coulomb/state-hub
2
0
Fork 0
generated from coulomb/repo-seed
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(consistency): fix-consistency-remote works without REPO for all repos

Browse Source 
Adds --remote CLI flag and fix_all_remote() function. When run without a
REPO argument, the target checks all registered repos and:
- Skips repos whose local path does not exist on this machine
- Skips repos that are already clean (no fixable issues, no FAILs, not
  behind remote, only C-08 background noise allowed)
- For repos that need work: git pull --ff-only then fix_repo()

Prints a summary of CLEAN (skipped) and NOT ON THIS HOST (skipped) repos
before the detailed fix reports.

Simplifies the Makefile target from shell-level curl+git to a single
uv run call using --remote. Same flag handles both single-repo and all-repos.

Also adds _git_pull() helper and 13 new tests (71 total in consistency suite).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Bernd Worsch
2026-03-26 14:38:30 +01:00
parent e8bac88ba2
commit 075b34945f
3 changed files with 276 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
scripts/consistency_check.py
View File

@@ -747,6 +747,25 @@ def _check_ghost_duplicates(
# Git helpers (T02 pull gate, T03 writeback)
# ---------------------------------------------------------------------------
def _git_pull(repo_path: str) -> tuple[bool, str]:
"""Run ``git pull --ff-only`` on *repo_path*.
Returns ``(success, message)`` where *message* describes the outcome.
Never raises — errors are returned as ``(False, "<reason>")``.
"""
try:
result = subprocess.run(
["git", "-C", repo_path, "pull", "--ff-only"],
capture_output=True, text=True, timeout=30,
)
if result.returncode == 0:
out = result.stdout.strip()
return True, out or "already up to date"
return False, result.stderr.strip() or "pull failed"
except Exception as exc:
return False, str(exc)
def _detect_behind_remote(repo_path: str) -> bool:
"""Return True if the remote tracking branch has commits the local repo lacks.
@@ -1078,6 +1097,92 @@ def fix_repo(
return report
# Check IDs that are known-background noise in multi-machine setups:
# C-08 = completed/archived DB workstream with no file (pre-ADR-001 legacy)
# These alone do not warrant a pull+fix cycle.
_BACKGROUND_CHECKS: frozenset[str] = frozenset({"C-08"})
def _report_needs_action(report: ConsistencyReport, behind_remote: bool) -> bool:
"""Return True if the repo warrants a pull+fix cycle.
A repo is considered clean (no action needed) when:
- It is not behind its remote tracking branch, AND
- It has no FAIL issues, AND
- Every WARN/INFO issue is in the background-noise set (C-08).
"""
if behind_remote:
return True
if report.failures:
return True
actionable_warns = [
i for i in report.warnings + report.infos
if i.check_id not in _BACKGROUND_CHECKS
]
return bool(actionable_warns)
def fix_all_remote(
api_base: str,
no_writeback: bool = False,
) -> list[ConsistencyReport]:
"""Pull-then-fix all registered repos that need attention.
For each repo with a resolvable local path on this machine:
1. Skip if the path does not exist (repo lives on another machine).
2. Run check_repo() and detect_behind_remote() — read-only.
3. If the repo is clean (no actionable issues, not behind remote): skip.
4. Otherwise: git pull --ff-only, then fix_repo().
Returns one ConsistencyReport per repo that was *not* skipped as clean.
Repos skipped as clean are printed to stdout but not included in the return value.
"""
repos = _api_get(api_base, "/repos")
if not isinstance(repos, list):
print("ERROR: Could not fetch repos from state-hub API", file=sys.stderr)
return []
reports: list[ConsistencyReport] = []
skipped_clean: list[str] = []
skipped_missing: list[str] = []
for repo in repos:
slug = repo["slug"]
# Resolve path using the same priority as check_repo
path = resolve_repo_path(repo)
if not path or not Path(path).is_dir():
skipped_missing.append(slug)
continue
# Read-only pass: detect issues and remote staleness
pre_report = check_repo(api_base, slug)
behind = _detect_behind_remote(path)
if not _report_needs_action(pre_report, behind):
skipped_clean.append(slug)
continue
# Pull before fixing
pull_ok, pull_msg = _git_pull(path)
pull_tag = f"pull: {pull_msg}"
if not pull_ok:
pull_tag = f"pull WARN: {pull_msg} — proceeding anyway"
report = fix_repo(api_base, slug, no_writeback=no_writeback)
report.fixes_applied.insert(0, pull_tag)
reports.append(report)
# Print clean/missing summary lines before the detailed reports
if skipped_clean:
print(f" CLEAN (skipped): {', '.join(skipped_clean)}")
if skipped_missing:
print(f" NOT ON THIS HOST (skipped): {', '.join(skipped_missing)}")
if skipped_clean or skipped_missing:
print()
return reports
# ---------------------------------------------------------------------------
# Output / rendering
# ---------------------------------------------------------------------------
@@ -1172,6 +1277,10 @@ def main() -> None:
help="Run checks against all registered repos with local_path")
parser.add_argument("--fix", action="store_true",
help="Apply auto-fixable issues (status drift, repo mismatch, etc.)")
parser.add_argument("--remote", action="store_true",
help="Pull each repo before fixing; when used with --all, skips repos "
"that are already clean (no actionable issues, not behind remote). "
"Implies --fix.")
parser.add_argument("--no-writeback", action="store_true", dest="no_writeback",
help="Disable DB→file status writeback (C-15) while keeping other fixes")
parser.add_argument("--repo-path", metavar="PATH", default=None,
@@ -1183,30 +1292,50 @@ def main() -> None:
help="Output JSON instead of human-readable text")
args = parser.parse_args()
# Resolve repo list
repo_slugs: list[str] = []
if args.all:
repos = _api_get(args.api_base, "/repos")
if not isinstance(repos, list):
print("ERROR: Could not fetch repos from state-hub API", file=sys.stderr)
sys.exit(1)
repo_slugs = [r["slug"] for r in repos if r.get("local_path")]
if not repo_slugs:
print("No repos with local_path registered.", file=sys.stderr)
no_wb = getattr(args, "no_writeback", False)
do_fix = args.fix or args.remote
# --remote --all: smart pull+fix across all repos
if args.remote and args.all:
reports = fix_all_remote(args.api_base, no_writeback=no_wb)
if not reports:
sys.exit(0)
else:
repo_slugs = [args.repo]
# Resolve repo list
repo_slugs: list[str] = []
if args.all:
repos = _api_get(args.api_base, "/repos")
if not isinstance(repos, list):
print("ERROR: Could not fetch repos from state-hub API", file=sys.stderr)
sys.exit(1)
repo_slugs = [r["slug"] for r in repos if r.get("local_path")]
if not repo_slugs:
print("No repos with local_path registered.", file=sys.stderr)
sys.exit(0)
else:
repo_slugs = [args.repo]
# --repo-path only applies to single-repo runs; silently ignored with --all
path_override = args.repo_path if not args.all else None
if args.fix:
no_wb = getattr(args, "no_writeback", False)
reports = [
fix_repo(args.api_base, slug, path_override, no_writeback=no_wb)
for slug in repo_slugs
]
else:
reports = [check_repo(args.api_base, slug, path_override) for slug in repo_slugs]
# --repo-path only applies to single-repo runs; silently ignored with --all
path_override = args.repo_path if not args.all else None
if args.remote:
# Single-repo remote: pull first, then fix
slug = repo_slugs[0]
repo = _api_get(args.api_base, f"/repos/{slug}")
path = resolve_repo_path(repo or {}, path_override) if repo else (path_override or "")
if path:
pull_ok, pull_msg = _git_pull(path)
prefix = "pull" if pull_ok else "pull WARN"
print(f" {prefix}: {pull_msg}")
report = fix_repo(args.api_base, slug, path_override, no_writeback=no_wb)
reports = [report]
elif do_fix:
reports = [
fix_repo(args.api_base, slug, path_override, no_writeback=no_wb)
for slug in repo_slugs
]
else:
reports = [check_repo(args.api_base, slug, path_override) for slug in repo_slugs]
if args.as_json:
output = (