fix(frontend): use signed URL redirect for workspace downloads to prevent truncation

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.github/workflows/classic-autogpt-ci.yml

@@ -139,7 +139,7 @@ jobs:
 
       - name: Upload logs to artifact
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: test-logs
           path: classic/original_autogpt/logs/

.github/workflows/classic-forge-ci.yml

@@ -237,7 +237,7 @@ jobs:
 
       - name: Upload logs to artifact
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: test-logs
           path: classic/forge/logs/

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

@@ -149,7 +149,7 @@ jobs:
           driver-opts: network=host
 
       - name: Set up Platform - Expose GHA cache to docker buildx CLI
-        uses: crazy-max/ghaction-github-runtime@v3
+        uses: crazy-max/ghaction-github-runtime@v4
 
       - name: Set up Platform - Build Docker images (with cache)
         working-directory: autogpt_platform
@@ -269,7 +269,7 @@ jobs:
 
       - name: Upload Playwright report
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: playwright-report
           path: playwright-report
@@ -278,7 +278,7 @@ jobs:
 
       - name: Upload Playwright test results
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: playwright-test-results
           path: test-results

autogpt_platform/backend/Dockerfile

@@ -111,13 +111,29 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # Copy poetry (build-time only, for `poetry install --only-root` to create entry points)
 COPY --from=builder /usr/local/lib/python3* /usr/local/lib/python3*
 COPY --from=builder /usr/local/bin/poetry /usr/local/bin/poetry
-# Copy Node.js installation for Prisma
+# Copy Node.js installation for Prisma and agent-browser.
+# npm/npx are symlinks in the builder (-> ../lib/node_modules/npm/bin/*-cli.js);
+# COPY resolves them to regular files, breaking require() paths.  Recreate as
+# proper symlinks so npm/npx can find their modules.
 COPY --from=builder /usr/bin/node /usr/bin/node
 COPY --from=builder /usr/lib/node_modules /usr/lib/node_modules
-COPY --from=builder /usr/bin/npm /usr/bin/npm
-COPY --from=builder /usr/bin/npx /usr/bin/npx
+RUN ln -s ../lib/node_modules/npm/bin/npm-cli.js /usr/bin/npm \
+    && ln -s ../lib/node_modules/npm/bin/npx-cli.js /usr/bin/npx
 COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
 
+# Install agent-browser (Copilot browser tool) + Chromium runtime dependencies.
+# These are the runtime libraries Chromium/Playwright needs on Debian 13 (trixie).
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 \
+    libdbus-1-3 libxkbcommon0 libatspi2.0-0t64 libxcomposite1 libxdamage1 \
+    libxfixes3 libxrandr2 libgbm1 libasound2t64 libpango-1.0-0 libcairo2 \
+    libx11-6 libx11-xcb1 libxcb1 libxext6 libglib2.0-0t64 \
+    fonts-liberation libfontconfig1 \
+    && rm -rf /var/lib/apt/lists/* \
+    && npm install -g agent-browser \
+    && agent-browser install \
+    && rm -rf /tmp/* /root/.npm
+
 WORKDIR /app/autogpt_platform/backend
 
 # Copy only the .venv from builder (not the entire /app directory)

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

@@ -11,7 +11,7 @@ from autogpt_libs import auth
 from fastapi import APIRouter, Depends, HTTPException, Query, Response, Security
 from fastapi.responses import StreamingResponse
 from prisma.models import UserWorkspaceFile
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator
 
 from backend.copilot import service as chat_service
 from backend.copilot import stream_registry
@@ -25,6 +25,7 @@ from backend.copilot.model import (
     delete_chat_session,
     get_chat_session,
     get_user_sessions,
+    update_session_title,
 )
 from backend.copilot.response_model import StreamError, StreamFinish, StreamHeartbeat
 from backend.copilot.tools.models import (
@@ -141,6 +142,20 @@ class CancelSessionResponse(BaseModel):
     reason: str | None = None
 
 
+class UpdateSessionTitleRequest(BaseModel):
+    """Request model for updating a session's title."""
+
+    title: str
+
+    @field_validator("title")
+    @classmethod
+    def title_must_not_be_blank(cls, v: str) -> str:
+        stripped = v.strip()
+        if not stripped:
+            raise ValueError("Title must not be blank")
+        return stripped
+
+
 # ========== Routes ==========
 
 
@@ -264,6 +279,43 @@ async def delete_session(
     return Response(status_code=204)
 
 
+@router.patch(
+    "/sessions/{session_id}/title",
+    summary="Update session title",
+    dependencies=[Security(auth.requires_user)],
+    status_code=200,
+    responses={404: {"description": "Session not found or access denied"}},
+)
+async def update_session_title_route(
+    session_id: str,
+    request: UpdateSessionTitleRequest,
+    user_id: Annotated[str, Security(auth.get_user_id)],
+) -> dict:
+    """
+    Update the title of a chat session.
+
+    Allows the user to rename their chat session.
+
+    Args:
+        session_id: The session ID to update.
+        request: Request body containing the new title.
+        user_id: The authenticated user's ID.
+
+    Returns:
+        dict: Status of the update.
+
+    Raises:
+        HTTPException: 404 if session not found or not owned by user.
+    """
+    success = await update_session_title(session_id, user_id, request.title)
+    if not success:
+        raise HTTPException(
+            status_code=404,
+            detail=f"Session {session_id} not found or access denied",
+        )
+    return {"status": "ok"}
+
+
 @router.get(
     "/sessions/{session_id}",
 )

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

@@ -1,4 +1,6 @@
-"""Tests for chat route file_ids validation and enrichment."""
+"""Tests for chat API routes: session title update and file attachment validation."""
+
+from unittest.mock import AsyncMock
 
 import fastapi
 import fastapi.testclient
@@ -17,6 +19,7 @@ TEST_USER_ID = "3e53486c-cf57-477e-ba2a-cb02dc828e1a"
 
 @pytest.fixture(autouse=True)
 def setup_app_auth(mock_jwt_user):
+    """Setup auth overrides for all tests in this module"""
     from autogpt_libs.auth.jwt_utils import get_jwt_payload
 
     app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
@@ -24,7 +27,95 @@ def setup_app_auth(mock_jwt_user):
     app.dependency_overrides.clear()
 
 
-# ---- file_ids Pydantic validation (B1) ----
+def _mock_update_session_title(
+    mocker: pytest_mock.MockerFixture, *, success: bool = True
+):
+    """Mock update_session_title."""
+    return mocker.patch(
+        "backend.api.features.chat.routes.update_session_title",
+        new_callable=AsyncMock,
+        return_value=success,
+    )
+
+
+# ─── Update title: success ─────────────────────────────────────────────
+
+
+def test_update_title_success(
+    mocker: pytest_mock.MockerFixture,
+    test_user_id: str,
+) -> None:
+    mock_update = _mock_update_session_title(mocker, success=True)
+
+    response = client.patch(
+        "/sessions/sess-1/title",
+        json={"title": "My project"},
+    )
+
+    assert response.status_code == 200
+    assert response.json() == {"status": "ok"}
+    mock_update.assert_called_once_with("sess-1", test_user_id, "My project")
+
+
+def test_update_title_trims_whitespace(
+    mocker: pytest_mock.MockerFixture,
+    test_user_id: str,
+) -> None:
+    mock_update = _mock_update_session_title(mocker, success=True)
+
+    response = client.patch(
+        "/sessions/sess-1/title",
+        json={"title": "  trimmed  "},
+    )
+
+    assert response.status_code == 200
+    mock_update.assert_called_once_with("sess-1", test_user_id, "trimmed")
+
+
+# ─── Update title: blank / whitespace-only → 422 ──────────────────────
+
+
+def test_update_title_blank_rejected(
+    test_user_id: str,
+) -> None:
+    """Whitespace-only titles must be rejected before hitting the DB."""
+    response = client.patch(
+        "/sessions/sess-1/title",
+        json={"title": "   "},
+    )
+
+    assert response.status_code == 422
+
+
+def test_update_title_empty_rejected(
+    test_user_id: str,
+) -> None:
+    response = client.patch(
+        "/sessions/sess-1/title",
+        json={"title": ""},
+    )
+
+    assert response.status_code == 422
+
+
+# ─── Update title: session not found or wrong user → 404 ──────────────
+
+
+def test_update_title_not_found(
+    mocker: pytest_mock.MockerFixture,
+    test_user_id: str,
+) -> None:
+    _mock_update_session_title(mocker, success=False)
+
+    response = client.patch(
+        "/sessions/sess-1/title",
+        json={"title": "New name"},
+    )
+
+    assert response.status_code == 404
+
+
+# ─── file_ids Pydantic validation ─────────────────────────────────────
 
 
 def test_stream_chat_rejects_too_many_file_ids():
@@ -92,7 +183,7 @@ def test_stream_chat_accepts_20_file_ids(mocker: pytest_mock.MockFixture):
     assert response.status_code == 200
 
 
-# ---- UUID format filtering ----
+# ─── UUID format filtering ─────────────────────────────────────────────
 
 
 def test_file_ids_filters_invalid_uuids(mocker: pytest_mock.MockFixture):
@@ -131,7 +222,7 @@ def test_file_ids_filters_invalid_uuids(mocker: pytest_mock.MockFixture):
     assert call_kwargs["where"]["id"]["in"] == [valid_id]
 
 
-# ---- Cross-workspace file_ids ----
+# ─── Cross-workspace file_ids ─────────────────────────────────────────
 
 
 def test_file_ids_scoped_to_workspace(mocker: pytest_mock.MockFixture):

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

@@ -131,6 +131,54 @@ class StorageUsageResponse(BaseModel):
     file_count: int
 
 
+class DownloadUrlResponse(BaseModel):
+    url: str
+    direct: bool  # True = browser can fetch URL directly (signed GCS URL)
+
+
+@router.get(
+    "/files/{file_id}/download-url",
+    summary="Get download URL for a file",
+)
+async def get_file_download_url(
+    user_id: Annotated[str, fastapi.Security(get_user_id)],
+    file_id: str,
+) -> DownloadUrlResponse:
+    """
+    Return a download URL for a workspace file.
+
+    For GCS storage: returns a time-limited signed URL the browser can fetch directly.
+    For local storage: returns the API download path (must still be proxied).
+    """
+    workspace = await get_workspace(user_id)
+    if workspace is None:
+        raise fastapi.HTTPException(status_code=404, detail="Workspace not found")
+
+    file = await get_workspace_file(file_id, workspace.id)
+    if file is None:
+        raise fastapi.HTTPException(status_code=404, detail="File not found")
+
+    storage = await get_workspace_storage()
+
+    if file.storage_path.startswith("local://"):
+        return DownloadUrlResponse(
+            url=f"/api/workspace/files/{file_id}/download",
+            direct=False,
+        )
+
+    # GCS — try to generate signed URL
+    try:
+        url = await storage.get_download_url(file.storage_path, expires_in=300)
+        if url.startswith("/api/"):
+            return DownloadUrlResponse(url=url, direct=False)
+        return DownloadUrlResponse(url=url, direct=True)
+    except Exception:
+        return DownloadUrlResponse(
+            url=f"/api/workspace/files/{file_id}/download",
+            direct=False,
+        )
+
+
 @router.get(
     "/files/{file_id}/download",
     summary="Download file by ID",

autogpt_platform/backend/backend/blocks/llm.py

@@ -116,6 +116,7 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
     CLAUDE_4_5_HAIKU = "claude-haiku-4-5-20251001"
     CLAUDE_4_6_OPUS = "claude-opus-4-6"
+    CLAUDE_4_6_SONNET = "claude-sonnet-4-6"
     CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
     # AI/ML API models
     AIML_API_QWEN2_5_72B = "Qwen/Qwen2.5-72B-Instruct-Turbo"
@@ -274,6 +275,9 @@ MODEL_METADATA = {
     LlmModel.CLAUDE_4_6_OPUS: ModelMetadata(
         "anthropic", 200000, 128000, "Claude Opus 4.6", "Anthropic", "Anthropic", 3
     ),  # claude-opus-4-6
+    LlmModel.CLAUDE_4_6_SONNET: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude Sonnet 4.6", "Anthropic", "Anthropic", 3
+    ),  # claude-sonnet-4-6
     LlmModel.CLAUDE_4_5_OPUS: ModelMetadata(
         "anthropic", 200000, 64000, "Claude Opus 4.5", "Anthropic", "Anthropic", 3
     ),  # claude-opus-4-5-20251101

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

@@ -83,7 +83,8 @@ class StagehandRecommendedLlmModel(str, Enum):
     GPT41_MINI = "gpt-4.1-mini-2025-04-14"
 
     # Anthropic
-    CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
+    CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"  # Keep for backwards compat
+    CLAUDE_4_6_SONNET = "claude-sonnet-4-6"
 
     @property
     def provider_name(self) -> str:
@@ -137,7 +138,7 @@ 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_4_6_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()
@@ -227,7 +228,7 @@ 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_4_6_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()
@@ -324,7 +325,7 @@ 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_4_6_SONNET,
             advanced=False,
         )
         model_credentials: AICredentials = AICredentialsField()

autogpt_platform/backend/backend/copilot/baseline/service.py

@@ -62,8 +62,8 @@ async def _update_title_async(
     """Generate and persist a session title in the background."""
     try:
         title = await _generate_session_title(message, user_id, session_id)
-        if title:
-            await update_session_title(session_id, title)
+        if title and user_id:
+            await update_session_title(session_id, user_id, title, only_if_empty=True)
     except Exception as e:
         logger.warning("[Baseline] Failed to update session title: %s", e)
 

autogpt_platform/backend/backend/copilot/db.py

@@ -81,6 +81,35 @@ async def update_chat_session(
     return ChatSession.from_db(session) if session else None
 
 
+async def update_chat_session_title(
+    session_id: str,
+    user_id: str,
+    title: str,
+    *,
+    only_if_empty: bool = False,
+) -> bool:
+    """Update the title of a chat session, scoped to the owning user.
+
+    Always filters by (session_id, user_id) so callers cannot mutate another
+    user's session even when they know the session_id.
+
+    Args:
+        only_if_empty: When True, uses an atomic ``UPDATE WHERE title IS NULL``
+            guard so auto-generated titles never overwrite a user-set title.
+
+    Returns True if a row was updated, False otherwise (session not found,
+    wrong user, or — when only_if_empty — title was already set).
+    """
+    where: ChatSessionWhereInput = {"id": session_id, "userId": user_id}
+    if only_if_empty:
+        where["title"] = None
+    result = await PrismaChatSession.prisma().update_many(
+        where=where,
+        data={"title": title, "updatedAt": datetime.now(UTC)},
+    )
+    return result > 0
+
+
 async def add_chat_message(
     session_id: str,
     role: str,

autogpt_platform/backend/backend/copilot/model.py

@@ -469,8 +469,16 @@ async def upsert_chat_session(
             )
             db_error = e
 
-        # Save to cache (best-effort, even if DB failed)
+        # Save to cache (best-effort, even if DB failed).
+        # Title updates (update_session_title) run *outside* this lock because
+        # they only touch the title field, not messages.  So a concurrent rename
+        # or auto-title may have written a newer title to Redis while this
+        # upsert was in progress.  Always prefer the cached title to avoid
+        # overwriting it with the stale in-memory copy.
         try:
+            existing_cached = await _get_session_from_cache(session.session_id)
+            if existing_cached and existing_cached.title:
+                session = session.model_copy(update={"title": existing_cached.title})
             await cache_chat_session(session)
         except Exception as e:
             # If DB succeeded but cache failed, raise cache error
@@ -685,24 +693,34 @@ async def delete_chat_session(session_id: str, user_id: str | None = None) -> bo
     return True
 
 
-async def update_session_title(session_id: str, title: str) -> bool:
-    """Update only the title of a chat session.
+async def update_session_title(
+    session_id: str,
+    user_id: str,
+    title: str,
+    *,
+    only_if_empty: bool = False,
+) -> bool:
+    """Update the title of a chat session, scoped to the owning user.
 
-    This is a lightweight operation that doesn't touch messages, avoiding
-    race conditions with concurrent message updates. Use this for background
-    title generation instead of upsert_chat_session.
+    Lightweight operation that doesn't touch messages, avoiding race conditions
+    with concurrent message updates.
 
     Args:
         session_id: The session ID to update.
+        user_id: Owning user — the DB query filters on this.
         title: The new title to set.
+        only_if_empty: When True, uses an atomic ``UPDATE WHERE title IS NULL``
+            so auto-generated titles never overwrite a user-set title.
 
     Returns:
-        True if updated successfully, False otherwise.
+        True if updated successfully, False otherwise (not found, wrong user,
+        or — when only_if_empty — title was already set).
     """
     try:
-        result = await chat_db().update_chat_session(session_id=session_id, title=title)
-        if result is None:
-            logger.warning(f"Session {session_id} not found for title update")
+        updated = await chat_db().update_chat_session_title(
+            session_id, user_id, title, only_if_empty=only_if_empty
+        )
+        if not updated:
             return False
 
         # Update title in cache if it exists (instead of invalidating).
@@ -714,9 +732,8 @@ async def update_session_title(session_id: str, title: str) -> bool:
                 cached.title = title
                 await cache_chat_session(cached)
         except Exception as e:
-            # Not critical - title will be correct on next full cache refresh
             logger.warning(
-                f"Failed to update title in cache for session {session_id}: {e}"
+                f"Cache title update failed for session {session_id} (non-critical): {e}"
             )
 
         return True

autogpt_platform/backend/backend/copilot/sdk/security_hooks.py

@@ -127,7 +127,6 @@ def create_security_hooks(
     sdk_cwd: str | None = None,
     max_subtasks: int = 3,
     on_compact: Callable[[], None] | None = None,
-    on_stop: Callable[[str, str], None] | None = None,
 ) -> dict[str, Any]:
     """Create the security hooks configuration for Claude Agent SDK.
 
@@ -136,15 +135,12 @@ def create_security_hooks(
     - PostToolUse: Log successful tool executions
     - PostToolUseFailure: Log and handle failed tool executions
     - PreCompact: Log context compaction events (SDK handles compaction automatically)
-    - Stop: Capture transcript path for stateless resume (when *on_stop* is provided)
 
     Args:
         user_id: Current user ID for isolation validation
         sdk_cwd: SDK working directory for workspace-scoped tool validation
         max_subtasks: Maximum concurrent Task (sub-agent) spawns allowed per session
-        on_stop: Callback ``(transcript_path, sdk_session_id)`` invoked when
-            the SDK finishes processing — used to read the JSONL transcript
-            before the CLI process exits.
+        on_compact: Callback invoked when SDK starts compacting context.
 
     Returns:
         Hooks configuration dict for ClaudeAgentOptions
@@ -311,30 +307,6 @@ def create_security_hooks(
                 on_compact()
             return cast(SyncHookJSONOutput, {})
 
-        # --- Stop hook: capture transcript path for stateless resume ---
-        async def stop_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Capture transcript path when SDK finishes processing.
-
-            The Stop hook fires while the CLI process is still alive, giving us
-            a reliable window to read the JSONL transcript before SIGTERM.
-            """
-            _ = context, tool_use_id
-            transcript_path = cast(str, input_data.get("transcript_path", ""))
-            sdk_session_id = cast(str, input_data.get("session_id", ""))
-
-            if transcript_path and on_stop:
-                logger.info(
-                    f"[SDK] Stop hook: transcript_path={transcript_path}, "
-                    f"sdk_session_id={sdk_session_id[:12]}..."
-                )
-                on_stop(transcript_path, sdk_session_id)
-
-            return cast(SyncHookJSONOutput, {})
-
         hooks: dict[str, Any] = {
             "PreToolUse": [HookMatcher(matcher="*", hooks=[pre_tool_use_hook])],
             "PostToolUse": [HookMatcher(matcher="*", hooks=[post_tool_use_hook])],
@@ -344,9 +316,6 @@ def create_security_hooks(
             "PreCompact": [HookMatcher(matcher="*", hooks=[pre_compact_hook])],
         }
 
-        if on_stop is not None:
-            hooks["Stop"] = [HookMatcher(matcher=None, hooks=[stop_hook])]
-
         return hooks
     except ImportError:
         # Fallback for when SDK isn't available - return empty hooks

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

@@ -12,7 +12,6 @@ import subprocess
 import sys
 import uuid
 from collections.abc import AsyncGenerator
-from dataclasses import dataclass
 from typing import Any, cast
 
 import openai
@@ -21,6 +20,9 @@ from claude_agent_sdk import (
     ClaudeAgentOptions,
     ClaudeSDKClient,
     ResultMessage,
+    TextBlock,
+    ThinkingBlock,
+    ToolResultBlock,
     ToolUseBlock,
 )
 from langfuse import propagate_attributes
@@ -74,11 +76,11 @@ from .tool_adapter import (
 from .transcript import (
     cleanup_cli_project_dir,
     download_transcript,
-    read_transcript_file,
     upload_transcript,
     validate_transcript,
     write_transcript_to_tempfile,
 )
+from .transcript_builder import TranscriptBuilder
 
 logger = logging.getLogger(__name__)
 config = ChatConfig()
@@ -137,19 +139,6 @@ _setup_langfuse_otel()
 _background_tasks: set[asyncio.Task[Any]] = set()
 
 
-@dataclass
-class CapturedTranscript:
-    """Info captured by the SDK Stop hook for stateless --resume."""
-
-    path: str = ""
-    sdk_session_id: str = ""
-    raw_content: str = ""
-
-    @property
-    def available(self) -> bool:
-        return bool(self.path)
-
-
 _SDK_CWD_PREFIX = WORKSPACE_PREFIX
 
 # Heartbeat interval — keep SSE alive through proxies/LBs during tool execution.
@@ -451,6 +440,49 @@ def _cleanup_sdk_tool_results(cwd: str) -> None:
         pass
 
 
+def _format_sdk_content_blocks(blocks: list) -> list[dict[str, Any]]:
+    """Convert SDK content blocks to transcript format.
+
+    Handles TextBlock, ToolUseBlock, ToolResultBlock, and ThinkingBlock.
+    Unknown block types are logged and skipped.
+    """
+    result: list[dict[str, Any]] = []
+    for block in blocks or []:
+        if isinstance(block, TextBlock):
+            result.append({"type": "text", "text": block.text})
+        elif isinstance(block, ToolUseBlock):
+            result.append(
+                {
+                    "type": "tool_use",
+                    "id": block.id,
+                    "name": block.name,
+                    "input": block.input,
+                }
+            )
+        elif isinstance(block, ToolResultBlock):
+            result.append(
+                {
+                    "type": "tool_result",
+                    "tool_use_id": block.tool_use_id,
+                    "content": block.content,
+                }
+            )
+        elif isinstance(block, ThinkingBlock):
+            result.append(
+                {
+                    "type": "thinking",
+                    "thinking": block.thinking,
+                    "signature": block.signature,
+                }
+            )
+        else:
+            logger.warning(
+                f"[SDK] Unknown content block type: {type(block).__name__}. "
+                f"This may indicate a new SDK version with additional block types."
+            )
+    return result
+
+
 async def _compress_messages(
     messages: list[ChatMessage],
 ) -> tuple[list[ChatMessage], bool]:
@@ -806,6 +838,11 @@ async def stream_chat_completion_sdk(
                 user_id=user_id, session_id=session_id, message_length=len(message)
             )
 
+    # Structured log prefix: [SDK][<session>][T<turn>]
+    # Turn = number of user messages (1-based), computed AFTER appending the new message.
+    turn = sum(1 for m in session.messages if m.role == "user")
+    log_prefix = f"[SDK][{session_id[:12]}][T{turn}]"
+
     session = await upsert_chat_session(session)
 
     # Generate title for new sessions (first user message)
@@ -823,10 +860,11 @@ async def stream_chat_completion_sdk(
     message_id = str(uuid.uuid4())
     stream_id = str(uuid.uuid4())
     stream_completed = False
+    ended_with_stream_error = False
     e2b_sandbox = None
     use_resume = False
     resume_file: str | None = None
-    captured_transcript = CapturedTranscript()
+    transcript_builder = TranscriptBuilder()
     sdk_cwd = ""
 
     # Acquire stream lock to prevent concurrent streams to the same session
@@ -841,7 +879,7 @@ async def stream_chat_completion_sdk(
     if lock_owner != stream_id:
         # Another stream is active
         logger.warning(
-            f"[SDK] Session {session_id} already has an active stream: {lock_owner}"
+            f"{log_prefix} Session already has an active stream: {lock_owner}"
         )
         yield StreamError(
             errorText="Another stream is already active for this session. "
@@ -865,7 +903,7 @@ async def stream_chat_completion_sdk(
             sdk_cwd = _make_sdk_cwd(session_id)
             os.makedirs(sdk_cwd, exist_ok=True)
         except (ValueError, OSError) as e:
-            logger.error("[SDK] [%s] Invalid SDK cwd: %s", session_id[:12], e)
+            logger.error("%s Invalid SDK cwd: %s", log_prefix, e)
             yield StreamError(
                 errorText="Unable to initialize working directory.",
                 code="sdk_cwd_error",
@@ -909,12 +947,13 @@ async def stream_chat_completion_sdk(
             ):
                 return None
             try:
-                return await download_transcript(user_id, session_id)
+                return await download_transcript(
+                    user_id, session_id, log_prefix=log_prefix
+                )
             except Exception as transcript_err:
                 logger.warning(
-                    "[SDK] [%s] Transcript download failed, continuing without "
-                    "--resume: %s",
-                    session_id[:12],
+                    "%s Transcript download failed, continuing without " "--resume: %s",
+                    log_prefix,
                     transcript_err,
                 )
                 return None
@@ -936,11 +975,18 @@ async def stream_chat_completion_sdk(
         transcript_msg_count = 0
         if dl:
             is_valid = validate_transcript(dl.content)
+            dl_lines = dl.content.strip().split("\n") if dl.content else []
+            logger.info(
+                "%s Downloaded transcript: %dB, %d lines, " "msg_count=%d, valid=%s",
+                log_prefix,
+                len(dl.content),
+                len(dl_lines),
+                dl.message_count,
+                is_valid,
+            )
             if is_valid:
-                logger.info(
-                    f"[SDK] Transcript available for session {session_id}: "
-                    f"{len(dl.content)}B, msg_count={dl.message_count}"
-                )
+                # Load previous FULL context into builder
+                transcript_builder.load_previous(dl.content, log_prefix=log_prefix)
                 resume_file = write_transcript_to_tempfile(
                     dl.content, session_id, sdk_cwd
                 )
@@ -948,16 +994,14 @@ async def stream_chat_completion_sdk(
                     use_resume = True
                     transcript_msg_count = dl.message_count
                     logger.debug(
-                        f"[SDK] Using --resume ({len(dl.content)}B, "
+                        f"{log_prefix} Using --resume ({len(dl.content)}B, "
                         f"msg_count={transcript_msg_count})"
                     )
             else:
-                logger.warning(
-                    f"[SDK] Transcript downloaded but invalid for {session_id}"
-                )
+                logger.warning(f"{log_prefix} Transcript downloaded but invalid")
         elif config.claude_agent_use_resume and user_id and len(session.messages) > 1:
             logger.warning(
-                f"[SDK] No transcript available for {session_id} "
+                f"{log_prefix} No transcript available "
                 f"({len(session.messages)} messages in session)"
             )
 
@@ -979,25 +1023,6 @@ async def stream_chat_completion_sdk(
 
         sdk_model = _resolve_sdk_model()
 
-        # --- Transcript capture via Stop hook ---
-        # Read the file content immediately — the SDK may clean up
-        # the file before our finally block runs.
-        def _on_stop(transcript_path: str, sdk_session_id: str) -> None:
-            captured_transcript.path = transcript_path
-            captured_transcript.sdk_session_id = sdk_session_id
-            content = read_transcript_file(transcript_path)
-            if content:
-                captured_transcript.raw_content = content
-                logger.info(
-                    f"[SDK] Stop hook: captured {len(content)}B from "
-                    f"{transcript_path}"
-                )
-            else:
-                logger.warning(
-                    f"[SDK] Stop hook: transcript file empty/missing at "
-                    f"{transcript_path}"
-                )
-
         # Track SDK-internal compaction (PreCompact hook → start, next msg → end)
         compaction = CompactionTracker()
 
@@ -1005,7 +1030,6 @@ async def stream_chat_completion_sdk(
             user_id,
             sdk_cwd=sdk_cwd,
             max_subtasks=config.claude_agent_max_subtasks,
-            on_stop=_on_stop if config.claude_agent_use_resume else None,
             on_compact=compaction.on_compact,
         )
 
@@ -1040,7 +1064,10 @@ async def stream_chat_completion_sdk(
             session_id=session_id,
             trace_name="copilot-sdk",
             tags=["sdk"],
-            metadata={"resume": str(use_resume)},
+            metadata={
+                "resume": str(use_resume),
+                "conversation_turn": str(turn),
+            },
         )
         _otel_ctx.__enter__()
 
@@ -1074,9 +1101,9 @@ async def stream_chat_completion_sdk(
                 query_message = f"{query_message}\n\n{attachments.hint}"
 
             logger.info(
-                "[SDK] [%s] Sending query — resume=%s, total_msgs=%d, "
+                "%s Sending query — resume=%s, total_msgs=%d, "
                 "query_len=%d, attached_files=%d, image_blocks=%d",
-                session_id[:12],
+                log_prefix,
                 use_resume,
                 len(session.messages),
                 len(query_message),
@@ -1105,8 +1132,13 @@ async def stream_chat_completion_sdk(
                 await client._transport.write(  # noqa: SLF001
                     json.dumps(user_msg) + "\n"
                 )
+                # Capture user message in transcript (multimodal)
+                transcript_builder.add_user_message(content=content_blocks)
             else:
                 await client.query(query_message, session_id=session_id)
+                # Capture actual user message in transcript (not the engineered query)
+                # query_message may include context wrappers, but transcript needs raw input
+                transcript_builder.add_user_message(content=current_message)
 
             assistant_response = ChatMessage(role="assistant", content="")
             accumulated_tool_calls: list[dict[str, Any]] = []
@@ -1150,8 +1182,8 @@ async def stream_chat_completion_sdk(
                         sdk_msg = done.pop().result()
                     except StopAsyncIteration:
                         logger.info(
-                            "[SDK] [%s] Stream ended normally (StopAsyncIteration)",
-                            session_id[:12],
+                            "%s Stream ended normally (StopAsyncIteration)",
+                            log_prefix,
                         )
                         break
                     except Exception as stream_err:
@@ -1160,8 +1192,8 @@ async def stream_chat_completion_sdk(
                         # so the session can still be saved and the
                         # frontend gets a clean finish.
                         logger.error(
-                            "[SDK] [%s] Stream error from SDK: %s",
-                            session_id[:12],
+                            "%s Stream error from SDK: %s",
+                            log_prefix,
                             stream_err,
                             exc_info=True,
                         )
@@ -1173,9 +1205,9 @@ async def stream_chat_completion_sdk(
                         break
 
                     logger.info(
-                        "[SDK] [%s] Received: %s %s "
+                        "%s Received: %s %s "
                         "(unresolved=%d, current=%d, resolved=%d)",
-                        session_id[:12],
+                        log_prefix,
                         type(sdk_msg).__name__,
                         getattr(sdk_msg, "subtype", ""),
                         len(adapter.current_tool_calls)
@@ -1184,6 +1216,15 @@ async def stream_chat_completion_sdk(
                         len(adapter.resolved_tool_calls),
                     )
 
+                    # Capture SDK messages in transcript
+                    if isinstance(sdk_msg, AssistantMessage):
+                        content_blocks = _format_sdk_content_blocks(sdk_msg.content)
+                        model_name = getattr(sdk_msg, "model", "")
+                        transcript_builder.add_assistant_message(
+                            content_blocks=content_blocks,
+                            model=model_name,
+                        )
+
                     # Race-condition fix: SDK hooks (PostToolUse) are
                     # executed asynchronously via start_soon() — the next
                     # message can arrive before the hook stashes output.
@@ -1210,10 +1251,10 @@ async def stream_chat_completion_sdk(
                             await asyncio.sleep(0)
                         else:
                             logger.warning(
-                                "[SDK] [%s] Timed out waiting for "
+                                "%s Timed out waiting for "
                                 "PostToolUse hook stash "
                                 "(%d unresolved tool calls)",
-                                session_id[:12],
+                                log_prefix,
                                 len(adapter.current_tool_calls)
                                 - len(adapter.resolved_tool_calls),
                             )
@@ -1221,9 +1262,9 @@ async def stream_chat_completion_sdk(
                     # Log ResultMessage details for debugging
                     if isinstance(sdk_msg, ResultMessage):
                         logger.info(
-                            "[SDK] [%s] Received: ResultMessage %s "
+                            "%s Received: ResultMessage %s "
                             "(unresolved=%d, current=%d, resolved=%d)",
-                            session_id[:12],
+                            log_prefix,
                             sdk_msg.subtype,
                             len(adapter.current_tool_calls)
                             - len(adapter.resolved_tool_calls),
@@ -1232,8 +1273,8 @@ async def stream_chat_completion_sdk(
                         )
                         if sdk_msg.subtype in ("error", "error_during_execution"):
                             logger.error(
-                                "[SDK] [%s] SDK execution failed with error: %s",
-                                session_id[:12],
+                                "%s SDK execution failed with error: %s",
+                                log_prefix,
                                 sdk_msg.result or "(no error message provided)",
                             )
 
@@ -1258,8 +1299,8 @@ async def stream_chat_completion_sdk(
                                 out_len = len(str(response.output))
                                 extra = f", output_len={out_len}"
                             logger.info(
-                                "[SDK] [%s] Tool event: %s, tool=%s%s",
-                                session_id[:12],
+                                "%s Tool event: %s, tool=%s%s",
+                                log_prefix,
                                 type(response).__name__,
                                 getattr(response, "toolName", "N/A"),
                                 extra,
@@ -1268,8 +1309,8 @@ async def stream_chat_completion_sdk(
                         # Log errors being sent to frontend
                         if isinstance(response, StreamError):
                             logger.error(
-                                "[SDK] [%s] Sending error to frontend: %s (code=%s)",
-                                session_id[:12],
+                                "%s Sending error to frontend: %s (code=%s)",
+                                log_prefix,
                                 response.errorText,
                                 response.code,
                             )
@@ -1335,8 +1376,8 @@ async def stream_chat_completion_sdk(
                 # server shutdown).  Log and let the safety-net / finally
                 # blocks handle cleanup.
                 logger.warning(
-                    "[SDK] [%s] Streaming loop cancelled (asyncio.CancelledError)",
-                    session_id[:12],
+                    "%s Streaming loop cancelled (asyncio.CancelledError)",
+                    log_prefix,
                 )
                 raise
             finally:
@@ -1350,7 +1391,8 @@ async def stream_chat_completion_sdk(
                     except (asyncio.CancelledError, StopAsyncIteration):
                         # Expected: task was cancelled or exhausted during cleanup
                         logger.info(
-                            "[SDK] Pending __anext__ task completed during cleanup"
+                            "%s Pending __anext__ task completed during cleanup",
+                            log_prefix,
                         )
 
             # Safety net: if tools are still unresolved after the
@@ -1359,9 +1401,9 @@ async def stream_chat_completion_sdk(
             # them now so the frontend stops showing spinners.
             if adapter.has_unresolved_tool_calls:
                 logger.warning(
-                    "[SDK] [%s] %d unresolved tool(s) after stream loop — "
+                    "%s %d unresolved tool(s) after stream loop — "
                     "flushing as safety net",
-                    session_id[:12],
+                    log_prefix,
                     len(adapter.current_tool_calls) - len(adapter.resolved_tool_calls),
                 )
                 safety_responses: list[StreamBaseResponse] = []
@@ -1372,8 +1414,8 @@ async def stream_chat_completion_sdk(
                         (StreamToolInputAvailable, StreamToolOutputAvailable),
                     ):
                         logger.info(
-                            "[SDK] [%s] Safety flush: %s, tool=%s",
-                            session_id[:12],
+                            "%s Safety flush: %s, tool=%s",
+                            log_prefix,
                             type(response).__name__,
                             getattr(response, "toolName", "N/A"),
                         )
@@ -1386,8 +1428,8 @@ async def stream_chat_completion_sdk(
             # StreamFinish is published by mark_session_completed in the processor.
             if not stream_completed and not ended_with_stream_error:
                 logger.info(
-                    "[SDK] [%s] Stream ended without ResultMessage (stopped by user)",
-                    session_id[:12],
+                    "%s Stream ended without ResultMessage (stopped by user)",
+                    log_prefix,
                 )
                 closing_responses: list[StreamBaseResponse] = []
                 adapter._end_text_if_open(closing_responses)
@@ -1408,69 +1450,36 @@ async def stream_chat_completion_sdk(
             ) and not has_appended_assistant:
                 session.messages.append(assistant_response)
 
-        # --- Upload transcript for next-turn --resume ---
-        # After async with the SDK task group has exited, so the Stop
-        # hook has already fired and the CLI has been SIGTERMed.  The
-        # CLI uses appendFileSync, so all writes are safely on disk.
-        if config.claude_agent_use_resume and user_id:
-            # With --resume the CLI appends to the resume file (most
-            # complete).  Otherwise use the Stop hook path.
-            if use_resume and resume_file:
-                raw_transcript = read_transcript_file(resume_file)
-                logger.debug("[SDK] Transcript source: resume file")
-            elif captured_transcript.path:
-                raw_transcript = read_transcript_file(captured_transcript.path)
-                logger.debug(
-                    "[SDK] Transcript source: stop hook (%s), read result: %s",
-                    captured_transcript.path,
-                    f"{len(raw_transcript)}B" if raw_transcript else "None",
-                )
-            else:
-                raw_transcript = None
+        # Transcript upload is handled exclusively in the finally block
+        # to avoid double-uploads (the success path used to upload the
+        # old resume file, then the finally block overwrote it with the
+        # stop hook content — which could be smaller after compaction).
 
-            if not raw_transcript:
-                logger.debug(
-                    "[SDK] No usable transcript — CLI file had no "
-                    "conversation entries (expected for first turn "
-                    "without --resume)"
-                )
-
-            if raw_transcript:
-                # Shield the upload from generator cancellation so a
-                # client disconnect / page refresh doesn't lose the
-                # transcript.  The upload must finish even if the SSE
-                # connection is torn down.
-                await asyncio.shield(
-                    _try_upload_transcript(
-                        user_id,
-                        session_id,
-                        raw_transcript,
-                        message_count=len(session.messages),
-                    )
-                )
-
-        logger.info(
-            "[SDK] [%s] Stream completed successfully with %d messages",
-            session_id[:12],
-            len(session.messages),
-        )
+        if ended_with_stream_error:
+            logger.warning(
+                "%s Stream ended with SDK error after %d messages",
+                log_prefix,
+                len(session.messages),
+            )
+        else:
+            logger.info(
+                "%s Stream completed successfully with %d messages",
+                log_prefix,
+                len(session.messages),
+            )
     except BaseException as e:
         # Catch BaseException to handle both Exception and CancelledError
         # (CancelledError inherits from BaseException in Python 3.8+)
         if isinstance(e, asyncio.CancelledError):
-            logger.warning("[SDK] [%s] Session cancelled", session_id[:12])
+            logger.warning("%s Session cancelled", log_prefix)
             error_msg = "Operation cancelled"
         else:
             error_msg = str(e) or type(e).__name__
             # SDK cleanup RuntimeError is expected during cancellation, log as warning
             if isinstance(e, RuntimeError) and "cancel scope" in str(e):
-                logger.warning(
-                    "[SDK] [%s] SDK cleanup error: %s", session_id[:12], error_msg
-                )
+                logger.warning("%s SDK cleanup error: %s", log_prefix, error_msg)
             else:
-                logger.error(
-                    f"[SDK] [%s] Error: {error_msg}", session_id[:12], exc_info=True
-                )
+                logger.error("%s Error: %s", log_prefix, error_msg, exc_info=True)
 
         # Append error marker to session (non-invasive text parsing approach)
         # The finally block will persist the session with this error marker
@@ -1481,8 +1490,8 @@ async def stream_chat_completion_sdk(
                 )
             )
             logger.debug(
-                "[SDK] [%s] Appended error marker, will be persisted in finally",
-                session_id[:12],
+                "%s Appended error marker, will be persisted in finally",
+                log_prefix,
             )
 
         # Yield StreamError for immediate feedback (only for non-cancellation errors)
@@ -1514,47 +1523,61 @@ async def stream_chat_completion_sdk(
             try:
                 await asyncio.shield(upsert_chat_session(session))
                 logger.info(
-                    "[SDK] [%s] Session persisted in finally with %d messages",
-                    session_id[:12],
+                    "%s Session persisted in finally with %d messages",
+                    log_prefix,
                     len(session.messages),
                 )
             except Exception as persist_err:
                 logger.error(
-                    "[SDK] [%s] Failed to persist session in finally: %s",
-                    session_id[:12],
+                    "%s Failed to persist session in finally: %s",
+                    log_prefix,
                     persist_err,
                     exc_info=True,
                 )
 
         # --- Upload transcript for next-turn --resume ---
         # This MUST run in finally so the transcript is uploaded even when
-        # the streaming loop raises an exception.  The CLI uses
-        # appendFileSync, so whatever was written before the error/SIGTERM
-        # is safely on disk and still useful for the next turn.
-        if config.claude_agent_use_resume and user_id:
+        # the streaming loop raises an exception.
+        # The transcript represents the COMPLETE active context (atomic).
+        if config.claude_agent_use_resume and user_id and session is not None:
             try:
-                # Prefer content captured in the Stop hook (read before
-                # cleanup removes the file).  Fall back to the resume
-                # file when the stop hook didn't fire (e.g. error before
-                # completion) so we don't lose the prior transcript.
-                raw_transcript = captured_transcript.raw_content or None
-                if not raw_transcript and use_resume and resume_file:
-                    raw_transcript = read_transcript_file(resume_file)
+                # Build complete transcript from captured SDK messages
+                transcript_content = transcript_builder.to_jsonl()
 
-                if raw_transcript and session is not None:
-                    await asyncio.shield(
-                        _try_upload_transcript(
-                            user_id,
-                            session_id,
-                            raw_transcript,
-                            message_count=len(session.messages),
-                        )
+                if not transcript_content:
+                    logger.warning(
+                        "%s No transcript to upload (builder empty)", log_prefix
+                    )
+                elif not validate_transcript(transcript_content):
+                    logger.warning(
+                        "%s Transcript invalid, skipping upload (entries=%d)",
+                        log_prefix,
+                        transcript_builder.entry_count,
                     )
                 else:
-                    logger.warning(f"[SDK] No transcript to upload for {session_id}")
+                    logger.info(
+                        "%s Uploading complete transcript (entries=%d, bytes=%d)",
+                        log_prefix,
+                        transcript_builder.entry_count,
+                        len(transcript_content),
+                    )
+                    # Shield upload from cancellation - let it complete even if
+                    # the finally block is interrupted. No timeout to avoid race
+                    # conditions where backgrounded uploads overwrite newer transcripts.
+                    await asyncio.shield(
+                        upload_transcript(
+                            user_id=user_id,
+                            session_id=session_id,
+                            content=transcript_content,
+                            message_count=len(session.messages),
+                            log_prefix=log_prefix,
+                        )
+                    )
             except Exception as upload_err:
                 logger.error(
-                    f"[SDK] Transcript upload failed in finally: {upload_err}",
+                    "%s Transcript upload failed in finally: %s",
+                    log_prefix,
+                    upload_err,
                     exc_info=True,
                 )
 
@@ -1565,33 +1588,6 @@ async def stream_chat_completion_sdk(
         await lock.release()
 
 
-async def _try_upload_transcript(
-    user_id: str,
-    session_id: str,
-    raw_content: str,
-    message_count: int = 0,
-) -> bool:
-    """Strip progress entries and upload transcript (with timeout).
-
-    Returns True if the upload completed without error.
-    """
-    try:
-        async with asyncio.timeout(30):
-            await upload_transcript(
-                user_id, session_id, raw_content, message_count=message_count
-            )
-        return True
-    except asyncio.TimeoutError:
-        logger.warning(f"[SDK] Transcript upload timed out for {session_id}")
-        return False
-    except Exception as e:
-        logger.error(
-            f"[SDK] Failed to upload transcript for {session_id}: {e}",
-            exc_info=True,
-        )
-        return False
-
-
 async def _update_title_async(
     session_id: str, message: str, user_id: str | None = None
 ) -> None:
@@ -1600,8 +1596,8 @@ async def _update_title_async(
         title = await _generate_session_title(
             message, user_id=user_id, session_id=session_id
         )
-        if title:
-            await update_session_title(session_id, title)
+        if title and user_id:
+            await update_session_title(session_id, user_id, title, only_if_empty=True)
             logger.debug(f"[SDK] Generated title for {session_id}: {title}")
     except Exception as e:
         logger.warning(f"[SDK] Failed to update session title: {e}")

autogpt_platform/backend/backend/copilot/sdk/transcript.py

@@ -10,13 +10,14 @@ Storage is handled via ``WorkspaceStorageBackend`` (GCS in prod, local
 filesystem for self-hosted) — no DB column needed.
 """
 
-import json
 import logging
 import os
 import re
 import time
 from dataclasses import dataclass
 
+from backend.util import json
+
 logger = logging.getLogger(__name__)
 
 # UUIDs are hex + hyphens; strip everything else to prevent path injection.
@@ -58,41 +59,37 @@ def strip_progress_entries(content: str) -> str:
     Removes entries whose ``type`` is in ``STRIPPABLE_TYPES`` and reparents
     any remaining child entries so the ``parentUuid`` chain stays intact.
     Typically reduces transcript size by ~30%.
+
+    Entries that are not stripped or reparented are kept as their original
+    raw JSON line to avoid unnecessary re-serialization that changes
+    whitespace or key ordering.
     """
     lines = content.strip().split("\n")
 
-    entries: list[dict] = []
+    # Parse entries, keeping the original line alongside the parsed dict.
+    parsed: list[tuple[str, dict | None]] = []
     for line in lines:
-        try:
-            entries.append(json.loads(line))
-        except json.JSONDecodeError:
-            # Keep unparseable lines as-is (safety)
-            entries.append({"_raw": line})
+        parsed.append((line, json.loads(line, fallback=None)))
 
+    # First pass: identify stripped UUIDs and build parent map.
     stripped_uuids: set[str] = set()
     uuid_to_parent: dict[str, str] = {}
-    kept: list[dict] = []
 
-    for entry in entries:
-        if "_raw" in entry:
-            kept.append(entry)
+    for _line, entry in parsed:
+        if not isinstance(entry, dict):
             continue
         uid = entry.get("uuid", "")
         parent = entry.get("parentUuid", "")
-        entry_type = entry.get("type", "")
-
         if uid:
             uuid_to_parent[uid] = parent
+        if entry.get("type", "") in STRIPPABLE_TYPES and uid:
+            stripped_uuids.add(uid)
 
-        if entry_type in STRIPPABLE_TYPES:
-            if uid:
-                stripped_uuids.add(uid)
-        else:
-            kept.append(entry)
-
-    # Reparent: walk up chain through stripped entries to find surviving ancestor
-    for entry in kept:
-        if "_raw" in entry:
+    # Second pass: keep non-stripped entries, reparenting where needed.
+    # Preserve original line when no reparenting is required.
+    reparented: set[str] = set()
+    for _line, entry in parsed:
+        if not isinstance(entry, dict):
             continue
         parent = entry.get("parentUuid", "")
         original_parent = parent
@@ -100,63 +97,32 @@ def strip_progress_entries(content: str) -> str:
             parent = uuid_to_parent.get(parent, "")
         if parent != original_parent:
             entry["parentUuid"] = parent
+            uid = entry.get("uuid", "")
+            if uid:
+                reparented.add(uid)
 
     result_lines: list[str] = []
-    for entry in kept:
-        if "_raw" in entry:
-            result_lines.append(entry["_raw"])
-        else:
+    for line, entry in parsed:
+        if not isinstance(entry, dict):
+            result_lines.append(line)
+            continue
+        if entry.get("type", "") in STRIPPABLE_TYPES:
+            continue
+        uid = entry.get("uuid", "")
+        if uid in reparented:
+            # Re-serialize only entries whose parentUuid was changed.
             result_lines.append(json.dumps(entry, separators=(",", ":")))
+        else:
+            result_lines.append(line)
 
     return "\n".join(result_lines) + "\n"
 
 
 # ---------------------------------------------------------------------------
-# Local file I/O (read from CLI's JSONL, write temp file for --resume)
+# Local file I/O (write temp file for --resume)
 # ---------------------------------------------------------------------------
 
 
-def read_transcript_file(transcript_path: str) -> str | None:
-    """Read a JSONL transcript file from disk.
-
-    Returns the raw JSONL content, or ``None`` if the file is missing, empty,
-    or only contains metadata (≤2 lines with no conversation messages).
-    """
-    if not transcript_path or not os.path.isfile(transcript_path):
-        logger.debug(f"[Transcript] File not found: {transcript_path}")
-        return None
-
-    try:
-        with open(transcript_path) as f:
-            content = f.read()
-
-        if not content.strip():
-            logger.debug("[Transcript] File is empty: %s", transcript_path)
-            return None
-
-        lines = content.strip().split("\n")
-
-        # Validate that the transcript has real conversation content
-        # (not just metadata like queue-operation entries).
-        if not validate_transcript(content):
-            logger.debug(
-                "[Transcript] No conversation content (%d lines) in %s",
-                len(lines),
-                transcript_path,
-            )
-            return None
-
-        logger.info(
-            f"[Transcript] Read {len(lines)} lines, "
-            f"{len(content)} bytes from {transcript_path}"
-        )
-        return content
-
-    except (json.JSONDecodeError, OSError) as e:
-        logger.warning(f"[Transcript] Failed to read {transcript_path}: {e}")
-        return None
-
-
 def _sanitize_id(raw_id: str, max_len: int = 36) -> str:
     """Sanitize an ID for safe use in file paths.
 
@@ -171,14 +137,6 @@ def _sanitize_id(raw_id: str, max_len: int = 36) -> str:
 _SAFE_CWD_PREFIX = os.path.realpath("/tmp/copilot-")
 
 
-def _encode_cwd_for_cli(cwd: str) -> str:
-    """Encode a working directory path the same way the Claude CLI does.
-
-    The CLI replaces all non-alphanumeric characters with ``-``.
-    """
-    return re.sub(r"[^a-zA-Z0-9]", "-", os.path.realpath(cwd))
-
-
 def cleanup_cli_project_dir(sdk_cwd: str) -> None:
     """Remove the CLI's project directory for a specific working directory.
 
@@ -188,7 +146,8 @@ def cleanup_cli_project_dir(sdk_cwd: str) -> None:
     """
     import shutil
 
-    cwd_encoded = _encode_cwd_for_cli(sdk_cwd)
+    # Encode cwd the same way CLI does (replaces non-alphanumeric with -)
+    cwd_encoded = re.sub(r"[^a-zA-Z0-9]", "-", os.path.realpath(sdk_cwd))
     config_dir = os.environ.get("CLAUDE_CONFIG_DIR") or os.path.expanduser("~/.claude")
     projects_base = os.path.realpath(os.path.join(config_dir, "projects"))
     project_dir = os.path.realpath(os.path.join(projects_base, cwd_encoded))
@@ -248,32 +207,29 @@ def write_transcript_to_tempfile(
 def validate_transcript(content: str | None) -> bool:
     """Check that a transcript has actual conversation messages.
 
-    A valid transcript for resume needs at least one user message and one
-    assistant message (not just queue-operation / file-history-snapshot
-    metadata).
+    A valid transcript needs at least one assistant message (not just
+    queue-operation / file-history-snapshot metadata).  We do NOT require
+    a ``type: "user"`` entry because with ``--resume`` the user's message
+    is passed as a CLI query parameter and does not appear in the
+    transcript file.
     """
     if not content or not content.strip():
         return False
 
     lines = content.strip().split("\n")
-    if len(lines) < 2:
-        return False
 
-    has_user = False
     has_assistant = False
 
     for line in lines:
-        try:
-            entry = json.loads(line)
-            msg_type = entry.get("type")
-            if msg_type == "user":
-                has_user = True
-            elif msg_type == "assistant":
-                has_assistant = True
-        except json.JSONDecodeError:
+        if not line.strip():
+            continue
+        entry = json.loads(line, fallback=None)
+        if not isinstance(entry, dict):
             return False
+        if entry.get("type") == "assistant":
+            has_assistant = True
 
-    return has_user and has_assistant
+    return has_assistant
 
 
 # ---------------------------------------------------------------------------
@@ -328,58 +284,56 @@ async def upload_transcript(
     session_id: str,
     content: str,
     message_count: int = 0,
+    log_prefix: str = "[Transcript]",
 ) -> None:
-    """Strip progress entries and upload transcript to bucket storage.
+    """Strip progress entries and upload complete transcript.
 
-    Safety: only overwrites when the new (stripped) transcript is larger than
-    what is already stored.  Since JSONL is append-only, the latest transcript
-    is always the longest.  This prevents a slow/stale background task from
-    clobbering a newer upload from a concurrent turn.
+    The transcript represents the FULL active context (atomic).
+    Each upload REPLACES the previous transcript entirely.
+
+    The executor holds a cluster lock per session, so concurrent uploads for
+    the same session cannot happen.
 
     Args:
-        message_count: ``len(session.messages)`` at upload time — used by
-            the next turn to detect staleness and compress only the gap.
+        content: Complete JSONL transcript (from TranscriptBuilder).
+        message_count: ``len(session.messages)`` at upload time.
     """
     from backend.util.workspace_storage import get_workspace_storage
 
+    # Strip metadata entries (progress, file-history-snapshot, etc.)
+    # Note: SDK-built transcripts shouldn't have these, but strip for safety
     stripped = strip_progress_entries(content)
     if not validate_transcript(stripped):
+        # Log entry types for debugging — helps identify why validation failed
+        entry_types: list[str] = []
+        for line in stripped.strip().split("\n"):
+            entry = json.loads(line, fallback={"type": "INVALID_JSON"})
+            entry_types.append(entry.get("type", "?"))
         logger.warning(
-            f"[Transcript] Skipping upload — stripped content not valid "
-            f"for session {session_id}"
+            "%s Skipping upload — stripped content not valid "
+            "(types=%s, stripped_len=%d, raw_len=%d)",
+            log_prefix,
+            entry_types,
+            len(stripped),
+            len(content),
         )
+        logger.debug("%s Raw content preview: %s", log_prefix, content[:500])
+        logger.debug("%s Stripped content: %s", log_prefix, stripped[:500])
         return
 
     storage = await get_workspace_storage()
     wid, fid, fname = _storage_path_parts(user_id, session_id)
     encoded = stripped.encode("utf-8")
-    new_size = len(encoded)
 
-    # Check existing transcript size to avoid overwriting newer with older
-    path = _build_storage_path(user_id, session_id, storage)
-    content_skipped = False
-    try:
-        existing = await storage.retrieve(path)
-        if len(existing) >= new_size:
-            logger.info(
-                f"[Transcript] Skipping content upload — existing ({len(existing)}B) "
-                f">= new ({new_size}B) for session {session_id}"
-            )
-            content_skipped = True
-    except (FileNotFoundError, Exception):
-        pass  # No existing transcript or retrieval error — proceed with upload
+    await storage.store(
+        workspace_id=wid,
+        file_id=fid,
+        filename=fname,
+        content=encoded,
+    )
 
-    if not content_skipped:
-        await storage.store(
-            workspace_id=wid,
-            file_id=fid,
-            filename=fname,
-            content=encoded,
-        )
-
-    # Always update metadata (even when content is skipped) so message_count
-    # stays current.  The gap-fill logic in _build_query_message relies on
-    # message_count to avoid re-compressing the same messages every turn.
+    # Update metadata so message_count stays current.  The gap-fill logic
+    # in _build_query_message relies on it to avoid re-compressing messages.
     try:
         meta = {"message_count": message_count, "uploaded_at": time.time()}
         mwid, mfid, mfname = _meta_storage_path_parts(user_id, session_id)
@@ -390,18 +344,18 @@ async def upload_transcript(
             content=json.dumps(meta).encode("utf-8"),
         )
     except Exception as e:
-        logger.warning(f"[Transcript] Failed to write metadata for {session_id}: {e}")
+        logger.warning(f"{log_prefix} Failed to write metadata: {e}")
 
     logger.info(
-        f"[Transcript] Uploaded {new_size}B "
-        f"(stripped from {len(content)}B, msg_count={message_count}, "
-        f"content_skipped={content_skipped}) "
-        f"for session {session_id}"
+        f"{log_prefix} Uploaded {len(encoded)}B "
+        f"(stripped from {len(content)}B, msg_count={message_count})"
     )
 
 
 async def download_transcript(
-    user_id: str, session_id: str
+    user_id: str,
+    session_id: str,
+    log_prefix: str = "[Transcript]",
 ) -> TranscriptDownload | None:
     """Download transcript and metadata from bucket storage.
 
@@ -417,10 +371,10 @@ async def download_transcript(
         data = await storage.retrieve(path)
         content = data.decode("utf-8")
     except FileNotFoundError:
-        logger.debug(f"[Transcript] No transcript in storage for {session_id}")
+        logger.debug(f"{log_prefix} No transcript in storage")
         return None
     except Exception as e:
-        logger.warning(f"[Transcript] Failed to download transcript: {e}")
+        logger.warning(f"{log_prefix} Failed to download transcript: {e}")
         return None
 
     # Try to load metadata (best-effort — old transcripts won't have it)
@@ -437,16 +391,13 @@ async def download_transcript(
             meta_path = f"local://{mwid}/{mfid}/{mfname}"
 
         meta_data = await storage.retrieve(meta_path)
-        meta = json.loads(meta_data.decode("utf-8"))
+        meta = json.loads(meta_data.decode("utf-8"), fallback={})
         message_count = meta.get("message_count", 0)
         uploaded_at = meta.get("uploaded_at", 0.0)
-    except (FileNotFoundError, json.JSONDecodeError, Exception):
+    except (FileNotFoundError, Exception):
         pass  # No metadata — treat as unknown (msg_count=0 → always fill gap)
 
-    logger.info(
-        f"[Transcript] Downloaded {len(content)}B "
-        f"(msg_count={message_count}) for session {session_id}"
-    )
+    logger.info(f"{log_prefix} Downloaded {len(content)}B (msg_count={message_count})")
     return TranscriptDownload(
         content=content,
         message_count=message_count,

autogpt_platform/backend/backend/copilot/sdk/transcript_builder.py

@@ -0,0 +1,150 @@
+"""Build complete JSONL transcript from SDK messages.
+
+The transcript represents the FULL active context at any point in time.
+Each upload REPLACES the previous transcript atomically.
+
+Flow:
+  Turn 1: Upload [msg1, msg2]
+  Turn 2: Download [msg1, msg2] → Upload [msg1, msg2, msg3, msg4] (REPLACE)
+  Turn 3: Download [msg1, msg2, msg3, msg4] → Upload [all messages] (REPLACE)
+
+The transcript is never incremental - always the complete atomic state.
+"""
+
+import logging
+from typing import Any
+from uuid import uuid4
+
+from pydantic import BaseModel
+
+from backend.util import json
+
+from .transcript import STRIPPABLE_TYPES
+
+logger = logging.getLogger(__name__)
+
+
+class TranscriptEntry(BaseModel):
+    """Single transcript entry (user or assistant turn)."""
+
+    type: str
+    uuid: str
+    parentUuid: str | None
+    message: dict[str, Any]
+
+
+class TranscriptBuilder:
+    """Build complete JSONL transcript from SDK messages.
+
+    This builder maintains the FULL conversation state, not incremental changes.
+    The output is always the complete active context.
+    """
+
+    def __init__(self) -> None:
+        self._entries: list[TranscriptEntry] = []
+        self._last_uuid: str | None = None
+
+    def load_previous(self, content: str, log_prefix: str = "[Transcript]") -> None:
+        """Load complete previous transcript.
+
+        This loads the FULL previous context. As new messages come in,
+        we append to this state. The final output is the complete context
+        (previous + new), not just the delta.
+        """
+        if not content or not content.strip():
+            return
+
+        lines = content.strip().split("\n")
+        for line_num, line in enumerate(lines, 1):
+            if not line.strip():
+                continue
+
+            data = json.loads(line, fallback=None)
+            if data is None:
+                logger.warning(
+                    "%s Failed to parse transcript line %d/%d",
+                    log_prefix,
+                    line_num,
+                    len(lines),
+                )
+                continue
+
+            # Load all non-strippable entries (user/assistant/system/etc.)
+            # Skip only STRIPPABLE_TYPES to match strip_progress_entries() behavior
+            entry_type = data.get("type", "")
+            if entry_type in STRIPPABLE_TYPES:
+                continue
+
+            entry = TranscriptEntry(
+                type=data["type"],
+                uuid=data.get("uuid") or str(uuid4()),
+                parentUuid=data.get("parentUuid"),
+                message=data.get("message", {}),
+            )
+            self._entries.append(entry)
+            self._last_uuid = entry.uuid
+
+        logger.info(
+            "%s Loaded %d entries from previous transcript (last_uuid=%s)",
+            log_prefix,
+            len(self._entries),
+            self._last_uuid[:12] if self._last_uuid else None,
+        )
+
+    def add_user_message(
+        self, content: str | list[dict], uuid: str | None = None
+    ) -> None:
+        """Add user message to the complete context."""
+        msg_uuid = uuid or str(uuid4())
+
+        self._entries.append(
+            TranscriptEntry(
+                type="user",
+                uuid=msg_uuid,
+                parentUuid=self._last_uuid,
+                message={"role": "user", "content": content},
+            )
+        )
+        self._last_uuid = msg_uuid
+
+    def add_assistant_message(
+        self, content_blocks: list[dict], model: str = ""
+    ) -> None:
+        """Add assistant message to the complete context."""
+        msg_uuid = str(uuid4())
+
+        self._entries.append(
+            TranscriptEntry(
+                type="assistant",
+                uuid=msg_uuid,
+                parentUuid=self._last_uuid,
+                message={
+                    "role": "assistant",
+                    "model": model,
+                    "content": content_blocks,
+                },
+            )
+        )
+        self._last_uuid = msg_uuid
+
+    def to_jsonl(self) -> str:
+        """Export complete context as JSONL.
+
+        Returns the FULL conversation state (all entries), not incremental.
+        This output REPLACES any previous transcript.
+        """
+        if not self._entries:
+            return ""
+
+        lines = [entry.model_dump_json(exclude_none=True) for entry in self._entries]
+        return "\n".join(lines) + "\n"
+
+    @property
+    def entry_count(self) -> int:
+        """Total number of entries in the complete context."""
+        return len(self._entries)
+
+    @property
+    def is_empty(self) -> bool:
+        """Whether this builder has any entries."""
+        return len(self._entries) == 0

autogpt_platform/backend/backend/copilot/sdk/transcript_test.py

@@ -1,11 +1,11 @@
 """Unit tests for JSONL transcript management utilities."""
 
-import json
 import os
 
+from backend.util import json
+
 from .transcript import (
     STRIPPABLE_TYPES,
-    read_transcript_file,
     strip_progress_entries,
     validate_transcript,
     write_transcript_to_tempfile,
@@ -38,49 +38,6 @@ PROGRESS_ENTRY = {
 VALID_TRANSCRIPT = _make_jsonl(METADATA_LINE, FILE_HISTORY, USER_MSG, ASST_MSG)
 
 
-# --- read_transcript_file ---
-
-
-class TestReadTranscriptFile:
-    def test_returns_content_for_valid_file(self, tmp_path):
-        path = tmp_path / "session.jsonl"
-        path.write_text(VALID_TRANSCRIPT)
-        result = read_transcript_file(str(path))
-        assert result is not None
-        assert "user" in result
-
-    def test_returns_none_for_missing_file(self):
-        assert read_transcript_file("/nonexistent/path.jsonl") is None
-
-    def test_returns_none_for_empty_path(self):
-        assert read_transcript_file("") is None
-
-    def test_returns_none_for_empty_file(self, tmp_path):
-        path = tmp_path / "empty.jsonl"
-        path.write_text("")
-        assert read_transcript_file(str(path)) is None
-
-    def test_returns_none_for_metadata_only(self, tmp_path):
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY)
-        path = tmp_path / "meta.jsonl"
-        path.write_text(content)
-        assert read_transcript_file(str(path)) is None
-
-    def test_returns_none_for_invalid_json(self, tmp_path):
-        path = tmp_path / "bad.jsonl"
-        path.write_text("not json\n{}\n{}\n")
-        assert read_transcript_file(str(path)) is None
-
-    def test_no_size_limit(self, tmp_path):
-        """Large files are accepted — bucket storage has no size limit."""
-        big_content = {"type": "user", "uuid": "u9", "data": "x" * 1_000_000}
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY, big_content, ASST_MSG)
-        path = tmp_path / "big.jsonl"
-        path.write_text(content)
-        result = read_transcript_file(str(path))
-        assert result is not None
-
-
 # --- write_transcript_to_tempfile ---
 
 
@@ -155,12 +112,56 @@ class TestValidateTranscript:
         assert validate_transcript(content) is False
 
     def test_assistant_only_no_user(self):
+        """With --resume the user message is a CLI query param, not a transcript entry.
+        A transcript with only assistant entries is valid."""
         content = _make_jsonl(METADATA_LINE, FILE_HISTORY, ASST_MSG)
-        assert validate_transcript(content) is False
+        assert validate_transcript(content) is True
+
+    def test_resume_transcript_without_user_entry(self):
+        """Simulates a real --resume stop hook transcript: the CLI session file
+        has summary + assistant entries but no user entry."""
+        summary = {"type": "summary", "uuid": "s1", "text": "context..."}
+        asst1 = {
+            "type": "assistant",
+            "uuid": "a1",
+            "message": {"role": "assistant", "content": "Hello!"},
+        }
+        asst2 = {
+            "type": "assistant",
+            "uuid": "a2",
+            "parentUuid": "a1",
+            "message": {"role": "assistant", "content": "Sure, let me help."},
+        }
+        content = _make_jsonl(summary, asst1, asst2)
+        assert validate_transcript(content) is True
+
+    def test_single_assistant_entry(self):
+        """A transcript with just one assistant line is valid — the CLI may
+        produce short transcripts for simple responses with no tool use."""
+        content = json.dumps(ASST_MSG) + "\n"
+        assert validate_transcript(content) is True
 
     def test_invalid_json_returns_false(self):
         assert validate_transcript("not json\n{}\n{}\n") is False
 
+    def test_malformed_json_after_valid_assistant_returns_false(self):
+        """Validation must scan all lines - malformed JSON anywhere should fail."""
+        valid_asst = json.dumps(ASST_MSG)
+        malformed = "not valid json"
+        content = valid_asst + "\n" + malformed + "\n"
+        assert validate_transcript(content) is False
+
+    def test_blank_lines_are_skipped(self):
+        """Transcripts with blank lines should be valid if they contain assistant entries."""
+        content = (
+            json.dumps(USER_MSG)
+            + "\n\n"  # blank line
+            + json.dumps(ASST_MSG)
+            + "\n"
+            + "\n"  # another blank line
+        )
+        assert validate_transcript(content) is True
+
 
 # --- strip_progress_entries ---
 
@@ -253,3 +254,31 @@ class TestStripProgressEntries:
         assert "queue-operation" not in result_types
         assert "user" in result_types
         assert "assistant" in result_types
+
+    def test_preserves_original_line_formatting(self):
+        """Non-reparented entries keep their original JSON formatting."""
+        # orjson produces compact JSON - test that we preserve the exact input
+        # when no reparenting is needed (no re-serialization)
+        original_line = json.dumps(USER_MSG)
+
+        content = original_line + "\n" + json.dumps(ASST_MSG) + "\n"
+        result = strip_progress_entries(content)
+        result_lines = result.strip().split("\n")
+
+        # Original line should be byte-identical (not re-serialized)
+        assert result_lines[0] == original_line
+
+    def test_reparented_entries_are_reserialized(self):
+        """Entries whose parentUuid changes must be re-serialized."""
+        progress = {"type": "progress", "uuid": "p1", "parentUuid": "u1"}
+        asst = {
+            "type": "assistant",
+            "uuid": "a1",
+            "parentUuid": "p1",
+            "message": {"role": "assistant", "content": "done"},
+        }
+        content = _make_jsonl(USER_MSG, progress, asst)
+        result = strip_progress_entries(content)
+        lines = result.strip().split("\n")
+        asst_entry = json.loads(lines[-1])
+        assert asst_entry["parentUuid"] == "u1"  # reparented

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -81,6 +81,7 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.CLAUDE_4_OPUS: 21,
     LlmModel.CLAUDE_4_SONNET: 5,
     LlmModel.CLAUDE_4_6_OPUS: 14,
+    LlmModel.CLAUDE_4_6_SONNET: 9,
     LlmModel.CLAUDE_4_5_HAIKU: 4,
     LlmModel.CLAUDE_4_5_OPUS: 14,
     LlmModel.CLAUDE_4_5_SONNET: 9,

autogpt_platform/backend/backend/data/db_manager.py

@@ -305,6 +305,7 @@ class DatabaseManager(AppService):
     delete_chat_session = _(chat_db.delete_chat_session)
     get_next_sequence = _(chat_db.get_next_sequence)
     update_tool_message_content = _(chat_db.update_tool_message_content)
+    update_chat_session_title = _(chat_db.update_chat_session_title)
 
 
 class DatabaseManagerClient(AppServiceClient):
@@ -475,3 +476,4 @@ class DatabaseManagerAsyncClient(AppServiceClient):
     delete_chat_session = d.delete_chat_session
     get_next_sequence = d.get_next_sequence
     update_tool_message_content = d.update_tool_message_content
+    update_chat_session_title = d.update_chat_session_title

autogpt_platform/backend/backend/data/integrations.py

@@ -184,17 +184,17 @@ async def find_webhook_by_credentials_and_props(
     credentials_id: str,
     webhook_type: str,
     resource: str,
-    events: Optional[list[str]],
+    events: list[str] | None = None,
 ) -> Webhook | None:
-    webhook = await IntegrationWebhook.prisma().find_first(
-        where={
-            "userId": user_id,
-            "credentialsId": credentials_id,
-            "webhookType": webhook_type,
-            "resource": resource,
-            **({"events": {"has_every": events}} if events else {}),
-        },
-    )
+    where: IntegrationWebhookWhereInput = {
+        "userId": user_id,
+        "credentialsId": credentials_id,
+        "webhookType": webhook_type,
+        "resource": resource,
+    }
+    if events is not None:
+        where["events"] = {"has_every": events}
+    webhook = await IntegrationWebhook.prisma().find_first(where=where)
     return Webhook.from_db(webhook) if webhook else None
 
 

autogpt_platform/backend/backend/executor/utils.py

@@ -15,6 +15,7 @@ from backend.data import graph as graph_db
 from backend.data import human_review as human_review_db
 from backend.data import onboarding as onboarding_db
 from backend.data import user as user_db
+from backend.data import workspace as workspace_db
 
 # Import dynamic field utilities from centralized location
 from backend.data.block import BlockInput, BlockOutputEntry
@@ -32,7 +33,6 @@ from backend.data.execution import (
 from backend.data.graph import GraphModel, Node
 from backend.data.model import USER_TIMEZONE_NOT_SET, CredentialsMetaInput, GraphInput
 from backend.data.rabbitmq import Exchange, ExchangeType, Queue, RabbitMQConfig
-from backend.data.workspace import get_or_create_workspace
 from backend.util.clients import (
     get_async_execution_event_bus,
     get_async_execution_queue,
@@ -831,8 +831,9 @@ async def add_graph_execution(
         udb = user_db
         gdb = graph_db
         odb = onboarding_db
+        wdb = workspace_db
     else:
-        edb = udb = gdb = odb = get_database_manager_async_client()
+        edb = udb = gdb = odb = wdb = get_database_manager_async_client()
 
     # Get or create the graph execution
     if graph_exec_id:
@@ -892,7 +893,7 @@ async def add_graph_execution(
     if execution_context is None:
         user = await udb.get_user_by_id(user_id)
         settings = await gdb.get_graph_settings(user_id=user_id, graph_id=graph_id)
-        workspace = await get_or_create_workspace(user_id)
+        workspace = await wdb.get_or_create_workspace(user_id)
 
         execution_context = ExecutionContext(
             # Execution identity

autogpt_platform/backend/backend/executor/utils_test.py

@@ -368,12 +368,10 @@ async def test_add_graph_execution_is_repeatable(mocker: MockerFixture):
     mock_get_event_bus = mocker.patch(
         "backend.executor.utils.get_async_execution_event_bus"
     )
+    mock_wdb = mocker.patch("backend.executor.utils.workspace_db")
     mock_workspace = mocker.MagicMock()
     mock_workspace.id = "test-workspace-id"
-    mocker.patch(
-        "backend.executor.utils.get_or_create_workspace",
-        new=mocker.AsyncMock(return_value=mock_workspace),
-    )
+    mock_wdb.get_or_create_workspace = mocker.AsyncMock(return_value=mock_workspace)
 
     # Setup mock returns
     # The function returns (graph, starting_nodes_input, compiled_nodes_input_masks, nodes_to_skip)
@@ -649,12 +647,10 @@ async def test_add_graph_execution_with_nodes_to_skip(mocker: MockerFixture):
     mock_get_event_bus = mocker.patch(
         "backend.executor.utils.get_async_execution_event_bus"
     )
+    mock_wdb = mocker.patch("backend.executor.utils.workspace_db")
     mock_workspace = mocker.MagicMock()
     mock_workspace.id = "test-workspace-id"
-    mocker.patch(
-        "backend.executor.utils.get_or_create_workspace",
-        new=mocker.AsyncMock(return_value=mock_workspace),
-    )
+    mock_wdb.get_or_create_workspace = mocker.AsyncMock(return_value=mock_workspace)
 
     # Setup returns - include nodes_to_skip in the tuple
     mock_validate.return_value = (

autogpt_platform/backend/backend/integrations/webhooks/telegram.py

@@ -76,7 +76,6 @@ class TelegramWebhooksManager(BaseWebhooksManager):
             credentials_id=credentials.id,
             webhook_type=webhook_type,
             resource=resource,
-            events=None,  # Ignore events for this lookup
         ):
             # Re-register with Telegram using the same URL but new allowed_updates
             ingress_url = webhook_ingress_url(self.PROVIDER_NAME, existing.id)
@@ -143,10 +142,6 @@ class TelegramWebhooksManager(BaseWebhooksManager):
             elif "video" in message:
                 event_type = "message.video"
             else:
-                logger.warning(
-                    "Unknown Telegram webhook payload type; "
-                    f"message.keys() = {message.keys()}"
-                )
                 event_type = "message.other"
         elif "edited_message" in payload:
             event_type = "message.edited_message"

autogpt_platform/backend/backend/util/json.py

@@ -72,19 +72,58 @@ def dumps(
 
 T = TypeVar("T")
 
-
-@overload
-def loads(data: str | bytes, *args, target_type: Type[T], **kwargs) -> T: ...
+# Sentinel value to detect when fallback is not provided
+_NO_FALLBACK = object()
 
 
 @overload
-def loads(data: str | bytes, *args, **kwargs) -> Any: ...
+def loads(
+    data: str | bytes, *args, target_type: Type[T], fallback: T | None = None, **kwargs
+) -> T:
+    pass
+
+
+@overload
+def loads(data: str | bytes, *args, fallback: Any = None, **kwargs) -> Any:
+    pass
 
 
 def loads(
-    data: str | bytes, *args, target_type: Type[T] | None = None, **kwargs
+    data: str | bytes,
+    *args,
+    target_type: Type[T] | None = None,
+    fallback: Any = _NO_FALLBACK,
+    **kwargs,
 ) -> Any:
-    parsed = orjson.loads(data)
+    """Parse JSON with optional fallback on decode errors.
+
+    Args:
+        data: JSON string or bytes to parse
+        target_type: Optional type to validate/cast result to
+        fallback: Value to return on JSONDecodeError. If not provided, raises.
+        **kwargs: Additional arguments (unused, for compatibility)
+
+    Returns:
+        Parsed JSON data, or fallback value if parsing fails
+
+    Raises:
+        orjson.JSONDecodeError: Only if fallback is not provided
+
+    Examples:
+        >>> loads('{"valid": "json"}')
+        {'valid': 'json'}
+        >>> loads('invalid json', fallback=None)
+        None
+        >>> loads('invalid json', fallback={})
+        {}
+        >>> loads('invalid json')  # raises orjson.JSONDecodeError
+    """
+    try:
+        parsed = orjson.loads(data)
+    except orjson.JSONDecodeError:
+        if fallback is not _NO_FALLBACK:
+            return fallback
+        raise
 
     if target_type:
         return type_match(parsed, target_type)

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

@@ -5,15 +5,19 @@ import {
 } from "@/components/ai-elements/conversation";
 import { Message, MessageContent } from "@/components/ai-elements/message";
 import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
-import { FileUIPart, UIDataTypes, UIMessage, UITools } from "ai";
+import { FileUIPart, ToolUIPart, UIDataTypes, UIMessage, UITools } from "ai";
 import { TOOL_PART_PREFIX } from "../JobStatsBar/constants";
 import { TurnStatsBar } from "../JobStatsBar/TurnStatsBar";
 import { parseSpecialMarkers } from "./helpers";
 import { AssistantMessageActions } from "./components/AssistantMessageActions";
+import { CollapsedToolGroup } from "./components/CollapsedToolGroup";
 import { MessageAttachments } from "./components/MessageAttachments";
 import { MessagePartRenderer } from "./components/MessagePartRenderer";
+import { ReasoningCollapse } from "./components/ReasoningCollapse";
 import { ThinkingIndicator } from "./components/ThinkingIndicator";
 
+type MessagePart = UIMessage<unknown, UIDataTypes, UITools>["parts"][number];
+
 interface Props {
   messages: UIMessage<unknown, UIDataTypes, UITools>[];
   status: string;
@@ -23,6 +27,132 @@ interface Props {
   sessionID?: string | null;
 }
 
+function isCompletedToolPart(part: MessagePart): part is ToolUIPart {
+  return (
+    part.type.startsWith("tool-") &&
+    "state" in part &&
+    (part.state === "output-available" || part.state === "output-error")
+  );
+}
+
+type RenderSegment =
+  | { kind: "part"; part: MessagePart; index: number }
+  | { kind: "collapsed-group"; parts: ToolUIPart[] };
+
+// Tool types that have custom renderers and should NOT be collapsed
+const CUSTOM_TOOL_TYPES = new Set([
+  "tool-find_block",
+  "tool-find_agent",
+  "tool-find_library_agent",
+  "tool-search_docs",
+  "tool-get_doc_page",
+  "tool-run_block",
+  "tool-run_mcp_tool",
+  "tool-run_agent",
+  "tool-schedule_agent",
+  "tool-create_agent",
+  "tool-edit_agent",
+  "tool-view_agent_output",
+  "tool-search_feature_requests",
+  "tool-create_feature_request",
+]);
+
+/**
+ * Groups consecutive completed generic tool parts into collapsed segments.
+ * Non-generic tools (those with custom renderers) and active/streaming tools
+ * are left as individual parts.
+ */
+function buildRenderSegments(
+  parts: MessagePart[],
+  baseIndex = 0,
+): RenderSegment[] {
+  const segments: RenderSegment[] = [];
+  let pendingGroup: Array<{ part: ToolUIPart; index: number }> | null = null;
+
+  function flushGroup() {
+    if (!pendingGroup) return;
+    if (pendingGroup.length >= 2) {
+      segments.push({
+        kind: "collapsed-group",
+        parts: pendingGroup.map((p) => p.part),
+      });
+    } else {
+      for (const p of pendingGroup) {
+        segments.push({ kind: "part", part: p.part, index: p.index });
+      }
+    }
+    pendingGroup = null;
+  }
+
+  parts.forEach((part, i) => {
+    const absoluteIndex = baseIndex + i;
+    const isGenericCompletedTool =
+      isCompletedToolPart(part) && !CUSTOM_TOOL_TYPES.has(part.type);
+
+    if (isGenericCompletedTool) {
+      if (!pendingGroup) pendingGroup = [];
+      pendingGroup.push({ part: part as ToolUIPart, index: absoluteIndex });
+    } else {
+      flushGroup();
+      segments.push({ kind: "part", part, index: absoluteIndex });
+    }
+  });
+
+  flushGroup();
+  return segments;
+}
+
+/**
+ * For finalized assistant messages, split parts into "reasoning" (intermediate
+ * text + tools before the final response) and "response" (final text after the
+ * last tool). If there are no tools, everything is response.
+ */
+function splitReasoningAndResponse(parts: MessagePart[]): {
+  reasoning: MessagePart[];
+  response: MessagePart[];
+} {
+  const lastToolIndex = parts.findLastIndex((p) => p.type.startsWith("tool-"));
+
+  // No tools → everything is response
+  if (lastToolIndex === -1) {
+    return { reasoning: [], response: parts };
+  }
+
+  // Check if there's any text after the last tool
+  const hasResponseAfterTools = parts
+    .slice(lastToolIndex + 1)
+    .some((p) => p.type === "text");
+
+  if (!hasResponseAfterTools) {
+    // No final text response → don't collapse anything
+    return { reasoning: [], response: parts };
+  }
+
+  return {
+    reasoning: parts.slice(0, lastToolIndex + 1),
+    response: parts.slice(lastToolIndex + 1),
+  };
+}
+
+function renderSegments(
+  segments: RenderSegment[],
+  messageID: string,
+): React.ReactNode[] {
+  return segments.map((seg, segIdx) => {
+    if (seg.kind === "collapsed-group") {
+      return <CollapsedToolGroup key={`group-${segIdx}`} parts={seg.parts} />;
+    }
+    return (
+      <MessagePartRenderer
+        key={`${messageID}-${seg.index}`}
+        part={seg.part}
+        messageID={messageID}
+        partIndex={seg.index}
+      />
+    );
+  });
+}
+
 /** Collect all messages belonging to a turn: the user message + every
  *  assistant message up to (but not including) the next user message. */
 function getTurnMessages(
@@ -119,6 +249,24 @@ export function ChatMessagesContainer({
             (p): p is FileUIPart => p.type === "file",
           );
 
+          // For finalized assistant messages, split into reasoning + response.
+          // During streaming, show everything normally with tool collapsing.
+          const isFinalized =
+            message.role === "assistant" && !isCurrentlyStreaming;
+          const { reasoning, response } = isFinalized
+            ? splitReasoningAndResponse(message.parts)
+            : { reasoning: [] as MessagePart[], response: message.parts };
+          const hasReasoning = reasoning.length > 0;
+
+          const responseStartIndex = message.parts.length - response.length;
+          const responseSegments =
+            message.role === "assistant"
+              ? buildRenderSegments(response, responseStartIndex)
+              : null;
+          const reasoningSegments = hasReasoning
+            ? buildRenderSegments(reasoning, 0)
+            : null;
+
           return (
             <Message from={message.role} key={message.id}>
               <MessageContent
@@ -128,14 +276,21 @@ export function ChatMessagesContainer({
                   "group-[.is-assistant]:bg-transparent group-[.is-assistant]:text-slate-900"
                 }
               >
-                {message.parts.map((part, i) => (
-                  <MessagePartRenderer
-                    key={`${message.id}-${i}`}
-                    part={part}
-                    messageID={message.id}
-                    partIndex={i}
-                  />
-                ))}
+                {hasReasoning && reasoningSegments && (
+                  <ReasoningCollapse>
+                    {renderSegments(reasoningSegments, message.id)}
+                  </ReasoningCollapse>
+                )}
+                {responseSegments
+                  ? renderSegments(responseSegments, message.id)
+                  : message.parts.map((part, i) => (
+                      <MessagePartRenderer
+                        key={`${message.id}-${i}`}
+                        part={part}
+                        messageID={message.id}
+                        partIndex={i}
+                      />
+                    ))}
                 {isLastInTurn && !isCurrentlyStreaming && (
                   <TurnStatsBar
                     turnMessages={getTurnMessages(messages, messageIndex)}

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

@@ -0,0 +1,152 @@
+"use client";
+
+import { useId, useState } from "react";
+import {
+  ArrowsClockwiseIcon,
+  CaretRightIcon,
+  CheckCircleIcon,
+  FileIcon,
+  FilesIcon,
+  GearIcon,
+  GlobeIcon,
+  ListChecksIcon,
+  MagnifyingGlassIcon,
+  MonitorIcon,
+  PencilSimpleIcon,
+  TerminalIcon,
+  TrashIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import {
+  type ToolCategory,
+  extractToolName,
+  getAnimationText,
+  getToolCategory,
+} from "../../../tools/GenericTool/helpers";
+
+interface Props {
+  parts: ToolUIPart[];
+}
+
+/** Category icon matching GenericTool's ToolIcon for completed states. */
+function EntryIcon({
+  category,
+  isError,
+}: {
+  category: ToolCategory;
+  isError: boolean;
+}) {
+  if (isError) {
+    return (
+      <WarningDiamondIcon size={14} weight="regular" className="text-red-500" />
+    );
+  }
+
+  const iconClass = "text-green-500";
+  switch (category) {
+    case "bash":
+      return <TerminalIcon size={14} weight="regular" className={iconClass} />;
+    case "web":
+      return <GlobeIcon size={14} weight="regular" className={iconClass} />;
+    case "browser":
+      return <MonitorIcon size={14} weight="regular" className={iconClass} />;
+    case "file-read":
+    case "file-write":
+      return <FileIcon size={14} weight="regular" className={iconClass} />;
+    case "file-delete":
+      return <TrashIcon size={14} weight="regular" className={iconClass} />;
+    case "file-list":
+      return <FilesIcon size={14} weight="regular" className={iconClass} />;
+    case "search":
+      return (
+        <MagnifyingGlassIcon size={14} weight="regular" className={iconClass} />
+      );
+    case "edit":
+      return (
+        <PencilSimpleIcon size={14} weight="regular" className={iconClass} />
+      );
+    case "todo":
+      return (
+        <ListChecksIcon size={14} weight="regular" className={iconClass} />
+      );
+    case "compaction":
+      return (
+        <ArrowsClockwiseIcon size={14} weight="regular" className={iconClass} />
+      );
+    default:
+      return <GearIcon size={14} weight="regular" className={iconClass} />;
+  }
+}
+
+export function CollapsedToolGroup({ parts }: Props) {
+  const [expanded, setExpanded] = useState(false);
+  const panelId = useId();
+
+  const errorCount = parts.filter((p) => p.state === "output-error").length;
+  const label =
+    errorCount > 0
+      ? `${parts.length} tool calls (${errorCount} failed)`
+      : `${parts.length} tool calls completed`;
+
+  return (
+    <div className="py-1">
+      <button
+        type="button"
+        onClick={() => setExpanded(!expanded)}
+        aria-expanded={expanded}
+        aria-controls={panelId}
+        className="flex items-center gap-1.5 text-sm text-muted-foreground transition-colors hover:text-foreground"
+      >
+        <CaretRightIcon
+          size={12}
+          weight="bold"
+          className={
+            "transition-transform duration-150 " + (expanded ? "rotate-90" : "")
+          }
+        />
+        {errorCount > 0 ? (
+          <WarningDiamondIcon
+            size={14}
+            weight="regular"
+            className="text-red-500"
+          />
+        ) : (
+          <CheckCircleIcon
+            size={14}
+            weight="regular"
+            className="text-green-500"
+          />
+        )}
+        <span>{label}</span>
+      </button>
+
+      {expanded && (
+        <div
+          id={panelId}
+          className="ml-5 mt-1 space-y-0.5 border-l border-neutral-200 pl-3"
+        >
+          {parts.map((part) => {
+            const toolName = extractToolName(part);
+            const category = getToolCategory(toolName);
+            const text = getAnimationText(part, category);
+            const isError = part.state === "output-error";
+
+            return (
+              <div
+                key={part.toolCallId}
+                className={
+                  "flex items-center gap-1.5 text-xs " +
+                  (isError ? "text-red-500" : "text-muted-foreground")
+                }
+              >
+                <EntryIcon category={category} isError={isError} />
+                <span>{text}</span>
+              </div>
+            );
+          })}
+        </div>
+      )}
+    </div>
+  );
+}

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

@@ -15,6 +15,7 @@ export function FeedbackModal({ isOpen, onSubmit, onCancel }: Props) {
   const [comment, setComment] = useState("");
 
   function handleSubmit() {
+    if (!comment.trim()) return;
     onSubmit(comment);
     setComment("");
   }
@@ -36,7 +37,7 @@ export function FeedbackModal({ isOpen, onSubmit, onCancel }: Props) {
     >
       <Dialog.Content>
         <div className="mx-auto w-[95%] space-y-4">
-          <p className="text-sm text-slate-600">
+          <p className="text-sm text-muted-foreground">
             Your feedback helps us improve. Share details below.
           </p>
           <Textarea
@@ -48,12 +49,18 @@ export function FeedbackModal({ isOpen, onSubmit, onCancel }: Props) {
             className="resize-none"
           />
           <div className="flex items-center justify-between">
-            <p className="text-xs text-slate-400">{comment.length}/2000</p>
+            <p className="text-xs text-muted-foreground">
+              {comment.length}/2000
+            </p>
             <div className="flex gap-2">
               <Button variant="outline" size="sm" onClick={handleClose}>
                 Cancel
               </Button>
-              <Button size="sm" onClick={handleSubmit}>
+              <Button
+                size="sm"
+                onClick={handleSubmit}
+                disabled={!comment.trim()}
+              >
                 Submit feedback
               </Button>
             </div>

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

@@ -0,0 +1,27 @@
+"use client";
+
+import { LightbulbIcon } from "@phosphor-icons/react";
+import { Dialog } from "@/components/molecules/Dialog/Dialog";
+
+interface Props {
+  children: React.ReactNode;
+}
+
+export function ReasoningCollapse({ children }: Props) {
+  return (
+    <Dialog title="Reasoning">
+      <Dialog.Trigger>
+        <button
+          type="button"
+          className="flex items-center gap-1 text-xs text-zinc-500 transition-colors hover:text-zinc-700"
+        >
+          <LightbulbIcon size={12} weight="bold" />
+          <span>Show reasoning</span>
+        </button>
+      </Dialog.Trigger>
+      <Dialog.Content>
+        <div className="space-y-1">{children}</div>
+      </Dialog.Content>
+    </Dialog>
+  );
+}

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

@@ -3,6 +3,7 @@ import {
   getGetV2ListSessionsQueryKey,
   useDeleteV2DeleteSession,
   useGetV2ListSessions,
+  usePatchV2UpdateSessionTitle,
 } from "@/app/api/__generated__/endpoints/chat/chat";
 import { Button } from "@/components/atoms/Button/Button";
 import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
@@ -17,7 +18,6 @@ import { toast } from "@/components/molecules/Toast/use-toast";
 import {
   Sidebar,
   SidebarContent,
-  SidebarFooter,
   SidebarHeader,
   SidebarTrigger,
   useSidebar,
@@ -25,8 +25,9 @@ import {
 import { cn } from "@/lib/utils";
 import { DotsThree, PlusCircleIcon, PlusIcon } from "@phosphor-icons/react";
 import { useQueryClient } from "@tanstack/react-query";
-import { motion } from "framer-motion";
+import { AnimatePresence, motion } from "framer-motion";
 import { parseAsString, useQueryState } from "nuqs";
+import { useEffect, useRef, useState } from "react";
 import { useCopilotUIStore } from "../../store";
 import { DeleteChatDialog } from "../DeleteChatDialog/DeleteChatDialog";
 
@@ -65,6 +66,39 @@ export function ChatSidebar() {
       },
     });
 
+  const [editingSessionId, setEditingSessionId] = useState<string | null>(null);
+  const [editingTitle, setEditingTitle] = useState("");
+  const renameInputRef = useRef<HTMLInputElement>(null);
+  const renameCancelledRef = useRef(false);
+
+  const { mutate: renameSession } = usePatchV2UpdateSessionTitle({
+    mutation: {
+      onSuccess: () => {
+        queryClient.invalidateQueries({
+          queryKey: getGetV2ListSessionsQueryKey(),
+        });
+        setEditingSessionId(null);
+      },
+      onError: (error) => {
+        toast({
+          title: "Failed to rename chat",
+          description:
+            error instanceof Error ? error.message : "An error occurred",
+          variant: "destructive",
+        });
+        setEditingSessionId(null);
+      },
+    },
+  });
+
+  // Auto-focus the rename input when editing starts
+  useEffect(() => {
+    if (editingSessionId && renameInputRef.current) {
+      renameInputRef.current.focus();
+      renameInputRef.current.select();
+    }
+  }, [editingSessionId]);
+
   const sessions =
     sessionsResponse?.status === 200 ? sessionsResponse.data.sessions : [];
 
@@ -76,6 +110,26 @@ export function ChatSidebar() {
     setSessionId(id);
   }
 
+  function handleRenameClick(
+    e: React.MouseEvent,
+    id: string,
+    title: string | null | undefined,
+  ) {
+    e.stopPropagation();
+    renameCancelledRef.current = false;
+    setEditingSessionId(id);
+    setEditingTitle(title || "");
+  }
+
+  function handleRenameSubmit(id: string) {
+    const trimmed = editingTitle.trim();
+    if (trimmed) {
+      renameSession({ sessionId: id, data: { title: trimmed } });
+    } else {
+      setEditingSessionId(null);
+    }
+  }
+
   function handleDeleteClick(
     e: React.MouseEvent,
     id: string,
@@ -160,29 +214,42 @@ export function ChatSidebar() {
             </motion.div>
           </SidebarHeader>
         )}
+        {!isCollapsed && (
+          <SidebarHeader className="shrink-0 px-4 pb-4 pt-4 shadow-[0_4px_6px_-1px_rgba(0,0,0,0.05)]">
+            <motion.div
+              initial={{ opacity: 0 }}
+              animate={{ opacity: 1 }}
+              transition={{ duration: 0.2, delay: 0.1 }}
+              className="flex flex-col gap-3 px-3"
+            >
+              <div className="flex items-center justify-between">
+                <Text variant="h3" size="body-medium">
+                  Your chats
+                </Text>
+                <div className="relative left-6">
+                  <SidebarTrigger />
+                </div>
+              </div>
+              <Button
+                variant="primary"
+                size="small"
+                onClick={handleNewChat}
+                className="w-full"
+                leftIcon={<PlusIcon className="h-4 w-4" weight="bold" />}
+              >
+                New Chat
+              </Button>
+            </motion.div>
+          </SidebarHeader>
+        )}
+
         <SidebarContent className="gap-4 overflow-y-auto px-4 py-4 [-ms-overflow-style:none] [scrollbar-width:none] [&::-webkit-scrollbar]:hidden">
-          {!isCollapsed && (
-            <motion.div
-              initial={{ opacity: 0 }}
-              animate={{ opacity: 1 }}
-              transition={{ duration: 0.2, delay: 0.1 }}
-              className="flex items-center justify-between px-3"
-            >
-              <Text variant="h3" size="body-medium">
-                Your chats
-              </Text>
-              <div className="relative left-6">
-                <SidebarTrigger />
-              </div>
-            </motion.div>
-          )}
-
           {!isCollapsed && (
             <motion.div
               initial={{ opacity: 0 }}
               animate={{ opacity: 1 }}
               transition={{ duration: 0.2, delay: 0.15 }}
-              className="mt-4 flex flex-col gap-1"
+              className="flex flex-col gap-1"
             >
               {isLoadingSessions ? (
                 <div className="flex min-h-[30rem] items-center justify-center py-4">
@@ -203,76 +270,105 @@ export function ChatSidebar() {
                         : "hover:bg-zinc-50",
                     )}
                   >
-                    <button
-                      onClick={() => handleSelectSession(session.id)}
-                      className="w-full px-3 py-2.5 pr-10 text-left"
-                    >
-                      <div className="flex min-w-0 max-w-full flex-col overflow-hidden">
-                        <div className="min-w-0 max-w-full">
-                          <Text
-                            variant="body"
-                            className={cn(
-                              "truncate font-normal",
-                              session.id === sessionId
-                                ? "text-zinc-600"
-                                : "text-zinc-800",
-                            )}
-                          >
-                            {session.title || `Untitled chat`}
+                    {editingSessionId === session.id ? (
+                      <div className="px-3 py-2.5">
+                        <input
+                          ref={renameInputRef}
+                          type="text"
+                          aria-label="Rename chat"
+                          value={editingTitle}
+                          onChange={(e) => setEditingTitle(e.target.value)}
+                          onKeyDown={(e) => {
+                            if (e.key === "Enter") {
+                              e.currentTarget.blur();
+                            } else if (e.key === "Escape") {
+                              renameCancelledRef.current = true;
+                              setEditingSessionId(null);
+                            }
+                          }}
+                          onBlur={() => {
+                            if (renameCancelledRef.current) {
+                              renameCancelledRef.current = false;
+                              return;
+                            }
+                            handleRenameSubmit(session.id);
+                          }}
+                          className="w-full rounded border border-zinc-300 bg-white px-2 py-1 text-sm text-zinc-800 outline-none focus:border-purple-500 focus:ring-1 focus:ring-purple-500"
+                        />
+                      </div>
+                    ) : (
+                      <button
+                        onClick={() => handleSelectSession(session.id)}
+                        className="w-full px-3 py-2.5 pr-10 text-left"
+                      >
+                        <div className="flex min-w-0 max-w-full flex-col overflow-hidden">
+                          <div className="min-w-0 max-w-full">
+                            <Text
+                              variant="body"
+                              className={cn(
+                                "truncate font-normal",
+                                session.id === sessionId
+                                  ? "text-zinc-600"
+                                  : "text-zinc-800",
+                              )}
+                            >
+                              <AnimatePresence mode="wait" initial={false}>
+                                <motion.span
+                                  key={session.title || "untitled"}
+                                  initial={{ opacity: 0, y: 4 }}
+                                  animate={{ opacity: 1, y: 0 }}
+                                  exit={{ opacity: 0, y: -4 }}
+                                  transition={{ duration: 0.2 }}
+                                  className="block truncate"
+                                >
+                                  {session.title || "Untitled chat"}
+                                </motion.span>
+                              </AnimatePresence>
+                            </Text>
+                          </div>
+                          <Text variant="small" className="text-neutral-400">
+                            {formatDate(session.updated_at)}
                           </Text>
                         </div>
-                        <Text variant="small" className="text-neutral-400">
-                          {formatDate(session.updated_at)}
-                        </Text>
-                      </div>
-                    </button>
-                    <DropdownMenu>
-                      <DropdownMenuTrigger asChild>
-                        <button
-                          onClick={(e) => e.stopPropagation()}
-                          className="absolute right-2 top-1/2 -translate-y-1/2 rounded-full p-1.5 text-zinc-600 transition-all hover:bg-neutral-100"
-                          aria-label="More actions"
-                        >
-                          <DotsThree className="h-4 w-4" />
-                        </button>
-                      </DropdownMenuTrigger>
-                      <DropdownMenuContent align="end">
-                        <DropdownMenuItem
-                          onClick={(e) =>
-                            handleDeleteClick(e, session.id, session.title)
-                          }
-                          disabled={isDeleting}
-                          className="text-red-600 focus:bg-red-50 focus:text-red-600"
-                        >
-                          Delete chat
-                        </DropdownMenuItem>
-                      </DropdownMenuContent>
-                    </DropdownMenu>
+                      </button>
+                    )}
+                    {editingSessionId !== session.id && (
+                      <DropdownMenu>
+                        <DropdownMenuTrigger asChild>
+                          <button
+                            onClick={(e) => e.stopPropagation()}
+                            className="absolute right-2 top-1/2 -translate-y-1/2 rounded-full p-1.5 text-zinc-600 transition-all hover:bg-neutral-100"
+                            aria-label="More actions"
+                          >
+                            <DotsThree className="h-4 w-4" />
+                          </button>
+                        </DropdownMenuTrigger>
+                        <DropdownMenuContent align="end">
+                          <DropdownMenuItem
+                            onClick={(e) =>
+                              handleRenameClick(e, session.id, session.title)
+                            }
+                          >
+                            Rename
+                          </DropdownMenuItem>
+                          <DropdownMenuItem
+                            onClick={(e) =>
+                              handleDeleteClick(e, session.id, session.title)
+                            }
+                            disabled={isDeleting}
+                            className="text-red-600 focus:bg-red-50 focus:text-red-600"
+                          >
+                            Delete chat
+                          </DropdownMenuItem>
+                        </DropdownMenuContent>
+                      </DropdownMenu>
+                    )}
                   </div>
                 ))
               )}
             </motion.div>
           )}
         </SidebarContent>
-        {!isCollapsed && sessionId && (
-          <SidebarFooter className="shrink-0 bg-zinc-50 p-3 pb-1 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
-            <motion.div
-              initial={{ opacity: 0 }}
-              animate={{ opacity: 1 }}
-              transition={{ duration: 0.2, delay: 0.2 }}
-            >
-              <Button
-                variant="primary"
-                size="small"
-                onClick={handleNewChat}
-                className="w-full"
-                leftIcon={<PlusIcon className="h-4 w-4" weight="bold" />}
-              >
-                New Chat
-              </Button>
-            </motion.div>
-          </SidebarFooter>
-        )}
       </Sidebar>
 
       <DeleteChatDialog

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

@@ -29,7 +29,6 @@ export function DeleteChatDialog({
           }
         },
       }}
-      onClose={isDeleting ? undefined : onCancel}
     >
       <Dialog.Content>
         <Text variant="body">

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

@@ -71,6 +71,17 @@ export function MobileDrawer({
                 <X width="1rem" height="1rem" />
               </Button>
             </div>
+            <div className="mt-2">
+              <Button
+                variant="primary"
+                size="small"
+                onClick={onNewChat}
+                className="w-full"
+                leftIcon={<PlusIcon width="1rem" height="1rem" />}
+              >
+                New Chat
+              </Button>
+            </div>
           </div>
           <div
             className={cn(
@@ -120,19 +131,6 @@ export function MobileDrawer({
               ))
             )}
           </div>
-          {currentSessionId && (
-            <div className="shrink-0 bg-white p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
-              <Button
-                variant="primary"
-                size="small"
-                onClick={onNewChat}
-                className="w-full"
-                leftIcon={<PlusIcon width="1rem" height="1rem" />}
-              >
-                New Chat
-              </Button>
-            </div>
-          )}
         </Drawer.Content>
       </Drawer.Portal>
     </Drawer.Root>

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

@@ -181,6 +181,14 @@ export function convertChatSessionMessagesToUiMessages(
 
     if (parts.length === 0) return;
 
+    // Merge consecutive assistant messages into a single UIMessage
+    // to avoid split bubbles on page reload.
+    const prevUI = uiMessages[uiMessages.length - 1];
+    if (msg.role === "assistant" && prevUI && prevUI.role === "assistant") {
+      prevUI.parts.push(...parts);
+      return;
+    }
+
     uiMessages.push({
       id: `${sessionId}-${index}`,
       role: msg.role,

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

@@ -10,7 +10,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 
 export type CreateAgentToolOutput =
   | AgentPreviewResponse
@@ -134,7 +134,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <ScaleLoader size={14} />;
   }
   return <PlusIcon size={14} weight="regular" className="text-neutral-400" />;
 }

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

@@ -9,7 +9,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 
 export type EditAgentToolOutput =
   | AgentPreviewResponse
@@ -121,7 +121,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <ScaleLoader size={14} />;
   }
   return (
     <PencilLineIcon size={14} weight="regular" className="text-neutral-400" />

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

@@ -31,6 +31,13 @@ import {
   OutputItem,
 } from "@/components/contextual/OutputRenderers";
 import type { OutputMetadata } from "@/components/contextual/OutputRenderers";
+import {
+  type ToolCategory,
+  extractToolName,
+  getAnimationText,
+  getToolCategory,
+  truncate,
+} from "./helpers";
 
 interface Props {
   part: ToolUIPart;
@@ -48,77 +55,6 @@ function RenderMedia({
   return <OutputItem value={value} metadata={metadata} renderer={renderer} />;
 }
 
-/* ------------------------------------------------------------------ */
-/*  Tool name helpers                                                  */
-/* ------------------------------------------------------------------ */
-
-function extractToolName(part: ToolUIPart): string {
-  return part.type.replace(/^tool-/, "");
-}
-
-function formatToolName(name: string): string {
-  return name.replace(/_/g, " ").replace(/^\w/, (c) => c.toUpperCase());
-}
-
-/* ------------------------------------------------------------------ */
-/*  Tool categorization                                                */
-/* ------------------------------------------------------------------ */
-
-type ToolCategory =
-  | "bash"
-  | "web"
-  | "browser"
-  | "file-read"
-  | "file-write"
-  | "file-delete"
-  | "file-list"
-  | "search"
-  | "edit"
-  | "todo"
-  | "compaction"
-  | "other";
-
-function getToolCategory(toolName: string): ToolCategory {
-  switch (toolName) {
-    case "bash_exec":
-      return "bash";
-    case "web_fetch":
-    case "WebSearch":
-    case "WebFetch":
-      return "web";
-    case "browser_navigate":
-    case "browser_act":
-    case "browser_screenshot":
-      return "browser";
-    case "read_workspace_file":
-    case "read_file":
-    case "Read":
-      return "file-read";
-    case "write_workspace_file":
-    case "write_file":
-    case "Write":
-      return "file-write";
-    case "delete_workspace_file":
-      return "file-delete";
-    case "list_workspace_files":
-    case "glob":
-    case "Glob":
-      return "file-list";
-    case "grep":
-    case "Grep":
-      return "search";
-    case "edit_file":
-    case "Edit":
-      return "edit";
-    case "TodoWrite":
-      return "todo";
-    case "context_compaction":
-      return "compaction";
-    default:
-      return "other";
-  }
-}
-
 /* ------------------------------------------------------------------ */
 /*  Tool icon                                                          */
 /* ------------------------------------------------------------------ */
@@ -141,7 +77,7 @@ function ToolIcon({
     return <OrbitLoader size={14} />;
   }
 
-  const iconClass = "text-neutral-400";
+  const iconClass = "text-green-500";
   switch (category) {
     case "bash":
       return <TerminalIcon size={14} weight="regular" className={iconClass} />;
@@ -210,191 +146,6 @@ function AccordionIcon({ category }: { category: ToolCategory }) {
   }
 }
 
-/* ------------------------------------------------------------------ */
-/*  Input extraction                                                   */
-/* ------------------------------------------------------------------ */
-
-function getInputSummary(toolName: string, input: unknown): string | null {
-  if (!input || typeof input !== "object") return null;
-  const inp = input as Record<string, unknown>;
-
-  switch (toolName) {
-    case "bash_exec":
-      return typeof inp.command === "string" ? inp.command : null;
-    case "web_fetch":
-    case "WebFetch":
-      return typeof inp.url === "string" ? inp.url : null;
-    case "WebSearch":
-      return typeof inp.query === "string" ? inp.query : null;
-    case "browser_navigate":
-      return typeof inp.url === "string" ? inp.url : null;
-    case "browser_act":
-      return typeof inp.action === "string"
-        ? inp.target
-          ? `${inp.action} ${inp.target}`
-          : (inp.action as string)
-        : null;
-    case "browser_screenshot":
-      return null;
-    case "read_workspace_file":
-    case "read_file":
-    case "Read":
-      return (
-        (typeof inp.file_path === "string" ? inp.file_path : null) ??
-        (typeof inp.path === "string" ? inp.path : null)
-      );
-    case "write_workspace_file":
-    case "write_file":
-    case "Write":
-      return (
-        (typeof inp.file_path === "string" ? inp.file_path : null) ??
-        (typeof inp.path === "string" ? inp.path : null)
-      );
-    case "delete_workspace_file":
-      return typeof inp.file_path === "string" ? inp.file_path : null;
-    case "glob":
-    case "Glob":
-      return typeof inp.pattern === "string" ? inp.pattern : null;
-    case "grep":
-    case "Grep":
-      return typeof inp.pattern === "string" ? inp.pattern : null;
-    case "edit_file":
-    case "Edit":
-      return typeof inp.file_path === "string" ? inp.file_path : null;
-    case "TodoWrite": {
-      // Extract the in-progress task name for the status line
-      const todos = Array.isArray(inp.todos) ? inp.todos : [];
-      const active = todos.find(
-        (t: Record<string, unknown>) => t.status === "in_progress",
-      );
-      if (active && typeof active.activeForm === "string")
-        return active.activeForm;
-      if (active && typeof active.content === "string") return active.content;
-      return null;
-    }
-    default:
-      return null;
-  }
-}
-
-function truncate(text: string, maxLen: number): string {
-  if (text.length <= maxLen) return text;
-  return text.slice(0, maxLen).trimEnd() + "…";
-}
-
-/* ------------------------------------------------------------------ */
-/*  Animation text                                                     */
-/* ------------------------------------------------------------------ */
-
-function getAnimationText(part: ToolUIPart, category: ToolCategory): string {
-  const toolName = extractToolName(part);
-  const summary = getInputSummary(toolName, part.input);
-  const shortSummary = summary ? truncate(summary, 60) : null;
-
-  switch (part.state) {
-    case "input-streaming":
-    case "input-available": {
-      switch (category) {
-        case "bash":
-          return shortSummary ? `Running: ${shortSummary}` : "Running command…";
-        case "web":
-          if (toolName === "WebSearch") {
-            return shortSummary
-              ? `Searching "${shortSummary}"`
-              : "Searching the web…";
-          }
-          return shortSummary
-            ? `Fetching ${shortSummary}`
-            : "Fetching web content…";
-        case "browser":
-          if (toolName === "browser_screenshot") return "Taking screenshot…";
-          return shortSummary
-            ? `Browsing ${shortSummary}`
-            : "Interacting with browser…";
-        case "file-read":
-          return shortSummary ? `Reading ${shortSummary}` : "Reading file…";
-        case "file-write":
-          return shortSummary ? `Writing ${shortSummary}` : "Writing file…";
-        case "file-delete":
-          return shortSummary ? `Deleting ${shortSummary}` : "Deleting file…";
-        case "file-list":
-          return shortSummary ? `Listing ${shortSummary}` : "Listing files…";
-        case "search":
-          return shortSummary
-            ? `Searching for "${shortSummary}"`
-            : "Searching…";
-        case "edit":
-          return shortSummary ? `Editing ${shortSummary}` : "Editing file…";
-        case "todo":
-          return shortSummary ? `${shortSummary}` : "Updating task list…";
-        case "compaction":
-          return "Summarizing earlier messages…";
-        default:
-          return `Running ${formatToolName(toolName)}…`;
-      }
-    }
-    case "output-available": {
-      switch (category) {
-        case "bash": {
-          const exitCode = getExitCode(part.output);
-          if (exitCode !== null && exitCode !== 0) {
-            return `Command exited with code ${exitCode}`;
-          }
-          return shortSummary ? `Ran: ${shortSummary}` : "Command completed";
-        }
-        case "web":
-          if (toolName === "WebSearch") {
-            return shortSummary
-              ? `Searched "${shortSummary}"`
-              : "Web search completed";
-          }
-          return shortSummary
-            ? `Fetched ${shortSummary}`
-            : "Fetched web content";
-        case "browser":
-          if (toolName === "browser_screenshot") return "Screenshot captured";
-          return shortSummary
-            ? `Browsed ${shortSummary}`
-            : "Browser action completed";
-        case "file-read":
-          return shortSummary ? `Read ${shortSummary}` : "File read completed";
-        case "file-write":
-          return shortSummary ? `Wrote ${shortSummary}` : "File written";
-        case "file-delete":
-          return shortSummary ? `Deleted ${shortSummary}` : "File deleted";
-        case "file-list":
-          return "Listed files";
-        case "search":
-          return shortSummary
-            ? `Searched for "${shortSummary}"`
-            : "Search completed";
-        case "edit":
-          return shortSummary ? `Edited ${shortSummary}` : "Edit completed";
-        case "todo":
-          return "Updated task list";
-        case "compaction":
-          return "Earlier messages were summarized";
-        default:
-          return `${formatToolName(toolName)} completed`;
-      }
-    }
-    case "output-error": {
-      switch (category) {
-        case "bash":
-          return "Command failed";
-        case "web":
-          return toolName === "WebSearch" ? "Search failed" : "Fetch failed";
-        case "browser":
-          return "Browser action failed";
-        default:
-          return `${formatToolName(toolName)} failed`;
-      }
-    }
-    default:
-      return `Running ${formatToolName(toolName)}…`;
-  }
-}
-
 /* ------------------------------------------------------------------ */
 /*  Output parsing helpers                                             */
 /* ------------------------------------------------------------------ */
@@ -435,13 +186,6 @@ function extractMcpText(output: Record<string, unknown>): string | null {
   return null;
 }
 
-function getExitCode(output: unknown): number | null {
-  const parsed = parseOutput(output);
-  if (!parsed) return null;
-  if (typeof parsed.exit_code === "number") return parsed.exit_code;
-  return null;
-}
-
 function getStringField(
   obj: Record<string, unknown>,
   ...keys: string[]

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

@@ -0,0 +1,285 @@
+import type { ToolUIPart } from "ai";
+
+/* ------------------------------------------------------------------ */
+/*  Tool name helpers                                                  */
+/* ------------------------------------------------------------------ */
+
+export function extractToolName(part: ToolUIPart): string {
+  return part.type.replace(/^tool-/, "");
+}
+
+export function formatToolName(name: string): string {
+  return name.replace(/_/g, " ").replace(/^\w/, (c) => c.toUpperCase());
+}
+
+/* ------------------------------------------------------------------ */
+/*  Tool categorization                                                */
+/* ------------------------------------------------------------------ */
+
+export type ToolCategory =
+  | "bash"
+  | "web"
+  | "browser"
+  | "file-read"
+  | "file-write"
+  | "file-delete"
+  | "file-list"
+  | "search"
+  | "edit"
+  | "todo"
+  | "compaction"
+  | "other";
+
+export function getToolCategory(toolName: string): ToolCategory {
+  switch (toolName) {
+    case "bash_exec":
+      return "bash";
+    case "web_fetch":
+    case "WebSearch":
+    case "WebFetch":
+      return "web";
+    case "browser_navigate":
+    case "browser_act":
+    case "browser_screenshot":
+      return "browser";
+    case "read_workspace_file":
+    case "read_file":
+    case "Read":
+      return "file-read";
+    case "write_workspace_file":
+    case "write_file":
+    case "Write":
+      return "file-write";
+    case "delete_workspace_file":
+      return "file-delete";
+    case "list_workspace_files":
+    case "glob":
+    case "Glob":
+      return "file-list";
+    case "grep":
+    case "Grep":
+      return "search";
+    case "edit_file":
+    case "Edit":
+      return "edit";
+    case "TodoWrite":
+      return "todo";
+    case "context_compaction":
+      return "compaction";
+    default:
+      return "other";
+  }
+}
+
+/* ------------------------------------------------------------------ */
+/*  Input summary                                                      */
+/* ------------------------------------------------------------------ */
+
+function getInputSummary(toolName: string, input: unknown): string | null {
+  if (!input || typeof input !== "object") return null;
+  const inp = input as Record<string, unknown>;
+
+  switch (toolName) {
+    case "bash_exec":
+      return typeof inp.command === "string" ? inp.command : null;
+    case "web_fetch":
+    case "WebFetch":
+      return typeof inp.url === "string" ? inp.url : null;
+    case "WebSearch":
+      return typeof inp.query === "string" ? inp.query : null;
+    case "browser_navigate":
+      return typeof inp.url === "string" ? inp.url : null;
+    case "browser_act":
+      if (typeof inp.action !== "string") return null;
+      return typeof inp.target === "string"
+        ? `${inp.action} ${inp.target}`
+        : inp.action;
+    case "browser_screenshot":
+      return null;
+    case "read_workspace_file":
+    case "read_file":
+    case "Read":
+      return (
+        (typeof inp.file_path === "string" ? inp.file_path : null) ??
+        (typeof inp.path === "string" ? inp.path : null)
+      );
+    case "write_workspace_file":
+    case "write_file":
+    case "Write":
+      return (
+        (typeof inp.file_path === "string" ? inp.file_path : null) ??
+        (typeof inp.path === "string" ? inp.path : null)
+      );
+    case "delete_workspace_file":
+      return typeof inp.file_path === "string" ? inp.file_path : null;
+    case "glob":
+    case "Glob":
+      return typeof inp.pattern === "string" ? inp.pattern : null;
+    case "grep":
+    case "Grep":
+      return typeof inp.pattern === "string" ? inp.pattern : null;
+    case "edit_file":
+    case "Edit":
+      return typeof inp.file_path === "string" ? inp.file_path : null;
+    case "TodoWrite": {
+      const todos = Array.isArray(inp.todos) ? inp.todos : [];
+      const active = todos.find(
+        (t: unknown) =>
+          t !== null &&
+          typeof t === "object" &&
+          (t as Record<string, unknown>).status === "in_progress",
+      ) as Record<string, unknown> | undefined;
+      if (active && typeof active.activeForm === "string")
+        return active.activeForm;
+      if (active && typeof active.content === "string") return active.content;
+      return null;
+    }
+    default:
+      return null;
+  }
+}
+
+export function truncate(text: string, maxLen: number): string {
+  if (text.length <= maxLen) return text;
+  return text.slice(0, maxLen).trimEnd() + "\u2026";
+}
+
+/* ------------------------------------------------------------------ */
+/*  Exit code helper                                                   */
+/* ------------------------------------------------------------------ */
+
+function getExitCode(output: unknown): number | null {
+  if (!output || typeof output !== "object") return null;
+  const parsed = output as Record<string, unknown>;
+  if (typeof parsed.exit_code === "number") return parsed.exit_code;
+  return null;
+}
+
+/* ------------------------------------------------------------------ */
+/*  Animation text                                                     */
+/* ------------------------------------------------------------------ */
+
+export function getAnimationText(
+  part: ToolUIPart,
+  category: ToolCategory,
+): string {
+  const toolName = extractToolName(part);
+  const summary = getInputSummary(toolName, part.input);
+  const shortSummary = summary ? truncate(summary, 60) : null;
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available": {
+      switch (category) {
+        case "bash":
+          return shortSummary
+            ? `Running: ${shortSummary}`
+            : "Running command\u2026";
+        case "web":
+          if (toolName === "WebSearch") {
+            return shortSummary
+              ? `Searching "${shortSummary}"`
+              : "Searching the web\u2026";
+          }
+          return shortSummary
+            ? `Fetching ${shortSummary}`
+            : "Fetching web content\u2026";
+        case "browser":
+          if (toolName === "browser_screenshot")
+            return "Taking screenshot\u2026";
+          return shortSummary
+            ? `Browsing ${shortSummary}`
+            : "Interacting with browser\u2026";
+        case "file-read":
+          return shortSummary
+            ? `Reading ${shortSummary}`
+            : "Reading file\u2026";
+        case "file-write":
+          return shortSummary
+            ? `Writing ${shortSummary}`
+            : "Writing file\u2026";
+        case "file-delete":
+          return shortSummary
+            ? `Deleting ${shortSummary}`
+            : "Deleting file\u2026";
+        case "file-list":
+          return shortSummary
+            ? `Listing ${shortSummary}`
+            : "Listing files\u2026";
+        case "search":
+          return shortSummary
+            ? `Searching for "${shortSummary}"`
+            : "Searching\u2026";
+        case "edit":
+          return shortSummary
+            ? `Editing ${shortSummary}`
+            : "Editing file\u2026";
+        case "todo":
+          return shortSummary ? `${shortSummary}` : "Updating task list\u2026";
+        case "compaction":
+          return "Summarizing earlier messages\u2026";
+        default:
+          return `Running ${formatToolName(toolName)}\u2026`;
+      }
+    }
+    case "output-available": {
+      switch (category) {
+        case "bash": {
+          const exitCode = getExitCode(part.output);
+          if (exitCode !== null && exitCode !== 0) {
+            return `Command exited with code ${exitCode}`;
+          }
+          return shortSummary ? `Ran: ${shortSummary}` : "Command completed";
+        }
+        case "web":
+          if (toolName === "WebSearch") {
+            return shortSummary
+              ? `Searched "${shortSummary}"`
+              : "Web search completed";
+          }
+          return shortSummary
+            ? `Fetched ${shortSummary}`
+            : "Fetched web content";
+        case "browser":
+          if (toolName === "browser_screenshot") return "Screenshot captured";
+          return shortSummary
+            ? `Browsed ${shortSummary}`
+            : "Browser action completed";
+        case "file-read":
+          return shortSummary ? `Read ${shortSummary}` : "File read completed";
+        case "file-write":
+          return shortSummary ? `Wrote ${shortSummary}` : "File written";
+        case "file-delete":
+          return shortSummary ? `Deleted ${shortSummary}` : "File deleted";
+        case "file-list":
+          return "Listed files";
+        case "search":
+          return shortSummary
+            ? `Searched for "${shortSummary}"`
+            : "Search completed";
+        case "edit":
+          return shortSummary ? `Edited ${shortSummary}` : "Edit completed";
+        case "todo":
+          return "Updated task list";
+        case "compaction":
+          return "Earlier messages were summarized";
+        default:
+          return `${formatToolName(toolName)} completed`;
+      }
+    }
+    case "output-error": {
+      switch (category) {
+        case "bash":
+          return "Command failed";
+        case "web":
+          return toolName === "WebSearch" ? "Search failed" : "Fetch failed";
+        case "browser":
+          return "Browser action failed";
+        default:
+          return `${formatToolName(toolName)} failed`;
+      }
+    }
+    default:
+      return `Running ${formatToolName(toolName)}\u2026`;
+  }
+}

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

@@ -2,7 +2,7 @@
 
 import type { ToolUIPart } from "ai";
 import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
 import {
   ContentGrid,
@@ -86,7 +86,7 @@ export function RunAgentTool({ part }: Props) {
 
       {isStreaming && !output && (
         <ToolAccordion
-          icon={<OrbitLoader size={32} />}
+          icon={<ScaleLoader size={14} />}
           title="Running agent, this may take a few minutes. Play while you wait."
           expanded={true}
         >

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

@@ -10,7 +10,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 
 export interface RunAgentInput {
   username_agent_slug?: string;
@@ -171,7 +171,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <ScaleLoader size={14} />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }

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

@@ -8,7 +8,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 
 /** Block details returned on first run_block attempt (before input_data provided). */
 export interface BlockDetailsResponse {
@@ -157,7 +157,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <ScaleLoader size={14} />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }

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

@@ -6,7 +6,7 @@ import { ResponseType } from "@/app/api/__generated__/models/responseType";
 import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
 import { WarningDiamondIcon, PlugsConnectedIcon } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ScaleLoader } from "../../components/ScaleLoader/ScaleLoader";
 
 // ------------------------------------------------------------------ //
 //  Re-export generated types for use by RunMCPTool components
@@ -212,7 +212,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <ScaleLoader size={14} />;
   }
   return (
     <PlugsConnectedIcon

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

@@ -2,12 +2,12 @@ import {
   getGetV2ListSessionsQueryKey,
   useDeleteV2DeleteSession,
   useGetV2ListSessions,
+  type getV2ListSessionsResponse,
 } from "@/app/api/__generated__/endpoints/chat/chat";
 import { toast } from "@/components/molecules/Toast/use-toast";
+import { uploadFileDirect } from "@/lib/direct-upload";
 import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
-import { getWebSocketToken } from "@/lib/supabase/actions";
 import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
-import { environment } from "@/services/environment";
 import { useQueryClient } from "@tanstack/react-query";
 import type { FileUIPart } from "ai";
 import { useEffect, useRef, useState } from "react";
@@ -15,6 +15,9 @@ import { useCopilotUIStore } from "./store";
 import { useChatSession } from "./useChatSession";
 import { useCopilotStream } from "./useCopilotStream";
 
+const TITLE_POLL_INTERVAL_MS = 2_000;
+const TITLE_POLL_MAX_ATTEMPTS = 5;
+
 interface UploadedFile {
   file_id: string;
   name: string;
@@ -125,49 +128,25 @@ export function useCopilotPage() {
     files: File[],
     sid: string,
   ): Promise<UploadedFile[]> {
-    // Upload directly to the Python backend, bypassing the Next.js serverless
-    // proxy.  Vercel's 4.5 MB function payload limit would reject larger files
-    // when routed through /api/workspace/files/upload.
-    const { token, error: tokenError } = await getWebSocketToken();
-    if (tokenError || !token) {
-      toast({
-        title: "Authentication error",
-        description: "Please sign in again.",
-        variant: "destructive",
-      });
-      return [];
-    }
-
-    const backendBase = environment.getAGPTServerBaseUrl();
-
     const results = await Promise.allSettled(
       files.map(async (file) => {
-        const formData = new FormData();
-        formData.append("file", file);
-        const url = new URL("/api/workspace/files/upload", backendBase);
-        url.searchParams.set("session_id", sid);
-        const res = await fetch(url.toString(), {
-          method: "POST",
-          headers: { Authorization: `Bearer ${token}` },
-          body: formData,
-        });
-        if (!res.ok) {
-          const err = await res.text();
+        try {
+          const data = await uploadFileDirect(file, sid);
+          if (!data.file_id) throw new Error("No file_id returned");
+          return {
+            file_id: data.file_id,
+            name: data.name || file.name,
+            mime_type: data.mime_type || "application/octet-stream",
+          } as UploadedFile;
+        } catch (err) {
           console.error("File upload failed:", err);
           toast({
             title: "File upload failed",
             description: file.name,
             variant: "destructive",
           });
-          throw new Error(err);
+          throw err;
         }
-        const data = await res.json();
-        if (!data.file_id) throw new Error("No file_id returned");
-        return {
-          file_id: data.file_id,
-          name: data.name || file.name,
-          mime_type: data.mime_type || "application/octet-stream",
-        } as UploadedFile;
       }),
     );
     return results
@@ -258,6 +237,52 @@ export function useCopilotPage() {
   const sessions =
     sessionsResponse?.status === 200 ? sessionsResponse.data.sessions : [];
 
+  // Start title polling when stream ends cleanly — sidebar title animates in
+  const titlePollRef = useRef<ReturnType<typeof setInterval>>();
+  const prevStatusRef = useRef(status);
+
+  useEffect(() => {
+    const prev = prevStatusRef.current;
+    prevStatusRef.current = status;
+
+    const wasActive = prev === "streaming" || prev === "submitted";
+    const isNowReady = status === "ready";
+
+    if (!wasActive || !isNowReady || !sessionId || isReconnecting) return;
+
+    queryClient.invalidateQueries({
+      queryKey: getGetV2ListSessionsQueryKey({ limit: 50 }),
+    });
+    const sid = sessionId;
+    let attempts = 0;
+    clearInterval(titlePollRef.current);
+    titlePollRef.current = setInterval(() => {
+      const data = queryClient.getQueryData<getV2ListSessionsResponse>(
+        getGetV2ListSessionsQueryKey({ limit: 50 }),
+      );
+      const hasTitle =
+        data?.status === 200 &&
+        data.data.sessions.some((s) => s.id === sid && s.title);
+      if (hasTitle || attempts >= TITLE_POLL_MAX_ATTEMPTS) {
+        clearInterval(titlePollRef.current);
+        titlePollRef.current = undefined;
+        return;
+      }
+      attempts += 1;
+      queryClient.invalidateQueries({
+        queryKey: getGetV2ListSessionsQueryKey({ limit: 50 }),
+      });
+    }, TITLE_POLL_INTERVAL_MS);
+  }, [status, sessionId, isReconnecting, queryClient]);
+
+  // Clean up polling on session change or unmount
+  useEffect(() => {
+    return () => {
+      clearInterval(titlePollRef.current);
+      titlePollRef.current = undefined;
+    };
+  }, [sessionId]);
+
   // --- Mobile drawer handlers ---
   function handleOpenDrawer() {
     setDrawerOpen(true);

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

@@ -92,12 +92,18 @@ export function useCopilotStream({
   // Set when the user explicitly clicks stop — prevents onError from
   // triggering a reconnect cycle for the resulting AbortError.
   const isUserStoppingRef = useRef(false);
+  // Set when all reconnect attempts are exhausted — prevents hasActiveStream
+  // from keeping the UI blocked forever when the backend is slow to clear it.
+  // Must be state (not ref) so that setting it triggers a re-render and
+  // recomputes `isReconnecting`.
+  const [reconnectExhausted, setReconnectExhausted] = useState(false);
 
   function handleReconnect(sid: string) {
     if (isReconnectScheduledRef.current || !sid) return;
 
     const nextAttempt = reconnectAttemptsRef.current + 1;
     if (nextAttempt > RECONNECT_MAX_ATTEMPTS) {
+      setReconnectExhausted(true);
       toast({
         title: "Connection lost",
         description: "Unable to reconnect. Please refresh the page.",
@@ -146,7 +152,11 @@ export function useCopilotStream({
         return;
       }
 
-      // Check if backend executor is still running after clean close
+      // Check if backend executor is still running after clean close.
+      // Brief delay to let the backend clear active_stream — without this,
+      // the refetch often races and sees stale active_stream=true, triggering
+      // unnecessary reconnect cycles.
+      await new Promise((r) => setTimeout(r, 500));
       const result = await refetchSession();
       const d = result.data;
       const backendActive =
@@ -276,6 +286,7 @@ export function useCopilotStream({
     setIsReconnectScheduled(false);
     hasShownDisconnectToast.current = false;
     isUserStoppingRef.current = false;
+    setReconnectExhausted(false);
     hasResumedRef.current.clear();
     return () => {
       clearTimeout(reconnectTimerRef.current);
@@ -299,6 +310,7 @@ export function useCopilotStream({
       if (status === "ready") {
         reconnectAttemptsRef.current = 0;
         hasShownDisconnectToast.current = false;
+        setReconnectExhausted(false);
       }
     }
   }, [status, sessionId, queryClient, isReconnectScheduled]);
@@ -358,10 +370,12 @@ export function useCopilotStream({
   }, [hasActiveStream]);
 
   // True while reconnecting or backend has active stream but we haven't connected yet.
-  // Suppressed when the user explicitly stopped — the backend may take a moment
-  // to clear active_stream but the UI should be responsive immediately.
+  // Suppressed when the user explicitly stopped or when all reconnect attempts
+  // are exhausted — the backend may be slow to clear active_stream but the UI
+  // should remain responsive.
   const isReconnecting =
     !isUserStoppingRef.current &&
+    !reconnectExhausted &&
     (isReconnectScheduled ||
       (hasActiveStream && status !== "streaming" && status !== "submitted"));
 

autogpt_platform/frontend/src/app/(platform)/signup/actions.ts

@@ -1,10 +1,11 @@
 "use server";
 
+import { postV1GetOrCreateUser } from "@/app/api/__generated__/endpoints/auth/auth";
+import { getOnboardingStatus, resolveResponse } from "@/app/api/helpers";
 import { getServerSupabase } from "@/lib/supabase/server/getServerSupabase";
 import { signupFormSchema } from "@/types/auth";
 import * as Sentry from "@sentry/nextjs";
 import { isWaitlistError, logWaitlistError } from "../../api/auth/utils";
-import { getOnboardingStatus } from "../../api/helpers";
 
 export async function signup(
   email: string,
@@ -57,6 +58,17 @@ export async function signup(
       await supabase.auth.setSession(data.session);
     }
 
+    try {
+      await resolveResponse(postV1GetOrCreateUser());
+    } catch (createUserError) {
+      console.error("Error creating user during signup:", createUserError);
+      Sentry.captureException(createUserError);
+      return {
+        success: false,
+        error: "Failed to complete account setup. Please try again.",
+      };
+    }
+
     // Get onboarding status from backend (includes chat flag evaluated for this user)
     const { shouldShowOnboarding } = await getOnboardingStatus();
     const next = shouldShowOnboarding ? "/onboarding" : "/";

autogpt_platform/frontend/src/app/api/helpers.ts

@@ -53,6 +53,8 @@ export function getPaginationNextPageNumber(
   if (!hasValidPaginationInfo(lastPage)) return undefined;
 
   const { pagination } = lastPage.data;
+  if (!pagination) return undefined;
+
   const hasMore =
     pagination.current_page * pagination.page_size < pagination.total_items;
   return hasMore ? pagination.current_page + 1 : undefined;

autogpt_platform/frontend/src/app/api/openapi.json

@@ -1305,6 +1305,59 @@
         }
       }
     },
+    "/api/chat/sessions/{session_id}/title": {
+      "patch": {
+        "tags": ["v2", "chat", "chat"],
+        "summary": "Update session title",
+        "description": "Update the title of a chat session.\n\nAllows the user to rename their chat session.\n\nArgs:\n    session_id: The session ID to update.\n    request: Request body containing the new title.\n    user_id: The authenticated user's ID.\n\nReturns:\n    dict: Status of the update.\n\nRaises:\n    HTTPException: 404 if session not found or not owned by user.",
+        "operationId": "patchV2Update session title",
+        "security": [{ "HTTPBearerJWT": [] }],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": { "type": "string", "title": "Session Id" }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateSessionTitleRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "additionalProperties": true,
+                  "title": "Response Patchv2Update Session Title"
+                }
+              }
+            }
+          },
+          "401": {
+            "$ref": "#/components/responses/HTTP401NotAuthenticatedError"
+          },
+          "404": { "description": "Session not found or access denied" },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": { "$ref": "#/components/schemas/HTTPValidationError" }
+              }
+            }
+          }
+        }
+      }
+    },
     "/api/credits": {
       "get": {
         "tags": ["v1", "credits"],
@@ -13291,6 +13344,13 @@
         "required": ["permissions"],
         "title": "UpdatePermissionsRequest"
       },
+      "UpdateSessionTitleRequest": {
+        "properties": { "title": { "type": "string", "title": "Title" } },
+        "type": "object",
+        "required": ["title"],
+        "title": "UpdateSessionTitleRequest",
+        "description": "Request model for updating a session's title."
+      },
       "UpdateTimezoneRequest": {
         "properties": {
           "timezone": {

autogpt_platform/frontend/src/app/api/proxy/[...path]/route.ts

@@ -31,11 +31,11 @@ function isWorkspaceDownloadRequest(path: string[]): boolean {
 }
 
 /**
- * Handle workspace file download requests with proper binary response streaming.
+ * Handle workspace file download requests using signed URL redirect or full buffering.
  */
 async function handleWorkspaceDownload(
   req: NextRequest,
-  backendUrl: string,
+  path: string[],
 ): Promise<NextResponse> {
   const token = await getServerAuthToken();
 
@@ -44,40 +44,64 @@ async function handleWorkspaceDownload(
     headers["Authorization"] = `Bearer ${token}`;
   }
 
-  const response = await fetch(backendUrl, {
+  // Build the download-url endpoint path (replace last segment)
+  const urlPath = [...path];
+  urlPath[urlPath.length - 1] = "download-url";
+  const downloadUrlEndpoint = buildBackendUrl(urlPath, "");
+
+  // Ask backend for signed URL
+  const urlResponse = await fetch(downloadUrlEndpoint, {
     method: "GET",
     headers,
-    redirect: "follow", // Follow redirects to signed URLs
   });
 
-  if (!response.ok) {
+  if (!urlResponse.ok) {
     return NextResponse.json(
-      { error: `Failed to download file: ${response.statusText}` },
-      { status: response.status },
+      { error: `Failed to get download URL: ${urlResponse.statusText}` },
+      { status: urlResponse.status },
     );
   }
 
-  // Get the content type from the backend response
-  const contentType =
-    response.headers.get("Content-Type") || "application/octet-stream";
-  const contentDisposition = response.headers.get("Content-Disposition");
+  const { url, direct } = (await urlResponse.json()) as {
+    url: string;
+    direct: boolean;
+  };
+
+  // Direct URL (GCS signed) — redirect browser to fetch directly from GCS
+  if (direct) {
+    return NextResponse.redirect(url, 302);
+  }
+
+  // Non-direct (local storage) — proxy with full buffering to avoid truncation
+  const backendUrl = buildBackendUrl(path, new URL(req.url).search);
+  const fileResponse = await fetch(backendUrl, {
+    method: "GET",
+    headers,
+    redirect: "follow",
+  });
+
+  if (!fileResponse.ok) {
+    return NextResponse.json(
+      { error: `Failed to download file: ${fileResponse.statusText}` },
+      { status: fileResponse.status },
+    );
+  }
+
+  const buffer = await fileResponse.arrayBuffer();
+  const contentType =
+    fileResponse.headers.get("Content-Type") || "application/octet-stream";
+  const contentDisposition = fileResponse.headers.get("Content-Disposition");
 
-  // Stream the response body
   const responseHeaders: Record<string, string> = {
     "Content-Type": contentType,
+    "Content-Length": String(buffer.byteLength),
   };
 
   if (contentDisposition) {
     responseHeaders["Content-Disposition"] = contentDisposition;
   }
 
-  const contentLength = response.headers.get("Content-Length");
-  if (contentLength) {
-    responseHeaders["Content-Length"] = contentLength;
-  }
-
-  // Stream the response body directly instead of buffering in memory
-  return new NextResponse(response.body, {
+  return new NextResponse(buffer, {
     status: 200,
     headers: responseHeaders,
   });
@@ -250,7 +274,7 @@ async function handler(
   try {
     // Handle workspace file downloads separately (binary response)
     if (method === "GET" && isWorkspaceDownloadRequest(path)) {
-      return await handleWorkspaceDownload(req, backendUrl);
+      return await handleWorkspaceDownload(req, path);
     }
 
     if (method === "GET" || method === "DELETE") {

autogpt_platform/frontend/src/app/globals.css

@@ -183,7 +183,7 @@ body[data-google-picker-open="true"] [data-dialog-content] {
 
 /* Streamdown external link dialog: "Open link" button */
 [data-streamdown="link-safety-modal"] button:last-of-type {
-  color: black;
+  color: white;
 }
 
 /* CoPilot chat table styling — remove left/right borders, increase padding */

autogpt_platform/frontend/src/components/ai-elements/message.tsx

@@ -7,6 +7,9 @@ import {
   TooltipContent,
   TooltipTrigger,
 } from "@/components/atoms/Tooltip/BaseTooltip";
+import { Button as AtomButton } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { Dialog } from "@/components/molecules/Dialog/Dialog";
 import { cn } from "@/lib/utils";
 import { cjk } from "@streamdown/cjk";
 import { code } from "@/lib/streamdown-code-plugin";
@@ -16,6 +19,7 @@ import type { UIMessage } from "ai";
 import { ChevronLeftIcon, ChevronRightIcon } from "lucide-react";
 import type { ComponentProps, HTMLAttributes, ReactElement } from "react";
 import { createContext, memo, useContext, useEffect, useState } from "react";
+import type { LinkSafetyModalProps } from "streamdown";
 import { Streamdown } from "streamdown";
 
 export type MessageProps = HTMLAttributes<HTMLDivElement> & {
@@ -307,6 +311,46 @@ function isSameOriginLink(url: string): boolean {
   }
 }
 
+function ExternalLinkModal({
+  url,
+  isOpen,
+  onClose,
+  onConfirm,
+}: LinkSafetyModalProps) {
+  return (
+    <Dialog
+      title="Open external link"
+      styling={{ maxWidth: "30rem", minWidth: "auto" }}
+      controlled={{
+        isOpen,
+        set: async (open) => {
+          if (!open) onClose();
+        },
+      }}
+    >
+      <Dialog.Content>
+        <Text variant="body">
+          You&apos;re about to visit an external website:
+        </Text>
+        <Text
+          variant="small"
+          className="mt-2 break-all rounded-md bg-neutral-100 p-3 font-mono"
+        >
+          {url}
+        </Text>
+        <Dialog.Footer>
+          <AtomButton variant="secondary" onClick={onClose}>
+            Cancel
+          </AtomButton>
+          <AtomButton variant="primary" onClick={onConfirm}>
+            Open link
+          </AtomButton>
+        </Dialog.Footer>
+      </Dialog.Content>
+    </Dialog>
+  );
+}
+
 export const MessageResponse = memo(
   ({ className, ...props }: MessageResponseProps) => (
     <Streamdown
@@ -318,6 +362,7 @@ export const MessageResponse = memo(
       linkSafety={{
         enabled: true,
         onLinkCheck: isSameOriginLink,
+        renderModal: (modalProps) => <ExternalLinkModal {...modalProps} />,
       }}
       {...props}
     />

autogpt_platform/frontend/src/components/renderers/InputRenderer/base/standard/widgets/FileInput/useWorkspaceUpload.ts

@@ -1,16 +1,11 @@
-import {
-  usePostWorkspaceUploadFileToWorkspace,
-  useDeleteWorkspaceDeleteAWorkspaceFile,
-} from "@/app/api/__generated__/endpoints/workspace/workspace";
+import { useDeleteWorkspaceDeleteAWorkspaceFile } from "@/app/api/__generated__/endpoints/workspace/workspace";
 import { useToast } from "@/components/molecules/Toast/use-toast";
+import { uploadFileDirect } from "@/lib/direct-upload";
 import { parseWorkspaceFileID, buildWorkspaceURI } from "@/lib/workspace-uri";
 
 export function useWorkspaceUpload() {
   const { toast } = useToast();
 
-  const { mutateAsync: uploadMutation } =
-    usePostWorkspaceUploadFileToWorkspace();
-
   const { mutate: deleteMutation } = useDeleteWorkspaceDeleteAWorkspaceFile({
     mutation: {
       onError: () => {
@@ -24,11 +19,7 @@ export function useWorkspaceUpload() {
   });
 
   async function handleUploadFile(file: File) {
-    const response = await uploadMutation({ data: { file } });
-    if (response.status !== 200) {
-      throw new Error("Upload failed");
-    }
-    const d = response.data;
+    const d = await uploadFileDirect(file);
     return {
       file_name: d.name,
       size: d.size_bytes,

autogpt_platform/frontend/src/lib/direct-upload.ts

@@ -0,0 +1,47 @@
+import { getWebSocketToken } from "@/lib/supabase/actions";
+import { environment } from "@/services/environment";
+
+interface UploadFileResponse {
+  file_id: string;
+  name: string;
+  path: string;
+  mime_type: string;
+  size_bytes: number;
+}
+
+/**
+ * Upload a file directly to the Python backend, bypassing the Next.js proxy.
+ * The Next.js serverless proxy has a ~4.5MB body size limit (Vercel) which
+ * rejects larger files with HTTP 413.
+ */
+export async function uploadFileDirect(
+  file: File,
+  sessionID?: string,
+): Promise<UploadFileResponse> {
+  const { token, error: tokenError } = await getWebSocketToken();
+  if (tokenError || !token) {
+    throw new Error("Authentication error — please sign in again.");
+  }
+
+  const backendBase = environment.getAGPTServerBaseUrl();
+  const url = new URL("/api/workspace/files/upload", backendBase);
+  if (sessionID) {
+    url.searchParams.set("session_id", sessionID);
+  }
+
+  const formData = new FormData();
+  formData.append("file", file);
+
+  const res = await fetch(url.toString(), {
+    method: "POST",
+    headers: { Authorization: `Bearer ${token}` },
+    body: formData,
+  });
+
+  if (!res.ok) {
+    const detail = await res.text().catch(() => res.statusText);
+    throw new Error(`Upload failed (${res.status}): ${detail}`);
+  }
+
+  return res.json();
+}

docs/integrations/block-integrations/llm.md

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

docs/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-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | 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-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | 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-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | 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 |