Apply FileRead memory caps

docs/tools/file-operations.mdx

@@ -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

src/query.ts

@@ -492,6 +492,16 @@ async function* queryLoop(
       querySource,
     )
     messagesForQuery = microcompactResult.messages
+    // Release original strings from contentReplacementState.replacements for
+    // tool results whose content was replaced with the cleared message.
+    if (microcompactResult.clearedToolUseIds?.length) {
+      const replacements = toolUseContext?.contentReplacementState?.replacements
+      if (replacements) {
+        for (const id of microcompactResult.clearedToolUseIds) {
+          replacements.delete(id)
+        }
+      }
+    }
     // For cached microcompact (cache editing), defer boundary message until after
     // the API response so we can use actual cache_deleted_input_tokens.
     // Gated behind feature() so the string is eliminated from external builds.

src/services/compact/microCompact.ts

@@ -217,6 +217,10 @@ export type MicrocompactResult = {
   compactionInfo?: {
     pendingCacheEdits?: PendingCacheEdits
   }
+  // Tool use IDs whose content was replaced with the cleared message.
+  // Callers should remove these from contentReplacementState.replacements
+  // to release the original strings from memory.
+  clearedToolUseIds?: string[]
 }
 
 /**
@@ -526,5 +530,5 @@ function maybeTimeBasedMicrocompact(
     notifyCacheDeletion(querySource)
   }
 
-  return { messages: result }
+  return { messages: result, clearedToolUseIds: [...clearSet] }
 }

src/tools/FileReadTool/FileReadTool.ts

@@ -337,9 +337,9 @@ 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.
+  maxResultSizeChars: 100_000,
   strict: true,
   async description() {
     return DESCRIPTION

src/utils/messages.ts

@@ -1364,6 +1364,54 @@ export function buildMessageLookups(
   }
 }
 
+/**
+ * Compute a lightweight structural fingerprint for buildMessageLookups caching.
+ * Only captures information that affects lookup results (types, IDs, counts),
+ * not content. Returns an empty string when the arrays are structurally empty.
+ *
+ * O(n) but allocates only a string — much cheaper than the 8 Maps/Sets that
+ * buildMessageLookups creates on every call.
+ */
+export function computeMessageStructureKey(
+  normalizedMessages: NormalizedMessage[],
+  messages: Message[],
+): string {
+  const parts: string[] = [
+    String(normalizedMessages.length),
+    '|',
+    String(messages.length),
+  ]
+  for (const msg of messages) {
+    parts.push(msg.type[0])
+    if (msg.type === 'assistant') {
+      const aMsg = msg as AssistantMessage
+      const content = aMsg.message?.content
+      if (Array.isArray(content)) {
+        for (const block of content) {
+          if (typeof block !== 'string' && block.type === 'tool_use') {
+            parts.push('t', (block as ToolUseBlock).id)
+          }
+        }
+      }
+    } else if (msg.type === 'user') {
+      const content = (msg as UserMessage).message?.content
+      if (Array.isArray(content)) {
+        for (const block of content) {
+          if (typeof block !== 'string' && block.type === 'tool_result') {
+            parts.push('r', (block as ToolResultBlockParam).tool_use_id)
+          }
+        }
+      }
+    }
+  }
+  for (const msg of normalizedMessages) {
+    if (msg.type === 'progress') {
+      parts.push('p', (msg as ProgressMessage).parentToolUseID as string)
+    }
+  }
+  return parts.join(',')
+}
+
 /** Empty lookups for static rendering contexts that don't need real lookups. */
 export const EMPTY_LOOKUPS: MessageLookups = {
   siblingToolUseIDs: new Map(),

src/utils/toolResultStorage.ts

@@ -56,9 +56,9 @@ export function getPersistenceThreshold(
   toolName: string,
   declaredMaxResultSizeChars: number,
 ): number {
-  // Infinity = hard opt-out. Read self-bounds via maxTokens; persisting its
-  // output to a file the model reads back with Read is circular. Checked
-  // before the GB override so tengu_satin_quoll can't force it back on.
+  // Infinity = hard opt-out (reserved for tools that self-bound via other
+  // mechanisms). Checked before the GB override so tengu_satin_quoll can't
+  // force it back on.
   if (!Number.isFinite(declaredMaxResultSizeChars)) {
     return declaredMaxResultSizeChars
   }
@@ -813,11 +813,12 @@ export async function enforceToolResultBudget(
       continue
     }
 
-    // Tools with maxResultSizeChars: Infinity (Read) — never persist.
-    // Mark as seen (frozen) so the decision sticks across turns. They don't
-    // count toward freshSize; if that lets the group slip under budget and
-    // the wire message is still large, that's the contract — Read's own
-    // maxTokens is the bound, not this wrapper.
+    // Tools with maxResultSizeChars: Infinity — never persist (reserved for
+    // tools that self-bound via other mechanisms). Mark as seen (frozen) so
+    // the decision sticks across turns. They don't count toward freshSize; if
+    // that lets the group slip under budget and the wire message is still
+    // large, that's the contract — the tool's own maxTokens is the bound, not
+    // this wrapper.
     const skipped = fresh.filter(c => shouldSkip(c.toolUseId))
     skipped.forEach(c => state.seenIds.add(c.toolUseId))
     const eligible = fresh.filter(c => !shouldSkip(c.toolUseId))