@cassiomc1/forgeloop 1.8.0 → 1.8.1

package/docs/AGENT_PROTOCOL_SUMMARY.md

@@ -7,7 +7,7 @@
 ForgeLoop is a portable protocol and support CLI for verifiable engineering workflows. It records and validates task state, contracts, routing, checks, evidence, continuity, and optional code attestations. It does not become an agent scheduler, delegation service, source-control authority, or secret manager.
 
 Protocol version: 1
-Package version: 1.8.0
+Package version: 1.8.1
 
 ## Canonical loop
 

package/docs/EXECUTION_PROFILE_BENCHMARKS.md

@@ -255,9 +255,12 @@ Before a host run exists, the summary is intentionally:
 
 Raw runs are stored below `benchmarks/execution-profiles/results/raw/` and
 recomputed aggregates below `benchmarks/execution-profiles/results/aggregate/`.
-The validator checks all scenario, raw-run, and aggregate schemas and
-recomputes aggregates from raw measurements. A changed overhead target is
-observable in the report; it is not a blocking lifecycle gate.
+Those recorded measurements are repository evidence and are intentionally not
+included in the core npm package. The package ships the deterministic scenario
+definitions and benchmark schemas needed to run a new measurement; the
+validator checks all scenario, raw-run, and aggregate schemas and recomputes
+aggregates from raw measurements. A changed overhead target is observable in
+the report; it is not a blocking lifecycle gate.
 
 CI can run `npm run benchmark:profiles:regression -- --json`. It reports
 `OK`, `EFFICIENCY_REGRESSION`, `NOT_MEASURED`, or `NOT_COMPARABLE`; a regression

package/docs/RELEASE_CHECKLIST.md

@@ -10,6 +10,9 @@ preparation and verification checklist; it does not authorize publication.
 - [ ] `PROTOCOL_VERSION` and the integration API version remain compatible.
 - [ ] `npm run release:identity` passes for the candidate version.
 - [ ] No release tag or registry version collision exists.
+- [ ] `npm pack --dry-run` contains the required scenario definitions but no
+      raw or aggregate benchmark results, tests, local state, or repository
+      metadata.
 
 ## Protocol and attestation
 
@@ -58,6 +61,8 @@ preparation and verification checklist; it does not authorize publication.
 - [ ] The exact validated commit is the release source.
 - [ ] GitHub Actions remain immutably pinned and use least-privilege permissions.
 - [ ] The npm workflow retains trusted OIDC publishing and explicit provenance.
+- [ ] The publication workflow fails closed when the candidate npm version
+      already exists or the package inspection finds forbidden paths.
 - [ ] Publication is performed only by the authorized release workflow.
 - [ ] Post-publication registry, tag, checksum, and release identity checks pass.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cassiomc1/forgeloop",
-  "version": "1.8.0",
+  "version": "1.8.1",
   "description": "Portable, verifiable engineering protocol for AI coding environments and developer workflows",
   "repository": {
     "type": "git",
@@ -22,7 +22,8 @@
     "src",
     "ENG",
     "schemas",
-    "benchmarks/execution-profiles",
+    "benchmarks/execution-profiles/*.json",
+    "benchmarks/execution-profiles/README.md",
     ".forgeloop/forgeloop.gitignore",
     "AGENTS.md",
     "CLAUDE.md",

package/benchmarks/execution-profiles/results/aggregate/codex-quality-repeat5-20260831/api-feature.json

@@ -1,552 +0,0 @@
-{
-  "schemaVersion": 1,
-  "benchmarkVersion": "1",
-  "runSetId": "codex-quality-repeat5-20260831",
-  "scenarioId": "api-feature",
-  "expectedProfile": "balanced",
-  "modeAggregates": {
-    "direct": {
-      "runCount": 5,
-      "verificationSuccessRate": 1,
-      "usageSources": [
-        "HOST_REPORTED"
-      ],
-      "totalTokens": {
-        "count": 5,
-        "average": 59078,
-        "p50": 56280,
-        "p95": 67514.4,
-        "minimum": 56105,
-        "maximum": 70250
-      },
-      "wallClockMs": {
-        "count": 5,
-        "average": 18534.6674,
-        "p50": 18008.7842,
-        "p95": 20778.556,
-        "minimum": 16579.167,
-        "maximum": 21038.59
-      },
-      "verificationCycles": {
-        "count": 5,
-        "average": 1,
-        "p50": 1,
-        "p95": 1,
-        "minimum": 1,
-        "maximum": 1
-      },
-      "comparableSteps": {
-        "count": 5,
-        "average": 4,
-        "p50": 4,
-        "p95": 4,
-        "minimum": 4,
-        "maximum": 4
-      },
-      "tokensPerComparableStep": {
-        "count": 5,
-        "average": 14769.5,
-        "p50": 14070,
-        "p95": 16878.6,
-        "minimum": 14026.25,
-        "maximum": 17562.5
-      },
-      "contextUsage": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "profiles": [],
-        "measuredRuns": 0,
-        "totalTokens": {
-          "count": 0,
-          "average": null,
-          "p50": null,
-          "p95": null,
-          "minimum": null,
-          "maximum": null
-        },
-        "items": {
-          "taskContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "guides": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "history": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "protocolInstructions": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "repositoryContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "other": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      },
-      "quality": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "scores": {
-          "visualQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "responsiveQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "accessibility": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "interactionPolish": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "requirementsCompleteness": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      }
-    },
-    "forgeloopBalanced": {
-      "runCount": 5,
-      "verificationSuccessRate": 1,
-      "usageSources": [
-        "HOST_REPORTED"
-      ],
-      "totalTokens": {
-        "count": 5,
-        "average": 63740.8,
-        "p50": 58391,
-        "p95": 72609.4,
-        "minimum": 57563,
-        "maximum": 72749
-      },
-      "wallClockMs": {
-        "count": 5,
-        "average": 20664.4763,
-        "p50": 19767.3477,
-        "p95": 22549.9598,
-        "minimum": 19194.4748,
-        "maximum": 22717.9043
-      },
-      "verificationCycles": {
-        "count": 5,
-        "average": 1,
-        "p50": 1,
-        "p95": 1,
-        "minimum": 1,
-        "maximum": 1
-      },
-      "comparableSteps": {
-        "count": 5,
-        "average": 4,
-        "p50": 4,
-        "p95": 4,
-        "minimum": 4,
-        "maximum": 4
-      },
-      "tokensPerComparableStep": {
-        "count": 5,
-        "average": 15935.2,
-        "p50": 14597.75,
-        "p95": 18152.35,
-        "minimum": 14390.75,
-        "maximum": 18187.25
-      },
-      "contextUsage": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "profiles": [
-          "balanced"
-        ],
-        "measuredRuns": 0,
-        "totalTokens": {
-          "count": 0,
-          "average": null,
-          "p50": null,
-          "p95": null,
-          "minimum": null,
-          "maximum": null
-        },
-        "items": {
-          "taskContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "guides": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "history": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "protocolInstructions": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "repositoryContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "other": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      },
-      "quality": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "scores": {
-          "visualQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "responsiveQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "accessibility": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "interactionPolish": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "requirementsCompleteness": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      }
-    },
-    "forgeloopAdaptive": {
-      "runCount": 5,
-      "verificationSuccessRate": 0.6,
-      "usageSources": [
-        "HOST_REPORTED"
-      ],
-      "totalTokens": {
-        "count": 5,
-        "average": 60282.8,
-        "p50": 57478,
-        "p95": 68718.2,
-        "minimum": 57345,
-        "maximum": 71471
-      },
-      "wallClockMs": {
-        "count": 5,
-        "average": 21523.2349,
-        "p50": 22457.2359,
-        "p95": 23335.5781,
-        "minimum": 18687.8011,
-        "maximum": 23501.7253
-      },
-      "verificationCycles": {
-        "count": 5,
-        "average": 1,
-        "p50": 1,
-        "p95": 1,
-        "minimum": 1,
-        "maximum": 1
-      },
-      "comparableSteps": {
-        "count": 5,
-        "average": 4,
-        "p50": 4,
-        "p95": 4,
-        "minimum": 4,
-        "maximum": 4
-      },
-      "tokensPerComparableStep": {
-        "count": 5,
-        "average": 15070.7,
-        "p50": 14369.5,
-        "p95": 17179.55,
-        "minimum": 14336.25,
-        "maximum": 17867.75
-      },
-      "contextUsage": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "profiles": [
-          "balanced"
-        ],
-        "measuredRuns": 0,
-        "totalTokens": {
-          "count": 0,
-          "average": null,
-          "p50": null,
-          "p95": null,
-          "minimum": null,
-          "maximum": null
-        },
-        "items": {
-          "taskContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "guides": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "history": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "protocolInstructions": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "repositoryContext": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "other": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      },
-      "quality": {
-        "sources": [
-          "UNKNOWN"
-        ],
-        "scores": {
-          "visualQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "responsiveQuality": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "accessibility": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "interactionPolish": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          },
-          "requirementsCompleteness": {
-            "count": 0,
-            "average": null,
-            "p50": null,
-            "p95": null,
-            "minimum": null,
-            "maximum": null
-          }
-        }
-      }
-    }
-  },
-  "comparisons": {
-    "direct": null,
-    "forgeloopBalanced": {
-      "comparablePairs": 5,
-      "tokenComparablePairs": 5,
-      "timeComparablePairs": 5,
-      "tokenOverheadPercent": {
-        "p50": 3.2154,
-        "p95": 23.3062
-      },
-      "timeOverheadPercent": {
-        "p50": 9.7491,
-        "p95": 24.2768
-      },
-      "claimStatus": "OBSERVATIONAL",
-      "claimAllowed": true,
-      "reason": "Trusted usage, actual timing, verification, and matching comparability metadata are present."
-    },
-    "forgeloopAdaptive": {
-      "comparablePairs": 3,
-      "tokenComparablePairs": 3,
-      "timeComparablePairs": 3,
-      "tokenOverheadPercent": {
-        "p50": 1.8923,
-        "p95": 1.9949
-      },
-      "timeOverheadPercent": {
-        "p50": 19.0659,
-        "p95": 24.138
-      },
-      "claimStatus": "OBSERVATIONAL",
-      "claimAllowed": true,
-      "reason": "Trusted usage, actual timing, verification, and matching comparability metadata are present."
-    }
-  },
-  "lightObjectives": null,
-  "sourcePolicy": "PROVIDER_REPORTED_OR_HOST_REPORTED_ONLY",
-  "claimsAllowed": true,
-  "generatedFromRunCount": 15,
-  "contextInflation": {
-    "status": "NOT_COMPARABLE",
-    "comparablePairs": 0,
-    "inflatedPairs": 0,
-    "lightContextTokens": {
-      "count": 0,
-      "average": null,
-      "p50": null,
-      "p95": null,
-      "minimum": null,
-      "maximum": null
-    },
-    "balancedContextTokens": {
-      "count": 0,
-      "average": null,
-      "p50": null,
-      "p95": null,
-      "minimum": null,
-      "maximum": null
-    },
-    "blocking": false,
-    "reason": "The adaptive mode did not resolve to LIGHT for this scenario."
-  }
-}