HKUDS/nanobot · error · TypeError

context_window_tokens must be an integer

Error message

context_window_tokens must be an integer

What it means

Type guard in LLMRuntimeManager.select_context_window: the caller passed a context_window_tokens argument that is not an int (bool is explicitly rejected too, since bool subclasses int). The value must be a real integer token count before the runtime's default context limit is replaced, because downstream admission logic does arithmetic on it.

Solutions

1. Coerce the value with int() before calling select_context_window
2. Fix the config source so the context window is stored as an integer
3. Reject non-integer input at the API/config boundary with a 4xx error

When it happens

Trigger: Thrown at nanobot/agent/model_runtime.py:159 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of HKUDS/nanobot@42f37dc4c0 (2026-08-26). Data as JSON: /api/errors/ab030f051d28d75b. Report an issue: GitHub.

Appendix: source

Thrown at nanobot/agent/model_runtime.py:159

    def select_model(self, model: str) -> LLMRuntime:
        """Change the default model without reconstructing downstream consumers."""
        if not isinstance(cast(object, model), str) or not model.strip():
            raise ValueError("model must be a non-empty string")
        self._runtime = replace(
            self._runtime,
            model=model.strip(),
            model_preset=None,
        )
        return self._runtime

    def select_context_window(self, context_window_tokens: int) -> LLMRuntime:
        """Change the default context limit for future admissions."""
        raw_context_window = cast(object, context_window_tokens)
        if not isinstance(raw_context_window, int) or isinstance(
            raw_context_window,
            bool,
        ):
            raise TypeError("context_window_tokens must be an integer")
        self._runtime = replace(
            self._runtime,
            context_window_tokens=context_window_tokens,
        )
        return self._runtime

    def _refresh_provider_generation(self) -> LLMRuntime | None:
        """Adopt direct provider-default changes only for provider-backed defaults."""
        if not self._tracks_provider_generation:
            return None
        runtime = self._runtime
        captured = LLMRuntime.capture(
            runtime.provider,
            runtime.model,
            context_window_tokens=runtime.context_window_tokens,
            model_preset=runtime.model_preset,
            snapshot_signature=runtime.snapshot_signature,
        )

View on GitHub (pinned to 42f37dc4c0)