datawhalechina/hello-agents · error · ValueError

Unsupported reviewer mode: {review_mode}

Error message

Unsupported reviewer mode: {review_mode}

What it means

build_reviewer_prompt accepts only the reviewer modes "standard" and "publication"; any other string (after strip+lowercase) raises ValueError. The mode selects the reviewer persona and checklist used to critique analysis reports, so an unknown mode has no prompt template to return.

Source

Thrown at Co-creation-projects/healer-666-Academic-Data-Agent/src/data_analysis_agent/prompts.py:193

  - 数据概览
  - 方法说明
  - 统计学治理说明
  - 核心假设检验结论
  - 结果解释
  - 讨论
  - 清洗后数据路径
  - 图表引用 such as ![图表]({figures_dir}/chart.png)
  - If any hypothesis test was run, the report must include the test statistic, p-value, effect size, and 95% CI together.
  - If more than two groups were compared pairwise, the report must state the multiple-comparison correction method explicitly.
"""


def build_reviewer_prompt(review_mode: str, *, focus_major_issues: bool = False) -> str:
    """Return the system prompt for the reviewer agent."""

    normalized_mode = review_mode.strip().lower()
    if normalized_mode not in {"standard", "publication"}:
        raise ValueError(f"Unsupported reviewer mode: {review_mode}")

    if normalized_mode == "publication":
        reviewer_role = "You are an exceptionally strict reviewer from a top-tier journal ecosystem such as Nature, Science, or Cell."
        checklist = """Review checklist:
- Verify that figure references are present, coherent, and point to this run's actual figure paths.
- If Generated artifacts evidence confirms that figures were saved in this run and artifact validation is green, do not reject solely because the compressed execution trace omits plotting details.
- Verify that any hypothesis test is reported with the test statistic, p-value, effect size, and 95% CI together.
- Verify that multi-group pairwise comparisons explicitly mention Bonferroni correction or Tukey HSD when required.
- Verify that the report does not confuse correlation with causation.
- Verify that there are no obvious logical leaps, implausible claims, over-interpretation relative to the sample size, or conclusions that contradict the execution trace.
- Verify that the report does not cite files, figures, or cleaned-data paths outside the current run directory contract.
- Verify that the chosen methods match the data structure, including dependency, repeated measures, or time-series risks when present.
"""
        decision_policy = """Decision policy:
- Return "Accept" only if the report is publication-grade, internally coherent, statistically defensible, and adequately grounded in the supplied evidence.
- Return "Reject" if any major statistical, logical, citation, artifact, or interpretation issue remains.
- You must not invent new results, new p-values, or new evidence that does not appear in the candidate report or the supplied review context.
"""

View on GitHub (pinned to 606a07d341)

Solutions

1. Use one of the two supported literals: "standard" or "publication" (case/whitespace insensitive).
2. Validate/whitelist the mode at the API or config boundary before it reaches the prompt builder.
3. Check for typos in the config key carrying the mode (e.g. review_mode vs reviewer_mode).
4. If you need a new mode, add it to the {"standard", "publication"} set in prompts.py and supply its checklist.

Example fix

# before
prompt = build_reviewer_prompt(review_mode=requested_mode)  # may raise

# after
ALLOWED_MODES = {"standard", "publication"}
mode = requested_mode.strip().lower()
if mode not in ALLOWED_MODES:
    raise ValueError(f"review_mode must be one of {sorted(ALLOWED_MODES)}, got '{requested_mode}'")
prompt = build_reviewer_prompt(review_mode=mode)

ALLOWED_REVIEW_MODES = {"standard", "publication"}
mode = raw_mode.strip().lower()
if mode not in ALLOWED_REVIEW_MODES:
    raise ValueError(f"review_mode must be one of {sorted(ALLOWED_REVIEW_MODES)}, got {raw_mode!r}")
prompt = build_reviewer_prompt(review_mode=mode)

def is_valid_review_mode(mode: str) -> bool:
    return isinstance(mode, str) and mode.strip().lower() in {"standard", "publication"}

try:
    prompt = build_reviewer_prompt(review_mode=mode)
except ValueError:
    prompt = build_reviewer_prompt(review_mode="standard")  # explicit fallback, logged

When it happens

Trigger: Calling build_reviewer_prompt(review_mode="strict"), "fast", "Publication " (works, normalized) vs. typo'd values like "pubilcation", or passing a user-supplied config value that was never validated upstream.

Common situations: Typos in configuration files or CLI flags; new reviewer modes expected by callers after a version change; user-facing UI letting free-text mode input through to the prompt builder.

Related errors

• Unsupported latency_mode: {latency_mode}
• Unsupported vision_review_mode: {vision_review_mode}
• Unsupported quality_mode: {quality_mode}
• Unsupported document_ingestion_mode: {mode}
• {name} 必须是数字

AI-assisted analysis of datawhalechina/hello-agents@606a07d341 (2026-08-14). Data as JSON: /api/errors/8cbcc02a4c5eb1b5. Report an issue: GitHub.