From 985eaee14ba01683dc75aa0bbeb4e4700e49989f Mon Sep 17 00:00:00 2001 From: yaojingang Date: Sun, 14 Jun 2026 10:43:19 +0800 Subject: [PATCH] feat: reject placeholder evidence submissions --- evidence/world_class/intake.schema.json | 13 ++++ registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 6 +- reports/context_budget.json | 12 +-- reports/context_budget.md | 2 +- reports/context_budget_summary.json | 6 +- reports/package_verification.json | 2 +- reports/package_verification.md | 2 +- reports/registry_audit.json | 8 +- reports/registry_audit.md | 4 +- reports/review-studio.html | 10 +-- reports/review-studio.json | 76 +++++++++---------- reports/security_trust_report.json | 2 +- reports/security_trust_report.md | 2 +- reports/skill-overview.json | 24 +++--- reports/upgrade_check.json | 4 +- reports/world_class_evidence_intake.md | 1 + scripts/render_world_class_evidence_intake.py | 1 + scripts/world_class_evidence_contract.py | 53 +++++++++++++ tests/verify_world_class_evidence_intake.py | 18 +++++ tests/verify_world_class_evidence_ledger.py | 44 +++++++++++ 21 files changed, 211 insertions(+), 81 deletions(-) diff --git a/evidence/world_class/intake.schema.json b/evidence/world_class/intake.schema.json index 96fb4484..51ef64fd 100644 --- a/evidence/world_class/intake.schema.json +++ b/evidence/world_class/intake.schema.json @@ -185,6 +185,19 @@ }, "then": { "properties": { + "submitted_at": { + "pattern": "^\\d{4}-\\d{2}-\\d{2}(?:T\\d{2}:\\d{2}:\\d{2}Z)?$" + }, + "submitted_by": { + "not": { + "enum": [ + "operator with provider credentials", + "human reviewer", + "target client or installer integrator", + "Browser/Chrome/IDE/provider client integrator" + ] + } + }, "artifact_refs": { "items": { "required": [ diff --git a/registry/index.json b/registry/index.json index 120f1940..28e5fbcf 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 97fafc10..e74fd53f 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": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/context_budget.json b/reports/context_budget.json index f68731a5..a3d01e53 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,15 +6,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 1191951, + "other_text_tokens": 1193567, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 1192702, - "deferred_resource_tokens": 383953, + "estimated_total_text_tokens": 1194318, + "deferred_resource_tokens": 384567, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96 }, { @@ -31,7 +31,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96 } ], @@ -54,7 +54,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96, "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 b3db2287..de4fc858 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 | 944 | 751 | 383953 | `governed` | scripts:336470 | 137.7 | - | ok | +| root | `.` | `production` | 1000 | 944 | 751 | 384567 | `governed` | scripts:337084 | 137.7 | - | 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 4e2399e3..eb53b5c3 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 944, "skill_body_tokens": 751, - "deferred_resource_tokens": 383953, + "deferred_resource_tokens": 384567, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/package_verification.json b/reports/package_verification.json index 24a09632..c1107239 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": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "archive_entry_count": 575, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index f2ed4845..9f931315 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: `54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d` +- Archive SHA256: `6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 476fda0d..d7cb45a2 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "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": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index cc99d634..8b63a7d3 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb` -- Archive SHA256: `54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d` +- Package SHA256: `da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942` +- Archive SHA256: `6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 4bd99144..cd0b2591 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -439,7 +439,7 @@

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 944/1000; deferred 383953/120000; top deferred scripts 336470; resource governance governed; quality density 137.7

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; 96 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 158 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

155 Python files; 0 hotspots; 0 blockers; largest 888 lines; 34 CLI handlers

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 100.0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 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; 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 944/1000; deferred 384567/120000; top deferred scripts 337084; resource governance governed; quality density 137.7

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; 96 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 158 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

155 Python files; 0 hotspots; 0 blockers; largest 888 lines; 34 CLI handlers

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 100.0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 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; 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
@@ -501,12 +501,12 @@
-

上下文

initial load 944/1000; deferred 383953/120000; top deferred scripts 336470; resource governance governed; quality density 137.7

+

上下文

initial load 944/1000; deferred 384567/120000; top deferred scripts 337084; resource governance governed; quality density 137.7

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
96
网络脚本
3
Help 失败
0
包体哈希
2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb
+

信任报告

Secret
0
脚本数
96
网络脚本
3
Help 失败
0
包体哈希
da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942

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。

@@ -574,12 +574,12 @@

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
54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d
+

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
6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8

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
575
失败数
0
警告数
0
归档哈希
54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
575
失败数
0
警告数
0
归档哈希
6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8
diff --git a/reports/review-studio.json b/reports/review-studio.json index 0fdf6088..bb4a6535 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 944/1000; deferred 383953/120000; top deferred scripts 336470; resource governance governed; quality density 137.7", + "detail": "initial load 944/1000; deferred 384567/120000; top deferred scripts 337084; resource governance governed; quality density 137.7", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -1336,9 +1336,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "58baf3fe11e00c2be487239945ab3cc43a70b545507e1f1c891d1aed9a6da25e", - "source_contract_sha256": "59b0f65b269be1bcd9b8ab46997136fd5c19da796d0797702fb6a0dc96274cb8", - "archive_sha256": "5f3d7a018d80277336598d3bf78c546f37a301c0e4d8be6691a9f8de349c6576", + "evidence_bundle_sha256": "f2e43ceb692ae62a187af57b89bc49fb420f5a747b9b3e9dd5b5e23601f30c4e", + "source_contract_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", + "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -1353,9 +1353,9 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 25 }, - "commit": "d808071fb55a91484e78fe40f4b64bb52815758a", + "commit": "3f0b262e5f11fdcf14db8dc70ddcb2a89941e52d", "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.", @@ -1460,7 +1460,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 180, - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" }, "skill_atlas": { "skill_count": 12, @@ -1498,8 +1498,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, "compatibility": { "openai": "pass", @@ -1530,7 +1530,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1546,7 +1546,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "archive_entry_count": 575, "failure_count": 0, "warning_count": 0 @@ -1625,12 +1625,12 @@ { "field": "archive_sha256", "from": "", - "to": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "to": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "to": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, @@ -3809,7 +3809,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.91, + "duration_ms": 29.87, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3837,7 +3837,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.72, + "duration_ms": 28.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3860,7 +3860,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.83, + "duration_ms": 29.77, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3888,7 +3888,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.47, + "duration_ms": 28.86, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3911,7 +3911,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.49, + "duration_ms": 28.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3939,7 +3939,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.13, + "duration_ms": 28.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3962,7 +3962,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.38, + "duration_ms": 28.63, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3989,7 +3989,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.42, + "duration_ms": 28.92, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4012,7 +4012,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.69, + "duration_ms": 28.27, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4041,7 +4041,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.75, + "duration_ms": 28.93, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -10257,7 +10257,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 180, - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" }, "failures": [], "warnings": [], @@ -13787,15 +13787,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 1191951, + "other_text_tokens": 1193567, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 1192702, - "deferred_resource_tokens": 383953, + "estimated_total_text_tokens": 1194318, + "deferred_resource_tokens": 384567, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96 }, { @@ -13812,7 +13812,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96 } ], @@ -13835,7 +13835,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 336470, + "estimated_tokens": 337084, "file_count": 96, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -15697,7 +15697,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-14T02:29:07Z", + "generated_at": "2026-06-14T02:40:09Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -17322,8 +17322,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, "compatibility": { "openai": "pass", @@ -17354,7 +17354,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -17379,7 +17379,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, @@ -17402,7 +17402,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "archive_entry_count": 575, "failure_count": 0, "warning_count": 0 @@ -18410,12 +18410,12 @@ { "field": "archive_sha256", "from": "", - "to": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "to": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "to": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index d0fceaad..acf0c1ee 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": 180, - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 1aaf342f..0bac3f8c 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: `180` -- Package SHA256: `2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb` +- Package SHA256: `da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942` ## Failures diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 218202eb..9ba8f417 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -922,9 +922,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "58baf3fe11e00c2be487239945ab3cc43a70b545507e1f1c891d1aed9a6da25e", - "source_contract_sha256": "59b0f65b269be1bcd9b8ab46997136fd5c19da796d0797702fb6a0dc96274cb8", - "archive_sha256": "5f3d7a018d80277336598d3bf78c546f37a301c0e4d8be6691a9f8de349c6576", + "evidence_bundle_sha256": "f2e43ceb692ae62a187af57b89bc49fb420f5a747b9b3e9dd5b5e23601f30c4e", + "source_contract_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", + "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -939,9 +939,9 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 25 }, - "commit": "d808071fb55a91484e78fe40f4b64bb52815758a", + "commit": "3f0b262e5f11fdcf14db8dc70ddcb2a89941e52d", "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.", @@ -1046,7 +1046,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 180, - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" }, "skill_atlas": { "skill_count": 12, @@ -1084,8 +1084,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb", - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "package_sha256": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, "compatibility": { "openai": "pass", @@ -1116,7 +1116,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1132,7 +1132,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d", + "archive_sha256": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8", "archive_entry_count": 575, "failure_count": 0, "warning_count": 0 @@ -1211,12 +1211,12 @@ { "field": "archive_sha256", "from": "", - "to": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "to": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "to": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 0800ab27..1e92f3c4 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "54e6b60578526fb40d38c7105cc61f59f0ca93c2811b1074b9ebc1620cfe853d" + "to": "6756fa63a5db07a3441347153ffb566e22b0a14ae4605b4ed3ab87d548a956b8" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2af3b1e7638215a67244ed897737e1d0b42b8c930c3a8ac66d87d818b3ba01bb" + "to": "da5488b7d14d1599f3d13ac30a6d4a9de1690867697e0f12426b3631bed47942" } ] }, diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index ec83cee8..ab44a4b2 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -202,6 +202,7 @@ This report validates the intake contract for human and external evidence. A val - Templates and planned work do not count as accepted evidence. - Real submissions must include the evidence-key critical artifact paths with verified SHA-256 digests. +- Real submissions must replace template submitter, date, and provenance placeholders with concrete evidence metadata. - Local command-runner output does not count as provider-backed model evidence. - Metadata fallback does not count as native permission enforcement. - Pending reviewer work does not count as human adjudication. diff --git a/scripts/render_world_class_evidence_intake.py b/scripts/render_world_class_evidence_intake.py index 4bdf781f..cc8a4d2f 100644 --- a/scripts/render_world_class_evidence_intake.py +++ b/scripts/render_world_class_evidence_intake.py @@ -297,6 +297,7 @@ def render_markdown(report: dict[str, Any]) -> str: "", "- Templates and planned work do not count as accepted evidence.", "- Real submissions must include the evidence-key critical artifact paths with verified SHA-256 digests.", + "- Real submissions must replace template submitter, date, and provenance placeholders with concrete evidence metadata.", "- Local command-runner output does not count as provider-backed model evidence.", "- Metadata fallback does not count as native permission enforcement.", "- Pending reviewer work does not count as human adjudication.", diff --git a/scripts/world_class_evidence_contract.py b/scripts/world_class_evidence_contract.py index 28747e78..ae057061 100644 --- a/scripts/world_class_evidence_contract.py +++ b/scripts/world_class_evidence_contract.py @@ -49,6 +49,7 @@ EXPECTED_SOURCE_TYPES = { "native-client-telemetry": "native-client-telemetry", } SHA256_RE = re.compile(r"^[0-9a-fA-F]{64}$") +SUBMITTED_AT_RE = re.compile(r"^\d{4}-\d{2}-\d{2}(?:T\d{2}:\d{2}:\d{2}Z)?$") DISALLOWED_REAL_ARTIFACTS = {"reports/telemetry_events.jsonl"} REQUIRED_REAL_ARTIFACT_PATHS = { "provider-holdout": {"reports/output_execution_runs.json"}, @@ -65,6 +66,18 @@ REQUIRED_REAL_ARTIFACT_PATHS = { "reports/telemetry_hook_recipes.json", }, } +PLACEHOLDER_FRAGMENTS = ( + "YYYY-MM-DD", + "name or team handle", + "operator with provider credentials", + "human reviewer", + "target client or installer integrator", + "Browser/Chrome/IDE/provider client integrator", + "Browser/Chrome/IDE/provider client", + "openai|claude|generic|vscode|other", + "client or installer component", + "/local/path/not/committed", +) def load_json(path: Path) -> dict[str, Any]: @@ -101,6 +114,20 @@ def add_error(errors: list[str], condition: bool, message: str) -> None: errors.append(message) +def has_placeholder_text(value: Any) -> bool: + text = str(value or "").strip() + if not text: + return False + lowered = text.lower() + return any(fragment.lower() in lowered for fragment in PLACEHOLDER_FRAGMENTS) + + +def require_real_text(errors: list[str], value: Any, field: str) -> None: + text = str(value or "").strip() + add_error(errors, bool(text), f"{field} is required") + add_error(errors, not has_placeholder_text(text), f"{field} must not use template placeholder text") + + def sha256_file(path: Path) -> str: digest = hashlib.sha256() with path.open("rb") as handle: @@ -197,6 +224,7 @@ def validate_artifact_refs( def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> None: key = str(payload.get("evidence_key", "")) + template_expected = payload.get("template_only") is True provenance = payload.get("provenance", {}) if isinstance(payload.get("provenance", {}), dict) else {} if key == "provider-holdout": add_error(errors, bool(str(provenance.get("provider", "")).strip()), "provider-holdout provenance.provider is required") @@ -208,6 +236,8 @@ def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> No ) elif key == "human-adjudication": add_error(errors, bool(str(provenance.get("reviewer", "")).strip()), "human-adjudication provenance.reviewer is required") + if not template_expected: + require_real_text(errors, provenance.get("reviewer", ""), "human-adjudication provenance.reviewer") add_error( errors, provenance.get("answer_key_opened_after_decisions") is True, @@ -215,11 +245,19 @@ def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> No ) elif key == "native-permission-enforcement": add_error(errors, bool(str(provenance.get("target", "")).strip()), "native-permission-enforcement provenance.target is required") + if not template_expected: + require_real_text(errors, provenance.get("target", ""), "native-permission-enforcement provenance.target") add_error( errors, bool(str(provenance.get("guard_location", "")).strip()), "native-permission-enforcement provenance.guard_location is required", ) + if not template_expected: + require_real_text( + errors, + provenance.get("guard_location", ""), + "native-permission-enforcement provenance.guard_location", + ) add_error( errors, str(provenance.get("guard_scope", "")).strip() @@ -238,6 +276,14 @@ def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> No ) elif key == "native-client-telemetry": add_error(errors, bool(str(provenance.get("client", "")).strip()), "native-client-telemetry provenance.client is required") + if not template_expected: + require_real_text(errors, provenance.get("client", ""), "native-client-telemetry provenance.client") + if str(provenance.get("native_host_manifest", "")).strip(): + require_real_text( + errors, + provenance.get("native_host_manifest", ""), + "native-client-telemetry provenance.native_host_manifest", + ) add_error(errors, provenance.get("event_source") == "external", "native-client-telemetry event_source must be external") add_error(errors, provenance.get("metadata_only") is True, "native-client-telemetry must be metadata_only") @@ -266,6 +312,13 @@ def validate_payload( add_error(errors, bool(str(payload.get("submitted_by", "")).strip()), "submitted_by is required") add_error(errors, bool(str(payload.get("submitted_at", "")).strip()), "submitted_at is required") add_error(errors, bool(str(payload.get("summary", "")).strip()), "summary is required") + if not template_expected: + require_real_text(errors, payload.get("submitted_by", ""), "submitted_by") + add_error( + errors, + bool(SUBMITTED_AT_RE.match(str(payload.get("submitted_at", "")).strip())), + "submitted_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ", + ) artifact_integrity = validate_artifact_refs(payload, errors, root=root, template_expected=template_expected) privacy = payload.get("privacy", {}) if isinstance(payload.get("privacy", {}), dict) else {} for key in REQUIRED_PRIVACY_FALSE: diff --git a/tests/verify_world_class_evidence_intake.py b/tests/verify_world_class_evidence_intake.py index a4c84edf..e175f5ff 100644 --- a/tests/verify_world_class_evidence_intake.py +++ b/tests/verify_world_class_evidence_intake.py @@ -159,6 +159,7 @@ def main() -> None: assert "`python3 scripts/yao.py world-class-ledger .`" in markdown, markdown assert "Templates and planned work do not count as accepted evidence." in markdown, markdown assert "Real submissions must include the evidence-key critical artifact paths with verified SHA-256 digests." in markdown, markdown + assert "Real submissions must replace template submitter, date, and provenance placeholders with concrete evidence metadata." in markdown, markdown kit_dir = TMP / "submission_kit" kit_proc = run_kit("--output-dir", str(kit_dir), "--evidence-key", "provider-holdout") @@ -219,6 +220,23 @@ def main() -> None: assert valid_checklist["provider-holdout"]["submission_path"].endswith("tests/tmp_world_class_evidence_intake/valid_submissions/provider-holdout.json"), valid_checklist["provider-holdout"] assert "tests/tmp_world_class_evidence_intake/valid_submissions" in valid_checklist["provider-holdout"]["commands"]["validate_intake"], valid_checklist["provider-holdout"] + placeholder_dir = TMP / "placeholder_submissions" + placeholder_dir.mkdir() + placeholder_submission = provider_submission(valid=True) + placeholder_submission["submitted_by"] = "operator with provider credentials" + placeholder_submission["submitted_at"] = "YYYY-MM-DD" + (placeholder_dir / "provider-holdout.json").write_text( + json.dumps(placeholder_submission, ensure_ascii=False, indent=2) + "\n", + encoding="utf-8", + ) + placeholder_payload = run_intake("--submissions-dir", str(placeholder_dir)) + assert placeholder_payload["ok"] is False, placeholder_payload + assert placeholder_payload["summary"]["decision"] == "fix-intake", placeholder_payload["summary"] + assert placeholder_payload["summary"]["invalid_submission_count"] == 1, placeholder_payload["summary"] + placeholder_errors = placeholder_payload["submissions"][0]["errors"] + assert any("submitted_by must not use template placeholder text" in error for error in placeholder_errors), placeholder_errors + assert any("submitted_at must use YYYY-MM-DD" in error for error in placeholder_errors), placeholder_errors + invalid_dir = TMP / "invalid_submissions" invalid_dir.mkdir() (invalid_dir / "provider-holdout.json").write_text( diff --git a/tests/verify_world_class_evidence_ledger.py b/tests/verify_world_class_evidence_ledger.py index 7dbe2dcf..4196e9fa 100644 --- a/tests/verify_world_class_evidence_ledger.py +++ b/tests/verify_world_class_evidence_ledger.py @@ -263,6 +263,50 @@ def main() -> None: for error in unrelated_accepted_provider["submission_state"]["errors"] ), unrelated_accepted_provider + placeholder_accepted_submissions = TMP / "placeholder_accepted_submissions" + placeholder_accepted_submissions.mkdir() + placeholder_submission = provider_submission(accepted_source_skill) + placeholder_submission["submitted_by"] = "operator with provider credentials" + placeholder_submission["submitted_at"] = "YYYY-MM-DD" + (placeholder_accepted_submissions / "provider-holdout.json").write_text( + json.dumps(placeholder_submission, ensure_ascii=False, indent=2) + "\n", + encoding="utf-8", + ) + placeholder_accepted_proc = subprocess.run( + [ + sys.executable, + str(SCRIPT), + str(accepted_source_skill), + "--output-json", + str(TMP / "placeholder_accepted_provider_ledger.json"), + "--output-md", + str(TMP / "placeholder_accepted_provider_ledger.md"), + "--submissions-dir", + str(placeholder_accepted_submissions), + "--generated-at", + "2026-06-13", + ], + cwd=ROOT, + capture_output=True, + text=True, + check=True, + ) + placeholder_accepted_payload = json.loads(placeholder_accepted_proc.stdout) + placeholder_accepted_summary = placeholder_accepted_payload["summary"] + assert placeholder_accepted_summary["source_accepted_count"] == 1, placeholder_accepted_summary + assert placeholder_accepted_summary["accepted_count"] == 0, placeholder_accepted_summary + assert placeholder_accepted_summary["invalid_submission_count"] == 1, placeholder_accepted_summary + placeholder_accepted_provider = { + entry["key"]: entry for entry in placeholder_accepted_payload["entries"] + }["provider-holdout"] + assert placeholder_accepted_provider["source_accepted"] is True, placeholder_accepted_provider + assert placeholder_accepted_provider["status"] == "pending", placeholder_accepted_provider + assert placeholder_accepted_provider["submission_state"]["status"] == "invalid-contract", placeholder_accepted_provider + assert any( + "submitted_by must not use template placeholder text" in error + for error in placeholder_accepted_provider["submission_state"]["errors"] + ), placeholder_accepted_provider + accepted_submissions = TMP / "accepted_submissions" accepted_submissions.mkdir() (accepted_submissions / "provider-holdout.json").write_text(