chore: steam refresh issue fix

## Changes 🏗️

<img width="800" height="621" alt="Screenshot 2026-02-11 at 19 32 39"
src="https://github.com/user-attachments/assets/e97be1a7-972e-4ae0-8dfa-6ade63cf287b"
/>

When the BE API has an error, prevent it from leaking into the stream
and instead handle it gracefully via toast.

## Checklist 📋

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

<!-- greptile_comment -->

<h2>Greptile Overview</h2>

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

This PR fixes an issue where backend API stream errors were leaking into
the chat prompt instead of being handled gracefully. The fix involves
both backend and frontend changes to ensure error events conform to the
AI SDK's strict schema.

**Key Changes:**
- **Backend (`response_model.py`)**: Added custom `to_sse()` method for
`StreamError` that only emits `type` and `errorText` fields, stripping
extra fields like `code` and `details` that cause AI SDK validation
failures
- **Backend (`prompt.py`)**: Added validation step after context
compression to remove orphaned tool responses without matching tool
calls, preventing "unexpected tool_use_id" API errors
- **Frontend (`route.ts`)**: Implemented SSE stream normalization with
`normalizeSSEStream()` and `normalizeSSEEvent()` functions to strip
non-conforming fields from error events before they reach the AI SDK
- **Frontend (`ChatMessagesContainer.tsx`)**: Added toast notifications
for errors and improved error display UI with deduplication logic

The changes ensure a clean separation between internal error metadata
(useful for logging/debugging) and the strict schema required by the AI
SDK on the frontend.
</details>


<details><summary><h3>Confidence Score: 4/5</h3></summary>

- This PR is safe to merge with low risk
- The changes are well-structured and address a specific bug with proper
error handling. The dual-layer approach (backend filtering in `to_sse()`
+ frontend normalization) provides defense-in-depth. However, the lack
of automated tests for the new error normalization logic and the
potential for edge cases in SSE parsing prevent a perfect score.
- Pay close attention to
`autogpt_platform/frontend/src/app/api/chat/sessions/[sessionId]/stream/route.ts`
- the SSE normalization logic should be tested with various error
scenarios
</details>


<details><summary><h3>Sequence Diagram</h3></summary>

```mermaid
sequenceDiagram
    participant User
    participant Frontend as ChatMessagesContainer
    participant Proxy as /api/chat/.../stream
    participant Backend as Backend API
    participant AISDK as AI SDK

    User->>Frontend: Send message
    Frontend->>Proxy: POST with message
    Proxy->>Backend: Forward request with auth
    Backend->>Backend: Process message
    
    alt Success Path
        Backend->>Proxy: SSE stream (text-delta, etc.)
        Proxy->>Proxy: normalizeSSEStream (pass through)
        Proxy->>AISDK: Forward SSE events
        AISDK->>Frontend: Update messages
        Frontend->>User: Display response
    else Error Path
        Backend->>Backend: StreamError.to_sse()
        Note over Backend: Only emit {type, errorText}
        Backend->>Proxy: SSE error event
        Proxy->>Proxy: normalizeSSEEvent()
        Note over Proxy: Strip extra fields (code, details)
        Proxy->>AISDK: {type: "error", errorText: "..."}
        AISDK->>Frontend: error state updated
        Frontend->>Frontend: Toast notification (deduplicated)
        Frontend->>User: Show error UI + toast
    end
```
</details>


<!-- greptile_other_comments_section -->

<!-- /greptile_comment -->

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Otto-AGPT <otto@agpt.co>

.github/workflows/claude-ci-failure-auto-fix.yml

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ github.event.workflow_run.head_branch }}
           fetch-depth: 0

.github/workflows/claude-dependabot.yml

@@ -30,7 +30,7 @@ jobs:
       actions: read # Required for CI access
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 1
 

.github/workflows/claude.yml

@@ -40,7 +40,7 @@ jobs:
       actions: read # Required for CI access
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 1
 

.github/workflows/codeql.yml

@@ -58,7 +58,7 @@ jobs:
         # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v6
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/copilot-setup-steps.yml

@@ -27,7 +27,7 @@ jobs:
     # If you do not check out your code, Copilot will do this for you.
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
           submodules: true

.github/workflows/docs-block-sync.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 1
 

.github/workflows/docs-claude-review.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 

.github/workflows/docs-enhance.yml

@@ -28,7 +28,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 1
 

.github/workflows/platform-autogpt-deploy-dev.yaml

@@ -25,7 +25,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ github.event.inputs.git_ref || github.ref_name }}
 
@@ -52,7 +52,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger deploy workflow
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v4
         with:
           token: ${{ secrets.DEPLOY_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

.github/workflows/platform-autogpt-deploy-prod.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ github.ref_name || 'master' }}
 
@@ -45,7 +45,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger deploy workflow
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v4
         with:
           token: ${{ secrets.DEPLOY_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

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

@@ -68,7 +68,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
           submodules: true

.github/workflows/platform-dev-deploy-event-dispatcher.yml

@@ -82,7 +82,7 @@ jobs:
           
       - name: Dispatch Deploy Event
         if: steps.check_status.outputs.should_deploy == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v4
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure
@@ -110,7 +110,7 @@ jobs:
 
       - name: Dispatch Undeploy Event (from comment)
         if: steps.check_status.outputs.should_undeploy == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v4
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure
@@ -168,7 +168,7 @@ jobs:
           github.event_name == 'pull_request' &&
           github.event.action == 'closed' &&
           steps.check_pr_close.outputs.should_undeploy == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v4
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

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

@@ -31,7 +31,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Check for component changes
         uses: dorny/paths-filter@v3
@@ -71,7 +71,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -107,7 +107,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
@@ -148,7 +148,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -277,7 +277,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 

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

@@ -29,7 +29,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -63,7 +63,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 

.github/workflows/repo-workflow-checker.yml

@@ -11,7 +11,7 @@ jobs:
     steps:
       # - name: Wait some time for all actions to start
       #   run: sleep 30
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         # with:
           # fetch-depth: 0
       - name: Set up Python

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

@@ -10,6 +10,8 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
+from backend.util.json import dumps as json_dumps
+
 
 class ResponseType(str, Enum):
     """Types of streaming responses following AI SDK protocol."""
@@ -193,6 +195,18 @@ class StreamError(StreamBaseResponse):
         default=None, description="Additional error details"
     )
 
+    def to_sse(self) -> str:
+        """Convert to SSE format, only emitting fields required by AI SDK protocol.
+
+        The AI SDK uses z.strictObject({type, errorText}) which rejects
+        any extra fields like `code` or `details`.
+        """
+        data = {
+            "type": self.type.value,
+            "errorText": self.errorText,
+        }
+        return f"data: {json_dumps(data)}\n\n"
+
 
 class StreamHeartbeat(StreamBaseResponse):
     """Heartbeat to keep SSE connection alive during long-running operations.

autogpt_platform/backend/backend/data/graph.py

@@ -743,6 +743,11 @@ class GraphModel(Graph, GraphMeta):
                 # For invalid blocks, we still raise immediately as this is a structural issue
                 raise ValueError(f"Invalid block {node.block_id} for node #{node.id}")
 
+            if block.disabled:
+                raise ValueError(
+                    f"Block {node.block_id} is disabled and cannot be used in graphs"
+                )
+
             node_input_mask = (
                 nodes_input_masks.get(node.id, {}) if nodes_input_masks else {}
             )

autogpt_platform/backend/backend/executor/manager.py

@@ -213,6 +213,9 @@ async def execute_node(
         block_name=node_block.name,
     )
 
+    if node_block.disabled:
+        raise ValueError(f"Block {node_block.id} is disabled and cannot be executed")
+
     # Sanity check: validate the execution input.
     input_data, error = validate_exec(node, data.inputs, resolve_input=False)
     if input_data is None:

autogpt_platform/backend/backend/util/prompt.py

@@ -364,6 +364,44 @@ def _remove_orphan_tool_responses(
     return result
 
 
+def validate_and_remove_orphan_tool_responses(
+    messages: list[dict],
+    log_warning: bool = True,
+) -> list[dict]:
+    """
+    Validate tool_call/tool_response pairs and remove orphaned responses.
+
+    Scans messages in order, tracking all tool_call IDs. Any tool response
+    referencing an ID not seen in a preceding message is considered orphaned
+    and removed. This prevents API errors like Anthropic's "unexpected tool_use_id".
+
+    Args:
+        messages: List of messages to validate (OpenAI or Anthropic format)
+        log_warning: Whether to log a warning when orphans are found
+
+    Returns:
+        A new list with orphaned tool responses removed
+    """
+    available_ids: set[str] = set()
+    orphan_ids: set[str] = set()
+
+    for msg in messages:
+        available_ids |= _extract_tool_call_ids_from_message(msg)
+        for resp_id in _extract_tool_response_ids_from_message(msg):
+            if resp_id not in available_ids:
+                orphan_ids.add(resp_id)
+
+    if not orphan_ids:
+        return messages
+
+    if log_warning:
+        logger.warning(
+            f"Removing {len(orphan_ids)} orphan tool response(s): {orphan_ids}"
+        )
+
+    return _remove_orphan_tool_responses(messages, orphan_ids)
+
+
 def _ensure_tool_pairs_intact(
     recent_messages: list[dict],
     all_messages: list[dict],
@@ -723,6 +761,13 @@ async def compress_context(
 
     # Filter out any None values that may have been introduced
     final_msgs: list[dict] = [m for m in msgs if m is not None]
+
+    # ---- STEP 6: Final tool-pair validation ---------------------------------
+    # After all compression steps, verify that every tool response has a
+    # matching tool_call in a preceding assistant message. Remove orphans
+    # to prevent API errors (e.g., Anthropic's "unexpected tool_use_id").
+    final_msgs = validate_and_remove_orphan_tool_responses(final_msgs)
+
     final_count = sum(_msg_tokens(m, enc) for m in final_msgs)
     error = None
     if final_count + reserve > target_tokens:

autogpt_platform/backend/poetry.lock

@@ -46,14 +46,14 @@ pycares = ">=4.9.0,<5"
 
 [[package]]
 name = "aiofiles"
-version = "24.1.0"
+version = "25.1.0"
 description = "File support for asyncio."
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "aiofiles-24.1.0-py3-none-any.whl", hash = "sha256:b4ec55f4195e3eb5d7abd1bf7e061763e864dd4954231fb8539a0ef8bb8260e5"},
-    {file = "aiofiles-24.1.0.tar.gz", hash = "sha256:22a075c9e5a3810f0c2e48f3008c94d68c65d763b9b03857924c99e57355166c"},
+    {file = "aiofiles-25.1.0-py3-none-any.whl", hash = "sha256:abe311e527c862958650f9438e859c1fa7568a141b22abcd015e120e86a85695"},
+    {file = "aiofiles-25.1.0.tar.gz", hash = "sha256:a8d728f0a29de45dc521f18f07297428d56992a742f0cd2701ba86e44d23d5b2"},
 ]
 
 [[package]]
@@ -8440,4 +8440,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "fc135114e01de39c8adf70f6132045e7d44a19473c1279aee0978de65aad1655"
+content-hash = "c06e96ad49388ba7a46786e9ea55ea2c1a57408e15613237b4bee40a592a12af"

autogpt_platform/backend/pyproject.toml

@@ -76,7 +76,7 @@ yt-dlp = "2025.12.08"
 zerobouncesdk = "^1.1.2"
 # NOTE: please insert new dependencies in their alphabetical location
 pytest-snapshot = "^0.9.0"
-aiofiles = "^24.1.0"
+aiofiles = "^25.1.0"
 tiktoken = "^0.12.0"
 aioclamd = "^1.0.0"
 setuptools = "^80.9.0"

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

@@ -10,8 +10,9 @@ import {
   MessageResponse,
 } from "@/components/ai-elements/message";
 import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
+import { toast } from "@/components/molecules/Toast/use-toast";
 import { ToolUIPart, UIDataTypes, UIMessage, UITools } from "ai";
-import { useEffect, useState } from "react";
+import { useEffect, useRef, useState } from "react";
 import { CreateAgentTool } from "../../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../../tools/EditAgent/EditAgent";
 import { FindAgentsTool } from "../../tools/FindAgents/FindAgents";
@@ -121,6 +122,7 @@ export const ChatMessagesContainer = ({
   isLoading,
 }: ChatMessagesContainerProps) => {
   const [thinkingPhrase, setThinkingPhrase] = useState(getRandomPhrase);
+  const lastToastTimeRef = useRef(0);
 
   useEffect(() => {
     if (status === "submitted") {
@@ -128,6 +130,20 @@ export const ChatMessagesContainer = ({
     }
   }, [status]);
 
+  // Show a toast when a new error occurs, debounced to avoid spam
+  useEffect(() => {
+    if (!error) return;
+    const now = Date.now();
+    if (now - lastToastTimeRef.current < 3_000) return;
+    lastToastTimeRef.current = now;
+    toast({
+      variant: "destructive",
+      title: "Something went wrong",
+      description:
+        "The assistant encountered an error. Please try sending your message again.",
+    });
+  }, [error]);
+
   const lastMessage = messages[messages.length - 1];
   const lastAssistantHasVisibleContent =
     lastMessage?.role === "assistant" &&
@@ -263,8 +279,12 @@ export const ChatMessagesContainer = ({
           </Message>
         )}
         {error && (
-          <div className="rounded-lg bg-red-50 p-3 text-red-600">
-            Error: {error.message}
+          <div className="rounded-lg bg-red-50 p-4 text-sm text-red-700">
+            <p className="font-medium">Something went wrong</p>
+            <p className="mt-1 text-red-600">
+              The assistant encountered an error. Please try sending your
+              message again.
+            </p>
           </div>
         )}
       </ConversationContent>

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

@@ -30,7 +30,7 @@ export function ContentCard({
   return (
     <div
       className={cn(
-        "rounded-lg bg-gradient-to-r from-purple-500/30 to-blue-500/30 p-[1px]",
+        "min-w-0 rounded-lg bg-gradient-to-r from-purple-500/30 to-blue-500/30 p-[1px]",
         className,
       )}
     >

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

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

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

@@ -0,0 +1,131 @@
+import { getGetV2GetSessionQueryKey } from "@/app/api/__generated__/endpoints/chat/chat";
+import { useQueryClient } from "@tanstack/react-query";
+import type { UIDataTypes, UIMessage, UITools } from "ai";
+import { useCallback, useEffect, useRef } from "react";
+import { convertChatSessionMessagesToUiMessages } from "../helpers/convertChatSessionToUiMessages";
+
+const OPERATING_TYPES = new Set([
+  "operation_started",
+  "operation_pending",
+  "operation_in_progress",
+]);
+
+const POLL_INTERVAL_MS = 5_000;
+
+/**
+ * Detects whether any message contains a tool part whose output indicates
+ * a long-running operation is still in progress.
+ */
+function hasOperatingTool(
+  messages: UIMessage<unknown, UIDataTypes, UITools>[],
+): boolean {
+  for (const msg of messages) {
+    for (const part of msg.parts) {
+      if (!part.type.startsWith("tool-")) continue;
+      const toolPart = part as { output?: unknown };
+      if (!toolPart.output) continue;
+      const output =
+        typeof toolPart.output === "string"
+          ? safeParse(toolPart.output)
+          : toolPart.output;
+      if (
+        output &&
+        typeof output === "object" &&
+        "type" in output &&
+        OPERATING_TYPES.has((output as { type: string }).type)
+      ) {
+        return true;
+      }
+    }
+  }
+  return false;
+}
+
+function safeParse(value: string): unknown {
+  try {
+    return JSON.parse(value);
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * Polls the session endpoint while any tool is in an "operating" state
+ * (operation_started / operation_pending / operation_in_progress).
+ *
+ * When the session data shows the tool output has changed (e.g. to
+ * agent_saved), it calls `setMessages` with the updated messages.
+ */
+export function useLongRunningToolPolling(
+  sessionId: string | null,
+  messages: UIMessage<unknown, UIDataTypes, UITools>[],
+  setMessages: (
+    updater: (
+      prev: UIMessage<unknown, UIDataTypes, UITools>[],
+    ) => UIMessage<unknown, UIDataTypes, UITools>[],
+  ) => void,
+) {
+  const queryClient = useQueryClient();
+  const isPollingRef = useRef(false);
+  const intervalRef = useRef<ReturnType<typeof setInterval> | null>(null);
+
+  const stopPolling = useCallback(() => {
+    if (intervalRef.current) {
+      clearInterval(intervalRef.current);
+      intervalRef.current = null;
+    }
+    isPollingRef.current = false;
+  }, []);
+
+  const poll = useCallback(async () => {
+    if (!sessionId) return;
+
+    // Invalidate the query cache so the next fetch gets fresh data
+    await queryClient.invalidateQueries({
+      queryKey: getGetV2GetSessionQueryKey(sessionId),
+    });
+
+    // Fetch fresh session data
+    const data = queryClient.getQueryData<{
+      status: number;
+      data: { messages?: unknown[] };
+    }>(getGetV2GetSessionQueryKey(sessionId));
+
+    if (data?.status !== 200 || !data.data.messages) return;
+
+    const freshMessages = convertChatSessionMessagesToUiMessages(
+      sessionId,
+      data.data.messages,
+    );
+
+    if (!freshMessages || freshMessages.length === 0) return;
+
+    // Only update if the fresh data no longer has operating tools
+    // (meaning the long-running tool completed)
+    if (!hasOperatingTool(freshMessages)) {
+      setMessages(() => freshMessages);
+      stopPolling();
+    }
+  }, [sessionId, queryClient, setMessages, stopPolling]);
+
+  useEffect(() => {
+    const shouldPoll = hasOperatingTool(messages);
+
+    if (shouldPoll && !isPollingRef.current && sessionId) {
+      isPollingRef.current = true;
+      intervalRef.current = setInterval(() => {
+        poll();
+      }, POLL_INTERVAL_MS);
+    } else if (!shouldPoll && isPollingRef.current) {
+      stopPolling();
+    }
+
+    return () => {
+      // Cleanup on unmount or dependency change
+      if (intervalRef.current) {
+        clearInterval(intervalRef.current);
+        intervalRef.current = null;
+      }
+    };
+  }, [messages, sessionId, poll, stopPolling]);
+}

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

@@ -4,7 +4,6 @@ import { WarningDiamondIcon } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
 import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
 import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
 import { ProgressBar } from "../../components/ProgressBar/ProgressBar";
 import {
   ContentCardDescription,
@@ -77,7 +76,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
     isOperationInProgressOutput(output)
   ) {
     return {
-      icon: <OrbitLoader size={32} />,
+      icon,
       title: "Creating agent, this may take a few minutes. Sit back and relax.",
     };
   }

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

@@ -203,7 +203,7 @@ export function getAccordionMeta(output: RunAgentToolOutput): {
         ? output.status.trim()
         : "started";
     return {
-      icon: <OrbitLoader size={28} className="text-neutral-700" />,
+      icon,
       title: output.graph_name,
       description: `Status: ${statusText}`,
     };

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

@@ -149,7 +149,7 @@ export function getAccordionMeta(output: RunBlockToolOutput): {
   if (isRunBlockBlockOutput(output)) {
     const keys = Object.keys(output.outputs ?? {});
     return {
-      icon: <OrbitLoader size={24} className="text-neutral-700" />,
+      icon,
       title: output.block_name,
       description:
         keys.length > 0

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

@@ -5,6 +5,7 @@ import { useChat } from "@ai-sdk/react";
 import { DefaultChatTransport } from "ai";
 import { useEffect, useMemo, useState } from "react";
 import { useChatSession } from "./useChatSession";
+import { useLongRunningToolPolling } from "./hooks/useLongRunningToolPolling";
 
 export function useCopilotPage() {
   const { isUserLoading, isLoggedIn } = useSupabase();
@@ -60,6 +61,11 @@ export function useCopilotPage() {
     });
   }, [hydratedMessages, setMessages]);
 
+  // Poll session endpoint when a long-running tool (create_agent, edit_agent)
+  // is in progress. When the backend completes, the session data will contain
+  // the final tool output — this hook detects the change and updates messages.
+  useLongRunningToolPolling(sessionId, messages, setMessages);
+
   // Clear messages when session is null
   useEffect(() => {
     if (!sessionId) setMessages([]);

autogpt_platform/frontend/src/app/api/chat/sessions/[sessionId]/stream/route.ts

@@ -1,11 +1,8 @@
 import { environment } from "@/services/environment";
 import { getServerAuthToken } from "@/lib/autogpt-server-api/helpers";
 import { NextRequest } from "next/server";
+import { normalizeSSEStream, SSE_HEADERS } from "../../../sse-helpers";
 
-/**
- * SSE Proxy for chat streaming.
- * Supports POST with context (page content + URL) in the request body.
- */
 export async function POST(
   request: NextRequest,
   { params }: { params: Promise<{ sessionId: string }> },
@@ -23,17 +20,14 @@ export async function POST(
       );
     }
 
-    // Get auth token from server-side session
     const token = await getServerAuthToken();
 
-    // Build backend URL
     const backendUrl = environment.getAGPTServerBaseUrl();
     const streamUrl = new URL(
       `/api/chat/sessions/${sessionId}/stream`,
       backendUrl,
     );
 
-    // Forward request to backend with auth header
     const headers: Record<string, string> = {
       "Content-Type": "application/json",
       Accept: "text/event-stream",
@@ -63,14 +57,15 @@ export async function POST(
       });
     }
 
-    // Return the SSE stream directly
-    return new Response(response.body, {
-      headers: {
-        "Content-Type": "text/event-stream",
-        "Cache-Control": "no-cache, no-transform",
-        Connection: "keep-alive",
-        "X-Accel-Buffering": "no",
-      },
+    if (!response.body) {
+      return new Response(
+        JSON.stringify({ error: "Empty response from chat service" }),
+        { status: 502, headers: { "Content-Type": "application/json" } },
+      );
+    }
+
+    return new Response(normalizeSSEStream(response.body), {
+      headers: SSE_HEADERS,
     });
   } catch (error) {
     console.error("SSE proxy error:", error);
@@ -87,13 +82,6 @@ export async function POST(
   }
 }
 
-/**
- * Resume an active stream for a session.
- *
- * Called by the AI SDK's `useChat(resume: true)` on page load.
- * Proxies to the backend which checks for an active stream and either
- * replays it (200 + SSE) or returns 204 No Content.
- */
 export async function GET(
   _request: NextRequest,
   { params }: { params: Promise<{ sessionId: string }> },
@@ -124,7 +112,6 @@ export async function GET(
       headers,
     });
 
-    // 204 = no active stream to resume
     if (response.status === 204) {
       return new Response(null, { status: 204 });
     }
@@ -137,12 +124,13 @@ export async function GET(
       });
     }
 
-    return new Response(response.body, {
+    if (!response.body) {
+      return new Response(null, { status: 204 });
+    }
+
+    return new Response(normalizeSSEStream(response.body), {
       headers: {
-        "Content-Type": "text/event-stream",
-        "Cache-Control": "no-cache, no-transform",
-        Connection: "keep-alive",
-        "X-Accel-Buffering": "no",
+        ...SSE_HEADERS,
         "x-vercel-ai-ui-message-stream": "v1",
       },
     });

autogpt_platform/frontend/src/app/api/chat/sse-helpers.ts

@@ -0,0 +1,72 @@
+export const SSE_HEADERS = {
+  "Content-Type": "text/event-stream",
+  "Cache-Control": "no-cache, no-transform",
+  Connection: "keep-alive",
+  "X-Accel-Buffering": "no",
+} as const;
+
+export function normalizeSSEStream(
+  input: ReadableStream<Uint8Array>,
+): ReadableStream<Uint8Array> {
+  const decoder = new TextDecoder();
+  const encoder = new TextEncoder();
+  let buffer = "";
+
+  return input.pipeThrough(
+    new TransformStream<Uint8Array, Uint8Array>({
+      transform(chunk, controller) {
+        buffer += decoder.decode(chunk, { stream: true });
+
+        const parts = buffer.split("\n\n");
+        buffer = parts.pop() ?? "";
+
+        for (const part of parts) {
+          const normalized = normalizeSSEEvent(part);
+          controller.enqueue(encoder.encode(normalized + "\n\n"));
+        }
+      },
+      flush(controller) {
+        if (buffer.trim()) {
+          const normalized = normalizeSSEEvent(buffer);
+          controller.enqueue(encoder.encode(normalized + "\n\n"));
+        }
+      },
+    }),
+  );
+}
+
+function normalizeSSEEvent(event: string): string {
+  const lines = event.split("\n");
+  const dataLines: string[] = [];
+  const otherLines: string[] = [];
+
+  for (const line of lines) {
+    if (line.startsWith("data: ")) {
+      dataLines.push(line.slice(6));
+    } else {
+      otherLines.push(line);
+    }
+  }
+
+  if (dataLines.length === 0) return event;
+
+  const dataStr = dataLines.join("\n");
+  try {
+    const parsed = JSON.parse(dataStr) as Record<string, unknown>;
+    if (parsed.type === "error") {
+      const normalized = {
+        type: "error",
+        errorText:
+          typeof parsed.errorText === "string"
+            ? parsed.errorText
+            : "An unexpected error occurred",
+      };
+      const newData = `data: ${JSON.stringify(normalized)}`;
+      return [...otherLines.filter((l) => l.length > 0), newData].join("\n");
+    }
+  } catch {
+    // Not valid JSON — pass through as-is
+  }
+
+  return event;
+}

autogpt_platform/frontend/src/app/api/chat/tasks/[taskId]/stream/route.ts

@@ -1,20 +1,8 @@
 import { environment } from "@/services/environment";
 import { getServerAuthToken } from "@/lib/autogpt-server-api/helpers";
 import { NextRequest } from "next/server";
+import { normalizeSSEStream, SSE_HEADERS } from "../../../sse-helpers";
 
-/**
- * SSE Proxy for task stream reconnection.
- *
- * This endpoint allows clients to reconnect to an ongoing or recently completed
- * background task's stream. It replays missed messages from Redis Streams and
- * subscribes to live updates if the task is still running.
- *
- * Client contract:
- * 1. When receiving an operation_started event, store the task_id
- * 2. To reconnect: GET /api/chat/tasks/{taskId}/stream?last_message_id={idx}
- * 3. Messages are replayed from the last_message_id position
- * 4. Stream ends when "finish" event is received
- */
 export async function GET(
   request: NextRequest,
   { params }: { params: Promise<{ taskId: string }> },
@@ -24,15 +12,12 @@ export async function GET(
   const lastMessageId = searchParams.get("last_message_id") || "0-0";
 
   try {
-    // Get auth token from server-side session
     const token = await getServerAuthToken();
 
-    // Build backend URL
     const backendUrl = environment.getAGPTServerBaseUrl();
     const streamUrl = new URL(`/api/chat/tasks/${taskId}/stream`, backendUrl);
     streamUrl.searchParams.set("last_message_id", lastMessageId);
 
-    // Forward request to backend with auth header
     const headers: Record<string, string> = {
       Accept: "text/event-stream",
       "Cache-Control": "no-cache",
@@ -56,14 +41,12 @@ export async function GET(
       });
     }
 
-    // Return the SSE stream directly
-    return new Response(response.body, {
-      headers: {
-        "Content-Type": "text/event-stream",
-        "Cache-Control": "no-cache, no-transform",
-        Connection: "keep-alive",
-        "X-Accel-Buffering": "no",
-      },
+    if (!response.body) {
+      return new Response(null, { status: 204 });
+    }
+
+    return new Response(normalizeSSEStream(response.body), {
+      headers: SSE_HEADERS,
     });
   } catch (error) {
     console.error("Task stream proxy error:", error);