Repair one independently confirmed local bug by addressing the rule the code violates and checking related variants within scope. Deliver regression tests, before and after test results, separate patch files, and one local commit.
中文简介正在准备中。当前显示英语简介。
Use when a confirmed local bug needs an invariant-level fix, variant search, tests, and one local commit.
安装前可以查看交给 AI 代理的指令内容。
Use after independent validation confirms one claim. Read the record contract. Before target commands, follow its project guidance.
Do not use for speculative bug hunting, proof of a completed patch, or a change that cannot be exercised by the local compiler or runtime.
Before editing, run uv run --no-project <script> check --before-repair <run-dir>
with the record validator. If this check fails,
stop and return its errors for an INCONCLUSIVE report. The gate requires
finding.repair_scope with a usable case plan and a consistent attempt count.
Use the declared scope as the repair brief. Identify the broken
invariant and search within its boundary for every instance of the
same violation. Read the threat model only to preserve intended behavior; it is
not a gate.
Run the project's existing suite and record its results. Write a regression test that fails on the baseline for the named bug and any fixed variant. Observe the failure. Fix the invariant within the repair brief with the smallest reviewable change.
Run the regression test and full existing suite again. Compare before and after failures. Fix new failures or explain a pre-existing one from receipts.
Record every variant as fixed or not_fixed with a reason. Produce exactly one
local commit. Never push or open a PR. From the baseline, write fix.patch for
production changes and tests.patch for test changes in patch/attempt-N/.
Write patch.json with the two commit SHAs, changed-file and line counts,
variants, suite results, and your agent identity. If the attempt produced no commit,
record patch_commit: null and return it as failed. Manifest the entire attempt
directory, including both patch files and the record, using
uv run --no-project <script> manifest <patch-attempt-dir>. Check it with the
record validator.
{
"schema_version": 1,
"attempt": 1,
"baseline_commit": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
"patch_commit": "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
"files_changed": 2,
"lines_added": 3,
"lines_removed": 1,
"variants": [],
"suite_before": {"command": "pytest", "passed": 9, "failed": 1, "skipped": 0},
"suite_after": {"command": "pytest", "passed": 10, "failed": 0, "skipped": 0},
"agent": "patcher-1"
}
| Shortcut | Required action |
|---|---|
| Only the reported line matters. | Search for the same invariant violation. |
| Minimal means the fewest lines. | Make the smallest reviewable invariant-level fix. |
| Tests pass after the patch. | Show the regression test failed before it. |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Build and test code with AddressSanitizer, a tool that detects invalid memory access during execution. Configure checks for C/C++ and unsafe Rust, investigate crash reports, and adjust settings for fuzzing, or testing with generated inputs.
中文简介正在准备中。当前显示英语简介。
Assess source code and live reproduction evidence to decide whether a change introduced a regression, a newly caused defect. Record supported conclusions, exclusions, severity, and unresolved gaps in an evidence-linked decision file.
中文简介正在准备中。当前显示英语简介。
Sets up AFL++ to test C/C++ programs with varied generated inputs, a technique called fuzzing. Covers running tests across CPU cores, monitoring progress, reducing input collections, and reproducing crashes for investigation.
中文简介正在准备中。当前显示英语简介。
Audits GitHub Actions workflows that run AI coding agents. Traces how attacker-controlled content reaches prompts, checks permissions and sandbox settings, and reports evidence, severity, and fixes for prompt injection and related configuration risks.
中文简介正在准备中。当前显示英语简介。
Reviews Algorand smart contracts written in TEAL or PyTeal for 11 vulnerability patterns. Produces a complete coverage table and findings with code references, severity ratings, and suggested fixes, with optional automated checks using Tealer.
中文简介正在准备中。当前显示英语简介。
Set up Atheris to test Python code and C extensions with automatically varied inputs. It guides test harness creation, coverage tracking to explore more code, and AddressSanitizer setup for finding memory errors.
中文简介正在准备中。当前显示英语简介。