristic
+  if (origStart === -1) origStart = 0
+  if (origEnd === -1) {
+    // Approximate: use the ratio of original to normalized length
+    const ratio = fileContent.length / normalizedFile.length
+    origEnd = Math.round(origStart + normalizedLength * ratio)
+  }
+
+  return fileContent.substring(origStart, origEnd)
+}
+
 /**
  * When old_string matched via quote normalization (curly quotes in file,
  * straight quotes from model), apply the same curly quote style to new_string

scripts/defines.ts

@@ -68,7 +68,7 @@ export const DEFAULT_BUILD_FEATURES = [
     'DIRECT_CONNECT',              // 直连模式（claude server / claude open）
     // Skill search & learning
     'EXPERIMENTAL_SKILL_SEARCH',   // 实验性技能搜索（DiscoverSkills）
-    'SKILL_LEARNING',              // projectContext cache 无淘汰机制（非 GB 级主因）
+    // 'SKILL_LEARNING',              // projectContext cache 无淘汰机制（非 GB 级主因）
     // P3: poor mode
     'POOR',                        // 穷鬼模式，跳过 extract_memories/prompt_suggestion 减少消耗
     // Team Memory

src/components/Message.tsx

@@ -77,6 +77,8 @@ export type Props = {
   lastThinkingBlockId?: string | null
   /** UUID of the latest user bash output message (for auto-expanding) */
   latestBashOutputUUID?: string | null
+  /** Whether to collapse diff display for this message */
+  shouldCollapseDiffs?: boolean
 }
 
 function MessageImpl({
@@ -99,6 +101,7 @@ function MessageImpl({
   isUserContinuation = false,
   lastThinkingBlockId,
   latestBashOutputUUID,
+  shouldCollapseDiffs,
 }: Props): React.ReactNode {
   switch (message.type) {
     case 'attachment':
@@ -181,6 +184,7 @@ function MessageImpl({
               isUserContinuation={isUserContinuation}
               lookups={lookups}
               isTranscriptMode={isTranscriptMode}
+              shouldCollapseDiffs={shouldCollapseDiffs}
             />
           ))}
         </Box>
@@ -293,6 +297,7 @@ function UserMessage({
   isUserContinuation,
   lookups,
   isTranscriptMode,
+  shouldCollapseDiffs,
 }: {
   message: NormalizedUserMessage
   addMargin: boolean
@@ -309,6 +314,7 @@ function UserMessage({
   isUserContinuation: boolean
   lookups: ReturnType<typeof buildMessageLookups>
   isTranscriptMode: boolean
+  shouldCollapseDiffs?: boolean
 }): React.ReactNode {
   const { columns } = useTerminalSize()
   switch (param.type) {
@@ -344,6 +350,7 @@ function UserMessage({
           verbose={verbose}
           width={columns - 5}
           isTranscriptMode={isTranscriptMode}
+          shouldCollapseDiffs={shouldCollapseDiffs}
         />
       )
     default:

src/components/MessageRow.tsx

@@ -55,6 +55,7 @@ export type Props = {
   columns: number
   isLoading: boolean
   lookups: ReturnType<typeof buildMessageLookups>
+  shouldCollapseDiffs?: boolean
 }
 
 /**
@@ -141,6 +142,7 @@ function MessageRowImpl({
   columns,
   isLoading,
   lookups,
+  shouldCollapseDiffs,
 }: Props): React.ReactNode {
   const isTranscriptMode = screen === 'transcript'
   const isGrouped = msg.type === 'grouped_tool_use'
@@ -221,6 +223,7 @@ function MessageRowImpl({
       isUserContinuation={isUserContinuation}
       lastThinkingBlockId={lastThinkingBlockId}
       latestBashOutputUUID={latestBashOutputUUID}
+      shouldCollapseDiffs={shouldCollapseDiffs}
     />
   )
   // OffscreenFreeze: the outer React.memo already bails for static messages,

src/components/Messages.tsx

@@ -814,6 +814,12 @@ const MessagesImpl = ({
           streamingToolUseIDs,
         ))
 
+    // Collapse diffs for messages beyond the latest N messages.
+    // verbose (ctrl+o) overrides and always shows full diffs.
+    const DIFF_COLLAPSE_DISTANCE = 0
+    const shouldCollapseDiffs =
+      renderableMessages.length - 1 - index > DIFF_COLLAPSE_DISTANCE
+
     const k = messageKey(msg)
     const row = (
       <MessageRow
@@ -838,6 +844,7 @@ const MessagesImpl = ({
         columns={columns}
         isLoading={isLoading}
         lookups={lookups}
+        shouldCollapseDiffs={shouldCollapseDiffs}
       />
     )
 

src/components/messages/UserToolResultMessage/UserToolResultMessage.tsx

@@ -27,6 +27,7 @@ type Props = {
   verbose: boolean
   width: number | string
   isTranscriptMode?: boolean
+  shouldCollapseDiffs?: boolean
 }
 
 export function UserToolResultMessage({
@@ -39,6 +40,7 @@ export function UserToolResultMessage({
   verbose,
   width,
   isTranscriptMode,
+  shouldCollapseDiffs,
 }: Props): React.ReactNode {
   const toolUse = useGetToolFromMessages(param.tool_use_id, tools, lookups)
   if (!toolUse) {
@@ -96,6 +98,7 @@ export function UserToolResultMessage({
       verbose={verbose}
       width={width}
       isTranscriptMode={isTranscriptMode}
+      shouldCollapseDiffs={shouldCollapseDiffs}
     />
   )
 }

src/components/messages/UserToolResultMessage/UserToolSuccessMessage.tsx

@@ -33,6 +33,7 @@ type Props = {
   verbose: boolean
   width: number | string
   isTranscriptMode?: boolean
+  shouldCollapseDiffs?: boolean
 }
 
 export function UserToolSuccessMessage({
@@ -46,6 +47,7 @@ export function UserToolSuccessMessage({
   verbose,
   width,
   isTranscriptMode,
+  shouldCollapseDiffs,
 }: Props): React.ReactNode {
   const [theme] = useTheme()
   // Hook stays inside feature() ternary so external builds don't pay a
@@ -83,12 +85,16 @@ export function UserToolSuccessMessage({
   }
   const toolResult = parsedOutput?.data ?? message.toolUseResult
 
+  // Collapse diff display for old messages (verbose/ctrl+o overrides)
+  const effectiveStyle =
+    shouldCollapseDiffs && !verbose ? 'condensed' : style
+
   const renderedMessage =
     tool.renderToolResultMessage?.(
       toolResult as never,
       filterToolProgressMessages(progressMessagesForMessage),
       {
-        style,
+        style: effectiveStyle,
         theme,
         tools,
         verbose,

src/main.tsx

@@ -6907,6 +6907,9 @@ async function logTenguInit({
 			allowDangerouslySkipPermissionsPassed,
 			thinkingType:
 				thinkingConfig.type as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+			...(thinkingConfig.type === "enabled" && {
+				thinkingBudgetTokens: thinkingConfig.budgetTokens,
+			}),
 			...(systemPromptFlag && {
 				systemPromptFlag:
 					systemPromptFlag as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,

src/services/AgentSummary/__tests__/agentSummary.test.ts

@@ -109,6 +109,10 @@ describe('startAgentSummarization', () => {
     lastTimerHandle = undefined
   })
 
+  function expectDebugLogContaining(fragment: string): void {
+    expect(debugLogs.some(message => message.includes(fragment))).toBe(true)
+  }
+
   test('summarizes bounded transcript once and skips unchanged fingerprints', async () => {
     handle = startTestSummarization()
 
@@ -157,7 +161,7 @@ describe('startAgentSummarization', () => {
 
     expect(forkCalls).toEqual([])
     expect(updateCalls).toEqual([])
-    expect(debugLogs).toContain(
+    expectDebugLogContaining(
       '[AgentSummary] Skipping summary for task-1: no bounded context available',
     )
   })
@@ -171,7 +175,7 @@ describe('startAgentSummarization', () => {
 
     expect(forkCalls).toEqual([])
     expect(updateCalls).toEqual([])
-    expect(debugLogs).toContain(
+    expectDebugLogContaining(
       '[AgentSummary] Skipping summary for task-1: not enough messages (2)',
     )
   })
@@ -188,9 +192,7 @@ describe('startAgentSummarization', () => {
 
     expect(forkCalls).toEqual([])
     expect(updateCalls).toEqual([])
-    expect(debugLogs).toContain(
-      '[AgentSummary] Skipping summary — poor mode active',
-    )
+    expectDebugLogContaining('[AgentSummary] Skipping summary — poor mode active')
     expect(scheduledCount).toBe(initialScheduledCount + 1)
     expect(lastTimerHandle).not.toBe(initialTimerHandle)
   })
@@ -220,9 +222,7 @@ describe('startAgentSummarization', () => {
 
     handle.stop()
 
-    expect(debugLogs).toContain(
-      '[AgentSummary] Stopping summarization for task-1',
-    )
+    expectDebugLogContaining('[AgentSummary] Stopping summarization for task-1')
     expect(clearedHandles).toEqual([pendingHandle])
   })
 })

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 => {

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/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,

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 +78,16 @@ export function recordLLMObservation(
     endTime?: Date
     completionStartTime?: Date
     tools?: unknown
+    /** Thinking depth configuration used for this request.
+     * Accepts the full API thinking config object. Fields:
+     * - type: thinking mode ("enabled", "adaptive", "disabled")
+     * - budget_tokens (snake_case, from Anthropic API) or budgetTokens (camelCase)
+     */
+    thinking?: {
+      type: string
+      budget_tokens?: number
+      budgetTokens?: number
+    }
   },
 ): void {
   if (!rootSpan || !isLangfuseEnabled()) return
@@ -97,6 +107,7 @@ export function recordLLMObservation(
         metadata: {
           provider: params.provider,
           model: params.model,
+          ...(params.thinking && { thinking: params.thinking }),
         },
         ...(params.completionStartTime && { completionStartTime: params.completionStartTime }),
       },

src/services/skillLearning/agentGenerator.ts

@@ -122,6 +122,7 @@ function buildAgentContent(params: {
     '',
     instincts
       .flatMap(instinct => instinct.evidence.map(evidence => `- ${evidence}`))
+      .slice(0, 20)
       .join('\n'),
     '',
   ].join('\n')

src/services/skillLearning/instinctParser.ts

@@ -35,15 +35,18 @@ export function createInstinct(
   })
 }
 
+const MAX_EVIDENCE_ENTRIES = 10
+
 export function normalizeInstinct(instinct: StoredInstinct): StoredInstinct {
+  const uniqueEvidence = Array.from(new Set(instinct.evidence.filter(Boolean)))
   return {
     ...instinct,
     id: instinct.id || buildInstinctId(instinct.trigger, instinct.action),
     confidence: clampConfidence(instinct.confidence),
-    evidence: Array.from(new Set(instinct.evidence.filter(Boolean))),
+    evidence: uniqueEvidence.slice(-MAX_EVIDENCE_ENTRIES),
     evidenceOutcome: instinct.evidenceOutcome,
     observationIds: instinct.observationIds
-      ? Array.from(new Set(instinct.observationIds))
+      ? Array.from(new Set(instinct.observationIds)).slice(-20)
       : undefined,
   }
 }

src/services/skillLearning/skillGenerator.ts

@@ -12,6 +12,9 @@ import {
 import type { LearnedSkillDraft, SkillLearningScope } from './types.js'
 
 export const DUPLICATE_SKILL_OVERLAP_THRESHOLD = 0.8
+const MAX_EVIDENCE_LINES_PER_APPEND = 20
+const MAX_EVIDENCE_LINES_IN_SKILL = 20
+const MAX_SKILL_FILE_BYTES = 50_000
 
 export type SkillGeneratorOptions = {
   cwd?: string
@@ -101,20 +104,41 @@ export async function appendInstinctEvidenceToSkill(
   const existing = await readFile(target.path, 'utf8').catch(
     () => target.content,
   )
+
+  // Skip if the file already exceeds the size cap
+  if (Buffer.byteLength(existing, 'utf8') >= MAX_SKILL_FILE_BYTES) {
+    return target.path
+  }
+
+  const allEvidence = instincts.flatMap(instinct =>
+    instinct.evidence.map(evidence => `- ${evidence}`),
+  )
+  const evidenceLines = allEvidence.slice(0, MAX_EVIDENCE_LINES_PER_APPEND)
+  if (evidenceLines.length < allEvidence.length) {
+    evidenceLines.push(
+      `- [... ${allEvidence.length - evidenceLines.length} more evidence entries omitted]`,
+    )
+  }
+
   const now = new Date().toISOString()
   const block = [
     '',
     `## Learned evidence (${now})`,
     '',
-    ...instincts.flatMap(instinct =>
-      instinct.evidence.map(evidence => `- ${evidence}`),
-    ),
+    ...evidenceLines,
     '',
   ].join('\n')
   const merged = existing.endsWith('\n')
     ? existing + block
     : `${existing}\n${block}`
-  await writeFile(target.path, merged, 'utf8')
+
+  // Final guard: truncate if merged exceeds size cap
+  const finalContent =
+    Buffer.byteLength(merged, 'utf8') > MAX_SKILL_FILE_BYTES
+      ? merged.slice(0, MAX_SKILL_FILE_BYTES)
+      : merged
+
+  await writeFile(target.path, finalContent, 'utf8')
   clearSkillIndexCache()
   return target.path
 }
@@ -191,6 +215,7 @@ function buildSkillContent(params: {
     '',
     instincts
       .flatMap(instinct => instinct.evidence.map(evidence => `- ${evidence}`))
+      .slice(0, MAX_EVIDENCE_LINES_IN_SKILL)
       .join('\n'),
     '',
   ]

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/__tests__/teammateMailbox.test.ts

@@ -365,7 +365,11 @@ describe('teammate mailbox retention', () => {
     if (code === undefined) {
       throw new Error('Expected filesystem errno code')
     }
-    expect(['EISDIR', 'EPERM', 'EACCES']).toContain(code)
+    const expectedCodes =
+      process.platform === 'win32'
+        ? ['EISDIR', 'EPERM', 'EACCES']
+        : ['EISDIR']
+    expect(expectedCodes).toContain(code)
     expect((await stat(inboxPath)).isDirectory()).toBe(true)
   })
 

src/utils/__tests__/udsMessaging.test.ts

@@ -275,7 +275,7 @@ describe('UDS inbox retention', () => {
         '../udsClient.js'
       )
 
-      const error = await sendToUdsSocket(path, 'hello', 50).then(
+      const error = await sendToUdsSocket(path, 'hello', 200).then(
         () => undefined,
         err => err,
       )
@@ -301,6 +301,75 @@ describe('UDS inbox retention', () => {
     }
   })
 
+  test('connectToPeer reports connection failures as peer connection errors', async () => {
+    const path = socketPath('uds-connect-error')
+    const { connectToPeer, UdsPeerConnectionError } = await import(
+      '../udsClient.js'
+    )
+
+    const error = await connectToPeer(path, () => {
+      throw new Error('Unexpected post-connect socket error')
+    }).then(
+      () => undefined,
+      err => err,
+    )
+
+    expect(error).toBeInstanceOf(UdsPeerConnectionError)
+    if (!(error instanceof UdsPeerConnectionError)) {
+      throw new Error('Expected UDS peer connection error')
+    }
+    expect(error.socketPath).toBe(path)
+  })
+
+  test('connectToPeer leaves connected socket lifecycle to the caller', async () => {
+    const path = socketPath('uds-connect-lifecycle')
+    if (process.platform !== 'win32') {
+      await mkdir(dirname(path), { recursive: true })
+    }
+
+    const sockets = new Set<Socket>()
+    const receiver = createServer(socket => {
+      sockets.add(socket)
+      socket.on('close', () => {
+        sockets.delete(socket)
+      })
+    })
+    await new Promise<void>((resolve, reject) => {
+      receiver.on('error', reject)
+      receiver.listen(path, () => resolve())
+    })
+
+    let client: Socket | undefined
+    const socketErrors: Error[] = []
+    try {
+      const { connectToPeer } = await import('../udsClient.js')
+      client = await connectToPeer(
+        path,
+        error => {
+          socketErrors.push(error)
+        },
+        1000,
+      )
+      await new Promise(resolve => setTimeout(resolve, 100))
+
+      expect(client.destroyed).toBe(false)
+      expect(client.listenerCount('error')).toBe(1)
+
+      const socketError = new Error('post-connect failure')
+      client.emit('error', socketError)
+      expect(socketErrors).toEqual([socketError])
+    } finally {
+      client?.destroy()
+      for (const socket of sockets) {
+        socket.destroy()
+      }
+      await closeServer(receiver)
+      if (process.platform !== 'win32') {
+        await unlink(path).catch(() => undefined)
+      }
+    }
+  })
+
   test('sendUdsMessage fails closed before connecting without an auth token', async () => {
     await expect(
       sendUdsMessage(socketPath('no-auth-token'), { type: 'text', data: 'x' }),

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)
 

src/utils/udsClient.ts

@@ -266,17 +266,48 @@ export async function sendToUdsSocket(
 
 /**
  * Connect to a peer and return the raw socket for bidirectional communication.
- * The caller is responsible for managing the connection lifecycle.
+ * The caller owns the post-connect lifecycle through onSocketError, which is
+ * attached before the Promise resolves so peer socket errors cannot be
+ * swallowed or surface through a listener handoff window.
+ * Pre-connect failures reject with UdsPeerConnectionError.
+ * This only opens the transport; callers still own any capability handshake.
  */
-export function connectToPeer(socketPath: string): Promise<Socket> {
+export function connectToPeer(
+  socketPath: string,
+  onSocketError: (error: Error) => void,
+  timeoutMs = 5000,
+): Promise<Socket> {
   return new Promise<Socket>((resolve, reject) => {
-    const conn = createConnection(socketPath, () => {
+    const conn = createConnection(socketPath)
+    let settled = false
+    const timeout = setTimeout(
+      fail,
+      timeoutMs,
+      new Error('Connection timed out'),
+    )
+    function cleanupListeners(): void {
+      clearTimeout(timeout)
+      conn.off('error', fail)
+    }
+    function fail(cause: unknown): void {
+      if (settled) {
+        return
+      }
+      settled = true
+      cleanupListeners()
+      conn.destroy()
+      reject(new UdsPeerConnectionError(socketPath, cause))
+    }
+    conn.once('connect', () => {
+      if (settled) {
+        return
+      }
+      settled = true
+      cleanupListeners()
+      conn.on('error', onSocketError)
       resolve(conn)
     })
-    conn.on('error', reject)
-    conn.setTimeout(5000, () => {
-      conn.destroy(new Error('Connection timed out'))
-    })
+    conn.on('error', fail)
   })
 }
 

src/utils/udsMessaging.ts

@@ -557,7 +557,26 @@ export async function startUdsMessaging(
         void (async () => {
           try {
             if (process.platform !== 'win32') {
-              await chmod(path, 0o600)
+              // Restrict socket permissions to owner-only. On macOS with
+              // Node.js v22, the listen callback may fire before the socket
+              // file is visible on disk (observed with nested tmpdir paths).
+              // The parent directory is already 0o700, so skipping chmod when
+              // the file is not yet visible is safe.
+              try {
+                await chmod(path, 0o600)
+              } catch (err: unknown) {
+                if (
+                  !(
+                    err instanceof Error &&
+                    (err as NodeJS.ErrnoException).code === 'ENOENT'
+                  )
+                ) {
+                  throw err
+                }
+                logForDebugging(
+                  `[udsMessaging] chmod skipped: socket file not yet visible at ${path}`,
+                )
+              }
             }
             srv.off('error', rejectBeforeListen)
             srv.on('error', logRuntimeError)