Files
wehub-resource-sync 23f7624596
ADR-166 MCP Bridge Security Lock / Static-source security lock (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / Compose default binds loopback + Mongo has auth (push) Failing after 2s
CodeQL Advanced / Analyze (rust) (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / plugin-agent-federation bindHost default (push) Failing after 1s
ADR-166 MCP Bridge Security Lock / Runtime behavior — 401 + terminal gate + fail-closed (push) Failing after 4s
business-pods-smoke / smoke (push) Failing after 1s
all-plugins-smoke / smoke-all (push) Failing after 2s
CI/CD Pipeline / Security & Code Quality (push) Failing after 1s
CI/CD Pipeline / Test Suite (ubuntu-latest) (push) Failing after 1s
CI/CD Pipeline / Build & Package (macos-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (ubuntu-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (windows-latest) (push) Has been skipped
CI/CD Pipeline / Documentation & Examples (push) Failing after 1s
Clone Tracker (14-day rolling) / Snapshot clones for ruflo ecosystem (push) Failing after 1s
CodeQL Advanced / Analyze (actions) (push) Failing after 1s
CodeQL Advanced / Analyze (javascript-typescript) (push) Failing after 1s
federation-peer-rust / stable-noop (push) Failing after 1s
metaharness-ci / score (push) Failing after 1s
metaharness-ci / router-compat (push) Failing after 0s
metaharness-ci / similarity-tests (push) Failing after 0s
no-agentbbs-smoke / smoke-without-agentbbs (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (windows-latest) (push) Has been skipped
codex-integration-audit / Codex integration audit (push) Failing after 1s
helpers-manifest-guard / guard (push) Failing after 1s
🔗 Cross-Agent Integration Tests / 🤝 Agent Coordination Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🧠 Memory Sharing Integration (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🛡️ Fault Tolerance Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / ⚡ Performance Integration Tests (push) Has been skipped
metaharness-ci / mcp-scan (push) Failing after 1s
metaharness-ci / eject-dryrun (push) Failing after 1s
metaharness-ci / metaharness-real-data (push) Failing after 0s
no-cli-optdep-bloat-2561 / guard (push) Failing after 1s
no-metaharness-smoke / smoke-without-metaharness (push) Failing after 1s
no-phantom-agentic-flow-subpath / guard (push) Failing after 1s
🔄 Automated Rollback Manager / 🚨 Failure Detection (push) Failing after 1s
V3 CI/CD Pipeline / Plugin hooks smoke / ubuntu-latest / Node 22 (push) Failing after 1s
V3 CI/CD Pipeline / ruflo-graph-intelligence build + test smoke (#2044, ADR-123) (push) Failing after 1s
CVE Audit Gate / Audit root (critical-blocking) (push) Failing after 2s
cost-tracker-smoke / smoke (push) Failing after 3s
oia-audit-weekly / audit (push) Failing after 2s
ruflo-agent-smoke / ruflo-agent structural smoke (push) Failing after 1s
📊 Status Badges Update / 📊 Update Status Badges (push) Failing after 1s
V3 CI/CD Pipeline / Static regression guards (#2267 YAML + (push) Failing after 1s
V3 CI/CD Pipeline / Test V3 Packages (push) Failing after 0s
V3 CI/CD Pipeline / agent_execute provider routing smoke (#2042) (push) Failing after 0s
CVE Audit Gate / Audit v3 (critical-blocking) (push) Failing after 1s
federation-peer-rust / stable-native (push) Failing after 2s
🔗 Cross-Agent Integration Tests / 🚀 Integration Test Setup (push) Failing after 2s
neural-trader-smoke / runtime-smoke (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (macos-latest) (push) Has been skipped
V3 CI/CD Pipeline / Build V3 (ubuntu-latest) (push) Has been skipped
V3 CI/CD Pipeline / Type Check V3 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 24 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 22 (push) Failing after 2s
V3 CI/CD Pipeline / browser rvf create flag smoke (#2015) (push) Failing after 0s
V3 CI/CD Pipeline / Dependency review (#2046) (push) Has been skipped
V3 CI/CD Pipeline / Supply-chain audit (#2046) (push) Failing after 0s
V3 CI/CD Pipeline / witness marker drift smoke (#2021) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader portfolio CG smoke (#2068, ADR-126 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader backtest signing smoke (#2068, ADR-126 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / kg-extract type-import classification smoke (#2049) (push) Failing after 0s
V3 CI/CD Pipeline / witness verify precondition smoke (#1880) (push) Failing after 2s
V3 CI/CD Pipeline / neural-trader pipeline risk-gate smoke (#2068, ADR-126 Phase 5) (push) Failing after 0s
V3 CI/CD Pipeline / neural-trader feature attribution smoke (#2068, ADR-126 Phase 6) (push) Failing after 0s
V3 CI/CD Pipeline / plugin-registry signature verification smoke (#1922, CWE-347) (push) Failing after 4s
V3 CI/CD Pipeline / memory stats legacy-DB smoke (#2120) (push) Failing after 4s
V3 CI/CD Pipeline / github deprecated actions smoke (#2089, ADR-127 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / graph query + pathfinder smoke (ADR-130 P2+P5) (push) Has been skipped
V3 CI/CD Pipeline / graph trajectory hooks smoke (ADR-130 P3) (push) Has been skipped
V3 CI/CD Pipeline / graph plugin adapter smoke (ADR-130 P4) (push) Has been skipped
V3 CI/CD Pipeline / graph benchmark (ADR-130 P6) (push) Has been skipped
V3 CI/CD Pipeline / statusline generator delegation smoke (#2195) (push) Failing after 1s
V3 CI/CD Pipeline / wizard init regression guard (#2206 (push) Failing after 1s
V3 CI/CD Pipeline / memory no-stray-db smoke (ADR-125 P7) (push) Failing after 1s
V3 CI/CD Pipeline / github-safe injection smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github actions pin smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github attribution opt-in smoke (#2089, ADR-127 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / pre-bash hook safety smoke (#2017) (push) Failing after 1s
V3 CI/CD Pipeline / Memory import smoke / ubuntu-latest (push) Failing after 0s
V3 CI/CD Pipeline / MCP protocol smoke / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / ruvllm WASM auto-init smoke (#2086) (push) Failing after 4s
V3 CI/CD Pipeline / MCP paired-tool round-trip smoke (#1889) (push) Failing after 1s
V3 CI/CD Pipeline / Plugin package install-safety (#1902/#1903/#1904) (push) Failing after 1s
V3 CI/CD Pipeline / Tool description discoverability (ADR-112) (push) Failing after 3s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (22) (push) Failing after 1s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (24) (push) Failing after 1s
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Vector-index dimension audit (#1947) (push) Failing after 0s
V3 CI/CD Pipeline / Hook-command install safety (#1921) (push) Failing after 1s
V3 CI/CD Pipeline / ToolOutputGuardrail smoke (ADR-131, (push) Failing after 1s
V3 CI/CD Pipeline / init-bundle invariants smoke (#2095, ADR-128 Phase 5) (push) Failing after 1s
V3 CI/CD Pipeline / wasm provider bridge smoke (ADR-129 P1) (push) Failing after 2s
V3 CI/CD Pipeline / wasm gallery CRUD smoke (ADR-129 P3) (push) Failing after 1s
V3 CI/CD Pipeline / wasm plugin bridge smoke (ADR-129 P4) (push) Failing after 0s
V3 CI/CD Pipeline / wasm compose smoke (ADR-129 P2) (push) Failing after 4s
V3 CI/CD Pipeline / graph schema smoke (ADR-130 P1) (push) Failing after 0s
Validate Marketplace / validate (push) Failing after 1s
🔍 Verification Pipeline / 🚀 Setup Verification (push) Failing after 1s
🔍 Verification Pipeline / 🛡️ Security Verification (push) Has been skipped
🔍 Verification Pipeline / 📝 Code Quality (push) Has been skipped
🔍 Verification Pipeline / 🧪 Test Verification (${{ matrix.os }}, Node ${{ matrix.node }}) (push) Has been skipped
🔍 Verification Pipeline / 🏗️ Build Verification (push) Has been skipped
🔍 Verification Pipeline / 📚 Documentation Verification (push) Has been skipped
CVE Audit Gate / High-severity report (warn only) (push) Has been cancelled
🔄 Automated Rollback Manager / 🔄 Execute Rollback (push) Has been cancelled
🔄 Automated Rollback Manager / ✅ Post-Rollback Verification (push) Has been cancelled
🔄 Automated Rollback Manager / 📊 Rollback Monitoring (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / windows-latest (push) Has been cancelled
🔄 Automated Rollback Manager / ⏳ Manual Rollback Approval (push) Has been cancelled
V3 CI/CD Pipeline / MCP protocol smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Memory import smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / ubuntu-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Publish to npm (alpha) (push) Has been cancelled
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / macos-latest / Node 22 (push) Has been cancelled
V3 CI/CD Pipeline / Plugin hooks smoke / macos-latest / Node 22 (push) Has been cancelled
CI/CD Pipeline / Deploy & Release (push) Has been cancelled
CI/CD Pipeline / CI Status (push) Has been cancelled
🔗 Cross-Agent Integration Tests / 📊 Integration Test Report (push) Has been cancelled
🔄 Automated Rollback Manager / 🔍 Pre-Rollback Validation (push) Has been cancelled
🔍 Verification Pipeline / ⚡ Performance Verification (push) Has been cancelled
🔍 Verification Pipeline / 📊 Verification Report (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:02:19 +08:00

212 lines
5.7 KiB
JSON

{
"label": "single-round proof-of-mechanism",
"disclaimers": [
"not flywheel proof",
"not compounding learning",
"not production learning"
],
"generation": 0,
"parent": null,
"branch": "main",
"kind": "synthetic",
"createdAt": 1700000000000,
"inputHoldoutHash": "sha256:3cb58b6d4cd6fe6f0fa1f114d604b5743963eb96c3b9648508bf2ea502dad9f9",
"baselineManifestHash": "sha256:ea6643a45ebd3578fedfbe44774d22327f6852115c8670c5ae2996652060f6d8",
"candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
"meetsPromotionRule": {
"version": "accept/v1+sig",
"result": true
},
"decisionReceipt": {
"promotionRuleVersion": "accept/v1+sig",
"verdictInputs": {
"heldOutScore": 0.7520000000000001,
"baselineHeldOutScore": 0.656,
"redblue": "PASS",
"drift": 0,
"driftThreshold": 0.05,
"replayDeterministic": true,
"receiptCoverage": 1,
"canaryRollbackRate": 0,
"baselineRollbackRate": 0
},
"result": {
"accept": true,
"terms": {
"held_out_improves": {
"value": "0.7520 > 0.6560",
"pass": true
},
"redblue_pass": {
"value": "PASS",
"pass": true
},
"drift_within": {
"value": "0 <= 0.05",
"pass": true
},
"replay_deterministic": {
"value": true,
"pass": true
},
"receipt_coverage_full": {
"value": 1,
"pass": true
},
"canary_no_worse": {
"value": "0 <= 0",
"pass": true
}
},
"failed": []
},
"significant": true,
"deltaCILow": 0.07600000000000004,
"promoted": true,
"reason": "promoted (all accept/v1+sig terms held)"
},
"shadow": {
"registrationId": "shadow:44b2b4e021f61a1482f1c3e8794517d4abcb490398d73dbaa70be96978cf39c0",
"state": "shadow",
"served": false,
"candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
"registeredAt": 1700000000000
},
"costReceipt": {
"usd": 0,
"llmCalls": 0,
"tier": "synthetic",
"notes": "deterministic synthetic round — no model, no network, no real store"
},
"mutationClass": "retrieval:multi",
"mutationSummary": "alpha:0.5→0.3, bodyWeight:1→1.5, mmrLambda:0.7→0.5, subjectWeight:2→1, typePenaltyFactor:1→0.5",
"deltas": {
"benchmark": 0.09600000000000009,
"security": 0,
"cost": 0
},
"promotion": {
"parentManifestHash": null,
"candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
"mutationClass": "retrieval:multi",
"mutationSummary": "alpha:0.5→0.3, bodyWeight:1→1.5, mmrLambda:0.7→0.5, subjectWeight:2→1, typePenaltyFactor:1→0.5",
"deltas": {
"benchmark": 0.09600000000000009,
"security": 0,
"cost": 0
},
"decisionReceipt": {
"promotionRuleVersion": "accept/v1+sig",
"verdictInputs": {
"heldOutScore": 0.7520000000000001,
"baselineHeldOutScore": 0.656,
"redblue": "PASS",
"drift": 0,
"driftThreshold": 0.05,
"replayDeterministic": true,
"receiptCoverage": 1,
"canaryRollbackRate": 0,
"baselineRollbackRate": 0
},
"result": {
"accept": true,
"terms": {
"held_out_improves": {
"value": "0.7520 > 0.6560",
"pass": true
},
"redblue_pass": {
"value": "PASS",
"pass": true
},
"drift_within": {
"value": "0 <= 0.05",
"pass": true
},
"replay_deterministic": {
"value": true,
"pass": true
},
"receipt_coverage_full": {
"value": 1,
"pass": true
},
"canary_no_worse": {
"value": "0 <= 0",
"pass": true
}
},
"failed": []
},
"significant": true,
"deltaCILow": 0.07600000000000004,
"promoted": true,
"reason": "promoted (all accept/v1+sig terms held)"
}
},
"regression": null,
"holdout": [
{
"taskId": "t0",
"baselineScore": 0.6,
"candidateScore": 0.7
},
{
"taskId": "t1",
"baselineScore": 0.8,
"candidateScore": 0.86
},
{
"taskId": "t2",
"baselineScore": 0.5,
"candidateScore": 0.62
},
{
"taskId": "t3",
"baselineScore": 0.72,
"candidateScore": 0.8
},
{
"taskId": "t4",
"baselineScore": 0.66,
"candidateScore": 0.78
}
],
"baselineManifest": {
"schema": "ruflo.proven-config/v1",
"policy": {
"ref": "sha256:0e7ffc6910134ff6ec2c1074165ee4571ed5df973c777b613c6dac6fea1c46a8",
"value": {
"alpha": 0.5,
"subjectWeight": 2,
"mmrLambda": 0.7,
"bodyWeight": 1,
"typePenaltyFactor": 1
}
},
"layer": "synthetic/proof",
"benchmark": {
"corpus": "synthetic-proof-v1",
"corpusHash": "sha256:3b8a34acbcd0e385ca4d9ddc177f8ea93152d98c29c46d9286419b492beded1b"
}
},
"candidateManifest": {
"schema": "ruflo.proven-config/v1",
"policy": {
"ref": "sha256:6141a8ea990c5063b77e090ae8f37f9c539d8aa8f58dcceb30f3a82f97e57319",
"value": {
"alpha": 0.3,
"subjectWeight": 1,
"mmrLambda": 0.5,
"bodyWeight": 1.5,
"typePenaltyFactor": 0.5
}
},
"layer": "synthetic/proof",
"benchmark": {
"corpus": "synthetic-proof-v1",
"corpusHash": "sha256:3b8a34acbcd0e385ca4d9ddc177f8ea93152d98c29c46d9286419b492beded1b"
}
}
}