chore: refresh falsey world-class HTML evidence

This commit is contained in:
yaojingang
2026-06-14 14:27:15 +08:00
parent fd5a790df9
commit 7ae32ed87e
18 changed files with 199 additions and 170 deletions
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
}
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
+36 -22
View File
@@ -3,23 +3,36 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 12,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.md",
" M reports/registry_audit.json",
" M reports/registry_audit.md",
" M reports/security_trust_report.json",
" M reports/security_trust_report.md",
" M reports/upgrade_check.json",
" M reports/world_class_operator_runbook.html"
],
"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": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974",
"source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -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": 12
},
"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": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"ready": false,
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"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": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974"
"sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -137,8 +151,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2cf2125532768f1508c9315e34da939fad4f1e82d208a8e396448ae566d58e7d"
"bytes": 7965,
"sha256": "d8028784464931bc1d44ce097feb95e531682ee5172f4e9680da7a11f93b2b98"
},
{
"label": "blind_review",
@@ -173,7 +187,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 99433,
"sha256": "7970e6e10389ab71f62ac9d4fef94156af0190c4f4cd20ba50628c6c20f88730"
"sha256": "7fccfda339c51073eb1c8325ac7740e7c6f44f4067b4ba66cba1afd5f095ac25"
},
{
"label": "python_compatibility",
@@ -187,14 +201,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "05064b43ac6b246bedf978f8ca7b6d8815598eb2ecf38fe7ff8e2fae0a2540c2"
"sha256": "f919e3f7834aee8891c5cc97a26ea9f8045b30b3c41e0bf6bbe9a1c13ee63d83"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "855a53df171f5265cbe270b753c6b88ca472619053f7daa1aa5c8550da20fb4d"
"sha256": "53af9d5a90682b65f190cd9b0cf99aaa1496cb3d16c7199df06d5bdfa0ded491"
},
{
"label": "install_simulation",
@@ -256,8 +270,8 @@
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 17601,
"sha256": "fccbe471168acd7f87fb1f0111753d6a2213ad26f41593512f915183a14feddc"
"bytes": 17616,
"sha256": "b94a0e9d92b6609eb6c06e608b52aa17174638bc1422e3b3d306521906bccb01"
},
{
"label": "world_class_claim_guard",
+17 -16
View File
@@ -1,19 +1,19 @@
# Benchmark Reproducibility
Generated at: `2026-06-14`
Commit: `a5d6a39782c8d990a7203e116ec3ba8f720b2061`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974`
Commit: `fd5a790df90b2b6faad58b671c42171186504bac`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `24`
- missing artifacts: `0`
- source contract sha256: `2911f884e900`
- archive sha256: `a514212a268d`
- source contract sha256: `ec040d5f83c4`
- archive sha256: `2204fd96f426`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `21`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd68
- 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: `12`
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: `24` / `24`
- sha256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974`
- sha256: `5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53`
## 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 | `2cf212553276` |
| output_execution | `reports/output_execution_runs.json` | present | `d80287844649` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
| trust_report | `reports/security_trust_report.json` | present | `7970e6e10389` |
| trust_report | `reports/security_trust_report.json` | present | `7fccfda339c5` |
| python_compatibility | `reports/python_compatibility.json` | present | `ae16e17266e4` |
| registry_audit | `reports/registry_audit.json` | present | `05064b43ac6b` |
| package_verification | `reports/package_verification.json` | present | `855a53df171f` |
| registry_audit | `reports/registry_audit.json` | present | `f919e3f7834a` |
| package_verification | `reports/package_verification.json` | present | `53af9d5a9068` |
| install_simulation | `reports/install_simulation.json` | present | `1ed7ce5266c2` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6bb2dcb0e1e5` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `164803bb1cea` |
@@ -89,7 +90,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `a6d609911ed5` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `443e0335d270` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `4bd789775307` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `fccbe471168a` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `b94a0e9d92b6` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `250d616b028c` |
## Reproduction Commands
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.08,
"duration_ms": 32.05,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.94,
"duration_ms": 32.15,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.49,
"duration_ms": 36.28,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.72,
"duration_ms": 35.12,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.52,
"duration_ms": 31.6,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.16,
"duration_ms": 31.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.79,
"duration_ms": 30.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.0,
"duration_ms": 30.67,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.79,
"duration_ms": 30.85,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.72,
"duration_ms": 30.65,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
+10 -10
View File
@@ -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 | 26.08 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 25.94 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 27.49 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.72 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 26.52 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.16 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.79 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.0 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.79 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.72 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 32.05 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 32.15 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 36.28 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.12 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 31.6 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.55 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.2 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.67 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.85 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.65 | 98 | 100.0 | pass |
## Next Fixes
+1 -1
View File
@@ -8,7 +8,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c`
- Archive SHA256: `2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710`
- Failures: `0`
- Warnings: `0`
+4 -4
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"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": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0`
- Archive SHA256: `a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c`
- Package SHA256: `ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c`
- Archive SHA256: `2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710`
- Install simulated: `True`
## Compatibility
+6 -6
View File
@@ -543,7 +543,7 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
@@ -615,7 +615,7 @@
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>98</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>98</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>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。</p></div>
</section>
@@ -673,8 +673,8 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
</section>
<section class="twocol">
@@ -694,12 +694,12 @@
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c</code></dd></div></dl></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710</code></dd></div></dl></div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>577</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c</code></dd></div></dl></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>577</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710</code></dd></div></dl></div>
</section>
<section class="twocol">
+69 -55
View File
@@ -1332,13 +1332,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974",
"source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -1356,11 +1356,11 @@
"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": 12
},
"commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"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.",
@@ -1465,7 +1465,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
},
"skill_atlas": {
"skill_count": 12,
@@ -1503,8 +1503,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -1535,7 +1535,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1551,7 +1551,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1630,12 +1630,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
@@ -3967,7 +3967,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.08,
"duration_ms": 32.05,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3995,7 +3995,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.94,
"duration_ms": 32.15,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4018,7 +4018,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.49,
"duration_ms": 36.28,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4046,7 +4046,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.72,
"duration_ms": 35.12,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4069,7 +4069,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.52,
"duration_ms": 31.6,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4097,7 +4097,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.16,
"duration_ms": 31.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4120,7 +4120,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.79,
"duration_ms": 30.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4147,7 +4147,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.0,
"duration_ms": 30.67,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4170,7 +4170,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.79,
"duration_ms": 30.85,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4199,7 +4199,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.72,
"duration_ms": 30.65,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4920,23 +4920,36 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 12,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.md",
" M reports/registry_audit.json",
" M reports/registry_audit.md",
" M reports/security_trust_report.json",
" M reports/security_trust_report.md",
" M reports/upgrade_check.json",
" M reports/world_class_operator_runbook.html"
],
"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": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974",
"source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -4954,14 +4967,15 @@
"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": 12
},
"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)",
@@ -4970,10 +4984,10 @@
"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": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"ready": false,
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"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)",
@@ -4981,7 +4995,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974"
"sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5054,8 +5068,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2cf2125532768f1508c9315e34da939fad4f1e82d208a8e396448ae566d58e7d"
"bytes": 7965,
"sha256": "d8028784464931bc1d44ce097feb95e531682ee5172f4e9680da7a11f93b2b98"
},
{
"label": "blind_review",
@@ -5090,7 +5104,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 99433,
"sha256": "7970e6e10389ab71f62ac9d4fef94156af0190c4f4cd20ba50628c6c20f88730"
"sha256": "7fccfda339c51073eb1c8325ac7740e7c6f44f4067b4ba66cba1afd5f095ac25"
},
{
"label": "python_compatibility",
@@ -5104,14 +5118,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "05064b43ac6b246bedf978f8ca7b6d8815598eb2ecf38fe7ff8e2fae0a2540c2"
"sha256": "f919e3f7834aee8891c5cc97a26ea9f8045b30b3c41e0bf6bbe9a1c13ee63d83"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "855a53df171f5265cbe270b753c6b88ca472619053f7daa1aa5c8550da20fb4d"
"sha256": "53af9d5a90682b65f190cd9b0cf99aaa1496cb3d16c7199df06d5bdfa0ded491"
},
{
"label": "install_simulation",
@@ -5173,8 +5187,8 @@
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 17601,
"sha256": "fccbe471168acd7f87fb1f0111753d6a2213ad26f41593512f915183a14feddc"
"bytes": 17616,
"sha256": "b94a0e9d92b6609eb6c06e608b52aa17174638bc1422e3b3d306521906bccb01"
},
{
"label": "world_class_claim_guard",
@@ -10813,7 +10827,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
},
"failures": [],
"warnings": [],
@@ -18427,8 +18441,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -18459,7 +18473,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -18484,7 +18498,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
@@ -18507,7 +18521,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -19515,12 +19529,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
+15 -15
View File
@@ -919,13 +919,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974",
"source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -943,11 +943,11 @@
"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": 12
},
"commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"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.",
@@ -1052,7 +1052,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
},
"skill_atlas": {
"skill_count": 12,
@@ -1090,8 +1090,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -1122,7 +1122,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1138,7 +1138,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1217,12 +1217,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
+1 -1
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
},
"failures": [],
"warnings": [],
+1 -1
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `182`
- Package SHA256: `2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0`
- Package SHA256: `ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c`
## Failures
+15 -15
View File
@@ -918,13 +918,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974",
"source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -942,11 +942,11 @@
"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": 12
},
"commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"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.",
@@ -1051,7 +1051,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
},
"skill_atlas": {
"skill_count": 12,
@@ -1089,8 +1089,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0",
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
"compatibility": {
"openai": "pass",
@@ -1121,7 +1121,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1137,7 +1137,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1216,12 +1216,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
+2 -2
View File
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c"
"to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0"
"to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c"
}
]
},
+5 -5
View File
@@ -57,7 +57,7 @@
<span class="eyebrow">Evidence Operations</span>
<h1>World-Class Operator Runbook</h1>
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong></strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong></strong></article></div>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
</section>
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
@@ -76,7 +76,7 @@
<section><h4>Privacy</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Run provider-backed output-exec with real credentials.</li><li>Provider execution should return non-estimated token usage.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Provider model run</span><code>model_executed_count: / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='source-check pass'><span>Timing observed</span><code>timing_observed_count: 10 / &gt;0</code><small>Provider execution should record timing metadata.</small></li><li class='source-check blocked'><span>Token usage observed</span><code>token_observed_count: / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Provider model run</span><code>model_executed_count: 0 / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='source-check pass'><span>Timing observed</span><code>timing_observed_count: 10 / &gt;0</code><small>Provider execution should record timing metadata.</small></li><li class='source-check blocked'><span>Token usage observed</span><code>token_observed_count: 0 / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>human · awaiting-submission</span><h3>Human Adjudication</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -93,7 +93,7 @@
<section><h4>Privacy</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Record a reviewer choice for every pair.</li><li>Every pair needs one valid human judgment.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check pass'><span>Review pairs exist</span><code>pair_count: 5 / &gt;0</code><small>Generate the blind A/B review pack.</small></li><li class='source-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='source-check blocked'><span>Judgments complete</span><code>judgment_count: / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li><li class='source-check pass'><span>No invalid decisions</span><code>invalid_decision_count: / ==0</code><small>Fix malformed winner/confidence entries.</small></li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check pass'><span>Review pairs exist</span><code>pair_count: 5 / &gt;0</code><small>Generate the blind A/B review pack.</small></li><li class='source-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='source-check blocked'><span>Judgments complete</span><code>judgment_count: 0 / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li><li class='source-check pass'><span>No invalid decisions</span><code>invalid_decision_count: 0 / ==0</code><small>Fix malformed winner/confidence entries.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>external · awaiting-submission</span><h3>Native Permission Enforcement</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -110,7 +110,7 @@
<section><h4>Privacy</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Collect real target-client or external runtime guard proof.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Native enforcement</span><code>native_enforcement_count: / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li><li class='source-check pass'><span>Probe failures</span><code>failure_count: / ==0</code><small>Runtime permission probes must stay clean.</small></li><li class='source-check pass'><span>Installer support</span><code>installer_enforcement_ready: True / true</code><small>Installer enforcement is supporting evidence, not native proof.</small></li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Native enforcement</span><code>native_enforcement_count: 0 / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li><li class='source-check pass'><span>Probe failures</span><code>failure_count: 0 / ==0</code><small>Runtime permission probes must stay clean.</small></li><li class='source-check pass'><span>Installer support</span><code>installer_enforcement_ready: True / true</code><small>Installer enforcement is supporting evidence, not native proof.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>external · awaiting-submission</span><h3>Native Client Telemetry</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -127,7 +127,7 @@
<section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
</article></div></section>
<section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
</main>