cc-os/plugins/os-doc-hygiene/scripts/calibrate_helpers.py

333 lines
12 KiB
Python

"""
calibrate_helpers.py — deterministic helpers for the `:calibrate` skill
(lifecycle-aware-doc-hygiene change, task 5.4).
Stdlib-only, no model. Three responsibilities, each a small
single-responsibility class taking injected inputs and returning
JSON-serializable output:
1. `ClusterSampler` — groups unmatched paths by path-shape (directory
prefix + a filename "shape class" where digit runs -> `#` and hex-looking
runs -> `~`) and emits capped representative samples per cluster.
2. `RuleReportBuilder` — given proposed rules (glob + lifetime) and the
repo's file list, assembles the 5-element rule-report data: glob
verbatim, matched paths (capped sample + total), near-miss boundary
paths, lifetime/tier, and a `why` placeholder the caller fills in.
3. `RuleQualityChecker` — deterministic lint: `class_not_path` (flags globs
whose filename segment looks instance-unique: long digit runs, hex
hashes, bare timestamps, or a wildcard-free glob matching exactly one
existing path) and `prefer_narrower` (compares two candidate globs by
match-count on the actual tree; the narrower one wins ties).
None of these classes call an LLM, read history, or touch git. They operate
purely on lists of strings (paths) handed in by the orchestrating skill.
"""
from __future__ import annotations
import fnmatch
import re
from dataclasses import dataclass, field
from pathlib import PurePosixPath
from typing import Optional
_DEFAULT_SAMPLE_CAP = 5
# --- shape-class helpers ---------------------------------------------------
_DIGIT_RUN = re.compile(r"\d+")
# hex run: 6+ consecutive hex chars (avoids false-triggering on short words)
_HEX_RUN = re.compile(r"(?<![0-9a-fA-F])[0-9a-fA-F]{6,}(?![0-9a-fA-F])")
# "instance-unique" detectors used by both shape-classing and rule-quality
# lints: a long digit run (8+, e.g. a timestamp or run-id), or a hex run
# (6+ chars, e.g. a git sha / hash).
_LONG_DIGIT_RUN = re.compile(r"\d{6,}")
def _filename_shape(name: str) -> str:
"""Collapse a filename into a shape class: digit runs -> '#', hex runs
(6+ hex chars) -> '~'. Order matters: hex collapse first (a hex run may
contain digits that would otherwise be independently collapsed)."""
shaped = _HEX_RUN.sub("~", name)
shaped = _DIGIT_RUN.sub("#", shaped)
return shaped
def _dir_prefix(path: str) -> str:
parts = PurePosixPath(path).parts[:-1]
return "/".join(parts)
@dataclass
class Cluster:
key: str # "<dir_prefix>::<shape>"
dir_prefix: str
shape: str
paths: list # all paths in this cluster, sorted
sample: list # capped representative sample
@property
def total(self) -> int:
return len(self.paths)
def to_dict(self) -> dict:
return {
"key": self.key,
"dir_prefix": self.dir_prefix,
"shape": self.shape,
"total": self.total,
"sample": list(self.sample),
}
class ClusterSampler:
"""Groups unmatched paths by path-shape (directory prefix + filename
shape class) and emits per-cluster representative samples, capped."""
def __init__(self, sample_cap: int = _DEFAULT_SAMPLE_CAP) -> None:
self._cap = sample_cap
def cluster(self, unmatched_paths: list) -> list:
"""Returns a list of Cluster, sorted by cluster key for determinism.
Each cluster groups paths sharing the same directory prefix AND the
same filename shape class."""
groups: dict = {}
for path in unmatched_paths:
dir_prefix = _dir_prefix(path)
filename = PurePosixPath(path).name
shape = _filename_shape(filename)
key = f"{dir_prefix}::{shape}"
groups.setdefault(key, []).append(path)
clusters = []
for key in sorted(groups.keys()):
paths = sorted(groups[key])
dir_prefix, shape = key.split("::", 1)
clusters.append(
Cluster(
key=key,
dir_prefix=dir_prefix,
shape=shape,
paths=paths,
sample=paths[: self._cap],
)
)
return clusters
def cluster_to_dicts(self, unmatched_paths: list) -> list:
return [c.to_dict() for c in self.cluster(unmatched_paths)]
# --- rule report assembly ---------------------------------------------------
def _glob_matches(glob_pattern: str, path: str) -> bool:
return fnmatch.fnmatch(path, glob_pattern)
def _relax_glob(glob_pattern: str) -> Optional[str]:
"""Produce a strictly broader variant of a glob for near-miss detection.
Widens every path segment that already contains a wildcard character to
a bare '*' (fully generic for that segment), preserving fixed segments
and the final segment's extension when present. This surfaces exactly
the #45 boundary-bug class: a glob like `autoresearch/classic-*/` that
silently misses a sibling `autoresearch/improve-*/` — relaxing the
`classic-*` segment to `*` reveals the sibling as a near-miss.
Returns None if no segment has a wildcard to relax (fully-fixed glob has
no meaningful near-miss boundary)."""
parts = glob_pattern.split("/")
if not parts:
return None
relaxed_parts = list(parts)
changed = False
for i, part in enumerate(parts):
if part in ("*", "**"):
continue # already fully generic
if any(ch in part for ch in "*?[") :
if "." in part:
stem, _, ext = part.rpartition(".")
relaxed = "*." + ext
else:
relaxed = "*"
if relaxed != part:
relaxed_parts[i] = relaxed
changed = True
if not changed:
return None
return "/".join(relaxed_parts)
@dataclass
class RuleReportEntry:
glob: str
lifetime: str
tier: str
matched_sample: list
matched_total: int
near_miss: list
why: str = ""
def to_dict(self) -> dict:
return {
"glob": self.glob,
"lifetime": self.lifetime,
"tier": self.tier,
"matches": {
"sample": list(self.matched_sample),
"total": self.matched_total,
},
"near_miss": list(self.near_miss),
"why": self.why,
}
class RuleReportBuilder:
"""Given proposed rules and the repo's file list, produces the 5-element
rule-report data per proposed rule: glob verbatim, matched paths (capped
sample + total), near-miss boundary, lifetime + tier, and a why string
(caller-supplied; this class does not author prose)."""
def __init__(self, sample_cap: int = _DEFAULT_SAMPLE_CAP) -> None:
self._cap = sample_cap
def build(self, proposed_rule: dict, all_paths: list) -> RuleReportEntry:
glob_pattern = proposed_rule["glob"]
lifetime = proposed_rule.get("lifetime", "keep")
tier = proposed_rule.get("tier", "confirm")
why = proposed_rule.get("why", "")
matched = sorted(p for p in all_paths if _glob_matches(glob_pattern, p))
near_miss: list = []
relaxed = _relax_glob(glob_pattern)
if relaxed is not None:
matched_set = set(matched)
near_miss = sorted(
p
for p in all_paths
if p not in matched_set and _glob_matches(relaxed, p)
)
return RuleReportEntry(
glob=glob_pattern,
lifetime=lifetime,
tier=tier,
matched_sample=matched[: self._cap],
matched_total=len(matched),
near_miss=near_miss,
why=why,
)
def build_all(self, proposed_rules: list, all_paths: list) -> list:
return [self.build(r, all_paths).to_dict() for r in proposed_rules]
# --- rule-quality checks -----------------------------------------------------
@dataclass
class QualityFinding:
check: str # "class_not_path" | "prefer_narrower"
glob: str
passed: bool
reason: str
def to_dict(self) -> dict:
return {
"check": self.check,
"glob": self.glob,
"passed": self.passed,
"reason": self.reason,
}
class RuleQualityChecker:
"""Deterministic lints applied to a proposed glob before persistence:
- `class_not_path`: flags a glob whose final path segment looks
instance-unique (a long digit run / bare timestamp, or a hex-looking
hash run), OR a glob with zero wildcard characters that currently
matches exactly one existing path (a rule that can, by construction,
only ever match that one file — a failed generalization).
- `prefer_narrower`: given two candidate globs for the same cluster,
report which one is narrower by match-count against the actual tree
(ties broken by raw pattern length, longer = more specific = narrower).
"""
def class_not_path(self, glob_pattern: str, all_paths: Optional[list] = None) -> QualityFinding:
last_segment = glob_pattern.split("/")[-1]
if _LONG_DIGIT_RUN.search(last_segment):
return QualityFinding(
check="class_not_path",
glob=glob_pattern,
passed=False,
reason=(
"glob's final segment contains a long digit run "
"(looks like a run-id or timestamp unique to one instance)"
),
)
if _HEX_RUN.search(last_segment):
return QualityFinding(
check="class_not_path",
glob=glob_pattern,
passed=False,
reason=(
"glob's final segment contains a hex-looking run "
"(looks like a hash unique to one instance)"
),
)
has_wildcard = any(ch in glob_pattern for ch in "*?[")
if not has_wildcard and all_paths is not None:
matches = [p for p in all_paths if _glob_matches(glob_pattern, p)]
if len(matches) <= 1:
return QualityFinding(
check="class_not_path",
glob=glob_pattern,
passed=False,
reason=(
"glob has no wildcard and matches at most one existing "
"path — by construction it can never match a future "
"file (failed generalization), flagged loudly"
),
)
return QualityFinding(
check="class_not_path",
glob=glob_pattern,
passed=True,
reason="glob names a recurring class, not a single instance",
)
def prefer_narrower(self, glob_a: str, glob_b: str, all_paths: list) -> dict:
"""Returns {"narrower": <glob>, "match_counts": {a: n, b: n}}."""
count_a = sum(1 for p in all_paths if _glob_matches(glob_a, p))
count_b = sum(1 for p in all_paths if _glob_matches(glob_b, p))
if count_a != count_b:
narrower = glob_a if count_a < count_b else glob_b
else:
# tie-break on identical match counts: fewer wildcard characters
# is more specific/narrower; if that also ties, the longer raw
# pattern is treated as more specific.
def _wildcard_count(g: str) -> int:
return sum(g.count(ch) for ch in "*?[")
wc_a, wc_b = _wildcard_count(glob_a), _wildcard_count(glob_b)
if wc_a != wc_b:
narrower = glob_a if wc_a < wc_b else glob_b
else:
narrower = glob_a if len(glob_a) >= len(glob_b) else glob_b
return {
"narrower": narrower,
"match_counts": {glob_a: count_a, glob_b: count_b},
}