chore: remove CLAUDE_CODE_MAX_OUTPUT_TOKENS env var handling

No longer needed with the new Claude Agent SDK version.

src/ai/claude-executor.ts

@@ -220,9 +220,7 @@ export async function runClaudePrompt(
   const mcpServers = buildMcpServers(sourceDir, agentName);
 
   // Build env vars to pass to SDK subprocesses
-  const sdkEnv: Record<string, string> = {
-    CLAUDE_CODE_MAX_OUTPUT_TOKENS: process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS || '64000',
-  };
+  const sdkEnv: Record<string, string> = {};
   if (process.env.ANTHROPIC_API_KEY) {
     sdkEnv.ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
   }

src/ai/message-handlers.ts

@@ -166,15 +166,6 @@ function handleStructuredError(
           false // Not retryable - needs code fix
         ),
       };
-    case 'max_output_tokens':
-      return {
-        detected: true,
-        shouldThrow: new PentestError(
-          `Max output tokens reached: ${content.slice(0, 100)}`,
-          'billing',
-          true // Retryable - may succeed with different content
-        ),
-      };
     case 'unknown':
     default:
       return { detected: true };

src/ai/types.ts

@@ -73,7 +73,6 @@ export type SDKAssistantMessageError =
   | 'rate_limit'
   | 'invalid_request'
   | 'server_error'
-  | 'max_output_tokens'
   | 'unknown';
 
 export interface AssistantMessage {