fix(chat): increase SDK buffer limit and add jq

- Add sdk_max_buffer_size config option (default 10MB, was 1MB)
- Pass max_buffer_size to ClaudeAgentOptions to prevent crashes on large tool outputs
- Install jq in Dockerfile for JSON processing capabilities

Fixes AUTOGPT-SERVER-7V2

autogpt_platform/backend/Dockerfile

@@ -62,12 +62,13 @@ ENV POETRY_HOME=/opt/poetry \
     DEBIAN_FRONTEND=noninteractive
 ENV PATH=/opt/poetry/bin:$PATH
 
-# Install Python, FFmpeg, and ImageMagick (required for video processing blocks)
+# Install Python, FFmpeg, ImageMagick, and CLI tools for agent use
 RUN apt-get update && apt-get install -y \
     python3.13 \
     python3-pip \
     ffmpeg \
     imagemagick \
+    jq \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy only necessary files from builder

autogpt_platform/backend/backend/api/features/chat/config.py

@@ -97,6 +97,11 @@ class ChatConfig(BaseSettings):
         default=True,
         description="Use Claude Agent SDK for chat completions",
     )
+    sdk_max_buffer_size: int = Field(
+        default=10 * 1024 * 1024,  # 10MB (default SDK is 1MB)
+        description="Max buffer size in bytes for SDK JSON message parsing. "
+        "Increase if tool outputs exceed the limit.",
+    )
 
     # Extended thinking configuration for Claude models
     thinking_enabled: bool = Field(

autogpt_platform/backend/backend/api/features/chat/sdk/service.py

@@ -290,6 +290,7 @@ async def stream_chat_completion_sdk(
                 allowed_tools=COPILOT_TOOL_NAMES,
                 hooks=create_security_hooks(user_id, sdk_cwd=sdk_cwd),  # type: ignore[arg-type]
                 cwd=sdk_cwd,
+                max_buffer_size=config.sdk_max_buffer_size,
             )
 
             adapter = SDKResponseAdapter(message_id=message_id)