fix(copilot): Use correct OpenRouter reasoning API format

Addresses review comments from CodeRabbit and Sentry:

- Change reasoning format from {"enabled": True} (invalid) to
  {"max_tokens": config.thinking_budget_tokens} per OpenRouter docs
- Add missing thinking_budget_tokens config field (default: 10000)
- Extract duplicate code into _apply_thinking_config() helper function
- Update description from 'adaptive' to 'extended' thinking for clarity

References:
- OpenRouter reasoning docs: https://openrouter.ai/docs/reasoning-tokens

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

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         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@v6
+        uses: actions/checkout@v4
         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@v6
+        uses: actions/checkout@v4
         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@v6
+      uses: actions/checkout@v4
 
     # 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@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           submodules: true

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

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

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

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

.github/workflows/docs-enhance.yml

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

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

@@ -25,7 +25,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         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@v4
+        uses: peter-evans/repository-dispatch@v3
         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@v6
+        uses: actions/checkout@v4
         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@v4
+        uses: peter-evans/repository-dispatch@v3
         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@v6
+        uses: actions/checkout@v4
         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@v4
+        uses: peter-evans/repository-dispatch@v3
         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@v4
+        uses: peter-evans/repository-dispatch@v3
         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@v4
+        uses: peter-evans/repository-dispatch@v3
         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@v6
+        uses: actions/checkout@v4
 
       - name: Check for component changes
         uses: dorny/paths-filter@v3
@@ -71,7 +71,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -107,7 +107,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -148,7 +148,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 
@@ -277,7 +277,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 

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

@@ -29,7 +29,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -63,7 +63,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         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@v6
+      - uses: actions/checkout@v4
         # with:
           # fetch-depth: 0
       - name: Set up Python

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

@@ -96,7 +96,13 @@ class ChatConfig(BaseSettings):
     # Extended thinking configuration for Claude models
     thinking_enabled: bool = Field(
         default=True,
-        description="Enable adaptive thinking for Claude models via OpenRouter",
+        description="Enable extended thinking for Claude models via OpenRouter",
+    )
+    thinking_budget_tokens: int = Field(
+        default=10000,
+        ge=1000,
+        le=100000,
+        description="Maximum tokens for extended thinking (budget_tokens for Claude)",
     )
 
     @field_validator("api_key", mode="before")

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

@@ -2,7 +2,7 @@ import asyncio
 import logging
 import uuid
 from datetime import UTC, datetime
-from typing import Any, cast
+from typing import Any
 from weakref import WeakValueDictionary
 
 from openai.types.chat import (
@@ -104,26 +104,6 @@ class ChatSession(BaseModel):
     successful_agent_runs: dict[str, int] = {}
     successful_agent_schedules: dict[str, int] = {}
 
-    def add_tool_call_to_current_turn(self, tool_call: dict) -> None:
-        """Attach a tool_call to the current turn's assistant message.
-
-        Searches backwards for the most recent assistant message (stopping at
-        any user message boundary). If found, appends the tool_call to it.
-        Otherwise creates a new assistant message with the tool_call.
-        """
-        for msg in reversed(self.messages):
-            if msg.role == "user":
-                break
-            if msg.role == "assistant":
-                if not msg.tool_calls:
-                    msg.tool_calls = []
-                msg.tool_calls.append(tool_call)
-                return
-
-        self.messages.append(
-            ChatMessage(role="assistant", content="", tool_calls=[tool_call])
-        )
-
     @staticmethod
     def new(user_id: str) -> "ChatSession":
         return ChatSession(
@@ -192,47 +172,6 @@ class ChatSession(BaseModel):
             successful_agent_schedules=successful_agent_schedules,
         )
 
-    @staticmethod
-    def _merge_consecutive_assistant_messages(
-        messages: list[ChatCompletionMessageParam],
-    ) -> list[ChatCompletionMessageParam]:
-        """Merge consecutive assistant messages into single messages.
-
-        Long-running tool flows can create split assistant messages: one with
-        text content and another with tool_calls. Anthropic's API requires
-        tool_result blocks to reference a tool_use in the immediately preceding
-        assistant message, so these splits cause 400 errors via OpenRouter.
-        """
-        if len(messages) < 2:
-            return messages
-
-        result: list[ChatCompletionMessageParam] = [messages[0]]
-        for msg in messages[1:]:
-            prev = result[-1]
-            if prev.get("role") != "assistant" or msg.get("role") != "assistant":
-                result.append(msg)
-                continue
-
-            prev = cast(ChatCompletionAssistantMessageParam, prev)
-            curr = cast(ChatCompletionAssistantMessageParam, msg)
-
-            curr_content = curr.get("content") or ""
-            if curr_content:
-                prev_content = prev.get("content") or ""
-                prev["content"] = (
-                    f"{prev_content}\n{curr_content}" if prev_content else curr_content
-                )
-
-            curr_tool_calls = curr.get("tool_calls")
-            if curr_tool_calls:
-                prev_tool_calls = prev.get("tool_calls")
-                prev["tool_calls"] = (
-                    list(prev_tool_calls) + list(curr_tool_calls)
-                    if prev_tool_calls
-                    else list(curr_tool_calls)
-                )
-        return result
-
     def to_openai_messages(self) -> list[ChatCompletionMessageParam]:
         messages = []
         for message in self.messages:
@@ -319,7 +258,7 @@ class ChatSession(BaseModel):
                         name=message.name or "",
                     )
                 )
-        return self._merge_consecutive_assistant_messages(messages)
+        return messages
 
 
 async def _get_session_from_cache(session_id: str) -> ChatSession | None:

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

@@ -1,16 +1,4 @@
-from typing import cast
-
 import pytest
-from openai.types.chat import (
-    ChatCompletionAssistantMessageParam,
-    ChatCompletionMessageParam,
-    ChatCompletionToolMessageParam,
-    ChatCompletionUserMessageParam,
-)
-from openai.types.chat.chat_completion_message_tool_call_param import (
-    ChatCompletionMessageToolCallParam,
-    Function,
-)
 
 from .model import (
     ChatMessage,
@@ -129,205 +117,3 @@ async def test_chatsession_db_storage(setup_test_user, test_user_id):
                 loaded.tool_calls is not None
             ), f"Tool calls missing for {orig.role} message"
             assert len(orig.tool_calls) == len(loaded.tool_calls)
-
-
-# --------------------------------------------------------------------------- #
-#  _merge_consecutive_assistant_messages                                       #
-# --------------------------------------------------------------------------- #
-
-_tc = ChatCompletionMessageToolCallParam(
-    id="tc1", type="function", function=Function(name="do_stuff", arguments="{}")
-)
-_tc2 = ChatCompletionMessageToolCallParam(
-    id="tc2", type="function", function=Function(name="other", arguments="{}")
-)
-
-
-def test_merge_noop_when_no_consecutive_assistants():
-    """Messages without consecutive assistants are returned unchanged."""
-    msgs = [
-        ChatCompletionUserMessageParam(role="user", content="hi"),
-        ChatCompletionAssistantMessageParam(role="assistant", content="hello"),
-        ChatCompletionUserMessageParam(role="user", content="bye"),
-    ]
-    merged = ChatSession._merge_consecutive_assistant_messages(msgs)
-    assert len(merged) == 3
-    assert [m["role"] for m in merged] == ["user", "assistant", "user"]
-
-
-def test_merge_splits_text_and_tool_calls():
-    """The exact bug scenario: text-only assistant followed by tool_calls-only assistant."""
-    msgs = [
-        ChatCompletionUserMessageParam(role="user", content="build agent"),
-        ChatCompletionAssistantMessageParam(
-            role="assistant", content="Let me build that"
-        ),
-        ChatCompletionAssistantMessageParam(
-            role="assistant", content="", tool_calls=[_tc]
-        ),
-        ChatCompletionToolMessageParam(role="tool", content="ok", tool_call_id="tc1"),
-    ]
-    merged = ChatSession._merge_consecutive_assistant_messages(msgs)
-
-    assert len(merged) == 3
-    assert merged[0]["role"] == "user"
-    assert merged[2]["role"] == "tool"
-    a = cast(ChatCompletionAssistantMessageParam, merged[1])
-    assert a["role"] == "assistant"
-    assert a.get("content") == "Let me build that"
-    assert a.get("tool_calls") == [_tc]
-
-
-def test_merge_combines_tool_calls_from_both():
-    """Both consecutive assistants have tool_calls — they get merged."""
-    msgs: list[ChatCompletionAssistantMessageParam] = [
-        ChatCompletionAssistantMessageParam(
-            role="assistant", content="text", tool_calls=[_tc]
-        ),
-        ChatCompletionAssistantMessageParam(
-            role="assistant", content="", tool_calls=[_tc2]
-        ),
-    ]
-    merged = ChatSession._merge_consecutive_assistant_messages(msgs)  # type: ignore[arg-type]
-
-    assert len(merged) == 1
-    a = cast(ChatCompletionAssistantMessageParam, merged[0])
-    assert a.get("tool_calls") == [_tc, _tc2]
-    assert a.get("content") == "text"
-
-
-def test_merge_three_consecutive_assistants():
-    """Three consecutive assistants collapse into one."""
-    msgs: list[ChatCompletionAssistantMessageParam] = [
-        ChatCompletionAssistantMessageParam(role="assistant", content="a"),
-        ChatCompletionAssistantMessageParam(role="assistant", content="b"),
-        ChatCompletionAssistantMessageParam(
-            role="assistant", content="", tool_calls=[_tc]
-        ),
-    ]
-    merged = ChatSession._merge_consecutive_assistant_messages(msgs)  # type: ignore[arg-type]
-
-    assert len(merged) == 1
-    a = cast(ChatCompletionAssistantMessageParam, merged[0])
-    assert a.get("content") == "a\nb"
-    assert a.get("tool_calls") == [_tc]
-
-
-def test_merge_empty_and_single_message():
-    """Edge cases: empty list and single message."""
-    assert ChatSession._merge_consecutive_assistant_messages([]) == []
-
-    single: list[ChatCompletionMessageParam] = [
-        ChatCompletionUserMessageParam(role="user", content="hi")
-    ]
-    assert ChatSession._merge_consecutive_assistant_messages(single) == single
-
-
-# --------------------------------------------------------------------------- #
-#  add_tool_call_to_current_turn                                               #
-# --------------------------------------------------------------------------- #
-
-_raw_tc = {
-    "id": "tc1",
-    "type": "function",
-    "function": {"name": "f", "arguments": "{}"},
-}
-_raw_tc2 = {
-    "id": "tc2",
-    "type": "function",
-    "function": {"name": "g", "arguments": "{}"},
-}
-
-
-def test_add_tool_call_appends_to_existing_assistant():
-    """When the last assistant is from the current turn, tool_call is added to it."""
-    session = ChatSession.new(user_id="u")
-    session.messages = [
-        ChatMessage(role="user", content="hi"),
-        ChatMessage(role="assistant", content="working on it"),
-    ]
-    session.add_tool_call_to_current_turn(_raw_tc)
-
-    assert len(session.messages) == 2  # no new message created
-    assert session.messages[1].tool_calls == [_raw_tc]
-
-
-def test_add_tool_call_creates_assistant_when_none_exists():
-    """When there's no current-turn assistant, a new one is created."""
-    session = ChatSession.new(user_id="u")
-    session.messages = [
-        ChatMessage(role="user", content="hi"),
-    ]
-    session.add_tool_call_to_current_turn(_raw_tc)
-
-    assert len(session.messages) == 2
-    assert session.messages[1].role == "assistant"
-    assert session.messages[1].tool_calls == [_raw_tc]
-
-
-def test_add_tool_call_does_not_cross_user_boundary():
-    """A user message acts as a boundary — previous assistant is not modified."""
-    session = ChatSession.new(user_id="u")
-    session.messages = [
-        ChatMessage(role="assistant", content="old turn"),
-        ChatMessage(role="user", content="new message"),
-    ]
-    session.add_tool_call_to_current_turn(_raw_tc)
-
-    assert len(session.messages) == 3  # new assistant was created
-    assert session.messages[0].tool_calls is None  # old assistant untouched
-    assert session.messages[2].role == "assistant"
-    assert session.messages[2].tool_calls == [_raw_tc]
-
-
-def test_add_tool_call_multiple_times():
-    """Multiple long-running tool calls accumulate on the same assistant."""
-    session = ChatSession.new(user_id="u")
-    session.messages = [
-        ChatMessage(role="user", content="hi"),
-        ChatMessage(role="assistant", content="doing stuff"),
-    ]
-    session.add_tool_call_to_current_turn(_raw_tc)
-    # Simulate a pending tool result in between (like _yield_tool_call does)
-    session.messages.append(
-        ChatMessage(role="tool", content="pending", tool_call_id="tc1")
-    )
-    session.add_tool_call_to_current_turn(_raw_tc2)
-
-    assert len(session.messages) == 3  # user, assistant, tool — no extra assistant
-    assert session.messages[1].tool_calls == [_raw_tc, _raw_tc2]
-
-
-def test_to_openai_messages_merges_split_assistants():
-    """End-to-end: session with split assistants produces valid OpenAI messages."""
-    session = ChatSession.new(user_id="u")
-    session.messages = [
-        ChatMessage(role="user", content="build agent"),
-        ChatMessage(role="assistant", content="Let me build that"),
-        ChatMessage(
-            role="assistant",
-            content="",
-            tool_calls=[
-                {
-                    "id": "tc1",
-                    "type": "function",
-                    "function": {"name": "create_agent", "arguments": "{}"},
-                }
-            ],
-        ),
-        ChatMessage(role="tool", content="done", tool_call_id="tc1"),
-        ChatMessage(role="assistant", content="Saved!"),
-        ChatMessage(role="user", content="show me an example run"),
-    ]
-    openai_msgs = session.to_openai_messages()
-
-    # The two consecutive assistants at index 1,2 should be merged
-    roles = [m["role"] for m in openai_msgs]
-    assert roles == ["user", "assistant", "tool", "assistant", "user"]
-
-    # The merged assistant should have both content and tool_calls
-    merged = cast(ChatCompletionAssistantMessageParam, openai_msgs[1])
-    assert merged.get("content") == "Let me build that"
-    tc_list = merged.get("tool_calls")
-    assert tc_list is not None and len(list(tc_list)) == 1
-    assert list(tc_list)[0]["id"] == "tc1"

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

@@ -10,8 +10,6 @@ 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."""
@@ -195,18 +193,6 @@ 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/api/features/chat/service.py

@@ -80,6 +80,19 @@ settings = Settings()
 client = openai.AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
 
 
+def _apply_thinking_config(extra_body: dict[str, Any], model: str) -> None:
+    """Apply extended thinking configuration for Anthropic models via OpenRouter.
+
+    OpenRouter's reasoning API expects either:
+    - {"max_tokens": N} for explicit token budget
+    - {"effort": "high"} for automatic budget
+
+    See: https://openrouter.ai/docs/reasoning-tokens
+    """
+    if config.thinking_enabled and "anthropic" in model.lower():
+        extra_body["reasoning"] = {"max_tokens": config.thinking_budget_tokens}
+
+
 langfuse = get_client()
 
 # Redis key prefix for tracking running long-running operations
@@ -800,13 +813,9 @@ async def stream_chat_completion(
         # Build the messages list in the correct order
         messages_to_save: list[ChatMessage] = []
 
-        # Add assistant message with tool_calls if any.
-        # Use extend (not assign) to preserve tool_calls already added by
-        # _yield_tool_call for long-running tools.
+        # Add assistant message with tool_calls if any
         if accumulated_tool_calls:
-            if not assistant_response.tool_calls:
-                assistant_response.tool_calls = []
-            assistant_response.tool_calls.extend(accumulated_tool_calls)
+            assistant_response.tool_calls = accumulated_tool_calls
             logger.info(
                 f"Added {len(accumulated_tool_calls)} tool calls to assistant message"
             )
@@ -1070,9 +1079,8 @@ async def _stream_chat_chunks(
                         :128
                     ]  # OpenRouter limit
 
-                # Enable adaptive thinking for Anthropic models via OpenRouter
-                if config.thinking_enabled and "anthropic" in model.lower():
-                    extra_body["reasoning"] = {"enabled": True}
+                # Enable extended thinking for Anthropic models via OpenRouter
+                _apply_thinking_config(extra_body, model)
 
                 api_call_start = time_module.perf_counter()
                 stream = await client.chat.completions.create(
@@ -1408,9 +1416,13 @@ async def _yield_tool_call(
                 operation_id=operation_id,
             )
 
-            # Attach the tool_call to the current turn's assistant message
-            # (or create one if this is a tool-only response with no text).
-            session.add_tool_call_to_current_turn(tool_calls[yield_idx])
+            # Save assistant message with tool_call FIRST (required by LLM)
+            assistant_message = ChatMessage(
+                role="assistant",
+                content="",
+                tool_calls=[tool_calls[yield_idx]],
+            )
+            session.messages.append(assistant_message)
 
             # Then save pending tool result
             pending_message = ChatMessage(
@@ -1833,9 +1845,8 @@ async def _generate_llm_continuation(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
-        # Enable adaptive thinking for Anthropic models via OpenRouter
-        if config.thinking_enabled and "anthropic" in config.model.lower():
-            extra_body["reasoning"] = {"enabled": True}
+        # Enable extended thinking for Anthropic models via OpenRouter
+        _apply_thinking_config(extra_body, config.model)
 
         retry_count = 0
         last_error: Exception | None = None
@@ -1967,9 +1978,8 @@ async def _generate_llm_continuation_with_streaming(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
-        # Enable adaptive thinking for Anthropic models via OpenRouter
-        if config.thinking_enabled and "anthropic" in config.model.lower():
-            extra_body["reasoning"] = {"enabled": True}
+        # Enable extended thinking for Anthropic models via OpenRouter
+        _apply_thinking_config(extra_body, config.model)
 
         # Make streaming LLM call (no tools - just text response)
         from typing import cast

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -21,71 +21,43 @@ logger = logging.getLogger(__name__)
 
 class HumanInTheLoopBlock(Block):
     """
-    Pauses execution and waits for human approval or rejection of the data.
+    This block pauses execution and waits for human approval or modification of the data.
 
-    When executed, this block creates a pending review entry and sets the node execution
-    status to REVIEW. The execution remains paused until a human user either approves
-    or rejects the data.
+    When executed, it creates a pending review entry and sets the node execution status
+    to REVIEW. The execution will remain paused until a human user either:
+    - Approves the data (with or without modifications)
+    - Rejects the data
 
-    **How it works:**
-    - The input data is presented to a human reviewer
-    - The reviewer can approve or reject (and optionally modify the data if editable)
-    - On approval: the data flows out through the `approved_data` output pin
-    - On rejection: the data flows out through the `rejected_data` output pin
-
-    **Important:** The output pins yield the actual data itself, NOT status strings.
-    The approval/rejection decision determines WHICH output pin fires, not the value.
-    You do NOT need to compare the output to "APPROVED" or "REJECTED" - simply connect
-    downstream blocks to the appropriate output pin for each case.
-
-    **Example usage:**
-    - Connect `approved_data` → next step in your workflow (data was approved)
-    - Connect `rejected_data` → error handling or notification (data was rejected)
+    This is useful for workflows that require human validation or intervention before
+    proceeding to the next steps.
     """
 
     class Input(BlockSchemaInput):
-        data: Any = SchemaField(
-            description="The data to be reviewed by a human user. "
-            "This exact data will be passed through to either approved_data or "
-            "rejected_data output based on the reviewer's decision."
-        )
+        data: Any = SchemaField(description="The data to be reviewed by a human user")
         name: str = SchemaField(
-            description="A descriptive name for what this data represents. "
-            "This helps the reviewer understand what they are reviewing.",
+            description="A descriptive name for what this data represents",
         )
         editable: bool = SchemaField(
-            description="Whether the human reviewer can edit the data before "
-            "approving or rejecting it",
+            description="Whether the human reviewer can edit the data",
             default=True,
             advanced=True,
         )
 
     class Output(BlockSchemaOutput):
         approved_data: Any = SchemaField(
-            description="Outputs the input data when the reviewer APPROVES it. "
-            "The value is the actual data itself (not a status string like 'APPROVED'). "
-            "If the reviewer edited the data, this contains the modified version. "
-            "Connect downstream blocks here for the 'approved' workflow path."
+            description="The data when approved (may be modified by reviewer)"
         )
         rejected_data: Any = SchemaField(
-            description="Outputs the input data when the reviewer REJECTS it. "
-            "The value is the actual data itself (not a status string like 'REJECTED'). "
-            "If the reviewer edited the data, this contains the modified version. "
-            "Connect downstream blocks here for the 'rejected' workflow path."
+            description="The data when rejected (may be modified by reviewer)"
         )
         review_message: str = SchemaField(
-            description="Optional message provided by the reviewer explaining their "
-            "decision. Only outputs when the reviewer provides a message; "
-            "this pin does not fire if no message was given.",
-            default="",
+            description="Any message provided by the reviewer", default=""
         )
 
     def __init__(self):
         super().__init__(
             id="8b2a7b3c-6e9d-4a5f-8c1b-2e3f4a5b6c7d",
-            description="Pause execution for human review. Data flows through "
-            "approved_data or rejected_data output based on the reviewer's decision. "
-            "Outputs contain the actual data, not status strings.",
+            description="Pause execution and wait for human approval or modification of data",
             categories={BlockCategory.BASIC},
             input_schema=HumanInTheLoopBlock.Input,
             output_schema=HumanInTheLoopBlock.Output,

autogpt_platform/backend/backend/data/graph.py

@@ -743,11 +743,6 @@ 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

@@ -213,9 +213,6 @@ 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

@@ -364,44 +364,6 @@ 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],
@@ -761,13 +723,6 @@ 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 = "25.1.0"
+version = "24.1.0"
 description = "File support for asyncio."
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "aiofiles-25.1.0-py3-none-any.whl", hash = "sha256:abe311e527c862958650f9438e859c1fa7568a141b22abcd015e120e86a85695"},
-    {file = "aiofiles-25.1.0.tar.gz", hash = "sha256:a8d728f0a29de45dc521f18f07297428d56992a742f0cd2701ba86e44d23d5b2"},
+    {file = "aiofiles-24.1.0-py3-none-any.whl", hash = "sha256:b4ec55f4195e3eb5d7abd1bf7e061763e864dd4954231fb8539a0ef8bb8260e5"},
+    {file = "aiofiles-24.1.0.tar.gz", hash = "sha256:22a075c9e5a3810f0c2e48f3008c94d68c65d763b9b03857924c99e57355166c"},
 ]
 
 [[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 = "c06e96ad49388ba7a46786e9ea55ea2c1a57408e15613237b4bee40a592a12af"
+content-hash = "fc135114e01de39c8adf70f6132045e7d44a19473c1279aee0978de65aad1655"

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 = "^25.1.0"
+aiofiles = "^24.1.0"
 tiktoken = "^0.12.0"
 aioclamd = "^1.0.0"
 setuptools = "^80.9.0"

autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/edges/CustomEdge.tsx

@@ -63,17 +63,6 @@ const CustomEdge = ({
 
   return (
     <>
-      {/* Invisible interaction path - wider hit area for hover detection */}
-      <path
-        d={edgePath}
-        fill="none"
-        stroke="black"
-        strokeOpacity={0}
-        strokeWidth={20}
-        className="react-flow__edge-interaction cursor-pointer"
-        onMouseEnter={() => setIsHovered(true)}
-        onMouseLeave={() => setIsHovered(false)}
-      />
       <BaseEdge
         path={edgePath}
         markerEnd={markerEnd}

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

@@ -1,11 +1,11 @@
 "use client";
 
+import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
 import { SidebarProvider } from "@/components/ui/sidebar";
 import { ChatContainer } from "./components/ChatContainer/ChatContainer";
 import { ChatSidebar } from "./components/ChatSidebar/ChatSidebar";
 import { MobileDrawer } from "./components/MobileDrawer/MobileDrawer";
 import { MobileHeader } from "./components/MobileHeader/MobileHeader";
-import { ScaleLoader } from "./components/ScaleLoader/ScaleLoader";
 import { useCopilotPage } from "./useCopilotPage";
 
 export function CopilotPage() {
@@ -34,11 +34,7 @@ export function CopilotPage() {
   } = useCopilotPage();
 
   if (isUserLoading || !isLoggedIn) {
-    return (
-      <div className="fixed inset-0 z-50 flex items-center justify-center bg-[#f8f8f9]">
-        <ScaleLoader className="text-neutral-400" />
-      </div>
-    );
+    return <LoadingSpinner size="large" cover />;
   }
 
   return (

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

@@ -10,9 +10,8 @@ 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, useRef, useState } from "react";
+import { useEffect, useState } from "react";
 import { CreateAgentTool } from "../../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../../tools/EditAgent/EditAgent";
 import { FindAgentsTool } from "../../tools/FindAgents/FindAgents";
@@ -122,7 +121,6 @@ export const ChatMessagesContainer = ({
   isLoading,
 }: ChatMessagesContainerProps) => {
   const [thinkingPhrase, setThinkingPhrase] = useState(getRandomPhrase);
-  const lastToastTimeRef = useRef(0);
 
   useEffect(() => {
     if (status === "submitted") {
@@ -130,20 +128,6 @@ 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" &&
@@ -159,10 +143,10 @@ export const ChatMessagesContainer = ({
 
   return (
     <Conversation className="min-h-0 flex-1">
-      <ConversationContent className="flex min-h-screen flex-1 flex-col gap-6 px-3 py-6">
+      <ConversationContent className="gap-6 px-3 py-6">
         {isLoading && messages.length === 0 && (
-          <div className="flex min-h-full flex-1 items-center justify-center">
-            <LoadingSpinner className="text-neutral-600" />
+          <div className="flex flex-1 items-center justify-center">
+            <LoadingSpinner size="large" className="text-neutral-400" />
           </div>
         )}
         {messages.map((message, messageIndex) => {
@@ -279,12 +263,8 @@ export const ChatMessagesContainer = ({
           </Message>
         )}
         {error && (
-          <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 className="rounded-lg bg-red-50 p-3 text-red-600">
+            Error: {error.message}
           </div>
         )}
       </ConversationContent>

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

@@ -121,8 +121,8 @@ export function ChatSidebar() {
             className="mt-4 flex flex-col gap-1"
           >
             {isLoadingSessions ? (
-              <div className="flex min-h-[30rem] items-center justify-center py-4">
-                <LoadingSpinner size="small" className="text-neutral-600" />
+              <div className="flex items-center justify-center py-4">
+                <LoadingSpinner size="small" className="text-neutral-400" />
               </div>
             ) : sessions.length === 0 ? (
               <p className="py-4 text-center text-sm text-neutral-500">

autogpt_platform/frontend/src/app/(platform)/copilot/components/ScaleLoader/ScaleLoader.module.css

@@ -1,35 +0,0 @@
-.loader {
-  width: 48px;
-  height: 48px;
-  display: inline-block;
-  position: relative;
-}
-
-.loader::after,
-.loader::before {
-  content: "";
-  box-sizing: border-box;
-  width: 100%;
-  height: 100%;
-  border-radius: 50%;
-  background: currentColor;
-  position: absolute;
-  left: 0;
-  top: 0;
-  animation: animloader 2s linear infinite;
-}
-
-.loader::after {
-  animation-delay: 1s;
-}
-
-@keyframes animloader {
-  0% {
-    transform: scale(0);
-    opacity: 1;
-  }
-  100% {
-    transform: scale(1);
-    opacity: 0;
-  }
-}

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

@@ -1,16 +0,0 @@
-import { cn } from "@/lib/utils";
-import styles from "./ScaleLoader.module.css";
-
-interface Props {
-  size?: number;
-  className?: string;
-}
-
-export function ScaleLoader({ size = 48, className }: Props) {
-  return (
-    <div
-      className={cn(styles.loader, className)}
-      style={{ width: size, height: size }}
-    />
-  );
-}

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

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

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

@@ -4,6 +4,7 @@ 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,
@@ -48,7 +49,12 @@ interface Props {
   part: CreateAgentToolPart;
 }
 
-function getAccordionMeta(output: CreateAgentToolOutput) {
+function getAccordionMeta(output: CreateAgentToolOutput): {
+  icon: React.ReactNode;
+  title: React.ReactNode;
+  titleClassName?: string;
+  description?: string;
+} {
   const icon = <AccordionIcon />;
 
   if (isAgentSavedOutput(output)) {
@@ -67,7 +73,6 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
       icon,
       title: "Needs clarification",
       description: `${questions.length} question${questions.length === 1 ? "" : "s"}`,
-      expanded: true,
     };
   }
   if (
@@ -76,7 +81,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
     isOperationInProgressOutput(output)
   ) {
     return {
-      icon,
+      icon: <OrbitLoader size={32} />,
       title: "Creating agent, this may take a few minutes. Sit back and relax.",
     };
   }
@@ -92,23 +97,18 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
 export function CreateAgentTool({ part }: Props) {
   const text = getAnimationText(part);
   const { onSend } = useCopilotChatActions();
-
   const isStreaming =
     part.state === "input-streaming" || part.state === "input-available";
 
   const output = getCreateAgentToolOutput(part);
-
   const isError =
     part.state === "output-error" || (!!output && isErrorOutput(output));
-
   const isOperating =
     !!output &&
     (isOperationStartedOutput(output) ||
       isOperationPendingOutput(output) ||
       isOperationInProgressOutput(output));
-
   const progress = useAsymptoticProgress(isOperating);
-
   const hasExpandableContent =
     part.state === "output-available" &&
     !!output &&
@@ -149,7 +149,10 @@ export function CreateAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
           {isOperating && (
             <ContentGrid>
               <ProgressBar value={progress} className="max-w-[280px]" />

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

@@ -146,7 +146,10 @@ export function EditAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
           {isOperating && (
             <ContentGrid>
               <ProgressBar value={progress} className="max-w-[280px]" />

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

@@ -61,7 +61,14 @@ export function RunAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunAgentExecutionStartedOutput(output) ||
+            isRunAgentSetupRequirementsOutput(output) ||
+            isRunAgentAgentDetailsOutput(output)
+          }
+        >
           {isRunAgentExecutionStartedOutput(output) && (
             <ExecutionStartedCard output={output} />
           )}

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 { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
 
 export interface RunAgentInput {
   username_agent_slug?: string;
@@ -171,7 +171,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }
@@ -203,7 +203,7 @@ export function getAccordionMeta(output: RunAgentToolOutput): {
         ? output.status.trim()
         : "started";
     return {
-      icon,
+      icon: <SpinnerLoader size={28} className="text-neutral-700" />,
       title: output.graph_name,
       description: `Status: ${statusText}`,
     };

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

@@ -55,7 +55,13 @@ export function RunBlockTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunBlockBlockOutput(output) ||
+            isRunBlockSetupRequirementsOutput(output)
+          }
+        >
           {isRunBlockBlockOutput(output) && <BlockOutputCard output={output} />}
 
           {isRunBlockSetupRequirementsOutput(output) && (

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 { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
 
 export interface RunBlockInput {
   block_id?: string;
@@ -120,7 +120,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }
@@ -149,7 +149,7 @@ export function getAccordionMeta(output: RunBlockToolOutput): {
   if (isRunBlockBlockOutput(output)) {
     const keys = Object.keys(output.outputs ?? {});
     return {
-      icon,
+      icon: <SpinnerLoader size={32} className="text-neutral-700" />,
       title: output.block_name,
       description:
         keys.length > 0

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

@@ -3,6 +3,7 @@ import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
 import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
 import { useChat } from "@ai-sdk/react";
 import { DefaultChatTransport } from "ai";
+import { useRouter } from "next/navigation";
 import { useEffect, useMemo, useState } from "react";
 import { useChatSession } from "./useChatSession";
 
@@ -10,6 +11,7 @@ export function useCopilotPage() {
   const { isUserLoading, isLoggedIn } = useSupabase();
   const [isDrawerOpen, setIsDrawerOpen] = useState(false);
   const [pendingMessage, setPendingMessage] = useState<string | null>(null);
+  const router = useRouter();
 
   const {
     sessionId,
@@ -52,6 +54,10 @@ export function useCopilotPage() {
     transport: transport ?? undefined,
   });
 
+  useEffect(() => {
+    if (!isUserLoading && !isLoggedIn) router.replace("/login");
+  }, [isUserLoading, isLoggedIn]);
+
   useEffect(() => {
     if (!hydratedMessages || hydratedMessages.length === 0) return;
     setMessages((prev) => {

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

@@ -1,8 +1,11 @@
 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 }> },
@@ -20,14 +23,17 @@ 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",
@@ -57,15 +63,14 @@ export async function POST(
       });
     }
 
-    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,
+    // 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",
+      },
     });
   } catch (error) {
     console.error("SSE proxy error:", error);
@@ -82,6 +87,13 @@ 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 }> },
@@ -112,6 +124,7 @@ export async function GET(
       headers,
     });
 
+    // 204 = no active stream to resume
     if (response.status === 204) {
       return new Response(null, { status: 204 });
     }
@@ -124,13 +137,12 @@ export async function GET(
       });
     }
 
-    if (!response.body) {
-      return new Response(null, { status: 204 });
-    }
-
-    return new Response(normalizeSSEStream(response.body), {
+    return new Response(response.body, {
       headers: {
-        ...SSE_HEADERS,
+        "Content-Type": "text/event-stream",
+        "Cache-Control": "no-cache, no-transform",
+        Connection: "keep-alive",
+        "X-Accel-Buffering": "no",
         "x-vercel-ai-ui-message-stream": "v1",
       },
     });

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

@@ -1,72 +0,0 @@
-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

@@ -1,8 +1,20 @@
 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 }> },
@@ -12,12 +24,15 @@ 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",
@@ -41,12 +56,14 @@ export async function GET(
       });
     }
 
-    if (!response.body) {
-      return new Response(null, { status: 204 });
-    }
-
-    return new Response(normalizeSSEStream(response.body), {
-      headers: SSE_HEADERS,
+    // 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",
+      },
     });
   } catch (error) {
     console.error("Task stream proxy error:", error);

autogpt_platform/frontend/src/lib/supabase/helpers.ts

@@ -6,7 +6,6 @@ import { SupabaseClient } from "@supabase/supabase-js";
 export const PROTECTED_PAGES = [
   "/auth/authorize",
   "/auth/integrations",
-  "/copilot",
   "/monitor",
   "/build",
   "/onboarding",

docs/integrations/README.md

@@ -61,7 +61,7 @@ Below is a comprehensive list of all available blocks, categorized by their prim
 | [Get List Item](block-integrations/basic.md#get-list-item) | Returns the element at the given index |
 | [Get Store Agent Details](block-integrations/system/store_operations.md#get-store-agent-details) | Get detailed information about an agent from the store |
 | [Get Weather Information](block-integrations/basic.md#get-weather-information) | Retrieves weather information for a specified location using OpenWeatherMap API |
-| [Human In The Loop](block-integrations/basic.md#human-in-the-loop) | Pause execution for human review |
+| [Human In The Loop](block-integrations/basic.md#human-in-the-loop) | Pause execution and wait for human approval or modification of data |
 | [List Is Empty](block-integrations/basic.md#list-is-empty) | Checks if a list is empty |
 | [List Library Agents](block-integrations/system/library_operations.md#list-library-agents) | List all agents in your personal library |
 | [Note](block-integrations/basic.md#note) | A visual annotation block that displays a sticky note in the workflow editor for documentation and organization purposes |

docs/integrations/block-integrations/basic.md

@@ -975,7 +975,7 @@ A travel planning application could use this block to provide users with current
 ## Human In The Loop
 
 ### What it is
-Pause execution for human review. Data flows through approved_data or rejected_data output based on the reviewer's decision. Outputs contain the actual data, not status strings.
+Pause execution and wait for human approval or modification of data
 
 ### How it works
 <!-- MANUAL: how_it_works -->
@@ -988,18 +988,18 @@ This enables human oversight at critical points in automated workflows, ensuring
 
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
-| data | The data to be reviewed by a human user. This exact data will be passed through to either approved_data or rejected_data output based on the reviewer's decision. | Data | Yes |
-| name | A descriptive name for what this data represents. This helps the reviewer understand what they are reviewing. | str | Yes |
-| editable | Whether the human reviewer can edit the data before approving or rejecting it | bool | No |
+| data | The data to be reviewed by a human user | Data | Yes |
+| name | A descriptive name for what this data represents | str | Yes |
+| editable | Whether the human reviewer can edit the data | bool | No |
 
 ### Outputs
 
 | Output | Description | Type |
 |--------|-------------|------|
 | error | Error message if the operation failed | str |
-| approved_data | Outputs the input data when the reviewer APPROVES it. The value is the actual data itself (not a status string like 'APPROVED'). If the reviewer edited the data, this contains the modified version. Connect downstream blocks here for the 'approved' workflow path. | Approved Data |
-| rejected_data | Outputs the input data when the reviewer REJECTS it. The value is the actual data itself (not a status string like 'REJECTED'). If the reviewer edited the data, this contains the modified version. Connect downstream blocks here for the 'rejected' workflow path. | Rejected Data |
-| review_message | Optional message provided by the reviewer explaining their decision. Only outputs when the reviewer provides a message; this pin does not fire if no message was given. | str |
+| approved_data | The data when approved (may be modified by reviewer) | Approved Data |
+| rejected_data | The data when rejected (may be modified by reviewer) | Rejected Data |
+| review_message | Any message provided by the reviewer | str |
 
 ### Possible use case
 <!-- MANUAL: use_case -->