docs(blocks): update video block documentation

- Remove deprecated output_return_type parameter
- Add model_id parameter to narration block

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

autogpt_platform/backend/.env.default

@@ -152,6 +152,7 @@ REPLICATE_API_KEY=
 REVID_API_KEY=
 SCREENSHOTONE_API_KEY=
 UNREAL_SPEECH_API_KEY=
+ELEVENLABS_API_KEY=
 
 # Data & Search Services
 E2B_API_KEY=

autogpt_platform/backend/Dockerfile

@@ -62,10 +62,11 @@ ENV POETRY_HOME=/opt/poetry \
     DEBIAN_FRONTEND=noninteractive
 ENV PATH=/opt/poetry/bin:$PATH
 
-# Install Python without upgrading system-managed packages
+# Install Python and FFmpeg (required for video processing blocks)
 RUN apt-get update && apt-get install -y \
     python3.13 \
     python3-pip \
+    ffmpeg \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy only necessary files from builder

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

@@ -1,11 +1,10 @@
 """Shared agent search functionality for find_agent and find_library_agent tools."""
 
 import logging
-from typing import Any, Literal
+from typing import Literal
 
 from backend.api.features.library import db as library_db
 from backend.api.features.store import db as store_db
-from backend.data.graph import get_graph
 from backend.util.exceptions import DatabaseError, NotFoundError
 
 from .models import (
@@ -15,39 +14,12 @@ from .models import (
     NoResultsResponse,
     ToolResponseBase,
 )
-from .utils import fetch_graph_from_store_slug
 
 logger = logging.getLogger(__name__)
 
 SearchSource = Literal["marketplace", "library"]
 
 
-async def _fetch_input_schema_for_store_agent(
-    creator: str, slug: str
-) -> dict[str, Any] | None:
-    """Fetch input schema for a marketplace agent. Returns None on error."""
-    try:
-        graph, _ = await fetch_graph_from_store_slug(creator, slug)
-        if graph and graph.input_schema:
-            return graph.input_schema.get("properties", {})
-    except Exception as e:
-        logger.debug(f"Could not fetch input schema for {creator}/{slug}: {e}")
-    return None
-
-
-async def _fetch_input_schema_for_library_agent(
-    graph_id: str, graph_version: int, user_id: str
-) -> dict[str, Any] | None:
-    """Fetch input schema for a library agent. Returns None on error."""
-    try:
-        graph = await get_graph(graph_id, graph_version, user_id=user_id)
-        if graph and graph.input_schema:
-            return graph.input_schema.get("properties", {})
-    except Exception as e:
-        logger.debug(f"Could not fetch input schema for graph {graph_id}: {e}")
-    return None
-
-
 async def search_agents(
     query: str,
     source: SearchSource,
@@ -83,10 +55,6 @@ async def search_agents(
             logger.info(f"Searching marketplace for: {query}")
             results = await store_db.get_store_agents(search_query=query, page_size=5)
             for agent in results.agents:
-                # Fetch input schema for this agent
-                inputs = await _fetch_input_schema_for_store_agent(
-                    agent.creator, agent.slug
-                )
                 agents.append(
                     AgentInfo(
                         id=f"{agent.creator}/{agent.slug}",
@@ -99,7 +67,6 @@ async def search_agents(
                         rating=agent.rating,
                         runs=agent.runs,
                         is_featured=False,
-                        inputs=inputs,
                     )
                 )
         else:  # library
@@ -110,10 +77,6 @@ async def search_agents(
                 page_size=10,
             )
             for agent in results.agents:
-                # Fetch input schema for this agent
-                inputs = await _fetch_input_schema_for_library_agent(
-                    agent.graph_id, agent.graph_version, user_id  # type: ignore[arg-type]
-                )
                 agents.append(
                     AgentInfo(
                         id=agent.id,
@@ -127,7 +90,6 @@ async def search_agents(
                         has_external_trigger=agent.has_external_trigger,
                         new_output=agent.new_output,
                         graph_id=agent.graph_id,
-                        inputs=inputs,
                     )
                 )
         logger.info(f"Found {len(agents)} agents in {source}")

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

@@ -68,10 +68,6 @@ class AgentInfo(BaseModel):
     has_external_trigger: bool | None = None
     new_output: bool | None = None
     graph_id: str | None = None
-    inputs: dict[str, Any] | None = Field(
-        default=None,
-        description="Input schema for the agent (properties from input_schema)",
-    )
 
 
 class AgentsFoundResponse(ToolResponseBase):

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

@@ -273,27 +273,6 @@ class RunAgentTool(BaseTool):
             input_properties = graph.input_schema.get("properties", {})
             required_fields = set(graph.input_schema.get("required", []))
             provided_inputs = set(params.inputs.keys())
-            valid_fields = set(input_properties.keys())
-
-            # Check for unknown fields - reject early with helpful message
-            unknown_fields = provided_inputs - valid_fields
-            if unknown_fields:
-                valid_list = ", ".join(sorted(valid_fields)) if valid_fields else "none"
-                return AgentDetailsResponse(
-                    message=(
-                        f"Unknown input field(s) provided: {', '.join(sorted(unknown_fields))}. "
-                        f"Valid fields for '{graph.name}': {valid_list}. "
-                        "Please check the field names and try again."
-                    ),
-                    session_id=session_id,
-                    agent=self._build_agent_details(
-                        graph,
-                        extract_credentials_from_schema(graph.credentials_input_schema),
-                    ),
-                    user_authenticated=True,
-                    graph_id=graph.id,
-                    graph_version=graph.version,
-                )
 
             # If agent has inputs but none were provided AND use_defaults is not set,
             # always show what's available first so user can decide

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

@@ -8,7 +8,7 @@ from backend.api.features.library import model as library_model
 from backend.api.features.store import db as store_db
 from backend.data import graph as graph_db
 from backend.data.graph import GraphModel
-from backend.data.model import Credentials, CredentialsFieldInfo, CredentialsMetaInput
+from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import NotFoundError
 
@@ -266,14 +266,13 @@ async def match_user_credentials_to_graph(
         credential_requirements,
         _node_fields,
     ) in aggregated_creds.items():
-        # Find first matching credential by provider, type, and scopes
+        # Find first matching credential by provider and type
         matching_cred = next(
             (
                 cred
                 for cred in available_creds
                 if cred.provider in credential_requirements.provider
                 and cred.type in credential_requirements.supported_types
-                and _credential_has_required_scopes(cred, credential_requirements)
             ),
             None,
         )
@@ -297,17 +296,10 @@ async def match_user_credentials_to_graph(
                     f"{credential_field_name} (validation failed: {e})"
                 )
         else:
-            # Build a helpful error message including scope requirements
-            error_parts = [
-                f"provider in {list(credential_requirements.provider)}",
-                f"type in {list(credential_requirements.supported_types)}",
-            ]
-            if credential_requirements.required_scopes:
-                error_parts.append(
-                    f"scopes including {list(credential_requirements.required_scopes)}"
-                )
             missing_creds.append(
-                f"{credential_field_name} (requires {', '.join(error_parts)})"
+                f"{credential_field_name} "
+                f"(requires provider in {list(credential_requirements.provider)}, "
+                f"type in {list(credential_requirements.supported_types)})"
             )
 
     logger.info(
@@ -317,28 +309,6 @@ async def match_user_credentials_to_graph(
     return graph_credentials_inputs, missing_creds
 
 
-def _credential_has_required_scopes(
-    credential: Credentials,
-    requirements: CredentialsFieldInfo,
-) -> bool:
-    """
-    Check if a credential has all the scopes required by the block.
-
-    For OAuth2 credentials, verifies that the credential's scopes are a superset
-    of the required scopes. For other credential types, returns True (no scope check).
-    """
-    # Only OAuth2 credentials have scopes to check
-    if credential.type != "oauth2":
-        return True
-
-    # If no scopes are required, any credential matches
-    if not requirements.required_scopes:
-        return True
-
-    # Check that credential scopes are a superset of required scopes
-    return set(credential.scopes).issuperset(requirements.required_scopes)
-
-
 async def check_user_has_required_credentials(
     user_id: str,
     required_credentials: list[CredentialsMetaInput],

autogpt_platform/backend/backend/blocks/elevenlabs/_auth.py

@@ -0,0 +1,28 @@
+"""ElevenLabs integration blocks - test credentials and shared utilities."""
+
+from typing import Literal
+
+from pydantic import SecretStr
+
+from backend.data.model import APIKeyCredentials, CredentialsMetaInput
+from backend.integrations.providers import ProviderName
+
+TEST_CREDENTIALS = APIKeyCredentials(
+    id="01234567-89ab-cdef-0123-456789abcdef",
+    provider="elevenlabs",
+    api_key=SecretStr("mock-elevenlabs-api-key"),
+    title="Mock ElevenLabs API key",
+    expires_at=None,
+)
+
+TEST_CREDENTIALS_INPUT = {
+    "provider": TEST_CREDENTIALS.provider,
+    "id": TEST_CREDENTIALS.id,
+    "type": TEST_CREDENTIALS.type,
+    "title": TEST_CREDENTIALS.title,
+}
+
+ElevenLabsCredentials = APIKeyCredentials
+ElevenLabsCredentialsInput = CredentialsMetaInput[
+    Literal[ProviderName.ELEVENLABS], Literal["api_key"]
+]

autogpt_platform/backend/backend/blocks/llm.py

@@ -115,6 +115,7 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     CLAUDE_4_5_OPUS = "claude-opus-4-5-20251101"
     CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
     CLAUDE_4_5_HAIKU = "claude-haiku-4-5-20251001"
+    CLAUDE_3_7_SONNET = "claude-3-7-sonnet-20250219"
     CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
     # AI/ML API models
     AIML_API_QWEN2_5_72B = "Qwen/Qwen2.5-72B-Instruct-Turbo"
@@ -279,6 +280,9 @@ MODEL_METADATA = {
     LlmModel.CLAUDE_4_5_HAIKU: ModelMetadata(
         "anthropic", 200000, 64000, "Claude Haiku 4.5", "Anthropic", "Anthropic", 2
     ),  # claude-haiku-4-5-20251001
+    LlmModel.CLAUDE_3_7_SONNET: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude 3.7 Sonnet", "Anthropic", "Anthropic", 2
+    ),  # claude-3-7-sonnet-20250219
     LlmModel.CLAUDE_3_HAIKU: ModelMetadata(
         "anthropic", 200000, 4096, "Claude 3 Haiku", "Anthropic", "Anthropic", 1
     ),  # claude-3-haiku-20240307

autogpt_platform/backend/backend/blocks/media.py

@@ -1,246 +0,0 @@
-import os
-import tempfile
-from typing import Optional
-
-from moviepy.audio.io.AudioFileClip import AudioFileClip
-from moviepy.video.fx.Loop import Loop
-from moviepy.video.io.VideoFileClip import VideoFileClip
-
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
-from backend.data.execution import ExecutionContext
-from backend.data.model import SchemaField
-from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
-
-
-class MediaDurationBlock(Block):
-
-    class Input(BlockSchemaInput):
-        media_in: MediaFileType = SchemaField(
-            description="Media input (URL, data URI, or local path)."
-        )
-        is_video: bool = SchemaField(
-            description="Whether the media is a video (True) or audio (False).",
-            default=True,
-        )
-
-    class Output(BlockSchemaOutput):
-        duration: float = SchemaField(
-            description="Duration of the media file (in seconds)."
-        )
-
-    def __init__(self):
-        super().__init__(
-            id="d8b91fd4-da26-42d4-8ecb-8b196c6d84b6",
-            description="Block to get the duration of a media file.",
-            categories={BlockCategory.MULTIMEDIA},
-            input_schema=MediaDurationBlock.Input,
-            output_schema=MediaDurationBlock.Output,
-        )
-
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ) -> BlockOutput:
-        # 1) Store the input media locally
-        local_media_path = await store_media_file(
-            file=input_data.media_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
-        )
-        assert execution_context.graph_exec_id is not None
-        media_abspath = get_exec_file_path(
-            execution_context.graph_exec_id, local_media_path
-        )
-
-        # 2) Load the clip
-        if input_data.is_video:
-            clip = VideoFileClip(media_abspath)
-        else:
-            clip = AudioFileClip(media_abspath)
-
-        yield "duration", clip.duration
-
-
-class LoopVideoBlock(Block):
-    """
-    Block for looping (repeating) a video clip until a given duration or number of loops.
-    """
-
-    class Input(BlockSchemaInput):
-        video_in: MediaFileType = SchemaField(
-            description="The input video (can be a URL, data URI, or local path)."
-        )
-        # Provide EITHER a `duration` or `n_loops` or both. We'll demonstrate `duration`.
-        duration: Optional[float] = SchemaField(
-            description="Target duration (in seconds) to loop the video to. If omitted, defaults to no looping.",
-            default=None,
-            ge=0.0,
-        )
-        n_loops: Optional[int] = SchemaField(
-            description="Number of times to repeat the video. If omitted, defaults to 1 (no repeat).",
-            default=None,
-            ge=1,
-        )
-
-    class Output(BlockSchemaOutput):
-        video_out: str = SchemaField(
-            description="Looped video returned either as a relative path or a data URI."
-        )
-
-    def __init__(self):
-        super().__init__(
-            id="8bf9eef6-5451-4213-b265-25306446e94b",
-            description="Block to loop a video to a given duration or number of repeats.",
-            categories={BlockCategory.MULTIMEDIA},
-            input_schema=LoopVideoBlock.Input,
-            output_schema=LoopVideoBlock.Output,
-        )
-
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ) -> BlockOutput:
-        assert execution_context.graph_exec_id is not None
-        assert execution_context.node_exec_id is not None
-        graph_exec_id = execution_context.graph_exec_id
-        node_exec_id = execution_context.node_exec_id
-
-        # 1) Store the input video locally
-        local_video_path = await store_media_file(
-            file=input_data.video_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
-        )
-        input_abspath = get_exec_file_path(graph_exec_id, local_video_path)
-
-        # 2) Load the clip
-        clip = VideoFileClip(input_abspath)
-
-        # 3) Apply the loop effect
-        looped_clip = clip
-        if input_data.duration:
-            # Loop until we reach the specified duration
-            looped_clip = looped_clip.with_effects([Loop(duration=input_data.duration)])
-        elif input_data.n_loops:
-            looped_clip = looped_clip.with_effects([Loop(n=input_data.n_loops)])
-        else:
-            raise ValueError("Either 'duration' or 'n_loops' must be provided.")
-
-        assert isinstance(looped_clip, VideoFileClip)
-
-        # 4) Save the looped output
-        output_filename = MediaFileType(
-            f"{node_exec_id}_looped_{os.path.basename(local_video_path)}"
-        )
-        output_abspath = get_exec_file_path(graph_exec_id, output_filename)
-
-        looped_clip = looped_clip.with_audio(clip.audio)
-        looped_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
-
-        # Return output - for_block_output returns workspace:// if available, else data URI
-        video_out = await store_media_file(
-            file=output_filename,
-            execution_context=execution_context,
-            return_format="for_block_output",
-        )
-
-        yield "video_out", video_out
-
-
-class AddAudioToVideoBlock(Block):
-    """
-    Block that adds (attaches) an audio track to an existing video.
-    Optionally scale the volume of the new track.
-    """
-
-    class Input(BlockSchemaInput):
-        video_in: MediaFileType = SchemaField(
-            description="Video input (URL, data URI, or local path)."
-        )
-        audio_in: MediaFileType = SchemaField(
-            description="Audio input (URL, data URI, or local path)."
-        )
-        volume: float = SchemaField(
-            description="Volume scale for the newly attached audio track (1.0 = original).",
-            default=1.0,
-        )
-
-    class Output(BlockSchemaOutput):
-        video_out: MediaFileType = SchemaField(
-            description="Final video (with attached audio), as a path or data URI."
-        )
-
-    def __init__(self):
-        super().__init__(
-            id="3503748d-62b6-4425-91d6-725b064af509",
-            description="Block to attach an audio file to a video file using moviepy.",
-            categories={BlockCategory.MULTIMEDIA},
-            input_schema=AddAudioToVideoBlock.Input,
-            output_schema=AddAudioToVideoBlock.Output,
-        )
-
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ) -> BlockOutput:
-        assert execution_context.graph_exec_id is not None
-        assert execution_context.node_exec_id is not None
-        graph_exec_id = execution_context.graph_exec_id
-        node_exec_id = execution_context.node_exec_id
-
-        # 1) Store the inputs locally
-        local_video_path = await store_media_file(
-            file=input_data.video_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
-        )
-        local_audio_path = await store_media_file(
-            file=input_data.audio_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
-        )
-
-        abs_temp_dir = os.path.join(tempfile.gettempdir(), "exec_file", graph_exec_id)
-        video_abspath = os.path.join(abs_temp_dir, local_video_path)
-        audio_abspath = os.path.join(abs_temp_dir, local_audio_path)
-
-        # 2) Load video + audio with moviepy
-        video_clip = VideoFileClip(video_abspath)
-        audio_clip = AudioFileClip(audio_abspath)
-        # Optionally scale volume
-        if input_data.volume != 1.0:
-            audio_clip = audio_clip.with_volume_scaled(input_data.volume)
-
-        # 3) Attach the new audio track
-        final_clip = video_clip.with_audio(audio_clip)
-
-        # 4) Write to output file
-        output_filename = MediaFileType(
-            f"{node_exec_id}_audio_attached_{os.path.basename(local_video_path)}"
-        )
-        output_abspath = os.path.join(abs_temp_dir, output_filename)
-        final_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
-
-        # 5) Return output - for_block_output returns workspace:// if available, else data URI
-        video_out = await store_media_file(
-            file=output_filename,
-            execution_context=execution_context,
-            return_format="for_block_output",
-        )
-
-        yield "video_out", video_out

autogpt_platform/backend/backend/blocks/stagehand/blocks.py

@@ -83,7 +83,7 @@ class StagehandRecommendedLlmModel(str, Enum):
     GPT41_MINI = "gpt-4.1-mini-2025-04-14"
 
     # Anthropic
-    CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
+    CLAUDE_3_7_SONNET = "claude-3-7-sonnet-20250219"
 
     @property
     def provider_name(self) -> str:
@@ -137,7 +137,7 @@ class StagehandObserveBlock(Block):
         model: StagehandRecommendedLlmModel = SchemaField(
             title="LLM Model",
             description="LLM to use for Stagehand (provider is inferred)",
-            default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
+            default=StagehandRecommendedLlmModel.CLAUDE_3_7_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()
@@ -230,7 +230,7 @@ class StagehandActBlock(Block):
         model: StagehandRecommendedLlmModel = SchemaField(
             title="LLM Model",
             description="LLM to use for Stagehand (provider is inferred)",
-            default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
+            default=StagehandRecommendedLlmModel.CLAUDE_3_7_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()
@@ -330,7 +330,7 @@ class StagehandExtractBlock(Block):
         model: StagehandRecommendedLlmModel = SchemaField(
             title="LLM Model",
             description="LLM to use for Stagehand (provider is inferred)",
-            default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
+            default=StagehandRecommendedLlmModel.CLAUDE_3_7_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()

autogpt_platform/backend/backend/blocks/video/__init__.py

@@ -0,0 +1,37 @@
+"""Video editing blocks for AutoGPT Platform.
+
+This module provides blocks for:
+- Downloading videos from URLs (YouTube, Vimeo, news sites, direct links)
+- Clipping/trimming video segments
+- Concatenating multiple videos
+- Adding text overlays
+- Adding AI-generated narration
+- Getting media duration
+- Looping videos
+- Adding audio to videos
+
+Dependencies:
+- yt-dlp: For video downloading
+- moviepy: For video editing operations
+- elevenlabs: For AI narration (optional)
+"""
+
+from backend.blocks.video.add_audio import AddAudioToVideoBlock
+from backend.blocks.video.clip import VideoClipBlock
+from backend.blocks.video.concat import VideoConcatBlock
+from backend.blocks.video.download import VideoDownloadBlock
+from backend.blocks.video.duration import MediaDurationBlock
+from backend.blocks.video.loop import LoopVideoBlock
+from backend.blocks.video.narration import VideoNarrationBlock
+from backend.blocks.video.text_overlay import VideoTextOverlayBlock
+
+__all__ = [
+    "AddAudioToVideoBlock",
+    "LoopVideoBlock",
+    "MediaDurationBlock",
+    "VideoClipBlock",
+    "VideoConcatBlock",
+    "VideoDownloadBlock",
+    "VideoNarrationBlock",
+    "VideoTextOverlayBlock",
+]

autogpt_platform/backend/backend/blocks/video/_utils.py

@@ -0,0 +1,34 @@
+"""Shared utilities for video blocks."""
+
+import os
+
+
+def get_video_codecs(output_path: str) -> tuple[str, str]:
+    """Get appropriate video and audio codecs based on output file extension.
+
+    Args:
+        output_path: Path to the output file (used to determine extension)
+
+    Returns:
+        Tuple of (video_codec, audio_codec)
+
+    Codec mappings:
+        - .mp4: H.264 + AAC (universal compatibility)
+        - .webm: VP8 + Vorbis (web streaming)
+        - .mkv: H.264 + AAC (container supports many codecs)
+        - .mov: H.264 + AAC (Apple QuickTime, widely compatible)
+        - .m4v: H.264 + AAC (Apple iTunes/devices)
+        - .avi: MPEG-4 + MP3 (legacy Windows)
+    """
+    ext = os.path.splitext(output_path)[1].lower()
+
+    codec_map: dict[str, tuple[str, str]] = {
+        ".mp4": ("libx264", "aac"),
+        ".webm": ("libvpx", "libvorbis"),
+        ".mkv": ("libx264", "aac"),
+        ".mov": ("libx264", "aac"),
+        ".m4v": ("libx264", "aac"),
+        ".avi": ("mpeg4", "libmp3lame"),
+    }
+
+    return codec_map.get(ext, ("libx264", "aac"))

autogpt_platform/backend/backend/blocks/video/add_audio.py

@@ -0,0 +1,102 @@
+"""AddAudioToVideoBlock - Attach an audio track to a video file."""
+
+import os
+import tempfile
+
+from moviepy.audio.io.AudioFileClip import AudioFileClip
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.file import MediaFileType, store_media_file
+
+
+class AddAudioToVideoBlock(Block):
+    """Add (attach) an audio track to an existing video."""
+
+    class Input(BlockSchemaInput):
+        video_in: MediaFileType = SchemaField(
+            description="Video input (URL, data URI, or local path)."
+        )
+        audio_in: MediaFileType = SchemaField(
+            description="Audio input (URL, data URI, or local path)."
+        )
+        volume: float = SchemaField(
+            description="Volume scale for the newly attached audio track (1.0 = original).",
+            default=1.0,
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: MediaFileType = SchemaField(
+            description="Final video (with attached audio), as a path or data URI."
+        )
+
+    def __init__(self):
+        super().__init__(
+            id="3503748d-62b6-4425-91d6-725b064af509",
+            description="Block to attach an audio file to a video file using moviepy.",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=AddAudioToVideoBlock.Input,
+            output_schema=AddAudioToVideoBlock.Output,
+        )
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        **kwargs,
+    ) -> BlockOutput:
+        assert execution_context.graph_exec_id is not None
+        assert execution_context.node_exec_id is not None
+        graph_exec_id = execution_context.graph_exec_id
+        node_exec_id = execution_context.node_exec_id
+
+        # 1) Store the inputs locally
+        local_video_path = await store_media_file(
+            file=input_data.video_in,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+        local_audio_path = await store_media_file(
+            file=input_data.audio_in,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+
+        abs_temp_dir = os.path.join(tempfile.gettempdir(), "exec_file", graph_exec_id)
+        video_abspath = os.path.join(abs_temp_dir, local_video_path)
+        audio_abspath = os.path.join(abs_temp_dir, local_audio_path)
+
+        # 2) Load video + audio with moviepy
+        video_clip = VideoFileClip(video_abspath)
+        audio_clip = AudioFileClip(audio_abspath)
+        # Optionally scale volume
+        if input_data.volume != 1.0:
+            audio_clip = audio_clip.with_volume_scaled(input_data.volume)
+
+        # 3) Attach the new audio track
+        final_clip = video_clip.with_audio(audio_clip)
+
+        # 4) Write to output file
+        output_filename = MediaFileType(
+            f"{node_exec_id}_audio_attached_{os.path.basename(local_video_path)}"
+        )
+        output_abspath = os.path.join(abs_temp_dir, output_filename)
+        final_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
+
+        # 5) Return output - for_block_output returns workspace:// if available, else data URI
+        video_out = await store_media_file(
+            file=output_filename,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+        yield "video_out", video_out

autogpt_platform/backend/backend/blocks/video/clip.py

@@ -0,0 +1,165 @@
+"""VideoClipBlock - Extract a segment from a video file."""
+
+import os
+from typing import Literal
+
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.blocks.video._utils import get_video_codecs
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.exceptions import BlockExecutionError
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class VideoClipBlock(Block):
+    """Extract a time segment from a video."""
+
+    class Input(BlockSchemaInput):
+        video_in: MediaFileType = SchemaField(
+            description="Input video (URL, data URI, or local path)"
+        )
+        start_time: float = SchemaField(description="Start time in seconds", ge=0.0)
+        end_time: float = SchemaField(description="End time in seconds", ge=0.0)
+        output_format: Literal["mp4", "webm", "mkv", "mov"] = SchemaField(
+            description="Output format", default="mp4", advanced=True
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: MediaFileType = SchemaField(
+            description="Clipped video file (path or data URI)"
+        )
+        duration: float = SchemaField(description="Clip duration in seconds")
+
+    def __init__(self):
+        super().__init__(
+            id="8f539119-e580-4d86-ad41-86fbcb22abb1",
+            description="Extract a time segment from a video",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=self.Input,
+            output_schema=self.Output,
+            test_input={
+                "video_in": "/tmp/test.mp4",
+                "start_time": 0.0,
+                "end_time": 10.0,
+            },
+            test_output=[("video_out", str), ("duration", float)],
+            test_mock={
+                "_clip_video": lambda *args: 10.0,
+                "_store_input_video": lambda *args, **kwargs: "test.mp4",
+                "_store_output_video": lambda *args, **kwargs: "clip_test.mp4",
+            },
+        )
+
+    async def _store_input_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store input video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+
+    async def _store_output_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store output video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+    def _clip_video(
+        self,
+        video_abspath: str,
+        output_abspath: str,
+        start_time: float,
+        end_time: float,
+    ) -> float:
+        """Extract a clip from a video. Extracted for testability."""
+        clip = None
+        subclip = None
+        try:
+            clip = VideoFileClip(video_abspath)
+            subclip = clip.subclipped(start_time, end_time)
+            video_codec, audio_codec = get_video_codecs(output_abspath)
+            subclip.write_videofile(
+                output_abspath, codec=video_codec, audio_codec=audio_codec
+            )
+            return subclip.duration
+        finally:
+            if subclip:
+                subclip.close()
+            if clip:
+                clip.close()
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        node_exec_id: str,
+        **kwargs,
+    ) -> BlockOutput:
+        # Validate time range
+        if input_data.end_time <= input_data.start_time:
+            raise BlockExecutionError(
+                message=f"end_time ({input_data.end_time}) must be greater than start_time ({input_data.start_time})",
+                block_name=self.name,
+                block_id=str(self.id),
+            )
+
+        try:
+            assert execution_context.graph_exec_id is not None
+
+            # Store the input video locally
+            local_video_path = await self._store_input_video(
+                execution_context, input_data.video_in
+            )
+            video_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, local_video_path
+            )
+
+            # Build output path
+            output_filename = MediaFileType(
+                f"{node_exec_id}_clip_{os.path.basename(local_video_path)}"
+            )
+            # Ensure correct extension
+            base, _ = os.path.splitext(output_filename)
+            output_filename = MediaFileType(f"{base}.{input_data.output_format}")
+            output_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, output_filename
+            )
+
+            duration = self._clip_video(
+                video_abspath,
+                output_abspath,
+                input_data.start_time,
+                input_data.end_time,
+            )
+
+            # Return as workspace path or data URI based on context
+            video_out = await self._store_output_video(
+                execution_context, output_filename
+            )
+
+            yield "video_out", video_out
+            yield "duration", duration
+
+        except BlockExecutionError:
+            raise
+        except Exception as e:
+            raise BlockExecutionError(
+                message=f"Failed to clip video: {e}",
+                block_name=self.name,
+                block_id=str(self.id),
+            ) from e

autogpt_platform/backend/backend/blocks/video/concat.py

@@ -0,0 +1,197 @@
+"""VideoConcatBlock - Concatenate multiple video clips into one."""
+
+from typing import Literal
+
+from moviepy import concatenate_videoclips
+from moviepy.video.fx import CrossFadeIn, CrossFadeOut, FadeIn, FadeOut
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.blocks.video._utils import get_video_codecs
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.exceptions import BlockExecutionError
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class VideoConcatBlock(Block):
+    """Merge multiple video clips into one continuous video."""
+
+    class Input(BlockSchemaInput):
+        videos: list[MediaFileType] = SchemaField(
+            description="List of video files to concatenate (in order)"
+        )
+        transition: Literal["none", "crossfade", "fade_black"] = SchemaField(
+            description="Transition between clips", default="none"
+        )
+        transition_duration: int = SchemaField(
+            description="Transition duration in seconds",
+            default=1,
+            ge=0,
+            advanced=True,
+        )
+        output_format: Literal["mp4", "webm", "mkv", "mov"] = SchemaField(
+            description="Output format", default="mp4", advanced=True
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: MediaFileType = SchemaField(
+            description="Concatenated video file (path or data URI)"
+        )
+        total_duration: float = SchemaField(description="Total duration in seconds")
+
+    def __init__(self):
+        super().__init__(
+            id="9b0f531a-1118-487f-aeec-3fa63ea8900a",
+            description="Merge multiple video clips into one continuous video",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=self.Input,
+            output_schema=self.Output,
+            test_input={"videos": ["/tmp/a.mp4", "/tmp/b.mp4"]},
+            test_output=[("video_out", str), ("total_duration", float)],
+            test_mock={
+                "_concat_videos": lambda *args: 20.0,
+                "_store_input_video": lambda *args, **kwargs: "test.mp4",
+                "_store_output_video": lambda *args, **kwargs: "concat_test.mp4",
+            },
+        )
+
+    async def _store_input_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store input video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+
+    async def _store_output_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store output video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+    def _concat_videos(
+        self,
+        video_abspaths: list[str],
+        output_abspath: str,
+        transition: str,
+        transition_duration: int,
+    ) -> float:
+        """Concatenate videos. Extracted for testability."""
+        clips = []
+        faded_clips = []
+        final = None
+        try:
+            # Load clips
+            for v in video_abspaths:
+                clips.append(VideoFileClip(v))
+
+            if transition == "crossfade":
+                for i, clip in enumerate(clips):
+                    effects = []
+                    if i > 0:
+                        effects.append(CrossFadeIn(transition_duration))
+                    if i < len(clips) - 1:
+                        effects.append(CrossFadeOut(transition_duration))
+                    if effects:
+                        clip = clip.with_effects(effects)
+                    faded_clips.append(clip)
+                final = concatenate_videoclips(
+                    faded_clips,
+                    method="compose",
+                    padding=-transition_duration,
+                )
+            elif transition == "fade_black":
+                for clip in clips:
+                    faded = clip.with_effects(
+                        [FadeIn(transition_duration), FadeOut(transition_duration)]
+                    )
+                    faded_clips.append(faded)
+                final = concatenate_videoclips(faded_clips)
+            else:
+                final = concatenate_videoclips(clips)
+
+            video_codec, audio_codec = get_video_codecs(output_abspath)
+            final.write_videofile(
+                output_abspath, codec=video_codec, audio_codec=audio_codec
+            )
+
+            return final.duration
+        finally:
+            if final:
+                final.close()
+            for clip in faded_clips:
+                clip.close()
+            for clip in clips:
+                clip.close()
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        node_exec_id: str,
+        **kwargs,
+    ) -> BlockOutput:
+        # Validate minimum clips
+        if len(input_data.videos) < 2:
+            raise BlockExecutionError(
+                message="At least 2 videos are required for concatenation",
+                block_name=self.name,
+                block_id=str(self.id),
+            )
+
+        try:
+            assert execution_context.graph_exec_id is not None
+
+            # Store all input videos locally
+            video_abspaths = []
+            for video in input_data.videos:
+                local_path = await self._store_input_video(execution_context, video)
+                video_abspaths.append(
+                    get_exec_file_path(execution_context.graph_exec_id, local_path)
+                )
+
+            # Build output path
+            output_filename = MediaFileType(
+                f"{node_exec_id}_concat.{input_data.output_format}"
+            )
+            output_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, output_filename
+            )
+
+            total_duration = self._concat_videos(
+                video_abspaths,
+                output_abspath,
+                input_data.transition,
+                input_data.transition_duration,
+            )
+
+            # Return as workspace path or data URI based on context
+            video_out = await self._store_output_video(
+                execution_context, output_filename
+            )
+
+            yield "video_out", video_out
+            yield "total_duration", total_duration
+
+        except BlockExecutionError:
+            raise
+        except Exception as e:
+            raise BlockExecutionError(
+                message=f"Failed to concatenate videos: {e}",
+                block_name=self.name,
+                block_id=str(self.id),
+            ) from e

autogpt_platform/backend/backend/blocks/video/download.py

@@ -0,0 +1,167 @@
+"""VideoDownloadBlock - Download video from URL (YouTube, Vimeo, news sites, direct links)."""
+
+import os
+import typing
+from typing import Literal
+
+import yt_dlp
+
+if typing.TYPE_CHECKING:
+    from yt_dlp import _Params
+
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.exceptions import BlockExecutionError
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class VideoDownloadBlock(Block):
+    """Download video from URL using yt-dlp."""
+
+    class Input(BlockSchemaInput):
+        url: str = SchemaField(
+            description="URL of the video to download (YouTube, Vimeo, direct link, etc.)",
+            placeholder="https://www.youtube.com/watch?v=...",
+        )
+        quality: Literal["best", "1080p", "720p", "480p", "audio_only"] = SchemaField(
+            description="Video quality preference", default="720p"
+        )
+        output_format: Literal["mp4", "webm", "mkv"] = SchemaField(
+            description="Output video format", default="mp4", advanced=True
+        )
+
+    class Output(BlockSchemaOutput):
+        video_file: MediaFileType = SchemaField(
+            description="Downloaded video (path or data URI)"
+        )
+        duration: float = SchemaField(description="Video duration in seconds")
+        title: str = SchemaField(description="Video title from source")
+        source_url: str = SchemaField(description="Original source URL")
+
+    def __init__(self):
+        super().__init__(
+            id="c35daabb-cd60-493b-b9ad-51f1fe4b50c4",
+            description="Download video from URL (YouTube, Vimeo, news sites, direct links)",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=self.Input,
+            output_schema=self.Output,
+            test_input={
+                "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
+                "quality": "480p",
+            },
+            test_output=[
+                ("video_file", str),
+                ("duration", float),
+                ("title", str),
+                ("source_url", str),
+            ],
+            test_mock={
+                "_download_video": lambda *args: ("video.mp4", 212.0, "Test Video"),
+                "_store_output_video": lambda *args, **kwargs: "video.mp4",
+            },
+        )
+
+    async def _store_output_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store output video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+    def _get_format_string(self, quality: str) -> str:
+        formats = {
+            "best": "bestvideo+bestaudio/best",
+            "1080p": "bestvideo[height<=1080]+bestaudio/best[height<=1080]",
+            "720p": "bestvideo[height<=720]+bestaudio/best[height<=720]",
+            "480p": "bestvideo[height<=480]+bestaudio/best[height<=480]",
+            "audio_only": "bestaudio/best",
+        }
+        return formats.get(quality, formats["720p"])
+
+    def _download_video(
+        self,
+        url: str,
+        quality: str,
+        output_format: str,
+        output_dir: str,
+        node_exec_id: str,
+    ) -> tuple[str, float, str]:
+        """Download video. Extracted for testability."""
+        output_template = os.path.join(
+            output_dir, f"{node_exec_id}_%(title).50s.%(ext)s"
+        )
+
+        ydl_opts: "_Params" = {
+            "format": self._get_format_string(quality),
+            "outtmpl": output_template,
+            "merge_output_format": output_format,
+            "quiet": True,
+            "no_warnings": True,
+        }
+
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(url, download=True)
+            video_path = ydl.prepare_filename(info)
+
+            # Handle format conversion in filename
+            if not video_path.endswith(f".{output_format}"):
+                video_path = video_path.rsplit(".", 1)[0] + f".{output_format}"
+
+            # Return just the filename, not the full path
+            filename = os.path.basename(video_path)
+
+            return (
+                filename,
+                info.get("duration") or 0.0,
+                info.get("title") or "Unknown",
+            )
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        node_exec_id: str,
+        **kwargs,
+    ) -> BlockOutput:
+        try:
+            assert execution_context.graph_exec_id is not None
+
+            # Get the exec file directory
+            output_dir = get_exec_file_path(execution_context.graph_exec_id, "")
+            os.makedirs(output_dir, exist_ok=True)
+
+            filename, duration, title = self._download_video(
+                input_data.url,
+                input_data.quality,
+                input_data.output_format,
+                output_dir,
+                node_exec_id,
+            )
+
+            # Return as workspace path or data URI based on context
+            video_out = await self._store_output_video(
+                execution_context, MediaFileType(filename)
+            )
+
+            yield "video_file", video_out
+            yield "duration", duration
+            yield "title", title
+            yield "source_url", input_data.url
+
+        except Exception as e:
+            raise BlockExecutionError(
+                message=f"Failed to download video: {e}",
+                block_name=self.name,
+                block_id=str(self.id),
+            ) from e

autogpt_platform/backend/backend/blocks/video/duration.py

@@ -0,0 +1,68 @@
+"""MediaDurationBlock - Get the duration of a media file."""
+
+from moviepy.audio.io.AudioFileClip import AudioFileClip
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class MediaDurationBlock(Block):
+    """Get the duration of a media file (video or audio)."""
+
+    class Input(BlockSchemaInput):
+        media_in: MediaFileType = SchemaField(
+            description="Media input (URL, data URI, or local path)."
+        )
+        is_video: bool = SchemaField(
+            description="Whether the media is a video (True) or audio (False).",
+            default=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        duration: float = SchemaField(
+            description="Duration of the media file (in seconds)."
+        )
+
+    def __init__(self):
+        super().__init__(
+            id="d8b91fd4-da26-42d4-8ecb-8b196c6d84b6",
+            description="Block to get the duration of a media file.",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=MediaDurationBlock.Input,
+            output_schema=MediaDurationBlock.Output,
+        )
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        **kwargs,
+    ) -> BlockOutput:
+        # 1) Store the input media locally
+        local_media_path = await store_media_file(
+            file=input_data.media_in,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+        assert execution_context.graph_exec_id is not None
+        media_abspath = get_exec_file_path(
+            execution_context.graph_exec_id, local_media_path
+        )
+
+        # 2) Load the clip
+        if input_data.is_video:
+            clip = VideoFileClip(media_abspath)
+        else:
+            clip = AudioFileClip(media_abspath)
+
+        yield "duration", clip.duration

autogpt_platform/backend/backend/blocks/video/loop.py

@@ -0,0 +1,104 @@
+"""LoopVideoBlock - Loop a video to a given duration or number of repeats."""
+
+import os
+from typing import Optional
+
+from moviepy.video.fx.Loop import Loop
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class LoopVideoBlock(Block):
+    """Loop (repeat) a video clip until a given duration or number of loops."""
+
+    class Input(BlockSchemaInput):
+        video_in: MediaFileType = SchemaField(
+            description="The input video (can be a URL, data URI, or local path)."
+        )
+        duration: Optional[float] = SchemaField(
+            description="Target duration (in seconds) to loop the video to. If omitted, defaults to no looping.",
+            default=None,
+            ge=0.0,
+        )
+        n_loops: Optional[int] = SchemaField(
+            description="Number of times to repeat the video. If omitted, defaults to 1 (no repeat).",
+            default=None,
+            ge=1,
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: str = SchemaField(
+            description="Looped video returned either as a relative path or a data URI."
+        )
+
+    def __init__(self):
+        super().__init__(
+            id="8bf9eef6-5451-4213-b265-25306446e94b",
+            description="Block to loop a video to a given duration or number of repeats.",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=LoopVideoBlock.Input,
+            output_schema=LoopVideoBlock.Output,
+        )
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        **kwargs,
+    ) -> BlockOutput:
+        assert execution_context.graph_exec_id is not None
+        assert execution_context.node_exec_id is not None
+        graph_exec_id = execution_context.graph_exec_id
+        node_exec_id = execution_context.node_exec_id
+
+        # 1) Store the input video locally
+        local_video_path = await store_media_file(
+            file=input_data.video_in,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+        input_abspath = get_exec_file_path(graph_exec_id, local_video_path)
+
+        # 2) Load the clip
+        clip = VideoFileClip(input_abspath)
+
+        # 3) Apply the loop effect
+        looped_clip = clip
+        if input_data.duration:
+            # Loop until we reach the specified duration
+            looped_clip = looped_clip.with_effects([Loop(duration=input_data.duration)])
+        elif input_data.n_loops:
+            looped_clip = looped_clip.with_effects([Loop(n=input_data.n_loops)])
+        else:
+            raise ValueError("Either 'duration' or 'n_loops' must be provided.")
+
+        assert isinstance(looped_clip, VideoFileClip)
+
+        # 4) Save the looped output
+        output_filename = MediaFileType(
+            f"{node_exec_id}_looped_{os.path.basename(local_video_path)}"
+        )
+        output_abspath = get_exec_file_path(graph_exec_id, output_filename)
+
+        looped_clip = looped_clip.with_audio(clip.audio)
+        looped_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
+
+        # Return output - for_block_output returns workspace:// if available, else data URI
+        video_out = await store_media_file(
+            file=output_filename,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+        yield "video_out", video_out

autogpt_platform/backend/backend/blocks/video/narration.py

@@ -0,0 +1,263 @@
+"""VideoNarrationBlock - Generate AI voice narration and add to video."""
+
+import os
+from typing import Literal
+
+from elevenlabs import ElevenLabs
+from moviepy import CompositeAudioClip
+from moviepy.audio.io.AudioFileClip import AudioFileClip
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.blocks.elevenlabs._auth import (
+    TEST_CREDENTIALS,
+    TEST_CREDENTIALS_INPUT,
+    ElevenLabsCredentials,
+    ElevenLabsCredentialsInput,
+)
+from backend.blocks.video._utils import get_video_codecs
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import CredentialsField, SchemaField
+from backend.util.exceptions import BlockExecutionError
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class VideoNarrationBlock(Block):
+    """Generate AI narration and add to video."""
+
+    class Input(BlockSchemaInput):
+        credentials: ElevenLabsCredentialsInput = CredentialsField(
+            description="ElevenLabs API key for voice synthesis"
+        )
+        video_in: MediaFileType = SchemaField(
+            description="Input video (URL, data URI, or local path)"
+        )
+        script: str = SchemaField(description="Narration script text")
+        voice_id: str = SchemaField(
+            description="ElevenLabs voice ID", default="21m00Tcm4TlvDq8ikWAM"  # Rachel
+        )
+        model_id: Literal[
+            "eleven_multilingual_v2",
+            "eleven_flash_v2_5",
+            "eleven_turbo_v2_5",
+            "eleven_turbo_v2",
+        ] = SchemaField(
+            description="ElevenLabs TTS model",
+            default="eleven_multilingual_v2",
+        )
+        mix_mode: Literal["replace", "mix", "ducking"] = SchemaField(
+            description="How to combine with original audio. 'ducking' applies stronger attenuation than 'mix'.",
+            default="ducking",
+        )
+        narration_volume: float = SchemaField(
+            description="Narration volume (0.0 to 2.0)",
+            default=1.0,
+            ge=0.0,
+            le=2.0,
+            advanced=True,
+        )
+        original_volume: float = SchemaField(
+            description="Original audio volume when mixing (0.0 to 1.0)",
+            default=0.3,
+            ge=0.0,
+            le=1.0,
+            advanced=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: MediaFileType = SchemaField(
+            description="Video with narration (path or data URI)"
+        )
+        audio_file: MediaFileType = SchemaField(
+            description="Generated audio file (path or data URI)"
+        )
+
+    def __init__(self):
+        super().__init__(
+            id="3d036b53-859c-4b17-9826-ca340f736e0e",
+            description="Generate AI narration and add to video",
+            categories={BlockCategory.MULTIMEDIA, BlockCategory.AI},
+            input_schema=self.Input,
+            output_schema=self.Output,
+            test_input={
+                "video_in": "/tmp/test.mp4",
+                "script": "Hello world",
+                "credentials": TEST_CREDENTIALS_INPUT,
+            },
+            test_credentials=TEST_CREDENTIALS,
+            test_output=[("video_out", str), ("audio_file", str)],
+            test_mock={
+                "_generate_narration_audio": lambda *args: b"mock audio content",
+                "_add_narration_to_video": lambda *args: None,
+                "_store_input_video": lambda *args, **kwargs: "test.mp4",
+                "_store_output_video": lambda *args, **kwargs: "narrated_test.mp4",
+            },
+        )
+
+    async def _store_input_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store input video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+
+    async def _store_output_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store output video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+    def _generate_narration_audio(
+        self, api_key: str, script: str, voice_id: str, model_id: str
+    ) -> bytes:
+        """Generate narration audio via ElevenLabs API."""
+        client = ElevenLabs(api_key=api_key)
+        audio_generator = client.text_to_speech.convert(
+            voice_id=voice_id,
+            text=script,
+            model_id=model_id,
+        )
+        # The SDK returns a generator, collect all chunks
+        return b"".join(audio_generator)
+
+    def _add_narration_to_video(
+        self,
+        video_abspath: str,
+        audio_abspath: str,
+        output_abspath: str,
+        mix_mode: str,
+        narration_volume: float,
+        original_volume: float,
+    ) -> None:
+        """Add narration audio to video. Extracted for testability."""
+        video = None
+        final = None
+        narration_original = None
+        narration_scaled = None
+        original = None
+
+        try:
+            video = VideoFileClip(video_abspath)
+            narration_original = AudioFileClip(audio_abspath)
+            narration_scaled = narration_original.with_volume_scaled(narration_volume)
+            narration = narration_scaled
+
+            if mix_mode == "replace":
+                final_audio = narration
+            elif mix_mode == "mix":
+                if video.audio:
+                    original = video.audio.with_volume_scaled(original_volume)
+                    final_audio = CompositeAudioClip([original, narration])
+                else:
+                    final_audio = narration
+            else:  # ducking - apply stronger attenuation
+                if video.audio:
+                    # Ducking uses a much lower volume for original audio
+                    ducking_volume = original_volume * 0.3
+                    original = video.audio.with_volume_scaled(ducking_volume)
+                    final_audio = CompositeAudioClip([original, narration])
+                else:
+                    final_audio = narration
+
+            final = video.with_audio(final_audio)
+            video_codec, audio_codec = get_video_codecs(output_abspath)
+            final.write_videofile(
+                output_abspath, codec=video_codec, audio_codec=audio_codec
+            )
+
+        finally:
+            if original:
+                original.close()
+            if narration_scaled:
+                narration_scaled.close()
+            if narration_original:
+                narration_original.close()
+            if final:
+                final.close()
+            if video:
+                video.close()
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        credentials: ElevenLabsCredentials,
+        execution_context: ExecutionContext,
+        node_exec_id: str,
+        **kwargs,
+    ) -> BlockOutput:
+        try:
+            assert execution_context.graph_exec_id is not None
+
+            # Store the input video locally
+            local_video_path = await self._store_input_video(
+                execution_context, input_data.video_in
+            )
+            video_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, local_video_path
+            )
+
+            # Generate narration audio via ElevenLabs
+            audio_content = self._generate_narration_audio(
+                credentials.api_key.get_secret_value(),
+                input_data.script,
+                input_data.voice_id,
+                input_data.model_id,
+            )
+
+            # Save audio to exec file path
+            audio_filename = MediaFileType(f"{node_exec_id}_narration.mp3")
+            audio_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, audio_filename
+            )
+            os.makedirs(os.path.dirname(audio_abspath), exist_ok=True)
+            with open(audio_abspath, "wb") as f:
+                f.write(audio_content)
+
+            # Add narration to video
+            output_filename = MediaFileType(
+                f"{node_exec_id}_narrated_{os.path.basename(local_video_path)}"
+            )
+            output_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, output_filename
+            )
+
+            self._add_narration_to_video(
+                video_abspath,
+                audio_abspath,
+                output_abspath,
+                input_data.mix_mode,
+                input_data.narration_volume,
+                input_data.original_volume,
+            )
+
+            # Return as workspace path or data URI based on context
+            video_out = await self._store_output_video(
+                execution_context, output_filename
+            )
+            audio_out = await self._store_output_video(
+                execution_context, audio_filename
+            )
+
+            yield "video_out", video_out
+            yield "audio_file", audio_out
+
+        except Exception as e:
+            raise BlockExecutionError(
+                message=f"Failed to add narration: {e}",
+                block_name=self.name,
+                block_id=str(self.id),
+            ) from e

autogpt_platform/backend/backend/blocks/video/text_overlay.py

@@ -0,0 +1,227 @@
+"""VideoTextOverlayBlock - Add text overlay to video."""
+
+import os
+from typing import Literal
+
+from moviepy import CompositeVideoClip, TextClip
+from moviepy.video.io.VideoFileClip import VideoFileClip
+
+from backend.blocks.video._utils import get_video_codecs
+from backend.data.block import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
+from backend.data.execution import ExecutionContext
+from backend.data.model import SchemaField
+from backend.util.exceptions import BlockExecutionError
+from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
+
+
+class VideoTextOverlayBlock(Block):
+    """Add text overlay/caption to video."""
+
+    class Input(BlockSchemaInput):
+        video_in: MediaFileType = SchemaField(
+            description="Input video (URL, data URI, or local path)"
+        )
+        text: str = SchemaField(description="Text to overlay on video")
+        position: Literal[
+            "top",
+            "center",
+            "bottom",
+            "top-left",
+            "top-right",
+            "bottom-left",
+            "bottom-right",
+        ] = SchemaField(description="Position of text on screen", default="bottom")
+        start_time: float | None = SchemaField(
+            description="When to show text (seconds). None = entire video",
+            default=None,
+            advanced=True,
+        )
+        end_time: float | None = SchemaField(
+            description="When to hide text (seconds). None = until end",
+            default=None,
+            advanced=True,
+        )
+        font_size: int = SchemaField(
+            description="Font size", default=48, ge=12, le=200, advanced=True
+        )
+        font_color: str = SchemaField(
+            description="Font color (hex or name)", default="white", advanced=True
+        )
+        bg_color: str | None = SchemaField(
+            description="Background color behind text (None for transparent)",
+            default=None,
+            advanced=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        video_out: MediaFileType = SchemaField(
+            description="Video with text overlay (path or data URI)"
+        )
+
+    def __init__(self):
+        super().__init__(
+            id="8ef14de6-cc90-430a-8cfa-3a003be92454",
+            description="Add text overlay/caption to video",
+            categories={BlockCategory.MULTIMEDIA},
+            input_schema=self.Input,
+            output_schema=self.Output,
+            test_input={"video_in": "/tmp/test.mp4", "text": "Hello World"},
+            test_output=[("video_out", str)],
+            test_mock={
+                "_add_text_overlay": lambda *args: None,
+                "_store_input_video": lambda *args, **kwargs: "test.mp4",
+                "_store_output_video": lambda *args, **kwargs: "overlay_test.mp4",
+            },
+        )
+
+    async def _store_input_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store input video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_local_processing",
+        )
+
+    async def _store_output_video(
+        self, execution_context: ExecutionContext, file: MediaFileType
+    ) -> MediaFileType:
+        """Store output video. Extracted for testability."""
+        return await store_media_file(
+            file=file,
+            execution_context=execution_context,
+            return_format="for_block_output",
+        )
+
+    def _add_text_overlay(
+        self,
+        video_abspath: str,
+        output_abspath: str,
+        text: str,
+        position: str,
+        start_time: float | None,
+        end_time: float | None,
+        font_size: int,
+        font_color: str,
+        bg_color: str | None,
+    ) -> None:
+        """Add text overlay to video. Extracted for testability."""
+        video = None
+        final = None
+        txt_clip = None
+        try:
+            video = VideoFileClip(video_abspath)
+
+            txt_clip = TextClip(
+                text=text,
+                font_size=font_size,
+                color=font_color,
+                bg_color=bg_color,
+            )
+
+            # Position mapping
+            pos_map = {
+                "top": ("center", "top"),
+                "center": ("center", "center"),
+                "bottom": ("center", "bottom"),
+                "top-left": ("left", "top"),
+                "top-right": ("right", "top"),
+                "bottom-left": ("left", "bottom"),
+                "bottom-right": ("right", "bottom"),
+            }
+
+            txt_clip = txt_clip.with_position(pos_map[position])
+
+            # Set timing
+            start = start_time or 0
+            end = end_time or video.duration
+            duration = max(0, end - start)
+            txt_clip = txt_clip.with_start(start).with_end(end).with_duration(duration)
+
+            final = CompositeVideoClip([video, txt_clip])
+            video_codec, audio_codec = get_video_codecs(output_abspath)
+            final.write_videofile(
+                output_abspath, codec=video_codec, audio_codec=audio_codec
+            )
+
+        finally:
+            if txt_clip:
+                txt_clip.close()
+            if final:
+                final.close()
+            if video:
+                video.close()
+
+    async def run(
+        self,
+        input_data: Input,
+        *,
+        execution_context: ExecutionContext,
+        node_exec_id: str,
+        **kwargs,
+    ) -> BlockOutput:
+        # Validate time range if both are provided
+        if (
+            input_data.start_time is not None
+            and input_data.end_time is not None
+            and input_data.end_time <= input_data.start_time
+        ):
+            raise BlockExecutionError(
+                message=f"end_time ({input_data.end_time}) must be greater than start_time ({input_data.start_time})",
+                block_name=self.name,
+                block_id=str(self.id),
+            )
+
+        try:
+            assert execution_context.graph_exec_id is not None
+
+            # Store the input video locally
+            local_video_path = await self._store_input_video(
+                execution_context, input_data.video_in
+            )
+            video_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, local_video_path
+            )
+
+            # Build output path
+            output_filename = MediaFileType(
+                f"{node_exec_id}_overlay_{os.path.basename(local_video_path)}"
+            )
+            output_abspath = get_exec_file_path(
+                execution_context.graph_exec_id, output_filename
+            )
+
+            self._add_text_overlay(
+                video_abspath,
+                output_abspath,
+                input_data.text,
+                input_data.position,
+                input_data.start_time,
+                input_data.end_time,
+                input_data.font_size,
+                input_data.font_color,
+                input_data.bg_color,
+            )
+
+            # Return as workspace path or data URI based on context
+            video_out = await self._store_output_video(
+                execution_context, output_filename
+            )
+
+            yield "video_out", video_out
+
+        except BlockExecutionError:
+            raise
+        except Exception as e:
+            raise BlockExecutionError(
+                message=f"Failed to add text overlay: {e}",
+                block_name=self.name,
+                block_id=str(self.id),
+            ) from e

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -36,12 +36,14 @@ from backend.blocks.replicate.replicate_block import ReplicateModelBlock
 from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
 from backend.blocks.talking_head import CreateTalkingAvatarVideoBlock
 from backend.blocks.text_to_speech_block import UnrealTextToSpeechBlock
+from backend.blocks.video.narration import VideoNarrationBlock
 from backend.data.block import Block, BlockCost, BlockCostType
 from backend.integrations.credentials_store import (
     aiml_api_credentials,
     anthropic_credentials,
     apollo_credentials,
     did_credentials,
+    elevenlabs_credentials,
     enrichlayer_credentials,
     groq_credentials,
     ideogram_credentials,
@@ -81,6 +83,7 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.CLAUDE_4_5_HAIKU: 4,
     LlmModel.CLAUDE_4_5_OPUS: 14,
     LlmModel.CLAUDE_4_5_SONNET: 9,
+    LlmModel.CLAUDE_3_7_SONNET: 5,
     LlmModel.CLAUDE_3_HAIKU: 1,
     LlmModel.AIML_API_QWEN2_5_72B: 1,
     LlmModel.AIML_API_LLAMA3_1_70B: 1,
@@ -639,4 +642,16 @@ BLOCK_COSTS: dict[Type[Block], list[BlockCost]] = {
             },
         ),
     ],
+    VideoNarrationBlock: [
+        BlockCost(
+            cost_amount=5,  # ElevenLabs TTS cost
+            cost_filter={
+                "credentials": {
+                    "id": elevenlabs_credentials.id,
+                    "provider": elevenlabs_credentials.provider,
+                    "type": elevenlabs_credentials.type,
+                }
+            },
+        )
+    ],
 }

autogpt_platform/backend/backend/data/model.py

@@ -666,16 +666,10 @@ class CredentialsFieldInfo(BaseModel, Generic[CP, CT]):
         if not (self.discriminator and self.discriminator_mapping):
             return self
 
-        try:
-            provider = self.discriminator_mapping[discriminator_value]
-        except KeyError:
-            raise ValueError(
-                f"Model '{discriminator_value}' is not supported. "
-                "It may have been deprecated. Please update your agent configuration."
-            )
-
         return CredentialsFieldInfo(
-            credentials_provider=frozenset([provider]),
+            credentials_provider=frozenset(
+                [self.discriminator_mapping[discriminator_value]]
+            ),
             credentials_types=self.supported_types,
             credentials_scopes=self.required_scopes,
             discriminator=self.discriminator,

autogpt_platform/backend/backend/integrations/credentials_store.py

@@ -224,6 +224,14 @@ openweathermap_credentials = APIKeyCredentials(
     expires_at=None,
 )
 
+elevenlabs_credentials = APIKeyCredentials(
+    id="f4a8b6c2-3d1e-4f5a-9b8c-7d6e5f4a3b2c",
+    provider="elevenlabs",
+    api_key=SecretStr(settings.secrets.elevenlabs_api_key),
+    title="Use Credits for ElevenLabs",
+    expires_at=None,
+)
+
 DEFAULT_CREDENTIALS = [
     ollama_credentials,
     revid_credentials,
@@ -252,6 +260,7 @@ DEFAULT_CREDENTIALS = [
     v0_credentials,
     webshare_proxy_credentials,
     openweathermap_credentials,
+    elevenlabs_credentials,
 ]
 
 SYSTEM_CREDENTIAL_IDS = {cred.id for cred in DEFAULT_CREDENTIALS}
@@ -366,6 +375,8 @@ class IntegrationCredentialsStore:
             all_credentials.append(webshare_proxy_credentials)
         if settings.secrets.openweathermap_api_key:
             all_credentials.append(openweathermap_credentials)
+        if settings.secrets.elevenlabs_api_key:
+            all_credentials.append(elevenlabs_credentials)
         return all_credentials
 
     async def get_creds_by_id(

autogpt_platform/backend/backend/integrations/providers.py

@@ -18,6 +18,7 @@ class ProviderName(str, Enum):
     DISCORD = "discord"
     D_ID = "d_id"
     E2B = "e2b"
+    ELEVENLABS = "elevenlabs"
     FAL = "fal"
     GITHUB = "github"
     GOOGLE = "google"

autogpt_platform/backend/backend/util/settings.py

@@ -656,6 +656,7 @@ class Secrets(UpdateTrackingModel["Secrets"], BaseSettings):
     e2b_api_key: str = Field(default="", description="E2B API key")
     nvidia_api_key: str = Field(default="", description="Nvidia API key")
     mem0_api_key: str = Field(default="", description="Mem0 API key")
+    elevenlabs_api_key: str = Field(default="", description="ElevenLabs API key")
 
     linear_client_id: str = Field(default="", description="Linear client ID")
     linear_client_secret: str = Field(default="", description="Linear client secret")

autogpt_platform/backend/migrations/20260126120000_migrate_claude_3_7_to_4_5_sonnet/migration.sql

@@ -1,22 +0,0 @@
--- Migrate Claude 3.7 Sonnet to Claude 4.5 Sonnet
--- This updates all AgentNode blocks that use the deprecated Claude 3.7 Sonnet model
--- Anthropic is retiring claude-3-7-sonnet-20250219 on February 19, 2026
-
--- Update AgentNode constant inputs
-UPDATE "AgentNode"
-SET    "constantInput" = JSONB_SET(
-         "constantInput"::jsonb,
-         '{model}',
-         '"claude-sonnet-4-5-20250929"'::jsonb
-       )
-WHERE  "constantInput"::jsonb->>'model' = 'claude-3-7-sonnet-20250219';
-
--- Update AgentPreset input overrides (stored in AgentNodeExecutionInputOutput)
-UPDATE "AgentNodeExecutionInputOutput"
-SET    "data" = JSONB_SET(
-         "data"::jsonb,
-         '{model}',
-         '"claude-sonnet-4-5-20250929"'::jsonb
-       )
-WHERE  "agentPresetId" IS NOT NULL
-  AND  "data"::jsonb->>'model' = 'claude-3-7-sonnet-20250219';

autogpt_platform/backend/poetry.lock

@@ -1169,6 +1169,29 @@ attrs = ">=21.3.0"
 e2b = ">=1.5.4,<2.0.0"
 httpx = ">=0.20.0,<1.0.0"
 
+[[package]]
+name = "elevenlabs"
+version = "1.59.0"
+description = ""
+optional = false
+python-versions = "<4.0,>=3.8"
+groups = ["main"]
+files = [
+    {file = "elevenlabs-1.59.0-py3-none-any.whl", hash = "sha256:468145db81a0bc867708b4a8619699f75583e9481b395ec1339d0b443da771ed"},
+    {file = "elevenlabs-1.59.0.tar.gz", hash = "sha256:16e735bd594e86d415dd445d249c8cc28b09996cfd627fbc10102c0a84698859"},
+]
+
+[package.dependencies]
+httpx = ">=0.21.2"
+pydantic = ">=1.9.2"
+pydantic-core = ">=2.18.2,<3.0.0"
+requests = ">=2.20"
+typing_extensions = ">=4.0.0"
+websockets = ">=11.0"
+
+[package.extras]
+pyaudio = ["pyaudio (>=0.2.14)"]
+
 [[package]]
 name = "email-validator"
 version = "2.2.0"
@@ -7361,6 +7384,28 @@ files = [
 defusedxml = ">=0.7.1,<0.8.0"
 requests = "*"
 
+[[package]]
+name = "yt-dlp"
+version = "2025.12.8"
+description = "A feature-rich command-line audio/video downloader"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "yt_dlp-2025.12.8-py3-none-any.whl", hash = "sha256:36e2584342e409cfbfa0b5e61448a1c5189e345cf4564294456ee509e7d3e065"},
+    {file = "yt_dlp-2025.12.8.tar.gz", hash = "sha256:b773c81bb6b71cb2c111cfb859f453c7a71cf2ef44eff234ff155877184c3e4f"},
+]
+
+[package.extras]
+build = ["build", "hatchling (>=1.27.0)", "pip", "setuptools (>=71.0.2)", "wheel"]
+curl-cffi = ["curl-cffi (>=0.5.10,<0.6.dev0 || >=0.10.dev0,<0.14) ; implementation_name == \"cpython\""]
+default = ["brotli ; implementation_name == \"cpython\"", "brotlicffi ; implementation_name != \"cpython\"", "certifi", "mutagen", "pycryptodomex", "requests (>=2.32.2,<3)", "urllib3 (>=2.0.2,<3)", "websockets (>=13.0)", "yt-dlp-ejs (==0.3.2)"]
+dev = ["autopep8 (>=2.0,<3.0)", "pre-commit", "pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)", "ruff (>=0.14.0,<0.15.0)"]
+pyinstaller = ["pyinstaller (>=6.17.0)"]
+secretstorage = ["cffi", "secretstorage"]
+static-analysis = ["autopep8 (>=2.0,<3.0)", "ruff (>=0.14.0,<0.15.0)"]
+test = ["pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)"]
+
 [[package]]
 name = "zerobouncesdk"
 version = "1.1.2"
@@ -7512,4 +7557,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "ee5742dc1a9df50dfc06d4b26a1682cbb2b25cab6b79ce5625ec272f93e4f4bf"
+content-hash = "8239323f9ae6713224dffd1fe8ba8b449fe88b6c3c7a90940294a74f43a0387a"

autogpt_platform/backend/pyproject.toml

@@ -20,6 +20,7 @@ click = "^8.2.0"
 cryptography = "^45.0"
 discord-py = "^2.5.2"
 e2b-code-interpreter = "^1.5.2"
+elevenlabs = "^1.50.0"
 fastapi = "^0.116.1"
 feedparser = "^6.0.11"
 flake8 = "^7.3.0"
@@ -71,6 +72,7 @@ tweepy = "^4.16.0"
 uvicorn = { extras = ["standard"], version = "^0.35.0" }
 websockets = "^15.0"
 youtube-transcript-api = "^1.2.1"
+yt-dlp = "2025.12.08"
 zerobouncesdk = "^1.1.2"
 # NOTE: please insert new dependencies in their alphabetical location
 pytest-snapshot = "^0.9.0"

autogpt_platform/backend/test/e2e_test_data.py

@@ -43,24 +43,19 @@ faker = Faker()
 # Constants for data generation limits (reduced for E2E tests)
 NUM_USERS = 15
 NUM_AGENT_BLOCKS = 30
-MIN_GRAPHS_PER_USER = 25
-MAX_GRAPHS_PER_USER = 25
+MIN_GRAPHS_PER_USER = 15
+MAX_GRAPHS_PER_USER = 15
 MIN_NODES_PER_GRAPH = 3
 MAX_NODES_PER_GRAPH = 6
 MIN_PRESETS_PER_USER = 2
 MAX_PRESETS_PER_USER = 3
-MIN_AGENTS_PER_USER = 25
-MAX_AGENTS_PER_USER = 25
+MIN_AGENTS_PER_USER = 15
+MAX_AGENTS_PER_USER = 15
 MIN_EXECUTIONS_PER_GRAPH = 2
 MAX_EXECUTIONS_PER_GRAPH = 8
 MIN_REVIEWS_PER_VERSION = 2
 MAX_REVIEWS_PER_VERSION = 5
 
-# Guaranteed minimums for marketplace tests (deterministic)
-GUARANTEED_FEATURED_AGENTS = 8
-GUARANTEED_FEATURED_CREATORS = 5
-GUARANTEED_TOP_AGENTS = 10
-
 
 def get_image():
     """Generate a consistent image URL using picsum.photos service."""
@@ -390,7 +385,7 @@ class TestDataCreator:
 
         library_agents = []
         for user in self.users:
-            num_agents = random.randint(MIN_AGENTS_PER_USER, MAX_AGENTS_PER_USER)
+            num_agents = 10  # Create exactly 10 agents per user
 
             # Get available graphs for this user
             user_graphs = [
@@ -512,17 +507,14 @@ class TestDataCreator:
             existing_profiles, min(num_creators, len(existing_profiles))
         )
 
-        # Guarantee at least GUARANTEED_FEATURED_CREATORS featured creators
-        num_featured = max(GUARANTEED_FEATURED_CREATORS, int(num_creators * 0.5))
+        # Mark about 50% of creators as featured (more for testing)
+        num_featured = max(2, int(num_creators * 0.5))
         num_featured = min(
             num_featured, len(selected_profiles)
         )  # Don't exceed available profiles
         featured_profile_ids = set(
             random.sample([p.id for p in selected_profiles], num_featured)
         )
-        print(
-            f"🎯 Creating {num_featured} featured creators (min: {GUARANTEED_FEATURED_CREATORS})"
-        )
 
         for profile in selected_profiles:
             try:
@@ -553,25 +545,21 @@ class TestDataCreator:
         return profiles
 
     async def create_test_store_submissions(self) -> List[Dict[str, Any]]:
-        """Create test store submissions using the API function.
-
-        DETERMINISTIC: Guarantees minimum featured agents for E2E tests.
-        """
+        """Create test store submissions using the API function."""
         print("Creating test store submissions...")
 
         submissions = []
         approved_submissions = []
-        featured_count = 0
-        submission_counter = 0
 
-        # Create a special test submission for test123@gmail.com (ALWAYS approved + featured)
+        # Create a special test submission for test123@gmail.com
         test_user = next(
             (user for user in self.users if user["email"] == "test123@gmail.com"), None
         )
-        if test_user and self.agent_graphs:
+        if test_user:
+            # Special test data for consistent testing
             test_submission_data = {
                 "user_id": test_user["id"],
-                "agent_id": self.agent_graphs[0]["id"],
+                "agent_id": self.agent_graphs[0]["id"],  # Use first available graph
                 "agent_version": 1,
                 "slug": "test-agent-submission",
                 "name": "Test Agent Submission",
@@ -592,24 +580,37 @@ class TestDataCreator:
                 submissions.append(test_submission.model_dump())
                 print("✅ Created special test store submission for test123@gmail.com")
 
-                # ALWAYS approve and feature the test submission
+                # Randomly approve, reject, or leave pending the test submission
                 if test_submission.store_listing_version_id:
-                    approved_submission = await review_store_submission(
-                        store_listing_version_id=test_submission.store_listing_version_id,
-                        is_approved=True,
-                        external_comments="Test submission approved",
-                        internal_comments="Auto-approved test submission",
-                        reviewer_id=test_user["id"],
-                    )
-                    approved_submissions.append(approved_submission.model_dump())
-                    print("✅ Approved test store submission")
+                    random_value = random.random()
+                    if random_value < 0.4:  # 40% chance to approve
+                        approved_submission = await review_store_submission(
+                            store_listing_version_id=test_submission.store_listing_version_id,
+                            is_approved=True,
+                            external_comments="Test submission approved",
+                            internal_comments="Auto-approved test submission",
+                            reviewer_id=test_user["id"],
+                        )
+                        approved_submissions.append(approved_submission.model_dump())
+                        print("✅ Approved test store submission")
 
-                    await prisma.storelistingversion.update(
-                        where={"id": test_submission.store_listing_version_id},
-                        data={"isFeatured": True},
-                    )
-                    featured_count += 1
-                    print("🌟 Marked test agent as FEATURED")
+                        # Mark approved submission as featured
+                        await prisma.storelistingversion.update(
+                            where={"id": test_submission.store_listing_version_id},
+                            data={"isFeatured": True},
+                        )
+                        print("🌟 Marked test agent as FEATURED")
+                    elif random_value < 0.7:  # 30% chance to reject (40% to 70%)
+                        await review_store_submission(
+                            store_listing_version_id=test_submission.store_listing_version_id,
+                            is_approved=False,
+                            external_comments="Test submission rejected - needs improvements",
+                            internal_comments="Auto-rejected test submission for E2E testing",
+                            reviewer_id=test_user["id"],
+                        )
+                        print("❌ Rejected test store submission")
+                    else:  # 30% chance to leave pending (70% to 100%)
+                        print("⏳ Left test submission pending for review")
 
             except Exception as e:
                 print(f"Error creating test store submission: {e}")
@@ -619,6 +620,7 @@ class TestDataCreator:
 
         # Create regular submissions for all users
         for user in self.users:
+            # Get available graphs for this specific user
             user_graphs = [
                 g for g in self.agent_graphs if g.get("userId") == user["id"]
             ]
@@ -629,17 +631,18 @@ class TestDataCreator:
                 )
                 continue
 
+            # Create exactly 4 store submissions per user
             for submission_index in range(4):
                 graph = random.choice(user_graphs)
-                submission_counter += 1
 
                 try:
                     print(
-                        f"Creating store submission for user {user['id']} with graph {graph['id']}"
+                        f"Creating store submission for user {user['id']} with graph {graph['id']} (owner: {graph.get('userId')})"
                     )
 
+                    # Use the API function to create store submission with correct parameters
                     submission = await create_store_submission(
-                        user_id=user["id"],
+                        user_id=user["id"],  # Must match graph's userId
                         agent_id=graph["id"],
                         agent_version=graph.get("version", 1),
                         slug=faker.slug(),
@@ -648,24 +651,22 @@ class TestDataCreator:
                         video_url=get_video_url() if random.random() < 0.3 else None,
                         image_urls=[get_image() for _ in range(3)],
                         description=faker.text(),
-                        categories=[get_category()],
+                        categories=[
+                            get_category()
+                        ],  # Single category from predefined list
                         changes_summary="Initial E2E test submission",
                     )
                     submissions.append(submission.model_dump())
                     print(f"✅ Created store submission: {submission.name}")
 
+                    # Randomly approve, reject, or leave pending the submission
                     if submission.store_listing_version_id:
-                        # DETERMINISTIC: First N submissions are always approved
-                        # First GUARANTEED_FEATURED_AGENTS of those are always featured
-                        should_approve = (
-                            submission_counter <= GUARANTEED_TOP_AGENTS
-                            or random.random() < 0.4
-                        )
-                        should_feature = featured_count < GUARANTEED_FEATURED_AGENTS
-
-                        if should_approve:
+                        random_value = random.random()
+                        if random_value < 0.4:  # 40% chance to approve
                             try:
+                                # Pick a random user as the reviewer (admin)
                                 reviewer_id = random.choice(self.users)["id"]
+
                                 approved_submission = await review_store_submission(
                                     store_listing_version_id=submission.store_listing_version_id,
                                     is_approved=True,
@@ -680,7 +681,16 @@ class TestDataCreator:
                                     f"✅ Approved store submission: {submission.name}"
                                 )
 
-                                if should_feature:
+                                # Mark some agents as featured during creation (30% chance)
+                                # More likely for creators and first submissions
+                                is_creator = user["id"] in [
+                                    p.get("userId") for p in self.profiles
+                                ]
+                                feature_chance = (
+                                    0.5 if is_creator else 0.2
+                                )  # 50% for creators, 20% for others
+
+                                if random.random() < feature_chance:
                                     try:
                                         await prisma.storelistingversion.update(
                                             where={
@@ -688,25 +698,8 @@ class TestDataCreator:
                                             },
                                             data={"isFeatured": True},
                                         )
-                                        featured_count += 1
                                         print(
-                                            f"🌟 Marked agent as FEATURED ({featured_count}/{GUARANTEED_FEATURED_AGENTS}): {submission.name}"
-                                        )
-                                    except Exception as e:
-                                        print(
-                                            f"Warning: Could not mark submission as featured: {e}"
-                                        )
-                                elif random.random() < 0.2:
-                                    try:
-                                        await prisma.storelistingversion.update(
-                                            where={
-                                                "id": submission.store_listing_version_id
-                                            },
-                                            data={"isFeatured": True},
-                                        )
-                                        featured_count += 1
-                                        print(
-                                            f"🌟 Marked agent as FEATURED (bonus): {submission.name}"
+                                            f"🌟 Marked agent as FEATURED: {submission.name}"
                                         )
                                     except Exception as e:
                                         print(
@@ -717,9 +710,11 @@ class TestDataCreator:
                                 print(
                                     f"Warning: Could not approve submission {submission.name}: {e}"
                                 )
-                        elif random.random() < 0.5:
+                        elif random_value < 0.7:  # 30% chance to reject (40% to 70%)
                             try:
+                                # Pick a random user as the reviewer (admin)
                                 reviewer_id = random.choice(self.users)["id"]
+
                                 await review_store_submission(
                                     store_listing_version_id=submission.store_listing_version_id,
                                     is_approved=False,
@@ -734,7 +729,7 @@ class TestDataCreator:
                                 print(
                                     f"Warning: Could not reject submission {submission.name}: {e}"
                                 )
-                        else:
+                        else:  # 30% chance to leave pending (70% to 100%)
                             print(
                                 f"⏳ Left submission pending for review: {submission.name}"
                             )
@@ -748,13 +743,9 @@ class TestDataCreator:
                     traceback.print_exc()
                     continue
 
-        print("\n📊 Store Submissions Summary:")
-        print(f"   Created: {len(submissions)}")
-        print(f"   Approved: {len(approved_submissions)}")
         print(
-            f"   Featured: {featured_count} (guaranteed min: {GUARANTEED_FEATURED_AGENTS})"
+            f"Created {len(submissions)} store submissions, approved {len(approved_submissions)}"
         )
-
         self.store_submissions = submissions
         return submissions
 
@@ -834,15 +825,12 @@ class TestDataCreator:
         print(f"✅ Agent blocks available: {len(self.agent_blocks)}")
         print(f"✅ Agent graphs created: {len(self.agent_graphs)}")
         print(f"✅ Library agents created: {len(self.library_agents)}")
-        print(f"✅ Creator profiles updated: {len(self.profiles)}")
-        print(f"✅ Store submissions created: {len(self.store_submissions)}")
+        print(f"✅ Creator profiles updated: {len(self.profiles)} (some featured)")
+        print(
+            f"✅ Store submissions created: {len(self.store_submissions)} (some marked as featured during creation)"
+        )
         print(f"✅ API keys created: {len(self.api_keys)}")
         print(f"✅ Presets created: {len(self.presets)}")
-        print("\n🎯 Deterministic Guarantees:")
-        print(f"   • Featured agents: >= {GUARANTEED_FEATURED_AGENTS}")
-        print(f"   • Featured creators: >= {GUARANTEED_FEATURED_CREATORS}")
-        print(f"   • Top agents (approved): >= {GUARANTEED_TOP_AGENTS}")
-        print(f"   • Library agents per user: >= {MIN_AGENTS_PER_USER}")
         print("\n🚀 Your E2E test database is ready to use!")
 
 

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/FavoritesSection.test.tsx

@@ -1,185 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen, waitFor } from "@/tests/integrations/test-utils";
-import { FavoritesSection } from "../FavoritesSection/FavoritesSection";
-import { server } from "@/mocks/mock-server";
-import { http, HttpResponse } from "msw";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-const mockFavoriteAgent = {
-  id: "fav-agent-id",
-  graph_id: "fav-graph-id",
-  graph_version: 1,
-  owner_user_id: "test-owner-id",
-  image_url: null,
-  creator_name: "Test Creator",
-  creator_image_url: "https://example.com/avatar.png",
-  status: "READY",
-  created_at: new Date().toISOString(),
-  updated_at: new Date().toISOString(),
-  name: "Favorite Agent Name",
-  description: "Test favorite agent",
-  input_schema: {},
-  output_schema: {},
-  credentials_input_schema: null,
-  has_external_trigger: false,
-  has_human_in_the_loop: false,
-  has_sensitive_action: false,
-  new_output: false,
-  can_access_graph: true,
-  is_latest_version: true,
-  is_favorite: true,
-};
-
-describe("FavoritesSection", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("renders favorites section when there are favorites", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [mockFavoriteAgent],
-          pagination: {
-            total_items: 1,
-            total_pages: 1,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    render(<FavoritesSection searchTerm="" />);
-
-    await waitFor(() => {
-      expect(screen.getByText(/favorites/i)).toBeInTheDocument();
-    });
-  });
-
-  test("renders favorite agent cards", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [mockFavoriteAgent],
-          pagination: {
-            total_items: 1,
-            total_pages: 1,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    render(<FavoritesSection searchTerm="" />);
-
-    await waitFor(() => {
-      expect(screen.getByText("Favorite Agent Name")).toBeInTheDocument();
-    });
-  });
-
-  test("shows agent count", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [mockFavoriteAgent],
-          pagination: {
-            total_items: 1,
-            total_pages: 1,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    render(<FavoritesSection searchTerm="" />);
-
-    await waitFor(() => {
-      expect(screen.getByTestId("agents-count")).toBeInTheDocument();
-    });
-  });
-
-  test("does not render when there are no favorites", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    const { container } = render(<FavoritesSection searchTerm="" />);
-
-    // Wait for loading to complete
-    await waitFor(() => {
-      // Component should return null when no favorites
-      expect(container.textContent).toBe("");
-    });
-  });
-
-  test("filters favorites based on search term", async () => {
-    mockAuthenticatedUser();
-
-    // Mock that returns different results based on search term
-    server.use(
-      http.get("*/api/library/agents/favorites*", ({ request }) => {
-        const url = new URL(request.url);
-        const searchTerm = url.searchParams.get("search_term");
-
-        if (searchTerm === "nonexistent") {
-          return HttpResponse.json({
-            agents: [],
-            pagination: {
-              total_items: 0,
-              total_pages: 0,
-              current_page: 1,
-              page_size: 20,
-            },
-          });
-        }
-
-        return HttpResponse.json({
-          agents: [mockFavoriteAgent],
-          pagination: {
-            total_items: 1,
-            total_pages: 1,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    const { rerender } = render(<FavoritesSection searchTerm="" />);
-
-    await waitFor(() => {
-      expect(screen.getByText("Favorite Agent Name")).toBeInTheDocument();
-    });
-
-    // Rerender with search term that yields no results
-    rerender(<FavoritesSection searchTerm="nonexistent" />);
-
-    await waitFor(() => {
-      expect(screen.queryByText("Favorite Agent Name")).not.toBeInTheDocument();
-    });
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/LibraryAgentCard.test.tsx

@@ -1,122 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen } from "@/tests/integrations/test-utils";
-import { LibraryAgentCard } from "../LibraryAgentCard/LibraryAgentCard";
-import { LibraryAgent } from "@/app/api/__generated__/models/libraryAgent";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-const mockAgent: LibraryAgent = {
-  id: "test-agent-id",
-  graph_id: "test-graph-id",
-  graph_version: 1,
-  owner_user_id: "test-owner-id",
-  image_url: null,
-  creator_name: "Test Creator",
-  creator_image_url: "https://example.com/avatar.png",
-  status: "READY",
-  created_at: new Date().toISOString(),
-  updated_at: new Date().toISOString(),
-  name: "Test Agent Name",
-  description: "Test agent description",
-  input_schema: {},
-  output_schema: {},
-  credentials_input_schema: null,
-  has_external_trigger: false,
-  has_human_in_the_loop: false,
-  has_sensitive_action: false,
-  new_output: false,
-  can_access_graph: true,
-  is_latest_version: true,
-  is_favorite: false,
-};
-
-describe("LibraryAgentCard", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("renders agent name", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    expect(screen.getByText("Test Agent Name")).toBeInTheDocument();
-  });
-
-  test("renders see runs link", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    expect(screen.getByText(/see runs/i)).toBeInTheDocument();
-  });
-
-  test("renders open in builder link when can_access_graph is true", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    expect(screen.getByText(/open in builder/i)).toBeInTheDocument();
-  });
-
-  test("does not render open in builder link when can_access_graph is false", () => {
-    mockAuthenticatedUser();
-    const agentWithoutAccess = { ...mockAgent, can_access_graph: false };
-    render(<LibraryAgentCard agent={agentWithoutAccess} />);
-
-    expect(screen.queryByText(/open in builder/i)).not.toBeInTheDocument();
-  });
-
-  test("shows 'FROM MARKETPLACE' label for marketplace agents", () => {
-    mockAuthenticatedUser();
-    const marketplaceAgent = {
-      ...mockAgent,
-      marketplace_listing: {
-        id: "listing-id",
-        name: "Marketplace Agent",
-        slug: "marketplace-agent",
-        creator: {
-          id: "creator-id",
-          name: "Creator Name",
-          slug: "creator-slug",
-        },
-      },
-    };
-    render(<LibraryAgentCard agent={marketplaceAgent} />);
-
-    expect(screen.getByText(/from marketplace/i)).toBeInTheDocument();
-  });
-
-  test("shows 'Built by you' label for user's own agents", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    expect(screen.getByText(/built by you/i)).toBeInTheDocument();
-  });
-
-  test("renders favorite button", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    // The favorite button should be present (as a heart icon button)
-    const card = screen.getByTestId("library-agent-card");
-    expect(card).toBeInTheDocument();
-  });
-
-  test("links to correct agent detail page", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    const link = screen.getByTestId("library-agent-card-see-runs-link");
-    expect(link).toHaveAttribute("href", "/library/agents/test-agent-id");
-  });
-
-  test("links to correct builder page", () => {
-    mockAuthenticatedUser();
-    render(<LibraryAgentCard agent={mockAgent} />);
-
-    const builderLink = screen.getByTestId(
-      "library-agent-card-open-in-builder-link",
-    );
-    expect(builderLink).toHaveAttribute("href", "/build?flowID=test-graph-id");
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/LibrarySearchBar.test.tsx

@@ -1,53 +0,0 @@
-import { describe, expect, test, vi } from "vitest";
-import { render, screen, fireEvent, waitFor } from "@/tests/integrations/test-utils";
-import { LibrarySearchBar } from "../LibrarySearchBar/LibrarySearchBar";
-
-describe("LibrarySearchBar", () => {
-  test("renders search input", () => {
-    const setSearchTerm = vi.fn();
-    render(<LibrarySearchBar setSearchTerm={setSearchTerm} />);
-
-    expect(screen.getByPlaceholderText(/search agents/i)).toBeInTheDocument();
-  });
-
-  test("renders search icon", () => {
-    const setSearchTerm = vi.fn();
-    const { container } = render(
-      <LibrarySearchBar setSearchTerm={setSearchTerm} />,
-    );
-
-    // Check for the magnifying glass icon (SVG element)
-    const searchIcon = container.querySelector("svg");
-    expect(searchIcon).toBeInTheDocument();
-  });
-
-  test("calls setSearchTerm on input change", async () => {
-    const setSearchTerm = vi.fn();
-    render(<LibrarySearchBar setSearchTerm={setSearchTerm} />);
-
-    const input = screen.getByPlaceholderText(/search agents/i);
-    fireEvent.change(input, { target: { value: "test query" } });
-
-    // The search bar uses debouncing, so we need to wait
-    await waitFor(
-      () => {
-        expect(setSearchTerm).toHaveBeenCalled();
-      },
-      { timeout: 1000 },
-    );
-  });
-
-  test("has correct test id", () => {
-    const setSearchTerm = vi.fn();
-    render(<LibrarySearchBar setSearchTerm={setSearchTerm} />);
-
-    expect(screen.getByTestId("search-bar")).toBeInTheDocument();
-  });
-
-  test("input has correct test id", () => {
-    const setSearchTerm = vi.fn();
-    render(<LibrarySearchBar setSearchTerm={setSearchTerm} />);
-
-    expect(screen.getByTestId("library-textbox")).toBeInTheDocument();
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/LibrarySortMenu.test.tsx

@@ -1,53 +0,0 @@
-import { describe, expect, test, vi } from "vitest";
-import { render, screen, fireEvent, waitFor } from "@/tests/integrations/test-utils";
-import { LibrarySortMenu } from "../LibrarySortMenu/LibrarySortMenu";
-
-describe("LibrarySortMenu", () => {
-  test("renders sort dropdown", () => {
-    const setLibrarySort = vi.fn();
-    render(<LibrarySortMenu setLibrarySort={setLibrarySort} />);
-
-    expect(screen.getByTestId("sort-by-dropdown")).toBeInTheDocument();
-  });
-
-  test("shows 'sort by' label on larger screens", () => {
-    const setLibrarySort = vi.fn();
-    render(<LibrarySortMenu setLibrarySort={setLibrarySort} />);
-
-    expect(screen.getByText(/sort by/i)).toBeInTheDocument();
-  });
-
-  test("shows default placeholder text", () => {
-    const setLibrarySort = vi.fn();
-    render(<LibrarySortMenu setLibrarySort={setLibrarySort} />);
-
-    expect(screen.getByText(/last modified/i)).toBeInTheDocument();
-  });
-
-  test("opens dropdown when clicked", async () => {
-    const setLibrarySort = vi.fn();
-    render(<LibrarySortMenu setLibrarySort={setLibrarySort} />);
-
-    const trigger = screen.getByRole("combobox");
-    fireEvent.click(trigger);
-
-    await waitFor(() => {
-      expect(screen.getByText(/creation date/i)).toBeInTheDocument();
-    });
-  });
-
-  test("shows both sort options in dropdown", async () => {
-    const setLibrarySort = vi.fn();
-    render(<LibrarySortMenu setLibrarySort={setLibrarySort} />);
-
-    const trigger = screen.getByRole("combobox");
-    fireEvent.click(trigger);
-
-    await waitFor(() => {
-      expect(screen.getByText(/creation date/i)).toBeInTheDocument();
-      expect(
-        screen.getAllByText(/last modified/i).length,
-      ).toBeGreaterThanOrEqual(1);
-    });
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/LibraryUploadAgentDialog.test.tsx

@@ -1,78 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen, fireEvent, waitFor } from "@/tests/integrations/test-utils";
-import LibraryUploadAgentDialog from "../LibraryUploadAgentDialog/LibraryUploadAgentDialog";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-describe("LibraryUploadAgentDialog", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("renders upload button", () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    expect(
-      screen.getByRole("button", { name: /upload agent/i }),
-    ).toBeInTheDocument();
-  });
-
-  test("opens dialog when upload button is clicked", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    const uploadButton = screen.getByRole("button", { name: /upload agent/i });
-    fireEvent.click(uploadButton);
-
-    await waitFor(() => {
-      expect(screen.getByText("Upload Agent")).toBeInTheDocument();
-    });
-  });
-
-  test("dialog contains agent name input", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    const uploadButton = screen.getByRole("button", { name: /upload agent/i });
-    fireEvent.click(uploadButton);
-
-    await waitFor(() => {
-      expect(screen.getByLabelText(/agent name/i)).toBeInTheDocument();
-    });
-  });
-
-  test("dialog contains agent description input", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    const uploadButton = screen.getByRole("button", { name: /upload agent/i });
-    fireEvent.click(uploadButton);
-
-    await waitFor(() => {
-      expect(screen.getByLabelText(/agent description/i)).toBeInTheDocument();
-    });
-  });
-
-  test("upload button is disabled when form is incomplete", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    const triggerButton = screen.getByRole("button", { name: /upload agent/i });
-    fireEvent.click(triggerButton);
-
-    await waitFor(() => {
-      const submitButton = screen.getByRole("button", { name: /^upload$/i });
-      expect(submitButton).toBeDisabled();
-    });
-  });
-
-  test("has correct test id on trigger button", () => {
-    mockAuthenticatedUser();
-    render(<LibraryUploadAgentDialog />);
-
-    expect(screen.getByTestId("upload-agent-button")).toBeInTheDocument();
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/auth-state.test.tsx

@@ -1,40 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen } from "@/tests/integrations/test-utils";
-import LibraryPage from "../../page";
-import {
-  mockAuthenticatedUser,
-  mockUnauthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-describe("LibraryPage - Auth State", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("renders page correctly when logged in", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    // Wait for upload button text to appear (indicates page is rendered)
-    expect(
-      await screen.findByText("Upload agent", { exact: false }),
-    ).toBeInTheDocument();
-
-    // Search bar should be visible
-    expect(screen.getByTestId("search-bar")).toBeInTheDocument();
-  });
-
-  test("renders page correctly when logged out", async () => {
-    mockUnauthenticatedUser();
-    render(<LibraryPage />);
-
-    // Wait for upload button text to appear (indicates page is rendered)
-    expect(
-      await screen.findByText("Upload agent", { exact: false }),
-    ).toBeInTheDocument();
-
-    // Search bar should still be visible
-    expect(screen.getByTestId("search-bar")).toBeInTheDocument();
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/empty-state.test.tsx

@@ -1,82 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen, waitFor } from "@/tests/integrations/test-utils";
-import LibraryPage from "../../page";
-import { server } from "@/mocks/mock-server";
-import { http, HttpResponse } from "msw";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-describe("LibraryPage - Empty State", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("handles empty agents list gracefully", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents*", () => {
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    render(<LibraryPage />);
-
-    // Page should still render without crashing
-    // Search bar should be visible even with no agents
-    expect(
-      await screen.findByPlaceholderText(/search agents/i),
-    ).toBeInTheDocument();
-
-    // Upload button should be visible
-    expect(
-      screen.getByRole("button", { name: /upload agent/i }),
-    ).toBeInTheDocument();
-  });
-
-  test("handles empty favorites gracefully", async () => {
-    mockAuthenticatedUser();
-
-    server.use(
-      http.get("*/api/library/agents/favorites*", () => {
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    render(<LibraryPage />);
-
-    // Page should still render without crashing
-    expect(
-      await screen.findByPlaceholderText(/search agents/i),
-    ).toBeInTheDocument();
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/error-handling.test.tsx

@@ -1,59 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen, waitFor } from "@/tests/integrations/test-utils";
-import LibraryPage from "../../page";
-import { server } from "@/mocks/mock-server";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-import { create500Handler } from "@/tests/integrations/helpers/create-500-handler";
-import {
-  getGetV2ListLibraryAgentsMockHandler422,
-  getGetV2ListFavoriteLibraryAgentsMockHandler422,
-} from "@/app/api/__generated__/endpoints/library/library.msw";
-
-describe("LibraryPage - Error Handling", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("handles API 422 error gracefully", async () => {
-    mockAuthenticatedUser();
-
-    server.use(getGetV2ListLibraryAgentsMockHandler422());
-
-    render(<LibraryPage />);
-
-    // Page should still render without crashing
-    // Search bar should be visible even with error
-    await waitFor(() => {
-      expect(screen.getByPlaceholderText(/search agents/i)).toBeInTheDocument();
-    });
-  });
-
-  test("handles favorites API 422 error gracefully", async () => {
-    mockAuthenticatedUser();
-
-    server.use(getGetV2ListFavoriteLibraryAgentsMockHandler422());
-
-    render(<LibraryPage />);
-
-    // Page should still render without crashing
-    await waitFor(() => {
-      expect(screen.getByPlaceholderText(/search agents/i)).toBeInTheDocument();
-    });
-  });
-
-  test("handles API 500 error gracefully", async () => {
-    mockAuthenticatedUser();
-
-    server.use(create500Handler("get", "*/api/library/agents*"));
-
-    render(<LibraryPage />);
-
-    // Page should still render without crashing
-    await waitFor(() => {
-      expect(screen.getByPlaceholderText(/search agents/i)).toBeInTheDocument();
-    });
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/loading-state.test.tsx

@@ -1,55 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen } from "@/tests/integrations/test-utils";
-import LibraryPage from "../../page";
-import { server } from "@/mocks/mock-server";
-import { http, HttpResponse, delay } from "msw";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-describe("LibraryPage - Loading State", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("shows loading spinner while agents are being fetched", async () => {
-    mockAuthenticatedUser();
-
-    // Override handlers to add delay to simulate loading
-    server.use(
-      http.get("*/api/library/agents*", async () => {
-        await delay(500);
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-      http.get("*/api/library/agents/favorites*", async () => {
-        await delay(500);
-        return HttpResponse.json({
-          agents: [],
-          pagination: {
-            total_items: 0,
-            total_pages: 0,
-            current_page: 1,
-            page_size: 20,
-          },
-        });
-      }),
-    );
-
-    const { container } = render(<LibraryPage />);
-
-    // Check for loading spinner (LoadingSpinner component)
-    const loadingElements = container.querySelectorAll(
-      '[class*="animate-spin"]',
-    );
-    expect(loadingElements.length).toBeGreaterThan(0);
-  });
-});

autogpt_platform/frontend/src/app/(platform)/library/components/__tests__/rendering.test.tsx

@@ -1,65 +0,0 @@
-import { describe, expect, test, afterEach } from "vitest";
-import { render, screen, waitFor } from "@/tests/integrations/test-utils";
-import LibraryPage from "../../page";
-import {
-  mockAuthenticatedUser,
-  resetAuthState,
-} from "@/tests/integrations/helpers/mock-supabase-auth";
-
-describe("LibraryPage - Rendering", () => {
-  afterEach(() => {
-    resetAuthState();
-  });
-
-  test("renders search bar", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    expect(
-      await screen.findByPlaceholderText(/search agents/i),
-    ).toBeInTheDocument();
-  });
-
-  test("renders upload agent button", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    expect(
-      await screen.findByRole("button", { name: /upload agent/i }),
-    ).toBeInTheDocument();
-  });
-
-  test("renders agent cards when data is loaded", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    // Wait for agent cards to appear (from mock data)
-    await waitFor(() => {
-      const agentCards = screen.getAllByTestId("library-agent-card");
-      expect(agentCards.length).toBeGreaterThan(0);
-    });
-  });
-
-  test("agent cards display agent name", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    // Wait for agent cards and check they have names
-    await waitFor(() => {
-      const agentNames = screen.getAllByTestId("library-agent-card-name");
-      expect(agentNames.length).toBeGreaterThan(0);
-    });
-  });
-
-  test("agent cards have see runs link", async () => {
-    mockAuthenticatedUser();
-    render(<LibraryPage />);
-
-    await waitFor(() => {
-      const seeRunsLinks = screen.getAllByTestId(
-        "library-agent-card-see-runs-link",
-      );
-      expect(seeRunsLinks.length).toBeGreaterThan(0);
-    });
-  });
-});

autogpt_platform/frontend/src/components/contextual/Chat/components/ChatContainer/useChatContainerAiSdk.ts

@@ -1,246 +0,0 @@
-/**
- * useChatContainerAiSdk - ChatContainer hook using Vercel AI SDK
- *
- * This is a drop-in replacement for useChatContainer that uses @ai-sdk/react
- * instead of the custom streaming implementation. The API surface is identical
- * to enable easy A/B testing and gradual migration.
- */
-
-import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
-import { useEffect, useMemo, useRef } from "react";
-import type { UIMessage } from "ai";
-import { useAiSdkChat } from "../../useAiSdkChat";
-import { usePageContext } from "../../usePageContext";
-import type { ChatMessageData } from "../ChatMessage/useChatMessage";
-import {
-  filterAuthMessages,
-  hasSentInitialPrompt,
-  markInitialPromptSent,
-  processInitialMessages,
-} from "./helpers";
-
-// Helper to convert backend messages to AI SDK UIMessage format
-function convertToUIMessages(
-  messages: SessionDetailResponse["messages"],
-): UIMessage[] {
-  const result: UIMessage[] = [];
-
-  for (const msg of messages) {
-    if (!msg.role || !msg.content) continue;
-
-    // Create parts based on message type
-    const parts: UIMessage["parts"] = [];
-
-    if (msg.role === "user" || msg.role === "assistant") {
-      if (typeof msg.content === "string") {
-        parts.push({ type: "text", text: msg.content });
-      }
-    }
-
-    // Handle tool calls in assistant messages
-    if (msg.role === "assistant" && msg.tool_calls) {
-      for (const toolCall of msg.tool_calls as Array<{
-        id: string;
-        type: string;
-        function: { name: string; arguments: string };
-      }>) {
-        if (toolCall.type === "function") {
-          let args = {};
-          try {
-            args = JSON.parse(toolCall.function.arguments);
-          } catch {
-            // Keep empty args
-          }
-          parts.push({
-            type: `tool-${toolCall.function.name}` as `tool-${string}`,
-            toolCallId: toolCall.id,
-            toolName: toolCall.function.name,
-            state: "input-available",
-            input: args,
-          } as UIMessage["parts"][number]);
-        }
-      }
-    }
-
-    // Handle tool responses
-    if (msg.role === "tool" && msg.tool_call_id) {
-      // Find the matching tool call to get the name
-      const toolName = "unknown";
-      let output: unknown = msg.content;
-      try {
-        output =
-          typeof msg.content === "string"
-            ? JSON.parse(msg.content)
-            : msg.content;
-      } catch {
-        // Keep as string
-      }
-
-      parts.push({
-        type: `tool-${toolName}` as `tool-${string}`,
-        toolCallId: msg.tool_call_id as string,
-        toolName,
-        state: "output-available",
-        output,
-      } as UIMessage["parts"][number]);
-    }
-
-    if (parts.length > 0) {
-      result.push({
-        id: msg.id || `msg-${Date.now()}-${Math.random()}`,
-        role: msg.role === "tool" ? "assistant" : (msg.role as "user" | "assistant"),
-        parts,
-        createdAt: msg.created_at ? new Date(msg.created_at as string) : new Date(),
-      });
-    }
-  }
-
-  return result;
-}
-
-interface Args {
-  sessionId: string | null;
-  initialMessages: SessionDetailResponse["messages"];
-  initialPrompt?: string;
-  onOperationStarted?: () => void;
-}
-
-export function useChatContainerAiSdk({
-  sessionId,
-  initialMessages,
-  initialPrompt,
-  onOperationStarted,
-}: Args) {
-  const { capturePageContext } = usePageContext();
-  const sendMessageRef = useRef<
-    (
-      content: string,
-      isUserMessage?: boolean,
-      context?: { url: string; content: string },
-    ) => Promise<void>
-  >();
-
-  // Convert initial messages to AI SDK format
-  const uiMessages = useMemo(
-    () => convertToUIMessages(initialMessages),
-    [initialMessages],
-  );
-
-  const {
-    messages: aiSdkMessages,
-    streamingChunks,
-    isStreaming,
-    error,
-    isRegionBlockedModalOpen,
-    setIsRegionBlockedModalOpen,
-    sendMessage,
-    stopStreaming,
-  } = useAiSdkChat({
-    sessionId,
-    initialMessages: uiMessages,
-    onOperationStarted,
-  });
-
-  // Keep ref updated for initial prompt handling
-  sendMessageRef.current = sendMessage;
-
-  // Merge AI SDK messages with processed initial messages
-  // This ensures we show both historical messages and new streaming messages
-  const allMessages = useMemo(() => {
-    const processedInitial = processInitialMessages(initialMessages);
-
-    // Build a set of message keys for deduplication
-    const seenKeys = new Set<string>();
-    const result: ChatMessageData[] = [];
-
-    // Add processed initial messages first
-    for (const msg of processedInitial) {
-      const key = getMessageKey(msg);
-      if (!seenKeys.has(key)) {
-        seenKeys.add(key);
-        result.push(msg);
-      }
-    }
-
-    // Add AI SDK messages that aren't duplicates
-    for (const msg of aiSdkMessages) {
-      const key = getMessageKey(msg);
-      if (!seenKeys.has(key)) {
-        seenKeys.add(key);
-        result.push(msg);
-      }
-    }
-
-    return result;
-  }, [initialMessages, aiSdkMessages]);
-
-  // Handle initial prompt
-  useEffect(
-    function handleInitialPrompt() {
-      if (!initialPrompt || !sessionId) return;
-      if (initialMessages.length > 0) return;
-      if (hasSentInitialPrompt(sessionId)) return;
-
-      markInitialPromptSent(sessionId);
-      const context = capturePageContext();
-      sendMessageRef.current?.(initialPrompt, true, context);
-    },
-    [initialPrompt, sessionId, initialMessages.length, capturePageContext],
-  );
-
-  // Send message with page context
-  async function sendMessageWithContext(
-    content: string,
-    isUserMessage: boolean = true,
-  ) {
-    const context = capturePageContext();
-    await sendMessage(content, isUserMessage, context);
-  }
-
-  function handleRegionModalOpenChange(open: boolean) {
-    setIsRegionBlockedModalOpen(open);
-  }
-
-  function handleRegionModalClose() {
-    setIsRegionBlockedModalOpen(false);
-  }
-
-  return {
-    messages: filterAuthMessages(allMessages),
-    streamingChunks,
-    isStreaming,
-    error,
-    isRegionBlockedModalOpen,
-    setIsRegionBlockedModalOpen,
-    sendMessageWithContext,
-    handleRegionModalOpenChange,
-    handleRegionModalClose,
-    sendMessage,
-    stopStreaming,
-  };
-}
-
-// Helper to generate deduplication key for a message
-function getMessageKey(msg: ChatMessageData): string {
-  if (msg.type === "message") {
-    return `msg:${msg.role}:${msg.content}`;
-  } else if (msg.type === "tool_call") {
-    return `toolcall:${msg.toolId}`;
-  } else if (msg.type === "tool_response") {
-    return `toolresponse:${(msg as { toolId?: string }).toolId}`;
-  } else if (
-    msg.type === "operation_started" ||
-    msg.type === "operation_pending" ||
-    msg.type === "operation_in_progress"
-  ) {
-    const typedMsg = msg as {
-      toolId?: string;
-      operationId?: string;
-      toolCallId?: string;
-      toolName?: string;
-    };
-    return `op:${typedMsg.toolId || typedMsg.operationId || typedMsg.toolCallId || ""}:${typedMsg.toolName || ""}`;
-  } else {
-    return `${msg.type}:${JSON.stringify(msg).slice(0, 100)}`;
-  }
-}

autogpt_platform/frontend/src/components/contextual/Chat/components/ChatInput/ChatInput.tsx

@@ -57,7 +57,6 @@ export function ChatInput({
     isStreaming,
     value,
     baseHandleKeyDown,
-    inputId,
   });
 
   return (

autogpt_platform/frontend/src/components/contextual/Chat/components/ChatInput/useVoiceRecording.ts

@@ -15,7 +15,6 @@ interface Args {
   isStreaming?: boolean;
   value: string;
   baseHandleKeyDown: (event: KeyboardEvent<HTMLTextAreaElement>) => void;
-  inputId?: string;
 }
 
 export function useVoiceRecording({
@@ -24,7 +23,6 @@ export function useVoiceRecording({
   isStreaming = false,
   value,
   baseHandleKeyDown,
-  inputId,
 }: Args) {
   const [isRecording, setIsRecording] = useState(false);
   const [isTranscribing, setIsTranscribing] = useState(false);
@@ -105,7 +103,7 @@ export function useVoiceRecording({
         setIsTranscribing(false);
       }
     },
-    [handleTranscription, inputId],
+    [handleTranscription],
   );
 
   const stopRecording = useCallback(() => {
@@ -203,15 +201,6 @@ export function useVoiceRecording({
     }
   }, [error, toast]);
 
-  useEffect(() => {
-    if (!isTranscribing && inputId) {
-      const inputElement = document.getElementById(inputId);
-      if (inputElement) {
-        inputElement.focus();
-      }
-    }
-  }, [isTranscribing, inputId]);
-
   const handleKeyDown = useCallback(
     (event: KeyboardEvent<HTMLTextAreaElement>) => {
       if (event.key === " " && !value.trim() && !isTranscribing) {

autogpt_platform/frontend/src/components/contextual/Chat/useAiSdkChat.ts

@@ -1,421 +0,0 @@
-"use client";
-
-/**
- * useAiSdkChat - Vercel AI SDK integration for CoPilot Chat
- *
- * This hook wraps @ai-sdk/react's useChat to provide:
- * - Streaming chat with the existing Python backend (already AI SDK protocol compatible)
- * - Integration with existing session management
- * - Custom tool response parsing for AutoGPT-specific types
- * - Page context injection
- *
- * The Python backend already implements the AI SDK Data Stream Protocol (v1),
- * so this hook can communicate directly without any backend changes.
- */
-
-import { useChat as useAiSdkChatBase } from "@ai-sdk/react";
-import { DefaultChatTransport, type UIMessage } from "ai";
-import { useCallback, useEffect, useMemo, useRef, useState } from "react";
-import { toast } from "sonner";
-import type { ChatMessageData } from "./components/ChatMessage/useChatMessage";
-
-// Tool response types from the backend
-type OperationType =
-  | "operation_started"
-  | "operation_pending"
-  | "operation_in_progress";
-
-interface ToolOutputBase {
-  type: string;
-  [key: string]: unknown;
-}
-
-interface UseAiSdkChatOptions {
-  sessionId: string | null;
-  initialMessages?: UIMessage[];
-  onOperationStarted?: () => void;
-  onStreamingChange?: (isStreaming: boolean) => void;
-}
-
-/**
- * Parse tool output from AI SDK message parts into ChatMessageData format
- */
-function parseToolOutput(
-  toolCallId: string,
-  toolName: string,
-  output: unknown,
-): ChatMessageData | null {
-  if (!output) return null;
-
-  let parsed: ToolOutputBase;
-  try {
-    parsed =
-      typeof output === "string"
-        ? JSON.parse(output)
-        : (output as ToolOutputBase);
-  } catch {
-    return null;
-  }
-
-  const type = parsed.type;
-
-  // Handle operation status types
-  if (
-    type === "operation_started" ||
-    type === "operation_pending" ||
-    type === "operation_in_progress"
-  ) {
-    return {
-      type: type as OperationType,
-      toolId: toolCallId,
-      toolName: toolName,
-      operationId: (parsed.operation_id as string) || undefined,
-      message: (parsed.message as string) || undefined,
-      timestamp: new Date(),
-    } as ChatMessageData;
-  }
-
-  // Handle agent carousel
-  if (type === "agent_carousel" && Array.isArray(parsed.agents)) {
-    return {
-      type: "agent_carousel",
-      toolId: toolCallId,
-      toolName: toolName,
-      agents: parsed.agents,
-      timestamp: new Date(),
-    } as ChatMessageData;
-  }
-
-  // Handle execution started
-  if (type === "execution_started") {
-    return {
-      type: "execution_started",
-      toolId: toolCallId,
-      toolName: toolName,
-      graphId: parsed.graph_id as string,
-      graphVersion: parsed.graph_version as number,
-      graphExecId: parsed.graph_exec_id as string,
-      nodeExecIds: parsed.node_exec_ids as string[],
-      timestamp: new Date(),
-    } as ChatMessageData;
-  }
-
-  // Handle error responses
-  if (type === "error") {
-    return {
-      type: "tool_response",
-      toolId: toolCallId,
-      toolName: toolName,
-      result: parsed,
-      success: false,
-      timestamp: new Date(),
-    } as ChatMessageData;
-  }
-
-  // Handle clarification questions
-  if (type === "clarification_questions" && Array.isArray(parsed.questions)) {
-    return {
-      type: "clarification_questions",
-      toolId: toolCallId,
-      toolName: toolName,
-      questions: parsed.questions,
-      timestamp: new Date(),
-    } as ChatMessageData;
-  }
-
-  // Handle credentials needed
-  if (type === "credentials_needed" || type === "setup_requirements") {
-    const credentials = parsed.credentials as
-      | Array<{
-          provider: string;
-          provider_name: string;
-          credential_type: string;
-          scopes?: string[];
-        }>
-      | undefined;
-    if (credentials && credentials.length > 0) {
-      return {
-        type: "credentials_needed",
-        toolId: toolCallId,
-        toolName: toolName,
-        credentials: credentials,
-        timestamp: new Date(),
-      } as ChatMessageData;
-    }
-  }
-
-  // Default: generic tool response
-  return {
-    type: "tool_response",
-    toolId: toolCallId,
-    toolName: toolName,
-    result: parsed,
-    success: true,
-    timestamp: new Date(),
-  } as ChatMessageData;
-}
-
-/**
- * Convert AI SDK UIMessage parts to ChatMessageData array
- */
-function convertMessageToChatData(message: UIMessage): ChatMessageData[] {
-  const result: ChatMessageData[] = [];
-
-  for (const part of message.parts) {
-    switch (part.type) {
-      case "text":
-        if (part.text.trim()) {
-          result.push({
-            type: "message",
-            role: message.role as "user" | "assistant",
-            content: part.text,
-            timestamp: new Date(message.createdAt || Date.now()),
-          });
-        }
-        break;
-
-      default:
-        // Handle tool parts (tool-*)
-        if (part.type.startsWith("tool-")) {
-          const toolPart = part as {
-            type: string;
-            toolCallId: string;
-            toolName: string;
-            state: string;
-            input?: Record<string, unknown>;
-            output?: unknown;
-          };
-
-          // Show tool call in progress
-          if (
-            toolPart.state === "input-streaming" ||
-            toolPart.state === "input-available"
-          ) {
-            result.push({
-              type: "tool_call",
-              toolId: toolPart.toolCallId,
-              toolName: toolPart.toolName,
-              arguments: toolPart.input || {},
-              timestamp: new Date(),
-            });
-          }
-
-          // Parse tool output when available
-          if (
-            toolPart.state === "output-available" &&
-            toolPart.output !== undefined
-          ) {
-            const parsed = parseToolOutput(
-              toolPart.toolCallId,
-              toolPart.toolName,
-              toolPart.output,
-            );
-            if (parsed) {
-              result.push(parsed);
-            }
-          }
-
-          // Handle tool errors
-          if (toolPart.state === "output-error") {
-            result.push({
-              type: "tool_response",
-              toolId: toolPart.toolCallId,
-              toolName: toolPart.toolName,
-              response: {
-                type: "error",
-                message: (toolPart as { errorText?: string }).errorText,
-              },
-              success: false,
-              timestamp: new Date(),
-            } as ChatMessageData);
-          }
-        }
-        break;
-    }
-  }
-
-  return result;
-}
-
-export function useAiSdkChat({
-  sessionId,
-  initialMessages = [],
-  onOperationStarted,
-  onStreamingChange,
-}: UseAiSdkChatOptions) {
-  const [isRegionBlockedModalOpen, setIsRegionBlockedModalOpen] =
-    useState(false);
-  const previousSessionIdRef = useRef<string | null>(null);
-  const hasNotifiedOperationRef = useRef<Set<string>>(new Set());
-
-  // Create transport with session-specific endpoint
-  const transport = useMemo(() => {
-    if (!sessionId) return undefined;
-    return new DefaultChatTransport({
-      api: `/api/chat/sessions/${sessionId}/stream`,
-      headers: {
-        "Content-Type": "application/json",
-      },
-    });
-  }, [sessionId]);
-
-  const {
-    messages: aiMessages,
-    status,
-    error,
-    stop,
-    setMessages,
-    sendMessage: aiSendMessage,
-  } = useAiSdkChatBase({
-    transport,
-    initialMessages,
-    onError: (err) => {
-      console.error("[useAiSdkChat] Error:", err);
-
-      // Check for region blocking
-      if (
-        err.message?.toLowerCase().includes("not available in your region") ||
-        (err as { code?: string }).code === "MODEL_NOT_AVAILABLE_REGION"
-      ) {
-        setIsRegionBlockedModalOpen(true);
-        return;
-      }
-
-      toast.error("Chat Error", {
-        description: err.message || "An error occurred",
-      });
-    },
-    onFinish: ({ message }) => {
-      console.info("[useAiSdkChat] Message finished:", {
-        id: message.id,
-        partsCount: message.parts.length,
-      });
-    },
-  });
-
-  // Track streaming status
-  const isStreaming = status === "streaming" || status === "submitted";
-
-  // Notify parent of streaming changes
-  useEffect(() => {
-    onStreamingChange?.(isStreaming);
-  }, [isStreaming, onStreamingChange]);
-
-  // Handle session changes - reset state
-  useEffect(() => {
-    if (sessionId === previousSessionIdRef.current) return;
-
-    if (previousSessionIdRef.current && status === "streaming") {
-      stop();
-    }
-
-    previousSessionIdRef.current = sessionId;
-    hasNotifiedOperationRef.current = new Set();
-
-    if (sessionId) {
-      setMessages(initialMessages);
-    }
-  }, [sessionId, status, stop, setMessages, initialMessages]);
-
-  // Convert AI SDK messages to ChatMessageData format
-  const messages = useMemo(() => {
-    const result: ChatMessageData[] = [];
-
-    for (const message of aiMessages) {
-      const converted = convertMessageToChatData(message);
-      result.push(...converted);
-
-      // Check for operation_started and notify
-      for (const msg of converted) {
-        if (
-          msg.type === "operation_started" &&
-          !hasNotifiedOperationRef.current.has(
-            (msg as { toolId?: string }).toolId || "",
-          )
-        ) {
-          hasNotifiedOperationRef.current.add(
-            (msg as { toolId?: string }).toolId || "",
-          );
-          onOperationStarted?.();
-        }
-      }
-    }
-
-    return result;
-  }, [aiMessages, onOperationStarted]);
-
-  // Get streaming text chunks from the last assistant message
-  const streamingChunks = useMemo(() => {
-    if (!isStreaming) return [];
-
-    const lastMessage = aiMessages[aiMessages.length - 1];
-    if (!lastMessage || lastMessage.role !== "assistant") return [];
-
-    const chunks: string[] = [];
-    for (const part of lastMessage.parts) {
-      if (part.type === "text" && part.text) {
-        chunks.push(part.text);
-      }
-    }
-
-    return chunks;
-  }, [aiMessages, isStreaming]);
-
-  // Send message with optional context
-  const sendMessage = useCallback(
-    async (
-      content: string,
-      isUserMessage: boolean = true,
-      context?: { url: string; content: string },
-    ) => {
-      if (!sessionId || !transport) {
-        console.error("[useAiSdkChat] Cannot send message: no session");
-        return;
-      }
-
-      setIsRegionBlockedModalOpen(false);
-
-      try {
-        await aiSendMessage(
-          { text: content },
-          {
-            body: {
-              is_user_message: isUserMessage,
-              context: context || null,
-            },
-          },
-        );
-      } catch (err) {
-        console.error("[useAiSdkChat] Failed to send message:", err);
-
-        if (err instanceof Error && err.name === "AbortError") return;
-
-        toast.error("Failed to send message", {
-          description:
-            err instanceof Error ? err.message : "Failed to send message",
-        });
-      }
-    },
-    [sessionId, transport, aiSendMessage],
-  );
-
-  // Stop streaming
-  const stopStreaming = useCallback(() => {
-    stop();
-  }, [stop]);
-
-  return {
-    messages,
-    streamingChunks,
-    isStreaming,
-    error,
-    status,
-    isRegionBlockedModalOpen,
-    setIsRegionBlockedModalOpen,
-    sendMessage,
-    stopStreaming,
-    // Expose raw AI SDK state for advanced use cases
-    aiMessages,
-    setAiMessages: setMessages,
-  };
-}

autogpt_platform/frontend/src/components/contextual/CredentialsInput/helpers.ts

@@ -26,6 +26,7 @@ export const providerIcons: Partial<
   nvidia: fallbackIcon,
   discord: FaDiscord,
   d_id: fallbackIcon,
+  elevenlabs: fallbackIcon,
   google_maps: FaGoogle,
   jina: fallbackIcon,
   ideogram: fallbackIcon,

autogpt_platform/frontend/src/tests/library.spec.ts

@@ -59,13 +59,12 @@ test.describe("Library", () => {
   });
 
   test("pagination works correctly", async ({ page }, testInfo) => {
-    test.setTimeout(testInfo.timeout * 3);
+    test.setTimeout(testInfo.timeout * 3); // Increase timeout for pagination operations
     await page.goto("/library");
 
-    const PAGE_SIZE = 20;
     const paginationResult = await libraryPage.testPagination();
 
-    if (paginationResult.initialCount >= PAGE_SIZE) {
+    if (paginationResult.initialCount >= 10) {
       expect(paginationResult.finalCount).toBeGreaterThanOrEqual(
         paginationResult.initialCount,
       );
@@ -134,10 +133,7 @@ test.describe("Library", () => {
     test.expect(clearedSearchValue).toBe("");
   });
 
-  test("pagination while searching works correctly", async ({
-    page,
-  }, testInfo) => {
-    test.setTimeout(testInfo.timeout * 3);
+  test("pagination while searching works correctly", async ({ page }) => {
     await page.goto("/library");
 
     const allAgents = await libraryPage.getAgents();
@@ -156,10 +152,9 @@ test.describe("Library", () => {
     );
     expect(matchingResults.length).toEqual(initialSearchResults.length);
 
-    const PAGE_SIZE = 20;
     const searchPaginationResult = await libraryPage.testPagination();
 
-    if (searchPaginationResult.initialCount >= PAGE_SIZE) {
+    if (searchPaginationResult.initialCount >= 10) {
       expect(searchPaginationResult.finalCount).toBeGreaterThanOrEqual(
         searchPaginationResult.initialCount,
       );

autogpt_platform/frontend/src/tests/marketplace-creator.spec.ts

@@ -69,12 +69,9 @@ test.describe("Marketplace Creator Page – Basic Functionality", () => {
       await marketplacePage.getFirstCreatorProfile(page);
     await firstCreatorProfile.click();
     await page.waitForURL("**/marketplace/creator/**");
-    await page.waitForLoadState("networkidle").catch(() => {});
-
     const firstAgent = page
       .locator('[data-testid="store-card"]:visible')
       .first();
-    await firstAgent.waitFor({ state: "visible", timeout: 30000 });
 
     await firstAgent.click();
     await page.waitForURL("**/marketplace/agent/**");

autogpt_platform/frontend/src/tests/marketplace.spec.ts

@@ -77,6 +77,7 @@ test.describe("Marketplace – Basic Functionality", () => {
 
     const firstFeaturedAgent =
       await marketplacePage.getFirstFeaturedAgent(page);
+    await firstFeaturedAgent.waitFor({ state: "visible" });
     await firstFeaturedAgent.click();
     await page.waitForURL("**/marketplace/agent/**");
     await matchesUrl(page, /\/marketplace\/agent\/.+/);
@@ -115,15 +116,7 @@ test.describe("Marketplace – Basic Functionality", () => {
     const searchTerm = page.getByText("DummyInput").first();
     await isVisible(searchTerm);
 
-    await page.waitForLoadState("networkidle").catch(() => {});
-
-    await page
-      .waitForFunction(
-        () =>
-          document.querySelectorAll('[data-testid="store-card"]').length > 0,
-        { timeout: 15000 },
-      )
-      .catch(() => console.log("No search results appeared within timeout"));
+    await page.waitForTimeout(10000);
 
     const results = await marketplacePage.getSearchResultsCount(page);
     expect(results).toBeGreaterThan(0);

autogpt_platform/frontend/src/tests/pages/library.page.ts

@@ -300,27 +300,21 @@ export class LibraryPage extends BasePage {
   async scrollToLoadMore(): Promise<void> {
     console.log(`scrolling to load more agents`);
 
-    const initialCount = await this.getAgentCountByListLength();
-    console.log(`Initial agent count (DOM cards): ${initialCount}`);
+    // Get initial agent count
+    const initialCount = await this.getAgentCount();
+    console.log(`Initial agent count: ${initialCount}`);
 
+    // Scroll down to trigger pagination
     await this.scrollToBottom();
 
-    await this.page
-      .waitForLoadState("networkidle", { timeout: 10000 })
-      .catch(() => console.log("Network idle timeout, continuing..."));
+    // Wait for potential new agents to load
+    await this.page.waitForTimeout(2000);
 
-    await this.page
-      .waitForFunction(
-        (prevCount) =>
-          document.querySelectorAll('[data-testid="library-agent-card"]')
-            .length > prevCount,
-        initialCount,
-        { timeout: 5000 },
-      )
-      .catch(() => {});
+    // Check if more agents loaded
+    const newCount = await this.getAgentCount();
+    console.log(`New agent count after scroll: ${newCount}`);
 
-    const newCount = await this.getAgentCountByListLength();
-    console.log(`New agent count after scroll (DOM cards): ${newCount}`);
+    return;
   }
 
   async testPagination(): Promise<{

autogpt_platform/frontend/src/tests/pages/marketplace.page.ts

@@ -9,7 +9,6 @@ export class MarketplacePage extends BasePage {
 
   async goto(page: Page) {
     await page.goto("/marketplace");
-    await page.waitForLoadState("networkidle").catch(() => {});
   }
 
   async getMarketplaceTitle(page: Page) {
@@ -110,24 +109,16 @@ export class MarketplacePage extends BasePage {
 
   async getFirstFeaturedAgent(page: Page) {
     const { getId } = getSelectors(page);
-    const card = getId("featured-store-card").first();
-    await card.waitFor({ state: "visible", timeout: 30000 });
-    return card;
+    return getId("featured-store-card").first();
   }
 
   async getFirstTopAgent() {
-    const card = this.page
-      .locator('[data-testid="store-card"]:visible')
-      .first();
-    await card.waitFor({ state: "visible", timeout: 30000 });
-    return card;
+    return this.page.locator('[data-testid="store-card"]:visible').first();
   }
 
   async getFirstCreatorProfile(page: Page) {
     const { getId } = getSelectors(page);
-    const card = getId("creator-card").first();
-    await card.waitFor({ state: "visible", timeout: 30000 });
-    return card;
+    return getId("creator-card").first();
   }
 
   async getSearchResultsCount(page: Page) {

docs/integrations/README.md

@@ -233,6 +233,7 @@ Below is a comprehensive list of all available blocks, categorized by their prim
 | [Stagehand Extract](block-integrations/stagehand/blocks.md#stagehand-extract) | Extract structured data from a webpage |
 | [Stagehand Observe](block-integrations/stagehand/blocks.md#stagehand-observe) | Find suggested actions for your workflows |
 | [Unreal Text To Speech](block-integrations/llm.md#unreal-text-to-speech) | Converts text to speech using the Unreal Speech API |
+| [Video Narration](block-integrations/video/narration.md#video-narration) | Generate AI narration and add to video |
 
 ## Search and Information Retrieval
 
@@ -472,9 +473,13 @@ Below is a comprehensive list of all available blocks, categorized by their prim
 
 | Block Name | Description |
 |------------|-------------|
-| [Add Audio To Video](block-integrations/multimedia.md#add-audio-to-video) | Block to attach an audio file to a video file using moviepy |
-| [Loop Video](block-integrations/multimedia.md#loop-video) | Block to loop a video to a given duration or number of repeats |
-| [Media Duration](block-integrations/multimedia.md#media-duration) | Block to get the duration of a media file |
+| [Add Audio To Video](block-integrations/video/add_audio.md#add-audio-to-video) | Block to attach an audio file to a video file using moviepy |
+| [Loop Video](block-integrations/video/loop.md#loop-video) | Block to loop a video to a given duration or number of repeats |
+| [Media Duration](block-integrations/video/duration.md#media-duration) | Block to get the duration of a media file |
+| [Video Clip](block-integrations/video/clip.md#video-clip) | Extract a time segment from a video |
+| [Video Concat](block-integrations/video/concat.md#video-concat) | Merge multiple video clips into one continuous video |
+| [Video Download](block-integrations/video/download.md#video-download) | Download video from URL (YouTube, Vimeo, news sites, direct links) |
+| [Video Text Overlay](block-integrations/video/text_overlay.md#video-text-overlay) | Add text overlay/caption to video |
 
 ## Productivity
 

docs/integrations/SUMMARY.md

@@ -85,7 +85,6 @@
 * [LLM](block-integrations/llm.md)
 * [Logic](block-integrations/logic.md)
 * [Misc](block-integrations/misc.md)
-* [Multimedia](block-integrations/multimedia.md)
 * [Notion Create Page](block-integrations/notion/create_page.md)
 * [Notion Read Database](block-integrations/notion/read_database.md)
 * [Notion Read Page](block-integrations/notion/read_page.md)
@@ -129,5 +128,13 @@
 * [Twitter Timeline](block-integrations/twitter/timeline.md)
 * [Twitter Tweet Lookup](block-integrations/twitter/tweet_lookup.md)
 * [Twitter User Lookup](block-integrations/twitter/user_lookup.md)
+* [Video Add Audio](block-integrations/video/add_audio.md)
+* [Video Clip](block-integrations/video/clip.md)
+* [Video Concat](block-integrations/video/concat.md)
+* [Video Download](block-integrations/video/download.md)
+* [Video Duration](block-integrations/video/duration.md)
+* [Video Loop](block-integrations/video/loop.md)
+* [Video Narration](block-integrations/video/narration.md)
+* [Video Text Overlay](block-integrations/video/text_overlay.md)
 * [Wolfram LLM API](block-integrations/wolfram/llm_api.md)
 * [Zerobounce Validate Emails](block-integrations/zerobounce/validate_emails.md)

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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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-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" \| "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-3-7-sonnet-20250219" \| "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/integrations/block-integrations/stagehand/blocks.md

@@ -20,7 +20,7 @@ Configure timeouts for DOM settlement and page loading. Variables can be passed
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
-| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
+| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-3-7-sonnet-20250219" | No |
 | url | URL to navigate to. | str | Yes |
 | action | Action to perform. Suggested actions are: click, fill, type, press, scroll, select from dropdown. For multi-step actions, add an entry for each step. | List[str] | Yes |
 | variables | Variables to use in the action. Variables contains data you want the action to use. | Dict[str, str] | No |
@@ -65,7 +65,7 @@ Supports searching within iframes and configurable timeouts for dynamic content
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
-| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
+| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-3-7-sonnet-20250219" | No |
 | url | URL to navigate to. | str | Yes |
 | instruction | Natural language description of elements or actions to discover. | str | Yes |
 | iframes | Whether to search within iframes. If True, Stagehand will search for actions within iframes. | bool | No |
@@ -106,7 +106,7 @@ Use this to explore a page's interactive elements before building automated work
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
-| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
+| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-3-7-sonnet-20250219" | No |
 | url | URL to navigate to. | str | Yes |
 | instruction | Natural language description of elements or actions to discover. | str | Yes |
 | iframes | Whether to search within iframes. If True, Stagehand will search for actions within iframes. | bool | No |

docs/integrations/block-integrations/video/add_audio.md

@@ -0,0 +1,39 @@
+# Video Add Audio
+<!-- MANUAL: file_description -->
+This block allows you to attach a separate audio track to a video file, replacing or combining with the original audio.
+<!-- END MANUAL -->
+
+## Add Audio To Video
+
+### What it is
+Block to attach an audio file to a video file using moviepy.
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy to combine video and audio files. It loads the video and audio inputs (which can be URLs, data URIs, or local paths), optionally scales the audio volume, then writes the combined result to a new video file using H.264 video codec and AAC audio codec.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| video_in | Video input (URL, data URI, or local path). | str (file) | Yes |
+| audio_in | Audio input (URL, data URI, or local path). | str (file) | Yes |
+| volume | Volume scale for the newly attached audio track (1.0 = original). | float | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Final video (with attached audio), as a path or data URI. | str (file) |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Adding background music to a silent screen recording
+- Replacing original audio with a voiceover or translated audio track
+- Combining AI-generated speech with stock footage
+- Adding sound effects to video content
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/clip.md

@@ -0,0 +1,41 @@
+# Video Clip
+<!-- MANUAL: file_description -->
+This block extracts a specific time segment from a video file, allowing you to trim videos to precise start and end times.
+<!-- END MANUAL -->
+
+## Video Clip
+
+### What it is
+Extract a time segment from a video
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy's `subclipped` function to extract a portion of the video between specified start and end times. It validates that end time is greater than start time, then creates a new video file containing only the selected segment. The output is encoded with H.264 video codec and AAC audio codec, preserving both video and audio from the original clip.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| video_in | Input video (URL, data URI, or local path) | str (file) | Yes |
+| start_time | Start time in seconds | float | Yes |
+| end_time | End time in seconds | float | Yes |
+| output_format | Output format | "mp4" \| "webm" \| "mkv" \| "mov" | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Clipped video file (path or data URI) | str (file) |
+| duration | Clip duration in seconds | float |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Extracting highlights from a longer video
+- Trimming intro/outro from recorded content
+- Creating short clips for social media from longer videos
+- Isolating specific segments for further processing in a workflow
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/concat.md

@@ -0,0 +1,41 @@
+# Video Concat
+<!-- MANUAL: file_description -->
+This block merges multiple video clips into a single continuous video, with optional transitions between clips.
+<!-- END MANUAL -->
+
+## Video Concat
+
+### What it is
+Merge multiple video clips into one continuous video
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy's `concatenate_videoclips` function to join multiple videos in sequence. It supports three transition modes: **none** (direct concatenation), **crossfade** (smooth blending where clips overlap), and **fade_black** (each clip fades out to black and the next fades in). At least 2 videos are required. The output is encoded with H.264 video codec and AAC audio codec.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| videos | List of video files to concatenate (in order) | List[str (file)] | Yes |
+| transition | Transition between clips | "none" \| "crossfade" \| "fade_black" | No |
+| transition_duration | Transition duration in seconds | int | No |
+| output_format | Output format | "mp4" \| "webm" \| "mkv" \| "mov" | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Concatenated video file (path or data URI) | str (file) |
+| total_duration | Total duration in seconds | float |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Combining multiple clips into a compilation video
+- Assembling intro, main content, and outro segments
+- Creating montages from multiple source videos
+- Building video playlists or slideshows with transitions
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/download.md

@@ -0,0 +1,42 @@
+# Video Download
+<!-- MANUAL: file_description -->
+This block downloads videos from URLs, supporting a wide range of video platforms and direct links.
+<!-- END MANUAL -->
+
+## Video Download
+
+### What it is
+Download video from URL (YouTube, Vimeo, news sites, direct links)
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses yt-dlp, a powerful video downloading library that supports over 1000 websites. It accepts a URL, quality preference, and output format, then downloads the video while merging the best available video and audio streams for the selected quality. Quality options: **best** (highest available), **1080p/720p/480p** (maximum resolution at that height), **audio_only** (extracts just the audio track).
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| url | URL of the video to download (YouTube, Vimeo, direct link, etc.) | str | Yes |
+| quality | Video quality preference | "best" \| "1080p" \| "720p" \| "480p" \| "audio_only" | No |
+| output_format | Output video format | "mp4" \| "webm" \| "mkv" | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_file | Downloaded video (path or data URI) | str (file) |
+| duration | Video duration in seconds | float |
+| title | Video title from source | str |
+| source_url | Original source URL | str |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Downloading source videos for editing or remixing
+- Archiving video content for offline processing
+- Extracting audio from videos for transcription or podcast creation
+- Gathering video content for automated content pipelines
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/duration.md

@@ -0,0 +1,38 @@
+# Video Duration
+<!-- MANUAL: file_description -->
+This block retrieves the duration of video or audio files, useful for planning and conditional logic in media workflows.
+<!-- END MANUAL -->
+
+## Media Duration
+
+### What it is
+Block to get the duration of a media file.
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy to load the media file and extract its duration property. It supports both video files (using VideoFileClip) and audio files (using AudioFileClip), determined by the `is_video` flag. The media can be provided as a URL, data URI, or local file path. The duration is returned in seconds as a floating-point number.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| media_in | Media input (URL, data URI, or local path). | str (file) | Yes |
+| is_video | Whether the media is a video (True) or audio (False). | bool | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| duration | Duration of the media file (in seconds). | float |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Checking video length before processing to avoid timeout issues
+- Calculating how many times to loop a video to reach a target duration
+- Validating that uploaded content meets length requirements
+- Building conditional workflows based on media duration
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/loop.md

@@ -0,0 +1,39 @@
+# Video Loop
+<!-- MANUAL: file_description -->
+This block repeats a video to extend its duration, either to a specific length or a set number of repetitions.
+<!-- END MANUAL -->
+
+## Loop Video
+
+### What it is
+Block to loop a video to a given duration or number of repeats.
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy's Loop effect to repeat a video clip. You can specify either a target duration (the video will repeat until reaching that length) or a number of loops (the video will repeat that many times). The Loop effect handles both video and audio looping automatically, maintaining sync. Either `duration` or `n_loops` must be provided. The output is encoded with H.264 video codec and AAC audio codec.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| video_in | The input video (can be a URL, data URI, or local path). | str (file) | Yes |
+| duration | Target duration (in seconds) to loop the video to. If omitted, defaults to no looping. | float | No |
+| n_loops | Number of times to repeat the video. If omitted, defaults to 1 (no repeat). | int | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Looped video returned either as a relative path or a data URI. | str |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Extending a short background video to match the length of narration audio
+- Creating seamless looping content for digital signage
+- Repeating a product demo video multiple times for emphasis
+- Extending short clips to meet minimum duration requirements for platforms
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/narration.md

@@ -0,0 +1,44 @@
+# Video Narration
+<!-- MANUAL: file_description -->
+This block generates AI voiceover narration using ElevenLabs and adds it to a video, with flexible audio mixing options.
+<!-- END MANUAL -->
+
+## Video Narration
+
+### What it is
+Generate AI narration and add to video
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses ElevenLabs text-to-speech API to generate natural-sounding narration from your script. It then combines the narration with the video using MoviePy. Three audio mixing modes are available: **replace** (completely replaces original audio), **mix** (blends narration with original audio at configurable volumes), and **ducking** (similar to mix but applies stronger attenuation to original audio, making narration more prominent). The block outputs both the final video and the generated audio file separately.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| video_in | Input video (URL, data URI, or local path) | str (file) | Yes |
+| script | Narration script text | str | Yes |
+| voice_id | ElevenLabs voice ID | str | No |
+| model_id | ElevenLabs TTS model | "eleven_multilingual_v2" \| "eleven_flash_v2_5" \| "eleven_turbo_v2_5" \| "eleven_turbo_v2" | No |
+| mix_mode | How to combine with original audio. 'ducking' applies stronger attenuation than 'mix'. | "replace" \| "mix" \| "ducking" | No |
+| narration_volume | Narration volume (0.0 to 2.0) | float | No |
+| original_volume | Original audio volume when mixing (0.0 to 1.0) | float | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Video with narration (path or data URI) | str (file) |
+| audio_file | Generated audio file (path or data URI) | str (file) |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Adding professional voiceover to product demos or tutorials
+- Creating narrated explainer videos from screen recordings
+- Generating multi-language versions of video content
+- Adding commentary to gameplay or walkthrough videos
+<!-- END MANUAL -->
+
+---

docs/integrations/block-integrations/video/text_overlay.md

@@ -0,0 +1,44 @@
+# Video Text Overlay
+<!-- MANUAL: file_description -->
+This block adds customizable text captions or titles to videos, with control over positioning, timing, and styling.
+<!-- END MANUAL -->
+
+## Video Text Overlay
+
+### What it is
+Add text overlay/caption to video
+
+### How it works
+<!-- MANUAL: how_it_works -->
+The block uses MoviePy's TextClip and CompositeVideoClip to render text onto video frames. The text is created as a separate clip with configurable font size, color, and optional background color, then composited over the video at the specified position. Timing can be controlled to show text only during specific portions of the video. Position options include center alignments (top, center, bottom) and corner positions (top-left, top-right, bottom-left, bottom-right). The output is encoded with H.264 video codec and AAC audio codec.
+<!-- END MANUAL -->
+
+### Inputs
+
+| Input | Description | Type | Required |
+|-------|-------------|------|----------|
+| video_in | Input video (URL, data URI, or local path) | str (file) | Yes |
+| text | Text to overlay on video | str | Yes |
+| position | Position of text on screen | "top" \| "center" \| "bottom" \| "top-left" \| "top-right" \| "bottom-left" \| "bottom-right" | No |
+| start_time | When to show text (seconds). None = entire video | float | No |
+| end_time | When to hide text (seconds). None = until end | float | No |
+| font_size | Font size | int | No |
+| font_color | Font color (hex or name) | str | No |
+| bg_color | Background color behind text (None for transparent) | str | No |
+
+### Outputs
+
+| Output | Description | Type |
+|--------|-------------|------|
+| error | Error message if the operation failed | str |
+| video_out | Video with text overlay (path or data URI) | str (file) |
+
+### Possible use case
+<!-- MANUAL: use_case -->
+- Adding titles or chapter headings to video content
+- Creating lower-thirds with speaker names or captions
+- Watermarking videos with branding text
+- Adding call-to-action text at specific moments in a video
+<!-- END MANUAL -->
+
+---