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

Author: 2228293026

CLAUDE.md

@@ -60,9 +60,8 @@ bun run health
 # Check unused exports
 bun run check:unused
 
-# Full check (typecheck + lint + test) — run after completing any task
-bun run test:all
-bun run typecheck
+# Full check (typecheck + lint fix + test) — run after completing any task
+bun run precheck
 
 # Remote Control Server
 bun run rcs

docs/memory-peak-analysis.md

@@ -12,12 +12,12 @@ Claude Code 将文件操作拆分为三个独立工具——这不是功能划
 
 | 工具 | 权限级别 | 核心方法 | 关键属性 |
 |------|---------|---------|---------|
-| **Read** | 只读（免审批） | `isReadOnly() → true` | `maxResultSizeChars: Infinity` |
+| **Read** | 只读（免审批） | `isReadOnly() → true` | `maxResultSizeChars: 100,000` |
 | **Edit** | 写入（需确认） | `checkWritePermissionForTool()` | `maxResultSizeChars: 100,000` |
 | **Write** | 写入（需确认） | `checkWritePermissionForTool()` | `maxResultSizeChars: 100,000` |
 
 <Tip>
-Read 的 `maxResultSizeChars` 是 `Infinity`，但这并不意味着无限制输出——真正的截断发生在 `validateContentTokens()` 中基于 token 预算的动态判定，而非字符数硬限制。
+Read 的 `maxResultSizeChars` 为 100,000（100KB）。超出此阈值的结果会被持久化到磁盘，减少长会话的内存压力。实际的 token 级别截断由 `validateContentTokens()` 动态控制。
 </Tip>
 
 ## FileRead：多模态文件读取引擎

docs/tools/file-operations.mdx

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-best",
-  "version": "1.11.1",
+  "version": "2.0.1",
   "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>",
@@ -65,7 +65,7 @@
     "postinstall": "node scripts/run-parallel.mjs scripts/postinstall.cjs scripts/setup-chrome-mcp.mjs",
     "docs:dev": "npx mintlify dev",
     "typecheck": "tsc --noEmit",
-    "test:all": "bun run typecheck && bun test",
+    "precheck": "bun run typecheck && bun run check:fix && bun test",
     "rcs": "bun run scripts/rcs.ts"
   },
   "dependencies": {

package.json

@@ -119,6 +119,44 @@ export class StylePool {
     this.none = this.intern([])
   }
 
+  private static readonly CACHE_MAX = 1000
+
+  /**
+   * Evict oldest entries from derivative caches when they exceed the limit.
+   * ids/styles are never evicted (id is an array index).
+   */
+  private evictCacheIfNeeded(): void {
+    if (this.transitionCache.size > StylePool.CACHE_MAX) {
+      const keys = this.transitionCache.keys()
+      for (
+        let i = 0;
+        i < this.transitionCache.size - StylePool.CACHE_MAX;
+        i++
+      ) {
+        const k = keys.next().value
+        if (k !== undefined) this.transitionCache.delete(k)
+      }
+    }
+    if (this.inverseCache.size > StylePool.CACHE_MAX) {
+      const keys = this.inverseCache.keys()
+      for (let i = 0; i < this.inverseCache.size - StylePool.CACHE_MAX; i++) {
+        const k = keys.next().value
+        if (k !== undefined) this.inverseCache.delete(k)
+      }
+    }
+    if (this.currentMatchCache.size > StylePool.CACHE_MAX) {
+      const keys = this.currentMatchCache.keys()
+      for (
+        let i = 0;
+        i < this.currentMatchCache.size - StylePool.CACHE_MAX;
+        i++
+      ) {
+        const k = keys.next().value
+        if (k !== undefined) this.currentMatchCache.delete(k)
+      }
+    }
+  }
+
   /**
    * Intern a style and return its ID. Bit 0 of the ID encodes whether the
    * style has a visible effect on space characters (background, inverse,
@@ -136,6 +174,7 @@ export class StylePool {
         (rawId << 1) |
         (styles.length > 0 && hasVisibleSpaceEffect(styles) ? 1 : 0)
       this.ids.set(key, id)
+      this.evictCacheIfNeeded()
     }
     return id
   }

packages/@ant/ink/src/core/screen.ts

@@ -468,7 +468,11 @@ describe('DeepSeek thinking mode (enableThinking)', () => {
     expect(assistant.reasoning_content).toBe('First thought.\nSecond thought.')
   })
 
-  test('skips empty thinking blocks', () => {
+  test('preserves empty thinking blocks as reasoning_content: "" (DeepSeek v4 thinking mode)', () => {
+    // DeepSeek v4 thinking mode sometimes returns reasoning_content: ""
+    // when the model answers directly without reasoning. The empty value
+    // must be echoed back in the next request — otherwise DeepSeek returns
+    // 400 ("reasoning_content ... must be passed back"). See issue #399.
     const result = anthropicMessagesToOpenAI(
       [
         makeUserMsg('question'),
@@ -481,7 +485,23 @@ describe('DeepSeek thinking mode (enableThinking)', () => {
       { enableThinking: true },
     )
     const assistant = result.filter(m => m.role === 'assistant')[0] as any
+    expect(assistant.reasoning_content).toBe('')
+    expect(assistant.content).toBe('Answer.')
+  })
+
+  test('omits reasoning_content when no thinking block is present', () => {
+    // No thinking block at all → no reasoning_content field on the
+    // OpenAI-format assistant message (relevant for non-thinking models).
+    const result = anthropicMessagesToOpenAI(
+      [
+        makeUserMsg('question'),
+        makeAssistantMsg([{ type: 'text', text: 'Answer.' }]),
+      ],
+      [] as any,
+    )
+    const assistant = result.filter(m => m.role === 'assistant')[0] as any
     expect(assistant.reasoning_content).toBeUndefined()
+    expect(assistant.content).toBe('Answer.')
   })
 
   // ── fix: reorder tool and user messages for OpenAI API compatibility (#168) ──

packages/@ant/model-provider/src/shared/__tests__/openaiConvertMessages.test.ts

@@ -439,6 +439,54 @@ describe('thinking support (reasoning_content)', () => {
     expect(blockStarts[1].content_block.type).toBe('tool_use')
   })
 
+  test('opens thinking block on empty reasoning_content (DeepSeek v4 direct-answer)', async () => {
+    // DeepSeek v4 thinking mode sometimes streams reasoning_content: ""
+    // before answering directly. We must still open a thinking block so the
+    // resulting assistant message carries an (empty) thinking block — that
+    // round-trips back as reasoning_content: "" in the next request,
+    // satisfying DeepSeek's requirement (see issue #399).
+    const events = await collectEvents([
+      makeChunk({
+        choices: [
+          {
+            index: 0,
+            delta: { reasoning_content: '' },
+            finish_reason: null,
+          },
+        ],
+      }),
+      makeChunk({
+        choices: [
+          {
+            index: 0,
+            delta: { content: 'Direct answer.' },
+            finish_reason: null,
+          },
+        ],
+      }),
+      makeChunk({
+        choices: [{ index: 0, delta: {}, finish_reason: 'stop' }],
+      }),
+    ])
+
+    // A thinking block was opened (and closed before the text block starts)
+    const blockStarts = events.filter(
+      e => e.type === 'content_block_start',
+    ) as any[]
+    expect(blockStarts.length).toBe(2)
+    expect(blockStarts[0].content_block.type).toBe('thinking')
+    expect(blockStarts[0].content_block.thinking).toBe('')
+    expect(blockStarts[1].content_block.type).toBe('text')
+
+    // No empty thinking_delta should be emitted — the empty string is
+    // already conveyed by the thinking block's initial value.
+    const thinkingDeltas = events.filter(
+      e =>
+        e.type === 'content_block_delta' && e.delta.type === 'thinking_delta',
+    )
+    expect(thinkingDeltas.length).toBe(0)
+  })
+
   test('thinking block index is 0, text block index is 1', async () => {
     const events = await collectEvents([
       makeChunk({

packages/@ant/model-provider/src/shared/__tests__/openaiStreamAdapter.test.ts

@@ -206,12 +206,14 @@ function convertInternalAssistantMessage(
         },
       })
     } else if (block.type === 'thinking') {
-      // DeepSeek thinking mode: always preserve reasoning_content.
-      // DeepSeek requires reasoning_content to be passed back in subsequent requests,
-      // especially when tool calls are involved (returns 400 if missing).
+      // DeepSeek thinking mode: always preserve reasoning_content,
+      // including the empty-string case. DeepSeek v4 may return
+      // reasoning_content: "" when the model answers directly, and the
+      // empty value must be echoed back in the next request — otherwise
+      // DeepSeek returns 400 ("reasoning_content ... must be passed back").
       const thinkingText = (block as unknown as Record<string, unknown>)
         .thinking
-      if (typeof thinkingText === 'string' && thinkingText) {
+      if (typeof thinkingText === 'string') {
         reasoningParts.push(thinkingText)
       }
     }

packages/@ant/model-provider/src/shared/openaiConvertMessages.ts

@@ -106,9 +106,13 @@ export async function* adaptOpenAIStreamToAnthropic(
     // Skip chunks that carry only usage data (no delta content)
     if (!delta) continue
 
-    // Handle reasoning_content → Anthropic thinking block
+    // Handle reasoning_content → Anthropic thinking block.
+    // Empty string is a valid signal: DeepSeek v4 thinking mode sometimes
+    // returns reasoning_content: "" when the model answers directly. The
+    // empty thinking block must round-trip back to the API in subsequent
+    // requests, otherwise DeepSeek rejects with 400.
     const reasoningContent = (delta as any).reasoning_content
-    if (reasoningContent != null && reasoningContent !== '') {
+    if (reasoningContent != null) {
       if (!thinkingBlockOpen) {
         currentContentIndex++
         thinkingBlockOpen = true
@@ -125,14 +129,16 @@ export async function* adaptOpenAIStreamToAnthropic(
         } as BetaRawMessageStreamEvent
       }
 
-      yield {
-        type: 'content_block_delta',
-        index: currentContentIndex,
-        delta: {
-          type: 'thinking_delta',
-          thinking: reasoningContent,
-        },
-      } as BetaRawMessageStreamEvent
+      if (reasoningContent !== '') {
+        yield {
+          type: 'content_block_delta',
+          index: currentContentIndex,
+          delta: {
+            type: 'thinking_delta',
+            thinking: reasoningContent,
+          },
+        } as BetaRawMessageStreamEvent
+      }
     }
 
     // Handle text content

packages/@ant/model-provider/src/shared/openaiStreamAdapter.ts

@@ -337,9 +337,10 @@ export type Output = z.infer<OutputSchema>
 export const FileReadTool = buildTool({
   name: FILE_READ_TOOL_NAME,
   searchHint: 'read files, images, PDFs, notebooks',
-  // Output is bounded by maxTokens (validateContentTokens). Persisting to a
-  // file the model reads back with Read is circular — never persist.
-  maxResultSizeChars: Infinity,
+  // Output is bounded by maxTokens (validateContentTokens). Results exceeding
+  // 100KB are persisted to disk (reducing memory pressure in long sessions)
+  // rather than kept in the message array indefinitely.
+  maxResultSizeChars: 100_000,
   strict: true,
   async description() {
     return DESCRIPTION