OpenBMB/ChatDev · error · ConfigError

memories must be a list

Error message

memories must be a list

What it means

The 'memories' key of an agent model config is present and non-null but is not a list. Memories are parsed as a list of MemoryAttachmentConfig entries; any other shape is rejected before item parsing begins.

Source

Thrown at entity/configs/node/agent.py:384

        tooling_cfg: List[ToolingConfig] = []
        if "tooling" in mapping and mapping["tooling"] is not None:
            raw_tooling = mapping["tooling"]
            if not isinstance(raw_tooling, list):
                 raise ConfigError("tooling must be a list", extend_path(path, "tooling"))
            for idx, item in enumerate(raw_tooling):
                tooling_cfg.append(
                    ToolingConfig.from_dict(item, path=extend_path(path, f"tooling[{idx}]"))
                )

        thinking_cfg = None
        if "thinking" in mapping and mapping["thinking"] is not None:
            thinking_cfg = ThinkingConfig.from_dict(mapping["thinking"], path=extend_path(path, "thinking"))

        memories_cfg: List[MemoryAttachmentConfig] = []
        if "memories" in mapping and mapping["memories"] is not None:
            raw_memories = mapping["memories"]
            if not isinstance(raw_memories, list):
                raise ConfigError("memories must be a list", extend_path(path, "memories"))
            for idx, item in enumerate(raw_memories):
                memories_cfg.append(
                    MemoryAttachmentConfig.from_dict(item, path=extend_path(path, f"memories[{idx}]"))
                )

        retry_cfg = None
        if "retry" in mapping and mapping["retry"] is not None:
            retry_cfg = AgentRetryConfig.from_dict(mapping["retry"], path=extend_path(path, "retry"))

        skills_cfg = None
        if "skills" in mapping and mapping["skills"] is not None:
            skills_cfg = AgentSkillsConfig.from_dict(mapping["skills"], path=extend_path(path, "skills"))

        return cls(
            provider=provider,
            base_url=base_url,
            name=model_name,
            role=role,

View on GitHub (pinned to 4fb2db0ea9)

Solutions

1. Wrap the attachment in a list: "memories": [{...}]
2. Check YAML list syntax (dash items) under 'memories'
3. Omit 'memories' or set null if no memory attachments are wanted

Example fix

// before
"memories": {"memory_id": "m1"}
// after
"memories": [{"memory_id": "m1"}]

memories = cfg.get('model', {}).get('memories')
if memories is not None and not isinstance(memories, list):
    cfg['model']['memories'] = [memories]

def has_list_memories(cfg: dict) -> bool:
    m = cfg.get('model', {}).get('memories')
    return m is None or isinstance(m, list)

try:
    ModelConfig.from_dict(data, path='agent')
except ConfigError as e:
    if 'memories' in e.path and isinstance(data['model'].get('memories'), dict):
        data['model']['memories'] = [data['model']['memories']]
        ModelConfig.from_dict(data, path='agent')
    else:
        raise

When it happens

Trigger: Passing memories as a single dict (one attachment not wrapped in a list), a string, or other non-list value. Absent/null 'memories' skips validation entirely.

Common situations: Same single-object-vs-list mistake as tooling; YAML indentation that makes 'memories' a mapping instead of a sequence.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• model.name must be a non-empty string
• model.input_mode must be 'prompt' or 'messages'
• tooling must be a list
• file_types entries must be strings
• recursive must be boolean

AI-assisted analysis of OpenBMB/ChatDev@4fb2db0ea9 (2026-08-27). Data as JSON: /api/errors/e89eeb3bae4d53da. Report an issue: GitHub.