bytedance/deer-flow · error · ValueError

mem0 score_threshold must be in [0, 1]

Error message

mem0 score_threshold must be in [0, 1]

What it means

Raised by Mem0Config.from_backend_config when memory.backend_config.score_threshold is outside [0.0, 1.0] after float() coercion. The value maps to mem0's relevance threshold for search() results — memories scoring below it are filtered out — so it must be a probability-style fraction.

Source

Thrown at backend/packages/harness/deerflow/agents/memory/backends/mem0/config.py:105

            allow_insecure_http=allow_insecure_http,
            top_k=int(cfg.get("top_k", 8)),
            score_threshold=float(cfg.get("score_threshold", 0.1)),
            max_injection_chars=int(cfg.get("max_injection_chars", 12000)),
            timeout_seconds=float(cfg.get("timeout_seconds", 10.0)),
            startup_policy=str(cfg.get("startup_policy", "fail_fast")),
            read_policy=str(failure_policy.get("read", "fail_open")),
            write_policy=str(failure_policy.get("write", "log_and_drop")),
        )
        if config.startup_policy not in _STARTUP_POLICIES:
            raise ValueError(f"mem0 startup_policy must be one of {sorted(_STARTUP_POLICIES)}")
        if config.read_policy not in _READ_POLICIES:
            raise ValueError(f"mem0 failure_policy.read must be one of {sorted(_READ_POLICIES)}")
        if config.write_policy not in _WRITE_POLICIES:
            raise ValueError(f"mem0 failure_policy.write must be one of {sorted(_WRITE_POLICIES)}")
        if not 1 <= config.top_k <= 1000:
            raise ValueError("mem0 top_k must be in [1, 1000]")
        if not 0.0 <= config.score_threshold <= 1.0:
            raise ValueError("mem0 score_threshold must be in [0, 1]")
        if config.max_injection_chars <= 0:
            raise ValueError("mem0 max_injection_chars must be positive")
        if config.timeout_seconds <= 0:
            raise ValueError("mem0 timeout_seconds must be positive")
        if not config.api_key_env.strip():
            raise ValueError("mem0 api_key_env must be a non-empty env var name")
        parsed_base_url = urlsplit(config.base_url)
        if parsed_base_url.scheme not in {"http", "https"} or not parsed_base_url.netloc:
            raise ValueError("mem0 base_url must be an absolute http:// or https:// URL")
        if parsed_base_url.scheme == "http" and not config.allow_insecure_http:
            raise ValueError("mem0 base_url must use https:// because it carries the API key; set allow_insecure_http: true only for trusted local development")
        return config

    def resolve_api_key(self) -> str:
        """Read the API key from the configured environment variable."""
        key = os.environ.get(self.api_key_env, "").strip()
        if not key:
            raise ValueError(f"mem0 API key missing: environment variable {self.api_key_env} is unset or empty")

View on GitHub (pinned to 1dd6ba1acb)

Solutions

1. Express the threshold as a 0..1 fraction (default 0.1; e.g. 0.85 for 85%)
2. Raise it to reduce noisy memories, lower it toward 0.0 to admit more results
3. Divide any percent-style value by 100 before writing it into config

Example fix

# before (config.yaml)
memory:
  backend_config:
    score_threshold: 85   # percent scale -> out of range

# after
memory:
  backend_config:
    score_threshold: 0.85

def score_threshold_ok(backend_config: dict) -> bool:
    try:
        return 0.0 <= float((backend_config or {}).get("score_threshold", 0.1)) <= 1.0
    except (TypeError, ValueError):
        return False

def is_valid_score_threshold(v: object) -> bool:
    return isinstance(v, (int, float)) and not isinstance(v, bool) and 0.0 <= v <= 1.0

When it happens

Trigger: score_threshold: 10, score_threshold: -0.1, or score_threshold: 85 (using a 0-100 percent scale) in backend_config.

Common situations: Coming from systems where thresholds are expressed as percentages (0-100); copy-paste of a confidence value from another tool; sign typos.

Related errors

• mem0 top_k must be in [1, 1000]
• mem0 max_injection_chars must be positive
• mem0 backend_config has unknown keys: {sorted(unknown)}
• mem0 failure_policy must be a mapping {read, write}
• mem0 failure_policy has unknown keys: {sorted(unknown_fp)}

AI-assisted analysis of bytedance/deer-flow@1dd6ba1acb (2026-08-14). Data as JSON: /api/errors/13619aa0399d9837. Report an issue: GitHub.