Merge branch 'swiftyos/posthog-metrics' of github.com:Significant-Gravitas/AutoGPT into swiftyos/posthog-metrics

## Changes 🏗️

- Make the loading UX better when switching between chats or loading a
new chat
- Make session/chat management logic more manageable
- Improving "Deep thinking" loading states
- Fix bug that happened when returning to chat after navigating away

## Checklist 📋

### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  - [x] Run the app locally and test the above

.github/workflows/platform-frontend-ci.yml

@@ -128,7 +128,7 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           exitOnceUploaded: true
 
-  test:
+  e2e_test:
     runs-on: big-boi
     needs: setup
     strategy:
@@ -258,3 +258,39 @@ jobs:
       - name: Print Final Docker Compose logs
         if: always()
         run: docker compose -f ../docker-compose.yml logs
+
+  integration_test:
+    runs-on: ubuntu-latest
+    needs: setup
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "22.18.0"
+
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Generate API client
+        run: pnpm generate:api
+
+      - name: Run Integration Tests
+        run: pnpm test:unit

AGENTS.md

@@ -16,6 +16,32 @@ See `docs/content/platform/getting-started.md` for setup instructions.
 - Format Python code with `poetry run format`.
 - Format frontend code using `pnpm format`.
 
+
+## Frontend guidelines:
+
+See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
+
+1. **Pages**: Create in `src/app/(platform)/feature-name/page.tsx`
+   - Add `usePageName.ts` hook for logic
+   - Put sub-components in local `components/` folder
+2. **Components**: Structure as `ComponentName/ComponentName.tsx` + `useComponentName.ts` + `helpers.ts`
+   - Use design system components from `src/components/` (atoms, molecules, organisms)
+   - Never use `src/components/__legacy__/*`
+3. **Data fetching**: Use generated API hooks from `@/app/api/__generated__/endpoints/`
+   - Regenerate with `pnpm generate:api`
+   - Pattern: `use{Method}{Version}{OperationName}`
+4. **Styling**: Tailwind CSS only, use design tokens, Phosphor Icons only
+5. **Testing**: Add Storybook stories for new components, Playwright for E2E
+6. **Code conventions**: Function declarations (not arrow functions) for components/handlers
+- Component props should be `interface Props { ... }` (not exported) unless the interface needs to be used outside the component
+- Separate render logic from business logic (component.tsx + useComponent.ts + helpers.ts)
+- Colocate state when possible and avoid creating large components, use sub-components ( local `/components` folder next to the parent component ) when sensible
+- Avoid large hooks, abstract logic into `helpers.ts` files when sensible
+- Use function declarations for components, arrow functions only for callbacks
+- No barrel files or `index.ts` re-exports
+- Do not use `useCallback` or `useMemo` unless strictly needed
+- Avoid comments at all times unless the code is very complex
+
 ## Testing
 
 - Backend: `poetry run test` (runs pytest with a docker based postgres + prisma).

autogpt_platform/CLAUDE.md

@@ -201,7 +201,7 @@ If you get any pushback or hit complex block conditions check the new_blocks gui
 3. Write tests alongside the route file
 4. Run `poetry run test` to verify
 
-**Frontend feature development:**
+### Frontend guidelines:
 
 See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 
@@ -217,6 +217,14 @@ See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 4. **Styling**: Tailwind CSS only, use design tokens, Phosphor Icons only
 5. **Testing**: Add Storybook stories for new components, Playwright for E2E
 6. **Code conventions**: Function declarations (not arrow functions) for components/handlers
+- Component props should be `interface Props { ... }` (not exported) unless the interface needs to be used outside the component
+- Separate render logic from business logic (component.tsx + useComponent.ts + helpers.ts)
+- Colocate state when possible and avoid creating large components, use sub-components ( local `/components` folder next to the parent component ) when sensible
+- Avoid large hooks, abstract logic into `helpers.ts` files when sensible
+- Use function declarations for components, arrow functions only for callbacks
+- No barrel files or `index.ts` re-exports
+- Do not use `useCallback` or `useMemo` unless strictly needed
+- Avoid comments at all times unless the code is very complex
 
 ### Security Implementation
 

autogpt_platform/backend/.env.default

@@ -178,5 +178,10 @@ AYRSHARE_JWT_KEY=
 SMARTLEAD_API_KEY=
 ZEROBOUNCE_API_KEY=
 
+# PostHog Analytics
+# Get API key from https://posthog.com - Project Settings > Project API Key
+POSTHOG_API_KEY=
+POSTHOG_HOST=https://eu.i.posthog.com
+
 # Other Services
 AUTOMOD_API_KEY=

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

@@ -290,6 +290,11 @@ async def _cache_session(session: ChatSession) -> None:
     await async_redis.setex(redis_key, config.session_ttl, session.model_dump_json())
 
 
+async def cache_chat_session(session: ChatSession) -> None:
+    """Cache a chat session without persisting to the database."""
+    await _cache_session(session)
+
+
 async def _get_session_from_db(session_id: str) -> ChatSession | None:
     """Get a chat session from the database."""
     prisma_session = await chat_db.get_chat_session(session_id)

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

@@ -172,12 +172,12 @@ async def get_session(
         user_id: The optional authenticated user ID, or None for anonymous access.
 
     Returns:
-        SessionDetailResponse: Details for the requested session; raises NotFoundError if not found.
+        SessionDetailResponse: Details for the requested session, or None if not found.
 
     """
     session = await get_chat_session(session_id, user_id)
     if not session:
-        raise NotFoundError(f"Session {session_id} not found")
+        raise NotFoundError(f"Session {session_id} not found.")
 
     messages = [message.model_dump() for message in session.messages]
     logger.info(
@@ -222,6 +222,8 @@ async def stream_chat_post(
     session = await _validate_and_get_session(session_id, user_id)
 
     async def event_generator() -> AsyncGenerator[str, None]:
+        chunk_count = 0
+        first_chunk_type: str | None = None
         async for chunk in chat_service.stream_chat_completion(
             session_id,
             request.message,
@@ -230,7 +232,26 @@ async def stream_chat_post(
             session=session,  # Pass pre-fetched session to avoid double-fetch
             context=request.context,
         ):
+            if chunk_count < 3:
+                logger.info(
+                    "Chat stream chunk",
+                    extra={
+                        "session_id": session_id,
+                        "chunk_type": str(chunk.type),
+                    },
+                )
+            if not first_chunk_type:
+                first_chunk_type = str(chunk.type)
+            chunk_count += 1
             yield chunk.to_sse()
+        logger.info(
+            "Chat stream completed",
+            extra={
+                "session_id": session_id,
+                "chunk_count": chunk_count,
+                "first_chunk_type": first_chunk_type,
+            },
+        )
         # AI SDK protocol termination
         yield "data: [DONE]\n\n"
 
@@ -275,6 +296,8 @@ async def stream_chat_get(
     session = await _validate_and_get_session(session_id, user_id)
 
     async def event_generator() -> AsyncGenerator[str, None]:
+        chunk_count = 0
+        first_chunk_type: str | None = None
         async for chunk in chat_service.stream_chat_completion(
             session_id,
             message,
@@ -282,7 +305,26 @@ async def stream_chat_get(
             user_id=user_id,
             session=session,  # Pass pre-fetched session to avoid double-fetch
         ):
+            if chunk_count < 3:
+                logger.info(
+                    "Chat stream chunk",
+                    extra={
+                        "session_id": session_id,
+                        "chunk_type": str(chunk.type),
+                    },
+                )
+            if not first_chunk_type:
+                first_chunk_type = str(chunk.type)
+            chunk_count += 1
             yield chunk.to_sse()
+        logger.info(
+            "Chat stream completed",
+            extra={
+                "session_id": session_id,
+                "chunk_count": chunk_count,
+                "first_chunk_type": first_chunk_type,
+            },
+        )
         # AI SDK protocol termination
         yield "data: [DONE]\n\n"
 

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

@@ -1,12 +1,20 @@
 import asyncio
 import logging
+import time
+from asyncio import CancelledError
 from collections.abc import AsyncGenerator
 from typing import Any
 
 import orjson
 from langfuse import get_client, propagate_attributes
 from langfuse.openai import openai  # type: ignore
-from openai import APIConnectionError, APIError, APIStatusError, RateLimitError
+from openai import (
+    APIConnectionError,
+    APIError,
+    APIStatusError,
+    PermissionDeniedError,
+    RateLimitError,
+)
 from openai.types.chat import ChatCompletionChunk, ChatCompletionToolParam
 
 from backend.data.understanding import (
@@ -21,6 +29,7 @@ from .model import (
     ChatMessage,
     ChatSession,
     Usage,
+    cache_chat_session,
     get_chat_session,
     update_session_title,
     upsert_chat_session,
@@ -39,6 +48,7 @@ from .response_model import (
     StreamUsage,
 )
 from .tools import execute_tool, tools
+from .tracking import track_user_message
 
 logger = logging.getLogger(__name__)
 
@@ -94,16 +104,33 @@ async def _build_system_prompt(user_id: str | None) -> tuple[str, Any]:
     return compiled, understanding
 
 
-async def _generate_session_title(message: str) -> str | None:
+async def _generate_session_title(
+    message: str,
+    user_id: str | None = None,
+    session_id: str | None = None,
+) -> str | None:
     """Generate a concise title for a chat session based on the first message.
 
     Args:
         message: The first user message in the session
+        user_id: User ID for OpenRouter tracing (optional)
+        session_id: Session ID for OpenRouter tracing (optional)
 
     Returns:
         A short title (3-6 words) or None if generation fails
     """
     try:
+        # Build extra_body for OpenRouter tracing and PostHog analytics
+        extra_body: dict[str, Any] = {}
+        if user_id:
+            extra_body["user"] = user_id[:128]  # OpenRouter limit
+            extra_body["posthogDistinctId"] = user_id
+        if session_id:
+            extra_body["session_id"] = session_id[:128]  # OpenRouter limit
+        extra_body["posthogProperties"] = {
+            "environment": settings.config.app_env.value,
+        }
+
         response = await client.chat.completions.create(
             model=config.title_model,
             messages=[
@@ -118,6 +145,7 @@ async def _generate_session_title(message: str) -> str | None:
                 {"role": "user", "content": message[:500]},  # Limit input length
             ],
             max_tokens=20,
+            extra_body=extra_body,
         )
         title = response.choices[0].message.content
         if title:
@@ -228,6 +256,14 @@ async def stream_chat_completion(
             f"new message_count={len(session.messages)}"
         )
 
+        # Track user message in PostHog
+        if is_user_message:
+            track_user_message(
+                user_id=user_id,
+                session_id=session_id,
+                message_length=len(message),
+            )
+
     logger.info(
         f"Upserting session: {session.session_id} with user id {session.user_id}, "
         f"message_count={len(session.messages)}"
@@ -247,10 +283,15 @@ async def stream_chat_completion(
             # stale data issues when the main flow modifies the session
             captured_session_id = session_id
             captured_message = message
+            captured_user_id = user_id
 
             async def _update_title():
                 try:
-                    title = await _generate_session_title(captured_message)
+                    title = await _generate_session_title(
+                        captured_message,
+                        user_id=captured_user_id,
+                        session_id=captured_session_id,
+                    )
                     if title:
                         # Use dedicated title update function that doesn't
                         # touch messages, avoiding race conditions
@@ -296,6 +337,10 @@ async def stream_chat_completion(
                 content="",
             )
             accumulated_tool_calls: list[dict[str, Any]] = []
+            has_saved_assistant_message = False
+            has_appended_streaming_message = False
+            last_cache_time = 0.0
+            last_cache_content_len = 0
 
             # Wrap main logic in try/finally to ensure Langfuse observations are always ended
             has_yielded_end = False
@@ -332,6 +377,23 @@ async def stream_chat_completion(
                         assert assistant_response.content is not None
                         assistant_response.content += delta
                         has_received_text = True
+                        if not has_appended_streaming_message:
+                            session.messages.append(assistant_response)
+                            has_appended_streaming_message = True
+                        current_time = time.monotonic()
+                        content_len = len(assistant_response.content)
+                        if (
+                            current_time - last_cache_time >= 1.0
+                            and content_len > last_cache_content_len
+                        ):
+                            try:
+                                await cache_chat_session(session)
+                            except Exception as e:
+                                logger.warning(
+                                    f"Failed to cache partial session {session.session_id}: {e}"
+                                )
+                            last_cache_time = current_time
+                            last_cache_content_len = content_len
                         yield chunk
                     elif isinstance(chunk, StreamTextEnd):
                         # Emit text-end after text completes
@@ -390,10 +452,42 @@ async def stream_chat_completion(
                             if has_received_text and not text_streaming_ended:
                                 yield StreamTextEnd(id=text_block_id)
                                 text_streaming_ended = True
+
+                            # Save assistant message before yielding finish to ensure it's persisted
+                            # even if client disconnects immediately after receiving StreamFinish
+                            if not has_saved_assistant_message:
+                                messages_to_save_early: list[ChatMessage] = []
+                                if accumulated_tool_calls:
+                                    assistant_response.tool_calls = (
+                                        accumulated_tool_calls
+                                    )
+                                if not has_appended_streaming_message and (
+                                    assistant_response.content
+                                    or assistant_response.tool_calls
+                                ):
+                                    messages_to_save_early.append(assistant_response)
+                                messages_to_save_early.extend(tool_response_messages)
+
+                                if messages_to_save_early:
+                                    session.messages.extend(messages_to_save_early)
+                                    logger.info(
+                                        f"Saving assistant message before StreamFinish: "
+                                        f"content_len={len(assistant_response.content or '')}, "
+                                        f"tool_calls={len(assistant_response.tool_calls or [])}, "
+                                        f"tool_responses={len(tool_response_messages)}"
+                                    )
+                                if (
+                                    messages_to_save_early
+                                    or has_appended_streaming_message
+                                ):
+                                    await upsert_chat_session(session)
+                                    has_saved_assistant_message = True
+
                             has_yielded_end = True
                             yield chunk
                     elif isinstance(chunk, StreamError):
                         has_yielded_error = True
+                        yield chunk
                     elif isinstance(chunk, StreamUsage):
                         session.usage.append(
                             Usage(
@@ -413,6 +507,27 @@ async def stream_chat_completion(
                     langfuse.update_current_trace(output=str(tool_response_messages))
                     langfuse.update_current_span(output=str(tool_response_messages))
 
+            except CancelledError:
+                if not has_saved_assistant_message:
+                    if accumulated_tool_calls:
+                        assistant_response.tool_calls = accumulated_tool_calls
+                    if assistant_response.content:
+                        assistant_response.content = (
+                            f"{assistant_response.content}\n\n[interrupted]"
+                        )
+                    else:
+                        assistant_response.content = "[interrupted]"
+                    if not has_appended_streaming_message:
+                        session.messages.append(assistant_response)
+                    if tool_response_messages:
+                        session.messages.extend(tool_response_messages)
+                    try:
+                        await upsert_chat_session(session)
+                    except Exception as e:
+                        logger.warning(
+                            f"Failed to save interrupted session {session.session_id}: {e}"
+                        )
+                raise
             except Exception as e:
                 logger.error(f"Error during stream: {e!s}", exc_info=True)
 
@@ -434,14 +549,19 @@ async def stream_chat_completion(
                     # Add assistant message if it has content or tool calls
                     if accumulated_tool_calls:
                         assistant_response.tool_calls = accumulated_tool_calls
-                    if assistant_response.content or assistant_response.tool_calls:
+                    if not has_appended_streaming_message and (
+                        assistant_response.content or assistant_response.tool_calls
+                    ):
                         messages_to_save.append(assistant_response)
 
                     # Add tool response messages after assistant message
                     messages_to_save.extend(tool_response_messages)
 
-                    session.messages.extend(messages_to_save)
-                    await upsert_chat_session(session)
+                    if not has_saved_assistant_message:
+                        if messages_to_save:
+                            session.messages.extend(messages_to_save)
+                        if messages_to_save or has_appended_streaming_message:
+                            await upsert_chat_session(session)
 
                     if not has_yielded_error:
                         error_message = str(e)
@@ -472,38 +592,49 @@ async def stream_chat_completion(
                 return  # Exit after retry to avoid double-saving in finally block
 
             # Normal completion path - save session and handle tool call continuation
-            logger.info(
-                f"Normal completion path: session={session.session_id}, "
-                f"current message_count={len(session.messages)}"
-            )
-
-            # Build the messages list in the correct order
-            messages_to_save: list[ChatMessage] = []
-
-            # Add assistant message with tool_calls if any
-            if accumulated_tool_calls:
-                assistant_response.tool_calls = accumulated_tool_calls
+            # Only save if we haven't already saved when StreamFinish was received
+            if not has_saved_assistant_message:
                 logger.info(
-                    f"Added {len(accumulated_tool_calls)} tool calls to assistant message"
-                )
-            if assistant_response.content or assistant_response.tool_calls:
-                messages_to_save.append(assistant_response)
-                logger.info(
-                    f"Saving assistant message with content_len={len(assistant_response.content or '')}, tool_calls={len(assistant_response.tool_calls or [])}"
+                    f"Normal completion path: session={session.session_id}, "
+                    f"current message_count={len(session.messages)}"
                 )
 
-            # Add tool response messages after assistant message
-            messages_to_save.extend(tool_response_messages)
-            logger.info(
-                f"Saving {len(tool_response_messages)} tool response messages, "
-                f"total_to_save={len(messages_to_save)}"
-            )
+                # Build the messages list in the correct order
+                messages_to_save: list[ChatMessage] = []
 
-            session.messages.extend(messages_to_save)
-            logger.info(
-                f"Extended session messages, new message_count={len(session.messages)}"
-            )
-            await upsert_chat_session(session)
+                # Add assistant message with tool_calls if any
+                if accumulated_tool_calls:
+                    assistant_response.tool_calls = accumulated_tool_calls
+                    logger.info(
+                        f"Added {len(accumulated_tool_calls)} tool calls to assistant message"
+                    )
+                if not has_appended_streaming_message and (
+                    assistant_response.content or assistant_response.tool_calls
+                ):
+                    messages_to_save.append(assistant_response)
+                    logger.info(
+                        f"Saving assistant message with content_len={len(assistant_response.content or '')}, tool_calls={len(assistant_response.tool_calls or [])}"
+                    )
+
+                # Add tool response messages after assistant message
+                messages_to_save.extend(tool_response_messages)
+                logger.info(
+                    f"Saving {len(tool_response_messages)} tool response messages, "
+                    f"total_to_save={len(messages_to_save)}"
+                )
+
+                if messages_to_save:
+                    session.messages.extend(messages_to_save)
+                    logger.info(
+                        f"Extended session messages, new message_count={len(session.messages)}"
+                    )
+                if messages_to_save or has_appended_streaming_message:
+                    await upsert_chat_session(session)
+            else:
+                logger.info(
+                    "Assistant message already saved when StreamFinish was received, "
+                    "skipping duplicate save"
+                )
 
             # If we did a tool call, stream the chat completion again to get the next response
             if has_done_tool_call:
@@ -545,6 +676,12 @@ def _is_retryable_error(error: Exception) -> bool:
     return False
 
 
+def _is_region_blocked_error(error: Exception) -> bool:
+    if isinstance(error, PermissionDeniedError):
+        return "not available in your region" in str(error).lower()
+    return "not available in your region" in str(error).lower()
+
+
 async def _stream_chat_chunks(
     session: ChatSession,
     tools: list[ChatCompletionToolParam],
@@ -593,6 +730,20 @@ async def _stream_chat_chunks(
                     f"{f' (retry {retry_count}/{MAX_RETRIES})' if retry_count > 0 else ''}"
                 )
 
+                # Build extra_body for OpenRouter tracing and PostHog analytics
+                extra_body: dict[str, Any] = {
+                    "posthogProperties": {
+                        "environment": settings.config.app_env.value,
+                    },
+                }
+                if session.user_id:
+                    extra_body["user"] = session.user_id[:128]  # OpenRouter limit
+                    extra_body["posthogDistinctId"] = session.user_id
+                if session.session_id:
+                    extra_body["session_id"] = session.session_id[
+                        :128
+                    ]  # OpenRouter limit
+
                 # Create the stream with proper types
                 stream = await client.chat.completions.create(
                     model=model,
@@ -601,6 +752,7 @@ async def _stream_chat_chunks(
                     tool_choice="auto",
                     stream=True,
                     stream_options={"include_usage": True},
+                    extra_body=extra_body,
                 )
 
                 # Variables to accumulate tool calls
@@ -737,7 +889,18 @@ async def _stream_chat_chunks(
                         f"Error in stream (not retrying): {e!s}",
                         exc_info=True,
                     )
-                    error_response = StreamError(errorText=str(e))
+                    error_code = None
+                    error_text = str(e)
+                    if _is_region_blocked_error(e):
+                        error_code = "MODEL_NOT_AVAILABLE_REGION"
+                        error_text = (
+                            "This model is not available in your region. "
+                            "Please connect via VPN and try again."
+                        )
+                    error_response = StreamError(
+                        errorText=error_text,
+                        code=error_code,
+                    )
                     yield error_response
                     yield StreamFinish()
                     return

autogpt_platform/backend/backend/api/features/chat/tools/__init__.py

@@ -1,8 +1,10 @@
+import logging
 from typing import TYPE_CHECKING, Any
 
 from openai.types.chat import ChatCompletionToolParam
 
 from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tracking import track_tool_called
 
 from .add_understanding import AddUnderstandingTool
 from .agent_output import AgentOutputTool
@@ -20,6 +22,8 @@ from .search_docs import SearchDocsTool
 if TYPE_CHECKING:
     from backend.api.features.chat.response_model import StreamToolOutputAvailable
 
+logger = logging.getLogger(__name__)
+
 # Single source of truth for all tools
 TOOL_REGISTRY: dict[str, BaseTool] = {
     "add_understanding": AddUnderstandingTool(),
@@ -56,4 +60,17 @@ async def execute_tool(
     tool = TOOL_REGISTRY.get(tool_name)
     if not tool:
         raise ValueError(f"Tool {tool_name} not found")
+
+    # Track tool call in PostHog
+    logger.info(
+        f"Tracking tool call: tool={tool_name}, user={user_id}, "
+        f"session={session.session_id}, call_id={tool_call_id}"
+    )
+    track_tool_called(
+        user_id=user_id,
+        session_id=session.session_id,
+        tool_name=tool_name,
+        tool_call_id=tool_call_id,
+    )
+
     return await tool.execute(user_id, session, tool_call_id, **parameters)

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

@@ -218,6 +218,7 @@ async def save_agent_to_library(
     library_agents = await library_db.create_library_agent(
         graph=created_graph,
         user_id=user_id,
+        sensitive_action_safe_mode=True,
         create_library_agents_for_sub_graphs=False,
     )
 

autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py

@@ -8,6 +8,10 @@ from pydantic import BaseModel, Field, field_validator
 
 from backend.api.features.chat.config import ChatConfig
 from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tracking import (
+    track_agent_run_success,
+    track_agent_scheduled,
+)
 from backend.api.features.library import db as library_db
 from backend.data.graph import GraphModel
 from backend.data.model import CredentialsMetaInput
@@ -453,6 +457,16 @@ class RunAgentTool(BaseTool):
             session.successful_agent_runs.get(library_agent.graph_id, 0) + 1
         )
 
+        # Track in PostHog
+        track_agent_run_success(
+            user_id=user_id,
+            session_id=session_id,
+            graph_id=library_agent.graph_id,
+            graph_name=library_agent.name,
+            execution_id=execution.id,
+            library_agent_id=library_agent.id,
+        )
+
         library_agent_link = f"/library/agents/{library_agent.id}"
         return ExecutionStartedResponse(
             message=(
@@ -534,6 +548,18 @@ class RunAgentTool(BaseTool):
             session.successful_agent_schedules.get(library_agent.graph_id, 0) + 1
         )
 
+        # Track in PostHog
+        track_agent_scheduled(
+            user_id=user_id,
+            session_id=session_id,
+            graph_id=library_agent.graph_id,
+            graph_name=library_agent.name,
+            schedule_id=result.id,
+            schedule_name=schedule_name,
+            cron=cron,
+            library_agent_id=library_agent.id,
+        )
+
         library_agent_link = f"/library/agents/{library_agent.id}"
         return ExecutionStartedResponse(
             message=(

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

@@ -0,0 +1,250 @@
+"""PostHog analytics tracking for the chat system."""
+
+import atexit
+import logging
+from typing import Any
+
+from posthog import Posthog
+
+from backend.util.settings import Settings
+
+logger = logging.getLogger(__name__)
+settings = Settings()
+
+# PostHog client instance (lazily initialized)
+_posthog_client: Posthog | None = None
+
+
+def _shutdown_posthog() -> None:
+    """Flush and shutdown PostHog client on process exit."""
+    if _posthog_client is not None:
+        _posthog_client.flush()
+        _posthog_client.shutdown()
+
+
+atexit.register(_shutdown_posthog)
+
+
+def _get_posthog_client() -> Posthog | None:
+    """Get or create the PostHog client instance."""
+    global _posthog_client
+    if _posthog_client is not None:
+        return _posthog_client
+
+    if not settings.secrets.posthog_api_key:
+        logger.debug("PostHog API key not configured, analytics disabled")
+        return None
+
+    _posthog_client = Posthog(
+        settings.secrets.posthog_api_key,
+        host=settings.secrets.posthog_host,
+    )
+    logger.info(
+        f"PostHog client initialized with host: {settings.secrets.posthog_host}"
+    )
+    return _posthog_client
+
+
+def _get_base_properties() -> dict[str, Any]:
+    """Get base properties included in all events."""
+    return {
+        "environment": settings.config.app_env.value,
+        "source": "chat_copilot",
+    }
+
+
+def track_user_message(
+    user_id: str | None,
+    session_id: str,
+    message_length: int,
+) -> None:
+    """Track when a user sends a message in chat.
+
+    Args:
+        user_id: The user's ID (or None for anonymous)
+        session_id: The chat session ID
+        message_length: Length of the user's message
+    """
+    client = _get_posthog_client()
+    if not client:
+        return
+
+    try:
+        properties = {
+            **_get_base_properties(),
+            "session_id": session_id,
+            "message_length": message_length,
+        }
+        client.capture(
+            distinct_id=user_id or f"anonymous_{session_id}",
+            event="copilot_message_sent",
+            properties=properties,
+        )
+    except Exception as e:
+        logger.warning(f"Failed to track user message: {e}")
+
+
+def track_tool_called(
+    user_id: str | None,
+    session_id: str,
+    tool_name: str,
+    tool_call_id: str,
+) -> None:
+    """Track when a tool is called in chat.
+
+    Args:
+        user_id: The user's ID (or None for anonymous)
+        session_id: The chat session ID
+        tool_name: Name of the tool being called
+        tool_call_id: Unique ID of the tool call
+    """
+    client = _get_posthog_client()
+    if not client:
+        logger.info("PostHog client not available for tool tracking")
+        return
+
+    try:
+        properties = {
+            **_get_base_properties(),
+            "session_id": session_id,
+            "tool_name": tool_name,
+            "tool_call_id": tool_call_id,
+        }
+        distinct_id = user_id or f"anonymous_{session_id}"
+        logger.info(
+            f"Sending copilot_tool_called event to PostHog: distinct_id={distinct_id}, "
+            f"tool_name={tool_name}"
+        )
+        client.capture(
+            distinct_id=distinct_id,
+            event="copilot_tool_called",
+            properties=properties,
+        )
+    except Exception as e:
+        logger.warning(f"Failed to track tool call: {e}")
+
+
+def track_agent_run_success(
+    user_id: str,
+    session_id: str,
+    graph_id: str,
+    graph_name: str,
+    execution_id: str,
+    library_agent_id: str,
+) -> None:
+    """Track when an agent is successfully run.
+
+    Args:
+        user_id: The user's ID
+        session_id: The chat session ID
+        graph_id: ID of the agent graph
+        graph_name: Name of the agent
+        execution_id: ID of the execution
+        library_agent_id: ID of the library agent
+    """
+    client = _get_posthog_client()
+    if not client:
+        return
+
+    try:
+        properties = {
+            **_get_base_properties(),
+            "session_id": session_id,
+            "graph_id": graph_id,
+            "graph_name": graph_name,
+            "execution_id": execution_id,
+            "library_agent_id": library_agent_id,
+        }
+        client.capture(
+            distinct_id=user_id,
+            event="copilot_agent_run_success",
+            properties=properties,
+        )
+    except Exception as e:
+        logger.warning(f"Failed to track agent run: {e}")
+
+
+def track_agent_scheduled(
+    user_id: str,
+    session_id: str,
+    graph_id: str,
+    graph_name: str,
+    schedule_id: str,
+    schedule_name: str,
+    cron: str,
+    library_agent_id: str,
+) -> None:
+    """Track when an agent is successfully scheduled.
+
+    Args:
+        user_id: The user's ID
+        session_id: The chat session ID
+        graph_id: ID of the agent graph
+        graph_name: Name of the agent
+        schedule_id: ID of the schedule
+        schedule_name: Name of the schedule
+        cron: Cron expression for the schedule
+        library_agent_id: ID of the library agent
+    """
+    client = _get_posthog_client()
+    if not client:
+        return
+
+    try:
+        properties = {
+            **_get_base_properties(),
+            "session_id": session_id,
+            "graph_id": graph_id,
+            "graph_name": graph_name,
+            "schedule_id": schedule_id,
+            "schedule_name": schedule_name,
+            "cron": cron,
+            "library_agent_id": library_agent_id,
+        }
+        client.capture(
+            distinct_id=user_id,
+            event="copilot_agent_scheduled",
+            properties=properties,
+        )
+    except Exception as e:
+        logger.warning(f"Failed to track agent schedule: {e}")
+
+
+def track_trigger_setup(
+    user_id: str,
+    session_id: str,
+    graph_id: str,
+    graph_name: str,
+    trigger_type: str,
+    library_agent_id: str,
+) -> None:
+    """Track when a trigger is set up for an agent.
+
+    Args:
+        user_id: The user's ID
+        session_id: The chat session ID
+        graph_id: ID of the agent graph
+        graph_name: Name of the agent
+        trigger_type: Type of trigger (e.g., 'webhook')
+        library_agent_id: ID of the library agent
+    """
+    client = _get_posthog_client()
+    if not client:
+        return
+
+    try:
+        properties = {
+            **_get_base_properties(),
+            "session_id": session_id,
+            "graph_id": graph_id,
+            "graph_name": graph_name,
+            "trigger_type": trigger_type,
+            "library_agent_id": library_agent_id,
+        }
+        client.capture(
+            distinct_id=user_id,
+            event="copilot_trigger_setup",
+            properties=properties,
+        )
+    except Exception as e:
+        logger.warning(f"Failed to track trigger setup: {e}")

autogpt_platform/backend/backend/api/features/library/db.py

@@ -401,27 +401,11 @@ async def add_generated_agent_image(
     )
 
 
-def _initialize_graph_settings(graph: graph_db.GraphModel) -> GraphSettings:
-    """
-    Initialize GraphSettings based on graph content.
-
-    Args:
-        graph: The graph to analyze
-
-    Returns:
-        GraphSettings with appropriate human_in_the_loop_safe_mode value
-    """
-    if graph.has_human_in_the_loop:
-        # Graph has HITL blocks - set safe mode to True by default
-        return GraphSettings(human_in_the_loop_safe_mode=True)
-    else:
-        # Graph has no HITL blocks - keep None
-        return GraphSettings(human_in_the_loop_safe_mode=None)
-
-
 async def create_library_agent(
     graph: graph_db.GraphModel,
     user_id: str,
+    hitl_safe_mode: bool = True,
+    sensitive_action_safe_mode: bool = False,
     create_library_agents_for_sub_graphs: bool = True,
 ) -> list[library_model.LibraryAgent]:
     """
@@ -430,6 +414,8 @@ async def create_library_agent(
     Args:
         agent: The agent/Graph to add to the library.
         user_id: The user to whom the agent will be added.
+        hitl_safe_mode: Whether HITL blocks require manual review (default True).
+        sensitive_action_safe_mode: Whether sensitive action blocks require review.
         create_library_agents_for_sub_graphs: If True, creates LibraryAgent records for sub-graphs as well.
 
     Returns:
@@ -465,7 +451,11 @@ async def create_library_agent(
                             }
                         },
                         settings=SafeJson(
-                            _initialize_graph_settings(graph_entry).model_dump()
+                            GraphSettings.from_graph(
+                                graph_entry,
+                                hitl_safe_mode=hitl_safe_mode,
+                                sensitive_action_safe_mode=sensitive_action_safe_mode,
+                            ).model_dump()
                         ),
                     ),
                     include=library_agent_include(
@@ -627,33 +617,6 @@ async def update_library_agent(
         raise DatabaseError("Failed to update library agent") from e
 
 
-async def update_library_agent_settings(
-    user_id: str,
-    agent_id: str,
-    settings: GraphSettings,
-) -> library_model.LibraryAgent:
-    """
-    Updates the settings for a specific LibraryAgent.
-
-    Args:
-        user_id: The owner of the LibraryAgent.
-        agent_id: The ID of the LibraryAgent to update.
-        settings: New GraphSettings to apply.
-
-    Returns:
-        The updated LibraryAgent.
-
-    Raises:
-        NotFoundError: If the specified LibraryAgent does not exist.
-        DatabaseError: If there's an error in the update operation.
-    """
-    return await update_library_agent(
-        library_agent_id=agent_id,
-        user_id=user_id,
-        settings=settings,
-    )
-
-
 async def delete_library_agent(
     library_agent_id: str, user_id: str, soft_delete: bool = True
 ) -> None:
@@ -838,7 +801,7 @@ async def add_store_agent_to_library(
                 "isCreatedByUser": False,
                 "useGraphIsActiveVersion": False,
                 "settings": SafeJson(
-                    _initialize_graph_settings(graph_model).model_dump()
+                    GraphSettings.from_graph(graph_model).model_dump()
                 ),
             },
             include=library_agent_include(
@@ -1228,8 +1191,15 @@ async def fork_library_agent(
         )
         new_graph = await on_graph_activate(new_graph, user_id=user_id)
 
-        # Create a library agent for the new graph
-        return (await create_library_agent(new_graph, user_id))[0]
+        # Create a library agent for the new graph, preserving safe mode settings
+        return (
+            await create_library_agent(
+                new_graph,
+                user_id,
+                hitl_safe_mode=original_agent.settings.human_in_the_loop_safe_mode,
+                sensitive_action_safe_mode=original_agent.settings.sensitive_action_safe_mode,
+            )
+        )[0]
     except prisma.errors.PrismaError as e:
         logger.error(f"Database error cloning library agent: {e}")
         raise DatabaseError("Failed to fork library agent") from e

autogpt_platform/backend/backend/api/features/library/model.py

@@ -73,6 +73,12 @@ class LibraryAgent(pydantic.BaseModel):
     has_external_trigger: bool = pydantic.Field(
         description="Whether the agent has an external trigger (e.g. webhook) node"
     )
+    has_human_in_the_loop: bool = pydantic.Field(
+        description="Whether the agent has human-in-the-loop blocks"
+    )
+    has_sensitive_action: bool = pydantic.Field(
+        description="Whether the agent has sensitive action blocks"
+    )
     trigger_setup_info: Optional[GraphTriggerInfo] = None
 
     # Indicates whether there's a new output (based on recent runs)
@@ -180,6 +186,8 @@ class LibraryAgent(pydantic.BaseModel):
                 graph.credentials_input_schema if sub_graphs is not None else None
             ),
             has_external_trigger=graph.has_external_trigger,
+            has_human_in_the_loop=graph.has_human_in_the_loop,
+            has_sensitive_action=graph.has_sensitive_action,
             trigger_setup_info=graph.trigger_setup_info,
             new_output=new_output,
             can_access_graph=can_access_graph,

autogpt_platform/backend/backend/api/features/library/routes_test.py

@@ -52,6 +52,8 @@ async def test_get_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
+                has_human_in_the_loop=False,
+                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -75,6 +77,8 @@ async def test_get_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
+                has_human_in_the_loop=False,
+                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -150,6 +154,8 @@ async def test_get_favorite_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
+                has_human_in_the_loop=False,
+                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -218,6 +224,8 @@ def test_add_agent_to_library_success(
         output_schema={"type": "object", "properties": {}},
         credentials_input_schema={"type": "object", "properties": {}},
         has_external_trigger=False,
+        has_human_in_the_loop=False,
+        has_sensitive_action=False,
         status=library_model.LibraryAgentStatus.COMPLETED,
         new_output=False,
         can_access_graph=True,

autogpt_platform/backend/backend/api/features/store/embeddings.py

@@ -154,16 +154,16 @@ async def store_content_embedding(
 
         # Upsert the embedding
         # WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
-        # Use {pgvector_schema}.vector for explicit pgvector type qualification
+        # Use unqualified ::vector - pgvector is in search_path on all environments
         await execute_raw_with_schema(
             """
             INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
                 "id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
             )
-            VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::{pgvector_schema}.vector, $5, $6::jsonb, NOW(), NOW())
+            VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
             ON CONFLICT ("contentType", "contentId", "userId")
             DO UPDATE SET
-                "embedding" = $4::{pgvector_schema}.vector,
+                "embedding" = $4::vector,
                 "searchableText" = $5,
                 "metadata" = $6::jsonb,
                 "updatedAt" = NOW()
@@ -879,8 +879,7 @@ async def semantic_search(
         min_similarity_idx = len(params) + 1
         params.append(min_similarity)
 
-        # Use regular string (not f-string) for template to preserve {schema_prefix} and {schema} placeholders
-        # Use OPERATOR({pgvector_schema}.<=>) for explicit operator schema qualification
+        # Use unqualified ::vector and <=> operator - pgvector is in search_path on all environments
         sql = (
             """
             SELECT
@@ -888,9 +887,9 @@ async def semantic_search(
                 "contentType" as content_type,
                 "searchableText" as searchable_text,
                 metadata,
-                1 - (embedding OPERATOR({pgvector_schema}.<=>) '"""
+                1 - (embedding <=> '"""
             + embedding_str
-            + """'::{pgvector_schema}.vector) as similarity
+            + """'::vector) as similarity
             FROM {schema_prefix}"UnifiedContentEmbedding"
             WHERE "contentType" IN ("""
             + content_type_placeholders
@@ -898,9 +897,9 @@ async def semantic_search(
             """
             + user_filter
             + """
-            AND 1 - (embedding OPERATOR({pgvector_schema}.<=>) '"""
+            AND 1 - (embedding <=> '"""
             + embedding_str
-            + """'::{pgvector_schema}.vector) >= $"""
+            + """'::vector) >= $"""
             + str(min_similarity_idx)
             + """
             ORDER BY similarity DESC

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -295,7 +295,7 @@ async def unified_hybrid_search(
                 FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
                 WHERE uce."contentType" = ANY({content_types_param}::{{schema_prefix}}"ContentType"[])
                 {user_filter}
-                ORDER BY uce.embedding OPERATOR({{pgvector_schema}}.<=>)  {embedding_param}::{{pgvector_schema}}.vector
+                ORDER BY uce.embedding <=> {embedding_param}::vector
                 LIMIT 200
             )
         ),
@@ -307,7 +307,7 @@ async def unified_hybrid_search(
                 uce.metadata,
                 uce."updatedAt" as updated_at,
                 -- Semantic score: cosine similarity (1 - distance)
-                COALESCE(1 - (uce.embedding OPERATOR({{pgvector_schema}}.<=>)  {embedding_param}::{{pgvector_schema}}.vector), 0) as semantic_score,
+                COALESCE(1 - (uce.embedding <=> {embedding_param}::vector), 0) as semantic_score,
                 -- Lexical score: ts_rank_cd
                 COALESCE(ts_rank_cd(uce.search, plainto_tsquery('english', {query_param})), 0) as lexical_raw,
                 -- Category match from metadata
@@ -583,7 +583,7 @@ async def hybrid_search(
                 WHERE uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
                 AND uce."userId" IS NULL
                 AND {where_clause}
-                ORDER BY uce.embedding OPERATOR({{pgvector_schema}}.<=>)  {embedding_param}::{{pgvector_schema}}.vector
+                ORDER BY uce.embedding <=> {embedding_param}::vector
                 LIMIT 200
             ) uce
         ),
@@ -605,7 +605,7 @@ async def hybrid_search(
                 -- Searchable text for BM25 reranking
                 COALESCE(sa.agent_name, '') || ' ' || COALESCE(sa.sub_heading, '') || ' ' || COALESCE(sa.description, '') as searchable_text,
                 -- Semantic score
-                COALESCE(1 - (uce.embedding OPERATOR({{pgvector_schema}}.<=>)  {embedding_param}::{{pgvector_schema}}.vector), 0) as semantic_score,
+                COALESCE(1 - (uce.embedding <=> {embedding_param}::vector), 0) as semantic_score,
                 -- Lexical score (raw, will normalize)
                 COALESCE(ts_rank_cd(uce.search, plainto_tsquery('english', {query_param})), 0) as lexical_raw,
                 -- Category match

autogpt_platform/backend/backend/api/features/v1.py

@@ -761,10 +761,8 @@ async def create_new_graph(
     graph.reassign_ids(user_id=user_id, reassign_graph_id=True)
     graph.validate_graph(for_run=False)
 
-    # The return value of the create graph & library function is intentionally not used here,
-    # as the graph already valid and no sub-graphs are returned back.
     await graph_db.create_graph(graph, user_id=user_id)
-    await library_db.create_library_agent(graph, user_id=user_id)
+    await library_db.create_library_agent(graph, user_id)
     activated_graph = await on_graph_activate(graph, user_id=user_id)
 
     if create_graph.source == "builder":
@@ -888,21 +886,19 @@ async def set_graph_active_version(
 async def _update_library_agent_version_and_settings(
     user_id: str, agent_graph: graph_db.GraphModel
 ) -> library_model.LibraryAgent:
-    # Keep the library agent up to date with the new active version
     library = await library_db.update_agent_version_in_library(
         user_id, agent_graph.id, agent_graph.version
     )
-    # If the graph has HITL node, initialize the setting if it's not already set.
-    if (
-        agent_graph.has_human_in_the_loop
-        and library.settings.human_in_the_loop_safe_mode is None
-    ):
-        await library_db.update_library_agent_settings(
+    updated_settings = GraphSettings.from_graph(
+        graph=agent_graph,
+        hitl_safe_mode=library.settings.human_in_the_loop_safe_mode,
+        sensitive_action_safe_mode=library.settings.sensitive_action_safe_mode,
+    )
+    if updated_settings != library.settings:
+        library = await library_db.update_library_agent(
+            library_agent_id=library.id,
             user_id=user_id,
-            agent_id=library.id,
-            settings=library.settings.model_copy(
-                update={"human_in_the_loop_safe_mode": True}
-            ),
+            settings=updated_settings,
         )
     return library
 
@@ -919,21 +915,18 @@ async def update_graph_settings(
     user_id: Annotated[str, Security(get_user_id)],
 ) -> GraphSettings:
     """Update graph settings for the user's library agent."""
-    # Get the library agent for this graph
     library_agent = await library_db.get_library_agent_by_graph_id(
         graph_id=graph_id, user_id=user_id
     )
     if not library_agent:
         raise HTTPException(404, f"Graph #{graph_id} not found in user's library")
 
-    # Update the library agent settings
-    updated_agent = await library_db.update_library_agent_settings(
+    updated_agent = await library_db.update_library_agent(
+        library_agent_id=library_agent.id,
         user_id=user_id,
-        agent_id=library_agent.id,
         settings=settings,
     )
 
-    # Return the updated settings
     return GraphSettings.model_validate(updated_agent.settings)
 
 

autogpt_platform/backend/backend/blocks/claude_code.py

@@ -0,0 +1,659 @@
+import json
+import shlex
+import uuid
+from typing import Literal, Optional
+
+from e2b import AsyncSandbox as BaseAsyncSandbox
+from pydantic import BaseModel, SecretStr
+
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.model import (
+    APIKeyCredentials,
+    CredentialsField,
+    CredentialsMetaInput,
+    SchemaField,
+)
+from backend.integrations.providers import ProviderName
+
+
+class ClaudeCodeExecutionError(Exception):
+    """Exception raised when Claude Code execution fails.
+
+    Carries the sandbox_id so it can be returned to the user for cleanup
+    when dispose_sandbox=False.
+    """
+
+    def __init__(self, message: str, sandbox_id: str = ""):
+        super().__init__(message)
+        self.sandbox_id = sandbox_id
+
+
+# Test credentials for E2B
+TEST_E2B_CREDENTIALS = APIKeyCredentials(
+    id="01234567-89ab-cdef-0123-456789abcdef",
+    provider="e2b",
+    api_key=SecretStr("mock-e2b-api-key"),
+    title="Mock E2B API key",
+    expires_at=None,
+)
+TEST_E2B_CREDENTIALS_INPUT = {
+    "provider": TEST_E2B_CREDENTIALS.provider,
+    "id": TEST_E2B_CREDENTIALS.id,
+    "type": TEST_E2B_CREDENTIALS.type,
+    "title": TEST_E2B_CREDENTIALS.title,
+}
+
+# Test credentials for Anthropic
+TEST_ANTHROPIC_CREDENTIALS = APIKeyCredentials(
+    id="2e568a2b-b2ea-475a-8564-9a676bf31c56",
+    provider="anthropic",
+    api_key=SecretStr("mock-anthropic-api-key"),
+    title="Mock Anthropic API key",
+    expires_at=None,
+)
+TEST_ANTHROPIC_CREDENTIALS_INPUT = {
+    "provider": TEST_ANTHROPIC_CREDENTIALS.provider,
+    "id": TEST_ANTHROPIC_CREDENTIALS.id,
+    "type": TEST_ANTHROPIC_CREDENTIALS.type,
+    "title": TEST_ANTHROPIC_CREDENTIALS.title,
+}
+
+
+class ClaudeCodeBlock(Block):
+    """
+    Execute tasks using Claude Code (Anthropic's AI coding assistant) in an E2B sandbox.
+
+    Claude Code can create files, install tools, run commands, and perform complex
+    coding tasks autonomously within a secure sandbox environment.
+    """
+
+    # Use base template - we'll install Claude Code ourselves for latest version
+    DEFAULT_TEMPLATE = "base"
+
+    class Input(BlockSchemaInput):
+        e2b_credentials: CredentialsMetaInput[
+            Literal[ProviderName.E2B], Literal["api_key"]
+        ] = CredentialsField(
+            description=(
+                "API key for the E2B platform to create the sandbox. "
+                "Get one on the [e2b website](https://e2b.dev/docs)"
+            ),
+        )
+
+        anthropic_credentials: CredentialsMetaInput[
+            Literal[ProviderName.ANTHROPIC], Literal["api_key"]
+        ] = CredentialsField(
+            description=(
+                "API key for Anthropic to power Claude Code. "
+                "Get one at [Anthropic's website](https://console.anthropic.com)"
+            ),
+        )
+
+        prompt: str = SchemaField(
+            description=(
+                "The task or instruction for Claude Code to execute. "
+                "Claude Code can create files, install packages, run commands, "
+                "and perform complex coding tasks."
+            ),
+            placeholder="Create a hello world index.html file",
+            default="",
+            advanced=False,
+        )
+
+        timeout: int = SchemaField(
+            description=(
+                "Sandbox timeout in seconds. Claude Code tasks can take "
+                "a while, so set this appropriately for your task complexity. "
+                "Note: This only applies when creating a new sandbox. "
+                "When reconnecting to an existing sandbox via sandbox_id, "
+                "the original timeout is retained."
+            ),
+            default=300,  # 5 minutes default
+            advanced=True,
+        )
+
+        setup_commands: list[str] = SchemaField(
+            description=(
+                "Optional shell commands to run before executing Claude Code. "
+                "Useful for installing dependencies or setting up the environment."
+            ),
+            default_factory=list,
+            advanced=True,
+        )
+
+        working_directory: str = SchemaField(
+            description="Working directory for Claude Code to operate in.",
+            default="/home/user",
+            advanced=True,
+        )
+
+        # Session/continuation support
+        session_id: str = SchemaField(
+            description=(
+                "Session ID to resume a previous conversation. "
+                "Leave empty for a new conversation. "
+                "Use the session_id from a previous run to continue that conversation."
+            ),
+            default="",
+            advanced=True,
+        )
+
+        sandbox_id: str = SchemaField(
+            description=(
+                "Sandbox ID to reconnect to an existing sandbox. "
+                "Required when resuming a session (along with session_id). "
+                "Use the sandbox_id from a previous run where dispose_sandbox was False."
+            ),
+            default="",
+            advanced=True,
+        )
+
+        conversation_history: str = SchemaField(
+            description=(
+                "Previous conversation history to continue from. "
+                "Use this to restore context on a fresh sandbox if the previous one timed out. "
+                "Pass the conversation_history output from a previous run."
+            ),
+            default="",
+            advanced=True,
+        )
+
+        dispose_sandbox: bool = SchemaField(
+            description=(
+                "Whether to dispose of the sandbox immediately after execution. "
+                "Set to False if you want to continue the conversation later "
+                "(you'll need both sandbox_id and session_id from the output)."
+            ),
+            default=True,
+            advanced=True,
+        )
+
+    class FileOutput(BaseModel):
+        """A file extracted from the sandbox."""
+
+        path: str
+        relative_path: str  # Path relative to working directory (for GitHub, etc.)
+        name: str
+        content: str
+
+    class Output(BlockSchemaOutput):
+        response: str = SchemaField(
+            description="The output/response from Claude Code execution"
+        )
+        files: list["ClaudeCodeBlock.FileOutput"] = SchemaField(
+            description=(
+                "List of text files created/modified by Claude Code during this execution. "
+                "Each file has 'path', 'relative_path', 'name', and 'content' fields."
+            )
+        )
+        conversation_history: str = SchemaField(
+            description=(
+                "Full conversation history including this turn. "
+                "Pass this to conversation_history input to continue on a fresh sandbox "
+                "if the previous sandbox timed out."
+            )
+        )
+        session_id: str = SchemaField(
+            description=(
+                "Session ID for this conversation. "
+                "Pass this back along with sandbox_id to continue the conversation."
+            )
+        )
+        sandbox_id: Optional[str] = SchemaField(
+            description=(
+                "ID of the sandbox instance. "
+                "Pass this back along with session_id to continue the conversation. "
+                "This is None if dispose_sandbox was True (sandbox was disposed)."
+            ),
+            default=None,
+        )
+        error: str = SchemaField(description="Error message if execution failed")
+
+    def __init__(self):
+        super().__init__(
+            id="4e34f4a5-9b89-4326-ba77-2dd6750b7194",
+            description=(
+                "Execute tasks using Claude Code in an E2B sandbox. "
+                "Claude Code can create files, install tools, run commands, "
+                "and perform complex coding tasks autonomously."
+            ),
+            categories={BlockCategory.DEVELOPER_TOOLS, BlockCategory.AI},
+            input_schema=ClaudeCodeBlock.Input,
+            output_schema=ClaudeCodeBlock.Output,
+            test_credentials={
+                "e2b_credentials": TEST_E2B_CREDENTIALS,
+                "anthropic_credentials": TEST_ANTHROPIC_CREDENTIALS,
+            },
+            test_input={
+                "e2b_credentials": TEST_E2B_CREDENTIALS_INPUT,
+                "anthropic_credentials": TEST_ANTHROPIC_CREDENTIALS_INPUT,
+                "prompt": "Create a hello world HTML file",
+                "timeout": 300,
+                "setup_commands": [],
+                "working_directory": "/home/user",
+                "session_id": "",
+                "sandbox_id": "",
+                "conversation_history": "",
+                "dispose_sandbox": True,
+            },
+            test_output=[
+                ("response", "Created index.html with hello world content"),
+                (
+                    "files",
+                    [
+                        {
+                            "path": "/home/user/index.html",
+                            "relative_path": "index.html",
+                            "name": "index.html",
+                            "content": "<html>Hello World</html>",
+                        }
+                    ],
+                ),
+                (
+                    "conversation_history",
+                    "User: Create a hello world HTML file\n"
+                    "Claude: Created index.html with hello world content",
+                ),
+                ("session_id", str),
+                ("sandbox_id", None),  # None because dispose_sandbox=True in test_input
+            ],
+            test_mock={
+                "execute_claude_code": lambda *args, **kwargs: (
+                    "Created index.html with hello world content",  # response
+                    [
+                        ClaudeCodeBlock.FileOutput(
+                            path="/home/user/index.html",
+                            relative_path="index.html",
+                            name="index.html",
+                            content="<html>Hello World</html>",
+                        )
+                    ],  # files
+                    "User: Create a hello world HTML file\n"
+                    "Claude: Created index.html with hello world content",  # conversation_history
+                    "test-session-id",  # session_id
+                    "sandbox_id",  # sandbox_id
+                ),
+            },
+        )
+
+    async def execute_claude_code(
+        self,
+        e2b_api_key: str,
+        anthropic_api_key: str,
+        prompt: str,
+        timeout: int,
+        setup_commands: list[str],
+        working_directory: str,
+        session_id: str,
+        existing_sandbox_id: str,
+        conversation_history: str,
+        dispose_sandbox: bool,
+    ) -> tuple[str, list["ClaudeCodeBlock.FileOutput"], str, str, str]:
+        """
+        Execute Claude Code in an E2B sandbox.
+
+        Returns:
+            Tuple of (response, files, conversation_history, session_id, sandbox_id)
+        """
+
+        # Validate that sandbox_id is provided when resuming a session
+        if session_id and not existing_sandbox_id:
+            raise ValueError(
+                "sandbox_id is required when resuming a session with session_id. "
+                "The session state is stored in the original sandbox. "
+                "If the sandbox has timed out, use conversation_history instead "
+                "to restore context on a fresh sandbox."
+            )
+
+        sandbox = None
+        sandbox_id = ""
+
+        try:
+            # Either reconnect to existing sandbox or create a new one
+            if existing_sandbox_id:
+                # Reconnect to existing sandbox for conversation continuation
+                sandbox = await BaseAsyncSandbox.connect(
+                    sandbox_id=existing_sandbox_id,
+                    api_key=e2b_api_key,
+                )
+            else:
+                # Create new sandbox
+                sandbox = await BaseAsyncSandbox.create(
+                    template=self.DEFAULT_TEMPLATE,
+                    api_key=e2b_api_key,
+                    timeout=timeout,
+                    envs={"ANTHROPIC_API_KEY": anthropic_api_key},
+                )
+
+                # Install Claude Code from npm (ensures we get the latest version)
+                install_result = await sandbox.commands.run(
+                    "npm install -g @anthropic-ai/claude-code@latest",
+                    timeout=120,  # 2 min timeout for install
+                )
+                if install_result.exit_code != 0:
+                    raise Exception(
+                        f"Failed to install Claude Code: {install_result.stderr}"
+                    )
+
+                # Run any user-provided setup commands
+                for cmd in setup_commands:
+                    setup_result = await sandbox.commands.run(cmd)
+                    if setup_result.exit_code != 0:
+                        raise Exception(
+                            f"Setup command failed: {cmd}\n"
+                            f"Exit code: {setup_result.exit_code}\n"
+                            f"Stdout: {setup_result.stdout}\n"
+                            f"Stderr: {setup_result.stderr}"
+                        )
+
+            # Capture sandbox_id immediately after creation/connection
+            # so it's available for error recovery if dispose_sandbox=False
+            sandbox_id = sandbox.sandbox_id
+
+            # Generate or use provided session ID
+            current_session_id = session_id if session_id else str(uuid.uuid4())
+
+            # Build base Claude flags
+            base_flags = "-p --dangerously-skip-permissions --output-format json"
+
+            # Add conversation history context if provided (for fresh sandbox continuation)
+            history_flag = ""
+            if conversation_history and not session_id:
+                # Inject previous conversation as context via system prompt
+                # Use consistent escaping via _escape_prompt helper
+                escaped_history = self._escape_prompt(
+                    f"Previous conversation context: {conversation_history}"
+                )
+                history_flag = f" --append-system-prompt {escaped_history}"
+
+            # Build Claude command based on whether we're resuming or starting new
+            # Use shlex.quote for working_directory and session IDs to prevent injection
+            safe_working_dir = shlex.quote(working_directory)
+            if session_id:
+                # Resuming existing session (sandbox still alive)
+                safe_session_id = shlex.quote(session_id)
+                claude_command = (
+                    f"cd {safe_working_dir} && "
+                    f"echo {self._escape_prompt(prompt)} | "
+                    f"claude --resume {safe_session_id} {base_flags}"
+                )
+            else:
+                # New session with specific ID
+                safe_current_session_id = shlex.quote(current_session_id)
+                claude_command = (
+                    f"cd {safe_working_dir} && "
+                    f"echo {self._escape_prompt(prompt)} | "
+                    f"claude --session-id {safe_current_session_id} {base_flags}{history_flag}"
+                )
+
+            # Capture timestamp before running Claude Code to filter files later
+            # Capture timestamp 1 second in the past to avoid race condition with file creation
+            timestamp_result = await sandbox.commands.run(
+                "date -u -d '1 second ago' +%Y-%m-%dT%H:%M:%S"
+            )
+            if timestamp_result.exit_code != 0:
+                raise RuntimeError(
+                    f"Failed to capture timestamp: {timestamp_result.stderr}"
+                )
+            start_timestamp = (
+                timestamp_result.stdout.strip() if timestamp_result.stdout else None
+            )
+
+            result = await sandbox.commands.run(
+                claude_command,
+                timeout=0,  # No command timeout - let sandbox timeout handle it
+            )
+
+            # Check for command failure
+            if result.exit_code != 0:
+                error_msg = result.stderr or result.stdout or "Unknown error"
+                raise Exception(
+                    f"Claude Code command failed with exit code {result.exit_code}:\n"
+                    f"{error_msg}"
+                )
+
+            raw_output = result.stdout or ""
+
+            # Parse JSON output to extract response and build conversation history
+            response = ""
+            new_conversation_history = conversation_history or ""
+
+            try:
+                # The JSON output contains the result
+                output_data = json.loads(raw_output)
+                response = output_data.get("result", raw_output)
+
+                # Build conversation history entry
+                turn_entry = f"User: {prompt}\nClaude: {response}"
+                if new_conversation_history:
+                    new_conversation_history = (
+                        f"{new_conversation_history}\n\n{turn_entry}"
+                    )
+                else:
+                    new_conversation_history = turn_entry
+
+            except json.JSONDecodeError:
+                # If not valid JSON, use raw output
+                response = raw_output
+                turn_entry = f"User: {prompt}\nClaude: {response}"
+                if new_conversation_history:
+                    new_conversation_history = (
+                        f"{new_conversation_history}\n\n{turn_entry}"
+                    )
+                else:
+                    new_conversation_history = turn_entry
+
+            # Extract files created/modified during this run
+            files = await self._extract_files(
+                sandbox, working_directory, start_timestamp
+            )
+
+            return (
+                response,
+                files,
+                new_conversation_history,
+                current_session_id,
+                sandbox_id,
+            )
+
+        except Exception as e:
+            # Wrap exception with sandbox_id so caller can access/cleanup
+            # the preserved sandbox when dispose_sandbox=False
+            raise ClaudeCodeExecutionError(str(e), sandbox_id) from e
+
+        finally:
+            if dispose_sandbox and sandbox:
+                await sandbox.kill()
+
+    async def _extract_files(
+        self,
+        sandbox: BaseAsyncSandbox,
+        working_directory: str,
+        since_timestamp: str | None = None,
+    ) -> list["ClaudeCodeBlock.FileOutput"]:
+        """
+        Extract text files created/modified during this Claude Code execution.
+
+        Args:
+            sandbox: The E2B sandbox instance
+            working_directory: Directory to search for files
+            since_timestamp: ISO timestamp - only return files modified after this time
+
+        Returns:
+            List of FileOutput objects with path, relative_path, name, and content
+        """
+        files: list[ClaudeCodeBlock.FileOutput] = []
+
+        # Text file extensions we can safely read as text
+        text_extensions = {
+            ".txt",
+            ".md",
+            ".html",
+            ".htm",
+            ".css",
+            ".js",
+            ".ts",
+            ".jsx",
+            ".tsx",
+            ".json",
+            ".xml",
+            ".yaml",
+            ".yml",
+            ".toml",
+            ".ini",
+            ".cfg",
+            ".conf",
+            ".py",
+            ".rb",
+            ".php",
+            ".java",
+            ".c",
+            ".cpp",
+            ".h",
+            ".hpp",
+            ".cs",
+            ".go",
+            ".rs",
+            ".swift",
+            ".kt",
+            ".scala",
+            ".sh",
+            ".bash",
+            ".zsh",
+            ".sql",
+            ".graphql",
+            ".env",
+            ".gitignore",
+            ".dockerfile",
+            "Dockerfile",
+            ".vue",
+            ".svelte",
+            ".astro",
+            ".mdx",
+            ".rst",
+            ".tex",
+            ".csv",
+            ".log",
+        }
+
+        try:
+            # List files recursively using find command
+            # Exclude node_modules and .git directories, but allow hidden files
+            # like .env and .gitignore (they're filtered by text_extensions later)
+            # Filter by timestamp to only get files created/modified during this run
+            safe_working_dir = shlex.quote(working_directory)
+            timestamp_filter = ""
+            if since_timestamp:
+                timestamp_filter = f"-newermt {shlex.quote(since_timestamp)} "
+            find_result = await sandbox.commands.run(
+                f"find {safe_working_dir} -type f "
+                f"{timestamp_filter}"
+                f"-not -path '*/node_modules/*' "
+                f"-not -path '*/.git/*' "
+                f"2>/dev/null"
+            )
+
+            if find_result.stdout:
+                for file_path in find_result.stdout.strip().split("\n"):
+                    if not file_path:
+                        continue
+
+                    # Check if it's a text file we can read
+                    is_text = any(
+                        file_path.endswith(ext) for ext in text_extensions
+                    ) or file_path.endswith("Dockerfile")
+
+                    if is_text:
+                        try:
+                            content = await sandbox.files.read(file_path)
+                            # Handle bytes or string
+                            if isinstance(content, bytes):
+                                content = content.decode("utf-8", errors="replace")
+
+                            # Extract filename from path
+                            file_name = file_path.split("/")[-1]
+
+                            # Calculate relative path by stripping working directory
+                            relative_path = file_path
+                            if file_path.startswith(working_directory):
+                                relative_path = file_path[len(working_directory) :]
+                                # Remove leading slash if present
+                                if relative_path.startswith("/"):
+                                    relative_path = relative_path[1:]
+
+                            files.append(
+                                ClaudeCodeBlock.FileOutput(
+                                    path=file_path,
+                                    relative_path=relative_path,
+                                    name=file_name,
+                                    content=content,
+                                )
+                            )
+                        except Exception:
+                            # Skip files that can't be read
+                            pass
+
+        except Exception:
+            # If file extraction fails, return empty results
+            pass
+
+        return files
+
+    def _escape_prompt(self, prompt: str) -> str:
+        """Escape the prompt for safe shell execution."""
+        # Use single quotes and escape any single quotes in the prompt
+        escaped = prompt.replace("'", "'\"'\"'")
+        return f"'{escaped}'"
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        e2b_credentials: APIKeyCredentials,
+        anthropic_credentials: APIKeyCredentials,
+        **kwargs,
+    ) -> BlockOutput:
+        try:
+            (
+                response,
+                files,
+                conversation_history,
+                session_id,
+                sandbox_id,
+            ) = await self.execute_claude_code(
+                e2b_api_key=e2b_credentials.api_key.get_secret_value(),
+                anthropic_api_key=anthropic_credentials.api_key.get_secret_value(),
+                prompt=input_data.prompt,
+                timeout=input_data.timeout,
+                setup_commands=input_data.setup_commands,
+                working_directory=input_data.working_directory,
+                session_id=input_data.session_id,
+                existing_sandbox_id=input_data.sandbox_id,
+                conversation_history=input_data.conversation_history,
+                dispose_sandbox=input_data.dispose_sandbox,
+            )
+
+            yield "response", response
+            # Always yield files (empty list if none) to match Output schema
+            yield "files", [f.model_dump() for f in files]
+            # Always yield conversation_history so user can restore context on fresh sandbox
+            yield "conversation_history", conversation_history
+            # Always yield session_id so user can continue conversation
+            yield "session_id", session_id
+            # Always yield sandbox_id (None if disposed) to match Output schema
+            yield "sandbox_id", sandbox_id if not input_data.dispose_sandbox else None
+
+        except ClaudeCodeExecutionError as e:
+            yield "error", str(e)
+            # If sandbox was preserved (dispose_sandbox=False), yield sandbox_id
+            # so user can reconnect to or clean up the orphaned sandbox
+            if not input_data.dispose_sandbox and e.sandbox_id:
+                yield "sandbox_id", e.sandbox_id
+        except Exception as e:
+            yield "error", str(e)

autogpt_platform/backend/backend/blocks/helpers/review.py

@@ -84,7 +84,7 @@ class HITLReviewHelper:
             Exception: If review creation or status update fails
         """
         # Skip review if safe mode is disabled - return auto-approved result
-        if not execution_context.safe_mode:
+        if not execution_context.human_in_the_loop_safe_mode:
             logger.info(
                 f"Block {block_name} skipping review for node {node_exec_id} - safe mode disabled"
             )

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -104,7 +104,7 @@ class HumanInTheLoopBlock(Block):
         execution_context: ExecutionContext,
         **_kwargs,
     ) -> BlockOutput:
-        if not execution_context.safe_mode:
+        if not execution_context.human_in_the_loop_safe_mode:
             logger.info(
                 f"HITL block skipping review for node {node_exec_id} - safe mode disabled"
             )

autogpt_platform/backend/backend/blocks/llm.py

@@ -79,6 +79,10 @@ class ModelMetadata(NamedTuple):
     provider: str
     context_window: int
     max_output_tokens: int | None
+    display_name: str
+    provider_name: str
+    creator_name: str
+    price_tier: Literal[1, 2, 3]
 
 
 class LlmModelMeta(EnumMeta):
@@ -171,6 +175,26 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     V0_1_5_LG = "v0-1.5-lg"
     V0_1_0_MD = "v0-1.0-md"
 
+    @classmethod
+    def __get_pydantic_json_schema__(cls, schema, handler):
+        json_schema = handler(schema)
+        llm_model_metadata = {}
+        for model in cls:
+            model_name = model.value
+            metadata = model.metadata
+            llm_model_metadata[model_name] = {
+                "creator": metadata.creator_name,
+                "creator_name": metadata.creator_name,
+                "title": metadata.display_name,
+                "provider": metadata.provider,
+                "provider_name": metadata.provider_name,
+                "name": model_name,
+                "price_tier": metadata.price_tier,
+            }
+        json_schema["llm_model"] = True
+        json_schema["llm_model_metadata"] = llm_model_metadata
+        return json_schema
+
     @property
     def metadata(self) -> ModelMetadata:
         return MODEL_METADATA[self]
@@ -190,119 +214,291 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
 
 MODEL_METADATA = {
     # https://platform.openai.com/docs/models
-    LlmModel.O3: ModelMetadata("openai", 200000, 100000),
-    LlmModel.O3_MINI: ModelMetadata("openai", 200000, 100000),  # o3-mini-2025-01-31
-    LlmModel.O1: ModelMetadata("openai", 200000, 100000),  # o1-2024-12-17
-    LlmModel.O1_MINI: ModelMetadata("openai", 128000, 65536),  # o1-mini-2024-09-12
+    LlmModel.O3: ModelMetadata("openai", 200000, 100000, "O3", "OpenAI", "OpenAI", 2),
+    LlmModel.O3_MINI: ModelMetadata(
+        "openai", 200000, 100000, "O3 Mini", "OpenAI", "OpenAI", 1
+    ),  # o3-mini-2025-01-31
+    LlmModel.O1: ModelMetadata(
+        "openai", 200000, 100000, "O1", "OpenAI", "OpenAI", 3
+    ),  # o1-2024-12-17
+    LlmModel.O1_MINI: ModelMetadata(
+        "openai", 128000, 65536, "O1 Mini", "OpenAI", "OpenAI", 2
+    ),  # o1-mini-2024-09-12
     # GPT-5 models
-    LlmModel.GPT5_2: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5_1: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5_MINI: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5_NANO: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5_CHAT: ModelMetadata("openai", 400000, 16384),
-    LlmModel.GPT41: ModelMetadata("openai", 1047576, 32768),
-    LlmModel.GPT41_MINI: ModelMetadata("openai", 1047576, 32768),
+    LlmModel.GPT5_2: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5.2", "OpenAI", "OpenAI", 3
+    ),
+    LlmModel.GPT5_1: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5.1", "OpenAI", "OpenAI", 2
+    ),
+    LlmModel.GPT5: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_MINI: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5 Mini", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_NANO: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5 Nano", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_CHAT: ModelMetadata(
+        "openai", 400000, 16384, "GPT-5 Chat Latest", "OpenAI", "OpenAI", 2
+    ),
+    LlmModel.GPT41: ModelMetadata(
+        "openai", 1047576, 32768, "GPT-4.1", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT41_MINI: ModelMetadata(
+        "openai", 1047576, 32768, "GPT-4.1 Mini", "OpenAI", "OpenAI", 1
+    ),
     LlmModel.GPT4O_MINI: ModelMetadata(
-        "openai", 128000, 16384
+        "openai", 128000, 16384, "GPT-4o Mini", "OpenAI", "OpenAI", 1
     ),  # gpt-4o-mini-2024-07-18
-    LlmModel.GPT4O: ModelMetadata("openai", 128000, 16384),  # gpt-4o-2024-08-06
+    LlmModel.GPT4O: ModelMetadata(
+        "openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2
+    ),  # gpt-4o-2024-08-06
     LlmModel.GPT4_TURBO: ModelMetadata(
-        "openai", 128000, 4096
+        "openai", 128000, 4096, "GPT-4 Turbo", "OpenAI", "OpenAI", 3
     ),  # gpt-4-turbo-2024-04-09
-    LlmModel.GPT3_5_TURBO: ModelMetadata("openai", 16385, 4096),  # gpt-3.5-turbo-0125
+    LlmModel.GPT3_5_TURBO: ModelMetadata(
+        "openai", 16385, 4096, "GPT-3.5 Turbo", "OpenAI", "OpenAI", 1
+    ),  # gpt-3.5-turbo-0125
     # https://docs.anthropic.com/en/docs/about-claude/models
     LlmModel.CLAUDE_4_1_OPUS: ModelMetadata(
-        "anthropic", 200000, 32000
+        "anthropic", 200000, 32000, "Claude Opus 4.1", "Anthropic", "Anthropic", 3
     ),  # claude-opus-4-1-20250805
     LlmModel.CLAUDE_4_OPUS: ModelMetadata(
-        "anthropic", 200000, 32000
+        "anthropic", 200000, 32000, "Claude Opus 4", "Anthropic", "Anthropic", 3
     ),  # claude-4-opus-20250514
     LlmModel.CLAUDE_4_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000
+        "anthropic", 200000, 64000, "Claude Sonnet 4", "Anthropic", "Anthropic", 2
     ),  # claude-4-sonnet-20250514
     LlmModel.CLAUDE_4_5_OPUS: ModelMetadata(
-        "anthropic", 200000, 64000
+        "anthropic", 200000, 64000, "Claude Opus 4.5", "Anthropic", "Anthropic", 3
     ),  # claude-opus-4-5-20251101
     LlmModel.CLAUDE_4_5_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000
+        "anthropic", 200000, 64000, "Claude Sonnet 4.5", "Anthropic", "Anthropic", 3
     ),  # claude-sonnet-4-5-20250929
     LlmModel.CLAUDE_4_5_HAIKU: ModelMetadata(
-        "anthropic", 200000, 64000
+        "anthropic", 200000, 64000, "Claude Haiku 4.5", "Anthropic", "Anthropic", 2
     ),  # claude-haiku-4-5-20251001
     LlmModel.CLAUDE_3_7_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000
+        "anthropic", 200000, 64000, "Claude 3.7 Sonnet", "Anthropic", "Anthropic", 2
     ),  # claude-3-7-sonnet-20250219
     LlmModel.CLAUDE_3_HAIKU: ModelMetadata(
-        "anthropic", 200000, 4096
+        "anthropic", 200000, 4096, "Claude 3 Haiku", "Anthropic", "Anthropic", 1
     ),  # claude-3-haiku-20240307
     # https://docs.aimlapi.com/api-overview/model-database/text-models
-    LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata("aiml_api", 32000, 8000),
-    LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata("aiml_api", 128000, 40000),
-    LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata("aiml_api", 128000, None),
-    LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata("aiml_api", 131000, 2000),
-    LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata("aiml_api", 128000, None),
-    # https://console.groq.com/docs/models
-    LlmModel.LLAMA3_3_70B: ModelMetadata("groq", 128000, 32768),
-    LlmModel.LLAMA3_1_8B: ModelMetadata("groq", 128000, 8192),
-    # https://ollama.com/library
-    LlmModel.OLLAMA_LLAMA3_3: ModelMetadata("ollama", 8192, None),
-    LlmModel.OLLAMA_LLAMA3_2: ModelMetadata("ollama", 8192, None),
-    LlmModel.OLLAMA_LLAMA3_8B: ModelMetadata("ollama", 8192, None),
-    LlmModel.OLLAMA_LLAMA3_405B: ModelMetadata("ollama", 8192, None),
-    LlmModel.OLLAMA_DOLPHIN: ModelMetadata("ollama", 32768, None),
-    # https://openrouter.ai/models
-    LlmModel.GEMINI_2_5_PRO: ModelMetadata("open_router", 1050000, 8192),
-    LlmModel.GEMINI_3_PRO_PREVIEW: ModelMetadata("open_router", 1048576, 65535),
-    LlmModel.GEMINI_2_5_FLASH: ModelMetadata("open_router", 1048576, 65535),
-    LlmModel.GEMINI_2_0_FLASH: ModelMetadata("open_router", 1048576, 8192),
-    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(
-        "open_router", 1048576, 65535
+    LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata(
+        "aiml_api", 32000, 8000, "Qwen 2.5 72B Instruct Turbo", "AI/ML", "Qwen", 1
+    ),
+    LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata(
+        "aiml_api",
+        128000,
+        40000,
+        "Llama 3.1 Nemotron 70B Instruct",
+        "AI/ML",
+        "Nvidia",
+        1,
+    ),
+    LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata(
+        "aiml_api", 128000, None, "Llama 3.3 70B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata(
+        "aiml_api", 131000, 2000, "Llama 3.1 70B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata(
+        "aiml_api", 128000, None, "Llama 3.2 3B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    # https://console.groq.com/docs/models
+    LlmModel.LLAMA3_3_70B: ModelMetadata(
+        "groq", 128000, 32768, "Llama 3.3 70B Versatile", "Groq", "Meta", 1
+    ),
+    LlmModel.LLAMA3_1_8B: ModelMetadata(
+        "groq", 128000, 8192, "Llama 3.1 8B Instant", "Groq", "Meta", 1
+    ),
+    # https://ollama.com/library
+    LlmModel.OLLAMA_LLAMA3_3: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.3", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_2: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.2", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_8B: ModelMetadata(
+        "ollama", 8192, None, "Llama 3", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_405B: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.1 405B", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_DOLPHIN: ModelMetadata(
+        "ollama", 32768, None, "Dolphin Mistral Latest", "Ollama", "Mistral AI", 1
+    ),
+    # https://openrouter.ai/models
+    LlmModel.GEMINI_2_5_PRO: ModelMetadata(
+        "open_router",
+        1050000,
+        8192,
+        "Gemini 2.5 Pro Preview 03.25",
+        "OpenRouter",
+        "Google",
+        2,
+    ),
+    LlmModel.GEMINI_3_PRO_PREVIEW: ModelMetadata(
+        "open_router", 1048576, 65535, "Gemini 3 Pro Preview", "OpenRouter", "Google", 2
+    ),
+    LlmModel.GEMINI_2_5_FLASH: ModelMetadata(
+        "open_router", 1048576, 65535, "Gemini 2.5 Flash", "OpenRouter", "Google", 1
+    ),
+    LlmModel.GEMINI_2_0_FLASH: ModelMetadata(
+        "open_router", 1048576, 8192, "Gemini 2.0 Flash 001", "OpenRouter", "Google", 1
+    ),
+    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(
+        "open_router",
+        1048576,
+        65535,
+        "Gemini 2.5 Flash Lite Preview 06.17",
+        "OpenRouter",
+        "Google",
+        1,
+    ),
+    LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata(
+        "open_router",
+        1048576,
+        8192,
+        "Gemini 2.0 Flash Lite 001",
+        "OpenRouter",
+        "Google",
+        1,
+    ),
+    LlmModel.MISTRAL_NEMO: ModelMetadata(
+        "open_router", 128000, 4096, "Mistral Nemo", "OpenRouter", "Mistral AI", 1
+    ),
+    LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata(
+        "open_router", 128000, 4096, "Command R 08.2024", "OpenRouter", "Cohere", 1
+    ),
+    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata(
+        "open_router", 128000, 4096, "Command R Plus 08.2024", "OpenRouter", "Cohere", 2
+    ),
+    LlmModel.DEEPSEEK_CHAT: ModelMetadata(
+        "open_router", 64000, 2048, "DeepSeek Chat", "OpenRouter", "DeepSeek", 1
+    ),
+    LlmModel.DEEPSEEK_R1_0528: ModelMetadata(
+        "open_router", 163840, 163840, "DeepSeek R1 0528", "OpenRouter", "DeepSeek", 1
+    ),
+    LlmModel.PERPLEXITY_SONAR: ModelMetadata(
+        "open_router", 127000, 8000, "Sonar", "OpenRouter", "Perplexity", 1
+    ),
+    LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata(
+        "open_router", 200000, 8000, "Sonar Pro", "OpenRouter", "Perplexity", 2
     ),
-    LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata("open_router", 1048576, 8192),
-    LlmModel.MISTRAL_NEMO: ModelMetadata("open_router", 128000, 4096),
-    LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata("open_router", 128000, 4096),
-    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata("open_router", 128000, 4096),
-    LlmModel.DEEPSEEK_CHAT: ModelMetadata("open_router", 64000, 2048),
-    LlmModel.DEEPSEEK_R1_0528: ModelMetadata("open_router", 163840, 163840),
-    LlmModel.PERPLEXITY_SONAR: ModelMetadata("open_router", 127000, 8000),
-    LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata("open_router", 200000, 8000),
     LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: ModelMetadata(
         "open_router",
         128000,
         16000,
+        "Sonar Deep Research",
+        "OpenRouter",
+        "Perplexity",
+        3,
     ),
     LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B: ModelMetadata(
-        "open_router", 131000, 4096
+        "open_router",
+        131000,
+        4096,
+        "Hermes 3 Llama 3.1 405B",
+        "OpenRouter",
+        "Nous Research",
+        1,
     ),
     LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B: ModelMetadata(
-        "open_router", 12288, 12288
+        "open_router",
+        12288,
+        12288,
+        "Hermes 3 Llama 3.1 70B",
+        "OpenRouter",
+        "Nous Research",
+        1,
+    ),
+    LlmModel.OPENAI_GPT_OSS_120B: ModelMetadata(
+        "open_router", 131072, 131072, "GPT-OSS 120B", "OpenRouter", "OpenAI", 1
+    ),
+    LlmModel.OPENAI_GPT_OSS_20B: ModelMetadata(
+        "open_router", 131072, 32768, "GPT-OSS 20B", "OpenRouter", "OpenAI", 1
+    ),
+    LlmModel.AMAZON_NOVA_LITE_V1: ModelMetadata(
+        "open_router", 300000, 5120, "Nova Lite V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.AMAZON_NOVA_MICRO_V1: ModelMetadata(
+        "open_router", 128000, 5120, "Nova Micro V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata(
+        "open_router", 300000, 5120, "Nova Pro V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata(
+        "open_router", 65536, 4096, "WizardLM 2 8x22B", "OpenRouter", "Microsoft", 1
+    ),
+    LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata(
+        "open_router", 4096, 4096, "MythoMax L2 13B", "OpenRouter", "Gryphe", 1
+    ),
+    LlmModel.META_LLAMA_4_SCOUT: ModelMetadata(
+        "open_router", 131072, 131072, "Llama 4 Scout", "OpenRouter", "Meta", 1
+    ),
+    LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata(
+        "open_router", 1048576, 1000000, "Llama 4 Maverick", "OpenRouter", "Meta", 1
+    ),
+    LlmModel.GROK_4: ModelMetadata(
+        "open_router", 256000, 256000, "Grok 4", "OpenRouter", "xAI", 3
+    ),
+    LlmModel.GROK_4_FAST: ModelMetadata(
+        "open_router", 2000000, 30000, "Grok 4 Fast", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.GROK_4_1_FAST: ModelMetadata(
+        "open_router", 2000000, 30000, "Grok 4.1 Fast", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.GROK_CODE_FAST_1: ModelMetadata(
+        "open_router", 256000, 10000, "Grok Code Fast 1", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.KIMI_K2: ModelMetadata(
+        "open_router", 131000, 131000, "Kimi K2", "OpenRouter", "Moonshot AI", 1
+    ),
+    LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata(
+        "open_router",
+        262144,
+        262144,
+        "Qwen 3 235B A22B Thinking 2507",
+        "OpenRouter",
+        "Qwen",
+        1,
+    ),
+    LlmModel.QWEN3_CODER: ModelMetadata(
+        "open_router", 262144, 262144, "Qwen 3 Coder", "OpenRouter", "Qwen", 3
     ),
-    LlmModel.OPENAI_GPT_OSS_120B: ModelMetadata("open_router", 131072, 131072),
-    LlmModel.OPENAI_GPT_OSS_20B: ModelMetadata("open_router", 131072, 32768),
-    LlmModel.AMAZON_NOVA_LITE_V1: ModelMetadata("open_router", 300000, 5120),
-    LlmModel.AMAZON_NOVA_MICRO_V1: ModelMetadata("open_router", 128000, 5120),
-    LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata("open_router", 300000, 5120),
-    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata("open_router", 65536, 4096),
-    LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata("open_router", 4096, 4096),
-    LlmModel.META_LLAMA_4_SCOUT: ModelMetadata("open_router", 131072, 131072),
-    LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata("open_router", 1048576, 1000000),
-    LlmModel.GROK_4: ModelMetadata("open_router", 256000, 256000),
-    LlmModel.GROK_4_FAST: ModelMetadata("open_router", 2000000, 30000),
-    LlmModel.GROK_4_1_FAST: ModelMetadata("open_router", 2000000, 30000),
-    LlmModel.GROK_CODE_FAST_1: ModelMetadata("open_router", 256000, 10000),
-    LlmModel.KIMI_K2: ModelMetadata("open_router", 131000, 131000),
-    LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata("open_router", 262144, 262144),
-    LlmModel.QWEN3_CODER: ModelMetadata("open_router", 262144, 262144),
     # Llama API models
-    LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata("llama_api", 128000, 4028),
-    LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata("llama_api", 128000, 4028),
-    LlmModel.LLAMA_API_LLAMA3_3_8B: ModelMetadata("llama_api", 128000, 4028),
-    LlmModel.LLAMA_API_LLAMA3_3_70B: ModelMetadata("llama_api", 128000, 4028),
+    LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata(
+        "llama_api",
+        128000,
+        4028,
+        "Llama 4 Scout 17B 16E Instruct FP8",
+        "Llama API",
+        "Meta",
+        1,
+    ),
+    LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata(
+        "llama_api",
+        128000,
+        4028,
+        "Llama 4 Maverick 17B 128E Instruct FP8",
+        "Llama API",
+        "Meta",
+        1,
+    ),
+    LlmModel.LLAMA_API_LLAMA3_3_8B: ModelMetadata(
+        "llama_api", 128000, 4028, "Llama 3.3 8B Instruct", "Llama API", "Meta", 1
+    ),
+    LlmModel.LLAMA_API_LLAMA3_3_70B: ModelMetadata(
+        "llama_api", 128000, 4028, "Llama 3.3 70B Instruct", "Llama API", "Meta", 1
+    ),
     # v0 by Vercel models
-    LlmModel.V0_1_5_MD: ModelMetadata("v0", 128000, 64000),
-    LlmModel.V0_1_5_LG: ModelMetadata("v0", 512000, 64000),
-    LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000),
+    LlmModel.V0_1_5_MD: ModelMetadata("v0", 128000, 64000, "v0 1.5 MD", "V0", "V0", 1),
+    LlmModel.V0_1_5_LG: ModelMetadata("v0", 512000, 64000, "v0 1.5 LG", "V0", "V0", 1),
+    LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000, "v0 1.0 MD", "V0", "V0", 1),
 }
 
 DEFAULT_LLM_MODEL = LlmModel.GPT5_2

autogpt_platform/backend/backend/blocks/test/test_smart_decision_maker.py

@@ -242,7 +242,7 @@ async def test_smart_decision_maker_tracks_llm_stats():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -343,7 +343,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -409,7 +409,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -471,7 +471,7 @@ async def test_smart_decision_maker_parameter_validation():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -535,7 +535,7 @@ async def test_smart_decision_maker_parameter_validation():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -658,7 +658,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -730,7 +730,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -786,7 +786,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -905,7 +905,7 @@ async def test_smart_decision_maker_agent_mode():
         # Create a mock execution context
 
         mock_execution_context = ExecutionContext(
-            safe_mode=False,
+            human_in_the_loop_safe_mode=False,
         )
 
         # Create a mock execution processor for agent mode tests
@@ -1027,7 +1027,7 @@ async def test_smart_decision_maker_traditional_mode_default():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(safe_mode=False)
+        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
 
         # Create a mock execution processor for tests
 

autogpt_platform/backend/backend/blocks/test/test_smart_decision_maker_dynamic_fields.py

@@ -386,7 +386,7 @@ async def test_output_yielding_with_dynamic_fields():
             outputs = {}
             from backend.data.execution import ExecutionContext
 
-            mock_execution_context = ExecutionContext(safe_mode=False)
+            mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
             mock_execution_processor = MagicMock()
 
             async for output_name, output_value in block.run(
@@ -609,7 +609,9 @@ async def test_validation_errors_dont_pollute_conversation():
                 outputs = {}
                 from backend.data.execution import ExecutionContext
 
-                mock_execution_context = ExecutionContext(safe_mode=False)
+                mock_execution_context = ExecutionContext(
+                    human_in_the_loop_safe_mode=False
+                )
 
                 # Create a proper mock execution processor for agent mode
                 from collections import defaultdict

autogpt_platform/backend/backend/data/block.py

@@ -474,7 +474,7 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         self.block_type = block_type
         self.webhook_config = webhook_config
         self.execution_stats: NodeExecutionStats = NodeExecutionStats()
-        self.requires_human_review: bool = False
+        self.is_sensitive_action: bool = False
 
         if self.webhook_config:
             if isinstance(self.webhook_config, BlockWebhookConfig):
@@ -637,8 +637,9 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
             - should_pause: True if execution should be paused for review
             - input_data_to_use: The input data to use (may be modified by reviewer)
         """
-        # Skip review if not required or safe mode is disabled
-        if not self.requires_human_review or not execution_context.safe_mode:
+        if not (
+            self.is_sensitive_action and execution_context.sensitive_action_safe_mode
+        ):
             return False, input_data
 
         from backend.blocks.helpers.review import HITLReviewHelper

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -99,10 +99,15 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.OPENAI_GPT_OSS_20B: 1,
     LlmModel.GEMINI_2_5_PRO: 4,
     LlmModel.GEMINI_3_PRO_PREVIEW: 5,
+    LlmModel.GEMINI_2_5_FLASH: 1,
+    LlmModel.GEMINI_2_0_FLASH: 1,
+    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
+    LlmModel.GEMINI_2_0_FLASH_LITE: 1,
     LlmModel.MISTRAL_NEMO: 1,
     LlmModel.COHERE_COMMAND_R_08_2024: 1,
     LlmModel.COHERE_COMMAND_R_PLUS_08_2024: 3,
     LlmModel.DEEPSEEK_CHAT: 2,
+    LlmModel.DEEPSEEK_R1_0528: 1,
     LlmModel.PERPLEXITY_SONAR: 1,
     LlmModel.PERPLEXITY_SONAR_PRO: 5,
     LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: 10,
@@ -126,11 +131,6 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.KIMI_K2: 1,
     LlmModel.QWEN3_235B_A22B_THINKING: 1,
     LlmModel.QWEN3_CODER: 9,
-    LlmModel.GEMINI_2_5_FLASH: 1,
-    LlmModel.GEMINI_2_0_FLASH: 1,
-    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
-    LlmModel.GEMINI_2_0_FLASH_LITE: 1,
-    LlmModel.DEEPSEEK_R1_0528: 1,
     # v0 by Vercel models
     LlmModel.V0_1_5_MD: 1,
     LlmModel.V0_1_5_LG: 2,

autogpt_platform/backend/backend/data/db.py

@@ -121,10 +121,14 @@ async def _raw_with_schema(
     Supports placeholders:
         - {schema_prefix}: Table/type prefix (e.g., "platform".)
         - {schema}: Raw schema name for application tables (e.g., platform)
-        - {pgvector_schema}: Schema where pgvector is installed (defaults to "public")
+
+    Note on pgvector types:
+        Use unqualified ::vector and <=> operator in queries. PostgreSQL resolves
+        these via search_path, which includes the schema where pgvector is installed
+        on all environments (local, CI, dev).
 
     Args:
-        query_template: SQL query with {schema_prefix}, {schema}, and/or {pgvector_schema} placeholders
+        query_template: SQL query with {schema_prefix} and/or {schema} placeholders
         *args: Query parameters
         execute: If False, executes SELECT query. If True, executes INSERT/UPDATE/DELETE.
         client: Optional Prisma client for transactions (only used when execute=True).
@@ -135,20 +139,16 @@ async def _raw_with_schema(
 
     Example with vector type:
         await execute_raw_with_schema(
-            'INSERT INTO {schema_prefix}"Embedding" (vec) VALUES ($1::{pgvector_schema}.vector)',
+            'INSERT INTO {schema_prefix}"Embedding" (vec) VALUES ($1::vector)',
             embedding_data
         )
     """
     schema = get_database_schema()
     schema_prefix = f'"{schema}".' if schema != "public" else ""
-    # pgvector extension is typically installed in "public" schema
-    # On Supabase it may be in "extensions" but "public" is the common default
-    pgvector_schema = "public"
 
     formatted_query = query_template.format(
         schema_prefix=schema_prefix,
         schema=schema,
-        pgvector_schema=pgvector_schema,
     )
 
     import prisma as prisma_module

autogpt_platform/backend/backend/data/event_bus.py

@@ -103,8 +103,18 @@ class RedisEventBus(BaseRedisEventBus[M], ABC):
         return redis.get_redis()
 
     def publish_event(self, event: M, channel_key: str):
-        message, full_channel_name = self._serialize_message(event, channel_key)
-        self.connection.publish(full_channel_name, message)
+        """
+        Publish an event to Redis. Gracefully handles connection failures
+        by logging the error instead of raising exceptions.
+        """
+        try:
+            message, full_channel_name = self._serialize_message(event, channel_key)
+            self.connection.publish(full_channel_name, message)
+        except Exception:
+            logger.exception(
+                f"Failed to publish event to Redis channel {channel_key}. "
+                "Event bus operation will continue without Redis connectivity."
+            )
 
     def listen_events(self, channel_key: str) -> Generator[M, None, None]:
         pubsub, full_channel_name = self._get_pubsub_channel(
@@ -128,9 +138,19 @@ class AsyncRedisEventBus(BaseRedisEventBus[M], ABC):
         return await redis.get_redis_async()
 
     async def publish_event(self, event: M, channel_key: str):
-        message, full_channel_name = self._serialize_message(event, channel_key)
-        connection = await self.connection
-        await connection.publish(full_channel_name, message)
+        """
+        Publish an event to Redis. Gracefully handles connection failures
+        by logging the error instead of raising exceptions.
+        """
+        try:
+            message, full_channel_name = self._serialize_message(event, channel_key)
+            connection = await self.connection
+            await connection.publish(full_channel_name, message)
+        except Exception:
+            logger.exception(
+                f"Failed to publish event to Redis channel {channel_key}. "
+                "Event bus operation will continue without Redis connectivity."
+            )
 
     async def listen_events(self, channel_key: str) -> AsyncGenerator[M, None]:
         pubsub, full_channel_name = self._get_pubsub_channel(

autogpt_platform/backend/backend/data/event_bus_test.py

@@ -0,0 +1,56 @@
+"""
+Tests for event_bus graceful degradation when Redis is unavailable.
+"""
+
+from unittest.mock import AsyncMock, patch
+
+import pytest
+from pydantic import BaseModel
+
+from backend.data.event_bus import AsyncRedisEventBus
+
+
+class TestEvent(BaseModel):
+    """Test event model."""
+
+    message: str
+
+
+class TestNotificationBus(AsyncRedisEventBus[TestEvent]):
+    """Test implementation of AsyncRedisEventBus."""
+
+    Model = TestEvent
+
+    @property
+    def event_bus_name(self) -> str:
+        return "test_event_bus"
+
+
+@pytest.mark.asyncio
+async def test_publish_event_handles_connection_failure_gracefully():
+    """Test that publish_event logs exception instead of raising when Redis is unavailable."""
+    bus = TestNotificationBus()
+    event = TestEvent(message="test message")
+
+    # Mock get_redis_async to raise connection error
+    with patch(
+        "backend.data.event_bus.redis.get_redis_async",
+        side_effect=ConnectionError("Authentication required."),
+    ):
+        # Should not raise exception
+        await bus.publish_event(event, "test_channel")
+
+
+@pytest.mark.asyncio
+async def test_publish_event_works_with_redis_available():
+    """Test that publish_event works normally when Redis is available."""
+    bus = TestNotificationBus()
+    event = TestEvent(message="test message")
+
+    # Mock successful Redis connection
+    mock_redis = AsyncMock()
+    mock_redis.publish = AsyncMock()
+
+    with patch("backend.data.event_bus.redis.get_redis_async", return_value=mock_redis):
+        await bus.publish_event(event, "test_channel")
+        mock_redis.publish.assert_called_once()

autogpt_platform/backend/backend/data/execution.py

@@ -81,7 +81,10 @@ class ExecutionContext(BaseModel):
     This includes information needed by blocks, sub-graphs, and execution management.
     """
 
-    safe_mode: bool = True
+    model_config = {"extra": "ignore"}
+
+    human_in_the_loop_safe_mode: bool = True
+    sensitive_action_safe_mode: bool = False
     user_timezone: str = "UTC"
     root_execution_id: Optional[str] = None
     parent_execution_id: Optional[str] = None

autogpt_platform/backend/backend/data/graph.py

@@ -3,7 +3,7 @@ import logging
 import uuid
 from collections import defaultdict
 from datetime import datetime, timezone
-from typing import TYPE_CHECKING, Any, Literal, Optional, cast
+from typing import TYPE_CHECKING, Annotated, Any, Literal, Optional, cast
 
 from prisma.enums import SubmissionStatus
 from prisma.models import (
@@ -20,7 +20,7 @@ from prisma.types import (
     AgentNodeLinkCreateInput,
     StoreListingVersionWhereInput,
 )
-from pydantic import BaseModel, Field, create_model
+from pydantic import BaseModel, BeforeValidator, Field, create_model
 from pydantic.fields import computed_field
 
 from backend.blocks.agent import AgentExecutorBlock
@@ -62,7 +62,31 @@ logger = logging.getLogger(__name__)
 
 
 class GraphSettings(BaseModel):
-    human_in_the_loop_safe_mode: bool | None = None
+    # Use Annotated with BeforeValidator to coerce None to default values.
+    # This handles cases where the database has null values for these fields.
+    model_config = {"extra": "ignore"}
+
+    human_in_the_loop_safe_mode: Annotated[
+        bool, BeforeValidator(lambda v: v if v is not None else True)
+    ] = True
+    sensitive_action_safe_mode: Annotated[
+        bool, BeforeValidator(lambda v: v if v is not None else False)
+    ] = False
+
+    @classmethod
+    def from_graph(
+        cls,
+        graph: "GraphModel",
+        hitl_safe_mode: bool | None = None,
+        sensitive_action_safe_mode: bool = False,
+    ) -> "GraphSettings":
+        # Default to True if not explicitly set
+        if hitl_safe_mode is None:
+            hitl_safe_mode = True
+        return cls(
+            human_in_the_loop_safe_mode=hitl_safe_mode,
+            sensitive_action_safe_mode=sensitive_action_safe_mode,
+        )
 
 
 class Link(BaseDbModel):
@@ -244,10 +268,14 @@ class BaseGraph(BaseDbModel):
         return any(
             node.block_id
             for node in self.nodes
-            if (
-                node.block.block_type == BlockType.HUMAN_IN_THE_LOOP
-                or node.block.requires_human_review
-            )
+            if node.block.block_type == BlockType.HUMAN_IN_THE_LOOP
+        )
+
+    @computed_field
+    @property
+    def has_sensitive_action(self) -> bool:
+        return any(
+            node.block_id for node in self.nodes if node.block.is_sensitive_action
         )
 
     @property

autogpt_platform/backend/backend/executor/scheduler.py

@@ -309,7 +309,7 @@ def ensure_embeddings_coverage():
 
         # Process in batches until no more missing embeddings
         while True:
-            result = db_client.backfill_missing_embeddings(batch_size=10)
+            result = db_client.backfill_missing_embeddings(batch_size=100)
 
             total_processed += result["processed"]
             total_success += result["success"]

autogpt_platform/backend/backend/executor/utils.py

@@ -873,11 +873,8 @@ async def add_graph_execution(
         settings = await gdb.get_graph_settings(user_id=user_id, graph_id=graph_id)
 
         execution_context = ExecutionContext(
-            safe_mode=(
-                settings.human_in_the_loop_safe_mode
-                if settings.human_in_the_loop_safe_mode is not None
-                else True
-            ),
+            human_in_the_loop_safe_mode=settings.human_in_the_loop_safe_mode,
+            sensitive_action_safe_mode=settings.sensitive_action_safe_mode,
             user_timezone=(
                 user.timezone if user.timezone != USER_TIMEZONE_NOT_SET else "UTC"
             ),

autogpt_platform/backend/backend/executor/utils_test.py

@@ -386,6 +386,7 @@ async def test_add_graph_execution_is_repeatable(mocker: MockerFixture):
     mock_user.timezone = "UTC"
     mock_settings = mocker.MagicMock()
     mock_settings.human_in_the_loop_safe_mode = True
+    mock_settings.sensitive_action_safe_mode = False
 
     mock_udb.get_user_by_id = mocker.AsyncMock(return_value=mock_user)
     mock_gdb.get_graph_settings = mocker.AsyncMock(return_value=mock_settings)
@@ -651,6 +652,7 @@ async def test_add_graph_execution_with_nodes_to_skip(mocker: MockerFixture):
     mock_user.timezone = "UTC"
     mock_settings = mocker.MagicMock()
     mock_settings.human_in_the_loop_safe_mode = True
+    mock_settings.sensitive_action_safe_mode = False
 
     mock_udb.get_user_by_id = mocker.AsyncMock(return_value=mock_user)
     mock_gdb.get_graph_settings = mocker.AsyncMock(return_value=mock_settings)

autogpt_platform/backend/backend/util/settings.py

@@ -666,6 +666,12 @@ class Secrets(UpdateTrackingModel["Secrets"], BaseSettings):
         default="https://cloud.langfuse.com", description="Langfuse host URL"
     )
 
+    # PostHog analytics
+    posthog_api_key: str = Field(default="", description="PostHog API key")
+    posthog_host: str = Field(
+        default="https://us.i.posthog.com", description="PostHog host URL"
+    )
+
     # Add more secret fields as needed
     model_config = SettingsConfigDict(
         env_file=".env",

autogpt_platform/backend/migrations/20260109181714_add_docs_embedding/migration.sql

@@ -1,11 +1,37 @@
 -- CreateExtension
 -- Supabase: pgvector must be enabled via Dashboard → Database → Extensions first
--- Create in public schema so vector type is available across all schemas
+-- Ensures vector extension is in the current schema (from DATABASE_URL ?schema= param)
+-- If it exists in a different schema (e.g., public), we drop and recreate it in the current schema
+-- This ensures vector type is in the same schema as tables, making ::vector work without explicit qualification
 DO $$
+DECLARE
+    current_schema_name text;
+    vector_schema text;
 BEGIN
-    CREATE EXTENSION IF NOT EXISTS "vector" WITH SCHEMA "public";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'vector extension not available or already exists, skipping';
+    -- Get the current schema from search_path
+    SELECT current_schema() INTO current_schema_name;
+
+    -- Check if vector extension exists and which schema it's in
+    SELECT n.nspname INTO vector_schema
+    FROM pg_extension e
+    JOIN pg_namespace n ON e.extnamespace = n.oid
+    WHERE e.extname = 'vector';
+
+    -- Handle removal if in wrong schema
+    IF vector_schema IS NOT NULL AND vector_schema != current_schema_name THEN
+        BEGIN
+            -- Vector exists in a different schema, drop it first
+            RAISE WARNING 'pgvector found in schema "%" but need it in "%". Dropping and reinstalling...',
+                vector_schema, current_schema_name;
+            EXECUTE 'DROP EXTENSION IF EXISTS vector CASCADE';
+        EXCEPTION WHEN OTHERS THEN
+            RAISE EXCEPTION 'Failed to drop pgvector from schema "%": %. You may need to drop it manually.',
+                vector_schema, SQLERRM;
+        END;
+    END IF;
+
+    -- Create extension in current schema (let it fail naturally if not available)
+    EXECUTE format('CREATE EXTENSION IF NOT EXISTS vector SCHEMA %I', current_schema_name);
 END $$;
 
 -- CreateEnum
@@ -19,7 +45,7 @@ CREATE TABLE "UnifiedContentEmbedding" (
     "contentType" "ContentType" NOT NULL,
     "contentId" TEXT NOT NULL,
     "userId" TEXT,
-    "embedding" public.vector(1536) NOT NULL,
+    "embedding" vector(1536) NOT NULL,
     "searchableText" TEXT NOT NULL,
     "metadata" JSONB NOT NULL DEFAULT '{}',
 
@@ -45,4 +71,4 @@ CREATE UNIQUE INDEX "UnifiedContentEmbedding_contentType_contentId_userId_key" O
 -- Uses cosine distance operator (<=>), which matches the query in hybrid_search.py
 -- Note: Drop first in case Prisma created a btree index (Prisma doesn't support HNSW)
 DROP INDEX IF EXISTS "UnifiedContentEmbedding_embedding_idx";
-CREATE INDEX "UnifiedContentEmbedding_embedding_idx" ON "UnifiedContentEmbedding" USING hnsw ("embedding" public.vector_cosine_ops);
+CREATE INDEX "UnifiedContentEmbedding_embedding_idx" ON "UnifiedContentEmbedding" USING hnsw ("embedding" vector_cosine_ops);

autogpt_platform/backend/migrations/20260112173500_add_supabase_extensions_to_platform_schema/migration.sql

@@ -1,71 +0,0 @@
--- Acknowledge Supabase-managed extensions to prevent drift warnings
--- These extensions are pre-installed by Supabase in specific schemas
--- This migration ensures they exist where available (Supabase) or skips gracefully (CI)
-
--- Create schemas (safe in both CI and Supabase)
-CREATE SCHEMA IF NOT EXISTS "extensions";
-
--- Extensions that exist in both CI and Supabase
-DO $$
-BEGIN
-    CREATE EXTENSION IF NOT EXISTS "pgcrypto" WITH SCHEMA "extensions";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pgcrypto extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE EXTENSION IF NOT EXISTS "uuid-ossp" WITH SCHEMA "extensions";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'uuid-ossp extension not available, skipping';
-END $$;
-
--- Supabase-specific extensions (skip gracefully in CI)
-DO $$
-BEGIN
-    CREATE EXTENSION IF NOT EXISTS "pg_stat_statements" WITH SCHEMA "extensions";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pg_stat_statements extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE EXTENSION IF NOT EXISTS "pg_net" WITH SCHEMA "extensions";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pg_net extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE EXTENSION IF NOT EXISTS "pgjwt" WITH SCHEMA "extensions";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pgjwt extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE SCHEMA IF NOT EXISTS "graphql";
-    CREATE EXTENSION IF NOT EXISTS "pg_graphql" WITH SCHEMA "graphql";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pg_graphql extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE SCHEMA IF NOT EXISTS "pgsodium";
-    CREATE EXTENSION IF NOT EXISTS "pgsodium" WITH SCHEMA "pgsodium";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'pgsodium extension not available, skipping';
-END $$;
-
-DO $$
-BEGIN
-    CREATE SCHEMA IF NOT EXISTS "vault";
-    CREATE EXTENSION IF NOT EXISTS "supabase_vault" WITH SCHEMA "vault";
-EXCEPTION WHEN OTHERS THEN
-    RAISE NOTICE 'supabase_vault extension not available, skipping';
-END $$;
-
-
--- Return to platform
-CREATE SCHEMA IF NOT EXISTS "platform";

autogpt_platform/backend/poetry.lock

@@ -4204,14 +4204,14 @@ strenum = {version = ">=0.4.9,<0.5.0", markers = "python_version < \"3.11\""}
 
 [[package]]
 name = "posthog"
-version = "6.1.1"
+version = "7.6.0"
 description = "Integrate PostHog into any python application."
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.10"
 groups = ["main"]
 files = [
-    {file = "posthog-6.1.1-py3-none-any.whl", hash = "sha256:329fd3d06b4d54cec925f47235bd8e327c91403c2f9ec38f1deb849535934dba"},
-    {file = "posthog-6.1.1.tar.gz", hash = "sha256:b453f54c4a2589da859fd575dd3bf86fcb40580727ec399535f268b1b9f318b8"},
+    {file = "posthog-7.6.0-py3-none-any.whl", hash = "sha256:c4dd78cf77c4fecceb965f86066e5ac37886ef867d68ffe75a1db5d681d7d9ad"},
+    {file = "posthog-7.6.0.tar.gz", hash = "sha256:941dfd278ee427c9b14640f09b35b5bb52a71bdf028d7dbb7307e1838fd3002e"},
 ]
 
 [package.dependencies]
@@ -4225,7 +4225,7 @@ typing-extensions = ">=4.2.0"
 [package.extras]
 dev = ["django-stubs", "lxml", "mypy", "mypy-baseline", "packaging", "pre-commit", "pydantic", "ruff", "setuptools", "tomli", "tomli_w", "twine", "types-mock", "types-python-dateutil", "types-requests", "types-setuptools", "types-six", "wheel"]
 langchain = ["langchain (>=0.2.0)"]
-test = ["anthropic", "coverage", "django", "freezegun (==1.5.1)", "google-genai", "langchain-anthropic (>=0.3.15)", "langchain-community (>=0.3.25)", "langchain-core (>=0.3.65)", "langchain-openai (>=0.3.22)", "langgraph (>=0.4.8)", "mock (>=2.0.0)", "openai", "parameterized (>=0.8.1)", "pydantic", "pytest", "pytest-asyncio", "pytest-timeout"]
+test = ["anthropic (>=0.72)", "coverage", "django", "freezegun (==1.5.1)", "google-genai", "langchain-anthropic (>=1.0)", "langchain-community (>=0.4)", "langchain-core (>=1.0)", "langchain-openai (>=1.0)", "langgraph (>=1.0)", "mock (>=2.0.0)", "openai (>=2.0)", "parameterized (>=0.8.1)", "pydantic", "pytest", "pytest-asyncio", "pytest-timeout"]
 
 [[package]]
 name = "postmarker"
@@ -7512,4 +7512,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "18b92e09596298c82432e4d0a85cb6d80a40b4229bee0a0c15f0529fd6cb21a4"
+content-hash = "ee5742dc1a9df50dfc06d4b26a1682cbb2b25cab6b79ce5625ec272f93e4f4bf"

autogpt_platform/backend/pyproject.toml

@@ -85,6 +85,7 @@ exa-py = "^1.14.20"
 croniter = "^6.0.0"
 stagehand = "^0.5.1"
 gravitas-md2gdocs = "^0.1.0"
+posthog = "^7.6.0"
 
 [tool.poetry.group.dev.dependencies]
 aiohappyeyeballs = "^2.6.1"

autogpt_platform/backend/scripts/generate_block_docs.py

@@ -34,7 +34,10 @@ logger = logging.getLogger(__name__)
 
 # Default output directory relative to repo root
 DEFAULT_OUTPUT_DIR = (
-    Path(__file__).parent.parent.parent.parent / "docs" / "integrations"
+    Path(__file__).parent.parent.parent.parent
+    / "docs"
+    / "integrations"
+    / "block-integrations"
 )
 
 
@@ -366,12 +369,12 @@ def generate_block_markdown(
     lines.append("")
 
     # What it is (full description)
-    lines.append(f"### What it is")
+    lines.append("### What it is")
     lines.append(block.description or "No description available.")
     lines.append("")
 
     # How it works (manual section)
-    lines.append(f"### How it works")
+    lines.append("### How it works")
     how_it_works = manual_content.get(
         "how_it_works", "_Add technical explanation here._"
     )
@@ -383,7 +386,7 @@ def generate_block_markdown(
     # Inputs table (auto-generated)
     visible_inputs = [f for f in block.inputs if not f.hidden]
     if visible_inputs:
-        lines.append(f"### Inputs")
+        lines.append("### Inputs")
         lines.append("")
         lines.append("| Input | Description | Type | Required |")
         lines.append("|-------|-------------|------|----------|")
@@ -400,7 +403,7 @@ def generate_block_markdown(
     # Outputs table (auto-generated)
     visible_outputs = [f for f in block.outputs if not f.hidden]
     if visible_outputs:
-        lines.append(f"### Outputs")
+        lines.append("### Outputs")
         lines.append("")
         lines.append("| Output | Description | Type |")
         lines.append("|--------|-------------|------|")
@@ -414,13 +417,21 @@ def generate_block_markdown(
         lines.append("")
 
     # Possible use case (manual section)
-    lines.append(f"### Possible use case")
+    lines.append("### Possible use case")
     use_case = manual_content.get("use_case", "_Add practical use case examples here._")
     lines.append("<!-- MANUAL: use_case -->")
     lines.append(use_case)
     lines.append("<!-- END MANUAL -->")
     lines.append("")
 
+    # Optional per-block extras (only include if has content)
+    extras = manual_content.get("extras", "")
+    if extras:
+        lines.append("<!-- MANUAL: extras -->")
+        lines.append(extras)
+        lines.append("<!-- END MANUAL -->")
+        lines.append("")
+
     lines.append("---")
     lines.append("")
 
@@ -456,25 +467,52 @@ def get_block_file_mapping(blocks: list[BlockDoc]) -> dict[str, list[BlockDoc]]:
     return dict(file_mapping)
 
 
-def generate_overview_table(blocks: list[BlockDoc]) -> str:
-    """Generate the overview table markdown (blocks.md)."""
+def generate_overview_table(blocks: list[BlockDoc], block_dir_prefix: str = "") -> str:
+    """Generate the overview table markdown (blocks.md).
+
+    Args:
+        blocks: List of block documentation objects
+        block_dir_prefix: Prefix for block file links (e.g., "block-integrations/")
+    """
     lines = []
 
+    # GitBook YAML frontmatter
+    lines.append("---")
+    lines.append("layout:")
+    lines.append("  width: default")
+    lines.append("  title:")
+    lines.append("    visible: true")
+    lines.append("  description:")
+    lines.append("    visible: true")
+    lines.append("  tableOfContents:")
+    lines.append("    visible: false")
+    lines.append("  outline:")
+    lines.append("    visible: true")
+    lines.append("  pagination:")
+    lines.append("    visible: true")
+    lines.append("  metadata:")
+    lines.append("    visible: true")
+    lines.append("---")
+    lines.append("")
+
     lines.append("# AutoGPT Blocks Overview")
     lines.append("")
     lines.append(
         'AutoGPT uses a modular approach with various "blocks" to handle different tasks. These blocks are the building blocks of AutoGPT workflows, allowing users to create complex automations by combining simple, specialized components.'
     )
     lines.append("")
-    lines.append('!!! info "Creating Your Own Blocks"')
-    lines.append("    Want to create your own custom blocks? Check out our guides:")
-    lines.append("    ")
+    lines.append('{% hint style="info" %}')
+    lines.append("**Creating Your Own Blocks**")
+    lines.append("")
+    lines.append("Want to create your own custom blocks? Check out our guides:")
+    lines.append("")
     lines.append(
-        "    - [Build your own Blocks](https://docs.agpt.co/platform/new_blocks/) - Step-by-step tutorial with examples"
+        "* [Build your own Blocks](https://docs.agpt.co/platform/new_blocks/) - Step-by-step tutorial with examples"
     )
     lines.append(
-        "    - [Block SDK Guide](https://docs.agpt.co/platform/block-sdk-guide/) - Advanced SDK patterns with OAuth, webhooks, and provider configuration"
+        "* [Block SDK Guide](https://docs.agpt.co/platform/block-sdk-guide/) - Advanced SDK patterns with OAuth, webhooks, and provider configuration"
     )
+    lines.append("{% endhint %}")
     lines.append("")
     lines.append(
         "Below is a comprehensive list of all available blocks, categorized by their primary function. Click on any block name to view its detailed documentation."
@@ -537,7 +575,8 @@ def generate_overview_table(blocks: list[BlockDoc]) -> str:
                     else "No description"
                 )
                 short_desc = short_desc.replace("\n", " ").replace("|", "\\|")
-                lines.append(f"| [{block.name}]({file_path}#{anchor}) | {short_desc} |")
+                link_path = f"{block_dir_prefix}{file_path}"
+                lines.append(f"| [{block.name}]({link_path}#{anchor}) | {short_desc} |")
             lines.append("")
             continue
 
@@ -563,13 +602,55 @@ def generate_overview_table(blocks: list[BlockDoc]) -> str:
             )
             short_desc = short_desc.replace("\n", " ").replace("|", "\\|")
 
-            lines.append(f"| [{block.name}]({file_path}#{anchor}) | {short_desc} |")
+            link_path = f"{block_dir_prefix}{file_path}"
+            lines.append(f"| [{block.name}]({link_path}#{anchor}) | {short_desc} |")
 
         lines.append("")
 
     return "\n".join(lines)
 
 
+def generate_summary_md(
+    blocks: list[BlockDoc], root_dir: Path, block_dir_prefix: str = ""
+) -> str:
+    """Generate SUMMARY.md for GitBook navigation.
+
+    Args:
+        blocks: List of block documentation objects
+        root_dir: The root docs directory (e.g., docs/integrations/)
+        block_dir_prefix: Prefix for block file links (e.g., "block-integrations/")
+    """
+    lines = []
+    lines.append("# Table of contents")
+    lines.append("")
+    lines.append("* [AutoGPT Blocks Overview](README.md)")
+    lines.append("")
+
+    # Check for guides/ directory at the root level (docs/integrations/guides/)
+    guides_dir = root_dir / "guides"
+    if guides_dir.exists():
+        lines.append("## Guides")
+        lines.append("")
+        for guide_file in sorted(guides_dir.glob("*.md")):
+            # Use just the file name for title (replace hyphens/underscores with spaces)
+            title = file_path_to_title(guide_file.stem.replace("-", "_") + ".md")
+            lines.append(f"* [{title}](guides/{guide_file.name})")
+        lines.append("")
+
+    lines.append("## Block Integrations")
+    lines.append("")
+
+    file_mapping = get_block_file_mapping(blocks)
+    for file_path in sorted(file_mapping.keys()):
+        title = file_path_to_title(file_path)
+        link_path = f"{block_dir_prefix}{file_path}"
+        lines.append(f"* [{title}]({link_path})")
+
+    lines.append("")
+
+    return "\n".join(lines)
+
+
 def load_all_blocks_for_docs() -> list[BlockDoc]:
     """Load all blocks and extract documentation."""
     from backend.blocks import load_all_blocks
@@ -653,6 +734,16 @@ def write_block_docs(
                 )
             )
 
+        # Add file-level additional_content section if present
+        file_additional = extract_manual_content(existing_content).get(
+            "additional_content", ""
+        )
+        if file_additional:
+            content_parts.append("<!-- MANUAL: additional_content -->")
+            content_parts.append(file_additional)
+            content_parts.append("<!-- END MANUAL -->")
+            content_parts.append("")
+
         full_content = file_header + "\n" + "\n".join(content_parts)
         generated_files[str(file_path)] = full_content
 
@@ -661,14 +752,28 @@ def write_block_docs(
 
         full_path.write_text(full_content)
 
-    # Generate overview file
-    overview_content = generate_overview_table(blocks)
-    overview_path = output_dir / "README.md"
+    # Generate overview file at the parent directory (docs/integrations/)
+    # with links prefixed to point into block-integrations/
+    root_dir = output_dir.parent
+    block_dir_name = output_dir.name  # "block-integrations"
+    block_dir_prefix = f"{block_dir_name}/"
+
+    overview_content = generate_overview_table(blocks, block_dir_prefix)
+    overview_path = root_dir / "README.md"
     generated_files["README.md"] = overview_content
     overview_path.write_text(overview_content)
 
     if verbose:
-        print("  Writing README.md (overview)")
+        print("  Writing README.md (overview) to parent directory")
+
+    # Generate SUMMARY.md for GitBook navigation at the parent directory
+    summary_content = generate_summary_md(blocks, root_dir, block_dir_prefix)
+    summary_path = root_dir / "SUMMARY.md"
+    generated_files["SUMMARY.md"] = summary_content
+    summary_path.write_text(summary_content)
+
+    if verbose:
+        print("  Writing SUMMARY.md (navigation) to parent directory")
 
     return generated_files
 
@@ -748,6 +853,16 @@ def check_docs_in_sync(output_dir: Path, blocks: list[BlockDoc]) -> bool:
             elif block_match.group(1).strip() != expected_block_content.strip():
                 mismatched_blocks.append(block.name)
 
+        # Add file-level additional_content to expected content (matches write_block_docs)
+        file_additional = extract_manual_content(existing_content).get(
+            "additional_content", ""
+        )
+        if file_additional:
+            content_parts.append("<!-- MANUAL: additional_content -->")
+            content_parts.append(file_additional)
+            content_parts.append("<!-- END MANUAL -->")
+            content_parts.append("")
+
         expected_content = file_header + "\n" + "\n".join(content_parts)
 
         if existing_content.strip() != expected_content.strip():
@@ -757,11 +872,15 @@ def check_docs_in_sync(output_dir: Path, blocks: list[BlockDoc]) -> bool:
             out_of_sync_details.append((file_path, mismatched_blocks))
             all_match = False
 
-    # Check overview
-    overview_path = output_dir / "README.md"
+    # Check overview at the parent directory (docs/integrations/)
+    root_dir = output_dir.parent
+    block_dir_name = output_dir.name  # "block-integrations"
+    block_dir_prefix = f"{block_dir_name}/"
+
+    overview_path = root_dir / "README.md"
     if overview_path.exists():
         existing_overview = overview_path.read_text()
-        expected_overview = generate_overview_table(blocks)
+        expected_overview = generate_overview_table(blocks, block_dir_prefix)
         if existing_overview.strip() != expected_overview.strip():
             print("OUT OF SYNC: README.md (overview)")
             print("  The blocks overview table needs regeneration")
@@ -772,6 +891,21 @@ def check_docs_in_sync(output_dir: Path, blocks: list[BlockDoc]) -> bool:
         out_of_sync_details.append(("README.md", ["overview table"]))
         all_match = False
 
+    # Check SUMMARY.md at the parent directory
+    summary_path = root_dir / "SUMMARY.md"
+    if summary_path.exists():
+        existing_summary = summary_path.read_text()
+        expected_summary = generate_summary_md(blocks, root_dir, block_dir_prefix)
+        if existing_summary.strip() != expected_summary.strip():
+            print("OUT OF SYNC: SUMMARY.md (navigation)")
+            print("  The GitBook navigation needs regeneration")
+            out_of_sync_details.append(("SUMMARY.md", ["navigation"]))
+            all_match = False
+    else:
+        print("MISSING: SUMMARY.md (navigation)")
+        out_of_sync_details.append(("SUMMARY.md", ["navigation"]))
+        all_match = False
+
     # Check for unfilled manual sections
     unfilled_patterns = [
         "_Add a description of this category of blocks._",

autogpt_platform/backend/snapshots/grph_single

@@ -11,6 +11,7 @@
   "forked_from_version": null,
   "has_external_trigger": false,
   "has_human_in_the_loop": false,
+  "has_sensitive_action": false,
   "id": "graph-123",
   "input_schema": {
     "properties": {},

autogpt_platform/backend/snapshots/grphs_all

@@ -11,6 +11,7 @@
     "forked_from_version": null,
     "has_external_trigger": false,
     "has_human_in_the_loop": false,
+    "has_sensitive_action": false,
     "id": "graph-123",
     "input_schema": {
       "properties": {},

autogpt_platform/backend/snapshots/lib_agts_search

@@ -27,6 +27,8 @@
         "properties": {}
       },
       "has_external_trigger": false,
+      "has_human_in_the_loop": false,
+      "has_sensitive_action": false,
       "trigger_setup_info": null,
       "new_output": false,
       "can_access_graph": true,
@@ -34,7 +36,8 @@
       "is_favorite": false,
       "recommended_schedule_cron": null,
       "settings": {
-        "human_in_the_loop_safe_mode": null
+        "human_in_the_loop_safe_mode": true,
+        "sensitive_action_safe_mode": false
       },
       "marketplace_listing": null
     },
@@ -65,6 +68,8 @@
         "properties": {}
       },
       "has_external_trigger": false,
+      "has_human_in_the_loop": false,
+      "has_sensitive_action": false,
       "trigger_setup_info": null,
       "new_output": false,
       "can_access_graph": false,
@@ -72,7 +77,8 @@
       "is_favorite": false,
       "recommended_schedule_cron": null,
       "settings": {
-        "human_in_the_loop_safe_mode": null
+        "human_in_the_loop_safe_mode": true,
+        "sensitive_action_safe_mode": false
       },
       "marketplace_listing": null
     }

autogpt_platform/frontend/.env.default

@@ -29,4 +29,8 @@ NEXT_PUBLIC_CLOUDFLARE_TURNSTILE_SITE_KEY=
 NEXT_PUBLIC_TURNSTILE=disabled
 
 # PR previews
-NEXT_PUBLIC_PREVIEW_STEALING_DEV=
+NEXT_PUBLIC_PREVIEW_STEALING_DEV=
+
+# PostHog Analytics
+NEXT_PUBLIC_POSTHOG_KEY=
+NEXT_PUBLIC_POSTHOG_HOST=https://eu.i.posthog.com

autogpt_platform/frontend/CONTRIBUTING.md

@@ -175,6 +175,8 @@ While server components and actions are cool and cutting-edge, they introduce a
 
 - Prefer [React Query](https://tanstack.com/query/latest/docs/framework/react/overview) for server state, colocated near consumers (see [state colocation](https://kentcdodds.com/blog/state-colocation-will-make-your-react-app-faster))
 - Co-locate UI state inside components/hooks; keep global state minimal
+- Avoid `useMemo` and `useCallback` unless you have a measured performance issue
+- Do not abuse `useEffect`; prefer state colocation and derive values directly when possible
 
 ### Styling and components
 
@@ -549,9 +551,48 @@ Files:
 Types:
 
 - Prefer `interface` for object shapes
-- Component props should be `interface Props { ... }`
+- Component props should be `interface Props { ... }` (not exported)
+- Only use specific exported names (e.g., `export interface MyComponentProps`) when the interface needs to be used outside the component
+- Keep type definitions inline with the component - do not create separate `types.ts` files unless types are shared across multiple files
 - Use precise types; avoid `any` and unsafe casts
 
+**Props naming examples:**
+
+```tsx
+// ✅ Good - internal props, not exported
+interface Props {
+  title: string;
+  onClose: () => void;
+}
+
+export function Modal({ title, onClose }: Props) {
+  // ...
+}
+
+// ✅ Good - exported when needed externally
+export interface ModalProps {
+  title: string;
+  onClose: () => void;
+}
+
+export function Modal({ title, onClose }: ModalProps) {
+  // ...
+}
+
+// ❌ Bad - unnecessarily specific name for internal use
+interface ModalComponentProps {
+  title: string;
+  onClose: () => void;
+}
+
+// ❌ Bad - separate types.ts file for single component
+// types.ts
+export interface ModalProps { ... }
+
+// Modal.tsx
+import type { ModalProps } from './types';
+```
+
 Parameters:
 
 - If more than one parameter is needed, pass a single `Args` object for clarity

autogpt_platform/frontend/orval.config.ts

@@ -16,6 +16,12 @@ export default defineConfig({
       client: "react-query",
       httpClient: "fetch",
       indexFiles: false,
+      mock: {
+        type: "msw",
+        baseUrl: "http://localhost:3000/api/proxy",
+        generateEachHttpStatus: true,
+        delay: 0,
+      },
       override: {
         mutator: {
           path: "./mutators/custom-mutator.ts",

autogpt_platform/frontend/package.json

@@ -15,6 +15,8 @@
     "types": "tsc --noEmit",
     "test": "NEXT_PUBLIC_PW_TEST=true next build --turbo && playwright test",
     "test-ui": "NEXT_PUBLIC_PW_TEST=true next build --turbo && playwright test --ui",
+    "test:unit": "vitest run",
+    "test:unit:watch": "vitest",
     "test:no-build": "playwright test",
     "gentests": "playwright codegen http://localhost:3000",
     "storybook": "storybook dev -p 6006",
@@ -32,6 +34,7 @@
     "@hookform/resolvers": "5.2.2",
     "@next/third-parties": "15.4.6",
     "@phosphor-icons/react": "2.1.10",
+    "@posthog/react": "1.7.0",
     "@radix-ui/react-accordion": "1.2.12",
     "@radix-ui/react-alert-dialog": "1.1.15",
     "@radix-ui/react-avatar": "1.1.10",
@@ -89,6 +92,7 @@
     "next-themes": "0.4.6",
     "nuqs": "2.7.2",
     "party-js": "2.2.0",
+    "posthog-js": "1.334.1",
     "react": "18.3.1",
     "react-currency-input-field": "4.0.3",
     "react-day-picker": "9.11.1",
@@ -127,6 +131,8 @@
     "@storybook/nextjs": "9.1.5",
     "@tanstack/eslint-plugin-query": "5.91.2",
     "@tanstack/react-query-devtools": "5.90.2",
+    "@testing-library/dom": "10.4.1",
+    "@testing-library/react": "16.3.2",
     "@types/canvas-confetti": "1.9.0",
     "@types/lodash": "4.17.20",
     "@types/negotiator": "0.6.4",
@@ -135,6 +141,7 @@
     "@types/react-dom": "18.3.5",
     "@types/react-modal": "3.16.3",
     "@types/react-window": "1.8.8",
+    "@vitejs/plugin-react": "5.1.2",
     "axe-playwright": "2.2.2",
     "chromatic": "13.3.3",
     "concurrently": "9.2.1",
@@ -142,6 +149,7 @@
     "eslint": "8.57.1",
     "eslint-config-next": "15.5.7",
     "eslint-plugin-storybook": "9.1.5",
+    "happy-dom": "20.3.4",
     "import-in-the-middle": "2.0.2",
     "msw": "2.11.6",
     "msw-storybook-addon": "2.0.6",
@@ -153,7 +161,9 @@
     "require-in-the-middle": "8.0.1",
     "storybook": "9.1.5",
     "tailwindcss": "3.4.17",
-    "typescript": "5.9.3"
+    "typescript": "5.9.3",
+    "vite-tsconfig-paths": "6.0.4",
+    "vitest": "4.0.17"
   },
   "msw": {
     "workerDirectory": [

autogpt_platform/frontend/src/app/(no-navbar)/logout/page.tsx

@@ -0,0 +1,58 @@
+"use client";
+
+import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
+import { Text } from "@/components/atoms/Text/Text";
+import { useToast } from "@/components/molecules/Toast/use-toast";
+import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
+import { useRouter } from "next/navigation";
+import { useEffect, useRef } from "react";
+
+const LOGOUT_REDIRECT_DELAY_MS = 400;
+
+function wait(ms: number): Promise<void> {
+  return new Promise(function resolveAfterDelay(resolve) {
+    setTimeout(resolve, ms);
+  });
+}
+
+export default function LogoutPage() {
+  const { logOut } = useSupabase();
+  const { toast } = useToast();
+  const router = useRouter();
+  const hasStartedRef = useRef(false);
+
+  useEffect(
+    function handleLogoutEffect() {
+      if (hasStartedRef.current) return;
+      hasStartedRef.current = true;
+
+      async function runLogout() {
+        try {
+          await logOut();
+        } catch {
+          toast({
+            title: "Failed to log out. Redirecting to login.",
+            variant: "destructive",
+          });
+        } finally {
+          await wait(LOGOUT_REDIRECT_DELAY_MS);
+          router.replace("/login");
+        }
+      }
+
+      void runLogout();
+    },
+    [logOut, router, toast],
+  );
+
+  return (
+    <div className="flex min-h-screen items-center justify-center px-4">
+      <div className="flex flex-col items-center justify-center gap-4 py-8">
+        <LoadingSpinner size="large" />
+        <Text variant="body" className="text-center">
+          Logging you out...
+        </Text>
+      </div>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/auth/callback/route.ts

@@ -9,7 +9,7 @@ export async function GET(request: Request) {
   const { searchParams, origin } = new URL(request.url);
   const code = searchParams.get("code");
 
-  let next = "/marketplace";
+  let next = "/";
 
   if (code) {
     const supabase = await getServerSupabase();

autogpt_platform/frontend/src/app/(platform)/build/components/FloatingSafeModeToogle.tsx

@@ -18,69 +18,118 @@ interface Props {
   fullWidth?: boolean;
 }
 
+interface SafeModeButtonProps {
+  isEnabled: boolean;
+  label: string;
+  tooltipEnabled: string;
+  tooltipDisabled: string;
+  onToggle: () => void;
+  isPending: boolean;
+  fullWidth?: boolean;
+}
+
+function SafeModeButton({
+  isEnabled,
+  label,
+  tooltipEnabled,
+  tooltipDisabled,
+  onToggle,
+  isPending,
+  fullWidth = false,
+}: SafeModeButtonProps) {
+  return (
+    <Tooltip delayDuration={100}>
+      <TooltipTrigger asChild>
+        <Button
+          variant={isEnabled ? "primary" : "outline"}
+          size="small"
+          onClick={onToggle}
+          disabled={isPending}
+          className={cn("justify-start", fullWidth ? "w-full" : "")}
+        >
+          {isEnabled ? (
+            <>
+              <ShieldCheckIcon weight="bold" size={16} />
+              <Text variant="body" className="text-zinc-200">
+                {label}: ON
+              </Text>
+            </>
+          ) : (
+            <>
+              <ShieldIcon weight="bold" size={16} />
+              <Text variant="body" className="text-zinc-600">
+                {label}: OFF
+              </Text>
+            </>
+          )}
+        </Button>
+      </TooltipTrigger>
+      <TooltipContent>
+        <div className="text-center">
+          <div className="font-medium">
+            {label}: {isEnabled ? "ON" : "OFF"}
+          </div>
+          <div className="mt-1 text-xs text-muted-foreground">
+            {isEnabled ? tooltipEnabled : tooltipDisabled}
+          </div>
+        </div>
+      </TooltipContent>
+    </Tooltip>
+  );
+}
+
 export function FloatingSafeModeToggle({
   graph,
   className,
   fullWidth = false,
 }: Props) {
   const {
-    currentSafeMode,
+    currentHITLSafeMode,
+    showHITLToggle,
+    isHITLStateUndetermined,
+    handleHITLToggle,
+    currentSensitiveActionSafeMode,
+    showSensitiveActionToggle,
+    handleSensitiveActionToggle,
     isPending,
     shouldShowToggle,
-    isStateUndetermined,
-    handleToggle,
   } = useAgentSafeMode(graph);
 
-  if (!shouldShowToggle || isStateUndetermined || isPending) {
+  if (!shouldShowToggle || isPending) {
+    return null;
+  }
+
+  const showHITL = showHITLToggle && !isHITLStateUndetermined;
+  const showSensitive = showSensitiveActionToggle;
+
+  if (!showHITL && !showSensitive) {
     return null;
   }
 
   return (
-    <div className={cn("fixed z-50", className)}>
-      <Tooltip delayDuration={100}>
-        <TooltipTrigger asChild>
-          <Button
-            variant={currentSafeMode! ? "primary" : "outline"}
-            key={graph.id}
-            size="small"
-            title={
-              currentSafeMode!
-                ? "Safe Mode: ON. Human in the loop blocks require manual review"
-                : "Safe Mode: OFF. Human in the loop blocks proceed automatically"
-            }
-            onClick={handleToggle}
-            className={cn(fullWidth ? "w-full" : "")}
-          >
-            {currentSafeMode! ? (
-              <>
-                <ShieldCheckIcon weight="bold" size={16} />
-                <Text variant="body" className="text-zinc-200">
-                  Safe Mode: ON
-                </Text>
-              </>
-            ) : (
-              <>
-                <ShieldIcon weight="bold" size={16} />
-                <Text variant="body" className="text-zinc-600">
-                  Safe Mode: OFF
-                </Text>
-              </>
-            )}
-          </Button>
-        </TooltipTrigger>
-        <TooltipContent>
-          <div className="text-center">
-            <div className="font-medium">
-              Safe Mode: {currentSafeMode! ? "ON" : "OFF"}
-            </div>
-            <div className="mt-1 text-xs text-muted-foreground">
-              {currentSafeMode!
-                ? "Human in the loop blocks require manual review"
-                : "Human in the loop blocks proceed automatically"}
-            </div>
-          </div>
-        </TooltipContent>
-      </Tooltip>
+    <div className={cn("fixed z-50 flex flex-col gap-2", className)}>
+      {showHITL && (
+        <SafeModeButton
+          isEnabled={currentHITLSafeMode}
+          label="Human in the loop block approval"
+          tooltipEnabled="The agent will pause at human-in-the-loop blocks and wait for your approval"
+          tooltipDisabled="Human in the loop blocks will proceed automatically"
+          onToggle={handleHITLToggle}
+          isPending={isPending}
+          fullWidth={fullWidth}
+        />
+      )}
+      {showSensitive && (
+        <SafeModeButton
+          isEnabled={currentSensitiveActionSafeMode}
+          label="Sensitive actions blocks approval"
+          tooltipEnabled="The agent will pause at sensitive action blocks and wait for your approval"
+          tooltipDisabled="Sensitive action blocks will proceed automatically"
+          onToggle={handleSensitiveActionToggle}
+          isPending={isPending}
+          fullWidth={fullWidth}
+        />
+      )}
     </div>
   );
 }

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/Chat.tsx

@@ -1,134 +0,0 @@
-"use client";
-
-import { Button } from "@/components/atoms/Button/Button";
-import { Text } from "@/components/atoms/Text/Text";
-import { cn } from "@/lib/utils";
-import { List } from "@phosphor-icons/react";
-import React, { useState } from "react";
-import { ChatContainer } from "./components/ChatContainer/ChatContainer";
-import { ChatErrorState } from "./components/ChatErrorState/ChatErrorState";
-import { ChatLoadingState } from "./components/ChatLoadingState/ChatLoadingState";
-import { SessionsDrawer } from "./components/SessionsDrawer/SessionsDrawer";
-import { useChat } from "./useChat";
-
-export interface ChatProps {
-  className?: string;
-  headerTitle?: React.ReactNode;
-  showHeader?: boolean;
-  showSessionInfo?: boolean;
-  showNewChatButton?: boolean;
-  onNewChat?: () => void;
-  headerActions?: React.ReactNode;
-}
-
-export function Chat({
-  className,
-  headerTitle = "AutoGPT Copilot",
-  showHeader = true,
-  showSessionInfo = true,
-  showNewChatButton = true,
-  onNewChat,
-  headerActions,
-}: ChatProps) {
-  const {
-    messages,
-    isLoading,
-    isCreating,
-    error,
-    sessionId,
-    createSession,
-    clearSession,
-    loadSession,
-  } = useChat();
-
-  const [isSessionsDrawerOpen, setIsSessionsDrawerOpen] = useState(false);
-
-  const handleNewChat = () => {
-    clearSession();
-    onNewChat?.();
-  };
-
-  const handleSelectSession = async (sessionId: string) => {
-    try {
-      await loadSession(sessionId);
-    } catch (err) {
-      console.error("Failed to load session:", err);
-    }
-  };
-
-  return (
-    <div className={cn("flex h-full flex-col", className)}>
-      {/* Header */}
-      {showHeader && (
-        <header className="shrink-0 border-t border-zinc-200 bg-white p-3">
-          <div className="flex items-center justify-between">
-            <div className="flex items-center gap-3">
-              <button
-                aria-label="View sessions"
-                onClick={() => setIsSessionsDrawerOpen(true)}
-                className="flex size-8 items-center justify-center rounded hover:bg-zinc-100"
-              >
-                <List width="1.25rem" height="1.25rem" />
-              </button>
-              {typeof headerTitle === "string" ? (
-                <Text variant="h2" className="text-lg font-semibold">
-                  {headerTitle}
-                </Text>
-              ) : (
-                headerTitle
-              )}
-            </div>
-            <div className="flex items-center gap-3">
-              {showSessionInfo && sessionId && (
-                <>
-                  {showNewChatButton && (
-                    <Button
-                      variant="outline"
-                      size="small"
-                      onClick={handleNewChat}
-                    >
-                      New Chat
-                    </Button>
-                  )}
-                </>
-              )}
-              {headerActions}
-            </div>
-          </div>
-        </header>
-      )}
-
-      {/* Main Content */}
-      <main className="flex min-h-0 flex-1 flex-col overflow-hidden">
-        {/* Loading State - show when explicitly loading/creating OR when we don't have a session yet and no error */}
-        {(isLoading || isCreating || (!sessionId && !error)) && (
-          <ChatLoadingState
-            message={isCreating ? "Creating session..." : "Loading..."}
-          />
-        )}
-
-        {/* Error State */}
-        {error && !isLoading && (
-          <ChatErrorState error={error} onRetry={createSession} />
-        )}
-
-        {/* Session Content */}
-        {sessionId && !isLoading && !error && (
-          <ChatContainer
-            sessionId={sessionId}
-            initialMessages={messages}
-            className="flex-1"
-          />
-        )}
-      </main>
-
-      {/* Sessions Drawer */}
-      <SessionsDrawer
-        isOpen={isSessionsDrawerOpen}
-        onClose={() => setIsSessionsDrawerOpen(false)}
-        onSelectSession={handleSelectSession}
-        currentSessionId={sessionId}
-      />
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ChatContainer/ChatContainer.tsx

@@ -1,88 +0,0 @@
-import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
-import { cn } from "@/lib/utils";
-import { useCallback } from "react";
-import { usePageContext } from "../../usePageContext";
-import { ChatInput } from "../ChatInput/ChatInput";
-import { MessageList } from "../MessageList/MessageList";
-import { QuickActionsWelcome } from "../QuickActionsWelcome/QuickActionsWelcome";
-import { useChatContainer } from "./useChatContainer";
-
-export interface ChatContainerProps {
-  sessionId: string | null;
-  initialMessages: SessionDetailResponse["messages"];
-  className?: string;
-}
-
-export function ChatContainer({
-  sessionId,
-  initialMessages,
-  className,
-}: ChatContainerProps) {
-  const { messages, streamingChunks, isStreaming, sendMessage } =
-    useChatContainer({
-      sessionId,
-      initialMessages,
-    });
-  const { capturePageContext } = usePageContext();
-
-  // Wrap sendMessage to automatically capture page context
-  const sendMessageWithContext = useCallback(
-    async (content: string, isUserMessage: boolean = true) => {
-      const context = capturePageContext();
-      await sendMessage(content, isUserMessage, context);
-    },
-    [sendMessage, capturePageContext],
-  );
-
-  const quickActions = [
-    "Find agents for social media management",
-    "Show me agents for content creation",
-    "Help me automate my business",
-    "What can you help me with?",
-  ];
-
-  return (
-    <div
-      className={cn("flex h-full min-h-0 flex-col", className)}
-      style={{
-        backgroundColor: "#ffffff",
-        backgroundImage:
-          "radial-gradient(#e5e5e5 0.5px, transparent 0.5px), radial-gradient(#e5e5e5 0.5px, #ffffff 0.5px)",
-        backgroundSize: "20px 20px",
-        backgroundPosition: "0 0, 10px 10px",
-      }}
-    >
-      {/* Messages or Welcome Screen */}
-      <div className="flex min-h-0 flex-1 flex-col overflow-hidden pb-24">
-        {messages.length === 0 ? (
-          <QuickActionsWelcome
-            title="Welcome to AutoGPT Copilot"
-            description="Start a conversation to discover and run AI agents."
-            actions={quickActions}
-            onActionClick={sendMessageWithContext}
-            disabled={isStreaming || !sessionId}
-          />
-        ) : (
-          <MessageList
-            messages={messages}
-            streamingChunks={streamingChunks}
-            isStreaming={isStreaming}
-            onSendMessage={sendMessageWithContext}
-            className="flex-1"
-          />
-        )}
-      </div>
-
-      {/* Input - Always visible */}
-      <div className="fixed bottom-0 left-0 right-0 z-50 border-t border-zinc-200 bg-white p-4">
-        <ChatInput
-          onSend={sendMessageWithContext}
-          disabled={isStreaming || !sessionId}
-          placeholder={
-            sessionId ? "Type your message..." : "Creating session..."
-          }
-        />
-      </div>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ChatInput/ChatInput.tsx

@@ -1,64 +0,0 @@
-import { Input } from "@/components/atoms/Input/Input";
-import { cn } from "@/lib/utils";
-import { ArrowUpIcon } from "@phosphor-icons/react";
-import { useChatInput } from "./useChatInput";
-
-export interface ChatInputProps {
-  onSend: (message: string) => void;
-  disabled?: boolean;
-  placeholder?: string;
-  className?: string;
-}
-
-export function ChatInput({
-  onSend,
-  disabled = false,
-  placeholder = "Type your message...",
-  className,
-}: ChatInputProps) {
-  const inputId = "chat-input";
-  const { value, setValue, handleKeyDown, handleSend } = useChatInput({
-    onSend,
-    disabled,
-    maxRows: 5,
-    inputId,
-  });
-
-  return (
-    <div className={cn("relative flex-1", className)}>
-      <Input
-        id={inputId}
-        label="Chat message input"
-        hideLabel
-        type="textarea"
-        value={value}
-        onChange={(e) => setValue(e.target.value)}
-        onKeyDown={handleKeyDown}
-        placeholder={placeholder}
-        disabled={disabled}
-        rows={1}
-        wrapperClassName="mb-0 relative"
-        className="pr-12"
-      />
-      <span id="chat-input-hint" className="sr-only">
-        Press Enter to send, Shift+Enter for new line
-      </span>
-
-      <button
-        onClick={handleSend}
-        disabled={disabled || !value.trim()}
-        className={cn(
-          "absolute right-3 top-1/2 flex h-8 w-8 -translate-y-1/2 items-center justify-center rounded-full",
-          "border border-zinc-800 bg-zinc-800 text-white",
-          "hover:border-zinc-900 hover:bg-zinc-900",
-          "disabled:border-zinc-200 disabled:bg-zinc-200 disabled:text-white disabled:opacity-50",
-          "transition-colors focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-neutral-950",
-          "disabled:pointer-events-none",
-        )}
-        aria-label="Send message"
-      >
-        <ArrowUpIcon className="h-3 w-3" weight="bold" />
-      </button>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ChatInput/useChatInput.ts

@@ -1,60 +0,0 @@
-import { KeyboardEvent, useCallback, useEffect, useState } from "react";
-
-interface UseChatInputArgs {
-  onSend: (message: string) => void;
-  disabled?: boolean;
-  maxRows?: number;
-  inputId?: string;
-}
-
-export function useChatInput({
-  onSend,
-  disabled = false,
-  maxRows = 5,
-  inputId = "chat-input",
-}: UseChatInputArgs) {
-  const [value, setValue] = useState("");
-
-  useEffect(() => {
-    const textarea = document.getElementById(inputId) as HTMLTextAreaElement;
-    if (!textarea) return;
-    textarea.style.height = "auto";
-    const lineHeight = parseInt(
-      window.getComputedStyle(textarea).lineHeight,
-      10,
-    );
-    const maxHeight = lineHeight * maxRows;
-    const newHeight = Math.min(textarea.scrollHeight, maxHeight);
-    textarea.style.height = `${newHeight}px`;
-    textarea.style.overflowY =
-      textarea.scrollHeight > maxHeight ? "auto" : "hidden";
-  }, [value, maxRows, inputId]);
-
-  const handleSend = useCallback(() => {
-    if (disabled || !value.trim()) return;
-    onSend(value.trim());
-    setValue("");
-    const textarea = document.getElementById(inputId) as HTMLTextAreaElement;
-    if (textarea) {
-      textarea.style.height = "auto";
-    }
-  }, [value, onSend, disabled, inputId]);
-
-  const handleKeyDown = useCallback(
-    (event: KeyboardEvent<HTMLInputElement | HTMLTextAreaElement>) => {
-      if (event.key === "Enter" && !event.shiftKey) {
-        event.preventDefault();
-        handleSend();
-      }
-      // Shift+Enter allows default behavior (new line) - no need to handle explicitly
-    },
-    [handleSend],
-  );
-
-  return {
-    value,
-    setValue,
-    handleKeyDown,
-    handleSend,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/MessageList/MessageList.tsx

@@ -1,121 +0,0 @@
-"use client";
-
-import { cn } from "@/lib/utils";
-import { ChatMessage } from "../ChatMessage/ChatMessage";
-import type { ChatMessageData } from "../ChatMessage/useChatMessage";
-import { StreamingMessage } from "../StreamingMessage/StreamingMessage";
-import { ThinkingMessage } from "../ThinkingMessage/ThinkingMessage";
-import { useMessageList } from "./useMessageList";
-
-export interface MessageListProps {
-  messages: ChatMessageData[];
-  streamingChunks?: string[];
-  isStreaming?: boolean;
-  className?: string;
-  onStreamComplete?: () => void;
-  onSendMessage?: (content: string) => void;
-}
-
-export function MessageList({
-  messages,
-  streamingChunks = [],
-  isStreaming = false,
-  className,
-  onStreamComplete,
-  onSendMessage,
-}: MessageListProps) {
-  const { messagesEndRef, messagesContainerRef } = useMessageList({
-    messageCount: messages.length,
-    isStreaming,
-  });
-
-  return (
-    <div
-      ref={messagesContainerRef}
-      className={cn(
-        "flex-1 overflow-y-auto",
-        "scrollbar-thin scrollbar-track-transparent scrollbar-thumb-zinc-300",
-        className,
-      )}
-    >
-      <div className="mx-auto flex max-w-3xl flex-col py-4">
-        {/* Render all persisted messages */}
-        {messages.map((message, index) => {
-          // Check if current message is an agent_output tool_response
-          // and if previous message is an assistant message
-          let agentOutput: ChatMessageData | undefined;
-
-          if (message.type === "tool_response" && message.result) {
-            let parsedResult: Record<string, unknown> | null = null;
-            try {
-              parsedResult =
-                typeof message.result === "string"
-                  ? JSON.parse(message.result)
-                  : (message.result as Record<string, unknown>);
-            } catch {
-              parsedResult = null;
-            }
-            if (parsedResult?.type === "agent_output") {
-              const prevMessage = messages[index - 1];
-              if (
-                prevMessage &&
-                prevMessage.type === "message" &&
-                prevMessage.role === "assistant"
-              ) {
-                // This agent output will be rendered inside the previous assistant message
-                // Skip rendering this message separately
-                return null;
-              }
-            }
-          }
-
-          // Check if next message is an agent_output tool_response to include in current assistant message
-          if (message.type === "message" && message.role === "assistant") {
-            const nextMessage = messages[index + 1];
-            if (
-              nextMessage &&
-              nextMessage.type === "tool_response" &&
-              nextMessage.result
-            ) {
-              let parsedResult: Record<string, unknown> | null = null;
-              try {
-                parsedResult =
-                  typeof nextMessage.result === "string"
-                    ? JSON.parse(nextMessage.result)
-                    : (nextMessage.result as Record<string, unknown>);
-              } catch {
-                parsedResult = null;
-              }
-              if (parsedResult?.type === "agent_output") {
-                agentOutput = nextMessage;
-              }
-            }
-          }
-
-          return (
-            <ChatMessage
-              key={index}
-              message={message}
-              onSendMessage={onSendMessage}
-              agentOutput={agentOutput}
-            />
-          );
-        })}
-
-        {/* Render thinking message when streaming but no chunks yet */}
-        {isStreaming && streamingChunks.length === 0 && <ThinkingMessage />}
-
-        {/* Render streaming message if active */}
-        {isStreaming && streamingChunks.length > 0 && (
-          <StreamingMessage
-            chunks={streamingChunks}
-            onComplete={onStreamComplete}
-          />
-        )}
-
-        {/* Invisible div to scroll to */}
-        <div ref={messagesEndRef} />
-      </div>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ThinkingMessage/ThinkingMessage.tsx

@@ -1,70 +0,0 @@
-import { cn } from "@/lib/utils";
-import { RobotIcon } from "@phosphor-icons/react";
-import { useEffect, useRef, useState } from "react";
-import { MessageBubble } from "../MessageBubble/MessageBubble";
-
-export interface ThinkingMessageProps {
-  className?: string;
-}
-
-export function ThinkingMessage({ className }: ThinkingMessageProps) {
-  const [showSlowLoader, setShowSlowLoader] = useState(false);
-  const timerRef = useRef<NodeJS.Timeout | null>(null);
-
-  useEffect(() => {
-    if (timerRef.current === null) {
-      timerRef.current = setTimeout(() => {
-        setShowSlowLoader(true);
-      }, 8000);
-    }
-
-    return () => {
-      if (timerRef.current) {
-        clearTimeout(timerRef.current);
-        timerRef.current = null;
-      }
-    };
-  }, []);
-
-  return (
-    <div
-      className={cn(
-        "group relative flex w-full justify-start gap-3 px-4 py-3",
-        className,
-      )}
-    >
-      <div className="flex w-full max-w-3xl gap-3">
-        <div className="flex-shrink-0">
-          <div className="flex h-7 w-7 items-center justify-center rounded-lg bg-indigo-500">
-            <RobotIcon className="h-4 w-4 text-indigo-50" />
-          </div>
-        </div>
-
-        <div className="flex min-w-0 flex-1 flex-col">
-          <MessageBubble variant="assistant">
-            <div className="transition-all duration-500 ease-in-out">
-              {showSlowLoader ? (
-                <div className="flex flex-col items-center gap-3 py-2">
-                  <div className="loader" style={{ flexShrink: 0 }} />
-                  <p className="text-sm text-slate-700">
-                    Taking a bit longer to think, wait a moment please
-                  </p>
-                </div>
-              ) : (
-                <span
-                  className="inline-block bg-gradient-to-r from-neutral-400 via-neutral-600 to-neutral-400 bg-clip-text text-transparent"
-                  style={{
-                    backgroundSize: "200% 100%",
-                    animation: "shimmer 2s ease-in-out infinite",
-                  }}
-                >
-                  Thinking...
-                </span>
-              )}
-            </div>
-          </MessageBubble>
-        </div>
-      </div>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ToolCallMessage/ToolCallMessage.tsx

@@ -1,24 +0,0 @@
-import { Text } from "@/components/atoms/Text/Text";
-import { cn } from "@/lib/utils";
-import { WrenchIcon } from "@phosphor-icons/react";
-import { getToolActionPhrase } from "../../helpers";
-
-export interface ToolCallMessageProps {
-  toolName: string;
-  className?: string;
-}
-
-export function ToolCallMessage({ toolName, className }: ToolCallMessageProps) {
-  return (
-    <div className={cn("flex items-center justify-center gap-2", className)}>
-      <WrenchIcon
-        size={14}
-        weight="bold"
-        className="flex-shrink-0 text-neutral-500"
-      />
-      <Text variant="small" className="text-neutral-500">
-        {getToolActionPhrase(toolName)}...
-      </Text>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/components/ToolResponseMessage/ToolResponseMessage.tsx

@@ -1,260 +0,0 @@
-import { Text } from "@/components/atoms/Text/Text";
-import "@/components/contextual/OutputRenderers";
-import {
-  globalRegistry,
-  OutputItem,
-} from "@/components/contextual/OutputRenderers";
-import { cn } from "@/lib/utils";
-import type { ToolResult } from "@/types/chat";
-import { WrenchIcon } from "@phosphor-icons/react";
-import { getToolActionPhrase } from "../../helpers";
-
-export interface ToolResponseMessageProps {
-  toolName: string;
-  result?: ToolResult;
-  success?: boolean;
-  className?: string;
-}
-
-export function ToolResponseMessage({
-  toolName,
-  result,
-  success: _success = true,
-  className,
-}: ToolResponseMessageProps) {
-  if (!result) {
-    return (
-      <div className={cn("flex items-center justify-center gap-2", className)}>
-        <WrenchIcon
-          size={14}
-          weight="bold"
-          className="flex-shrink-0 text-neutral-500"
-        />
-        <Text variant="small" className="text-neutral-500">
-          {getToolActionPhrase(toolName)}...
-        </Text>
-      </div>
-    );
-  }
-
-  let parsedResult: Record<string, unknown> | null = null;
-  try {
-    parsedResult =
-      typeof result === "string"
-        ? JSON.parse(result)
-        : (result as Record<string, unknown>);
-  } catch {
-    parsedResult = null;
-  }
-
-  if (parsedResult && typeof parsedResult === "object") {
-    const responseType = parsedResult.type as string | undefined;
-
-    if (responseType === "agent_output") {
-      const execution = parsedResult.execution as
-        | {
-            outputs?: Record<string, unknown[]>;
-          }
-        | null
-        | undefined;
-      const outputs = execution?.outputs || {};
-      const message = parsedResult.message as string | undefined;
-
-      return (
-        <div className={cn("space-y-4 px-4 py-2", className)}>
-          <div className="flex items-center gap-2">
-            <WrenchIcon
-              size={14}
-              weight="bold"
-              className="flex-shrink-0 text-neutral-500"
-            />
-            <Text variant="small" className="text-neutral-500">
-              {getToolActionPhrase(toolName)}
-            </Text>
-          </div>
-          {message && (
-            <div className="rounded border p-4">
-              <Text variant="small" className="text-neutral-600">
-                {message}
-              </Text>
-            </div>
-          )}
-          {Object.keys(outputs).length > 0 && (
-            <div className="space-y-4">
-              {Object.entries(outputs).map(([outputName, values]) =>
-                values.map((value, index) => {
-                  const renderer = globalRegistry.getRenderer(value);
-                  if (renderer) {
-                    return (
-                      <OutputItem
-                        key={`${outputName}-${index}`}
-                        value={value}
-                        renderer={renderer}
-                        label={outputName}
-                      />
-                    );
-                  }
-                  return (
-                    <div
-                      key={`${outputName}-${index}`}
-                      className="rounded border p-4"
-                    >
-                      <Text variant="large-medium" className="mb-2 capitalize">
-                        {outputName}
-                      </Text>
-                      <pre className="overflow-auto text-sm">
-                        {JSON.stringify(value, null, 2)}
-                      </pre>
-                    </div>
-                  );
-                }),
-              )}
-            </div>
-          )}
-        </div>
-      );
-    }
-
-    if (responseType === "block_output" && parsedResult.outputs) {
-      const outputs = parsedResult.outputs as Record<string, unknown[]>;
-
-      return (
-        <div className={cn("space-y-4 px-4 py-2", className)}>
-          <div className="flex items-center gap-2">
-            <WrenchIcon
-              size={14}
-              weight="bold"
-              className="flex-shrink-0 text-neutral-500"
-            />
-            <Text variant="small" className="text-neutral-500">
-              {getToolActionPhrase(toolName)}
-            </Text>
-          </div>
-          <div className="space-y-4">
-            {Object.entries(outputs).map(([outputName, values]) =>
-              values.map((value, index) => {
-                const renderer = globalRegistry.getRenderer(value);
-                if (renderer) {
-                  return (
-                    <OutputItem
-                      key={`${outputName}-${index}`}
-                      value={value}
-                      renderer={renderer}
-                      label={outputName}
-                    />
-                  );
-                }
-                return (
-                  <div
-                    key={`${outputName}-${index}`}
-                    className="rounded border p-4"
-                  >
-                    <Text variant="large-medium" className="mb-2 capitalize">
-                      {outputName}
-                    </Text>
-                    <pre className="overflow-auto text-sm">
-                      {JSON.stringify(value, null, 2)}
-                    </pre>
-                  </div>
-                );
-              }),
-            )}
-          </div>
-        </div>
-      );
-    }
-
-    // Handle other response types with a message field (e.g., understanding_updated)
-    if (parsedResult.message && typeof parsedResult.message === "string") {
-      // Format tool name from snake_case to Title Case
-      const formattedToolName = toolName
-        .split("_")
-        .map((word) => word.charAt(0).toUpperCase() + word.slice(1))
-        .join(" ");
-
-      // Clean up message - remove incomplete user_name references
-      let cleanedMessage = parsedResult.message;
-      // Remove "Updated understanding with: user_name" pattern if user_name is just a placeholder
-      cleanedMessage = cleanedMessage.replace(
-        /Updated understanding with:\s*user_name\.?\s*/gi,
-        "",
-      );
-      // Remove standalone user_name references
-      cleanedMessage = cleanedMessage.replace(/\buser_name\b\.?\s*/gi, "");
-      cleanedMessage = cleanedMessage.trim();
-
-      // Only show message if it has content after cleaning
-      if (!cleanedMessage) {
-        return (
-          <div
-            className={cn(
-              "flex items-center justify-center gap-2 px-4 py-2",
-              className,
-            )}
-          >
-            <WrenchIcon
-              size={14}
-              weight="bold"
-              className="flex-shrink-0 text-neutral-500"
-            />
-            <Text variant="small" className="text-neutral-500">
-              {formattedToolName}
-            </Text>
-          </div>
-        );
-      }
-
-      return (
-        <div className={cn("space-y-2 px-4 py-2", className)}>
-          <div className="flex items-center justify-center gap-2">
-            <WrenchIcon
-              size={14}
-              weight="bold"
-              className="flex-shrink-0 text-neutral-500"
-            />
-            <Text variant="small" className="text-neutral-500">
-              {formattedToolName}
-            </Text>
-          </div>
-          <div className="rounded border p-4">
-            <Text variant="small" className="text-neutral-600">
-              {cleanedMessage}
-            </Text>
-          </div>
-        </div>
-      );
-    }
-  }
-
-  const renderer = globalRegistry.getRenderer(result);
-  if (renderer) {
-    return (
-      <div className={cn("px-4 py-2", className)}>
-        <div className="mb-2 flex items-center gap-2">
-          <WrenchIcon
-            size={14}
-            weight="bold"
-            className="flex-shrink-0 text-neutral-500"
-          />
-          <Text variant="small" className="text-neutral-500">
-            {getToolActionPhrase(toolName)}
-          </Text>
-        </div>
-        <OutputItem value={result} renderer={renderer} />
-      </div>
-    );
-  }
-
-  return (
-    <div className={cn("flex items-center justify-center gap-2", className)}>
-      <WrenchIcon
-        size={14}
-        weight="bold"
-        className="flex-shrink-0 text-neutral-500"
-      />
-      <Text variant="small" className="text-neutral-500">
-        {getToolActionPhrase(toolName)}...
-      </Text>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/helpers.ts

@@ -1,66 +0,0 @@
-/**
- * Maps internal tool names to user-friendly display names with emojis.
- * @deprecated Use getToolActionPhrase or getToolCompletionPhrase for status messages
- *
- * @param toolName - The internal tool name from the backend
- * @returns A user-friendly display name with an emoji prefix
- */
-export function getToolDisplayName(toolName: string): string {
-  const toolDisplayNames: Record<string, string> = {
-    find_agent: "🔍 Search Marketplace",
-    get_agent_details: "📋 Get Agent Details",
-    check_credentials: "🔑 Check Credentials",
-    setup_agent: "⚙️ Setup Agent",
-    run_agent: "▶️ Run Agent",
-    get_required_setup_info: "📝 Get Setup Requirements",
-  };
-  return toolDisplayNames[toolName] || toolName;
-}
-
-/**
- * Maps internal tool names to human-friendly action phrases (present continuous).
- * Used for tool call messages to indicate what action is currently happening.
- *
- * @param toolName - The internal tool name from the backend
- * @returns A human-friendly action phrase in present continuous tense
- */
-export function getToolActionPhrase(toolName: string): string {
-  const toolActionPhrases: Record<string, string> = {
-    find_agent: "Looking for agents in the marketplace",
-    agent_carousel: "Looking for agents in the marketplace",
-    get_agent_details: "Learning about the agent",
-    check_credentials: "Checking your credentials",
-    setup_agent: "Setting up the agent",
-    execution_started: "Running the agent",
-    run_agent: "Running the agent",
-    get_required_setup_info: "Getting setup requirements",
-    schedule_agent: "Scheduling the agent to run",
-  };
-
-  // Return mapped phrase or generate human-friendly fallback
-  return toolActionPhrases[toolName] || toolName;
-}
-
-/**
- * Maps internal tool names to human-friendly completion phrases (past tense).
- * Used for tool response messages to indicate what action was completed.
- *
- * @param toolName - The internal tool name from the backend
- * @returns A human-friendly completion phrase in past tense
- */
-export function getToolCompletionPhrase(toolName: string): string {
-  const toolCompletionPhrases: Record<string, string> = {
-    find_agent: "Finished searching the marketplace",
-    get_agent_details: "Got agent details",
-    check_credentials: "Checked credentials",
-    setup_agent: "Agent setup complete",
-    run_agent: "Agent execution started",
-    get_required_setup_info: "Got setup requirements",
-  };
-
-  // Return mapped phrase or generate human-friendly fallback
-  return (
-    toolCompletionPhrases[toolName] ||
-    `Finished ${toolName.replace(/_/g, " ").replace("...", "")}`
-  );
-}

autogpt_platform/frontend/src/app/(platform)/chat/components/Chat/useChatSession.ts

@@ -1,271 +0,0 @@
-import {
-  getGetV2GetSessionQueryKey,
-  getGetV2GetSessionQueryOptions,
-  postV2CreateSession,
-  useGetV2GetSession,
-  usePatchV2SessionAssignUser,
-  usePostV2CreateSession,
-} from "@/app/api/__generated__/endpoints/chat/chat";
-import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
-import { okData } from "@/app/api/helpers";
-import { isValidUUID } from "@/lib/utils";
-import { Key, storage } from "@/services/storage/local-storage";
-import { useQueryClient } from "@tanstack/react-query";
-import { useCallback, useEffect, useMemo, useRef, useState } from "react";
-import { toast } from "sonner";
-
-interface UseChatSessionArgs {
-  urlSessionId?: string | null;
-  autoCreate?: boolean;
-}
-
-export function useChatSession({
-  urlSessionId,
-  autoCreate = false,
-}: UseChatSessionArgs = {}) {
-  const queryClient = useQueryClient();
-  const [sessionId, setSessionId] = useState<string | null>(null);
-  const [error, setError] = useState<Error | null>(null);
-  const justCreatedSessionIdRef = useRef<string | null>(null);
-
-  useEffect(() => {
-    if (urlSessionId) {
-      if (!isValidUUID(urlSessionId)) {
-        console.error("Invalid session ID format:", urlSessionId);
-        toast.error("Invalid session ID", {
-          description:
-            "The session ID in the URL is not valid. Starting a new session...",
-        });
-        setSessionId(null);
-        storage.clean(Key.CHAT_SESSION_ID);
-        return;
-      }
-      setSessionId(urlSessionId);
-      storage.set(Key.CHAT_SESSION_ID, urlSessionId);
-    } else {
-      const storedSessionId = storage.get(Key.CHAT_SESSION_ID);
-      if (storedSessionId) {
-        if (!isValidUUID(storedSessionId)) {
-          console.error("Invalid stored session ID:", storedSessionId);
-          storage.clean(Key.CHAT_SESSION_ID);
-          setSessionId(null);
-        } else {
-          setSessionId(storedSessionId);
-        }
-      } else if (autoCreate) {
-        setSessionId(null);
-      }
-    }
-  }, [urlSessionId, autoCreate]);
-
-  const {
-    mutateAsync: createSessionMutation,
-    isPending: isCreating,
-    error: createError,
-  } = usePostV2CreateSession();
-
-  const {
-    data: sessionData,
-    isLoading: isLoadingSession,
-    error: loadError,
-    refetch,
-  } = useGetV2GetSession(sessionId || "", {
-    query: {
-      enabled: !!sessionId,
-      select: okData,
-      staleTime: Infinity, // Never mark as stale
-      refetchOnMount: false, // Don't refetch on component mount
-      refetchOnWindowFocus: false, // Don't refetch when window regains focus
-      refetchOnReconnect: false, // Don't refetch when network reconnects
-      retry: 1,
-    },
-  });
-
-  const { mutateAsync: claimSessionMutation } = usePatchV2SessionAssignUser();
-
-  const session = useMemo(() => {
-    if (sessionData) return sessionData;
-
-    if (sessionId && justCreatedSessionIdRef.current === sessionId) {
-      return {
-        id: sessionId,
-        user_id: null,
-        messages: [],
-        created_at: new Date().toISOString(),
-        updated_at: new Date().toISOString(),
-      } as SessionDetailResponse;
-    }
-    return null;
-  }, [sessionData, sessionId]);
-
-  const messages = session?.messages || [];
-  const isLoading = isCreating || isLoadingSession;
-
-  useEffect(() => {
-    if (createError) {
-      setError(
-        createError instanceof Error
-          ? createError
-          : new Error("Failed to create session"),
-      );
-    } else if (loadError) {
-      setError(
-        loadError instanceof Error
-          ? loadError
-          : new Error("Failed to load session"),
-      );
-    } else {
-      setError(null);
-    }
-  }, [createError, loadError]);
-
-  const createSession = useCallback(
-    async function createSession() {
-      try {
-        setError(null);
-        const response = await postV2CreateSession({
-          body: JSON.stringify({}),
-        });
-        if (response.status !== 200) {
-          throw new Error("Failed to create session");
-        }
-        const newSessionId = response.data.id;
-        setSessionId(newSessionId);
-        storage.set(Key.CHAT_SESSION_ID, newSessionId);
-        justCreatedSessionIdRef.current = newSessionId;
-        setTimeout(() => {
-          if (justCreatedSessionIdRef.current === newSessionId) {
-            justCreatedSessionIdRef.current = null;
-          }
-        }, 10000);
-        return newSessionId;
-      } catch (err) {
-        const error =
-          err instanceof Error ? err : new Error("Failed to create session");
-        setError(error);
-        toast.error("Failed to create chat session", {
-          description: error.message,
-        });
-        throw error;
-      }
-    },
-    [createSessionMutation],
-  );
-
-  const loadSession = useCallback(
-    async function loadSession(id: string) {
-      try {
-        setError(null);
-        // Invalidate the query cache for this session to force a fresh fetch
-        await queryClient.invalidateQueries({
-          queryKey: getGetV2GetSessionQueryKey(id),
-        });
-        // Set sessionId after invalidation to ensure the hook refetches
-        setSessionId(id);
-        storage.set(Key.CHAT_SESSION_ID, id);
-        // Force fetch with fresh data (bypass cache)
-        const queryOptions = getGetV2GetSessionQueryOptions(id, {
-          query: {
-            staleTime: 0, // Force fresh fetch
-            retry: 1,
-          },
-        });
-        const result = await queryClient.fetchQuery(queryOptions);
-        if (!result || ("status" in result && result.status !== 200)) {
-          console.warn("Session not found on server, clearing local state");
-          storage.clean(Key.CHAT_SESSION_ID);
-          setSessionId(null);
-          throw new Error("Session not found");
-        }
-      } catch (err) {
-        const error =
-          err instanceof Error ? err : new Error("Failed to load session");
-        setError(error);
-        throw error;
-      }
-    },
-    [queryClient],
-  );
-
-  const refreshSession = useCallback(
-    async function refreshSession() {
-      if (!sessionId) {
-        console.log("[refreshSession] Skipping - no session ID");
-        return;
-      }
-      try {
-        setError(null);
-        await refetch();
-      } catch (err) {
-        const error =
-          err instanceof Error ? err : new Error("Failed to refresh session");
-        setError(error);
-        throw error;
-      }
-    },
-    [sessionId, refetch],
-  );
-
-  const claimSession = useCallback(
-    async function claimSession(id: string) {
-      try {
-        setError(null);
-        await claimSessionMutation({ sessionId: id });
-        if (justCreatedSessionIdRef.current === id) {
-          justCreatedSessionIdRef.current = null;
-        }
-        await queryClient.invalidateQueries({
-          queryKey: getGetV2GetSessionQueryKey(id),
-        });
-        await refetch();
-        toast.success("Session claimed successfully", {
-          description: "Your chat history has been saved to your account",
-        });
-      } catch (err: unknown) {
-        const error =
-          err instanceof Error ? err : new Error("Failed to claim session");
-        const is404 =
-          (typeof err === "object" &&
-            err !== null &&
-            "status" in err &&
-            err.status === 404) ||
-          (typeof err === "object" &&
-            err !== null &&
-            "response" in err &&
-            typeof err.response === "object" &&
-            err.response !== null &&
-            "status" in err.response &&
-            err.response.status === 404);
-        if (!is404) {
-          setError(error);
-          toast.error("Failed to claim session", {
-            description: error.message || "Unable to claim session",
-          });
-        }
-        throw error;
-      }
-    },
-    [claimSessionMutation, queryClient, refetch],
-  );
-
-  const clearSession = useCallback(function clearSession() {
-    setSessionId(null);
-    setError(null);
-    storage.clean(Key.CHAT_SESSION_ID);
-    justCreatedSessionIdRef.current = null;
-  }, []);
-
-  return {
-    session,
-    sessionId,
-    messages,
-    isLoading,
-    isCreating,
-    error,
-    createSession,
-    loadSession,
-    refreshSession,
-    claimSession,
-    clearSession,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/chat/page.tsx

@@ -1,27 +0,0 @@
-"use client";
-
-import { Flag, useGetFlag } from "@/services/feature-flags/use-get-flag";
-import { useRouter } from "next/navigation";
-import { useEffect } from "react";
-import { Chat } from "./components/Chat/Chat";
-
-export default function ChatPage() {
-  const isChatEnabled = useGetFlag(Flag.CHAT);
-  const router = useRouter();
-
-  useEffect(() => {
-    if (isChatEnabled === false) {
-      router.push("/marketplace");
-    }
-  }, [isChatEnabled, router]);
-
-  if (isChatEnabled === null || isChatEnabled === false) {
-    return null;
-  }
-
-  return (
-    <div className="flex h-full flex-col">
-      <Chat className="flex-1" />
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/NewChatContext.tsx

@@ -0,0 +1,41 @@
+"use client";
+
+import { createContext, useContext, useRef, type ReactNode } from "react";
+
+interface NewChatContextValue {
+  onNewChatClick: () => void;
+  setOnNewChatClick: (handler?: () => void) => void;
+  performNewChat?: () => void;
+  setPerformNewChat: (handler?: () => void) => void;
+}
+
+const NewChatContext = createContext<NewChatContextValue | null>(null);
+
+export function NewChatProvider({ children }: { children: ReactNode }) {
+  const onNewChatRef = useRef<(() => void) | undefined>();
+  const performNewChatRef = useRef<(() => void) | undefined>();
+  const contextValueRef = useRef<NewChatContextValue>({
+    onNewChatClick() {
+      onNewChatRef.current?.();
+    },
+    setOnNewChatClick(handler?: () => void) {
+      onNewChatRef.current = handler;
+    },
+    performNewChat() {
+      performNewChatRef.current?.();
+    },
+    setPerformNewChat(handler?: () => void) {
+      performNewChatRef.current = handler;
+    },
+  });
+
+  return (
+    <NewChatContext.Provider value={contextValueRef.current}>
+      {children}
+    </NewChatContext.Provider>
+  );
+}
+
+export function useNewChat() {
+  return useContext(NewChatContext);
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/CopilotShell.tsx

@@ -0,0 +1,105 @@
+"use client";
+
+import { ChatLoader } from "@/components/contextual/Chat/components/ChatLoader/ChatLoader";
+import { NAVBAR_HEIGHT_PX } from "@/lib/constants";
+import type { ReactNode } from "react";
+import { useEffect } from "react";
+import { useNewChat } from "../../NewChatContext";
+import { DesktopSidebar } from "./components/DesktopSidebar/DesktopSidebar";
+import { LoadingState } from "./components/LoadingState/LoadingState";
+import { MobileDrawer } from "./components/MobileDrawer/MobileDrawer";
+import { MobileHeader } from "./components/MobileHeader/MobileHeader";
+import { useCopilotShell } from "./useCopilotShell";
+
+interface Props {
+  children: ReactNode;
+}
+
+export function CopilotShell({ children }: Props) {
+  const {
+    isMobile,
+    isDrawerOpen,
+    isLoading,
+    isLoggedIn,
+    hasActiveSession,
+    sessions,
+    currentSessionId,
+    handleSelectSession,
+    handleOpenDrawer,
+    handleCloseDrawer,
+    handleDrawerOpenChange,
+    handleNewChat,
+    hasNextPage,
+    isFetchingNextPage,
+    fetchNextPage,
+    isReadyToShowContent,
+  } = useCopilotShell();
+
+  const newChatContext = useNewChat();
+  const handleNewChatClickWrapper =
+    newChatContext?.onNewChatClick || handleNewChat;
+
+  useEffect(
+    function registerNewChatHandler() {
+      if (!newChatContext) return;
+      newChatContext.setPerformNewChat(handleNewChat);
+      return function cleanup() {
+        newChatContext.setPerformNewChat(undefined);
+      };
+    },
+    [newChatContext, handleNewChat],
+  );
+
+  if (!isLoggedIn) {
+    return (
+      <div className="flex h-full items-center justify-center">
+        <ChatLoader />
+      </div>
+    );
+  }
+
+  return (
+    <div
+      className="flex overflow-hidden bg-[#EFEFF0]"
+      style={{ height: `calc(100vh - ${NAVBAR_HEIGHT_PX}px)` }}
+    >
+      {!isMobile && (
+        <DesktopSidebar
+          sessions={sessions}
+          currentSessionId={currentSessionId}
+          isLoading={isLoading}
+          hasNextPage={hasNextPage}
+          isFetchingNextPage={isFetchingNextPage}
+          onSelectSession={handleSelectSession}
+          onFetchNextPage={fetchNextPage}
+          onNewChat={handleNewChatClickWrapper}
+          hasActiveSession={Boolean(hasActiveSession)}
+        />
+      )}
+
+      <div className="relative flex min-h-0 flex-1 flex-col">
+        {isMobile && <MobileHeader onOpenDrawer={handleOpenDrawer} />}
+        <div className="flex min-h-0 flex-1 flex-col">
+          {isReadyToShowContent ? children : <LoadingState />}
+        </div>
+      </div>
+
+      {isMobile && (
+        <MobileDrawer
+          isOpen={isDrawerOpen}
+          sessions={sessions}
+          currentSessionId={currentSessionId}
+          isLoading={isLoading}
+          hasNextPage={hasNextPage}
+          isFetchingNextPage={isFetchingNextPage}
+          onSelectSession={handleSelectSession}
+          onFetchNextPage={fetchNextPage}
+          onNewChat={handleNewChatClickWrapper}
+          onClose={handleCloseDrawer}
+          onOpenChange={handleDrawerOpenChange}
+          hasActiveSession={Boolean(hasActiveSession)}
+        />
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/DesktopSidebar/DesktopSidebar.tsx

@@ -0,0 +1,70 @@
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { scrollbarStyles } from "@/components/styles/scrollbars";
+import { cn } from "@/lib/utils";
+import { Plus } from "@phosphor-icons/react";
+import { SessionsList } from "../SessionsList/SessionsList";
+
+interface Props {
+  sessions: SessionSummaryResponse[];
+  currentSessionId: string | null;
+  isLoading: boolean;
+  hasNextPage: boolean;
+  isFetchingNextPage: boolean;
+  onSelectSession: (sessionId: string) => void;
+  onFetchNextPage: () => void;
+  onNewChat: () => void;
+  hasActiveSession: boolean;
+}
+
+export function DesktopSidebar({
+  sessions,
+  currentSessionId,
+  isLoading,
+  hasNextPage,
+  isFetchingNextPage,
+  onSelectSession,
+  onFetchNextPage,
+  onNewChat,
+  hasActiveSession,
+}: Props) {
+  return (
+    <aside className="flex h-full w-80 flex-col border-r border-zinc-100 bg-zinc-50">
+      <div className="shrink-0 px-6 py-4">
+        <Text variant="h3" size="body-medium">
+          Your chats
+        </Text>
+      </div>
+      <div
+        className={cn(
+          "flex min-h-0 flex-1 flex-col overflow-y-auto px-3 py-3",
+          scrollbarStyles,
+        )}
+      >
+        <SessionsList
+          sessions={sessions}
+          currentSessionId={currentSessionId}
+          isLoading={isLoading}
+          hasNextPage={hasNextPage}
+          isFetchingNextPage={isFetchingNextPage}
+          onSelectSession={onSelectSession}
+          onFetchNextPage={onFetchNextPage}
+        />
+      </div>
+      {hasActiveSession && (
+        <div className="shrink-0 bg-zinc-50 p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
+          <Button
+            variant="primary"
+            size="small"
+            onClick={onNewChat}
+            className="w-full"
+            leftIcon={<Plus width="1rem" height="1rem" />}
+          >
+            New Chat
+          </Button>
+        </div>
+      )}
+    </aside>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/LoadingState/LoadingState.tsx

@@ -0,0 +1,15 @@
+import { Text } from "@/components/atoms/Text/Text";
+import { ChatLoader } from "@/components/contextual/Chat/components/ChatLoader/ChatLoader";
+
+export function LoadingState() {
+  return (
+    <div className="flex flex-1 items-center justify-center">
+      <div className="flex flex-col items-center gap-4">
+        <ChatLoader />
+        <Text variant="body" className="text-zinc-500">
+          Loading your chats...
+        </Text>
+      </div>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/MobileDrawer/MobileDrawer.tsx

@@ -0,0 +1,91 @@
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { scrollbarStyles } from "@/components/styles/scrollbars";
+import { cn } from "@/lib/utils";
+import { PlusIcon, X } from "@phosphor-icons/react";
+import { Drawer } from "vaul";
+import { SessionsList } from "../SessionsList/SessionsList";
+
+interface Props {
+  isOpen: boolean;
+  sessions: SessionSummaryResponse[];
+  currentSessionId: string | null;
+  isLoading: boolean;
+  hasNextPage: boolean;
+  isFetchingNextPage: boolean;
+  onSelectSession: (sessionId: string) => void;
+  onFetchNextPage: () => void;
+  onNewChat: () => void;
+  onClose: () => void;
+  onOpenChange: (open: boolean) => void;
+  hasActiveSession: boolean;
+}
+
+export function MobileDrawer({
+  isOpen,
+  sessions,
+  currentSessionId,
+  isLoading,
+  hasNextPage,
+  isFetchingNextPage,
+  onSelectSession,
+  onFetchNextPage,
+  onNewChat,
+  onClose,
+  onOpenChange,
+  hasActiveSession,
+}: Props) {
+  return (
+    <Drawer.Root open={isOpen} onOpenChange={onOpenChange} direction="left">
+      <Drawer.Portal>
+        <Drawer.Overlay className="fixed inset-0 z-[60] bg-black/10 backdrop-blur-sm" />
+        <Drawer.Content className="fixed left-0 top-0 z-[70] flex h-full w-80 flex-col border-r border-zinc-200 bg-zinc-50">
+          <div className="shrink-0 border-b border-zinc-200 p-4">
+            <div className="flex items-center justify-between">
+              <Drawer.Title className="text-lg font-semibold text-zinc-800">
+                Your chats
+              </Drawer.Title>
+              <Button
+                variant="icon"
+                size="icon"
+                aria-label="Close sessions"
+                onClick={onClose}
+              >
+                <X width="1.25rem" height="1.25rem" />
+              </Button>
+            </div>
+          </div>
+          <div
+            className={cn(
+              "flex min-h-0 flex-1 flex-col overflow-y-auto px-3 py-3",
+              scrollbarStyles,
+            )}
+          >
+            <SessionsList
+              sessions={sessions}
+              currentSessionId={currentSessionId}
+              isLoading={isLoading}
+              hasNextPage={hasNextPage}
+              isFetchingNextPage={isFetchingNextPage}
+              onSelectSession={onSelectSession}
+              onFetchNextPage={onFetchNextPage}
+            />
+          </div>
+          {hasActiveSession && (
+            <div className="shrink-0 bg-white p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
+              <Button
+                variant="primary"
+                size="small"
+                onClick={onNewChat}
+                className="w-full"
+                leftIcon={<PlusIcon width="1rem" height="1rem" />}
+              >
+                New Chat
+              </Button>
+            </div>
+          )}
+        </Drawer.Content>
+      </Drawer.Portal>
+    </Drawer.Root>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/MobileDrawer/useMobileDrawer.ts

@@ -0,0 +1,24 @@
+import { useState } from "react";
+
+export function useMobileDrawer() {
+  const [isDrawerOpen, setIsDrawerOpen] = useState(false);
+
+  function handleOpenDrawer() {
+    setIsDrawerOpen(true);
+  }
+
+  function handleCloseDrawer() {
+    setIsDrawerOpen(false);
+  }
+
+  function handleDrawerOpenChange(open: boolean) {
+    setIsDrawerOpen(open);
+  }
+
+  return {
+    isDrawerOpen,
+    handleOpenDrawer,
+    handleCloseDrawer,
+    handleDrawerOpenChange,
+  };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/MobileHeader/MobileHeader.tsx

@@ -0,0 +1,22 @@
+import { Button } from "@/components/atoms/Button/Button";
+import { NAVBAR_HEIGHT_PX } from "@/lib/constants";
+import { ListIcon } from "@phosphor-icons/react";
+
+interface Props {
+  onOpenDrawer: () => void;
+}
+
+export function MobileHeader({ onOpenDrawer }: Props) {
+  return (
+    <Button
+      variant="icon"
+      size="icon"
+      aria-label="Open sessions"
+      onClick={onOpenDrawer}
+      className="fixed z-50 bg-white shadow-md"
+      style={{ left: "1rem", top: `${NAVBAR_HEIGHT_PX + 20}px` }}
+    >
+      <ListIcon width="1.25rem" height="1.25rem" />
+    </Button>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/SessionsList/SessionsList.tsx

@@ -0,0 +1,80 @@
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { Skeleton } from "@/components/__legacy__/ui/skeleton";
+import { Text } from "@/components/atoms/Text/Text";
+import { InfiniteList } from "@/components/molecules/InfiniteList/InfiniteList";
+import { cn } from "@/lib/utils";
+import { getSessionTitle } from "../../helpers";
+
+interface Props {
+  sessions: SessionSummaryResponse[];
+  currentSessionId: string | null;
+  isLoading: boolean;
+  hasNextPage: boolean;
+  isFetchingNextPage: boolean;
+  onSelectSession: (sessionId: string) => void;
+  onFetchNextPage: () => void;
+}
+
+export function SessionsList({
+  sessions,
+  currentSessionId,
+  isLoading,
+  hasNextPage,
+  isFetchingNextPage,
+  onSelectSession,
+  onFetchNextPage,
+}: Props) {
+  if (isLoading) {
+    return (
+      <div className="space-y-1">
+        {Array.from({ length: 5 }).map((_, i) => (
+          <div key={i} className="rounded-lg px-3 py-2.5">
+            <Skeleton className="h-5 w-full" />
+          </div>
+        ))}
+      </div>
+    );
+  }
+
+  if (sessions.length === 0) {
+    return (
+      <div className="flex h-full items-center justify-center">
+        <Text variant="body" className="text-zinc-500">
+          You don&apos;t have previous chats
+        </Text>
+      </div>
+    );
+  }
+
+  return (
+    <InfiniteList
+      items={sessions}
+      hasMore={hasNextPage}
+      isFetchingMore={isFetchingNextPage}
+      onEndReached={onFetchNextPage}
+      className="space-y-1"
+      renderItem={(session) => {
+        const isActive = session.id === currentSessionId;
+        return (
+          <button
+            onClick={() => onSelectSession(session.id)}
+            className={cn(
+              "w-full rounded-lg px-3 py-2.5 text-left transition-colors",
+              isActive ? "bg-zinc-100" : "hover:bg-zinc-50",
+            )}
+          >
+            <Text
+              variant="body"
+              className={cn(
+                "font-normal",
+                isActive ? "text-zinc-600" : "text-zinc-800",
+              )}
+            >
+              {getSessionTitle(session)}
+            </Text>
+          </button>
+        );
+      }}
+    />
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/SessionsList/useSessionsPagination.ts

@@ -0,0 +1,92 @@
+import { useGetV2ListSessions } from "@/app/api/__generated__/endpoints/chat/chat";
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { okData } from "@/app/api/helpers";
+import { useEffect, useMemo, useState } from "react";
+
+const PAGE_SIZE = 50;
+
+export interface UseSessionsPaginationArgs {
+  enabled: boolean;
+}
+
+export function useSessionsPagination({ enabled }: UseSessionsPaginationArgs) {
+  const [offset, setOffset] = useState(0);
+  const [accumulatedSessions, setAccumulatedSessions] = useState<
+    SessionSummaryResponse[]
+  >([]);
+  const [totalCount, setTotalCount] = useState<number | null>(null);
+
+  const { data, isLoading, isFetching, isError } = useGetV2ListSessions(
+    { limit: PAGE_SIZE, offset },
+    {
+      query: {
+        enabled: enabled && offset >= 0,
+      },
+    },
+  );
+
+  useEffect(() => {
+    const responseData = okData(data);
+    if (responseData) {
+      const newSessions = responseData.sessions;
+      const total = responseData.total;
+      setTotalCount(total);
+
+      if (offset === 0) {
+        setAccumulatedSessions(newSessions);
+      } else {
+        setAccumulatedSessions((prev) => [...prev, ...newSessions]);
+      }
+    } else if (!enabled) {
+      setAccumulatedSessions([]);
+      setTotalCount(null);
+    }
+  }, [data, offset, enabled]);
+
+  const hasNextPage = useMemo(() => {
+    if (totalCount === null) return false;
+    return accumulatedSessions.length < totalCount;
+  }, [accumulatedSessions.length, totalCount]);
+
+  const areAllSessionsLoaded = useMemo(() => {
+    if (totalCount === null) return false;
+    return (
+      accumulatedSessions.length >= totalCount && !isFetching && !isLoading
+    );
+  }, [accumulatedSessions.length, totalCount, isFetching, isLoading]);
+
+  useEffect(() => {
+    if (
+      hasNextPage &&
+      !isFetching &&
+      !isLoading &&
+      !isError &&
+      totalCount !== null
+    ) {
+      setOffset((prev) => prev + PAGE_SIZE);
+    }
+  }, [hasNextPage, isFetching, isLoading, isError, totalCount]);
+
+  function fetchNextPage() {
+    if (hasNextPage && !isFetching) {
+      setOffset((prev) => prev + PAGE_SIZE);
+    }
+  }
+
+  function reset() {
+    setOffset(0);
+    setAccumulatedSessions([]);
+    setTotalCount(null);
+  }
+
+  return {
+    sessions: accumulatedSessions,
+    isLoading,
+    isFetching,
+    hasNextPage,
+    areAllSessionsLoaded,
+    totalCount,
+    fetchNextPage,
+    reset,
+  };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/helpers.ts

@@ -0,0 +1,165 @@
+import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { format, formatDistanceToNow, isToday } from "date-fns";
+
+export function convertSessionDetailToSummary(
+  session: SessionDetailResponse,
+): SessionSummaryResponse {
+  return {
+    id: session.id,
+    created_at: session.created_at,
+    updated_at: session.updated_at,
+    title: undefined,
+  };
+}
+
+export function filterVisibleSessions(
+  sessions: SessionSummaryResponse[],
+): SessionSummaryResponse[] {
+  return sessions.filter(
+    (session) => session.updated_at !== session.created_at,
+  );
+}
+
+export function getSessionTitle(session: SessionSummaryResponse): string {
+  if (session.title) return session.title;
+  const isNewSession = session.updated_at === session.created_at;
+  if (isNewSession) {
+    const createdDate = new Date(session.created_at);
+    if (isToday(createdDate)) {
+      return "Today";
+    }
+    return format(createdDate, "MMM d, yyyy");
+  }
+  return "Untitled Chat";
+}
+
+export function getSessionUpdatedLabel(
+  session: SessionSummaryResponse,
+): string {
+  if (!session.updated_at) return "";
+  return formatDistanceToNow(new Date(session.updated_at), { addSuffix: true });
+}
+
+export function mergeCurrentSessionIntoList(
+  accumulatedSessions: SessionSummaryResponse[],
+  currentSessionId: string | null,
+  currentSessionData: SessionDetailResponse | null | undefined,
+): SessionSummaryResponse[] {
+  const filteredSessions: SessionSummaryResponse[] = [];
+
+  if (accumulatedSessions.length > 0) {
+    const visibleSessions = filterVisibleSessions(accumulatedSessions);
+
+    if (currentSessionId) {
+      const currentInAll = accumulatedSessions.find(
+        (s) => s.id === currentSessionId,
+      );
+      if (currentInAll) {
+        const isInVisible = visibleSessions.some(
+          (s) => s.id === currentSessionId,
+        );
+        if (!isInVisible) {
+          filteredSessions.push(currentInAll);
+        }
+      }
+    }
+
+    filteredSessions.push(...visibleSessions);
+  }
+
+  if (currentSessionId && currentSessionData) {
+    const isCurrentInList = filteredSessions.some(
+      (s) => s.id === currentSessionId,
+    );
+    if (!isCurrentInList) {
+      const summarySession = convertSessionDetailToSummary(currentSessionData);
+      filteredSessions.unshift(summarySession);
+    }
+  }
+
+  return filteredSessions;
+}
+
+export function getCurrentSessionId(
+  searchParams: URLSearchParams,
+): string | null {
+  return searchParams.get("sessionId");
+}
+
+export function shouldAutoSelectSession(
+  areAllSessionsLoaded: boolean,
+  hasAutoSelectedSession: boolean,
+  paramSessionId: string | null,
+  visibleSessions: SessionSummaryResponse[],
+  accumulatedSessions: SessionSummaryResponse[],
+  isLoading: boolean,
+  totalCount: number | null,
+): {
+  shouldSelect: boolean;
+  sessionIdToSelect: string | null;
+  shouldCreate: boolean;
+} {
+  if (!areAllSessionsLoaded || hasAutoSelectedSession) {
+    return {
+      shouldSelect: false,
+      sessionIdToSelect: null,
+      shouldCreate: false,
+    };
+  }
+
+  if (paramSessionId) {
+    return {
+      shouldSelect: false,
+      sessionIdToSelect: null,
+      shouldCreate: false,
+    };
+  }
+
+  if (visibleSessions.length > 0) {
+    return {
+      shouldSelect: true,
+      sessionIdToSelect: visibleSessions[0].id,
+      shouldCreate: false,
+    };
+  }
+
+  if (accumulatedSessions.length === 0 && !isLoading && totalCount === 0) {
+    return { shouldSelect: false, sessionIdToSelect: null, shouldCreate: true };
+  }
+
+  if (totalCount === 0) {
+    return {
+      shouldSelect: false,
+      sessionIdToSelect: null,
+      shouldCreate: false,
+    };
+  }
+
+  return { shouldSelect: false, sessionIdToSelect: null, shouldCreate: false };
+}
+
+export function checkReadyToShowContent(
+  areAllSessionsLoaded: boolean,
+  paramSessionId: string | null,
+  accumulatedSessions: SessionSummaryResponse[],
+  isCurrentSessionLoading: boolean,
+  currentSessionData: SessionDetailResponse | null | undefined,
+  hasAutoSelectedSession: boolean,
+): boolean {
+  if (!areAllSessionsLoaded) return false;
+
+  if (paramSessionId) {
+    const sessionFound = accumulatedSessions.some(
+      (s) => s.id === paramSessionId,
+    );
+    return (
+      sessionFound ||
+      (!isCurrentSessionLoading &&
+        currentSessionData !== undefined &&
+        currentSessionData !== null)
+    );
+  }
+
+  return hasAutoSelectedSession;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/useCopilotShell.ts

@@ -0,0 +1,172 @@
+"use client";
+
+import {
+  getGetV2ListSessionsQueryKey,
+  useGetV2GetSession,
+} from "@/app/api/__generated__/endpoints/chat/chat";
+import { okData } from "@/app/api/helpers";
+import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
+import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
+import { useQueryClient } from "@tanstack/react-query";
+import { usePathname, useRouter, useSearchParams } from "next/navigation";
+import { useEffect, useRef, useState } from "react";
+import { useMobileDrawer } from "./components/MobileDrawer/useMobileDrawer";
+import { useSessionsPagination } from "./components/SessionsList/useSessionsPagination";
+import {
+  checkReadyToShowContent,
+  filterVisibleSessions,
+  getCurrentSessionId,
+  mergeCurrentSessionIntoList,
+} from "./helpers";
+
+export function useCopilotShell() {
+  const router = useRouter();
+  const pathname = usePathname();
+  const searchParams = useSearchParams();
+  const queryClient = useQueryClient();
+  const breakpoint = useBreakpoint();
+  const { isLoggedIn } = useSupabase();
+  const isMobile =
+    breakpoint === "base" || breakpoint === "sm" || breakpoint === "md";
+
+  const isOnHomepage = pathname === "/copilot";
+  const paramSessionId = searchParams.get("sessionId");
+
+  const {
+    isDrawerOpen,
+    handleOpenDrawer,
+    handleCloseDrawer,
+    handleDrawerOpenChange,
+  } = useMobileDrawer();
+
+  const paginationEnabled = !isMobile || isDrawerOpen || !!paramSessionId;
+
+  const {
+    sessions: accumulatedSessions,
+    isLoading: isSessionsLoading,
+    isFetching: isSessionsFetching,
+    hasNextPage,
+    areAllSessionsLoaded,
+    fetchNextPage,
+    reset: resetPagination,
+  } = useSessionsPagination({
+    enabled: paginationEnabled,
+  });
+
+  const currentSessionId = getCurrentSessionId(searchParams);
+
+  const { data: currentSessionData, isLoading: isCurrentSessionLoading } =
+    useGetV2GetSession(currentSessionId || "", {
+      query: {
+        enabled: !!currentSessionId,
+        select: okData,
+      },
+    });
+
+  const [hasAutoSelectedSession, setHasAutoSelectedSession] = useState(false);
+  const hasAutoSelectedRef = useRef(false);
+
+  // Mark as auto-selected when sessionId is in URL
+  useEffect(() => {
+    if (paramSessionId && !hasAutoSelectedRef.current) {
+      hasAutoSelectedRef.current = true;
+      setHasAutoSelectedSession(true);
+    }
+  }, [paramSessionId]);
+
+  // On homepage without sessionId, mark as ready immediately
+  useEffect(() => {
+    if (isOnHomepage && !paramSessionId && !hasAutoSelectedRef.current) {
+      hasAutoSelectedRef.current = true;
+      setHasAutoSelectedSession(true);
+    }
+  }, [isOnHomepage, paramSessionId]);
+
+  // Invalidate sessions list when navigating to homepage (to show newly created sessions)
+  useEffect(() => {
+    if (isOnHomepage && !paramSessionId) {
+      queryClient.invalidateQueries({
+        queryKey: getGetV2ListSessionsQueryKey(),
+      });
+    }
+  }, [isOnHomepage, paramSessionId, queryClient]);
+
+  // Reset pagination when query becomes disabled
+  const prevPaginationEnabledRef = useRef(paginationEnabled);
+  useEffect(() => {
+    if (prevPaginationEnabledRef.current && !paginationEnabled) {
+      resetPagination();
+      resetAutoSelect();
+    }
+    prevPaginationEnabledRef.current = paginationEnabled;
+  }, [paginationEnabled, resetPagination]);
+
+  const sessions = mergeCurrentSessionIntoList(
+    accumulatedSessions,
+    currentSessionId,
+    currentSessionData,
+  );
+
+  const visibleSessions = filterVisibleSessions(sessions);
+
+  const sidebarSelectedSessionId =
+    isOnHomepage && !paramSessionId ? null : currentSessionId;
+
+  const isReadyToShowContent = isOnHomepage
+    ? true
+    : checkReadyToShowContent(
+        areAllSessionsLoaded,
+        paramSessionId,
+        accumulatedSessions,
+        isCurrentSessionLoading,
+        currentSessionData,
+        hasAutoSelectedSession,
+      );
+
+  function handleSelectSession(sessionId: string) {
+    // Navigate using replaceState to avoid full page reload
+    window.history.replaceState(null, "", `/copilot?sessionId=${sessionId}`);
+    // Force a re-render by updating the URL through router
+    router.replace(`/copilot?sessionId=${sessionId}`);
+    if (isMobile) handleCloseDrawer();
+  }
+
+  function handleNewChat() {
+    resetAutoSelect();
+    resetPagination();
+    // Invalidate and refetch sessions list to ensure newly created sessions appear
+    queryClient.invalidateQueries({
+      queryKey: getGetV2ListSessionsQueryKey(),
+    });
+    window.history.replaceState(null, "", "/copilot");
+    router.replace("/copilot");
+    if (isMobile) handleCloseDrawer();
+  }
+
+  function resetAutoSelect() {
+    hasAutoSelectedRef.current = false;
+    setHasAutoSelectedSession(false);
+  }
+
+  const isLoading = isSessionsLoading && accumulatedSessions.length === 0;
+
+  return {
+    isMobile,
+    isDrawerOpen,
+    isLoggedIn,
+    hasActiveSession:
+      Boolean(currentSessionId) && (!isOnHomepage || Boolean(paramSessionId)),
+    isLoading,
+    sessions: visibleSessions,
+    currentSessionId: sidebarSelectedSessionId,
+    handleSelectSession,
+    handleOpenDrawer,
+    handleCloseDrawer,
+    handleDrawerOpenChange,
+    handleNewChat,
+    hasNextPage,
+    isFetchingNextPage: isSessionsFetching,
+    fetchNextPage,
+    isReadyToShowContent,
+  };
+}

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

@@ -0,0 +1,56 @@
+import type { User } from "@supabase/supabase-js";
+
+export type PageState =
+  | { type: "welcome" }
+  | { type: "newChat" }
+  | { type: "creating"; prompt: string }
+  | { type: "chat"; sessionId: string; initialPrompt?: string };
+
+export function getInitialPromptFromState(
+  pageState: PageState,
+  storedInitialPrompt: string | undefined,
+) {
+  if (storedInitialPrompt) return storedInitialPrompt;
+  if (pageState.type === "creating") return pageState.prompt;
+  if (pageState.type === "chat") return pageState.initialPrompt;
+}
+
+export function shouldResetToWelcome(pageState: PageState) {
+  return (
+    pageState.type !== "newChat" &&
+    pageState.type !== "creating" &&
+    pageState.type !== "welcome"
+  );
+}
+
+export function getGreetingName(user?: User | null): string {
+  if (!user) return "there";
+  const metadata = user.user_metadata as Record<string, unknown> | undefined;
+  const fullName = metadata?.full_name;
+  const name = metadata?.name;
+  if (typeof fullName === "string" && fullName.trim()) {
+    return fullName.split(" ")[0];
+  }
+  if (typeof name === "string" && name.trim()) {
+    return name.split(" ")[0];
+  }
+  if (user.email) {
+    return user.email.split("@")[0];
+  }
+  return "there";
+}
+
+export function buildCopilotChatUrl(prompt: string): string {
+  const trimmed = prompt.trim();
+  if (!trimmed) return "/copilot/chat";
+  const encoded = encodeURIComponent(trimmed);
+  return `/copilot/chat?prompt=${encoded}`;
+}
+
+export function getQuickActions(): string[] {
+  return [
+    "Show me what I can automate",
+    "Design a custom workflow",
+    "Help me with content creation",
+  ];
+}

autogpt_platform/frontend/src/app/(platform)/copilot/layout.tsx

@@ -0,0 +1,11 @@
+import type { ReactNode } from "react";
+import { NewChatProvider } from "./NewChatContext";
+import { CopilotShell } from "./components/CopilotShell/CopilotShell";
+
+export default function CopilotLayout({ children }: { children: ReactNode }) {
+  return (
+    <NewChatProvider>
+      <CopilotShell>{children}</CopilotShell>
+    </NewChatProvider>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/page.tsx

@@ -0,0 +1,169 @@
+"use client";
+
+import { Skeleton } from "@/components/__legacy__/ui/skeleton";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { Chat } from "@/components/contextual/Chat/Chat";
+import { ChatInput } from "@/components/contextual/Chat/components/ChatInput/ChatInput";
+import { ChatLoader } from "@/components/contextual/Chat/components/ChatLoader/ChatLoader";
+import { Dialog } from "@/components/molecules/Dialog/Dialog";
+import { useCopilotPage } from "./useCopilotPage";
+
+export default function CopilotPage() {
+  const { state, handlers } = useCopilotPage();
+  const {
+    greetingName,
+    quickActions,
+    isLoading,
+    pageState,
+    isNewChatModalOpen,
+    isReady,
+  } = state;
+  const {
+    handleQuickAction,
+    startChatWithPrompt,
+    handleSessionNotFound,
+    handleStreamingChange,
+    handleCancelNewChat,
+    proceedWithNewChat,
+    handleNewChatModalOpen,
+  } = handlers;
+
+  if (!isReady) {
+    return null;
+  }
+
+  // Show Chat when we have an active session
+  if (pageState.type === "chat") {
+    return (
+      <div className="flex h-full flex-col">
+        <Chat
+          key={pageState.sessionId ?? "welcome"}
+          className="flex-1"
+          urlSessionId={pageState.sessionId}
+          initialPrompt={pageState.initialPrompt}
+          onSessionNotFound={handleSessionNotFound}
+          onStreamingChange={handleStreamingChange}
+        />
+        <Dialog
+          title="Interrupt current chat?"
+          styling={{ maxWidth: 300, width: "100%" }}
+          controlled={{
+            isOpen: isNewChatModalOpen,
+            set: handleNewChatModalOpen,
+          }}
+          onClose={handleCancelNewChat}
+        >
+          <Dialog.Content>
+            <div className="flex flex-col gap-4">
+              <Text variant="body">
+                The current chat response will be interrupted. Are you sure you
+                want to start a new chat?
+              </Text>
+              <Dialog.Footer>
+                <Button
+                  type="button"
+                  variant="outline"
+                  onClick={handleCancelNewChat}
+                >
+                  Cancel
+                </Button>
+                <Button
+                  type="button"
+                  variant="primary"
+                  onClick={proceedWithNewChat}
+                >
+                  Start new chat
+                </Button>
+              </Dialog.Footer>
+            </div>
+          </Dialog.Content>
+        </Dialog>
+      </div>
+    );
+  }
+
+  if (pageState.type === "newChat") {
+    return (
+      <div className="flex h-full flex-1 flex-col items-center justify-center bg-[#f8f8f9]">
+        <div className="flex flex-col items-center gap-4">
+          <ChatLoader />
+          <Text variant="body" className="text-zinc-500">
+            Loading your chats...
+          </Text>
+        </div>
+      </div>
+    );
+  }
+
+  // Show loading state while creating session and sending first message
+  if (pageState.type === "creating") {
+    return (
+      <div className="flex h-full flex-1 flex-col items-center justify-center bg-[#f8f8f9]">
+        <div className="flex flex-col items-center gap-4">
+          <ChatLoader />
+          <Text variant="body" className="text-zinc-500">
+            Loading your chats...
+          </Text>
+        </div>
+      </div>
+    );
+  }
+
+  // Show Welcome screen
+  return (
+    <div className="flex h-full flex-1 items-center justify-center overflow-y-auto bg-[#f8f8f9] px-6 py-10">
+      <div className="w-full text-center">
+        {isLoading ? (
+          <div className="mx-auto max-w-2xl">
+            <Skeleton className="mx-auto mb-3 h-8 w-64" />
+            <Skeleton className="mx-auto mb-8 h-6 w-80" />
+            <div className="mb-8">
+              <Skeleton className="mx-auto h-14 w-full rounded-lg" />
+            </div>
+            <div className="flex flex-wrap items-center justify-center gap-3">
+              {Array.from({ length: 4 }).map((_, i) => (
+                <Skeleton key={i} className="h-9 w-48 rounded-md" />
+              ))}
+            </div>
+          </div>
+        ) : (
+          <>
+            <div className="mx-auto max-w-2xl">
+              <Text
+                variant="h3"
+                className="mb-3 !text-[1.375rem] text-zinc-700"
+              >
+                Hey, <span className="text-violet-600">{greetingName}</span>
+              </Text>
+              <Text variant="h3" className="mb-8 !font-normal">
+                What do you want to automate?
+              </Text>
+
+              <div className="mb-6">
+                <ChatInput
+                  onSend={startChatWithPrompt}
+                  placeholder='You can search or just ask - e.g. "create a blog post outline"'
+                />
+              </div>
+            </div>
+            <div className="flex flex-nowrap items-center justify-center gap-3 overflow-x-auto [-ms-overflow-style:none] [scrollbar-width:none] [&::-webkit-scrollbar]:hidden">
+              {quickActions.map((action) => (
+                <Button
+                  key={action}
+                  type="button"
+                  variant="outline"
+                  size="small"
+                  onClick={() => handleQuickAction(action)}
+                  className="h-auto shrink-0 border-zinc-600 !px-4 !py-2 text-[1rem] text-zinc-600"
+                >
+                  {action}
+                </Button>
+              ))}
+            </div>
+          </>
+        )}
+      </div>
+    </div>
+  );
+}

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

@@ -0,0 +1,266 @@
+import { postV2CreateSession } from "@/app/api/__generated__/endpoints/chat/chat";
+import { useToast } from "@/components/molecules/Toast/use-toast";
+import { getHomepageRoute } from "@/lib/constants";
+import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
+import {
+  Flag,
+  type FlagValues,
+  useGetFlag,
+} from "@/services/feature-flags/use-get-flag";
+import * as Sentry from "@sentry/nextjs";
+import { useFlags } from "launchdarkly-react-client-sdk";
+import { useRouter } from "next/navigation";
+import { useEffect, useReducer } from "react";
+import { useNewChat } from "./NewChatContext";
+import { getGreetingName, getQuickActions, type PageState } from "./helpers";
+import { useCopilotURLState } from "./useCopilotURLState";
+
+type CopilotState = {
+  pageState: PageState;
+  isStreaming: boolean;
+  isNewChatModalOpen: boolean;
+  initialPrompts: Record<string, string>;
+  previousSessionId: string | null;
+};
+
+type CopilotAction =
+  | { type: "setPageState"; pageState: PageState }
+  | { type: "setStreaming"; isStreaming: boolean }
+  | { type: "setNewChatModalOpen"; isOpen: boolean }
+  | { type: "setInitialPrompt"; sessionId: string; prompt: string }
+  | { type: "setPreviousSessionId"; sessionId: string | null };
+
+function isSamePageState(next: PageState, current: PageState) {
+  if (next.type !== current.type) return false;
+  if (next.type === "creating" && current.type === "creating") {
+    return next.prompt === current.prompt;
+  }
+  if (next.type === "chat" && current.type === "chat") {
+    return (
+      next.sessionId === current.sessionId &&
+      next.initialPrompt === current.initialPrompt
+    );
+  }
+  return true;
+}
+
+function copilotReducer(
+  state: CopilotState,
+  action: CopilotAction,
+): CopilotState {
+  if (action.type === "setPageState") {
+    if (isSamePageState(action.pageState, state.pageState)) return state;
+    return { ...state, pageState: action.pageState };
+  }
+  if (action.type === "setStreaming") {
+    if (action.isStreaming === state.isStreaming) return state;
+    return { ...state, isStreaming: action.isStreaming };
+  }
+  if (action.type === "setNewChatModalOpen") {
+    if (action.isOpen === state.isNewChatModalOpen) return state;
+    return { ...state, isNewChatModalOpen: action.isOpen };
+  }
+  if (action.type === "setInitialPrompt") {
+    if (state.initialPrompts[action.sessionId] === action.prompt) return state;
+    return {
+      ...state,
+      initialPrompts: {
+        ...state.initialPrompts,
+        [action.sessionId]: action.prompt,
+      },
+    };
+  }
+  if (action.type === "setPreviousSessionId") {
+    if (state.previousSessionId === action.sessionId) return state;
+    return { ...state, previousSessionId: action.sessionId };
+  }
+  return state;
+}
+
+export function useCopilotPage() {
+  const router = useRouter();
+  const { user, isLoggedIn, isUserLoading } = useSupabase();
+  const { toast } = useToast();
+
+  const isChatEnabled = useGetFlag(Flag.CHAT);
+  const flags = useFlags<FlagValues>();
+  const homepageRoute = getHomepageRoute(isChatEnabled);
+  const envEnabled = process.env.NEXT_PUBLIC_LAUNCHDARKLY_ENABLED === "true";
+  const clientId = process.env.NEXT_PUBLIC_LAUNCHDARKLY_CLIENT_ID;
+  const isLaunchDarklyConfigured = envEnabled && Boolean(clientId);
+  const isFlagReady =
+    !isLaunchDarklyConfigured || flags[Flag.CHAT] !== undefined;
+
+  const [state, dispatch] = useReducer(copilotReducer, {
+    pageState: { type: "welcome" },
+    isStreaming: false,
+    isNewChatModalOpen: false,
+    initialPrompts: {},
+    previousSessionId: null,
+  });
+
+  const newChatContext = useNewChat();
+  const greetingName = getGreetingName(user);
+  const quickActions = getQuickActions();
+
+  function setPageState(pageState: PageState) {
+    dispatch({ type: "setPageState", pageState });
+  }
+
+  function setInitialPrompt(sessionId: string, prompt: string) {
+    dispatch({ type: "setInitialPrompt", sessionId, prompt });
+  }
+
+  function setPreviousSessionId(sessionId: string | null) {
+    dispatch({ type: "setPreviousSessionId", sessionId });
+  }
+
+  const { setUrlSessionId } = useCopilotURLState({
+    pageState: state.pageState,
+    initialPrompts: state.initialPrompts,
+    previousSessionId: state.previousSessionId,
+    setPageState,
+    setInitialPrompt,
+    setPreviousSessionId,
+  });
+
+  useEffect(
+    function registerNewChatHandler() {
+      if (!newChatContext) return;
+      newChatContext.setOnNewChatClick(handleNewChatClick);
+      return function cleanup() {
+        newChatContext.setOnNewChatClick(undefined);
+      };
+    },
+    [newChatContext, handleNewChatClick],
+  );
+
+  useEffect(
+    function transitionNewChatToWelcome() {
+      if (state.pageState.type === "newChat") {
+        function setWelcomeState() {
+          dispatch({ type: "setPageState", pageState: { type: "welcome" } });
+        }
+
+        const timer = setTimeout(setWelcomeState, 300);
+
+        return function cleanup() {
+          clearTimeout(timer);
+        };
+      }
+    },
+    [state.pageState.type],
+  );
+
+  useEffect(
+    function ensureAccess() {
+      if (!isFlagReady) return;
+      if (isChatEnabled === false) {
+        router.replace(homepageRoute);
+      }
+    },
+    [homepageRoute, isChatEnabled, isFlagReady, router],
+  );
+
+  async function startChatWithPrompt(prompt: string) {
+    if (!prompt?.trim()) return;
+    if (state.pageState.type === "creating") return;
+
+    const trimmedPrompt = prompt.trim();
+    dispatch({
+      type: "setPageState",
+      pageState: { type: "creating", prompt: trimmedPrompt },
+    });
+
+    try {
+      const sessionResponse = await postV2CreateSession({
+        body: JSON.stringify({}),
+      });
+
+      if (sessionResponse.status !== 200 || !sessionResponse.data?.id) {
+        throw new Error("Failed to create session");
+      }
+
+      const sessionId = sessionResponse.data.id;
+
+      dispatch({
+        type: "setInitialPrompt",
+        sessionId,
+        prompt: trimmedPrompt,
+      });
+
+      await setUrlSessionId(sessionId, { shallow: false });
+      dispatch({
+        type: "setPageState",
+        pageState: { type: "chat", sessionId, initialPrompt: trimmedPrompt },
+      });
+    } catch (error) {
+      console.error("[CopilotPage] Failed to start chat:", error);
+      toast({ title: "Failed to start chat", variant: "destructive" });
+      Sentry.captureException(error);
+      dispatch({ type: "setPageState", pageState: { type: "welcome" } });
+    }
+  }
+
+  function handleQuickAction(action: string) {
+    startChatWithPrompt(action);
+  }
+
+  function handleSessionNotFound() {
+    router.replace("/copilot");
+  }
+
+  function handleStreamingChange(isStreamingValue: boolean) {
+    dispatch({ type: "setStreaming", isStreaming: isStreamingValue });
+  }
+
+  async function proceedWithNewChat() {
+    dispatch({ type: "setNewChatModalOpen", isOpen: false });
+    if (newChatContext?.performNewChat) {
+      newChatContext.performNewChat();
+      return;
+    }
+    try {
+      await setUrlSessionId(null, { shallow: false });
+    } catch (error) {
+      console.error("[CopilotPage] Failed to clear session:", error);
+    }
+    router.replace("/copilot");
+  }
+
+  function handleCancelNewChat() {
+    dispatch({ type: "setNewChatModalOpen", isOpen: false });
+  }
+
+  function handleNewChatModalOpen(isOpen: boolean) {
+    dispatch({ type: "setNewChatModalOpen", isOpen });
+  }
+
+  function handleNewChatClick() {
+    if (state.isStreaming) {
+      dispatch({ type: "setNewChatModalOpen", isOpen: true });
+    } else {
+      proceedWithNewChat();
+    }
+  }
+
+  return {
+    state: {
+      greetingName,
+      quickActions,
+      isLoading: isUserLoading,
+      pageState: state.pageState,
+      isNewChatModalOpen: state.isNewChatModalOpen,
+      isReady: isFlagReady && isChatEnabled !== false && isLoggedIn,
+    },
+    handlers: {
+      handleQuickAction,
+      startChatWithPrompt,
+      handleSessionNotFound,
+      handleStreamingChange,
+      handleCancelNewChat,
+      proceedWithNewChat,
+      handleNewChatModalOpen,
+    },
+  };
+}

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

@@ -0,0 +1,80 @@
+import { parseAsString, useQueryState } from "nuqs";
+import { useLayoutEffect } from "react";
+import {
+  getInitialPromptFromState,
+  type PageState,
+  shouldResetToWelcome,
+} from "./helpers";
+
+interface UseCopilotUrlStateArgs {
+  pageState: PageState;
+  initialPrompts: Record<string, string>;
+  previousSessionId: string | null;
+  setPageState: (pageState: PageState) => void;
+  setInitialPrompt: (sessionId: string, prompt: string) => void;
+  setPreviousSessionId: (sessionId: string | null) => void;
+}
+
+export function useCopilotURLState({
+  pageState,
+  initialPrompts,
+  previousSessionId,
+  setPageState,
+  setInitialPrompt,
+  setPreviousSessionId,
+}: UseCopilotUrlStateArgs) {
+  const [urlSessionId, setUrlSessionId] = useQueryState(
+    "sessionId",
+    parseAsString,
+  );
+
+  function syncSessionFromUrl() {
+    if (urlSessionId) {
+      if (pageState.type === "chat" && pageState.sessionId === urlSessionId) {
+        setPreviousSessionId(urlSessionId);
+        return;
+      }
+
+      const storedInitialPrompt = initialPrompts[urlSessionId];
+      const currentInitialPrompt = getInitialPromptFromState(
+        pageState,
+        storedInitialPrompt,
+      );
+
+      if (currentInitialPrompt) {
+        setInitialPrompt(urlSessionId, currentInitialPrompt);
+      }
+
+      setPageState({
+        type: "chat",
+        sessionId: urlSessionId,
+        initialPrompt: currentInitialPrompt,
+      });
+      setPreviousSessionId(urlSessionId);
+      return;
+    }
+
+    const wasInChat = previousSessionId !== null && pageState.type === "chat";
+    setPreviousSessionId(null);
+    if (wasInChat) {
+      setPageState({ type: "newChat" });
+      return;
+    }
+
+    if (shouldResetToWelcome(pageState)) {
+      setPageState({ type: "welcome" });
+    }
+  }
+
+  useLayoutEffect(syncSessionFromUrl, [
+    urlSessionId,
+    pageState.type,
+    previousSessionId,
+    initialPrompts,
+  ]);
+
+  return {
+    urlSessionId,
+    setUrlSessionId,
+  };
+}

autogpt_platform/frontend/src/app/(platform)/error/page.tsx

@@ -1,6 +1,8 @@
 "use client";
 
 import { ErrorCard } from "@/components/molecules/ErrorCard/ErrorCard";
+import { getHomepageRoute } from "@/lib/constants";
+import { Flag, useGetFlag } from "@/services/feature-flags/use-get-flag";
 import { useSearchParams } from "next/navigation";
 import { Suspense } from "react";
 import { getErrorDetails } from "./helpers";
@@ -9,6 +11,8 @@ function ErrorPageContent() {
   const searchParams = useSearchParams();
   const errorMessage = searchParams.get("message");
   const errorDetails = getErrorDetails(errorMessage);
+  const isChatEnabled = useGetFlag(Flag.CHAT);
+  const homepageRoute = getHomepageRoute(isChatEnabled);
 
   function handleRetry() {
     // Auth-related errors should redirect to login
@@ -25,8 +29,8 @@ function ErrorPageContent() {
         window.location.reload();
       }, 2000);
     } else {
-      // For server/network errors, go to marketplace
-      window.location.href = "/marketplace";
+      // For server/network errors, go to home
+      window.location.href = homepageRoute;
     }
   }
 

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/AgentSettingsModal/AgentSettingsModal.tsx

@@ -31,10 +31,18 @@ export function AgentSettingsModal({
     }
   }
 
-  const { currentSafeMode, isPending, hasHITLBlocks, handleToggle } =
-    useAgentSafeMode(agent);
+  const {
+    currentHITLSafeMode,
+    showHITLToggle,
+    handleHITLToggle,
+    currentSensitiveActionSafeMode,
+    showSensitiveActionToggle,
+    handleSensitiveActionToggle,
+    isPending,
+    shouldShowToggle,
+  } = useAgentSafeMode(agent);
 
-  if (!hasHITLBlocks) return null;
+  if (!shouldShowToggle) return null;
 
   return (
     <Dialog
@@ -57,23 +65,48 @@ export function AgentSettingsModal({
       )}
       <Dialog.Content>
         <div className="space-y-6">
-          <div className="flex w-full flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
-            <div className="flex w-full items-start justify-between gap-4">
-              <div className="flex-1">
-                <Text variant="large-semibold">Require human approval</Text>
-                <Text variant="large" className="mt-1 text-zinc-900">
-                  The agent will pause and wait for your review before
-                  continuing
-                </Text>
+          {showHITLToggle && (
+            <div className="flex w-full flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
+              <div className="flex w-full items-start justify-between gap-4">
+                <div className="flex-1">
+                  <Text variant="large-semibold">
+                    Human-in-the-loop approval
+                  </Text>
+                  <Text variant="large" className="mt-1 text-zinc-900">
+                    The agent will pause at human-in-the-loop blocks and wait
+                    for your review before continuing
+                  </Text>
+                </div>
+                <Switch
+                  checked={currentHITLSafeMode || false}
+                  onCheckedChange={handleHITLToggle}
+                  disabled={isPending}
+                  className="mt-1"
+                />
               </div>
-              <Switch
-                checked={currentSafeMode || false}
-                onCheckedChange={handleToggle}
-                disabled={isPending}
-                className="mt-1"
-              />
             </div>
-          </div>
+          )}
+          {showSensitiveActionToggle && (
+            <div className="flex w-full flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
+              <div className="flex w-full items-start justify-between gap-4">
+                <div className="flex-1">
+                  <Text variant="large-semibold">
+                    Sensitive action approval
+                  </Text>
+                  <Text variant="large" className="mt-1 text-zinc-900">
+                    The agent will pause at sensitive action blocks and wait for
+                    your review before continuing
+                  </Text>
+                </div>
+                <Switch
+                  checked={currentSensitiveActionSafeMode}
+                  onCheckedChange={handleSensitiveActionToggle}
+                  disabled={isPending}
+                  className="mt-1"
+                />
+              </div>
+            </div>
+          )}
         </div>
       </Dialog.Content>
     </Dialog>

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/RunAgentModal.tsx

@@ -180,7 +180,7 @@ export function RunAgentModal({
 
               {/* Content */}
               {hasAnySetupFields ? (
-                <div className="mt-10 pb-32">
+                <div className="mt-4 pb-10">
                   <RunAgentModalContextProvider
                     value={{
                       agent,

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/components/ModalHeader/ModalHeader.tsx

@@ -29,7 +29,7 @@ export function ModalHeader({ agent }: ModalHeaderProps) {
           <ShowMoreText
             previewLimit={400}
             variant="small"
-            className="mt-4 !text-zinc-700"
+            className="mb-2 mt-4 !text-zinc-700"
           >
             {agent.description}
           </ShowMoreText>
@@ -40,6 +40,8 @@ export function ModalHeader({ agent }: ModalHeaderProps) {
             <Text variant="lead-semibold" className="text-blue-600">
               Tip
             </Text>
+            <div className="h-px w-full bg-blue-100" />
+
             <Text variant="body">
               For best results, run this agent{" "}
               {humanizeCronExpression(
@@ -50,7 +52,7 @@ export function ModalHeader({ agent }: ModalHeaderProps) {
         ) : null}
 
         {agent.instructions ? (
-          <div className="flex flex-col gap-4 rounded-medium border border-purple-100 bg-[#F1EBFE/5] p-4">
+          <div className="mt-4 flex flex-col gap-4 rounded-medium border border-purple-100 bg-[#f1ebfe80] p-4">
             <Text variant="lead-semibold" className="text-purple-600">
               Instructions
             </Text>

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/selected-views/SelectedRunView/components/SafeModeToggle.tsx

@@ -5,48 +5,112 @@ import { Graph } from "@/lib/autogpt-server-api/types";
 import { cn } from "@/lib/utils";
 import { ShieldCheckIcon, ShieldIcon } from "@phosphor-icons/react";
 import { useAgentSafeMode } from "@/hooks/useAgentSafeMode";
+import {
+  Tooltip,
+  TooltipContent,
+  TooltipTrigger,
+} from "@/components/atoms/Tooltip/BaseTooltip";
 
 interface Props {
   graph: GraphModel | LibraryAgent | Graph;
   className?: string;
-  fullWidth?: boolean;
 }
 
-export function SafeModeToggle({ graph }: Props) {
+interface SafeModeIconButtonProps {
+  isEnabled: boolean;
+  label: string;
+  tooltipEnabled: string;
+  tooltipDisabled: string;
+  onToggle: () => void;
+  isPending: boolean;
+}
+
+function SafeModeIconButton({
+  isEnabled,
+  label,
+  tooltipEnabled,
+  tooltipDisabled,
+  onToggle,
+  isPending,
+}: SafeModeIconButtonProps) {
+  return (
+    <Tooltip delayDuration={100}>
+      <TooltipTrigger asChild>
+        <Button
+          variant="icon"
+          size="icon"
+          aria-label={`${label}: ${isEnabled ? "ON" : "OFF"}. ${isEnabled ? tooltipEnabled : tooltipDisabled}`}
+          onClick={onToggle}
+          disabled={isPending}
+          className={cn(isPending ? "opacity-0" : "opacity-100")}
+        >
+          {isEnabled ? (
+            <ShieldCheckIcon weight="bold" size={16} />
+          ) : (
+            <ShieldIcon weight="bold" size={16} />
+          )}
+        </Button>
+      </TooltipTrigger>
+      <TooltipContent>
+        <div className="text-center">
+          <div className="font-medium">
+            {label}: {isEnabled ? "ON" : "OFF"}
+          </div>
+          <div className="mt-1 text-xs text-muted-foreground">
+            {isEnabled ? tooltipEnabled : tooltipDisabled}
+          </div>
+        </div>
+      </TooltipContent>
+    </Tooltip>
+  );
+}
+
+export function SafeModeToggle({ graph, className }: Props) {
   const {
-    currentSafeMode,
+    currentHITLSafeMode,
+    showHITLToggle,
+    isHITLStateUndetermined,
+    handleHITLToggle,
+    currentSensitiveActionSafeMode,
+    showSensitiveActionToggle,
+    handleSensitiveActionToggle,
     isPending,
     shouldShowToggle,
-    isStateUndetermined,
-    handleToggle,
   } = useAgentSafeMode(graph);
 
-  if (!shouldShowToggle || isStateUndetermined) {
+  if (!shouldShowToggle || isHITLStateUndetermined) {
+    return null;
+  }
+
+  const showHITL = showHITLToggle && !isHITLStateUndetermined;
+  const showSensitive = showSensitiveActionToggle;
+
+  if (!showHITL && !showSensitive) {
     return null;
   }
 
   return (
-    <Button
-      variant="icon"
-      key={graph.id}
-      size="icon"
-      aria-label={
-        currentSafeMode!
-          ? "Safe Mode: ON. Human in the loop blocks require manual review"
-          : "Safe Mode: OFF. Human in the loop blocks proceed automatically"
-      }
-      onClick={handleToggle}
-      className={cn(isPending ? "opacity-0" : "opacity-100")}
-    >
-      {currentSafeMode! ? (
-        <>
-          <ShieldCheckIcon weight="bold" size={16} />
-        </>
-      ) : (
-        <>
-          <ShieldIcon weight="bold" size={16} />
-        </>
+    <div className={cn("flex gap-1", className)}>
+      {showHITL && (
+        <SafeModeIconButton
+          isEnabled={currentHITLSafeMode}
+          label="Human-in-the-loop"
+          tooltipEnabled="The agent will pause at human-in-the-loop blocks and wait for your approval"
+          tooltipDisabled="Human-in-the-loop blocks will proceed automatically"
+          onToggle={handleHITLToggle}
+          isPending={isPending}
+        />
       )}
-    </Button>
+      {showSensitive && (
+        <SafeModeIconButton
+          isEnabled={currentSensitiveActionSafeMode}
+          label="Sensitive actions"
+          tooltipEnabled="The agent will pause at sensitive action blocks and wait for your approval"
+          tooltipDisabled="Sensitive action blocks will proceed automatically"
+          onToggle={handleSensitiveActionToggle}
+          isPending={isPending}
+        />
+      )}
+    </div>
   );
 }

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/selected-views/SelectedSettingsView/SelectedSettingsView.tsx

@@ -13,8 +13,16 @@ interface Props {
 }
 
 export function SelectedSettingsView({ agent, onClearSelectedRun }: Props) {
-  const { currentSafeMode, isPending, hasHITLBlocks, handleToggle } =
-    useAgentSafeMode(agent);
+  const {
+    currentHITLSafeMode,
+    showHITLToggle,
+    handleHITLToggle,
+    currentSensitiveActionSafeMode,
+    showSensitiveActionToggle,
+    handleSensitiveActionToggle,
+    isPending,
+    shouldShowToggle,
+  } = useAgentSafeMode(agent);
 
   return (
     <SelectedViewLayout agent={agent}>
@@ -34,24 +42,51 @@ export function SelectedSettingsView({ agent, onClearSelectedRun }: Props) {
         </div>
 
         <div className={`${AGENT_LIBRARY_SECTION_PADDING_X} space-y-6`}>
-          {hasHITLBlocks ? (
-            <div className="flex w-full max-w-2xl flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
-              <div className="flex w-full items-start justify-between gap-4">
-                <div className="flex-1">
-                  <Text variant="large-semibold">Require human approval</Text>
-                  <Text variant="large" className="mt-1 text-zinc-900">
-                    The agent will pause and wait for your review before
-                    continuing
-                  </Text>
+          {shouldShowToggle ? (
+            <>
+              {showHITLToggle && (
+                <div className="flex w-full max-w-2xl flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
+                  <div className="flex w-full items-start justify-between gap-4">
+                    <div className="flex-1">
+                      <Text variant="large-semibold">
+                        Human-in-the-loop approval
+                      </Text>
+                      <Text variant="large" className="mt-1 text-zinc-900">
+                        The agent will pause at human-in-the-loop blocks and
+                        wait for your review before continuing
+                      </Text>
+                    </div>
+                    <Switch
+                      checked={currentHITLSafeMode || false}
+                      onCheckedChange={handleHITLToggle}
+                      disabled={isPending}
+                      className="mt-1"
+                    />
+                  </div>
                 </div>
-                <Switch
-                  checked={currentSafeMode || false}
-                  onCheckedChange={handleToggle}
-                  disabled={isPending}
-                  className="mt-1"
-                />
-              </div>
-            </div>
+              )}
+              {showSensitiveActionToggle && (
+                <div className="flex w-full max-w-2xl flex-col items-start gap-4 rounded-xl border border-zinc-100 bg-white p-6">
+                  <div className="flex w-full items-start justify-between gap-4">
+                    <div className="flex-1">
+                      <Text variant="large-semibold">
+                        Sensitive action approval
+                      </Text>
+                      <Text variant="large" className="mt-1 text-zinc-900">
+                        The agent will pause at sensitive action blocks and wait
+                        for your review before continuing
+                      </Text>
+                    </div>
+                    <Switch
+                      checked={currentSensitiveActionSafeMode}
+                      onCheckedChange={handleSensitiveActionToggle}
+                      disabled={isPending}
+                      className="mt-1"
+                    />
+                  </div>
+                </div>
+              )}
+            </>
           ) : (
             <div className="rounded-xl border border-zinc-100 bg-white p-6">
               <Text variant="body" className="text-muted-foreground">

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/OldAgentLibraryView/components/agent-run-draft-view.tsx

@@ -1,8 +1,15 @@
 "use client";
-import React, { useCallback, useEffect, useMemo, useState } from "react";
+import React, {
+  useCallback,
+  useContext,
+  useEffect,
+  useMemo,
+  useState,
+} from "react";
 
 import {
   CredentialsMetaInput,
+  CredentialsType,
   GraphExecutionID,
   GraphMeta,
   LibraryAgentPreset,
@@ -29,7 +36,11 @@ import {
 } from "@/components/__legacy__/ui/icons";
 import { Input } from "@/components/__legacy__/ui/input";
 import { Button } from "@/components/atoms/Button/Button";
-import { CredentialsInput } from "@/components/contextual/CredentialsInput/CredentialsInput";
+import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
+import {
+  findSavedCredentialByProviderAndType,
+  findSavedUserCredentialByProviderAndType,
+} from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/helpers";
 import { InformationTooltip } from "@/components/molecules/InformationTooltip/InformationTooltip";
 import {
   useToast,
@@ -37,6 +48,7 @@ import {
 } from "@/components/molecules/Toast/use-toast";
 import { humanizeCronExpression } from "@/lib/cron-expression-utils";
 import { cn, isEmpty } from "@/lib/utils";
+import { CredentialsProvidersContext } from "@/providers/agent-credentials/credentials-provider";
 import { ClockIcon, CopyIcon, InfoIcon } from "@phosphor-icons/react";
 import { CalendarClockIcon, Trash2Icon } from "lucide-react";
 
@@ -90,6 +102,7 @@ export function AgentRunDraftView({
   const api = useBackendAPI();
   const { toast } = useToast();
   const toastOnFail = useToastOnFail();
+  const allProviders = useContext(CredentialsProvidersContext);
 
   const [inputValues, setInputValues] = useState<Record<string, any>>({});
   const [inputCredentials, setInputCredentials] = useState<
@@ -128,6 +141,77 @@ export function AgentRunDraftView({
     () => graph.credentials_input_schema.properties,
     [graph],
   );
+  const credentialFields = useMemo(
+    function getCredentialFields() {
+      return Object.entries(agentCredentialsInputFields);
+    },
+    [agentCredentialsInputFields],
+  );
+  const requiredCredentials = useMemo(
+    function getRequiredCredentials() {
+      return new Set(
+        (graph.credentials_input_schema?.required as string[]) || [],
+      );
+    },
+    [graph.credentials_input_schema?.required],
+  );
+
+  useEffect(
+    function initializeDefaultCredentials() {
+      if (!allProviders) return;
+      if (!graph.credentials_input_schema?.properties) return;
+      if (requiredCredentials.size === 0) return;
+
+      setInputCredentials(function updateCredentials(currentCreds) {
+        const next = { ...currentCreds };
+        let didAdd = false;
+
+        for (const key of requiredCredentials) {
+          if (next[key]) continue;
+          const schema = graph.credentials_input_schema.properties[key];
+          if (!schema) continue;
+
+          const providerNames = schema.credentials_provider || [];
+          const credentialTypes = schema.credentials_types || [];
+          const requiredScopes = schema.credentials_scopes;
+
+          const userCredential = findSavedUserCredentialByProviderAndType(
+            providerNames,
+            credentialTypes,
+            requiredScopes,
+            allProviders,
+          );
+
+          const savedCredential =
+            userCredential ||
+            findSavedCredentialByProviderAndType(
+              providerNames,
+              credentialTypes,
+              requiredScopes,
+              allProviders,
+            );
+
+          if (!savedCredential) continue;
+
+          next[key] = {
+            id: savedCredential.id,
+            provider: savedCredential.provider,
+            type: savedCredential.type as CredentialsType,
+            title: savedCredential.title,
+          };
+          didAdd = true;
+        }
+
+        if (!didAdd) return currentCreds;
+        return next;
+      });
+    },
+    [
+      allProviders,
+      graph.credentials_input_schema?.properties,
+      requiredCredentials,
+    ],
+  );
 
   const [allRequiredInputsAreSet, missingInputs] = useMemo(() => {
     const nonEmptyInputs = new Set(
@@ -145,18 +229,35 @@ export function AgentRunDraftView({
     );
     return [isSuperset, difference];
   }, [agentInputSchema.required, inputValues]);
-  const [allCredentialsAreSet, missingCredentials] = useMemo(() => {
-    const availableCredentials = new Set(Object.keys(inputCredentials));
-    const allCredentials = new Set(Object.keys(agentCredentialsInputFields));
-    // Backwards-compatible implementation of isSupersetOf and difference
-    const isSuperset = Array.from(allCredentials).every((item) =>
-      availableCredentials.has(item),
-    );
-    const difference = Array.from(allCredentials).filter(
-      (item) => !availableCredentials.has(item),
-    );
-    return [isSuperset, difference];
-  }, [agentCredentialsInputFields, inputCredentials]);
+  const [allCredentialsAreSet, missingCredentials] = useMemo(
+    function getCredentialStatus() {
+      const missing = Array.from(requiredCredentials).filter((key) => {
+        const cred = inputCredentials[key];
+        return !cred || !cred.id;
+      });
+      return [missing.length === 0, missing];
+    },
+    [requiredCredentials, inputCredentials],
+  );
+  function addChangedCredentials(prev: Set<keyof LibraryAgentPresetUpdatable>) {
+    const next = new Set(prev);
+    next.add("credentials");
+    return next;
+  }
+
+  function handleCredentialChange(key: string, value?: CredentialsMetaInput) {
+    setInputCredentials(function updateInputCredentials(currentCreds) {
+      const next = { ...currentCreds };
+      if (value === undefined) {
+        delete next[key];
+        return next;
+      }
+      next[key] = value;
+      return next;
+    });
+    setChangedPresetAttributes(addChangedCredentials);
+  }
+
   const notifyMissingInputs = useCallback(
     (needPresetName: boolean = true) => {
       const allMissingFields = (
@@ -649,35 +750,6 @@ export function AgentRunDraftView({
               </>
             )}
 
-            {/* Credentials inputs */}
-            {Object.entries(agentCredentialsInputFields).map(
-              ([key, inputSubSchema]) => (
-                <CredentialsInput
-                  key={key}
-                  schema={{ ...inputSubSchema, discriminator: undefined }}
-                  selectedCredentials={
-                    inputCredentials[key] ?? inputSubSchema.default
-                  }
-                  onSelectCredentials={(value) => {
-                    setInputCredentials((obj) => {
-                      const newObj = { ...obj };
-                      if (value === undefined) {
-                        delete newObj[key];
-                        return newObj;
-                      }
-                      return {
-                        ...obj,
-                        [key]: value,
-                      };
-                    });
-                    setChangedPresetAttributes((prev) =>
-                      prev.add("credentials"),
-                    );
-                  }}
-                />
-              ),
-            )}
-
             {/* Regular inputs */}
             {Object.entries(agentInputFields).map(([key, inputSubSchema]) => (
               <RunAgentInputs
@@ -695,6 +767,17 @@ export function AgentRunDraftView({
                 data-testid={`agent-input-${key}`}
               />
             ))}
+
+            {/* Credentials inputs */}
+            {credentialFields.length > 0 && (
+              <CredentialsGroupedView
+                credentialFields={credentialFields}
+                requiredCredentials={requiredCredentials}
+                inputCredentials={inputCredentials}
+                inputValues={inputValues}
+                onCredentialChange={handleCredentialChange}
+              />
+            )}
           </CardContent>
         </Card>
       </div>

autogpt_platform/frontend/src/app/(platform)/library/components/LibraryAgentCard/useLibraryAgentCard.ts

@@ -8,6 +8,8 @@ import { useGetV2GetUserProfile } from "@/app/api/__generated__/endpoints/store/
 import { LibraryAgent } from "@/app/api/__generated__/models/libraryAgent";
 import { okData } from "@/app/api/helpers";
 import { useToast } from "@/components/molecules/Toast/use-toast";
+import { isLogoutInProgress } from "@/lib/autogpt-server-api/helpers";
+import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
 import { updateFavoriteInQueries } from "./helpers";
 
 interface Props {
@@ -23,10 +25,14 @@ export function useLibraryAgentCard({ agent }: Props) {
   const { toast } = useToast();
   const queryClient = getQueryClient();
   const { mutateAsync: updateLibraryAgent } = usePatchV2UpdateLibraryAgent();
+  const { user, isLoggedIn } = useSupabase();
+  const logoutInProgress = isLogoutInProgress();
 
   const { data: profile } = useGetV2GetUserProfile({
     query: {
       select: okData,
+      enabled: isLoggedIn && !!user && !logoutInProgress,
+      queryKey: ["/api/store/profile", user?.id],
     },
   });
 

autogpt_platform/frontend/src/app/(platform)/login/useLoginPage.ts

@@ -1,6 +1,8 @@
 import { useToast } from "@/components/molecules/Toast/use-toast";
+import { getHomepageRoute } from "@/lib/constants";
 import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
 import { environment } from "@/services/environment";
+import { Flag, useGetFlag } from "@/services/feature-flags/use-get-flag";
 import { loginFormSchema, LoginProvider } from "@/types/auth";
 import { zodResolver } from "@hookform/resolvers/zod";
 import { useRouter, useSearchParams } from "next/navigation";
@@ -20,15 +22,17 @@ export function useLoginPage() {
   const [isGoogleLoading, setIsGoogleLoading] = useState(false);
   const [showNotAllowedModal, setShowNotAllowedModal] = useState(false);
   const isCloudEnv = environment.isCloud();
+  const isChatEnabled = useGetFlag(Flag.CHAT);
+  const homepageRoute = getHomepageRoute(isChatEnabled);
 
   // Get redirect destination from 'next' query parameter
   const nextUrl = searchParams.get("next");
 
   useEffect(() => {
     if (isLoggedIn && !isLoggingIn) {
-      router.push(nextUrl || "/marketplace");
+      router.push(nextUrl || homepageRoute);
     }
-  }, [isLoggedIn, isLoggingIn, nextUrl, router]);
+  }, [homepageRoute, isLoggedIn, isLoggingIn, nextUrl, router]);
 
   const form = useForm<z.infer<typeof loginFormSchema>>({
     resolver: zodResolver(loginFormSchema),
@@ -98,7 +102,7 @@ export function useLoginPage() {
       } else if (result.onboarding) {
         router.replace("/onboarding");
       } else {
-        router.replace("/marketplace");
+        router.replace(homepageRoute);
       }
     } catch (error) {
       toast({

autogpt_platform/frontend/src/app/(platform)/marketplace/components/MainMarketplacePage/__tests__/main.test.tsx

@@ -0,0 +1,15 @@
+import { expect, test } from "vitest";
+import { render, screen } from "@/tests/integrations/test-utils";
+import { MainMarkeplacePage } from "../MainMarketplacePage";
+import { server } from "@/mocks/mock-server";
+import { getDeleteV2DeleteStoreSubmissionMockHandler422 } from "@/app/api/__generated__/endpoints/store/store.msw";
+
+// Only for CI testing purpose, will remove it in future PR
+test("MainMarketplacePage", async () => {
+  server.use(getDeleteV2DeleteStoreSubmissionMockHandler422());
+
+  render(<MainMarkeplacePage />);
+  expect(
+    await screen.findByText("Featured agents", { exact: false }),
+  ).toBeDefined();
+});