# Chat model returns empty content when I inject a delayed ToolMessage from a scheduled callback **URL:** \ **Category:** Talking Shop\ **Tags:** intro-to-langgraph, python-help\ **Created:** [October 26, 2025, 8:20am UTC](https://forum.langchain.com/t/chat-model-returns-empty-content-when-i-inject-a-delayed-toolmessage-from-a-scheduled-callback/1951 "2025-10-26T08:20:40Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![vicky70](https://avatars.discourse-cdn.com/v4/letter/v/4af34b/32.png) [@vicky70](https://forum.langchain.com/u/vicky70)\ **Post date:** [October 26, 2025, 8:20am UTC](https://forum.langchain.com/t/chat-model-returns-empty-content-when-i-inject-a-delayed-toolmessage-from-a-scheduled-callback/1951/1 "2025-10-26T08:20:40Z")
Hey! I have a scheduler that triggers a tool function later (outside the original user–model exchange). When the scheduled time comes, it sends a **ToolMessage** back into the chat model — but the model returns an empty message (`content=""`) instead of responding. **This is the flow of messages:** [HumanMessage] → [AIMessage] → [ToolMessage] → [AIMessage] → … → [ToolMessage (from scheduled function)] The final **ToolMessage** is the one created when the scheduled callback fires. That’s where the issue happens — the model simply returns an empty string. **The Scheduled Callback:** ```auto def _task_reminder_callback(thread_id: str, task_description: str): print(f"\n\n === AGENT: TASK REMINDER! (for thread: {thread_id}) === ") print(f" TASK: {task_description} ") print(" ======================================================= \n\n") config = {"configurable": {"thread_id": thread_id, "user_id": "user_123"}} workflow_instance = app_state.get("WORKFLOW") state = workflow_instance.get_state(config) # Find the most recent tool call for schedule_reminder tool_call_id = None if state and state.values and "messages" in state.values: for msg in reversed(state.values["messages"]): if hasattr(msg, 'tool_calls') and msg.tool_calls: for tool_call in msg.tool_calls: if tool_call.get('name') == 'schedule_reminder': tool_call_id = tool_call.get('id') break if tool_call_id: break print(f'[DEBUG] tool_call_id: {tool_call_id}') if workflow_instance: try: reminder_message = ToolMessage( content=( f"REMINDER: generate a natural sounding message to remind user " f"that it's time to do this task:\n\n {task_description}.\n\n" ), tool_call_id=tool_call_id ) result = workflow_instance.invoke({"messages": reminder_message}, config=config) print(f" === Successfully invoked workflow for reminder in thread {thread_id} === \n\n {result} === \n\n") except Exception as e: print(f" !!! ERROR in _task_reminder_callback for thread {thread_id}: {e} !!! \n\n") else: print(f" !!! ERROR: WORKFLOW not initialized. Cannot run reminder for thread {thread_id} !!!") ``` **Problem** When this scheduled function runs and I call `workflow_instance.invoke()` with a `ToolMessage`, the chat model **returns an empty content message AIMessage(`content=""`)** — it doesn’t “react” like it normally would when the tool message comes directly during conversation flow. **Expected behavior:** The model should interpret the tool message and respond naturally (e.g., “Hey, it’s time to do your scheduled task!”). **My Question:** How can I correctly re-inject a delayed `ToolMessage` into the workflow so that the model _responds_ like it does during normal tool use? Is there something special about how the `tool_call_id` or message history needs to be linked so the model knows what to do? Or do I need to send a different type of message (like `SystemMessage` or `AssistantMessage`) when reactivating the model after a delay? ---
**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\ **Post date:** [October 26, 2025, 11:49am UTC](https://forum.langchain.com/t/chat-model-returns-empty-content-when-i-inject-a-delayed-toolmessage-from-a-scheduled-callback/1951/2 "2025-10-26T11:49:42Z")
Hi @vicky70 have you tried this? ```py # 1) Build the ToolMessage with the SAME tool_call_id produced earlier by the model reminder_message = ToolMessage( content=( f"REMINDER: generate a natural sounding message to remind the user " f"that it's time to do this task:\n\n{task_description}.\n\n" ), tool_call_id=tool_call_id, name="schedule_reminder", # include tool name for clarity ) # 2) Append it to the thread state AS IF it came from the 'tools' node next_config = workflow_instance.update_state( config, {"messages": [reminder_message]}, as_node="tools", # drives the graph to the agent/model next ) # 3) Resume the graph so the model reacts to the tool output result = workflow_instance.invoke(None, config=next_config) ``` ---
**Author:** ![vinishiru](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/vinishiru/32/2362_2.png) [@vinishiru](https://forum.langchain.com/u/vinishiru)\ **Post date:** [February 19, 2026, 7:11pm UTC](https://forum.langchain.com/t/chat-model-returns-empty-content-when-i-inject-a-delayed-toolmessage-from-a-scheduled-callback/1951/3 "2026-02-19T19:11:27Z")
Hello @vicky70 , have you successfully implemented this behavior? I also have a tool that returns a partial result from the agent call, but in a later moment I try to inject a ToolMessage (with same tool\_call\_id), but the model generates a empty content response. I have tried the @pawel-twardziak approach, but the model also generates an empty response, even when updating the graph state as it was resuming the result from the tool node. I have also used a time-travel approach, search for the state when the tool was originally called, overwriting the tool result, as if it was completed as a direct call, but this way I lose any message exchanged between the user and the agent. I had better results creating the tool message and a HumanMessage that instructs the model to continue the conversation, both on the same input message array, but oddly the model seens to ignore the ToolMessage data and generate a response that is not present on the appended ToolMessage. Example: ```python messages = [ ToolMessage( content=ai_agent_prompt_dto.prompt, tool_call_id=ai_agent_prompt_dto.context[ "tool_call_id" ], ), HumanMessage(content="You have received the tool delayed result. You must continue with the conversation."), ] ``` ---
**Author:** ![Bitcot\_Kaushal](https://avatars.discourse-cdn.com/v4/letter/b/59ef9b/32.png) [@Bitcot\_Kaushal](https://forum.langchain.com/u/Bitcot_Kaushal)\ **Post date:** [February 20, 2026, 2:54am UTC](https://forum.langchain.com/t/chat-model-returns-empty-content-when-i-inject-a-delayed-toolmessage-from-a-scheduled-callback/1951/4 "2026-02-20T02:54:49Z")
Hey @vicky70 This usually happens because the graph isn’t actually being resumed in the same execution context the model expects. When you inject a delayed `ToolMessage`, the model will only react if: 1. The `tool_call_id` matches **exactly** the one from the original `AIMessage.tool_calls`. 2. The message is appended as coming from the `"tools"` node. 3. The graph is resumed from the correct next edge (not restarted with a fresh invoke). In **LangGraph** , a `ToolMessage` by itself doesn’t trigger reasoning — it only works if the graph state machine thinks it just finished executing a tool. If that edge isn’t active anymore (because time passed or the flow completed), the model can legitimately return `AIMessage(content="")`. That empty response usually means: > “There is no pending tool result expected in this state.” * * * ### Why your HumanMessage workaround behaves oddly When you add: ```auto HumanMessage("You have received the tool delayed result...") ``` you’re effectively starting a **new reasoning turn**. So the model ignores the tool linkage and just treats it like fresh input. That’s why it doesn’t behave like native tool completion. * * * ### What works more reliably in production Instead of trying to “resume” the original tool call hours later: ✅ Treat the reminder as a **new user event** → Inject a `HumanMessage` like: > “System reminder: It’s time to do X.” and let the agent respond normally. This avoids fighting the internal state machine. * * * ### Why this happens (architecturally) LangGraph’s execution model assumes: ```auto AI → tool_call → ToolMessage → AI (immediate continuation) ``` It is not designed for: ```auto AI → tool_call → [hours later] → ToolMessage → AI ``` Once the run is complete, there is no suspended edge waiting for that tool result. * * * In short: You’re not doing it wrong — you’re hitting a lifecycle limitation. Delayed tool reinjection only works if the graph is still in a waiting state. Otherwise, treat it as a new conversational turn.