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

Tighten Review Studio source anchors

Browse Source
This commit is contained in:
yaojingang
2026-06-17 03:10:24 +08:00
parent c4f903bf8a
commit 52ec9e3720
4 changed files with 72 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/review-studio.html
+2 -2
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+64 -64
View File
@@ -232,7 +232,7 @@
"label": "output eval cases",
"kind": "eval",
"line": 1,
"matched_pattern": "",
"matched_pattern": "\"id\"",
"excerpt": "{\"id\":\"skill-package-contract\",\"prompt\":\"Turn this repeated workflow into a reusable team skill package.\",\"baseline_output\":\"I can write a prompt for that workflow and include a s…",
"exists": true,
"link": "../evals/output/cases.jsonl"
@@ -4769,7 +4769,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.8,
"duration_ms": 26.9,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4797,7 +4797,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.3,
"duration_ms": 25.49,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4820,7 +4820,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.02,
"duration_ms": 25.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4848,7 +4848,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.2,
"duration_ms": 28.61,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4871,7 +4871,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.27,
"duration_ms": 28.59,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4899,7 +4899,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.59,
"duration_ms": 26.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4922,7 +4922,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.08,
"duration_ms": 26.0,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4949,7 +4949,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.0,
"duration_ms": 26.3,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4972,7 +4972,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.31,
"duration_ms": 25.82,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5001,7 +5001,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.12,
"duration_ms": 25.81,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -6973,7 +6973,7 @@
"compiled_targets": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"target_count": 5,
@@ -12344,7 +12344,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 239,
"package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7"
"package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995"
},
"failures": [],
"warnings": [],
@@ -15761,7 +15761,7 @@
"python_compatibility": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"root": ".",
"summary": {
"target_python": "3.11",
@@ -17142,7 +17142,7 @@
"architecture_maintainability": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"python_file_count": 222,
@@ -17175,28 +17175,12 @@
},
{
"path": "tests/verify_world_class_evidence_intake.py",
"lines": 690,
"lines": 628,
"kind": "test",
"severity": "pass",
"early_watch": true,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "tests/verify_output_review_adjudication.py",
"lines": 598,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "tests/verify_review_studio.py",
"lines": 596,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_benchmark_reproducibility.py",
"lines": 595,
@@ -17205,14 +17189,6 @@
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_skill_overview.py",
"lines": 588,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/build_skill_atlas.py",
"lines": 586,
@@ -17230,21 +17206,29 @@
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/trust_check.py",
"lines": 582,
"path": "scripts/render_skill_overview.py",
"lines": 584,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "tests/verify_world_class_evidence_ledger.py",
"lines": 579,
"path": "tests/verify_review_studio.py",
"lines": 584,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/trust_check.py",
"lines": 582,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 568,
@@ -17260,6 +17244,22 @@
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "tests/verify_world_class_evidence_ledger.py",
"lines": 567,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_world_class_preflight.py",
"lines": 562,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
}
],
"watchlist": [],
@@ -17274,7 +17274,7 @@
},
{
"path": "tests/verify_world_class_evidence_intake.py",
"lines": 690,
"lines": 628,
"kind": "test",
"severity": "pass",
"early_watch": true,
@@ -17296,9 +17296,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1094768,
"other_text_tokens": 1094713,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1095565,
"estimated_total_text_tokens": 1095510,
"deferred_resource_tokens": 498644,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
@@ -18200,7 +18200,7 @@
},
"catalog": {
"workspace_root": ".",
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skills": [
{
"name": "yao-meta-skill",
@@ -19101,7 +19101,7 @@
"name": "incident-command-governor",
"path": "examples/governed-incident-command/generated-skill",
"reason": "review overdue by cadence monthly",
"age_days": 74,
"age_days": 78,
"allowed_days": 31,
"actionable": false,
"scope": "example"
@@ -19269,7 +19269,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16T19:04:13Z",
"generated_at": "2026-06-16T17:53:31Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -24577,11 +24577,11 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-17"
},
"index": {
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"package_count": 1,
"packages": [
{
@@ -25279,11 +25279,11 @@
"install_simulation": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"package_dir": "tests/tmp_review_studio/dist",
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
"package_dir": "dist",
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 685,
@@ -25304,7 +25304,7 @@
{
"id": "archive-present",
"status": "pass",
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
"detail": "Package archive exists: dist/yao-meta-skill.zip"
},
{
"id": "archive-safe-paths",
@@ -25550,16 +25550,16 @@
"failures": [],
"warnings": [],
"artifacts": {
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
"json": "tests/tmp_review_studio/install_simulation.json",
"markdown": "tests/tmp_review_studio/install_simulation.md"
"archive": "dist/yao-meta-skill.zip",
"package_manifest": "dist/manifest.json",
"json": "reports/install_simulation.json",
"markdown": "reports/install_simulation.md"
}
},
"upgrade_check": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"previous": {
"name": "yao-meta-skill",
"version": "1.0.0",
@@ -25648,8 +25648,8 @@
"artifacts": {
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
"current_package": "reports/registry_audit.json",
"json": "tests/tmp_review_studio/upgrade_check.json",
"markdown": "tests/tmp_review_studio/upgrade_check.md"
"json": "reports/upgrade_check.json",
"markdown": "reports/upgrade_check.md"
}
},
"manifest": {
scripts/review_studio_actions.py
+1 -1
View File
@@ -102,7 +102,7 @@ ACTION_GUIDANCE: dict[str, dict[str, Any]] = {
"why": "没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。",
"source_fix": "evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md",
"source_paths": [
{"path": "evals/output/cases.jsonl", "label": "output eval cases", "kind": "eval", "patterns": ["case_id"]},
{"path": "evals/output/cases.jsonl", "label": "output eval cases", "kind": "eval", "patterns": ['"case_id"', '"id"']},
{"path": "reports/output_quality_scorecard.md", "label": "output scorecard", "kind": "report", "patterns": ["# Output"]},
{"path": "reports/output_execution_runs.md", "label": "output execution runs", "kind": "report", "patterns": ["# Output Execution"]},
{"path": "reports/output_blind_review_pack.md", "label": "blind A/B review pack", "kind": "report", "patterns": ["# Output Blind"]},
tests/verify_review_studio.py
+5 -11
View File
@@ -261,6 +261,7 @@ def main() -> None:
assert all(item["exists"] for item in world_class_action["source_refs"]), world_class_action
assert all("matched_pattern" in item for item in world_class_action["source_refs"]), world_class_action
assert all("excerpt" in item for item in world_class_action["source_refs"]), world_class_action
assert all(isinstance(item["line"], int) and item["line"] >= 1 for item in world_class_action["source_refs"]), world_class_action
assert any(
item["path"] == "reports/world_class_evidence_ledger.md"
and item["matched_pattern"] == "# World-Class Evidence Ledger"
@@ -313,11 +314,8 @@ def main() -> None:
assert full_payload["data"]["world_class_submission_review"]["summary"]["awaiting_submission_count"] == 4, full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["source_check_count"] >= 13, full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["source_blocked_count"] >= 6, full_payload["data"]["world_class_submission_review"]
human_review_item = next(
item
for item in full_payload["data"]["world_class_submission_review"]["items"]
if item["evidence_key"] == "human-adjudication"
)
human_review_items = full_payload["data"]["world_class_submission_review"]["items"]
human_review_item = next(item for item in human_review_items if item["evidence_key"] == "human-adjudication")
human_review_source = {item["field"]: item for item in human_review_item["source_checklist"]}
assert human_review_item["observed_state"]["raw_content_allowed"] is False, human_review_item
assert human_review_item["observed_state"]["raw_content_path_count"] == 0, human_review_item
@@ -405,12 +403,8 @@ def main() -> None:
assert all(item["exists"] for item in synthetic_actions[0]["source_refs"]), synthetic_actions
assert all(isinstance(item["line"], int) and item["line"] >= 1 for item in synthetic_actions[0]["source_refs"]), synthetic_actions
assert all("excerpt" in item for item in synthetic_actions[0]["source_refs"]), synthetic_actions
assert any(
item["path"] == "reports/output_review_kit.html"
and item["matched_pattern"] == "Output Review Kit"
and "Output Review Kit" in item["excerpt"]
for item in synthetic_actions[0]["source_refs"]
), synthetic_actions
assert any(item["path"] == "reports/output_review_kit.html" and item["matched_pattern"] == "Output Review Kit" and "Output Review Kit" in item["excerpt"] for item in synthetic_actions[0]["source_refs"]), synthetic_actions
assert any(item["path"] == "evals/output/cases.jsonl" and item["matched_pattern"] == '"id"' and '"id"' in item["excerpt"] for item in synthetic_actions[0]["source_refs"]), synthetic_actions
synthetic_json = json.dumps(synthetic_actions, ensure_ascii=False)
assert str(ROOT) not in synthetic_json, synthetic_json
synthetic_html = review_studio.render_review_actions(synthetic_actions)