Merge branch 'dev' into chore/remove-deprecated-openai-models

## Summary
Adds a warning to the Getting Started docs clarifying that **Podman and
podman-compose are not supported**.

## Problem
Users on Windows using `podman-compose` instead of Docker get errors
like:
```
Error: the specified Containerfile or Dockerfile does not exist, ..\..\autogpt_platform\backend\Dockerfile
```

This is because Podman handles relative paths differently than Docker,
causing incorrect path resolution on Windows.

## Solution
- Added a clear warning section after the Windows WSL 2 notes
- Explains the error users might see
- Directs them to install Docker Desktop instead

Closes #11358

<!-- greptile_comment -->

<details><summary><h3>Greptile Summary</h3></summary>

Adds a "Podman Not Supported" warning section to the Getting Started
documentation, placed after the Windows/WSL 2 installation notes. The
section clarifies that Docker is required, shows the typical error
message users encounter when using Podman, and directs them to install
Docker Desktop instead. This addresses issue #11358 where Windows users
using `podman-compose` hit path resolution errors.

- Adds `### ⚠️ Podman Not Supported` section under Manual Setup, after
Windows Installation Note
- Includes the specific error message users see with Podman for easy
identification
- Links to Docker Desktop installation docs as the recommended solution
- Formatting is consistent with existing sections in the document (emoji
headings, code blocks for errors)
</details>


<details><summary><h3>Confidence Score: 5/5</h3></summary>

- This PR is safe to merge — it only adds a documentation warning
section with no code changes.
- The change is a small, well-written documentation addition that adds a
Podman compatibility warning. It touches only one markdown file,
introduces no code changes, and is consistent with the existing document
structure and style. No issues were found.
- No files require special attention.
</details>


<details><summary><h3>Flowchart</h3></summary>

```mermaid
flowchart TD
    A[User wants to run AutoGPT] --> B{Which container runtime?}
    B -->|Docker / Docker Desktop| C[docker compose up -d --build]
    C --> D[AutoGPT starts successfully]
    B -->|Podman / podman-compose| E[podman-compose up -d --build]
    E --> F[Error: Containerfile or Dockerfile does not exist]
    F --> G[New warning section directs user to install Docker Desktop]
    G --> C
```
</details>


<sub>Last reviewed commit: 23ea6bd</sub>

<!-- greptile_other_comments_section -->

<!-- /greptile_comment -->

autogpt_platform/backend/backend/blocks/llm.py

@@ -106,8 +106,6 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     GPT41_MINI = "gpt-4.1-mini-2025-04-14"
     GPT4O_MINI = "gpt-4o-mini"
     GPT4O = "gpt-4o"
-    GPT4_TURBO = "gpt-4-turbo"
-    GPT3_5_TURBO = "gpt-3.5-turbo"
     # Anthropic models
     CLAUDE_4_1_OPUS = "claude-opus-4-1-20250805"
     CLAUDE_4_OPUS = "claude-opus-4-20250514"
@@ -255,12 +253,6 @@ MODEL_METADATA = {
     LlmModel.GPT4O: ModelMetadata(
         "openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2
     ),  # gpt-4o-2024-08-06
-    LlmModel.GPT4_TURBO: ModelMetadata(
-        "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", "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, "Claude Opus 4.1", "Anthropic", "Anthropic", 3

autogpt_platform/backend/backend/copilot/config.py

@@ -27,7 +27,6 @@ class ChatConfig(BaseSettings):
     session_ttl: int = Field(default=43200, description="Session TTL in seconds")
 
     # Streaming Configuration
-    stream_timeout: int = Field(default=300, description="Stream timeout in seconds")
     max_retries: int = Field(
         default=3,
         description="Max retries for fallback path (SDK handles retries internally)",
@@ -39,8 +38,10 @@ class ChatConfig(BaseSettings):
 
     # Long-running operation configuration
     long_running_operation_ttl: int = Field(
-        default=600,
-        description="TTL in seconds for long-running operation tracking in Redis (safety net if pod dies)",
+        default=3600,
+        description="TTL in seconds for long-running operation deduplication lock "
+        "(1 hour, matches stream_ttl). Prevents duplicate operations if pod dies. "
+        "For longer operations, the stream_registry heartbeat keeps them alive.",
     )
 
     # Stream registry configuration for SSE reconnection
@@ -48,6 +49,11 @@ class ChatConfig(BaseSettings):
         default=3600,
         description="TTL in seconds for stream data in Redis (1 hour)",
     )
+    stream_lock_ttl: int = Field(
+        default=120,
+        description="TTL in seconds for stream lock (2 minutes). Short timeout allows "
+        "reconnection after refresh/crash without long waits.",
+    )
     stream_max_length: int = Field(
         default=10000,
         description="Maximum number of messages to store per stream",

autogpt_platform/backend/backend/copilot/db.py

@@ -3,8 +3,9 @@
 import asyncio
 import logging
 from datetime import UTC, datetime
-from typing import Any, cast
+from typing import Any
 
+from prisma.errors import UniqueViolationError
 from prisma.models import ChatMessage as PrismaChatMessage
 from prisma.models import ChatSession as PrismaChatSession
 from prisma.types import (
@@ -92,10 +93,9 @@ async def add_chat_message(
     function_call: dict[str, Any] | None = None,
 ) -> ChatMessage:
     """Add a message to a chat session."""
-    # Build input dict dynamically rather than using ChatMessageCreateInput directly
-    # because Prisma's TypedDict validation rejects optional fields set to None.
-    # We only include fields that have values, then cast at the end.
-    data: dict[str, Any] = {
+    # Build ChatMessageCreateInput with only non-None values
+    # (Prisma TypedDict rejects optional fields set to None)
+    data: ChatMessageCreateInput = {
         "Session": {"connect": {"id": session_id}},
         "role": role,
         "sequence": sequence,
@@ -123,7 +123,7 @@ async def add_chat_message(
             where={"id": session_id},
             data={"updatedAt": datetime.now(UTC)},
         ),
-        PrismaChatMessage.prisma().create(data=cast(ChatMessageCreateInput, data)),
+        PrismaChatMessage.prisma().create(data=data),
     )
     return ChatMessage.from_db(message)
 
@@ -132,58 +132,93 @@ async def add_chat_messages_batch(
     session_id: str,
     messages: list[dict[str, Any]],
     start_sequence: int,
-) -> list[ChatMessage]:
+) -> int:
     """Add multiple messages to a chat session in a batch.
 
-    Uses a transaction for atomicity - if any message creation fails,
-    the entire batch is rolled back.
+    Uses collision detection with retry: tries to create messages starting
+    at start_sequence. If a unique constraint violation occurs (e.g., the
+    streaming loop and long-running callback race), queries the latest
+    sequence and retries with the correct offset. This avoids unnecessary
+    upserts and DB queries in the common case (no collision).
+
+    Returns:
+        Next sequence number for the next message to be inserted. This equals
+        start_sequence + len(messages) and allows callers to update their
+        counters even when collision detection adjusts start_sequence.
     """
     if not messages:
-        return []
+        # No messages to add - return current count
+        return start_sequence
 
-    created_messages = []
+    max_retries = 5
+    for attempt in range(max_retries):
+        try:
+            # Single timestamp for all messages and session update
+            now = datetime.now(UTC)
 
-    async with db.transaction() as tx:
-        for i, msg in enumerate(messages):
-            # Build input dict dynamically rather than using ChatMessageCreateInput
-            # directly because Prisma's TypedDict validation rejects optional fields
-            # set to None. We only include fields that have values, then cast.
-            data: dict[str, Any] = {
-                "Session": {"connect": {"id": session_id}},
-                "role": msg["role"],
-                "sequence": start_sequence + i,
-            }
+            async with db.transaction() as tx:
+                # Build all message data
+                messages_data = []
+                for i, msg in enumerate(messages):
+                    # Build ChatMessageCreateInput with only non-None values
+                    # (Prisma TypedDict rejects optional fields set to None)
+                    # Note: create_many doesn't support nested creates, use sessionId directly
+                    data: ChatMessageCreateInput = {
+                        "sessionId": session_id,
+                        "role": msg["role"],
+                        "sequence": start_sequence + i,
+                        "createdAt": now,
+                    }
 
-            # Add optional string fields
-            if msg.get("content") is not None:
-                data["content"] = msg["content"]
-            if msg.get("name") is not None:
-                data["name"] = msg["name"]
-            if msg.get("tool_call_id") is not None:
-                data["toolCallId"] = msg["tool_call_id"]
-            if msg.get("refusal") is not None:
-                data["refusal"] = msg["refusal"]
+                    # Add optional string fields
+                    if msg.get("content") is not None:
+                        data["content"] = msg["content"]
+                    if msg.get("name") is not None:
+                        data["name"] = msg["name"]
+                    if msg.get("tool_call_id") is not None:
+                        data["toolCallId"] = msg["tool_call_id"]
+                    if msg.get("refusal") is not None:
+                        data["refusal"] = msg["refusal"]
 
-            # Add optional JSON fields only when they have values
-            if msg.get("tool_calls") is not None:
-                data["toolCalls"] = SafeJson(msg["tool_calls"])
-            if msg.get("function_call") is not None:
-                data["functionCall"] = SafeJson(msg["function_call"])
+                    # Add optional JSON fields only when they have values
+                    if msg.get("tool_calls") is not None:
+                        data["toolCalls"] = SafeJson(msg["tool_calls"])
+                    if msg.get("function_call") is not None:
+                        data["functionCall"] = SafeJson(msg["function_call"])
 
-            created = await PrismaChatMessage.prisma(tx).create(
-                data=cast(ChatMessageCreateInput, data)
-            )
-            created_messages.append(created)
+                    messages_data.append(data)
 
-        # Update session's updatedAt timestamp within the same transaction.
-        # Note: Token usage (total_prompt_tokens, total_completion_tokens) is updated
-        # separately via update_chat_session() after streaming completes.
-        await PrismaChatSession.prisma(tx).update(
-            where={"id": session_id},
-            data={"updatedAt": datetime.now(UTC)},
-        )
+                # Run create_many and session update in parallel within transaction
+                # Both use the same timestamp for consistency
+                await asyncio.gather(
+                    PrismaChatMessage.prisma(tx).create_many(data=messages_data),
+                    PrismaChatSession.prisma(tx).update(
+                        where={"id": session_id},
+                        data={"updatedAt": now},
+                    ),
+                )
 
-    return [ChatMessage.from_db(m) for m in created_messages]
+            # Return next sequence number for counter sync
+            return start_sequence + len(messages)
+
+        except UniqueViolationError:
+            if attempt < max_retries - 1:
+                # Collision detected - query MAX(sequence)+1 and retry with correct offset
+                logger.info(
+                    f"Collision detected for session {session_id} at sequence "
+                    f"{start_sequence}, querying DB for latest sequence"
+                )
+                start_sequence = await get_next_sequence(session_id)
+                logger.info(
+                    f"Retrying batch insert with start_sequence={start_sequence}"
+                )
+                continue
+            else:
+                # Max retries exceeded - propagate error
+                raise
+
+    # Should never reach here due to raise in exception handler
+    raise RuntimeError(f"Failed to insert messages after {max_retries} attempts")
 
 
 async def get_user_chat_sessions(
@@ -237,10 +272,20 @@ async def delete_chat_session(session_id: str, user_id: str | None = None) -> bo
         return False
 
 
-async def get_chat_session_message_count(session_id: str) -> int:
-    """Get the number of messages in a chat session."""
-    count = await PrismaChatMessage.prisma().count(where={"sessionId": session_id})
-    return count
+async def get_next_sequence(session_id: str) -> int:
+    """Get the next sequence number for a new message in this session.
+
+    Uses MAX(sequence) + 1 for robustness. Returns 0 if no messages exist.
+    More robust than COUNT(*) because it's immune to deleted messages.
+
+    Optimized to select only the sequence column using raw SQL.
+    The unique index on (sessionId, sequence) makes this query fast.
+    """
+    results = await db.query_raw_with_schema(
+        'SELECT "sequence" FROM {schema_prefix}"ChatMessage" WHERE "sessionId" = $1 ORDER BY "sequence" DESC LIMIT 1',
+        session_id,
+    )
+    return 0 if not results else results[0]["sequence"] + 1
 
 
 async def update_tool_message_content(

autogpt_platform/backend/backend/copilot/executor/processor.py

@@ -266,7 +266,11 @@ class CoPilotProcessor:
 
         except asyncio.CancelledError:
             log.info("Task cancelled")
-            await stream_registry.mark_task_completed(entry.task_id, status="failed")
+            await stream_registry.mark_task_completed(
+                entry.task_id,
+                status="failed",
+                error_message="Task was cancelled",
+            )
             raise
 
         except Exception as e:

autogpt_platform/backend/backend/copilot/model.py

@@ -434,8 +434,6 @@ async def _get_session_from_db(session_id: str) -> ChatSession | None:
 
 async def upsert_chat_session(
     session: ChatSession,
-    *,
-    existing_message_count: int | None = None,
 ) -> ChatSession:
     """Update a chat session in both cache and database.
 
@@ -443,12 +441,6 @@ async def upsert_chat_session(
     operations (e.g., background title update and main stream handler)
     attempt to upsert the same session simultaneously.
 
-    Args:
-        existing_message_count: If provided, skip the DB query to count
-            existing messages. The caller is responsible for tracking this
-            accurately. Useful for incremental saves in a streaming loop
-            where the caller already knows how many messages are persisted.
-
     Raises:
         DatabaseError: If the database write fails. The cache is still updated
             as a best-effort optimization, but the error is propagated to ensure
@@ -459,11 +451,8 @@ async def upsert_chat_session(
     lock = await _get_session_lock(session.session_id)
 
     async with lock:
-        # Get existing message count from DB for incremental saves
-        if existing_message_count is None:
-            existing_message_count = await chat_db().get_chat_session_message_count(
-                session.session_id
-            )
+        # Always query DB for existing message count to ensure consistency
+        existing_message_count = await chat_db().get_next_sequence(session.session_id)
 
         db_error: Exception | None = None
 
@@ -587,9 +576,7 @@ async def append_and_save_message(session_id: str, message: ChatMessage) -> Chat
             raise ValueError(f"Session {session_id} not found")
 
         session.messages.append(message)
-        existing_message_count = await chat_db().get_chat_session_message_count(
-            session_id
-        )
+        existing_message_count = await chat_db().get_next_sequence(session_id)
 
         try:
             await _save_session_to_db(session, existing_message_count)

autogpt_platform/backend/backend/copilot/model_test.py

@@ -331,3 +331,96 @@ def test_to_openai_messages_merges_split_assistants():
     tc_list = merged.get("tool_calls")
     assert tc_list is not None and len(list(tc_list)) == 1
     assert list(tc_list)[0]["id"] == "tc1"
+
+
+# --------------------------------------------------------------------------- #
+#  Concurrent save collision detection                                        #
+# --------------------------------------------------------------------------- #
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_concurrent_saves_collision_detection(setup_test_user, test_user_id):
+    """Test that concurrent saves from streaming loop and callback handle collisions correctly.
+
+    Simulates the race condition where:
+    1. Streaming loop starts with saved_msg_count=5
+    2. Long-running callback appends message #5 and saves
+    3. Streaming loop tries to save with stale count=5
+
+    The collision detection should handle this gracefully.
+    """
+    import asyncio
+
+    # Create a session with initial messages
+    session = ChatSession.new(user_id=test_user_id)
+    for i in range(3):
+        session.messages.append(
+            ChatMessage(
+                role="user" if i % 2 == 0 else "assistant", content=f"Message {i}"
+            )
+        )
+
+    # Save initial messages
+    session = await upsert_chat_session(session)
+
+    # Simulate streaming loop and callback saving concurrently
+    async def streaming_loop_save():
+        """Simulates streaming loop saving messages."""
+        # Add 2 messages
+        session.messages.append(ChatMessage(role="user", content="Streaming message 1"))
+        session.messages.append(
+            ChatMessage(role="assistant", content="Streaming message 2")
+        )
+
+        # Wait a bit to let callback potentially save first
+        await asyncio.sleep(0.01)
+
+        # Save (will query DB for existing count)
+        return await upsert_chat_session(session)
+
+    async def callback_save():
+        """Simulates long-running callback saving a message."""
+        # Add 1 message
+        session.messages.append(
+            ChatMessage(role="tool", content="Callback result", tool_call_id="tc1")
+        )
+
+        # Save immediately (will query DB for existing count)
+        return await upsert_chat_session(session)
+
+    # Run both saves concurrently - one will hit collision detection
+    results = await asyncio.gather(streaming_loop_save(), callback_save())
+
+    # Both should succeed
+    assert all(r is not None for r in results)
+
+    # Reload session from DB to verify
+    from backend.data.redis_client import get_redis_async
+
+    redis_key = f"chat:session:{session.session_id}"
+    async_redis = await get_redis_async()
+    await async_redis.delete(redis_key)  # Clear cache to force DB load
+
+    loaded_session = await get_chat_session(session.session_id, test_user_id)
+    assert loaded_session is not None
+
+    # Should have all 6 messages (3 initial + 2 streaming + 1 callback)
+    assert len(loaded_session.messages) == 6
+
+    # Verify no duplicate sequences
+    sequences = []
+    for i, msg in enumerate(loaded_session.messages):
+        # Messages should have sequential sequence numbers starting from 0
+        sequences.append(i)
+
+    # All sequences should be unique and sequential
+    assert sequences == list(range(6))
+
+    # Verify message content is preserved
+    contents = [m.content for m in loaded_session.messages]
+    assert "Message 0" in contents
+    assert "Message 1" in contents
+    assert "Message 2" in contents
+    assert "Streaming message 1" in contents
+    assert "Streaming message 2" in contents
+    assert "Callback result" in contents

autogpt_platform/backend/backend/copilot/sdk/service.py

@@ -7,8 +7,10 @@ import os
 import uuid
 from collections.abc import AsyncGenerator
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, cast
 
+from backend.data.redis_client import get_redis_async
+from backend.executor.cluster_lock import AsyncClusterLock
 from backend.util.exceptions import NotFoundError
 
 from .. import stream_registry
@@ -61,6 +63,7 @@ from .transcript import (
 logger = logging.getLogger(__name__)
 config = ChatConfig()
 
+
 # Set to hold background tasks to prevent garbage collection
 _background_tasks: set[asyncio.Task[Any]] = set()
 
@@ -132,8 +135,12 @@ is delivered to the user via a background stream.
   All tasks must run in the foreground.
 """
 
+STREAM_LOCK_PREFIX = "copilot:stream:lock:"
 
-def _build_long_running_callback(user_id: str | None) -> LongRunningCallback:
+
+def _build_long_running_callback(
+    user_id: str | None,
+) -> LongRunningCallback:
     """Build a callback that delegates long-running tools to the non-SDK infrastructure.
 
     Long-running tools (create_agent, edit_agent, etc.) are delegated to the
@@ -142,6 +149,9 @@ def _build_long_running_callback(user_id: str | None) -> LongRunningCallback:
     page refreshes / pod restarts, and the frontend shows the proper loading
     widget with progress updates.
 
+    Args:
+        user_id: User ID for the session
+
     The returned callback matches the ``LongRunningCallback`` signature:
     ``(tool_name, args, session) -> MCP response dict``.
     """
@@ -207,7 +217,8 @@ def _build_long_running_callback(user_id: str | None) -> LongRunningCallback:
             tool_call_id=tool_call_id,
         )
         session.messages.append(pending_message)
-        await upsert_chat_session(session)
+        # Collision detection happens in add_chat_messages_batch (db.py)
+        session = await upsert_chat_session(session)
 
         # --- Spawn background task (reuses non-SDK infrastructure) ---
         bg_task = asyncio.create_task(
@@ -527,6 +538,9 @@ async def stream_chat_completion_sdk(
             f"Session {session_id} not found. Please create a new session first."
         )
 
+    # Type narrowing: session is guaranteed ChatSession after the check above
+    session = cast(ChatSession, session)
+
     # Append the new message to the session if it's not already there
     new_message_role = "user" if is_user_message else "assistant"
     if message and (
@@ -564,6 +578,29 @@ async def stream_chat_completion_sdk(
     system_prompt += _SDK_TOOL_SUPPLEMENT
     message_id = str(uuid.uuid4())
     task_id = str(uuid.uuid4())
+    stream_id = task_id  # Use task_id as unique stream identifier
+
+    # Acquire stream lock to prevent concurrent streams to the same session
+    lock = AsyncClusterLock(
+        redis=await get_redis_async(),
+        key=f"{STREAM_LOCK_PREFIX}{session_id}",
+        owner_id=stream_id,
+        timeout=config.stream_lock_ttl,
+    )
+
+    lock_owner = await lock.try_acquire()
+    if lock_owner != stream_id:
+        # Another stream is active
+        logger.warning(
+            f"[SDK] Session {session_id} already has an active stream: {lock_owner}"
+        )
+        yield StreamError(
+            errorText="Another stream is already active for this session. "
+            "Please wait or stop it.",
+            code="stream_already_active",
+        )
+        yield StreamFinish()
+        return
 
     yield StreamStart(messageId=message_id, taskId=task_id)
 
@@ -715,9 +752,6 @@ async def stream_chat_completion_sdk(
                 accumulated_tool_calls: list[dict[str, Any]] = []
                 has_appended_assistant = False
                 has_tool_results = False
-                # Track persisted message count to skip DB count queries
-                # on incremental saves.  Initial save happened at line 545.
-                saved_msg_count = len(session.messages)
 
                 # Use an explicit async iterator with non-cancelling heartbeats.
                 # CRITICAL: we must NOT cancel __anext__() mid-flight — doing so
@@ -744,6 +778,8 @@ async def stream_chat_completion_sdk(
 
                         if not done:
                             # Timeout — emit heartbeat but keep the task alive
+                            # Also refresh lock TTL to keep it alive
+                            await lock.refresh()
                             yield StreamHeartbeat()
                             continue
 
@@ -893,13 +929,10 @@ async def stream_chat_completion_sdk(
                                     has_appended_assistant = True
                                 # Save before tool execution starts so the
                                 # pending tool call is visible on refresh /
-                                # other devices.
+                                # other devices. Collision detection happens
+                                # in add_chat_messages_batch (db.py).
                                 try:
-                                    await upsert_chat_session(
-                                        session,
-                                        existing_message_count=saved_msg_count,
-                                    )
-                                    saved_msg_count = len(session.messages)
+                                    session = await upsert_chat_session(session)
                                 except Exception as save_err:
                                     logger.warning(
                                         "[SDK] [%s] Incremental save " "failed: %s",
@@ -922,12 +955,9 @@ async def stream_chat_completion_sdk(
                                 has_tool_results = True
                                 # Save after tool completes so the result is
                                 # visible on refresh / other devices.
+                                # Collision detection happens in add_chat_messages_batch (db.py).
                                 try:
-                                    await upsert_chat_session(
-                                        session,
-                                        existing_message_count=saved_msg_count,
-                                    )
-                                    saved_msg_count = len(session.messages)
+                                    session = await upsert_chat_session(session)
                                 except Exception as save_err:
                                     logger.warning(
                                         "[SDK] [%s] Incremental save " "failed: %s",
@@ -1059,7 +1089,7 @@ async def stream_chat_completion_sdk(
                 "to use the OpenAI-compatible fallback."
             )
 
-        await asyncio.shield(upsert_chat_session(session))
+        session = cast(ChatSession, await asyncio.shield(upsert_chat_session(session)))
         logger.info(
             "[SDK] [%s] Session saved with %d messages",
             session_id[:12],
@@ -1076,10 +1106,11 @@ async def stream_chat_completion_sdk(
         raise
     except Exception as e:
         logger.error(f"[SDK] Error: {e}", exc_info=True)
-        try:
-            await asyncio.shield(upsert_chat_session(session))
-        except Exception as save_err:
-            logger.error(f"[SDK] Failed to save session on error: {save_err}")
+        if session:
+            try:
+                await asyncio.shield(upsert_chat_session(session))
+            except Exception as save_err:
+                logger.error(f"[SDK] Failed to save session on error: {save_err}")
         yield StreamError(
             errorText="An error occurred. Please try again.",
             code="sdk_error",
@@ -1101,7 +1132,7 @@ async def stream_chat_completion_sdk(
                 if not raw_transcript and use_resume and resume_file:
                     raw_transcript = read_transcript_file(resume_file)
 
-                if raw_transcript:
+                if raw_transcript and session is not None:
                     await asyncio.shield(
                         _try_upload_transcript(
                             user_id,
@@ -1121,6 +1152,9 @@ async def stream_chat_completion_sdk(
         if sdk_cwd:
             _cleanup_sdk_tool_results(sdk_cwd)
 
+        # Release stream lock to allow new streams for this session
+        await lock.release()
+
 
 async def _try_upload_transcript(
     user_id: str,

autogpt_platform/backend/backend/copilot/service.py

@@ -352,7 +352,8 @@ async def assign_user_to_session(
     if not session:
         raise NotFoundError(f"Session {session_id} not found")
     session.user_id = user_id
-    return await upsert_chat_session(session)
+    session = await upsert_chat_session(session)
+    return session
 
 
 async def stream_chat_completion(
@@ -1563,7 +1564,11 @@ async def _yield_tool_call(
             await _mark_operation_completed(tool_call_id)
             # Mark stream registry task as failed if it was created
             try:
-                await stream_registry.mark_task_completed(task_id, status="failed")
+                await stream_registry.mark_task_completed(
+                    task_id,
+                    status="failed",
+                    error_message=f"Failed to setup tool {tool_name}: {e}",
+                )
             except Exception as mark_err:
                 logger.warning(f"Failed to mark task {task_id} as failed: {mark_err}")
             logger.error(
@@ -1731,7 +1736,11 @@ async def _execute_long_running_tool_with_streaming(
         session = await get_chat_session(session_id, user_id)
         if not session:
             logger.error(f"Session {session_id} not found for background tool")
-            await stream_registry.mark_task_completed(task_id, status="failed")
+            await stream_registry.mark_task_completed(
+                task_id,
+                status="failed",
+                error_message=f"Session {session_id} not found",
+            )
             return
 
         # Pass operation_id and task_id to the tool for async processing

autogpt_platform/backend/backend/copilot/stream_registry.py

@@ -644,6 +644,8 @@ async def _stream_listener(
 async def mark_task_completed(
     task_id: str,
     status: Literal["completed", "failed"] = "completed",
+    *,
+    error_message: str | None = None,
 ) -> bool:
     """Mark a task as completed and publish finish event.
 
@@ -654,6 +656,10 @@ async def mark_task_completed(
     Args:
         task_id: Task ID to mark as completed
         status: Final status ("completed" or "failed")
+        error_message: If provided and status="failed", publish a StreamError
+            before StreamFinish so connected clients see why the task ended.
+            If not provided, no StreamError is published (caller should publish
+            manually if needed to avoid duplicates).
 
     Returns:
         True if task was newly marked completed, False if already completed/failed
@@ -669,6 +675,17 @@ async def mark_task_completed(
         logger.debug(f"Task {task_id} already completed/failed, skipping")
         return False
 
+    # Publish error event before finish so connected clients know WHY the
+    # task ended. Only publish if caller provided an explicit error message
+    # to avoid duplicates with code paths that manually publish StreamError.
+    # This is best-effort — if it fails, the StreamFinish still ensures
+    # listeners clean up.
+    if status == "failed" and error_message:
+        try:
+            await publish_chunk(task_id, StreamError(errorText=error_message))
+        except Exception as e:
+            logger.warning(f"Failed to publish error event for task {task_id}: {e}")
+
     # THEN publish finish event (best-effort - listeners can detect via status polling)
     try:
         await publish_chunk(task_id, StreamFinish())
@@ -821,27 +838,6 @@ async def get_active_task_for_session(
                 if task_user_id and user_id != task_user_id:
                     continue
 
-                # Auto-expire stale tasks that exceeded stream_timeout
-                created_at_str = meta.get("created_at", "")
-                if created_at_str:
-                    try:
-                        created_at = datetime.fromisoformat(created_at_str)
-                        age_seconds = (
-                            datetime.now(timezone.utc) - created_at
-                        ).total_seconds()
-                        if age_seconds > config.stream_timeout:
-                            logger.warning(
-                                f"[TASK_LOOKUP] Auto-expiring stale task {task_id[:8]}... "
-                                f"(age={age_seconds:.0f}s > timeout={config.stream_timeout}s)"
-                            )
-                            await mark_task_completed(task_id, "failed")
-                            continue
-                    except (ValueError, TypeError) as exc:
-                        logger.warning(
-                            f"[TASK_LOOKUP] Failed to parse created_at "
-                            f"for task {task_id[:8]}...: {exc}"
-                        )
-
                 logger.info(
                     f"[TASK_LOOKUP] Found running task {task_id[:8]}... for session {session_id[:8]}..."
                 )

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -75,8 +75,6 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.GPT41_MINI: 1,
     LlmModel.GPT4O_MINI: 1,
     LlmModel.GPT4O: 3,
-    LlmModel.GPT4_TURBO: 10,
-    LlmModel.GPT3_5_TURBO: 1,
     LlmModel.CLAUDE_4_1_OPUS: 21,
     LlmModel.CLAUDE_4_OPUS: 21,
     LlmModel.CLAUDE_4_SONNET: 5,

autogpt_platform/backend/backend/data/credit_test.py

@@ -79,7 +79,7 @@ async def test_block_credit_usage(server: SpinTestServer):
             node_exec_id="test_node_exec",
             block_id=AITextGeneratorBlock().id,
             inputs={
-                "model": "gpt-4-turbo",
+                "model": "gpt-4o",
                 "credentials": {
                     "id": openai_credentials.id,
                     "provider": openai_credentials.provider,
@@ -100,7 +100,7 @@ async def test_block_credit_usage(server: SpinTestServer):
             graph_exec_id="test_graph_exec",
             node_exec_id="test_node_exec",
             block_id=AITextGeneratorBlock().id,
-            inputs={"model": "gpt-4-turbo", "api_key": "owned_api_key"},
+            inputs={"model": "gpt-4o", "api_key": "owned_api_key"},
             execution_context=ExecutionContext(user_timezone="UTC"),
         ),
     )

autogpt_platform/backend/backend/data/db_manager.py

@@ -303,7 +303,7 @@ class DatabaseManager(AppService):
     get_user_chat_sessions = _(chat_db.get_user_chat_sessions)
     get_user_session_count = _(chat_db.get_user_session_count)
     delete_chat_session = _(chat_db.delete_chat_session)
-    get_chat_session_message_count = _(chat_db.get_chat_session_message_count)
+    get_next_sequence = _(chat_db.get_next_sequence)
     update_tool_message_content = _(chat_db.update_tool_message_content)
 
 
@@ -473,5 +473,5 @@ class DatabaseManagerAsyncClient(AppServiceClient):
     get_user_chat_sessions = d.get_user_chat_sessions
     get_user_session_count = d.get_user_session_count
     delete_chat_session = d.delete_chat_session
-    get_chat_session_message_count = d.get_chat_session_message_count
+    get_next_sequence = d.get_next_sequence
     update_tool_message_content = d.update_tool_message_content

autogpt_platform/backend/backend/executor/cluster_lock.py

@@ -1,5 +1,6 @@
 """Redis-based distributed locking for cluster coordination."""
 
+import asyncio
 import logging
 import threading
 import time
@@ -7,6 +8,7 @@ from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from redis import Redis
+    from redis.asyncio import Redis as AsyncRedis
 
 logger = logging.getLogger(__name__)
 
@@ -126,3 +128,124 @@ class ClusterLock:
 
         with self._refresh_lock:
             self._last_refresh = 0.0
+
+
+class AsyncClusterLock:
+    """Async Redis-based distributed lock for preventing duplicate execution."""
+
+    def __init__(
+        self, redis: "AsyncRedis", key: str, owner_id: str, timeout: int = 300
+    ):
+        self.redis = redis
+        self.key = key
+        self.owner_id = owner_id
+        self.timeout = timeout
+        self._last_refresh = 0.0
+        self._refresh_lock = asyncio.Lock()
+
+    async def try_acquire(self) -> str | None:
+        """Try to acquire the lock.
+
+        Returns:
+            - owner_id (self.owner_id) if successfully acquired
+            - different owner_id if someone else holds the lock
+            - None if Redis is unavailable or other error
+        """
+        try:
+            success = await self.redis.set(
+                self.key, self.owner_id, nx=True, ex=self.timeout
+            )
+            if success:
+                async with self._refresh_lock:
+                    self._last_refresh = time.time()
+                return self.owner_id  # Successfully acquired
+
+            # Failed to acquire, get current owner
+            current_value = await self.redis.get(self.key)
+            if current_value:
+                current_owner = (
+                    current_value.decode("utf-8")
+                    if isinstance(current_value, bytes)
+                    else str(current_value)
+                )
+                return current_owner
+
+            # Key doesn't exist but we failed to set it - race condition or Redis issue
+            return None
+
+        except Exception as e:
+            logger.error(f"AsyncClusterLock.try_acquire failed for key {self.key}: {e}")
+            return None
+
+    async def refresh(self) -> bool:
+        """Refresh lock TTL if we still own it.
+
+        Rate limited to at most once every timeout/10 seconds (minimum 1 second).
+        During rate limiting, still verifies lock existence but skips TTL extension.
+        Setting _last_refresh to 0 bypasses rate limiting for testing.
+
+        Async-safe: uses asyncio.Lock to protect _last_refresh access.
+        """
+        # Calculate refresh interval: max(timeout // 10, 1)
+        refresh_interval = max(self.timeout // 10, 1)
+        current_time = time.time()
+
+        # Check if we're within the rate limit period (async-safe read)
+        # _last_refresh == 0 forces a refresh (bypasses rate limiting for testing)
+        async with self._refresh_lock:
+            last_refresh = self._last_refresh
+        is_rate_limited = (
+            last_refresh > 0 and (current_time - last_refresh) < refresh_interval
+        )
+
+        try:
+            # Always verify lock existence, even during rate limiting
+            current_value = await self.redis.get(self.key)
+            if not current_value:
+                async with self._refresh_lock:
+                    self._last_refresh = 0
+                return False
+
+            stored_owner = (
+                current_value.decode("utf-8")
+                if isinstance(current_value, bytes)
+                else str(current_value)
+            )
+            if stored_owner != self.owner_id:
+                async with self._refresh_lock:
+                    self._last_refresh = 0
+                return False
+
+            # If rate limited, return True but don't update TTL or timestamp
+            if is_rate_limited:
+                return True
+
+            # Perform actual refresh
+            if await self.redis.expire(self.key, self.timeout):
+                async with self._refresh_lock:
+                    self._last_refresh = current_time
+                return True
+
+            async with self._refresh_lock:
+                self._last_refresh = 0
+            return False
+
+        except Exception as e:
+            logger.error(f"AsyncClusterLock.refresh failed for key {self.key}: {e}")
+            async with self._refresh_lock:
+                self._last_refresh = 0
+            return False
+
+    async def release(self):
+        """Release the lock."""
+        async with self._refresh_lock:
+            if self._last_refresh == 0:
+                return
+
+        try:
+            await self.redis.delete(self.key)
+        except Exception:
+            pass
+
+        async with self._refresh_lock:
+            self._last_refresh = 0.0

autogpt_platform/backend/migrations/20260216120000_migrate_deprecated_gpt4_gpt35_models/migration.sql

@@ -0,0 +1,42 @@
+-- Migrate deprecated OpenAI GPT-4-turbo and GPT-3.5-turbo models
+-- This updates all AgentNode blocks that use deprecated models
+-- OpenAI is retiring these models:
+--   - gpt-4-turbo: March 26, 2026 -> migrate to gpt-4o
+--   - gpt-3.5-turbo: September 28, 2026 -> migrate to gpt-4o-mini
+
+-- Update gpt-4-turbo to gpt-4o (staying in same capability tier)
+UPDATE "AgentNode"
+SET    "constantInput" = JSONB_SET(
+         "constantInput"::jsonb,
+         '{model}',
+         '"gpt-4o"'::jsonb
+       )
+WHERE  "constantInput"::jsonb->>'model' = 'gpt-4-turbo';
+
+-- Update gpt-3.5-turbo to gpt-4o-mini (appropriate replacement for lightweight model)
+UPDATE "AgentNode"
+SET    "constantInput" = JSONB_SET(
+         "constantInput"::jsonb,
+         '{model}',
+         '"gpt-4o-mini"'::jsonb
+       )
+WHERE  "constantInput"::jsonb->>'model' = 'gpt-3.5-turbo';
+
+-- Update AgentPreset input overrides (stored in AgentNodeExecutionInputOutput)
+UPDATE "AgentNodeExecutionInputOutput"
+SET    "data" = JSONB_SET(
+         "data"::jsonb,
+         '{model}',
+         '"gpt-4o"'::jsonb
+       )
+WHERE  "agentPresetId" IS NOT NULL
+  AND  "data"::jsonb->>'model' = 'gpt-4-turbo';
+
+UPDATE "AgentNodeExecutionInputOutput"
+SET    "data" = JSONB_SET(
+         "data"::jsonb,
+         '{model}',
+         '"gpt-4o-mini"'::jsonb
+       )
+WHERE  "agentPresetId" IS NOT NULL
+  AND  "data"::jsonb->>'model' = 'gpt-3.5-turbo';

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

@@ -11,6 +11,11 @@ import {
   MessageResponse,
 } from "@/components/ai-elements/message";
 import { Text } from "@/components/atoms/Text/Text";
+import {
+  CredentialsProvidersContext,
+  type CredentialsProviderData,
+  type CredentialsProvidersContextType,
+} from "@/providers/agent-credentials/credentials-provider";
 import { CopilotChatActionsProvider } from "../components/CopilotChatActionsProvider/CopilotChatActionsProvider";
 import { CreateAgentTool } from "../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../tools/EditAgent/EditAgent";
@@ -97,6 +102,65 @@ function uid() {
   return `sg-${++_id}`;
 }
 
+// ---------------------------------------------------------------------------
+// Mock credential providers for setup-requirements demos
+// ---------------------------------------------------------------------------
+
+const noop = () => Promise.reject(new Error("Styleguide mock"));
+
+function makeMockProvider(
+  provider: string,
+  providerName: string,
+  savedCredentials: CredentialsProviderData["savedCredentials"] = [],
+): CredentialsProviderData {
+  return {
+    provider,
+    providerName,
+    savedCredentials,
+    isSystemProvider: false,
+    oAuthCallback: noop as CredentialsProviderData["oAuthCallback"],
+    mcpOAuthCallback: noop as CredentialsProviderData["mcpOAuthCallback"],
+    createAPIKeyCredentials:
+      noop as CredentialsProviderData["createAPIKeyCredentials"],
+    createUserPasswordCredentials:
+      noop as CredentialsProviderData["createUserPasswordCredentials"],
+    createHostScopedCredentials:
+      noop as CredentialsProviderData["createHostScopedCredentials"],
+    deleteCredentials: noop as CredentialsProviderData["deleteCredentials"],
+  };
+}
+
+/**
+ * Provider context where the user already has saved credentials
+ * so the credential picker shows a selection list.
+ */
+const MOCK_PROVIDERS_WITH_CREDENTIALS: CredentialsProvidersContextType = {
+  google: makeMockProvider("google", "Google", [
+    {
+      id: "cred-google-1",
+      provider: "google",
+      type: "oauth2",
+      title: "work@company.com",
+      scopes: ["email", "calendar"],
+    },
+    {
+      id: "cred-google-2",
+      provider: "google",
+      type: "oauth2",
+      title: "personal@gmail.com",
+      scopes: ["email", "calendar"],
+    },
+  ]),
+};
+
+/**
+ * Provider context where the user has NO saved credentials,
+ * so the credential picker shows an "add new" flow.
+ */
+const MOCK_PROVIDERS_WITHOUT_CREDENTIALS: CredentialsProvidersContextType = {
+  openweathermap: makeMockProvider("openweathermap", "OpenWeatherMap"),
+};
+
 // ---------------------------------------------------------------------------
 // Page
 // ---------------------------------------------------------------------------
@@ -554,45 +618,80 @@ export default function StyleguidePage() {
                 />
               </SubSection>
 
-              <SubSection label="Output available (setup requirements)">
-                <RunBlockTool
-                  part={{
-                    type: "tool-run_block",
-                    toolCallId: uid(),
-                    state: "output-available",
-                    input: { block_id: "weather-block-123" },
-                    output: {
-                      type: ResponseType.setup_requirements,
-                      message:
-                        "This block requires API credentials to run. Please configure them below.",
-                      setup_info: {
-                        agent_name: "Weather Agent",
-                        requirements: {
-                          inputs: [
-                            {
-                              name: "city",
-                              title: "City",
-                              type: "string",
-                              required: true,
-                              description: "The city to get weather for",
-                            },
-                          ],
-                        },
-                        user_readiness: {
-                          missing_credentials: {
-                            openweathermap: {
-                              provider: "openweathermap",
-                              credentials_type: "api_key",
-                              title: "OpenWeatherMap API Key",
-                              description:
-                                "Required to access weather data. Get your key at openweathermap.org",
+              <SubSection label="Setup requirements — no credentials (add new)">
+                <CredentialsProvidersContext.Provider
+                  value={MOCK_PROVIDERS_WITHOUT_CREDENTIALS}
+                >
+                  <RunBlockTool
+                    part={{
+                      type: "tool-run_block",
+                      toolCallId: uid(),
+                      state: "output-available",
+                      input: { block_id: "weather-block-123" },
+                      output: {
+                        type: ResponseType.setup_requirements,
+                        message:
+                          "This block requires API credentials to run. Please configure them below.",
+                        setup_info: {
+                          agent_id: "agent-weather-1",
+                          agent_name: "Weather Agent",
+                          requirements: {
+                            inputs: [
+                              {
+                                name: "city",
+                                title: "City",
+                                type: "string",
+                                required: true,
+                                description: "The city to get weather for",
+                              },
+                            ],
+                          },
+                          user_readiness: {
+                            missing_credentials: {
+                              openweathermap_key: {
+                                provider: "openweathermap",
+                                types: ["api_key"],
+                              },
                             },
                           },
                         },
                       },
-                    },
-                  }}
-                />
+                    }}
+                  />
+                </CredentialsProvidersContext.Provider>
+              </SubSection>
+
+              <SubSection label="Setup requirements — has credentials (pick from list)">
+                <CredentialsProvidersContext.Provider
+                  value={MOCK_PROVIDERS_WITH_CREDENTIALS}
+                >
+                  <RunBlockTool
+                    part={{
+                      type: "tool-run_block",
+                      toolCallId: uid(),
+                      state: "output-available",
+                      input: { block_id: "calendar-block-456" },
+                      output: {
+                        type: ResponseType.setup_requirements,
+                        message:
+                          "This block requires Google credentials. Pick an account below or connect a new one.",
+                        setup_info: {
+                          agent_id: "agent-calendar-1",
+                          agent_name: "Calendar Agent",
+                          user_readiness: {
+                            missing_credentials: {
+                              google_oauth: {
+                                provider: "google",
+                                types: ["oauth2"],
+                                scopes: ["email", "calendar"],
+                              },
+                            },
+                          },
+                        },
+                      },
+                    }}
+                  />
+                </CredentialsProvidersContext.Provider>
               </SubSection>
 
               <SubSection label="Output available (error)">
@@ -849,34 +948,71 @@ export default function StyleguidePage() {
                 />
               </SubSection>
 
-              <SubSection label="Output available (setup requirements)">
-                <RunAgentTool
-                  part={{
-                    type: "tool-run_agent",
-                    toolCallId: uid(),
-                    state: "output-available",
-                    input: { username_agent_slug: "creator/my-agent" },
-                    output: {
-                      type: ResponseType.setup_requirements,
-                      message: "This agent requires additional setup.",
-                      setup_info: {
-                        agent_name: "YouTube Summarizer",
-                        requirements: {},
-                        user_readiness: {
-                          missing_credentials: {
-                            youtube_api: {
-                              provider: "youtube",
-                              credentials_type: "api_key",
-                              title: "YouTube Data API Key",
-                              description:
-                                "Required to access YouTube video data.",
+              <SubSection label="Setup requirements — no credentials (add new)">
+                <CredentialsProvidersContext.Provider
+                  value={MOCK_PROVIDERS_WITHOUT_CREDENTIALS}
+                >
+                  <RunAgentTool
+                    part={{
+                      type: "tool-run_agent",
+                      toolCallId: uid(),
+                      state: "output-available",
+                      input: { username_agent_slug: "creator/weather-agent" },
+                      output: {
+                        type: ResponseType.setup_requirements,
+                        message:
+                          "This agent requires an API key. Add your credentials below.",
+                        setup_info: {
+                          agent_id: "agent-weather-1",
+                          agent_name: "Weather Agent",
+                          requirements: {},
+                          user_readiness: {
+                            missing_credentials: {
+                              openweathermap_key: {
+                                provider: "openweathermap",
+                                types: ["api_key"],
+                              },
                             },
                           },
                         },
                       },
-                    },
-                  }}
-                />
+                    }}
+                  />
+                </CredentialsProvidersContext.Provider>
+              </SubSection>
+
+              <SubSection label="Setup requirements — has credentials (pick from list)">
+                <CredentialsProvidersContext.Provider
+                  value={MOCK_PROVIDERS_WITH_CREDENTIALS}
+                >
+                  <RunAgentTool
+                    part={{
+                      type: "tool-run_agent",
+                      toolCallId: uid(),
+                      state: "output-available",
+                      input: { username_agent_slug: "creator/calendar-agent" },
+                      output: {
+                        type: ResponseType.setup_requirements,
+                        message:
+                          "This agent needs Google credentials. Pick an account or connect a new one.",
+                        setup_info: {
+                          agent_id: "agent-calendar-1",
+                          agent_name: "Google Calendar Agent",
+                          requirements: {},
+                          user_readiness: {
+                            missing_credentials: {
+                              google_oauth: {
+                                provider: "google",
+                                types: ["oauth2"],
+                                scopes: ["email", "calendar"],
+                              },
+                            },
+                          },
+                        },
+                      },
+                    }}
+                  />
+                </CredentialsProvidersContext.Provider>
               </SubSection>
 
               <SubSection label="Output available (need login)">

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

@@ -16,7 +16,6 @@ import {
   ContentCardDescription,
   ContentCodeBlock,
   ContentGrid,
-  ContentHint,
   ContentMessage,
 } from "../../components/ToolAccordion/AccordionContent";
 import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
@@ -24,8 +23,8 @@ import {
   ClarificationQuestionsCard,
   ClarifyingQuestion,
 } from "./components/ClarificationQuestionsCard";
-import sparklesImg from "./components/MiniGame/assets/sparkles.png";
-import { MiniGame } from "./components/MiniGame/MiniGame";
+import sparklesImg from "../../components/MiniGame/assets/sparkles.png";
+import { MiniGame } from "../../components/MiniGame/MiniGame";
 import { SuggestedGoalCard } from "./components/SuggestedGoalCard";
 import {
   AccordionIcon,
@@ -93,9 +92,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
   ) {
     return {
       icon,
-      title:
-        "Creating agent, this may take a few minutes. Play while you wait.",
-      expanded: true,
+      title: output.message || "Agent creation started",
     };
   }
   return {
@@ -169,15 +166,22 @@ export function CreateAgentTool({ part }: Props) {
         />
       </div>
 
+      {isStreaming && (
+        <ToolAccordion
+          icon={<AccordionIcon />}
+          title="Creating agent, this may take a few minutes. Play while you wait."
+          expanded
+        >
+          <ContentGrid>
+            <MiniGame />
+          </ContentGrid>
+        </ToolAccordion>
+      )}
+
       {hasExpandableContent && output && (
         <ToolAccordion {...getAccordionMeta(output)}>
-          {isOperating && (
-            <ContentGrid>
-              <MiniGame />
-              <ContentHint>
-                This could take a few minutes — play while you wait!
-              </ContentHint>
-            </ContentGrid>
+          {isOperating && output.message && (
+            <ContentMessage>{output.message}</ContentMessage>
           )}
 
           {isAgentSavedOutput(output) && (

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

@@ -4,17 +4,15 @@ import { WarningDiamondIcon } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
 import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
 import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
 import {
   ContentCardDescription,
   ContentCodeBlock,
   ContentGrid,
-  ContentHint,
   ContentLink,
   ContentMessage,
 } from "../../components/ToolAccordion/AccordionContent";
 import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
-import { MiniGame } from "../CreateAgent/components/MiniGame/MiniGame";
+import { MiniGame } from "../../components/MiniGame/MiniGame";
 import {
   ClarificationQuestionsCard,
   ClarifyingQuestion,
@@ -81,9 +79,8 @@ function getAccordionMeta(output: EditAgentToolOutput): {
     isOperationInProgressOutput(output)
   ) {
     return {
-      icon: <OrbitLoader size={32} />,
-      title: "Editing agent, this may take a few minutes. Play while you wait.",
-      expanded: true,
+      icon,
+      title: output.message || "Agent editing started",
     };
   }
   return {
@@ -148,15 +145,22 @@ export function EditAgentTool({ part }: Props) {
         />
       </div>
 
+      {isStreaming && (
+        <ToolAccordion
+          icon={<AccordionIcon />}
+          title="Editing agent, this may take a few minutes. Play while you wait."
+          expanded
+        >
+          <ContentGrid>
+            <MiniGame />
+          </ContentGrid>
+        </ToolAccordion>
+      )}
+
       {hasExpandableContent && output && (
         <ToolAccordion {...getAccordionMeta(output)}>
-          {isOperating && (
-            <ContentGrid>
-              <MiniGame />
-              <ContentHint>
-                This could take a few minutes — play while you wait!
-              </ContentHint>
-            </ContentGrid>
+          {isOperating && output.message && (
+            <ContentMessage>{output.message}</ContentMessage>
           )}
 
           {isAgentSavedOutput(output) && (

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

@@ -9,7 +9,7 @@ import {
   ContentHint,
   ContentMessage,
 } from "../../components/ToolAccordion/AccordionContent";
-import { MiniGame } from "../CreateAgent/components/MiniGame/MiniGame";
+import { MiniGame } from "../../components/MiniGame/MiniGame";
 import {
   getAccordionMeta,
   getAnimationText,
@@ -47,14 +47,25 @@ export function RunAgentTool({ part }: Props) {
   const isError =
     part.state === "output-error" ||
     (!!output && isRunAgentErrorOutput(output));
+  const isOutputAvailable = part.state === "output-available" && !!output;
+
+  const setupRequirementsOutput =
+    isOutputAvailable && isRunAgentSetupRequirementsOutput(output)
+      ? output
+      : null;
+
+  const agentDetailsOutput =
+    isOutputAvailable && isRunAgentAgentDetailsOutput(output) ? output : null;
+
+  const needLoginOutput =
+    isOutputAvailable && isRunAgentNeedLoginOutput(output) ? output : null;
+
   const hasExpandableContent =
-    part.state === "output-available" &&
-    !!output &&
-    (isRunAgentExecutionStartedOutput(output) ||
-      isRunAgentAgentDetailsOutput(output) ||
-      isRunAgentSetupRequirementsOutput(output) ||
-      isRunAgentNeedLoginOutput(output) ||
-      isRunAgentErrorOutput(output));
+    isOutputAvailable &&
+    !setupRequirementsOutput &&
+    !agentDetailsOutput &&
+    !needLoginOutput &&
+    (isRunAgentExecutionStartedOutput(output) || isRunAgentErrorOutput(output));
 
   return (
     <div className="py-2">
@@ -81,24 +92,30 @@ export function RunAgentTool({ part }: Props) {
         </ToolAccordion>
       )}
 
+      {setupRequirementsOutput && (
+        <div className="mt-2">
+          <SetupRequirementsCard output={setupRequirementsOutput} />
+        </div>
+      )}
+
+      {agentDetailsOutput && (
+        <div className="mt-2">
+          <AgentDetailsCard output={agentDetailsOutput} />
+        </div>
+      )}
+
+      {needLoginOutput && (
+        <div className="mt-2">
+          <ContentMessage>{needLoginOutput.message}</ContentMessage>
+        </div>
+      )}
+
       {hasExpandableContent && output && (
         <ToolAccordion {...getAccordionMeta(output)}>
           {isRunAgentExecutionStartedOutput(output) && (
             <ExecutionStartedCard output={output} />
           )}
 
-          {isRunAgentAgentDetailsOutput(output) && (
-            <AgentDetailsCard output={output} />
-          )}
-
-          {isRunAgentSetupRequirementsOutput(output) && (
-            <SetupRequirementsCard output={output} />
-          )}
-
-          {isRunAgentNeedLoginOutput(output) && (
-            <ContentMessage>{output.message}</ContentMessage>
-          )}
-
           {isRunAgentErrorOutput(output) && <ErrorCard output={output} />}
         </ToolAccordion>
       )}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/SetupRequirementsCard/SetupRequirementsCard.tsx

@@ -1,10 +1,11 @@
 "use client";
 
-import { useState } from "react";
-import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
-import { Button } from "@/components/atoms/Button/Button";
-import type { CredentialsMetaInput } from "@/lib/autogpt-server-api/types";
 import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
+import type { CredentialsMetaInput } from "@/lib/autogpt-server-api/types";
+import { useState } from "react";
 import { useCopilotChatActions } from "../../../../components/CopilotChatActionsProvider/useCopilotChatActions";
 import {
   ContentBadge,
@@ -38,40 +39,40 @@ export function SetupRequirementsCard({ output }: Props) {
     setInputCredentials((prev) => ({ ...prev, [key]: value }));
   }
 
-  const isAllComplete =
-    credentialFields.length > 0 &&
+  const needsCredentials = credentialFields.length > 0;
+  const isAllCredentialsComplete =
+    needsCredentials &&
     [...requiredCredentials].every((key) => !!inputCredentials[key]);
 
+  const canProceed =
+    !hasSent && (!needsCredentials || isAllCredentialsComplete);
+
   function handleProceed() {
     setHasSent(true);
-    onSend(
-      "I've configured the required credentials. Please check if everything is ready and proceed with running the agent.",
-    );
+    const message = needsCredentials
+      ? "I've configured the required credentials. Please check if everything is ready and proceed with running the agent."
+      : "Please proceed with running the agent.";
+    onSend(message);
   }
 
   return (
     <div className="grid gap-2">
       <ContentMessage>{output.message}</ContentMessage>
 
-      {credentialFields.length > 0 && (
+      {needsCredentials && (
         <div className="rounded-2xl border bg-background p-3">
-          <CredentialsGroupedView
-            credentialFields={credentialFields}
-            requiredCredentials={requiredCredentials}
-            inputCredentials={inputCredentials}
-            inputValues={{}}
-            onCredentialChange={handleCredentialChange}
-          />
-          {isAllComplete && !hasSent && (
-            <Button
-              variant="primary"
-              size="small"
-              className="mt-3 w-full"
-              onClick={handleProceed}
-            >
-              Proceed
-            </Button>
-          )}
+          <Text variant="small" className="w-fit border-b text-zinc-500">
+            Agent credentials
+          </Text>
+          <div className="mt-6">
+            <CredentialsGroupedView
+              credentialFields={credentialFields}
+              requiredCredentials={requiredCredentials}
+              inputCredentials={inputCredentials}
+              inputValues={{}}
+              onCredentialChange={handleCredentialChange}
+            />
+          </div>
         </div>
       )}
 
@@ -100,6 +101,18 @@ export function SetupRequirementsCard({ output }: Props) {
           </div>
         </div>
       )}
+
+      {(needsCredentials || expectedInputs.length > 0) && (
+        <Button
+          variant="primary"
+          size="small"
+          className="mt-4 w-fit"
+          disabled={!canProceed}
+          onClick={handleProceed}
+        >
+          Proceed
+        </Button>
+      )}
     </div>
   );
 }

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

@@ -39,12 +39,19 @@ export function RunBlockTool({ part }: Props) {
   const isError =
     part.state === "output-error" ||
     (!!output && isRunBlockErrorOutput(output));
+  const setupRequirementsOutput =
+    part.state === "output-available" &&
+    output &&
+    isRunBlockSetupRequirementsOutput(output)
+      ? output
+      : null;
+
   const hasExpandableContent =
     part.state === "output-available" &&
     !!output &&
+    !setupRequirementsOutput &&
     (isRunBlockBlockOutput(output) ||
       isRunBlockDetailsOutput(output) ||
-      isRunBlockSetupRequirementsOutput(output) ||
       isRunBlockErrorOutput(output));
 
   return (
@@ -57,6 +64,12 @@ export function RunBlockTool({ part }: Props) {
         />
       </div>
 
+      {setupRequirementsOutput && (
+        <div className="mt-2">
+          <SetupRequirementsCard output={setupRequirementsOutput} />
+        </div>
+      )}
+
       {hasExpandableContent && output && (
         <ToolAccordion {...getAccordionMeta(output)}>
           {isRunBlockBlockOutput(output) && <BlockOutputCard output={output} />}
@@ -65,10 +78,6 @@ export function RunBlockTool({ part }: Props) {
             <BlockDetailsCard output={output} />
           )}
 
-          {isRunBlockSetupRequirementsOutput(output) && (
-            <SetupRequirementsCard output={output} />
-          )}
-
           {isRunBlockErrorOutput(output) && <ErrorCard output={output} />}
         </ToolAccordion>
       )}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/components/SetupRequirementsCard/SetupRequirementsCard.tsx

@@ -6,15 +6,9 @@ import { Text } from "@/components/atoms/Text/Text";
 import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
 import { FormRenderer } from "@/components/renderers/InputRenderer/FormRenderer";
 import type { CredentialsMetaInput } from "@/lib/autogpt-server-api/types";
-import { AnimatePresence, motion } from "framer-motion";
 import { useState } from "react";
 import { useCopilotChatActions } from "../../../../components/CopilotChatActionsProvider/useCopilotChatActions";
-import {
-  ContentBadge,
-  ContentCardDescription,
-  ContentCardTitle,
-  ContentMessage,
-} from "../../../../components/ToolAccordion/AccordionContent";
+import { ContentMessage } from "../../../../components/ToolAccordion/AccordionContent";
 import {
   buildExpectedInputsSchema,
   coerceCredentialFields,
@@ -31,10 +25,8 @@ export function SetupRequirementsCard({ output }: Props) {
   const [inputCredentials, setInputCredentials] = useState<
     Record<string, CredentialsMetaInput | undefined>
   >({});
-  const [hasSentCredentials, setHasSentCredentials] = useState(false);
-
-  const [showInputForm, setShowInputForm] = useState(false);
   const [inputValues, setInputValues] = useState<Record<string, unknown>>({});
+  const [hasSent, setHasSent] = useState(false);
 
   const { credentialFields, requiredCredentials } = coerceCredentialFields(
     output.setup_info.user_readiness?.missing_credentials,
@@ -50,27 +42,49 @@ export function SetupRequirementsCard({ output }: Props) {
     setInputCredentials((prev) => ({ ...prev, [key]: value }));
   }
 
+  const needsCredentials = credentialFields.length > 0;
   const isAllCredentialsComplete =
-    credentialFields.length > 0 &&
+    needsCredentials &&
     [...requiredCredentials].every((key) => !!inputCredentials[key]);
 
-  function handleProceedCredentials() {
-    setHasSentCredentials(true);
-    onSend(
-      "I've configured the required credentials. Please re-run the block now.",
-    );
-  }
+  const needsInputs = inputSchema !== null;
+  const requiredInputNames = expectedInputs
+    .filter((i) => i.required)
+    .map((i) => i.name);
+  const isAllInputsComplete =
+    needsInputs &&
+    requiredInputNames.every((name) => {
+      const v = inputValues[name];
+      return v !== undefined && v !== null && v !== "";
+    });
 
-  function handleRunWithInputs() {
-    const nonEmpty = Object.fromEntries(
-      Object.entries(inputValues).filter(
-        ([, v]) => v !== undefined && v !== null && v !== "",
-      ),
-    );
-    onSend(
-      `Run the block with these inputs: ${JSON.stringify(nonEmpty, null, 2)}`,
-    );
-    setShowInputForm(false);
+  const canRun =
+    !hasSent &&
+    (!needsCredentials || isAllCredentialsComplete) &&
+    (!needsInputs || isAllInputsComplete);
+
+  function handleRun() {
+    setHasSent(true);
+
+    const parts: string[] = [];
+    if (needsCredentials) {
+      parts.push("I've configured the required credentials.");
+    }
+
+    if (needsInputs) {
+      const nonEmpty = Object.fromEntries(
+        Object.entries(inputValues).filter(
+          ([, v]) => v !== undefined && v !== null && v !== "",
+        ),
+      );
+      parts.push(
+        `Run the block with these inputs: ${JSON.stringify(nonEmpty, null, 2)}`,
+      );
+    } else {
+      parts.push("Please re-run the block now.");
+    }
+
+    onSend(parts.join(" "));
     setInputValues({});
   }
 
@@ -78,119 +92,54 @@ export function SetupRequirementsCard({ output }: Props) {
     <div className="grid gap-2">
       <ContentMessage>{output.message}</ContentMessage>
 
-      {credentialFields.length > 0 && (
+      {needsCredentials && (
         <div className="rounded-2xl border bg-background p-3">
-          <CredentialsGroupedView
-            credentialFields={credentialFields}
-            requiredCredentials={requiredCredentials}
-            inputCredentials={inputCredentials}
-            inputValues={{}}
-            onCredentialChange={handleCredentialChange}
-          />
-          {isAllCredentialsComplete && !hasSentCredentials && (
-            <Button
-              variant="primary"
-              size="small"
-              className="mt-3 w-full"
-              onClick={handleProceedCredentials}
-            >
-              Proceed
-            </Button>
-          )}
+          <Text variant="small" className="w-fit border-b text-zinc-500">
+            Block credentials
+          </Text>
+          <div className="mt-6">
+            <CredentialsGroupedView
+              credentialFields={credentialFields}
+              requiredCredentials={requiredCredentials}
+              inputCredentials={inputCredentials}
+              inputValues={{}}
+              onCredentialChange={handleCredentialChange}
+            />
+          </div>
         </div>
       )}
 
       {inputSchema && (
-        <div className="flex gap-2 pt-2">
-          <Button
-            variant="outline"
-            size="small"
-            className="w-fit"
-            onClick={() => setShowInputForm((prev) => !prev)}
-          >
-            {showInputForm ? "Hide inputs" : "Fill in inputs"}
-          </Button>
+        <div className="rounded-2xl border bg-background p-3 pt-4">
+          <Text variant="small" className="w-fit border-b text-zinc-500">
+            Block inputs
+          </Text>
+          <FormRenderer
+            jsonSchema={inputSchema}
+            className="mb-3 mt-3"
+            handleChange={(v) => setInputValues(v.formData ?? {})}
+            uiSchema={{
+              "ui:submitButtonOptions": { norender: true },
+            }}
+            initialValues={inputValues}
+            formContext={{
+              showHandles: false,
+              size: "small",
+            }}
+          />
         </div>
       )}
 
-      <AnimatePresence initial={false}>
-        {showInputForm && inputSchema && (
-          <motion.div
-            initial={{ height: 0, opacity: 0, filter: "blur(6px)" }}
-            animate={{ height: "auto", opacity: 1, filter: "blur(0px)" }}
-            exit={{ height: 0, opacity: 0, filter: "blur(6px)" }}
-            transition={{
-              height: { type: "spring", bounce: 0.15, duration: 0.5 },
-              opacity: { duration: 0.25 },
-              filter: { duration: 0.2 },
-            }}
-            className="overflow-hidden"
-            style={{ willChange: "height, opacity, filter" }}
-          >
-            <div className="rounded-2xl border bg-background p-3 pt-4">
-              <Text variant="body-medium">Block inputs</Text>
-              <FormRenderer
-                jsonSchema={inputSchema}
-                handleChange={(v) => setInputValues(v.formData ?? {})}
-                uiSchema={{
-                  "ui:submitButtonOptions": { norender: true },
-                }}
-                initialValues={inputValues}
-                formContext={{
-                  showHandles: false,
-                  size: "small",
-                }}
-              />
-              <div className="-mt-8 flex gap-2">
-                <Button
-                  variant="primary"
-                  size="small"
-                  className="w-fit"
-                  onClick={handleRunWithInputs}
-                >
-                  Run
-                </Button>
-                <Button
-                  variant="secondary"
-                  size="small"
-                  className="w-fit"
-                  onClick={() => {
-                    setShowInputForm(false);
-                    setInputValues({});
-                  }}
-                >
-                  Cancel
-                </Button>
-              </div>
-            </div>
-          </motion.div>
-        )}
-      </AnimatePresence>
-
-      {expectedInputs.length > 0 && !inputSchema && (
-        <div className="rounded-2xl border bg-background p-3">
-          <ContentCardTitle className="text-xs">
-            Expected inputs
-          </ContentCardTitle>
-          <div className="mt-2 grid gap-2">
-            {expectedInputs.map((input) => (
-              <div key={input.name} className="rounded-xl border p-2">
-                <div className="flex items-center justify-between gap-2">
-                  <ContentCardTitle className="text-xs">
-                    {input.title}
-                  </ContentCardTitle>
-                  <ContentBadge>
-                    {input.required ? "Required" : "Optional"}
-                  </ContentBadge>
-                </div>
-                <ContentCardDescription className="mt-1">
-                  {input.name} &bull; {input.type}
-                  {input.description ? ` \u2022 ${input.description}` : ""}
-                </ContentCardDescription>
-              </div>
-            ))}
-          </div>
-        </div>
+      {(needsCredentials || needsInputs) && (
+        <Button
+          variant="primary"
+          size="small"
+          className="w-fit"
+          disabled={!canRun}
+          onClick={handleRun}
+        >
+          Proceed
+        </Button>
       )}
     </div>
   );

autogpt_platform/frontend/src/components/contextual/CredentialsInput/components/CredentialsFlatView/CredentialsFlatView.tsx

@@ -119,7 +119,7 @@ export function CredentialsFlatView({
       ) : (
         !readOnly && (
           <Button
-            variant="secondary"
+            variant="primary"
             size="small"
             onClick={onAddCredential}
             className="w-fit"

autogpt_platform/frontend/src/components/renderers/InputRenderer/FormRenderer.tsx

@@ -1,10 +1,11 @@
+import { cn } from "@/lib/utils";
 import { RJSFSchema } from "@rjsf/utils";
-import { preprocessInputSchema } from "./utils/input-schema-pre-processor";
 import { useMemo } from "react";
-import { customValidator } from "./utils/custom-validator";
 import Form from "./registry";
 import { ExtendedFormContextType } from "./types";
+import { customValidator } from "./utils/custom-validator";
 import { generateUiSchemaForCustomFields } from "./utils/generate-ui-schema";
+import { preprocessInputSchema } from "./utils/input-schema-pre-processor";
 
 type FormRendererProps = {
   jsonSchema: RJSFSchema;
@@ -12,15 +13,17 @@ type FormRendererProps = {
   uiSchema: any;
   initialValues: any;
   formContext: ExtendedFormContextType;
+  className?: string;
 };
 
-export const FormRenderer = ({
+export function FormRenderer({
   jsonSchema,
   handleChange,
   uiSchema,
   initialValues,
   formContext,
-}: FormRendererProps) => {
+  className,
+}: FormRendererProps) {
   const preprocessedSchema = useMemo(() => {
     return preprocessInputSchema(jsonSchema);
   }, [jsonSchema]);
@@ -31,7 +34,10 @@ export const FormRenderer = ({
   }, [preprocessedSchema, uiSchema]);
 
   return (
-    <div className={"mb-6 mt-4"} data-tutorial-id="input-handles">
+    <div
+      className={cn("mb-6 mt-4", className)}
+      data-tutorial-id="input-handles"
+    >
       <Form
         formContext={formContext}
         idPrefix="agpt"
@@ -45,4 +51,4 @@ export const FormRenderer = ({
       />
     </div>
   );
-};
+}

docs/integrations/block-integrations/llm.md

@@ -65,7 +65,7 @@ The result routes data to yes_output or no_output, enabling intelligent branchin
 | condition | A plaintext English description of the condition to evaluate | str | Yes |
 | yes_value | (Optional) Value to output if the condition is true. If not provided, input_value will be used. | Yes Value | No |
 | no_value | (Optional) Value to output if the condition is false. If not provided, input_value will be used. | No Value | No |
-| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 
 ### Outputs
 
@@ -103,7 +103,7 @@ The block sends the entire conversation history to the chosen LLM, including sys
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. | str | No |
 | messages | List of messages in the conversation. | List[Any] | Yes |
-| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
 | ollama_host | Ollama host for local  models | str | No |
 
@@ -257,7 +257,7 @@ The block formulates a prompt based on the given focus or source data, sends it
 |-------|-------------|------|----------|
 | focus | The focus of the list to generate. | str | No |
 | source_data | The data to generate the list from. | str | No |
-| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | max_retries | Maximum number of retries for generating a valid list. | int | No |
 | force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -424,7 +424,7 @@ The block sends the input prompt to a chosen LLM, along with any system prompts
 | prompt | The prompt to send to the language model. | str | Yes |
 | expected_format | Expected format of the response. If provided, the response will be validated against this format. The keys should be the expected fields in the response, and the values should be the description of the field. | Dict[str, str] | Yes |
 | list_result | Whether the response should be a list of objects in the expected format. | bool | No |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |
@@ -464,7 +464,7 @@ The block sends the input prompt to a chosen LLM, processes the response, and re
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. You can use any of the {keys} from Prompt Values to fill in the prompt with values from the prompt values dictionary by putting them in curly braces. | str | Yes |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | retry | Number of times to retry the LLM call if the response does not match the expected format. | int | No |
 | prompt_values | Values used to fill in the prompt. The values can be used in the prompt by putting them in a double curly braces, e.g. {{variable_name}}. | Dict[str, str] | No |
@@ -501,7 +501,7 @@ The block splits the input text into smaller chunks, sends each chunk to an LLM
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | text | The text to summarize. | str | Yes |
-| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | focus | The topic to focus on in the summary | str | No |
 | style | The style of the summary to generate. | "concise" \| "detailed" \| "bullet points" \| "numbered list" | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -763,7 +763,7 @@ Configure agent_mode_max_iterations to control loop behavior: 0 for single decis
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. | str | Yes |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | multiple_tool_calls | Whether to allow multiple tool calls in a single response. | bool | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |

docs/platform/getting-started.md

@@ -218,6 +218,17 @@ If you initially installed Docker with Hyper-V, you **don’t need to reinstall*
 
 For more details, refer to [Docker's official documentation](https://docs.docker.com/desktop/windows/wsl/).
 
+### ⚠️ Podman Not Supported
+
+AutoGPT requires **Docker** (Docker Desktop or Docker Engine). **Podman and podman-compose are not supported** and may cause path resolution issues, particularly on Windows.
+
+If you see errors like:
+```text
+Error: the specified Containerfile or Dockerfile does not exist, ..\..\autogpt_platform\backend\Dockerfile
+```
+
+This indicates you're using Podman instead of Docker. Please install [Docker Desktop](https://docs.docker.com/desktop/) and use `docker compose` instead of `podman-compose`.
+
 
 ## Development