feat(platform): update OpenAI calls to use responses.create for reasoning models

Adds conditional support for OpenAI's Responses API for reasoning models
(o1, o3, etc.) that are incompatible with chat.completions.create.

Changes:
- Add openai_responses.py helper module with:
  - requires_responses_api() for model detection (exact matching)
  - convert_tools_to_responses_format() for tool format conversion
  - extract_responses_tool_calls() for tool call extraction
  - extract_usage() for normalized token usage
  - extract_responses_content() for content extraction
  - extract_responses_reasoning() for reasoning extraction
- Update llm.py OpenAI provider to conditionally use responses.create
  for reasoning models while keeping chat.completions.create for others
- Add unit tests for helper functions

Resolves: #11624
Linear: OPEN-2911

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/dummy.py

@@ -0,0 +1,154 @@
+"""Dummy Agent Generator for testing.
+
+Returns mock responses matching the format expected from the external service.
+Enable via AGENTGENERATOR_USE_DUMMY=true in settings.
+
+WARNING: This is for testing only. Do not use in production.
+"""
+
+import asyncio
+import logging
+import uuid
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+# Dummy decomposition result (instructions type)
+DUMMY_DECOMPOSITION_RESULT: dict[str, Any] = {
+    "type": "instructions",
+    "steps": [
+        {
+            "description": "Get input from user",
+            "action": "input",
+            "block_name": "AgentInputBlock",
+        },
+        {
+            "description": "Process the input",
+            "action": "process",
+            "block_name": "TextFormatterBlock",
+        },
+        {
+            "description": "Return output to user",
+            "action": "output",
+            "block_name": "AgentOutputBlock",
+        },
+    ],
+}
+
+# Block IDs from backend/blocks/io.py
+AGENT_INPUT_BLOCK_ID = "c0a8e994-ebf1-4a9c-a4d8-89d09c86741b"
+AGENT_OUTPUT_BLOCK_ID = "363ae599-353e-4804-937e-b2ee3cef3da4"
+
+
+def _generate_dummy_agent_json() -> dict[str, Any]:
+    """Generate a minimal valid agent JSON for testing."""
+    input_node_id = str(uuid.uuid4())
+    output_node_id = str(uuid.uuid4())
+
+    return {
+        "id": str(uuid.uuid4()),
+        "version": 1,
+        "is_active": True,
+        "name": "Dummy Test Agent",
+        "description": "A dummy agent generated for testing purposes",
+        "nodes": [
+            {
+                "id": input_node_id,
+                "block_id": AGENT_INPUT_BLOCK_ID,
+                "input_default": {
+                    "name": "input",
+                    "title": "Input",
+                    "description": "Enter your input",
+                    "placeholder_values": [],
+                },
+                "metadata": {"position": {"x": 0, "y": 0}},
+            },
+            {
+                "id": output_node_id,
+                "block_id": AGENT_OUTPUT_BLOCK_ID,
+                "input_default": {
+                    "name": "output",
+                    "title": "Output",
+                    "description": "Agent output",
+                    "format": "{output}",
+                },
+                "metadata": {"position": {"x": 400, "y": 0}},
+            },
+        ],
+        "links": [
+            {
+                "id": str(uuid.uuid4()),
+                "source_id": input_node_id,
+                "sink_id": output_node_id,
+                "source_name": "result",
+                "sink_name": "value",
+                "is_static": False,
+            },
+        ],
+    }
+
+
+async def decompose_goal_dummy(
+    description: str,
+    context: str = "",
+    library_agents: list[dict[str, Any]] | None = None,
+) -> dict[str, Any]:
+    """Return dummy decomposition result."""
+    logger.info("Using dummy agent generator for decompose_goal")
+    return DUMMY_DECOMPOSITION_RESULT.copy()
+
+
+async def generate_agent_dummy(
+    instructions: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any]:
+    """Return dummy agent JSON after a simulated delay."""
+    logger.info("Using dummy agent generator for generate_agent (30s delay)")
+    await asyncio.sleep(30)
+    return _generate_dummy_agent_json()
+
+
+async def generate_agent_patch_dummy(
+    update_request: str,
+    current_agent: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any]:
+    """Return dummy patched agent (returns the current agent with updated description)."""
+    logger.info("Using dummy agent generator for generate_agent_patch")
+    patched = current_agent.copy()
+    patched["description"] = (
+        f"{current_agent.get('description', '')} (updated: {update_request})"
+    )
+    return patched
+
+
+async def customize_template_dummy(
+    template_agent: dict[str, Any],
+    modification_request: str,
+    context: str = "",
+) -> dict[str, Any]:
+    """Return dummy customized template (returns template with updated description)."""
+    logger.info("Using dummy agent generator for customize_template")
+    customized = template_agent.copy()
+    customized["description"] = (
+        f"{template_agent.get('description', '')} (customized: {modification_request})"
+    )
+    return customized
+
+
+async def get_blocks_dummy() -> list[dict[str, Any]]:
+    """Return dummy blocks list."""
+    logger.info("Using dummy agent generator for get_blocks")
+    return [
+        {"id": AGENT_INPUT_BLOCK_ID, "name": "AgentInputBlock"},
+        {"id": AGENT_OUTPUT_BLOCK_ID, "name": "AgentOutputBlock"},
+    ]
+
+
+async def health_check_dummy() -> bool:
+    """Always returns healthy for dummy service."""
+    return True

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/service.py

@@ -12,8 +12,19 @@ import httpx
 
 from backend.util.settings import Settings
 
+from .dummy import (
+    customize_template_dummy,
+    decompose_goal_dummy,
+    generate_agent_dummy,
+    generate_agent_patch_dummy,
+    get_blocks_dummy,
+    health_check_dummy,
+)
+
 logger = logging.getLogger(__name__)
 
+_dummy_mode_warned = False
+
 
 def _create_error_response(
     error_message: str,
@@ -90,10 +101,26 @@ def _get_settings() -> Settings:
     return _settings
 
 
-def is_external_service_configured() -> bool:
-    """Check if external Agent Generator service is configured."""
+def _is_dummy_mode() -> bool:
+    """Check if dummy mode is enabled for testing."""
+    global _dummy_mode_warned
     settings = _get_settings()
-    return bool(settings.config.agentgenerator_host)
+    is_dummy = bool(settings.config.agentgenerator_use_dummy)
+    if is_dummy and not _dummy_mode_warned:
+        logger.warning(
+            "Agent Generator running in DUMMY MODE - returning mock responses. "
+            "Do not use in production!"
+        )
+        _dummy_mode_warned = True
+    return is_dummy
+
+
+def is_external_service_configured() -> bool:
+    """Check if external Agent Generator service is configured (or dummy mode)."""
+    settings = _get_settings()
+    return bool(settings.config.agentgenerator_host) or bool(
+        settings.config.agentgenerator_use_dummy
+    )
 
 
 def _get_base_url() -> str:
@@ -137,6 +164,9 @@ async def decompose_goal_external(
         - {"type": "error", "error": "...", "error_type": "..."} on error
         Or None on unexpected error
     """
+    if _is_dummy_mode():
+        return await decompose_goal_dummy(description, context, library_agents)
+
     client = _get_client()
 
     if context:
@@ -226,6 +256,11 @@ async def generate_agent_external(
     Returns:
         Agent JSON dict, {"status": "accepted"} for async, or error dict {"type": "error", ...} on error
     """
+    if _is_dummy_mode():
+        return await generate_agent_dummy(
+            instructions, library_agents, operation_id, task_id
+        )
+
     client = _get_client()
 
     # Build request payload
@@ -297,6 +332,11 @@ async def generate_agent_patch_external(
     Returns:
         Updated agent JSON, clarifying questions dict, {"status": "accepted"} for async, or error dict on error
     """
+    if _is_dummy_mode():
+        return await generate_agent_patch_dummy(
+            update_request, current_agent, library_agents, operation_id, task_id
+        )
+
     client = _get_client()
 
     # Build request payload
@@ -383,6 +423,11 @@ async def customize_template_external(
     Returns:
         Customized agent JSON, clarifying questions dict, or error dict on error
     """
+    if _is_dummy_mode():
+        return await customize_template_dummy(
+            template_agent, modification_request, context
+        )
+
     client = _get_client()
 
     request = modification_request
@@ -445,6 +490,9 @@ async def get_blocks_external() -> list[dict[str, Any]] | None:
     Returns:
         List of block info dicts or None on error
     """
+    if _is_dummy_mode():
+        return await get_blocks_dummy()
+
     client = _get_client()
 
     try:
@@ -478,6 +526,9 @@ async def health_check() -> bool:
     if not is_external_service_configured():
         return False
 
+    if _is_dummy_mode():
+        return await health_check_dummy()
+
     client = _get_client()
 
     try:

autogpt_platform/backend/backend/blocks/llm.py

@@ -32,6 +32,14 @@ from backend.data.model import (
 from backend.integrations.providers import ProviderName
 from backend.util import json
 from backend.util.logging import TruncatedLogger
+from backend.util.openai_responses import (
+    convert_tools_to_responses_format,
+    extract_responses_content,
+    extract_responses_reasoning,
+    extract_responses_tool_calls,
+    extract_usage,
+    requires_responses_api,
+)
 from backend.util.prompt import compress_context, estimate_token_count
 from backend.util.text import TextFormatter
 
@@ -659,38 +667,72 @@ async def llm_call(
     max_tokens = max(min(available_tokens, model_max_output, user_max), 1)
 
     if provider == "openai":
-        tools_param = tools if tools else openai.NOT_GIVEN
         oai_client = openai.AsyncOpenAI(api_key=credentials.api_key.get_secret_value())
-        response_format = None
 
-        parallel_tool_calls = get_parallel_tool_calls_param(
-            llm_model, parallel_tool_calls
-        )
+        # Check if this model requires the Responses API (reasoning models: o1, o3, etc.)
+        if requires_responses_api(llm_model.value):
+            # Use responses.create for reasoning models
+            tools_converted = (
+                convert_tools_to_responses_format(tools) if tools else None
+            )
 
-        if force_json_output:
-            response_format = {"type": "json_object"}
+            response = await oai_client.responses.create(
+                model=llm_model.value,
+                input=prompt,  # type: ignore
+                tools=tools_converted,  # type: ignore
+                max_output_tokens=max_tokens,
+                store=False,  # Don't persist conversations
+            )
 
-        response = await oai_client.chat.completions.create(
-            model=llm_model.value,
-            messages=prompt,  # type: ignore
-            response_format=response_format,  # type: ignore
-            max_completion_tokens=max_tokens,
-            tools=tools_param,  # type: ignore
-            parallel_tool_calls=parallel_tool_calls,
-        )
+            tool_calls = extract_responses_tool_calls(response)
+            reasoning = extract_responses_reasoning(response)
+            content = extract_responses_content(response)
+            prompt_tokens, completion_tokens = extract_usage(response, True)
 
-        tool_calls = extract_openai_tool_calls(response)
-        reasoning = extract_openai_reasoning(response)
+            return LLMResponse(
+                raw_response=response,
+                prompt=prompt,
+                response=content,
+                tool_calls=tool_calls,
+                prompt_tokens=prompt_tokens,
+                completion_tokens=completion_tokens,
+                reasoning=reasoning,
+            )
+        else:
+            # Use chat.completions.create for standard models
+            tools_param = tools if tools else openai.NOT_GIVEN
+            response_format = None
 
-        return LLMResponse(
-            raw_response=response.choices[0].message,
-            prompt=prompt,
-            response=response.choices[0].message.content or "",
-            tool_calls=tool_calls,
-            prompt_tokens=response.usage.prompt_tokens if response.usage else 0,
-            completion_tokens=response.usage.completion_tokens if response.usage else 0,
-            reasoning=reasoning,
-        )
+            parallel_tool_calls = get_parallel_tool_calls_param(
+                llm_model, parallel_tool_calls
+            )
+
+            if force_json_output:
+                response_format = {"type": "json_object"}
+
+            response = await oai_client.chat.completions.create(
+                model=llm_model.value,
+                messages=prompt,  # type: ignore
+                response_format=response_format,  # type: ignore
+                max_completion_tokens=max_tokens,
+                tools=tools_param,  # type: ignore
+                parallel_tool_calls=parallel_tool_calls,
+            )
+
+            tool_calls = extract_openai_tool_calls(response)
+            reasoning = extract_openai_reasoning(response)
+
+            return LLMResponse(
+                raw_response=response.choices[0].message,
+                prompt=prompt,
+                response=response.choices[0].message.content or "",
+                tool_calls=tool_calls,
+                prompt_tokens=response.usage.prompt_tokens if response.usage else 0,
+                completion_tokens=(
+                    response.usage.completion_tokens if response.usage else 0
+                ),
+                reasoning=reasoning,
+            )
     elif provider == "anthropic":
 
         an_tools = convert_openai_tool_fmt_to_anthropic(tools)

autogpt_platform/backend/backend/util/openai_responses.py

@@ -0,0 +1,185 @@
+"""Helpers for OpenAI Responses API migration.
+
+This module provides utilities for conditionally using OpenAI's Responses API
+instead of Chat Completions for reasoning models (o1, o3, etc.) that require it.
+"""
+
+from typing import Any
+
+# Exact model identifiers that require the Responses API.
+# Use exact matching to avoid false positives on future models.
+# NOTE: Update this set when OpenAI releases new reasoning models.
+REASONING_MODELS = frozenset(
+    {
+        # O1 family
+        "o1",
+        "o1-mini",
+        "o1-preview",
+        "o1-2024-12-17",
+        # O3 family
+        "o3",
+        "o3-mini",
+        "o3-2025-04-16",
+        "o3-mini-2025-01-31",
+    }
+)
+
+
+def requires_responses_api(model: str) -> bool:
+    """Check if model requires the Responses API (exact match).
+
+    Args:
+        model: The model identifier string (e.g., "o3-mini", "gpt-4o")
+
+    Returns:
+        True if the model requires responses.create, False otherwise
+    """
+    return model in REASONING_MODELS
+
+
+def convert_tools_to_responses_format(tools: list[dict] | None) -> list[dict]:
+    """Convert Chat Completions tool format to Responses API format.
+
+    The Responses API uses internally-tagged polymorphism (flatter structure)
+    and functions are strict by default.
+
+    Chat Completions format:
+        {"type": "function", "function": {"name": "...", "parameters": {...}}}
+
+    Responses API format:
+        {"type": "function", "name": "...", "parameters": {...}}
+
+    Args:
+        tools: List of tools in Chat Completions format
+
+    Returns:
+        List of tools in Responses API format
+    """
+    if not tools:
+        return []
+
+    converted = []
+    for tool in tools:
+        if tool.get("type") == "function":
+            func = tool.get("function", {})
+            converted.append(
+                {
+                    "type": "function",
+                    "name": func.get("name"),
+                    "description": func.get("description"),
+                    "parameters": func.get("parameters"),
+                    # Note: strict=True is default in Responses API
+                }
+            )
+        else:
+            # Pass through non-function tools as-is
+            converted.append(tool)
+    return converted
+
+
+def extract_responses_tool_calls(response: Any) -> list[dict] | None:
+    """Extract tool calls from Responses API response.
+
+    The Responses API returns tool calls as separate items in the output array
+    with type="function_call".
+
+    Args:
+        response: The Responses API response object
+
+    Returns:
+        List of tool calls in a normalized format, or None if no tool calls
+    """
+    tool_calls = []
+    for item in response.output:
+        if getattr(item, "type", None) == "function_call":
+            tool_calls.append(
+                {
+                    "id": item.call_id,
+                    "type": "function",
+                    "function": {
+                        "name": item.name,
+                        "arguments": item.arguments,
+                    },
+                }
+            )
+    return tool_calls if tool_calls else None
+
+
+def extract_usage(response: Any, is_responses_api: bool) -> tuple[int, int]:
+    """Extract token usage from either API response.
+
+    The Responses API uses different field names for token counts:
+    - Chat Completions: prompt_tokens, completion_tokens
+    - Responses API: input_tokens, output_tokens
+
+    Args:
+        response: The API response object
+        is_responses_api: True if response is from Responses API
+
+    Returns:
+        Tuple of (prompt_tokens, completion_tokens)
+    """
+    if not response.usage:
+        return 0, 0
+
+    if is_responses_api:
+        # Responses API uses different field names
+        return (
+            getattr(response.usage, "input_tokens", 0),
+            getattr(response.usage, "output_tokens", 0),
+        )
+    else:
+        # Chat Completions API
+        return (
+            getattr(response.usage, "prompt_tokens", 0),
+            getattr(response.usage, "completion_tokens", 0),
+        )
+
+
+def extract_responses_content(response: Any) -> str:
+    """Extract text content from Responses API response.
+
+    Args:
+        response: The Responses API response object
+
+    Returns:
+        The text content from the response, or empty string if none
+    """
+    # The SDK provides a helper property
+    if hasattr(response, "output_text"):
+        return response.output_text or ""
+
+    # Fallback: manually extract from output items
+    for item in response.output:
+        if getattr(item, "type", None) == "message":
+            for content in getattr(item, "content", []):
+                if getattr(content, "type", None) == "output_text":
+                    return getattr(content, "text", "")
+    return ""
+
+
+def extract_responses_reasoning(response: Any) -> str | None:
+    """Extract reasoning content from Responses API response.
+
+    Reasoning models return their reasoning process in the response,
+    which can be useful for debugging or display.
+
+    Args:
+        response: The Responses API response object
+
+    Returns:
+        The reasoning text, or None if not present
+    """
+    for item in response.output:
+        if getattr(item, "type", None) == "reasoning":
+            # Reasoning items may have summary or content
+            summary = getattr(item, "summary", [])
+            if summary:
+                # Join summary items if present
+                texts = []
+                for s in summary:
+                    if hasattr(s, "text"):
+                        texts.append(s.text)
+                if texts:
+                    return "\n".join(texts)
+    return None

autogpt_platform/backend/backend/util/openai_responses_test.py

@@ -0,0 +1,155 @@
+"""Tests for OpenAI Responses API helpers."""
+
+import pytest
+
+from backend.util.openai_responses import (
+    REASONING_MODELS,
+    convert_tools_to_responses_format,
+    requires_responses_api,
+)
+
+
+class TestRequiresResponsesApi:
+    """Tests for the requires_responses_api function."""
+
+    def test_o1_models_require_responses_api(self):
+        """O1 family models should require the Responses API."""
+        assert requires_responses_api("o1") is True
+        assert requires_responses_api("o1-mini") is True
+        assert requires_responses_api("o1-preview") is True
+        assert requires_responses_api("o1-2024-12-17") is True
+
+    def test_o3_models_require_responses_api(self):
+        """O3 family models should require the Responses API."""
+        assert requires_responses_api("o3") is True
+        assert requires_responses_api("o3-mini") is True
+        assert requires_responses_api("o3-2025-04-16") is True
+        assert requires_responses_api("o3-mini-2025-01-31") is True
+
+    def test_gpt_models_do_not_require_responses_api(self):
+        """GPT models should NOT require the Responses API."""
+        assert requires_responses_api("gpt-4o") is False
+        assert requires_responses_api("gpt-4o-mini") is False
+        assert requires_responses_api("gpt-4-turbo") is False
+        assert requires_responses_api("gpt-3.5-turbo") is False
+        assert requires_responses_api("gpt-5") is False
+        assert requires_responses_api("gpt-5-mini") is False
+
+    def test_other_models_do_not_require_responses_api(self):
+        """Other provider models should NOT require the Responses API."""
+        assert requires_responses_api("claude-3-opus") is False
+        assert requires_responses_api("llama-3.3-70b") is False
+        assert requires_responses_api("gemini-pro") is False
+
+    def test_empty_string_does_not_require_responses_api(self):
+        """Empty string should not require the Responses API."""
+        assert requires_responses_api("") is False
+
+    def test_exact_matching_no_false_positives(self):
+        """Should not match models that just start with 'o1' or 'o3'."""
+        # These are hypothetical models that start with o1/o3 but aren't
+        # actually reasoning models
+        assert requires_responses_api("o1-turbo-hypothetical") is False
+        assert requires_responses_api("o3-fast-hypothetical") is False
+        assert requires_responses_api("o100") is False
+
+
+class TestConvertToolsToResponsesFormat:
+    """Tests for the convert_tools_to_responses_format function."""
+
+    def test_empty_tools_returns_empty_list(self):
+        """Empty or None tools should return empty list."""
+        assert convert_tools_to_responses_format(None) == []
+        assert convert_tools_to_responses_format([]) == []
+
+    def test_converts_function_tool_format(self):
+        """Should convert Chat Completions function format to Responses format."""
+        chat_completions_tools = [
+            {
+                "type": "function",
+                "function": {
+                    "name": "get_weather",
+                    "description": "Get the weather in a location",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {"type": "string"},
+                        },
+                        "required": ["location"],
+                    },
+                },
+            }
+        ]
+
+        result = convert_tools_to_responses_format(chat_completions_tools)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "function"
+        assert result[0]["name"] == "get_weather"
+        assert result[0]["description"] == "Get the weather in a location"
+        assert result[0]["parameters"] == {
+            "type": "object",
+            "properties": {
+                "location": {"type": "string"},
+            },
+            "required": ["location"],
+        }
+        # Should not have nested "function" key
+        assert "function" not in result[0]
+
+    def test_handles_multiple_tools(self):
+        """Should handle multiple tools."""
+        chat_completions_tools = [
+            {
+                "type": "function",
+                "function": {
+                    "name": "tool_1",
+                    "description": "First tool",
+                    "parameters": {"type": "object", "properties": {}},
+                },
+            },
+            {
+                "type": "function",
+                "function": {
+                    "name": "tool_2",
+                    "description": "Second tool",
+                    "parameters": {"type": "object", "properties": {}},
+                },
+            },
+        ]
+
+        result = convert_tools_to_responses_format(chat_completions_tools)
+
+        assert len(result) == 2
+        assert result[0]["name"] == "tool_1"
+        assert result[1]["name"] == "tool_2"
+
+    def test_passes_through_non_function_tools(self):
+        """Non-function tools should be passed through as-is."""
+        tools = [{"type": "web_search", "config": {"enabled": True}}]
+
+        result = convert_tools_to_responses_format(tools)
+
+        assert result == tools
+
+
+class TestReasoningModelsSet:
+    """Tests for the REASONING_MODELS constant."""
+
+    def test_reasoning_models_is_frozenset(self):
+        """REASONING_MODELS should be a frozenset (immutable)."""
+        assert isinstance(REASONING_MODELS, frozenset)
+
+    def test_contains_expected_models(self):
+        """Should contain all expected reasoning models."""
+        expected = {
+            "o1",
+            "o1-mini",
+            "o1-preview",
+            "o1-2024-12-17",
+            "o3",
+            "o3-mini",
+            "o3-2025-04-16",
+            "o3-mini-2025-01-31",
+        }
+        assert expected.issubset(REASONING_MODELS)

autogpt_platform/backend/backend/util/settings.py

@@ -368,6 +368,10 @@ class Config(UpdateTrackingModel["Config"], BaseSettings):
         default=600,
         description="The timeout in seconds for Agent Generator service requests (includes retries for rate limits)",
     )
+    agentgenerator_use_dummy: bool = Field(
+        default=False,
+        description="Use dummy agent generator responses for testing (bypasses external service)",
+    )
 
     enable_example_blocks: bool = Field(
         default=False,

autogpt_platform/backend/test/agent_generator/test_service.py

@@ -25,6 +25,7 @@ class TestServiceConfiguration:
         """Test that external service is not configured when host is empty."""
         mock_settings = MagicMock()
         mock_settings.config.agentgenerator_host = ""
+        mock_settings.config.agentgenerator_use_dummy = False
 
         with patch.object(service, "_get_settings", return_value=mock_settings):
             assert service.is_external_service_configured() is False

autogpt_platform/frontend/instrumentation-client.ts

@@ -22,6 +22,11 @@ Sentry.init({
 
   enabled: shouldEnable,
 
+  // Suppress cross-origin stylesheet errors from Sentry Replay (rrweb)
+  // serializing DOM snapshots with cross-origin stylesheets
+  // (e.g., from browser extensions or CDN-loaded CSS)
+  ignoreErrors: [/Not allowed to access cross-origin stylesheet/],
+
   // Add optional integrations for additional features
   integrations: [
     Sentry.captureConsoleIntegration(),

autogpt_platform/frontend/src/app/(platform)/copilot/hooks/Untitled

@@ -1,10 +0,0 @@
-import { parseAsString, useQueryState } from "nuqs";
-
-export function useCopilotSessionId() {
-  const [urlSessionId, setUrlSessionId] = useQueryState(
-    "sessionId",
-    parseAsString,
-  );
-
-  return { urlSessionId, setUrlSessionId };
-}

autogpt_platform/frontend/src/app/(platform)/copilot/hooks/useLongRunningToolPolling.ts

@@ -0,0 +1,126 @@
+import { getGetV2GetSessionQueryKey } from "@/app/api/__generated__/endpoints/chat/chat";
+import { useQueryClient } from "@tanstack/react-query";
+import type { UIDataTypes, UIMessage, UITools } from "ai";
+import { useCallback, useEffect, useRef } from "react";
+import { convertChatSessionMessagesToUiMessages } from "../helpers/convertChatSessionToUiMessages";
+
+const OPERATING_TYPES = new Set([
+  "operation_started",
+  "operation_pending",
+  "operation_in_progress",
+]);
+
+const POLL_INTERVAL_MS = 1_500;
+
+/**
+ * Detects whether any message contains a tool part whose output indicates
+ * a long-running operation is still in progress.
+ */
+function hasOperatingTool(
+  messages: UIMessage<unknown, UIDataTypes, UITools>[],
+) {
+  for (const msg of messages) {
+    for (const part of msg.parts) {
+      if (!part.type.startsWith("tool-")) continue;
+      const toolPart = part as { output?: unknown };
+      if (!toolPart.output) continue;
+      const output =
+        typeof toolPart.output === "string"
+          ? safeParse(toolPart.output)
+          : toolPart.output;
+      if (
+        output &&
+        typeof output === "object" &&
+        "type" in output &&
+        OPERATING_TYPES.has((output as { type: string }).type)
+      ) {
+        return true;
+      }
+    }
+  }
+  return false;
+}
+
+function safeParse(value: string): unknown {
+  try {
+    return JSON.parse(value);
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * Polls the session endpoint while any tool is in an "operating" state
+ * (operation_started / operation_pending / operation_in_progress).
+ *
+ * When the session data shows the tool output has changed (e.g. to
+ * agent_saved), it calls `setMessages` with the updated messages.
+ */
+export function useLongRunningToolPolling(
+  sessionId: string | null,
+  messages: UIMessage<unknown, UIDataTypes, UITools>[],
+  setMessages: (
+    updater: (
+      prev: UIMessage<unknown, UIDataTypes, UITools>[],
+    ) => UIMessage<unknown, UIDataTypes, UITools>[],
+  ) => void,
+) {
+  const queryClient = useQueryClient();
+  const intervalRef = useRef<ReturnType<typeof setInterval> | null>(null);
+
+  const stopPolling = useCallback(() => {
+    if (intervalRef.current) {
+      clearInterval(intervalRef.current);
+      intervalRef.current = null;
+    }
+  }, []);
+
+  const poll = useCallback(async () => {
+    if (!sessionId) return;
+
+    // Invalidate the query cache so the next fetch gets fresh data
+    await queryClient.invalidateQueries({
+      queryKey: getGetV2GetSessionQueryKey(sessionId),
+    });
+
+    // Fetch fresh session data
+    const data = queryClient.getQueryData<{
+      status: number;
+      data: { messages?: unknown[] };
+    }>(getGetV2GetSessionQueryKey(sessionId));
+
+    if (data?.status !== 200 || !data.data.messages) return;
+
+    const freshMessages = convertChatSessionMessagesToUiMessages(
+      sessionId,
+      data.data.messages,
+    );
+
+    if (!freshMessages || freshMessages.length === 0) return;
+
+    // Update when the long-running tool completed
+    if (!hasOperatingTool(freshMessages)) {
+      setMessages(() => freshMessages);
+      stopPolling();
+    }
+  }, [sessionId, queryClient, setMessages, stopPolling]);
+
+  useEffect(() => {
+    const shouldPoll = hasOperatingTool(messages);
+
+    // Always clear any previous interval first so we never leak timers
+    // when the effect re-runs due to dependency changes (e.g. messages
+    // updating as the LLM streams text after the tool call).
+    stopPolling();
+
+    if (shouldPoll && sessionId) {
+      intervalRef.current = setInterval(() => {
+        poll();
+      }, POLL_INTERVAL_MS);
+    }
+
+    return () => {
+      stopPolling();
+    };
+  }, [messages, sessionId, poll, stopPolling]);
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/CreateAgent.tsx

@@ -1,24 +1,30 @@
 "use client";
 
-import { WarningDiamondIcon } from "@phosphor-icons/react";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import {
+  BookOpenIcon,
+  CheckFatIcon,
+  PencilSimpleIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
+import NextLink from "next/link";
 import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
 import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
-import { ProgressBar } from "../../components/ProgressBar/ProgressBar";
 import {
   ContentCardDescription,
   ContentCodeBlock,
   ContentGrid,
   ContentHint,
-  ContentLink,
   ContentMessage,
 } from "../../components/ToolAccordion/AccordionContent";
 import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
-import { useAsymptoticProgress } from "../../hooks/useAsymptoticProgress";
 import {
   ClarificationQuestionsCard,
   ClarifyingQuestion,
 } from "./components/ClarificationQuestionsCard";
+import { MiniGame } from "./components/MiniGame/MiniGame";
 import {
   AccordionIcon,
   formatMaybeJson,
@@ -52,7 +58,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
   const icon = <AccordionIcon />;
 
   if (isAgentSavedOutput(output)) {
-    return { icon, title: output.agent_name };
+    return { icon, title: output.agent_name, expanded: true };
   }
   if (isAgentPreviewOutput(output)) {
     return {
@@ -78,6 +84,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
     return {
       icon,
       title: "Creating agent, this may take a few minutes. Sit back and relax.",
+      expanded: true,
     };
   }
   return {
@@ -107,8 +114,6 @@ export function CreateAgentTool({ part }: Props) {
       isOperationPendingOutput(output) ||
       isOperationInProgressOutput(output));
 
-  const progress = useAsymptoticProgress(isOperating);
-
   const hasExpandableContent =
     part.state === "output-available" &&
     !!output &&
@@ -152,31 +157,53 @@ export function CreateAgentTool({ part }: Props) {
         <ToolAccordion {...getAccordionMeta(output)}>
           {isOperating && (
             <ContentGrid>
-              <ProgressBar value={progress} className="max-w-[280px]" />
+              <MiniGame />
               <ContentHint>
-                This could take a few minutes, grab a coffee ☕
+                This could take a few minutes — play while you wait!
               </ContentHint>
             </ContentGrid>
           )}
 
           {isAgentSavedOutput(output) && (
-            <ContentGrid>
-              <ContentMessage>{output.message}</ContentMessage>
-              <div className="flex flex-wrap gap-2">
-                <ContentLink href={output.library_agent_link}>
-                  Open in library
-                </ContentLink>
-                <ContentLink href={output.agent_page_link}>
-                  Open in builder
-                </ContentLink>
+            <div className="rounded-xl border border-border/60 bg-card p-4 shadow-sm">
+              <div className="flex items-baseline gap-2">
+                <CheckFatIcon
+                  size={18}
+                  weight="regular"
+                  className="relative top-1 text-green-500"
+                />
+                <Text
+                  variant="body-medium"
+                  className="text-blacks mb-2 text-[16px]"
+                >
+                  {output.message}
+                </Text>
               </div>
-              <ContentCodeBlock>
-                {truncateText(
-                  formatMaybeJson({ agent_id: output.agent_id }),
-                  800,
-                )}
-              </ContentCodeBlock>
-            </ContentGrid>
+              <div className="mt-3 flex flex-wrap gap-4">
+                <Button variant="outline" size="small">
+                  <NextLink
+                    href={output.library_agent_link}
+                    className="inline-flex items-center gap-1.5"
+                    target="_blank"
+                    rel="noopener noreferrer"
+                  >
+                    <BookOpenIcon size={14} weight="regular" />
+                    Open in library
+                  </NextLink>
+                </Button>
+                <Button variant="outline" size="small">
+                  <NextLink
+                    href={output.agent_page_link}
+                    target="_blank"
+                    rel="noopener noreferrer"
+                    className="inline-flex items-center gap-1.5"
+                  >
+                    <PencilSimpleIcon size={14} weight="regular" />
+                    Open in builder
+                  </NextLink>
+                </Button>
+              </div>
+            </div>
           )}
 
           {isAgentPreviewOutput(output) && (

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/components/MiniGame/MiniGame.tsx

@@ -0,0 +1,21 @@
+"use client";
+
+import { useMiniGame } from "./useMiniGame";
+
+export function MiniGame() {
+  const { canvasRef } = useMiniGame();
+
+  return (
+    <div
+      className="w-full overflow-hidden rounded-md bg-background text-foreground"
+      style={{ border: "1px solid #d17fff" }}
+    >
+      <canvas
+        ref={canvasRef}
+        tabIndex={0}
+        className="block w-full outline-none"
+        style={{ imageRendering: "pixelated" }}
+      />
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/components/MiniGame/useMiniGame.ts

@@ -0,0 +1,579 @@
+import { useEffect, useRef } from "react";
+
+/* ------------------------------------------------------------------ */
+/*  Constants                                                         */
+/* ------------------------------------------------------------------ */
+
+const CANVAS_HEIGHT = 150;
+const GRAVITY = 0.55;
+const JUMP_FORCE = -9.5;
+const BASE_SPEED = 3;
+const SPEED_INCREMENT = 0.0008;
+const SPAWN_MIN = 70;
+const SPAWN_MAX = 130;
+const CHAR_SIZE = 18;
+const CHAR_X = 50;
+const GROUND_PAD = 20;
+const STORAGE_KEY = "copilot-minigame-highscore";
+
+// Colors
+const COLOR_BG = "#E8EAF6";
+const COLOR_CHAR = "#263238";
+const COLOR_BOSS = "#F50057";
+
+// Boss
+const BOSS_SIZE = 36;
+const BOSS_ENTER_SPEED = 2;
+const BOSS_LEAVE_SPEED = 3;
+const BOSS_SHOOT_COOLDOWN = 90;
+const BOSS_SHOTS_TO_EVADE = 5;
+const BOSS_INTERVAL = 20; // every N score
+const PROJ_SPEED = 4.5;
+const PROJ_SIZE = 12;
+
+/* ------------------------------------------------------------------ */
+/*  Types                                                             */
+/* ------------------------------------------------------------------ */
+
+interface Obstacle {
+  x: number;
+  width: number;
+  height: number;
+  scored: boolean;
+}
+
+interface Projectile {
+  x: number;
+  y: number;
+  speed: number;
+  evaded: boolean;
+  type: "low" | "high";
+}
+
+interface BossState {
+  phase: "inactive" | "entering" | "fighting" | "leaving";
+  x: number;
+  targetX: number;
+  shotsEvaded: number;
+  cooldown: number;
+  projectiles: Projectile[];
+  bob: number;
+}
+
+interface GameState {
+  charY: number;
+  vy: number;
+  obstacles: Obstacle[];
+  score: number;
+  highScore: number;
+  speed: number;
+  frame: number;
+  nextSpawn: number;
+  running: boolean;
+  over: boolean;
+  groundY: number;
+  boss: BossState;
+  bossThreshold: number;
+}
+
+/* ------------------------------------------------------------------ */
+/*  Helpers                                                           */
+/* ------------------------------------------------------------------ */
+
+function randInt(min: number, max: number) {
+  return Math.floor(Math.random() * (max - min + 1)) + min;
+}
+
+function readHighScore(): number {
+  try {
+    return parseInt(localStorage.getItem(STORAGE_KEY) || "0", 10) || 0;
+  } catch {
+    return 0;
+  }
+}
+
+function writeHighScore(score: number) {
+  try {
+    localStorage.setItem(STORAGE_KEY, String(score));
+  } catch {
+    /* noop */
+  }
+}
+
+function makeBoss(): BossState {
+  return {
+    phase: "inactive",
+    x: 0,
+    targetX: 0,
+    shotsEvaded: 0,
+    cooldown: 0,
+    projectiles: [],
+    bob: 0,
+  };
+}
+
+function makeState(groundY: number): GameState {
+  return {
+    charY: groundY - CHAR_SIZE,
+    vy: 0,
+    obstacles: [],
+    score: 0,
+    highScore: readHighScore(),
+    speed: BASE_SPEED,
+    frame: 0,
+    nextSpawn: randInt(SPAWN_MIN, SPAWN_MAX),
+    running: false,
+    over: false,
+    groundY,
+    boss: makeBoss(),
+    bossThreshold: BOSS_INTERVAL,
+  };
+}
+
+function gameOver(s: GameState) {
+  s.running = false;
+  s.over = true;
+  if (s.score > s.highScore) {
+    s.highScore = s.score;
+    writeHighScore(s.score);
+  }
+}
+
+/* ------------------------------------------------------------------ */
+/*  Projectile collision — shared between fighting & leaving phases   */
+/* ------------------------------------------------------------------ */
+
+/** Returns true if the player died. */
+function tickProjectiles(s: GameState): boolean {
+  const boss = s.boss;
+
+  for (const p of boss.projectiles) {
+    p.x -= p.speed;
+
+    if (!p.evaded && p.x + PROJ_SIZE < CHAR_X) {
+      p.evaded = true;
+      boss.shotsEvaded++;
+    }
+
+    // Collision
+    if (
+      !p.evaded &&
+      CHAR_X + CHAR_SIZE > p.x &&
+      CHAR_X < p.x + PROJ_SIZE &&
+      s.charY + CHAR_SIZE > p.y &&
+      s.charY < p.y + PROJ_SIZE
+    ) {
+      gameOver(s);
+      return true;
+    }
+  }
+
+  boss.projectiles = boss.projectiles.filter((p) => p.x + PROJ_SIZE > -20);
+  return false;
+}
+
+/* ------------------------------------------------------------------ */
+/*  Update                                                            */
+/* ------------------------------------------------------------------ */
+
+function update(s: GameState, canvasWidth: number) {
+  if (!s.running) return;
+
+  s.frame++;
+
+  // Speed only ramps during regular play
+  if (s.boss.phase === "inactive") {
+    s.speed = BASE_SPEED + s.frame * SPEED_INCREMENT;
+  }
+
+  // ---- Character physics (always active) ---- //
+  s.vy += GRAVITY;
+  s.charY += s.vy;
+  if (s.charY + CHAR_SIZE >= s.groundY) {
+    s.charY = s.groundY - CHAR_SIZE;
+    s.vy = 0;
+  }
+
+  // ---- Trigger boss ---- //
+  if (s.boss.phase === "inactive" && s.score >= s.bossThreshold) {
+    s.boss.phase = "entering";
+    s.boss.x = canvasWidth + 10;
+    s.boss.targetX = canvasWidth - BOSS_SIZE - 40;
+    s.boss.shotsEvaded = 0;
+    s.boss.cooldown = BOSS_SHOOT_COOLDOWN;
+    s.boss.projectiles = [];
+    s.obstacles = [];
+  }
+
+  // ---- Boss: entering ---- //
+  if (s.boss.phase === "entering") {
+    s.boss.bob = Math.sin(s.frame * 0.05) * 3;
+    s.boss.x -= BOSS_ENTER_SPEED;
+    if (s.boss.x <= s.boss.targetX) {
+      s.boss.x = s.boss.targetX;
+      s.boss.phase = "fighting";
+    }
+    return; // no obstacles while entering
+  }
+
+  // ---- Boss: fighting ---- //
+  if (s.boss.phase === "fighting") {
+    s.boss.bob = Math.sin(s.frame * 0.05) * 3;
+
+    // Shoot
+    s.boss.cooldown--;
+    if (s.boss.cooldown <= 0) {
+      const isLow = Math.random() < 0.5;
+      s.boss.projectiles.push({
+        x: s.boss.x - PROJ_SIZE,
+        y: isLow ? s.groundY - 14 : s.groundY - 70,
+        speed: PROJ_SPEED,
+        evaded: false,
+        type: isLow ? "low" : "high",
+      });
+      s.boss.cooldown = BOSS_SHOOT_COOLDOWN;
+    }
+
+    if (tickProjectiles(s)) return;
+
+    // Boss defeated?
+    if (s.boss.shotsEvaded >= BOSS_SHOTS_TO_EVADE) {
+      s.boss.phase = "leaving";
+      s.score += 5; // bonus
+      s.bossThreshold = s.score + BOSS_INTERVAL;
+    }
+    return;
+  }
+
+  // ---- Boss: leaving ---- //
+  if (s.boss.phase === "leaving") {
+    s.boss.bob = Math.sin(s.frame * 0.05) * 3;
+    s.boss.x += BOSS_LEAVE_SPEED;
+
+    // Still check in-flight projectiles
+    if (tickProjectiles(s)) return;
+
+    if (s.boss.x > canvasWidth + 50) {
+      s.boss = makeBoss();
+      s.nextSpawn = s.frame + randInt(SPAWN_MIN / 2, SPAWN_MAX / 2);
+    }
+    return;
+  }
+
+  // ---- Regular obstacle play ---- //
+  if (s.frame >= s.nextSpawn) {
+    s.obstacles.push({
+      x: canvasWidth + 10,
+      width: randInt(10, 16),
+      height: randInt(20, 48),
+      scored: false,
+    });
+    s.nextSpawn = s.frame + randInt(SPAWN_MIN, SPAWN_MAX);
+  }
+
+  for (const o of s.obstacles) {
+    o.x -= s.speed;
+    if (!o.scored && o.x + o.width < CHAR_X) {
+      o.scored = true;
+      s.score++;
+    }
+  }
+
+  s.obstacles = s.obstacles.filter((o) => o.x + o.width > -20);
+
+  for (const o of s.obstacles) {
+    const oY = s.groundY - o.height;
+    if (
+      CHAR_X + CHAR_SIZE > o.x &&
+      CHAR_X < o.x + o.width &&
+      s.charY + CHAR_SIZE > oY
+    ) {
+      gameOver(s);
+      return;
+    }
+  }
+}
+
+/* ------------------------------------------------------------------ */
+/*  Drawing                                                           */
+/* ------------------------------------------------------------------ */
+
+function drawBoss(ctx: CanvasRenderingContext2D, s: GameState, bg: string) {
+  const bx = s.boss.x;
+  const by = s.groundY - BOSS_SIZE + s.boss.bob;
+
+  // Body
+  ctx.save();
+  ctx.fillStyle = COLOR_BOSS;
+  ctx.globalAlpha = 0.9;
+  ctx.beginPath();
+  ctx.roundRect(bx, by, BOSS_SIZE, BOSS_SIZE, 4);
+  ctx.fill();
+  ctx.restore();
+
+  // Eyes
+  ctx.save();
+  ctx.fillStyle = bg;
+  const eyeY = by + 13;
+  ctx.beginPath();
+  ctx.arc(bx + 10, eyeY, 4, 0, Math.PI * 2);
+  ctx.fill();
+  ctx.beginPath();
+  ctx.arc(bx + 26, eyeY, 4, 0, Math.PI * 2);
+  ctx.fill();
+  ctx.restore();
+
+  // Angry eyebrows
+  ctx.save();
+  ctx.strokeStyle = bg;
+  ctx.lineWidth = 2;
+  ctx.beginPath();
+  ctx.moveTo(bx + 5, eyeY - 7);
+  ctx.lineTo(bx + 14, eyeY - 4);
+  ctx.stroke();
+  ctx.beginPath();
+  ctx.moveTo(bx + 31, eyeY - 7);
+  ctx.lineTo(bx + 22, eyeY - 4);
+  ctx.stroke();
+  ctx.restore();
+
+  // Zigzag mouth
+  ctx.save();
+  ctx.strokeStyle = bg;
+  ctx.lineWidth = 1.5;
+  ctx.beginPath();
+  ctx.moveTo(bx + 10, by + 27);
+  ctx.lineTo(bx + 14, by + 24);
+  ctx.lineTo(bx + 18, by + 27);
+  ctx.lineTo(bx + 22, by + 24);
+  ctx.lineTo(bx + 26, by + 27);
+  ctx.stroke();
+  ctx.restore();
+}
+
+function drawProjectiles(ctx: CanvasRenderingContext2D, boss: BossState) {
+  ctx.save();
+  ctx.fillStyle = COLOR_BOSS;
+  ctx.globalAlpha = 0.8;
+  for (const p of boss.projectiles) {
+    if (p.evaded) continue;
+    ctx.beginPath();
+    ctx.arc(
+      p.x + PROJ_SIZE / 2,
+      p.y + PROJ_SIZE / 2,
+      PROJ_SIZE / 2,
+      0,
+      Math.PI * 2,
+    );
+    ctx.fill();
+  }
+  ctx.restore();
+}
+
+function draw(
+  ctx: CanvasRenderingContext2D,
+  s: GameState,
+  w: number,
+  h: number,
+  fg: string,
+  started: boolean,
+) {
+  ctx.fillStyle = COLOR_BG;
+  ctx.fillRect(0, 0, w, h);
+
+  // Ground
+  ctx.save();
+  ctx.strokeStyle = fg;
+  ctx.globalAlpha = 0.15;
+  ctx.setLineDash([4, 4]);
+  ctx.beginPath();
+  ctx.moveTo(0, s.groundY);
+  ctx.lineTo(w, s.groundY);
+  ctx.stroke();
+  ctx.restore();
+
+  // Character
+  ctx.save();
+  ctx.fillStyle = COLOR_CHAR;
+  ctx.globalAlpha = 0.85;
+  ctx.beginPath();
+  ctx.roundRect(CHAR_X, s.charY, CHAR_SIZE, CHAR_SIZE, 3);
+  ctx.fill();
+  ctx.restore();
+
+  // Eyes
+  ctx.save();
+  ctx.fillStyle = COLOR_BG;
+  ctx.beginPath();
+  ctx.arc(CHAR_X + 6, s.charY + 7, 2.5, 0, Math.PI * 2);
+  ctx.fill();
+  ctx.beginPath();
+  ctx.arc(CHAR_X + 12, s.charY + 7, 2.5, 0, Math.PI * 2);
+  ctx.fill();
+  ctx.restore();
+
+  // Obstacles
+  ctx.save();
+  ctx.fillStyle = fg;
+  ctx.globalAlpha = 0.55;
+  for (const o of s.obstacles) {
+    ctx.fillRect(o.x, s.groundY - o.height, o.width, o.height);
+  }
+  ctx.restore();
+
+  // Boss + projectiles
+  if (s.boss.phase !== "inactive") {
+    drawBoss(ctx, s, COLOR_BG);
+    drawProjectiles(ctx, s.boss);
+  }
+
+  // Score HUD
+  ctx.save();
+  ctx.fillStyle = fg;
+  ctx.globalAlpha = 0.5;
+  ctx.font = "bold 11px monospace";
+  ctx.textAlign = "right";
+  ctx.fillText(`Score: ${s.score}`, w - 12, 20);
+  ctx.fillText(`Best: ${s.highScore}`, w - 12, 34);
+  if (s.boss.phase === "fighting") {
+    ctx.fillText(
+      `Evade: ${s.boss.shotsEvaded}/${BOSS_SHOTS_TO_EVADE}`,
+      w - 12,
+      48,
+    );
+  }
+  ctx.restore();
+
+  // Prompts
+  if (!started && !s.running && !s.over) {
+    ctx.save();
+    ctx.fillStyle = fg;
+    ctx.globalAlpha = 0.5;
+    ctx.font = "12px sans-serif";
+    ctx.textAlign = "center";
+    ctx.fillText("Click or press Space to play while you wait", w / 2, h / 2);
+    ctx.restore();
+  }
+
+  if (s.over) {
+    ctx.save();
+    ctx.fillStyle = fg;
+    ctx.globalAlpha = 0.7;
+    ctx.font = "bold 13px sans-serif";
+    ctx.textAlign = "center";
+    ctx.fillText("Game Over", w / 2, h / 2 - 8);
+    ctx.font = "11px sans-serif";
+    ctx.fillText("Click or Space to restart", w / 2, h / 2 + 10);
+    ctx.restore();
+  }
+}
+
+/* ------------------------------------------------------------------ */
+/*  Hook                                                              */
+/* ------------------------------------------------------------------ */
+
+export function useMiniGame() {
+  const canvasRef = useRef<HTMLCanvasElement>(null);
+  const stateRef = useRef<GameState | null>(null);
+  const rafRef = useRef(0);
+  const startedRef = useRef(false);
+
+  useEffect(() => {
+    const canvas = canvasRef.current;
+    if (!canvas) return;
+
+    const container = canvas.parentElement;
+    if (container) {
+      canvas.width = container.clientWidth;
+      canvas.height = CANVAS_HEIGHT;
+    }
+
+    const groundY = canvas.height - GROUND_PAD;
+    stateRef.current = makeState(groundY);
+
+    const style = getComputedStyle(canvas);
+    let fg = style.color || "#71717a";
+
+    // -------------------------------------------------------------- //
+    //  Jump                                                           //
+    // -------------------------------------------------------------- //
+    function jump() {
+      const s = stateRef.current;
+      if (!s) return;
+
+      if (s.over) {
+        const hs = s.highScore;
+        const gy = s.groundY;
+        stateRef.current = makeState(gy);
+        stateRef.current.highScore = hs;
+        stateRef.current.running = true;
+        startedRef.current = true;
+        return;
+      }
+
+      if (!s.running) {
+        s.running = true;
+        startedRef.current = true;
+        return;
+      }
+
+      // Only jump when on the ground
+      if (s.charY + CHAR_SIZE >= s.groundY) {
+        s.vy = JUMP_FORCE;
+      }
+    }
+
+    function onKey(e: KeyboardEvent) {
+      if (e.code === "Space" || e.key === " ") {
+        e.preventDefault();
+        jump();
+      }
+    }
+
+    function onClick() {
+      canvas?.focus();
+      jump();
+    }
+
+    // -------------------------------------------------------------- //
+    //  Loop                                                           //
+    // -------------------------------------------------------------- //
+    function loop() {
+      const s = stateRef.current;
+      if (!canvas || !s) return;
+      const ctx = canvas.getContext("2d");
+      if (!ctx) return;
+
+      update(s, canvas.width);
+      draw(ctx, s, canvas.width, canvas.height, fg, startedRef.current);
+      rafRef.current = requestAnimationFrame(loop);
+    }
+
+    rafRef.current = requestAnimationFrame(loop);
+
+    canvas.addEventListener("click", onClick);
+    canvas.addEventListener("keydown", onKey);
+
+    const observer = new ResizeObserver((entries) => {
+      for (const entry of entries) {
+        canvas.width = entry.contentRect.width;
+        canvas.height = CANVAS_HEIGHT;
+        if (stateRef.current) {
+          stateRef.current.groundY = canvas.height - GROUND_PAD;
+        }
+        const cs = getComputedStyle(canvas);
+        fg = cs.color || fg;
+      }
+    });
+    if (container) observer.observe(container);
+
+    return () => {
+      cancelAnimationFrame(rafRef.current);
+      canvas.removeEventListener("click", onClick);
+      canvas.removeEventListener("keydown", onKey);
+      observer.disconnect();
+    };
+  }, []);
+
+  return { canvasRef };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/useCopilotPage.ts

@@ -1,10 +1,14 @@
 import { useGetV2ListSessions } from "@/app/api/__generated__/endpoints/chat/chat";
+import { toast } from "@/components/molecules/Toast/use-toast";
 import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
 import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
 import { useChat } from "@ai-sdk/react";
 import { DefaultChatTransport } from "ai";
-import { useEffect, useMemo, useState } from "react";
+import { useEffect, useMemo, useRef, useState } from "react";
 import { useChatSession } from "./useChatSession";
+import { useLongRunningToolPolling } from "./hooks/useLongRunningToolPolling";
+
+const STREAM_START_TIMEOUT_MS = 12_000;
 
 export function useCopilotPage() {
   const { isUserLoading, isLoggedIn } = useSupabase();
@@ -52,6 +56,24 @@ export function useCopilotPage() {
     transport: transport ?? undefined,
   });
 
+  // Abort the stream if the backend doesn't start sending data within 12s.
+  const stopRef = useRef(stop);
+  stopRef.current = stop;
+  useEffect(() => {
+    if (status !== "submitted") return;
+
+    const timer = setTimeout(() => {
+      stopRef.current();
+      toast({
+        title: "Stream timed out",
+        description: "The server took too long to respond. Please try again.",
+        variant: "destructive",
+      });
+    }, STREAM_START_TIMEOUT_MS);
+
+    return () => clearTimeout(timer);
+  }, [status]);
+
   useEffect(() => {
     if (!hydratedMessages || hydratedMessages.length === 0) return;
     setMessages((prev) => {
@@ -60,6 +82,11 @@ export function useCopilotPage() {
     });
   }, [hydratedMessages, setMessages]);
 
+  // Poll session endpoint when a long-running tool (create_agent, edit_agent)
+  // is in progress. When the backend completes, the session data will contain
+  // the final tool output — this hook detects the change and updates messages.
+  useLongRunningToolPolling(sessionId, messages, setMessages);
+
   // Clear messages when session is null
   useEffect(() => {
     if (!sessionId) setMessages([]);

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/sidebar/SidebarRunsList/components/ScheduleListItem.tsx

@@ -29,6 +29,7 @@ export function ScheduleListItem({
       description={formatDistanceToNow(schedule.next_run_time, {
         addSuffix: true,
       })}
+      descriptionTitle={new Date(schedule.next_run_time).toString()}
       onClick={onClick}
       selected={selected}
       icon={

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/sidebar/SidebarRunsList/components/SidebarItemCard.tsx

@@ -7,6 +7,7 @@ import React from "react";
 interface Props {
   title: string;
   description?: string;
+  descriptionTitle?: string;
   icon?: React.ReactNode;
   selected?: boolean;
   onClick?: () => void;
@@ -16,6 +17,7 @@ interface Props {
 export function SidebarItemCard({
   title,
   description,
+  descriptionTitle,
   icon,
   selected,
   onClick,
@@ -38,7 +40,11 @@ export function SidebarItemCard({
           >
             {title}
           </Text>
-          <Text variant="body" className="leading-tight !text-zinc-500">
+          <Text
+            variant="body"
+            className="leading-tight !text-zinc-500"
+            title={descriptionTitle}
+          >
             {description}
           </Text>
         </div>

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/sidebar/SidebarRunsList/components/TaskListItem.tsx

@@ -81,6 +81,9 @@ export function TaskListItem({
           ? formatDistanceToNow(run.started_at, { addSuffix: true })
           : "—"
       }
+      descriptionTitle={
+        run.started_at ? new Date(run.started_at).toString() : undefined
+      }
       onClick={onClick}
       selected={selected}
       actions={

autogpt_platform/frontend/src/app/globals.css

@@ -180,3 +180,14 @@ body[data-google-picker-open="true"] [data-dialog-content] {
   z-index: 1 !important;
   pointer-events: none !important;
 }
+
+/* CoPilot chat table styling — remove left/right borders, increase padding */
+[data-streamdown="table-wrapper"] table {
+  border-left: none;
+  border-right: none;
+}
+
+[data-streamdown="table-wrapper"] th,
+[data-streamdown="table-wrapper"] td {
+  padding: 0.875rem 1rem; /* py-3.5 px-4 */
+}

autogpt_platform/frontend/src/components/contextual/OutputRenderers/renderers/MarkdownRenderer.tsx

@@ -226,7 +226,7 @@ function renderMarkdown(
           table: ({ children, ...props }) => (
             <div className="my-4 overflow-x-auto">
               <table
-                className="min-w-full divide-y divide-gray-200 rounded-lg border border-gray-200 dark:divide-gray-700 dark:border-gray-700"
+                className="min-w-full divide-y divide-gray-200 border-y border-gray-200 dark:divide-gray-700 dark:border-gray-700"
                 {...props}
               >
                 {children}
@@ -235,7 +235,7 @@ function renderMarkdown(
           ),
           th: ({ children, ...props }) => (
             <th
-              className="bg-gray-50 px-4 py-3 text-left text-xs font-semibold uppercase tracking-wider text-gray-700 dark:bg-gray-800 dark:text-gray-300"
+              className="bg-gray-50 px-4 py-3.5 text-left text-xs font-semibold uppercase tracking-wider text-gray-700 dark:bg-gray-800 dark:text-gray-300"
               {...props}
             >
               {children}
@@ -243,7 +243,7 @@ function renderMarkdown(
           ),
           td: ({ children, ...props }) => (
             <td
-              className="border-t border-gray-200 px-4 py-3 text-sm text-gray-600 dark:border-gray-700 dark:text-gray-400"
+              className="border-t border-gray-200 px-4 py-3.5 text-sm text-gray-600 dark:border-gray-700 dark:text-gray-400"
               {...props}
             >
               {children}