fix: patch checks full target span + marker injection/integrity (algo #8)

This commit is contained in:
2026-07-16 06:20:29 -04:00
parent caea9150b3
commit 65126feada
4 changed files with 178 additions and 7 deletions
+43 -7
View File
@@ -282,9 +282,34 @@ def _protected_ranges(content: str, spans: list[str]) -> list[tuple[int, int]]:
return ranges
def _in_ranges(pos: int, ranges: list[tuple[int, int]]) -> bool:
"""判断位置 pos 是否落在任意冻结区间内。"""
return any(start <= pos < end for start, end in ranges)
def _span_overlaps_ranges(pos: int, length: int, ranges: list[tuple[int, int]]) -> bool:
"""判断 [pos, pos+length) 是否与任一冻结区间相交(不止起点)。
起点落在正文、末端伸入冻结区的 target 也须拦截,否则 replace/delete 会连带
改动冻结区(如破坏 appendix/momentum marker)。
参数:
pos: target 在正文中的起点。
length: target 长度。
ranges: 冻结区间 [start, end) 列表。
返回:
与任一区间相交返回 True。
"""
end = pos + length
return any(start < end and pos < r_end for start, r_end in ranges)
# 冻结区 marker 字面量:LLM 生成的 edit 不得注入这些字面量,否则破坏 marker 配对
_MARKER_LITERALS = (APPENDIX_START, APPENDIX_END, MOMENTUM_START, MOMENTUM_END)
def _edit_injects_marker(edit: dict) -> bool:
"""判断 edit 的 target/content 是否含冻结区 marker 字面量(注入拦截)。"""
for key in ("target", "content"):
value = edit.get(key)
if isinstance(value, str) and any(m in value for m in _MARKER_LITERALS):
return True
return False
def _append_at(content: str, ranges: list[tuple[int, int]]) -> int:
@@ -317,8 +342,8 @@ def _do_insert_after(
_insert_at(content, _append_at(content, ranges), payload),
"applied_insert_after_fallback",
)
if _in_ranges(pos, ranges):
logger.warning("insert_after 目标冻结区,跳过 target={}", target[:80])
if _span_overlaps_ranges(pos, len(target), ranges):
logger.warning("insert_after 目标跨入冻结区,跳过 target={}", target[:80])
return content, "skipped_protected"
at = pos + len(target)
nl = content.find("\n", at)
@@ -340,8 +365,8 @@ def _do_replace_delete(
if pos == -1:
logger.warning("{} 锚点缺失,跳过 target={}", op, target[:80])
return content, "skipped_target_not_found"
if _in_ranges(pos, ranges):
logger.warning("{} 目标冻结区,跳过 target={}", op, target[:80])
if _span_overlaps_ranges(pos, len(target), ranges):
logger.warning("{} 目标跨入冻结区,跳过 target={}", op, target[:80])
return content, "skipped_protected"
new_content = content.replace(target, payload if op == "replace" else "", 1)
return new_content, "applied_" + op
@@ -403,6 +428,17 @@ def apply_patch_with_report(
reports: list[dict] = []
for i, edit in enumerate(edits, 1):
try:
if isinstance(edit, dict) and _edit_injects_marker(edit):
logger.warning("edit 含冻结区 marker 字面量,拒绝该 edit index={}", i)
report = {
"op": str(edit.get("op", "")),
"target": str(edit.get("target", "") or "")[:200],
"content_preview": str(edit.get("content", "") or "")[:200],
"status": "skipped_marker_injection",
}
report["index"] = i
reports.append(report)
continue
ranges = _protected_ranges(content, spans)
content, report = _apply_one(content, edit, ranges)
except (KeyError, TypeError, ValueError, AttributeError) as exc: