Back to Details

hunt-regressions

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Discover candidates

发现候选项

When to Use

何时使用

Input: sealed preparation, frozen S0/S1, change context and registry assignment. On retry, include this assignment's prior candidate-ID mapping. The caller supplies these, including for independent use. Follow project guidance before target work.
输入：已封存的准备材料、冻结的 S0/S1、变更上下文和注册表分配结果。 重试时，包含本次任务先前的候选项 ID 映射。调用方会提供这些内容， 包括独立使用时所需的信息。 开始目标工作前，遵循项目指导。

When NOT to Use

何时不要使用

Proving a known candidate; use reproduction. Discovery cannot confirm findings.
证明已知候选项；请使用复现。发现阶段无法确认发现结果。

Hunt

排查

  1. Read the standard and file contract. Verify preparation; read frozen change messages, PR discussion and security documentation for intent and supported use.
  2. Review the entire diff; trace changed behavior through callers to real interfaces. Use frozen sources and supplied context, not later fixes, advisories or other reviews.
  3. Record each lead's changed code, previously supported behavior, reachable trigger, proposed new defect, false-positive checks and required proof. Retain supplied leads suggesting old bugs or incomplete fixes for adjudication. Leave PoC construction to reproduction.
  4. Reserve each lead's ID through registry.py 
    candidate
    using its stable hypothesis key and assigned agent handle. Reuse the key on retry. Write candidate files and 
    hunt.json
    with IDs, file mappings, coverage and limitations. An empty list is valid. If blocked, record partial coverage and uninspected areas. Seal the package.
  1. 阅读标准和 文件契约。验证准备情况；读取冻结的变更消息、 PR 讨论和安全文档，以了解意图和受支持的用法。
  2. 审查完整的 diff；通过调用方将变更后的行为追踪至真实接口。 使用冻结的源代码和提供的上下文，而非后续修复、安全公告或其他审查结果。
  3. 记录每条线索的变更代码、此前受支持的行为、可达触发条件、 拟议的新缺陷、误报检查和所需证据。保留所提供的、暗示旧有缺陷或 修复不完整的线索，以供裁定。将 PoC 构建留给复现阶段。
  4. 通过 registry.py 的 
    candidate
    使用每条线索稳定的假设键和已分配的 Agent handle，预留其 ID。 重试时复用该键。编写候选文件及 
    hunt.json
    ，其中包含 ID、文件映射、 覆盖情况和限制说明。空列表也是有效结果。 如果受阻，记录部分覆盖范围和未检查区域。封存该包。

Report Back

回报结果

Keep detailed evidence in the sealed package. Return only:
  • Status: 
    complete
    or 
    blocked
    , matching the record.
  • Record: sealed 
    hunt.json
    path, or why none was produced.
  • Result: candidate count and material coverage gaps.
  • Blocker: missing prerequisite or required caller action, if blocked.
将详细证据保留在已封存的包中。仅返回：
  • 状态：
    complete
    或 
    blocked
    ，与记录一致。
  • 记录：已封存的 
    hunt.json
    路径，或未生成记录的原因。
  • 结果：候选项数量和实质性覆盖缺口。
  • 阻碍因素：如被阻塞，列出缺失的前置条件或调用方所需采取的操作。

Rationalizations to Reject

应拒绝的理由

  • “A helper fails on invented input”: show a supported interface that reaches it.
  • “某个辅助函数在虚构输入上失败”：必须给出一个能够到达该辅助函数的受支持接口。