From 499214b052869193d96cdd7e73f537a57eb7bb8d Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 14:50:44 +0800 Subject: [PATCH] Align review waiver gate policy with studio gates --- references/review-waiver-method.md | 10 ++ registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 6 +- reports/benchmark_reproducibility.json | 54 +++--- reports/benchmark_reproducibility.md | 31 ++-- reports/context_budget.json | 14 +- reports/context_budget.md | 2 +- reports/context_budget_summary.json | 6 +- reports/evidence_consistency.json | 56 +++--- reports/output_execution_runs.json | 20 +-- reports/output_execution_runs.md | 20 +-- reports/package_verification.json | 2 +- reports/package_verification.md | 2 +- reports/registry_audit.json | 8 +- reports/registry_audit.md | 4 +- reports/review-studio.html | 22 +-- reports/review-studio.json | 238 +++++++++++++++++-------- reports/review-viewer.json | 76 ++++++-- reports/review_waivers.json | 42 ++++- reports/review_waivers.md | 3 + reports/security_trust_report.json | 2 +- reports/security_trust_report.md | 2 +- reports/skill-interpretation.html | 8 +- reports/skill-interpretation.json | 76 ++++++-- reports/skill-overview.html | 8 +- reports/skill-overview.json | 76 ++++++-- reports/skillops/daily/2026-06-16.json | 6 +- reports/skillops/daily/2026-06-16.md | 2 +- reports/skillops/weekly/2026-W25.json | 6 +- reports/skillops/weekly/2026-W25.md | 2 +- reports/upgrade_check.json | 4 +- scripts/render_review_waivers.py | 15 +- tests/verify_review_waivers.py | 87 +++++++++ 33 files changed, 647 insertions(+), 265 deletions(-) diff --git a/references/review-waiver-method.md b/references/review-waiver-method.md index 291feb1..84d3fc7 100644 --- a/references/review-waiver-method.md +++ b/references/review-waiver-method.md @@ -25,6 +25,16 @@ Every waiver must include: - `evidence`: optional path or note that explains the decision. - `scope`: default `current-release`. +## Gate Key Policy + +The waiver ledger must track the Review Studio gate universe explicitly: + +- `review_studio_gate_keys`: every gate Review Studio can render. +- `waiverable_gate_keys`: warning gates that may receive bounded human acceptance. +- `non_waivable_gate_keys`: gates that must not be accepted through a waiver. + +When Review Studio adds or renames a gate, update the waiver gate policy and tests in the same change. `review-waivers` and `world-class-evidence` stay non-waivable: the first is the waiver mechanism itself, and the second can only be satisfied by accepted ledger evidence. + ## Release Semantics - Invalid waiver records block Review Studio. diff --git a/registry/index.json b/registry/index.json index ebe332e..611cd1f 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 01c8ffd..aac73e6 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index edcfc87..04512eb 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 33, + "sample": [ + " M references/review-waiver-method.md", + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -37,14 +50,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -53,10 +67,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "ready": false, + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -64,7 +78,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d" + "sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "c6d6e307a51e70c9c3146a57b506c4b92752417f704fe2fcff13134feb6f334f" + "bytes": 7966, + "sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "7222c5a1b18f76e0b0a1d0a49a19255669bde759ced8eed5ddceddc424b4f796" + "sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436" }, { "label": "python_compatibility", @@ -187,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "e8cd7941efbceb36d4cad4bd06600aad48ab0d2b56061256bb39ab3d7ebdd471" + "sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "3189b49d1bef034fb9c9798a28a5bf3c6ac8bd0e73822b452cbacaa278a09043" + "sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55" }, { "label": "install_simulation", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 20bd0d5..eb823cd 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `be399c8b60c7734bde87b479d1bbacb43757f64b` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d` +Commit: `6a879132211add348540043cc2ff2c87cf2a50e6` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `795cfae7d2e0` -- archive sha256: `c061bfca61f6` +- source contract sha256: `1e466c4508d6` +- archive sha256: `88dc8d392047` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4 - world-class ready: `false` - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `33` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `true` -- reason: clean generation-time HEAD +- ready: `false` +- reason: working tree was dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d` +- sha256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8` ## Methodology Sections @@ -72,15 +73,15 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `c6d6e307a51e` | +| output_execution | `reports/output_execution_runs.json` | present | `fd065f84dd52` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `7222c5a1b18f` | +| trust_report | `reports/security_trust_report.json` | present | `e6353c1589c3` | | python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` | -| registry_audit | `reports/registry_audit.json` | present | `e8cd7941efbc` | -| package_verification | `reports/package_verification.json` | present | `3189b49d1bef` | +| registry_audit | `reports/registry_audit.json` | present | `879a11cef513` | +| package_verification | `reports/package_verification.json` | present | `45b51edb26bc` | | install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `c0e499f9f051` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` | diff --git a/reports/context_budget.json b/reports/context_budget.json index 5f9f67a..76b3031 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,20 +6,20 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1048692, + "other_text_tokens": 1050165, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1049489, - "deferred_resource_tokens": 485971, + "estimated_total_text_tokens": 1050962, + "deferred_resource_tokens": 486314, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125 }, { "path": "references", - "estimated_tokens": 28099, + "estimated_tokens": 28248, "file_count": 35 }, { @@ -36,7 +36,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125 } ], @@ -59,7 +59,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/context_budget.md b/reports/context_budget.md index 9971096..8d72382 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -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 | 485971 | `governed` | scripts:425993 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 486314 | `governed` | scripts:426187 | 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 | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index d3075a3..bcef6ce 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 485971, + "deferred_resource_tokens": 486314, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 5c7013b..5616149 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "be399c8b60c7734bde87b479d1bbacb43757f64b", - "actual": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "expected": "6a879132211add348540043cc2ff2c87cf2a50e6", + "actual": "6a879132211add348540043cc2ff2c87cf2a50e6", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,30 +261,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "be399c8b60c7734bde87b479d1bbacb43757f64b", - "actual": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "expected": "6a879132211add348540043cc2ff2c87cf2a50e6", + "actual": "6a879132211add348540043cc2ff2c87cf2a50e6", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,30 +407,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -598,7 +598,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -662,7 +662,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -894,7 +894,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -942,7 +942,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 8c4e7ca..2b2c026 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.03, + "duration_ms": 32.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.67, + "duration_ms": 35.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.12, + "duration_ms": 37.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.21, + "duration_ms": 34.3, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.86, + "duration_ms": 32.89, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.36, + "duration_ms": 33.18, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.46, + "duration_ms": 33.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.85, + "duration_ms": 33.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.35, + "duration_ms": 34.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.62, + "duration_ms": 34.62, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 281ffa6..975c9fd 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 32.03 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 31.67 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 32.12 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.21 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 30.86 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.36 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 31.46 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.85 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.35 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.62 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 32.31 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 35.69 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 37.25 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 34.3 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 32.89 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 33.18 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 33.42 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 33.85 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.38 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.62 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 523a9c2..43df8ed 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 216c228..e590c59 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c` +- Archive SHA256: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 22eb5f8..595c43d 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index f2b8214..234da30 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31` -- Archive SHA256: `c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c` +- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642` +- Archive SHA256: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index bc555f0..cc1361b 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
@@ -807,12 +807,12 @@
-

上下文

initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31
+

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

@@ -837,14 +837,14 @@
-

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

+

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

漂移信号

事件数
1
采用率
0
漏触发
0
Bad Output Count
0
风险带
low
-

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
是
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
-

周度队列

决策
curator-review
Week Id
2026-W25
日报数
1
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
是
Writes Source Files
否
Auto Patch Enabled
否
+

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
否
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
+

周度队列

决策
curator-review
Week Id
2026-W25
日报数
1
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
否
Writes Source Files
否
Auto Patch Enabled
否
@@ -877,8 +877,8 @@
-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
@@ -898,12 +898,12 @@

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288
diff --git a/reports/review-studio.json b/reports/review-studio.json index b043912..6eb3ac8 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -107,7 +107,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly", "link": "adoption_drift_report.md" }, @@ -1027,7 +1027,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -1131,7 +1131,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -1922,13 +1922,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1946,11 +1946,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -2055,7 +2055,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "skill_atlas": { "skill_count": 12, @@ -2093,8 +2093,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -2125,7 +2125,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -2141,7 +2141,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -2220,12 +2220,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, @@ -2306,19 +2306,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "failures": [], @@ -4602,7 +4642,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.03, + "duration_ms": 32.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4630,7 +4670,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.67, + "duration_ms": 35.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4653,7 +4693,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.12, + "duration_ms": 37.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4681,7 +4721,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.21, + "duration_ms": 34.3, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4704,7 +4744,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.86, + "duration_ms": 32.89, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4732,7 +4772,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.36, + "duration_ms": 33.18, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4755,7 +4795,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.46, + "duration_ms": 33.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4782,7 +4822,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.85, + "duration_ms": 33.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4805,7 +4845,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.35, + "duration_ms": 34.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4834,7 +4874,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.62, + "duration_ms": 34.62, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5560,23 +5600,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 33, + "sample": [ + " M references/review-waiver-method.md", + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5594,14 +5647,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -5610,10 +5664,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "ready": false, + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -5621,7 +5675,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d" + "sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5694,8 +5748,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "c6d6e307a51e70c9c3146a57b506c4b92752417f704fe2fcff13134feb6f334f" + "bytes": 7966, + "sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818" }, { "label": "blind_review", @@ -5730,7 +5784,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "7222c5a1b18f76e0b0a1d0a49a19255669bde759ced8eed5ddceddc424b4f796" + "sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436" }, { "label": "python_compatibility", @@ -5744,14 +5798,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "e8cd7941efbceb36d4cad4bd06600aad48ab0d2b56061256bb39ab3d7ebdd471" + "sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "3189b49d1bef034fb9c9798a28a5bf3c6ac8bd0e73822b452cbacaa278a09043" + "sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55" }, { "label": "install_simulation", @@ -12005,7 +12059,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "failures": [], "warnings": [], @@ -16429,20 +16483,20 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1048692, + "other_text_tokens": 1050165, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1049489, - "deferred_resource_tokens": 485971, + "estimated_total_text_tokens": 1050962, + "deferred_resource_tokens": 486314, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125 }, { "path": "references", - "estimated_tokens": 28099, + "estimated_tokens": 28248, "file_count": 35 }, { @@ -16459,7 +16513,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125 } ], @@ -16482,7 +16536,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425993, + "estimated_tokens": 426187, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -18476,7 +18530,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18493,7 +18547,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18942,7 +18996,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ @@ -18991,7 +19045,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19011,7 +19065,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19263,7 +19317,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -19314,19 +19368,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "waivers": [], @@ -23333,8 +23427,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -23365,7 +23459,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -23390,7 +23484,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, @@ -23413,7 +23507,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -24421,12 +24515,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 59b5f3e..f4469ad 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -206,7 +206,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -997,13 +997,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,11 +1021,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1130,7 +1130,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "skill_atlas": { "skill_count": 12, @@ -1168,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -1200,7 +1200,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1295,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, @@ -1381,19 +1381,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "failures": [], diff --git a/reports/review_waivers.json b/reports/review_waivers.json index aa2558e..d88d2a1 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -18,19 +18,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "waivers": [], diff --git a/reports/review_waivers.md b/reports/review_waivers.md index 6c8d594..46be463 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -16,6 +16,9 @@ - Minimum reason chars: `20` - Expiry is required for every waiver. - World-class evidence completion cannot be waived; it can only be proven by accepted ledger evidence. +- Review Studio gates: `architecture-maintainability, context-budget, intent-canvas, operations-loop, output-lab, permission-gates, permission-runtime, python-compat, registry-audit, release-notes, review-waivers, runtime-matrix, skill-atlas, trigger-lab, trust-report, world-class-evidence` +- Waiverable gates: `architecture-maintainability, context-budget, intent-canvas, operations-loop, output-lab, permission-gates, permission-runtime, python-compat, registry-audit, release-notes, runtime-matrix, skill-atlas, trigger-lab, trust-report` +- Non-waivable gates: `review-waivers, world-class-evidence` ## Waivers diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 4e8ffc7..6708cb3 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 3e592fd..7f7560e 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `216` -- Package SHA256: `795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31` +- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642` ## Failures diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 1647a08..6f246b0 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -764,7 +764,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-interpretation.html，再继续扩展包体。After creation, open reports/skill-interpretation.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16828.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16914.纳入下一轮修复Fix next
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 938ef29..51d2d25 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -206,7 +206,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -1001,13 +1001,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,11 +1025,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1134,7 +1134,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "skill_atlas": { "skill_count": 12, @@ -1172,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -1204,7 +1204,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1299,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, @@ -1385,19 +1385,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "failures": [], diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 9c1a235..eb49127 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -764,7 +764,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。After creation, open reports/skill-overview.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16914 个词/字。Entrypoint is about 360 words/characters; references are about 16914.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16828.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16914.纳入下一轮修复Fix next
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 0a958b4..7c7c3f0 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -101,7 +101,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字，references 约 16828 个词/字。", + "入口约 360 个词/字，references 约 16914 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -205,7 +205,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 360 个词/字，references 约 16828 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16914 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -996,13 +996,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", - "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", + "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1020,11 +1020,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 33 }, - "commit": "be399c8b60c7734bde87b479d1bbacb43757f64b", + "commit": "6a879132211add348540043cc2ff2c87cf2a50e6", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1129,7 +1129,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", + "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, @@ -1380,19 +1380,59 @@ "blocker_waivers_allowed": false, "minimum_reason_chars": 20, "expires_required": true, - "known_gate_keys": [ + "review_studio_gate_keys": [ + "architecture-maintainability", "context-budget", "intent-canvas", "operations-loop", "output-lab", "permission-gates", "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "review-waivers", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report", + "world-class-evidence" + ], + "known_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", "registry-audit", "release-notes", "runtime-matrix", "skill-atlas", "trigger-lab", "trust-report" + ], + "waiverable_gate_keys": [ + "architecture-maintainability", + "context-budget", + "intent-canvas", + "operations-loop", + "output-lab", + "permission-gates", + "permission-runtime", + "python-compat", + "registry-audit", + "release-notes", + "runtime-matrix", + "skill-atlas", + "trigger-lab", + "trust-report" + ], + "non_waivable_gate_keys": [ + "review-waivers", + "world-class-evidence" ] }, "failures": [], diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index a35cbc8..386b061 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index 105c41c..d0fbea0 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -14,7 +14,7 @@ Generated at: `2026-06-16` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `true` +- release lock ready: `false` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 998d23e..65c79eb 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -287,7 +287,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index 4d75fc3..1fd6a71 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -13,7 +13,7 @@ Week: `2026-W25` - top_score: `88` - skill_count: `12` - actionable_portfolio_issue_count: `0` -- release_lock_ready: `True` +- release_lock_ready: `False` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 9fa7e99..721b7ab 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" + "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" + "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" } ] }, diff --git a/scripts/render_review_waivers.py b/scripts/render_review_waivers.py index 5936148..d049e60 100644 --- a/scripts/render_review_waivers.py +++ b/scripts/render_review_waivers.py @@ -8,20 +8,27 @@ from typing import Any ROOT = Path(__file__).resolve().parent.parent -KNOWN_GATE_KEYS = { +REVIEW_STUDIO_GATE_KEYS = { "intent-canvas", "trigger-lab", "output-lab", "context-budget", "runtime-matrix", "trust-report", + "python-compat", + "architecture-maintainability", "permission-gates", "permission-runtime", "skill-atlas", "operations-loop", + "review-waivers", + "world-class-evidence", "registry-audit", "release-notes", } +NON_WAIVABLE_GATE_KEYS = {"review-waivers", "world-class-evidence"} +WAIVERABLE_GATE_KEYS = REVIEW_STUDIO_GATE_KEYS - NON_WAIVABLE_GATE_KEYS +KNOWN_GATE_KEYS = WAIVERABLE_GATE_KEYS VALID_DECISIONS = {"accepted-risk", "false-positive", "temporary-exception"} MIN_REASON_CHARS = 20 @@ -270,7 +277,10 @@ def render_report( "blocker_waivers_allowed": False, "minimum_reason_chars": MIN_REASON_CHARS, "expires_required": True, + "review_studio_gate_keys": sorted(REVIEW_STUDIO_GATE_KEYS), "known_gate_keys": sorted(KNOWN_GATE_KEYS), + "waiverable_gate_keys": sorted(WAIVERABLE_GATE_KEYS), + "non_waivable_gate_keys": sorted(NON_WAIVABLE_GATE_KEYS), }, "waivers": waivers, "waiver_candidates": waiver_candidates, @@ -308,6 +318,9 @@ def render_markdown(report: dict[str, Any]) -> str: f"- Minimum reason chars: `{report['policy']['minimum_reason_chars']}`", "- Expiry is required for every waiver.", "- World-class evidence completion cannot be waived; it can only be proven by accepted ledger evidence.", + f"- Review Studio gates: `{', '.join(report['policy']['review_studio_gate_keys'])}`", + f"- Waiverable gates: `{', '.join(report['policy']['waiverable_gate_keys'])}`", + f"- Non-waivable gates: `{', '.join(report['policy']['non_waivable_gate_keys'])}`", "", "## Waivers", "", diff --git a/tests/verify_review_waivers.py b/tests/verify_review_waivers.py index 248565c..e74b9a9 100644 --- a/tests/verify_review_waivers.py +++ b/tests/verify_review_waivers.py @@ -8,6 +8,9 @@ from pathlib import Path ROOT = Path(__file__).resolve().parent.parent SCRIPT = ROOT / "scripts" / "render_review_waivers.py" +sys.path.insert(0, str(ROOT / "scripts")) + +import render_review_waivers as review_waivers # noqa: E402 def run(*args: str, check: bool = True) -> subprocess.CompletedProcess: @@ -21,6 +24,29 @@ def run(*args: str, check: bool = True) -> subprocess.CompletedProcess: def main() -> None: + assert review_waivers.REVIEW_STUDIO_GATE_KEYS == { + "intent-canvas", + "trigger-lab", + "output-lab", + "context-budget", + "runtime-matrix", + "trust-report", + "python-compat", + "architecture-maintainability", + "permission-gates", + "permission-runtime", + "skill-atlas", + "operations-loop", + "review-waivers", + "world-class-evidence", + "registry-audit", + "release-notes", + }, review_waivers.REVIEW_STUDIO_GATE_KEYS + assert review_waivers.NON_WAIVABLE_GATE_KEYS == {"review-waivers", "world-class-evidence"} + assert "python-compat" in review_waivers.WAIVERABLE_GATE_KEYS + assert "architecture-maintainability" in review_waivers.WAIVERABLE_GATE_KEYS + assert "world-class-evidence" not in review_waivers.WAIVERABLE_GATE_KEYS + tmp_root = ROOT / "tests" / "tmp_review_waivers" if tmp_root.exists(): shutil.rmtree(tmp_root) @@ -56,6 +82,64 @@ def main() -> None: assert added_payload["summary"]["covered_gate_keys"] == ["trust-report"], added_payload assert "trust-report" in (skill / "reports" / "review_waivers.md").read_text(encoding="utf-8") + python_compat = run( + str(skill), + "--generated-at", + "2026-06-13", + "--add-waiver", + "--gate-key", + "python-compat", + "--reviewer", + "Yao Team", + "--reason", + "Python compatibility warning is understood and bounded to this release.", + "--expires-at", + "2026-09-30", + ) + python_compat_payload = json.loads(python_compat.stdout) + assert python_compat_payload["ok"], python_compat_payload + assert python_compat_payload["summary"]["covered_gate_keys"] == ["python-compat", "trust-report"], python_compat_payload + + architecture = run( + str(skill), + "--generated-at", + "2026-06-13", + "--add-waiver", + "--gate-key", + "architecture-maintainability", + "--reviewer", + "Yao Team", + "--reason", + "Architecture warning is accepted only while the planned split remains in scope.", + "--expires-at", + "2026-09-30", + ) + architecture_payload = json.loads(architecture.stdout) + assert architecture_payload["ok"], architecture_payload + assert architecture_payload["summary"]["covered_gate_keys"] == [ + "architecture-maintainability", + "python-compat", + "trust-report", + ], architecture_payload + + non_waivable = run( + str(skill), + "--generated-at", + "2026-06-13", + "--add-waiver", + "--gate-key", + "world-class-evidence", + "--reviewer", + "Yao Team", + "--reason", + "World class evidence cannot be waived even with a reviewer.", + "--expires-at", + "2026-09-30", + check=False, + ) + assert non_waivable.returncode == 2, non_waivable.stdout + assert "invalid choice" in non_waivable.stderr, non_waivable.stderr + expired_source = tmp_root / "expired.json" expired_source.write_text( json.dumps( @@ -123,6 +207,9 @@ def main() -> None: root_markdown = root_report_md.read_text(encoding="utf-8") assert "Candidate Actions" in root_markdown, root_markdown assert "World-class evidence completion cannot be waived" in root_markdown, root_markdown + assert "Review Studio gates" in root_markdown, root_markdown + assert "Waiverable gates" in root_markdown, root_markdown + assert "Non-waivable gates" in root_markdown, root_markdown assert "`world-class-evidence` | `cannot-waive` | `false`" in root_markdown, root_markdown print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))