bytedance/deer-flow · error · ValueError

fact.source.type must be a string

Error message

fact.source.type must be a string

What it means

When fact['source'] is a dict, its 'type' member (defaulting to 'unknown') must be a str; a non-string type (int, list, dict) raises ValueError. String sources are auto-converted to {'type': ..., 'threadId': ...}, so this error only fires for dict sources with a bad type value.

Source

Thrown at backend/packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/storage.py:224

    normalized["status"] = "active"
    normalized["scope"] = copy.deepcopy(scope)
    _require_string_list(normalized, "topics")
    _require_string_list(normalized, "consolidatedFrom")
    revision = normalized.get("revision", 1)
    if isinstance(revision, bool) or not isinstance(revision, int) or revision < 1:
        raise ValueError("fact.revision must be an integer >= 1")
    source = normalized.get("source")
    if isinstance(source, str):
        if source in {"manual", "consolidation", "import", "unknown"}:
            normalized["source"] = {"type": source, "threadId": None}
        else:
            normalized["source"] = {"type": "conversation", "threadId": source}
    elif not isinstance(source, dict):
        normalized["source"] = {"type": "unknown", "threadId": None}
    else:
        normalized["source"].setdefault("type", "unknown")
        if not isinstance(normalized["source"].get("type"), str):
            raise ValueError("fact.source.type must be a string")
        if normalized["source"].get("threadId") is not None and not isinstance(normalized["source"].get("threadId"), str):
            raise ValueError("fact.source.threadId must be a string or null")
    normalized["title"] = _fact_title(normalized)
    now = utc_now_iso_z()
    if existing is None:
        normalized.setdefault("createdAt", now)
        normalized.setdefault("updatedAt", normalized["createdAt"])
        normalized["revision"] = revision
    else:
        existing_revision = existing.get("revision")
        if not isinstance(existing_revision, int) or existing_revision < 1:
            raise MemoryStorageCorruption(f"Stored fact {normalized['id']!r} has an invalid revision")
        if revision != existing_revision:
            raise MemoryFactRevisionConflict(f"Expected fact {normalized['id']!r} revision {revision}, found {existing_revision}")
        normalized["createdAt"] = existing.get("createdAt") or normalized.get("createdAt") or now
        comparison_keys = {"revision", "updatedAt"}
        incoming_material = {key: value for key, value in normalized.items() if key not in comparison_keys}
        existing_material = {key: value for key, value in existing.items() if key not in comparison_keys}

View on GitHub (pinned to 1dd6ba1acb)

Solutions

1. Set source as a plain string ('manual' | 'consolidation' | 'import' | 'unknown' or a thread id) and let the backend normalize it.
2. If using the dict form, ensure source['type'] is a str literal from the documented set.
3. Validate imported source dicts with a type guard before saving.

Example fix

# before
memory.save_fact({"content": "...", "source": {"type": 3, "threadId": None}})
# after
memory.save_fact({"content": "...", "source": {"type": "manual", "threadId": None}})

src = fact.get("source")
if isinstance(src, dict):
    t = src.get("type", "unknown")
    src["type"] = t if isinstance(t, str) else str(t)
elif src is not None and not isinstance(src, str):
    fact["source"] = "unknown"

def has_valid_source_type(fact: dict) -> bool:
    src = fact.get("source")
    return not isinstance(src, dict) or isinstance(src.get("type", "unknown"), str)

When it happens

Trigger: Saving {'source': {'type': 1}}, {'source': {'type': ['manual']}}, or a source dict built from unvalidated import JSON.

Common situations: Imports mapping a numeric source enum into type; producers nesting the wrong object; LLM tool output with structured source objects of mixed types.

Related errors

• fact.category must be a string
• fact.{field} must be a list of strings
• fact.content must be a string
• fact.source.threadId must be a string or null
• retrieval fact.id must be a non-empty string

AI-assisted analysis of bytedance/deer-flow@1dd6ba1acb (2026-08-14). Data as JSON: /api/errors/935bfdda0bb168ac. Report an issue: GitHub.