datawhalechina/hello-agents · error · ConfigurationError

LLM_TIMEOUT 必须大于 0

Error message

LLM_TIMEOUT 必须大于 0

What it means

Raised by LLMSettings validation when LLM_TIMEOUT is <= 0. A non-positive timeout would make every request fail immediately or behave undefined, so it is rejected up front. Note the type check happens earlier: a non-integer string raises '必须是整数' first; this error means the value parsed fine but is 0 or negative.

Source

Thrown at Co-creation-projects/zenith191-RequirementClarifierAgent/src/config.py:80

            for name, value in (
                ("LLM_MODEL_ID", self.model),
                ("LLM_API_KEY", self.api_key),
                ("LLM_BASE_URL", self.base_url),
            )
            if not value
        ]
        if missing:
            raise ConfigurationError(
                "缺少 LLM 配置：" + ", ".join(missing) + "。请先复制并填写 .env。"
            )

        lowered_key = self.api_key.casefold()
        if lowered_key.startswith("your_") or lowered_key in {"changeme", "replace_me"}:
            raise ConfigurationError("LLM_API_KEY 仍是占位符，请在 .env 中填写真实密钥")
        if not 0 <= self.temperature <= 2:
            raise ConfigurationError("LLM_TEMPERATURE 必须位于 0 到 2 之间")
        if self.timeout <= 0:
            raise ConfigurationError("LLM_TIMEOUT 必须大于 0")

View on GitHub (pinned to 606a07d341)

Solutions

1. Set a positive integer of seconds, e.g. LLM_TIMEOUT=120 (the default).
2. For long LLM calls, raise it (e.g. 300) rather than zeroing it — this config has no 'infinite' mode.
3. Remove the variable to accept the default 120.

Example fix

# .env before
LLM_TIMEOUT=0

# .env after
LLM_TIMEOUT=120

import os

timeout = int(os.getenv("LLM_TIMEOUT", "120"))
if timeout <= 0:
    raise SystemExit("LLM_TIMEOUT must be a positive integer of seconds")

try:
    settings = LLMSettings.from_env()
except ConfigurationError as e:
    if "TIMEOUT" in str(e):
        os.environ.pop("LLM_TIMEOUT", None)  # fall back to default 120
        settings = LLMSettings.from_env()
    else:
        raise

When it happens

Trigger: Setting LLM_TIMEOUT=0 (sometimes done to mean 'no timeout'), LLM_TIMEOUT=-1 copied from a socket-timeout convention, or passing timeout=0 programmatically.

Common situations: Developer intends 'disable timeout' and uses 0 or -1 as in other libraries; CI env carries a negative test value; misreading units (0 seconds vs 0 minutes).

Understand the failure class

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• Unsupported latency_mode: {latency_mode}
• Unsupported vision_review_mode: {vision_review_mode}
• Unsupported quality_mode: {quality_mode}
• Unsupported document_ingestion_mode: {mode}
• Unsupported reviewer mode: {review_mode}

AI-assisted analysis of datawhalechina/hello-agents@606a07d341 (2026-08-14). Data as JSON: /api/errors/51fbe256f2c481b3. Report an issue: GitHub.