microsoft/semantic-kernel · error · ValueError

Failed to determine if the agent should terminate because th

Error message

Failed to determine if the agent should terminate because the model did not return a valid response.

What it means

Raised by custom_termination_strategy after the model failed to return either the TERMINATE_TRUE_KEYWORD or TERMINATE_FALSE_KEYWORD across all retry attempts. The strategy asks a yes/no termination decision; if the model keeps returning other tokens it raises ValueError.

Source

Thrown at python/samples/demos/document_generator/custom_termination_strategy.py:75

                completion = await self.chat_completion_service.get_chat_message_content(
                    chat_history,
                    AzureChatPromptExecutionSettings(),
                )

                if not completion:
                    continue

                if TERMINATE_FALSE_KEYWORD in completion.content.lower():
                    return False
                if TERMINATE_TRUE_KEYWORD in completion.content.lower():
                    return True

                chat_history.add_message(completion)
                chat_history.add_user_message(
                    f"You must only say either '{TERMINATE_TRUE_KEYWORD}' or '{TERMINATE_FALSE_KEYWORD}'."
                )

            raise ValueError(
                "Failed to determine if the agent should terminate because the model did not return a valid response."
            )

    def get_system_message(self) -> str:
        return f"""
You are in a chat with multiple agents collaborating to create a document.
Each message in the chat history contains the agent's name and the message content.

The chat history may start empty as no agents have spoken yet.

Here are the agents with their indices, names, and descriptions:
{NEWLINE.join(f"[{index}] {agent.name}:{NEWLINE}{agent.description}" for index, agent in enumerate(self.agents))}

Your task is NOT to continue the conversation. Determine if the latest content is approved by all agents.
If approved, say "{TERMINATE_TRUE_KEYWORD}". Otherwise, say "{TERMINATE_FALSE_KEYWORD}".
"""

View on GitHub (pinned to c028a0c7dc)

Solutions

  1. Use a stronger instruction-following model for the termination check.
  2. Increase retry count so the model gets more correction prompts.
  3. Normalize the response (strip punctuation/whitespace, take the first token) before keyword matching.
  4. Ensure TERMINATE_TRUE_KEYWORD / TERMINATE_FALSE_KEYWORD are distinct, unambiguous tokens.

Example fix

// before
if TERMINATE_FALSE_KEYWORD in completion.content.lower():
    return False

// after
token = (completion.content or '').strip().lower().rstrip('.!,')
if TERMINATE_FALSE_KEYWORD in token:
    return False
Defensive patterns

Strategy: validation

Validate before calling

def parse_termination(content: str | None, true_kw: str, false_kw: str) -> bool | None:
    if not content:
        return None
    c = content.strip().lower().rstrip('.!,')
    if false_kw in c:
        return False
    if true_kw in c:
        return True
    return None

Try / catch

decision = parse_termination(completion.content, TERMINATE_TRUE_KEYWORD, TERMINATE_FALSE_KEYWORD)
if decision is not None:
    return decision
chat_history.add_message(completion)
chat_history.add_user_message(f"Reply with only '{TERMINATE_TRUE_KEYWORD}' or '{TERMINATE_FALSE_KEYWORD}'.")

Prevention

When it happens

Trigger: The model returns an explanation instead of the bare keyword; TERMINATE_TRUE_KEYWORD/TERMINATE_FALSE_KEYWORD substrings are absent from completion.content.lower(); completion.content is None.

Common situations: Weak instruction-following models; overly verbose system prompts; keywords that collide with common English words causing misfires; the model wrapping the keyword in punctuation.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/f7d68df9983bd953. Report an issue: GitHub.