infiniflow/ragflow · error · RuntimeError

Unsupported language for local provider: {language}

Error message

Unsupported language for local provider: {language}

What it means

Raised by LocalProvider._prepare_script() when the normalized language is neither 'python' nor in {'javascript', 'nodejs'}. The provider only knows how to build a wrapper script for those languages (build_python_wrapper / build_javascript_wrapper), so any other language string reaches the trailing RuntimeError. Note _normalize_language() runs first, so only genuinely unsupported languages get here.

Source

Thrown at agent/sandbox/providers/local.py:279

        if self.max_memory_mb <= 0:
            raise SandboxProviderConfigError("SANDBOX_LOCAL_MAX_MEMORY_MB must be greater than 0.")
        if self.max_output_bytes <= 0:
            raise SandboxProviderConfigError("SANDBOX_LOCAL_MAX_OUTPUT_BYTES must be greater than 0.")
        if self.max_artifacts < 0:
            raise SandboxProviderConfigError("SANDBOX_LOCAL_MAX_ARTIFACTS must be greater than or equal to 0.")
        if self.max_artifact_bytes <= 0:
            raise SandboxProviderConfigError("SANDBOX_LOCAL_MAX_ARTIFACT_BYTES must be greater than 0.")

    def _prepare_script(self, instance_dir: Path, language: str, code: str, args_json: str) -> tuple[list[str], Path]:
        if language == "python":
            script_path = instance_dir / "main.py"
            script_path.write_text(build_python_wrapper(code, args_json), encoding="utf-8")
            return [self.python_bin, str(script_path)], script_path
        if language in {"javascript", "nodejs"}:
            script_path = instance_dir / "main.js"
            script_path.write_text(build_javascript_wrapper(code, args_json), encoding="utf-8")
            return [self.node_bin, str(script_path)], script_path
        raise RuntimeError(f"Unsupported language for local provider: {language}")

    def _build_child_env(self, instance_dir: Path) -> dict[str, str]:
        env = {
            "HOME": str(instance_dir),
            "MPLBACKEND": "Agg",
            "PATH": os.environ.get("PATH", ""),
            "PYTHONUNBUFFERED": "1",
            "TMPDIR": str(instance_dir),
        }
        for name in LOCAL_PYTHON_THREAD_ENV_VARS:
            value = os.environ.get(name)
            if value is not None:
                env[name] = value
        return env

    def _limit_child_process(self) -> None:
        import resource

View on GitHub (pinned to 554fb1133a)

Solutions

1. Pass one of the supported languages exactly: 'python', 'javascript', or 'nodejs'.
2. Before executing, check language in provider.get_supported_languages() and reject/fallback in the caller for anything else.
3. If you need another runtime, use a different provider (self_managed / SSH) or extend the provider with a new wrapper — do not retry with the same string.
4. Print get_supported_languages() at startup in integrations to catch mismatches early.

Example fix

// before
result = provider.execute_code(instance_id, code, language="bash")

// after
supported = provider.get_supported_languages()
if language not in supported:
    raise ValueError(f"Unsupported language {language!r}; supported: {supported}")
result = provider.execute_code(instance_id, code, language="python")

language = provider._normalize_language(language)
if language not in provider.get_supported_languages():
    raise ValueError(f"Unsupported language: {language}")

from typing import Final

SUPPORTED: Final[frozenset[str]] = frozenset({"python", "javascript", "nodejs"})

def is_supported_language(lang: str) -> bool:
    """True when LocalProvider can execute this language."""
    return isinstance(lang, str) and lang.strip().lower() in SUPPORTED

try:
    provider.execute_code(instance_id, code, language)
except RuntimeError as e:
    if "Unsupported language" in str(e):
        # re-dispatch as python or reject the request
        raise ValueError(str(e)) from e
    raise

When it happens

Trigger: Calling execute_code(instance_id, code, language='bash'|'go'|'java'|'ruby'|''); passing a template string to create_instance() that normalizes to something outside the supported set. Check get_supported_languages() — it returns ['python', 'javascript', 'nodejs'].

Common situations: An LLM-generated agent tool call specifying an unsupported language; version skew where a caller assumes a language added in a newer release; typos like 'js' if _normalize_language does not map them; passing a template name (e.g. 'python:3.11') instead of a bare language.

Related errors

• No sandbox provider configured. Please configure sandbox set
• SANDBOX_LOCAL_TIMEOUT must be greater than 0.
• SANDBOX_LOCAL_MAX_MEMORY_MB must be greater than 0.
• SANDBOX_LOCAL_MAX_OUTPUT_BYTES must be greater than 0.
• SANDBOX_LOCAL_MAX_ARTIFACTS must be greater than or equal to

AI-assisted analysis of infiniflow/ragflow@554fb1133a (2026-08-15). Data as JSON: /api/errors/9e2b454e278fddfa. Report an issue: GitHub.