frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Detect stale clean release locks

Browse Source
This commit is contained in:
yaojingang
2026-06-17 00:22:57 +08:00
parent 108f4d8b87
commit 7476c7ccbf
31 changed files with 346 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/architecture_maintainability.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"python_file_count": 215,
reports/architecture_maintainability.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Architecture Maintainability
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/context_budget.json
+6 -6
View File
@@ -6,15 +6,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1076786,
"other_text_tokens": 1078122,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1077583,
"deferred_resource_tokens": 495216,
"estimated_total_text_tokens": 1078919,
"deferred_resource_tokens": 495718,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435118,
"estimated_tokens": 435620,
"file_count": 140
},
{
@@ -36,7 +36,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435118,
"estimated_tokens": 435620,
"file_count": 140
}
],
@@ -59,7 +59,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 435118,
"estimated_tokens": 435620,
"file_count": 140,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
reports/context_budget.md
+1 -1
View File
@@ -2,7 +2,7 @@
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
| root | `.` | `production` | 1000 | 990 | 797 | 495216 | `governed` | scripts:435118 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 495718 | `governed` | scripts:435620 | 131.3 | - | ok |
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
reports/context_budget_summary.json
+3 -3
View File
@@ -8,11 +8,11 @@
"budget_limit": 1000,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 495216,
"deferred_resource_tokens": 495718,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435118,
"estimated_tokens": 435620,
"file_count": 140
}
],
@@ -35,7 +35,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 435118,
"estimated_tokens": 435620,
"file_count": 140,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
reports/python_compatibility.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"root": ".",
"summary": {
"target_python": "3.11",
reports/python_compatibility.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Python Compatibility
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/review-studio.html
+13 -13
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+188 -188
View File
File diff suppressed because it is too large Load Diff
reports/security_trust_report.json
+3 -2
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
},
"failures": [],
"warnings": [],
@@ -780,7 +780,7 @@
"uses_input": false,
"uses_network": false,
"uses_file_write": true,
"uses_subprocess": false,
"uses_subprocess": true,
"network_urls": [],
"network_hosts": []
},
@@ -3275,6 +3275,7 @@
"scripts/ci_test.py",
"scripts/render_benchmark_reproducibility.py",
"scripts/render_eval_dashboard.py",
"scripts/render_evidence_consistency.py",
"scripts/run_eval_suite.py",
"scripts/run_output_execution.py",
"scripts/sync_local_install.py",
reports/security_trust_report.md
+2 -2
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `231`
- Package SHA256: `d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69`
- Package SHA256: `9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b`
## Failures
@@ -114,7 +114,7 @@
| scripts/render_daily_skillops_report.py | cli | True | True | True | False | False | True | False | Renders a Daily SkillOps report that summarizes explicit-source patterns, proposals, approval state, and release evidence without scanning private logs or applying patches. |
| scripts/render_description_drift_history.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/render_eval_dashboard.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/render_evidence_consistency.py | cli | True | True | True | False | False | True | False | Renders a cross-report evidence consistency gate for generated Skill OS reports. |
| scripts/render_evidence_consistency.py | cli | True | True | True | False | False | True | True | Renders a cross-report evidence consistency gate for generated Skill OS reports. |
| scripts/render_intent_confidence.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/render_intent_dialogue.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/render_iteration_directions.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
reports/skill_os2_audit.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"item_count": 15,
reports/skill_os2_audit.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Audit
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/skill_os2_coverage.json
+9 -9
View File
@@ -1,28 +1,28 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"item_count": 21,
"module_count": 8,
"recommended_pr_count": 13,
"pass_count": 21,
"warn_count": 0,
"pass_count": 20,
"warn_count": 1,
"missing_count": 0,
"extension_track_count": 4,
"extension_partial_count": 0,
"extension_planned_count": 0,
"extension_covered_count": 4,
"adaptive_extension_ready": true,
"local_blueprint_ready": true,
"local_blueprint_ready": false,
"public_world_class_ready": false,
"world_class_evidence_pending_count": 4,
"decision": "local-blueprint-covered-evidence-pending"
"decision": "continue-implementation"
},
"status_counts": {
"pass": 21,
"warn": 0,
"pass": 20,
"warn": 1,
"missing": 0
},
"extension_status_counts": {
@@ -611,9 +611,9 @@
"key": "evidence-consistency",
"category": "recommended-pr",
"label": "Evidence Consistency",
"status": "pass",
"status": "warn",
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
"current": "35 consistency checks",
"current": "36 consistency checks",
"command": "make ci-test",
"test": "tests/verify_evidence_consistency.py",
"evidence": [
reports/skill_os2_coverage.md
+7 -7
View File
@@ -1,15 +1,15 @@
# Skill OS 2.0 Blueprint Coverage
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
- decision: `local-blueprint-covered-evidence-pending`
- local blueprint ready: `true`
- decision: `continue-implementation`
- local blueprint ready: `false`
- public world-class ready: `false`
- pass: `21` / `21`
- pass: `20` / `21`
- missing: `0`
- warn: `0`
- warn: `1`
- reference extensions: `4`
- extension covered: `4`
- extension partial: `0`
@@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
| Evidence Consistency | `pass` | 35 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
| Evidence Consistency | `warn` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
## Reference Extension Tracks
@@ -213,7 +213,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are
### Evidence Consistency
- objective: Recommended Skill OS 2.0 implementation PR from the upgrade plan.
- status: `pass`
- status: `warn`
- existing evidence: `scripts/render_evidence_consistency.py`, `reports/evidence_consistency.json`, `tests/verify_evidence_consistency.py`
- next action: Keep this item covered as the implementation evolves.
reports/world_class_claim_guard.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"ledger_ready_to_claim_world_class": false,
reports/world_class_claim_guard.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Claim Guard
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_evidence_intake.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"schema_present": true,
reports/world_class_evidence_intake.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Intake
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_evidence_ledger.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "evidence-pending",
"ready_to_claim_world_class": false,
reports/world_class_evidence_ledger.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Ledger
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_evidence_plan.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"audit_decision": "continue-iteration",
reports/world_class_evidence_plan.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Plan
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_evidence_preflight.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
reports/world_class_evidence_preflight.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Preflight
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_operator_runbook.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
reports/world_class_operator_runbook.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Operator Runbook
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
reports/world_class_submission_review.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
reports/world_class_submission_review.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Submission Review
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
scripts/render_evidence_consistency.py
+43
View File
@@ -1,6 +1,7 @@
#!/usr/bin/env python3
import argparse
import json
import subprocess
from datetime import date
from pathlib import Path
from typing import Any
@@ -37,6 +38,22 @@ SCRIPT_INTERFACE = "cli"
SCRIPT_INTERFACE_REASON = "Renders a cross-report evidence consistency gate for generated Skill OS reports."
def git_worktree_status(skill_dir: Path) -> dict[str, Any]:
try:
proc = subprocess.run(
["git", "-C", str(skill_dir), "status", "--porcelain=v1", "-uall"],
capture_output=True,
text=True,
check=False,
)
except OSError:
return {"available": False, "clean": None, "changed_file_count": None}
if proc.returncode != 0:
return {"available": False, "clean": None, "changed_file_count": None}
changes = [line for line in proc.stdout.splitlines() if line.strip()]
return {"available": True, "clean": not changes, "changed_file_count": len(changes)}
def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
reports: dict[str, dict[str, Any]] = {}
text_reports: dict[str, str] = {}
@@ -145,6 +162,32 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
paths=[REQUIRED_REPORTS["benchmark"]],
detail="The benchmark release lock must reflect the generation-time git dirty flag.",
)
current_git_status = git_worktree_status(skill_dir)
if current_git_status.get("available") and current_git_status.get("clean") is True:
compare_values(
checks,
key="benchmark-clean-worktree-release-lock",
label="Clean worktree keeps a clean benchmark release lock",
expected=True,
actual=benchmark_summary.get("release_lock_ready"),
paths=[REQUIRED_REPORTS["benchmark"]],
detail=(
"If the current worktree is clean, the committed benchmark report must not still carry a dirty release lock from an earlier generation."
),
)
else:
add_check(
checks,
key="benchmark-clean-worktree-release-lock",
label="Clean worktree keeps a clean benchmark release lock",
status="pass",
expected="checked only when git is available and the current worktree is clean",
actual=current_git_status,
paths=[REQUIRED_REPORTS["benchmark"]],
detail=(
"Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass."
),
)
skill_name = str(overview.get("name") or nested(review_studio, ["data", "frontmatter", "name"]) or skill_dir.name)
expected_skill_ir_path = find_skill_ir_path(skill_dir, skill_name, require_schema=True)
expected_skill_ir = {
tests/verify_evidence_consistency.py
+51
View File
@@ -423,6 +423,57 @@ def main() -> None:
benchmark_flow_drift_checks["release-evidence-flow-covers-first-class-reports"]
)
stale_clean_lock_root = TMP / "stale-clean-lock-skill"
copy_reports(stale_clean_lock_root)
benchmark_path = stale_clean_lock_root / "reports" / "benchmark_reproducibility.json"
benchmark = json.loads(benchmark_path.read_text(encoding="utf-8"))
benchmark["git_status"]["dirty"] = True
benchmark["git_status"]["changed_file_count"] = 3
benchmark["summary"]["release_lock_ready"] = False
benchmark["summary"]["working_tree_dirty"] = True
benchmark["summary"]["changed_file_count"] = 3
benchmark["release_lock"]["ready"] = False
benchmark["release_lock"]["reason"] = "working tree was dirty at generation time"
benchmark_path.write_text(json.dumps(benchmark, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
for report_name in ["skill-overview", "skill-interpretation"]:
report_path = stale_clean_lock_root / "reports" / f"{report_name}.json"
report = json.loads(report_path.read_text(encoding="utf-8"))
report["benchmark_reproducibility"]["summary"]["release_lock_ready"] = False
report["benchmark_reproducibility"]["summary"]["working_tree_dirty"] = True
report["benchmark_reproducibility"]["summary"]["changed_file_count"] = 3
report_path.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
subprocess.run(["git", "init"], cwd=stale_clean_lock_root, capture_output=True, text=True, check=True)
subprocess.run(["git", "add", "."], cwd=stale_clean_lock_root, capture_output=True, text=True, check=True)
subprocess.run(
["git", "-c", "user.name=Yao Test", "-c", "user.email=yao-test@example.com", "commit", "-m", "seed"],
cwd=stale_clean_lock_root,
capture_output=True,
text=True,
check=True,
)
stale_clean_lock_proc = run(
[
sys.executable,
str(SCRIPT),
str(stale_clean_lock_root),
"--output-json",
str(TMP / "stale_clean_lock.json"),
"--output-md",
str(TMP / "stale_clean_lock.md"),
"--generated-at",
"2026-06-15",
]
)
assert stale_clean_lock_proc.returncode == 2, stale_clean_lock_proc.stdout
stale_clean_lock_payload = json.loads(stale_clean_lock_proc.stdout)
stale_clean_lock_checks = {item["key"]: item for item in stale_clean_lock_payload["checks"]}
assert stale_clean_lock_checks["benchmark-release-lock-self-consistency"]["status"] == "pass", (
stale_clean_lock_checks["benchmark-release-lock-self-consistency"]
)
assert stale_clean_lock_checks["benchmark-clean-worktree-release-lock"]["status"] == "fail", (
stale_clean_lock_checks["benchmark-clean-worktree-release-lock"]
)
workflow_drift_root = TMP / "workflow-drift-skill"
copy_reports(workflow_drift_root)
studio_path = workflow_drift_root / "reports" / "review-studio.json"