fix: bugs (#885)

* fix: error output truncation (10KB→40KB) and MCP tool bugs

- toolErrors.ts: increase error truncation limit from 10KB to 40KB
  Shell output can be up to 30KB, so 10KB was silently cutting off
  error logs from systemctl, apt, python, etc.

- MCPTool: cache compiled AJV validators (was recompiling every call)
- MCPTool: fix validateInput error message showing [object Object]
- MCPTool: null-guard mapToolResultToToolResultBlockParam
- MCPTool: explicit null check in isResultTruncated
- ReadMcpResourceTool: null-guard mapToolResultToToolResultBlockParam

Tests (84 passing):
- src/utils/toolErrors.test.ts (13 tests)
- src/tools/BashTool/commandSemantics.test.ts (24 tests)
- src/tools/BashTool/utils.test.ts (32 tests)
- src/tools/MCPTool/MCPTool.test.ts (15 tests)

* fix: address review blockers from PR #885

Blocker 1: Fix abort path in callMCPTool
- Previously returned { content: undefined } on AbortError, which masked
  the cancellation and caused mapToolResultToToolResultBlockParam to send
  empty content to the API as if it were a successful result.
- Now converts abort errors to our AbortError class and re-throws, so the
  tool execution framework handles it properly (skips logging, creates
  is_error: true result with [Request interrupted by user for tool use]).

Blocker 2: Fix memory leak in AJV validator cache
- Changed compiledValidatorCache from Map to WeakMap so schemas from
  disconnected/refreshed MCP tools can be garbage collected instead of
  accumulating strong references indefinitely.

Also: null guards now return descriptive indicators instead of empty
strings, making it clear when content is unexpectedly missing.

---------

Co-authored-by: FluxLuFFy <FluxLuFFy@users.noreply.github.com>
Co-authored-by: Fix Bot <fix@openclaw.ai>

src/services/mcp/client.ts

@@ -55,6 +55,7 @@ import { type MCPProgress, MCPTool } from '../../tools/MCPTool/MCPTool.js'
 import { createMcpAuthTool } from '../../tools/McpAuthTool/McpAuthTool.js'
 import { ReadMcpResourceTool } from '../../tools/ReadMcpResourceTool/ReadMcpResourceTool.js'
 import { createAbortController } from '../../utils/abortController.js'
+import { AbortError, isAbortError } from '../../utils/errors.js'
 import { count } from '../../utils/array.js'
 import {
   checkAndRefreshOAuthTokenIfNeeded,
@@ -3283,11 +3284,18 @@ async function callMCPTool({
       }
     }
 
-    // When the users hits esc, avoid logspew
-    if (!(e instanceof Error) || e.name !== 'AbortError') {
-      throw e
+    // When the user hits esc, convert to our AbortError class so the tool
+    // execution framework handles it properly (skips logging, creates
+    // is_error: true result with [Request interrupted by user for tool use]).
+    // Previously this returned { content: undefined }, which masked the
+    // cancellation and caused mapToolResultToToolResultBlockParam to send
+    // empty/undefined content to the API as if it were a successful result.
+    if (isAbortError(e)) {
+      throw new AbortError(
+        e instanceof Error ? e.message : 'Tool execution cancelled',
+      )
     }
-    return { content: undefined }
+    throw e
   } finally {
     // Always clear intervals
     if (progressInterval !== undefined) {