agentscope-ai/agentscope · error · ValueError

f"Unsupported LLM provider: {provider}"

Error message

f"Unsupported LLM provider: {provider}"

What it means

A pydantic field_validator on the agentscope LLM config subclass only accepts provider == 'agentscope'; any other provider string re-raises mem0's 'Unsupported LLM provider' error during config parsing.

Source

Thrown at src/agentscope/middleware/_longterm_memory/_mem0/_agentscope_adapter.py:421

    other provider continues to be rejected with the same error mem0
    would have raised)."""
    from pydantic import field_validator

    from mem0.embeddings.configs import EmbedderConfig
    from mem0.llms.configs import LlmConfig

    class _AgentScopeLlmConfig(LlmConfig):
        """``LlmConfig`` subclass that accepts the AgentScope provider."""

        @field_validator("config")
        @classmethod
        def validate_config(cls, v: Any, values: Any) -> Any:
            """Allow ``provider == "agentscope"``; reject everything
            else with mem0's original error."""
            provider = values.data.get("provider")
            if provider == _AGENTSCOPE_PROVIDER:
                return v
            raise ValueError(f"Unsupported LLM provider: {provider}")

    class _AgentScopeEmbedderConfig(EmbedderConfig):
        """``EmbedderConfig`` subclass that accepts the AgentScope
        provider."""

        @field_validator("config")
        @classmethod
        def validate_config(cls, v: Any, values: Any) -> Any:
            """Allow ``provider == "agentscope"``; reject everything
            else with mem0's original error."""
            provider = values.data.get("provider")
            if provider == _AGENTSCOPE_PROVIDER:
                return v
            raise ValueError(
                f"Unsupported embedding provider: {provider}",
            )

    return _AgentScopeLlmConfig, _AgentScopeEmbedderConfig

View on GitHub (pinned to e90f1c7592)

Solutions

1. Set provider='agentscope' (exact lowercase) on the llm block
2. Prefer build_mem0_config which fills the provider automatically

Example fix

// before
MemoryConfig(llm={'provider': 'openai', ...})
// after
MemoryConfig(llm={'provider': 'agentscope', ...})

assert llm_block.get('provider') == 'agentscope', 'provider must be exactly "agentscope"'

try:
    MemoryConfig(**cfg)
except ValueError as e:
    if 'Unsupported LLM provider' in str(e):
        cfg['llm']['provider'] = 'agentscope'
    else:
        raise

When it happens

Trigger: Building MemoryConfig(llm=...) with the agentscope config classes but provider set to 'openai', 'anthropic', a typo like 'AgentScope', or None.

Common situations: Editing a copied mem0 config and forgetting to change provider; case mismatch after refactor.

Related errors

• f"Unsupported embedding provider: {provider}"
• "AgentScopeLLM requires `model` in the config to be an Agent
• f"AgentScopeLLM `model` must be a ChatModelBase, got {type(s
• "AgentScopeLLM received no usable messages (empty list or al
• "AgentScopeEmbedding requires `model` in the config to be an

AI-assisted analysis of agentscope-ai/agentscope@e90f1c7592 (2026-08-28). Data as JSON: /api/errors/53236addc7ab70ed. Report an issue: GitHub.