feat(review): 新增确定性检查前置与结论结构化内核
- checks.py：确定性检查（find_zero_length / find_duplicate_entities 传 window + 纯 Python 派生空文字、未闭合多段线）。问题带 source=deterministic，handle 来自 工具/数据本身，不依赖 LLM 回忆 - findings.py：解析 LLM 的 JSON 结论 + handle 交叉校验（引用未知 handle 时保留问题、 剥掉 handle、verified=False）+ findings 装配 - config.py：新增 DETERMINISTIC_CHECKS / VALIDATE_HANDLES / CHECK_UNCLOSED_POLYLINES 开关与 ZERO_LENGTH_TOLERANCE / DUP_TOLERANCE / DUP_GROUP_LIMIT 实机验证：find_zero_length / find_duplicate_entities 的 window 参数在基座上生效 （schema 未声明，C++ 侧 parseCommonQuery 实际支持）。
This commit is contained in:
gjm committed
1 parent
a0ea902b50
commit
f6d61f8d07
6 files changed
+884
No files matched your search
@@ -0,0 +1,164 @@
|
||||
"""确定性检查：MCP 工具（find_zero_length / find_duplicate_entities）+ 纯 Python 派生。
|
||||
|
||||
产出的 issue 带 `source="deterministic"`，其 handle 来自工具/数据本身，
|
||||
因此被视为**可信**，可直接进入批注链路，不依赖 LLM 回忆。
|
||||
|
||||
注意：`find_zero_length` / `find_duplicate_entities` 的 `window` 参数在 C++ 侧
|
||||
（`parseCommonQuery`）**实际生效**，只是 JSON schema 未声明——Python 侧显式传参即可。
|
||||
"""
|
||||
|
||||
from . import config
|
||||
from .mcp_client import McpError, McpToolError, result_json
|
||||
|
||||
|
||||
def make_issue(category, severity, message, *, handle=None, handles=None,
|
||||
source="deterministic"):
|
||||
"""构造统一 issue（`verified` 由 findings 层补齐）。"""
|
||||
issue = {
|
||||
"category": category,
|
||||
"severity": severity,
|
||||
"message": message,
|
||||
"source": source,
|
||||
}
|
||||
if handle:
|
||||
issue["handle"] = handle
|
||||
if handles:
|
||||
issue["handles"] = list(handles)
|
||||
return issue
|
||||
|
||||
|
||||
def _iter_items(envelope):
|
||||
"""健壮迭代 items（`result_json` 解析失败会返回原始字符串）。"""
|
||||
if not isinstance(envelope, dict):
|
||||
return []
|
||||
items = envelope.get("items")
|
||||
if not isinstance(items, list):
|
||||
return []
|
||||
return [i for i in items if isinstance(i, dict)]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# MCP 检查
|
||||
# ---------------------------------------------------------------------------
|
||||
def check_zero_length(ctx, window, *, tolerance, limit, log=print):
|
||||
"""find_zero_length(window) → 逐条零长度实体转 issue。"""
|
||||
try:
|
||||
resp = ctx.tools.call(
|
||||
"find_zero_length",
|
||||
{"window": window, "tolerance": tolerance, "limit": limit},
|
||||
)
|
||||
except (McpError, McpToolError) as exc:
|
||||
log(f" [确定性] find_zero_length 失败: {exc}")
|
||||
return []
|
||||
|
||||
out = []
|
||||
for item in _iter_items(result_json(resp, {})):
|
||||
handle = item.get("handle")
|
||||
if not handle:
|
||||
continue
|
||||
out.append(
|
||||
make_issue(
|
||||
"几何", "medium",
|
||||
f"零长度/退化实体（类型 {item.get('type')}，长度 {item.get('length')}）",
|
||||
handle=handle,
|
||||
)
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def check_duplicate_entities(ctx, window, *, tolerance, group_limit, log=print):
|
||||
"""find_duplicate_entities(window) → 每个重复组一条 issue。
|
||||
|
||||
`limit` 的语义是「最大重复组数」（非条目数）。一组重复是一个问题，
|
||||
故只产出一条 issue，主 handle 取组内首个，全部 handle 放进 `handles`。
|
||||
"""
|
||||
try:
|
||||
resp = ctx.tools.call(
|
||||
"find_duplicate_entities",
|
||||
{"window": window, "tolerance": tolerance, "limit": group_limit},
|
||||
)
|
||||
except (McpError, McpToolError) as exc:
|
||||
log(f" [确定性] find_duplicate_entities 失败: {exc}")
|
||||
return []
|
||||
|
||||
env = result_json(resp, {})
|
||||
groups = env.get("groups") if isinstance(env, dict) else None
|
||||
out = []
|
||||
for group in groups or []:
|
||||
if not isinstance(group, dict):
|
||||
continue
|
||||
handles = [h for h in (group.get("handles") or []) if h]
|
||||
if not handles:
|
||||
continue
|
||||
out.append(
|
||||
make_issue(
|
||||
"几何", "low",
|
||||
f"重复/重叠实体组（类型 {group.get('type')}，共 {len(handles)} 个几何相同）",
|
||||
handle=handles[0],
|
||||
handles=handles,
|
||||
)
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 纯 Python 派生（零额外 MCP 往返）
|
||||
# ---------------------------------------------------------------------------
|
||||
def _empty_texts(evidence):
|
||||
out = []
|
||||
for item in _iter_items(evidence.get("texts")):
|
||||
content = item.get("content")
|
||||
if content is None or str(content).strip() == "":
|
||||
out.append(
|
||||
make_issue("文字", "medium", "存在空文字或仅含空格的文字",
|
||||
handle=item.get("handle"))
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def _unclosed_polylines(evidence):
|
||||
out = []
|
||||
for item in _iter_items(evidence.get("polylines")):
|
||||
if item.get("vertex_count", 0) >= 3 and item.get("closed") is False:
|
||||
out.append(
|
||||
make_issue("几何", "low",
|
||||
"多段线顶点≥3但未闭合，可能是应当闭合的轮廓",
|
||||
handle=item.get("handle"))
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def derive_from_evidence(evidence, *, check_unclosed=True):
|
||||
"""从已采集证据里做零成本派生检查。"""
|
||||
issues = _empty_texts(evidence)
|
||||
if check_unclosed:
|
||||
issues += _unclosed_polylines(evidence)
|
||||
return issues
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 入口
|
||||
# ---------------------------------------------------------------------------
|
||||
def run_deterministic_checks(ctx, evidence, *, log=print):
|
||||
"""对单个图框跑全部确定性检查，返回 issue 列表。
|
||||
|
||||
任何单项 MCP 失败都只记录并跳过，不抛出（不拖垮该图框）。
|
||||
"""
|
||||
issues = derive_from_evidence(
|
||||
evidence, check_unclosed=config.CHECK_UNCLOSED_POLYLINES
|
||||
)
|
||||
window = evidence.get("window")
|
||||
if window:
|
||||
issues += check_zero_length(
|
||||
ctx, window,
|
||||
tolerance=config.ZERO_LENGTH_TOLERANCE,
|
||||
limit=config.FRAME_ENTITY_LIMIT,
|
||||
log=log,
|
||||
)
|
||||
issues += check_duplicate_entities(
|
||||
ctx, window,
|
||||
tolerance=config.DUP_TOLERANCE,
|
||||
group_limit=config.DUP_GROUP_LIMIT,
|
||||
log=log,
|
||||
)
|
||||
return issues
|
||||
Reference in new issue
Block a user