@ryuenn3123/agentic-senior-core 4.4.0 → 5.1.0

package/.agent-context/state/benchmark-comparison-schema.json

@@ -1,181 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "Benchmark Before-vs-After Comparison",
-  "description": "Schema for comparing benchmark results across releases or configuration changes. Each entry captures quality, bug signal, runtime, and token metrics for a before and after snapshot.",
-  "type": "object",
-  "required": ["schemaVersion", "comparisonId", "generatedAt", "before", "after", "delta"],
-  "properties": {
-    "schemaVersion": {
-      "type": "string",
-      "const": "1.0.0"
-    },
-    "comparisonId": {
-      "type": "string",
-      "description": "Unique identifier for this comparison run."
-    },
-    "generatedAt": {
-      "type": "string",
-      "format": "date-time"
-    },
-    "baselineVersion": {
-      "type": "string",
-      "description": "Package version of the before snapshot."
-    },
-    "candidateVersion": {
-      "type": "string",
-      "description": "Package version of the after snapshot."
-    },
-    "comparisonType": {
-      "type": "string",
-      "enum": ["release-to-release", "config-change", "model-swap", "manual"],
-      "description": "What triggered this comparison."
-    },
-    "before": { "$ref": "#/$defs/snapshot" },
-    "after": { "$ref": "#/$defs/snapshot" },
-    "delta": { "$ref": "#/$defs/deltaReport" },
-    "verdict": {
-      "type": "string",
-      "enum": ["pass", "warn", "fail"],
-      "description": "Overall comparison verdict based on threshold policy."
-    },
-    "verdictReason": {
-      "type": "string",
-      "description": "Human-readable explanation of the verdict."
-    }
-  },
-  "$defs": {
-    "snapshot": {
-      "type": "object",
-      "required": ["capturedAt", "quality", "runtime"],
-      "properties": {
-        "capturedAt": {
-          "type": "string",
-          "format": "date-time"
-        },
-        "packageVersion": {
-          "type": "string"
-        },
-        "quality": {
-          "type": "object",
-          "properties": {
-            "top1Accuracy": {
-              "type": "number",
-              "minimum": 0,
-              "maximum": 1,
-              "description": "Fraction of scenarios where the top-ranked output was correct."
-            },
-            "manualCorrectionRate": {
-              "type": "number",
-              "minimum": 0,
-              "maximum": 1,
-              "description": "Fraction of outputs requiring human correction."
-            },
-            "averageJudgeScore": {
-              "type": "number",
-              "minimum": 0,
-              "maximum": 10,
-              "description": "Mean score across all judge dimensions."
-            },
-            "scenarioCount": {
-              "type": "integer",
-              "minimum": 1
-            }
-          }
-        },
-        "bugSignal": {
-          "type": "object",
-          "properties": {
-            "validationFailures": {
-              "type": "integer",
-              "minimum": 0,
-              "description": "Number of validation check failures."
-            },
-            "securityWarnings": {
-              "type": "integer",
-              "minimum": 0
-            },
-            "deprecationWarnings": {
-              "type": "integer",
-              "minimum": 0
-            }
-          }
-        },
-        "runtime": {
-          "type": "object",
-          "properties": {
-            "totalDurationMs": {
-              "type": "number",
-              "description": "Total benchmark suite execution time in milliseconds."
-            },
-            "averageScenarioDurationMs": {
-              "type": "number"
-            },
-            "peakMemoryMb": {
-              "type": "number"
-            }
-          }
-        },
-        "token": {
-          "type": "object",
-          "properties": {
-            "nativeSavingsPercent": {
-              "type": "number",
-              "description": "Token savings from native optimization."
-            },
-            "proxySavingsPercent": {
-              "type": "number",
-              "description": "Token savings from external proxy optimization."
-            },
-            "totalInputTokens": {
-              "type": "integer"
-            },
-            "totalOutputTokens": {
-              "type": "integer"
-            }
-          }
-        }
-      }
-    },
-    "deltaReport": {
-      "type": "object",
-      "properties": {
-        "top1AccuracyChange": {
-          "type": "number",
-          "description": "After minus before. Positive means improvement."
-        },
-        "manualCorrectionRateChange": {
-          "type": "number",
-          "description": "After minus before. Negative means improvement."
-        },
-        "averageJudgeScoreChange": {
-          "type": "number"
-        },
-        "validationFailureChange": {
-          "type": "integer"
-        },
-        "totalDurationMsChange": {
-          "type": "number"
-        },
-        "nativeSavingsChange": {
-          "type": "number"
-        },
-        "regressionDetected": {
-          "type": "boolean",
-          "description": "True if any metric crossed a threshold in the wrong direction."
-        },
-        "regressionDetails": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "properties": {
-              "metric": { "type": "string" },
-              "threshold": { "type": "number" },
-              "actual": { "type": "number" },
-              "direction": { "type": "string", "enum": ["increase", "decrease"] }
-            }
-          }
-        }
-      }
-    }
-  }
-}

package/.agent-context/state/benchmark-reproducibility.json

@@ -1,87 +0,0 @@
-{
-  "version": "1.0.0",
-  "phase": "v2.5.1",
-  "updatedAt": "2026-04-13",
-  "deterministicRuntime": {
-    "timezone": "UTC",
-    "locale": "C",
-    "nodeMajor": "22",
-    "lineEndings": "LF-preferred",
-    "shellNotes": "PowerShell and POSIX shells are supported; prefer portable commands for benchmark reruns."
-  },
-  "scenarios": [
-    {
-      "id": "planning",
-      "category": "planning",
-      "inputReferences": [
-        ".agent-context/state/architecture-map.md",
-        ".agent-context/state/dependency-map.md",
-        ".agent-context/rules/architecture.md"
-      ],
-      "expectedSignals": [
-        "clear sequencing",
-        "risk mapping",
-        "rollback path"
-      ],
-      "primaryCommand": "npm run benchmark:detection"
-    },
-    {
-      "id": "refactor",
-      "category": "refactor",
-      "inputReferences": [
-        "tests/cli-smoke.test.mjs",
-        "scripts/validate.mjs"
-      ],
-      "expectedSignals": [
-        "regression awareness",
-        "small safe diffs",
-        "test-backed changes"
-      ],
-      "primaryCommand": "npm run benchmark:gate"
-    },
-    {
-      "id": "security",
-      "category": "security",
-      "inputReferences": [
-        ".agent-context/rules/security.md",
-        "scripts/forbidden-content-check.mjs"
-      ],
-      "expectedSignals": [
-        "secret hygiene",
-        "unsafe pattern detection",
-        "release blocking on risk"
-      ],
-      "primaryCommand": "npm run gate:release"
-    },
-    {
-      "id": "delivery",
-      "category": "delivery",
-      "inputReferences": [
-        "scripts/release-gate.mjs",
-        "scripts/benchmark-intelligence.mjs",
-        "scripts/benchmark-gate.mjs"
-      ],
-      "expectedSignals": [
-        "release readiness",
-        "static external watchlist retirement",
-        "no stale benchmark research dependency"
-      ],
-      "primaryCommand": "npm run benchmark:intelligence"
-    }
-  ],
-  "rerunInstructions": [
-    "Run npm run benchmark:detection to regenerate detection benchmark output.",
-    "Run npm run benchmark:gate to validate benchmark anti-regression thresholds.",
-    "Run npm run benchmark:intelligence to confirm static external benchmark watchlists stay retired.",
-    "Run npm run benchmark:bundle to emit a reproducible benchmark evidence bundle.",
-    "Run npm run benchmark:writer-judge to emit writer-judge side-by-side matrix output."
-  ],
-  "commandExamples": [
-    "npm run benchmark:detection",
-    "npm run benchmark:gate",
-    "npm run benchmark:intelligence",
-    "npm run benchmark:bundle",
-    "npm run benchmark:writer-judge",
-    "node ./scripts/benchmark-evidence-bundle.mjs --stdout-only"
-  ]
-}

package/.agent-context/state/benchmark-thresholds.json

@@ -1,10 +0,0 @@
-{
-  "minimumTop1Accuracy": 0.9,
-  "maximumManualCorrectionRate": 0.12,
-  "maximumTop1AccuracyDrop": 0.02,
-  "maximumManualCorrectionIncrease": 0.03,
-  "previousReleaseBaseline": {
-    "top1Accuracy": 0.9167,
-    "manualCorrectionRate": 0.0833
-  }
-}

package/.agent-context/state/benchmark-writer-judge-config.json

@@ -1,58 +0,0 @@
-{
-  "version": "1.0.0",
-  "phase": "v2.5.1",
-  "blindReviewMode": true,
-  "writerLane": {
-    "models": [
-      {
-        "id": "writer-copilot-balanced",
-        "provider": "github-copilot",
-        "profile": "balanced"
-      },
-      {
-        "id": "writer-claude-architect",
-        "provider": "anthropic",
-        "profile": "architect"
-      },
-      {
-        "id": "writer-gemini-ops",
-        "provider": "google",
-        "profile": "operations"
-      }
-    ],
-    "weights": {
-      "quality": 40,
-      "efficiency": 20,
-      "reliability": 25,
-      "freshness": 15
-    },
-    "scenarioMultipliers": {
-      "planning": 1,
-      "refactor": 1.02,
-      "security": 1.03,
-      "delivery": 0.98
-    }
-  },
-  "judgeLane": {
-    "models": [
-      {
-        "id": "judge-claude-audit",
-        "provider": "anthropic",
-        "profile": "audit"
-      },
-      {
-        "id": "judge-gpt-risk",
-        "provider": "openai",
-        "profile": "risk"
-      }
-    ],
-    "minimumCompositeScore": 75,
-    "leniencyWindow": 2,
-    "weights": {
-      "clarity": 35,
-      "correctness": 35,
-      "risk": 20,
-      "consistency": 10
-    }
-  }
-}

package/.agent-context/state/dependency-map.md

@@ -1,41 +0,0 @@
-# Dependency Map
-
-Use this map to keep Agentic-Senior-Core's CLI, governance, and validation layers from collapsing into circular or over-coupled code.
-
-## Allowed Dependency Direction
-
-1. `bin/` may call command modules only.
-2. `lib/cli/commands/**` may orchestrate detector, compiler, scaffolder, memory, token, backup, rollback, preflight, and utility modules.
-3. `lib/cli/compiler.mjs` may read constants and utilities, but must not import command modules.
-4. `lib/cli/project-scaffolder/**` may use utilities and local scaffolder submodules; validation logic stays below the scaffolder entrypoint.
-5. `scripts/**` may call CLI library modules for audits and reports, but release/validation scripts must avoid mutating generated state unless that is their explicit job.
-6. `tests/**` may exercise public CLI commands, public module exports, scripts, and generated artifacts.
-7. `.agent-context/**` stores governance data and must not depend on generated adapter content as its authority.
-
-## Module Constraints
-
-| Source | Allowed Dependencies | Forbidden Dependencies |
-| --- | --- | --- |
-| `bin/agentic-senior-core.js` | `lib/cli/commands/*` | direct compiler, scaffolder, or validation internals |
-| `lib/cli/commands/init.mjs` | detector, compiler, scaffolder, token/memory continuity, setup helpers | UI style presets, backend framework defaults, generated adapters as source |
-| `lib/cli/commands/upgrade.mjs` | detector, compiler, scaffolder seeds, backup/rollback, shared setup helpers | duplicated setup-policy helpers, silent stack migration |
-| `lib/cli/project-scaffolder.mjs` | stable public scaffolder exports | private validation helpers that do not need public API exposure |
-| `lib/cli/project-scaffolder/design-contract.mjs` | validation submodule, constants, utilities | hardcoded final palettes, fixed layouts, external design memory |
-| `scripts/sync-thin-adapters.mjs` | `AGENTS.md` and native import bridge targets | hand-maintained duplicate policy blocks |
-| `scripts/validate*.mjs` | config, coverage checks, file evidence | stale V2 skill-marketplace artifacts |
-| `.agent-context/prompts/bootstrap-design.md` | current repo evidence and frontend rule | prior-chat visuals, unrelated screenshots, template style presets |
-
-## Circular Dependency Guardrail
-
-- Reject `commands -> project-scaffolder -> commands`.
-- Reject `compiler -> commands`.
-- Reject `scripts/validate -> tests`.
-- Reject generated adapters becoming inputs for `AGENTS.md` or `.agent-context/`.
-- Move repeated command setup policy into shared helper modules instead of copying local functions.
-
-## Package Hygiene
-
-- Keep one npm lockfile: `package-lock.json`.
-- Ignore Bun lockfiles unless the package manager strategy changes explicitly.
-- Keep generated reports out of the shipped package.
-- Keep `onboarding-report.json` tracked only as current repo operational state; installed projects regenerate it.

package/.agent-context/state/memory-adapter-contract.json

@@ -1,52 +0,0 @@
-{
-  "schemaVersion": "1.0.0",
-  "contractName": "cross-agent-memory-adapter",
-  "description": "Adapter contract for ingesting and retrieving shared memory observations across IDE hosts.",
-  "requiredAdapters": [
-    "claude-code",
-    "gemini-cli",
-    "vscode-chat"
-  ],
-  "requiredOperations": {
-    "ingestion": [
-      "captureObservation",
-      "captureSessionSummary"
-    ],
-    "retrieval": [
-      "searchIndex",
-      "getTimeline",
-      "getObservations"
-    ],
-    "privacy": [
-      "applyPrivateTagRedaction",
-      "applyInlineSecretRedaction"
-    ]
-  },
-  "adapters": [
-    {
-      "adapterId": "claude-code",
-      "hostType": "plugin-hooks",
-      "status": "pilot-ready",
-      "ingestionEvents": ["SessionStart", "UserPromptSubmit", "PostToolUse", "Stop", "SessionEnd"],
-      "retrievalMode": "mcp-tools"
-    },
-    {
-      "adapterId": "gemini-cli",
-      "hostType": "plugin-hooks",
-      "status": "pilot-ready",
-      "ingestionEvents": ["session_start", "prompt_submit", "post_tool", "session_end"],
-      "retrievalMode": "mcp-tools"
-    },
-    {
-      "adapterId": "vscode-chat",
-      "hostType": "chat-customization-plugin",
-      "status": "pilot-ready",
-      "ingestionEvents": ["chatStart", "promptSubmit", "postToolUse", "chatEnd"],
-      "retrievalMode": "mcp-tools"
-    }
-  ],
-  "notes": [
-    "Web chat hosts are explicitly out of scope for this pilot because local runtime hooks are unavailable.",
-    "Adapters should emit provider-agnostic payloads matching .agent-context/state/memory-schema-v1.json."
-  ]
-}

package/.agent-context/state/memory-schema-v1.json

@@ -1,88 +0,0 @@
-{
-  "schemaVersion": "1.0.0",
-  "schemaName": "cross-agent-memory-observation",
-  "description": "Provider-agnostic schema for persistent memory observations shared across coding agents and IDE hosts.",
-  "requiredFields": [
-    "id",
-    "projectId",
-    "sessionId",
-    "adapterId",
-    "eventType",
-    "timestamp",
-    "title",
-    "summary",
-    "detail",
-    "privacy"
-  ],
-  "fieldDefinitions": {
-    "id": {
-      "type": "string",
-      "description": "Stable unique observation identifier."
-    },
-    "projectId": {
-      "type": "string",
-      "description": "Repository or workspace identifier."
-    },
-    "sessionId": {
-      "type": "string",
-      "description": "Source session identifier from host adapter."
-    },
-    "adapterId": {
-      "type": "string",
-      "allowedValues": ["claude-code", "gemini-cli", "vscode-chat", "custom"],
-      "description": "Host adapter that captured this observation."
-    },
-    "eventType": {
-      "type": "string",
-      "allowedValues": ["prompt", "tool-use", "decision", "summary", "issue", "context"],
-      "description": "Observation type for retrieval filtering."
-    },
-    "timestamp": {
-      "type": "string",
-      "format": "date-time",
-      "description": "ISO timestamp when observation was captured."
-    },
-    "title": {
-      "type": "string",
-      "description": "Compact human-readable headline."
-    },
-    "summary": {
-      "type": "string",
-      "description": "Compact session-start payload used for progressive disclosure."
-    },
-    "detail": {
-      "type": "string",
-      "description": "Expanded observation text fetched on demand."
-    },
-    "tags": {
-      "type": "array",
-      "items": "string",
-      "description": "Optional normalized tags for query refinement."
-    },
-    "privacy": {
-      "type": "object",
-      "requiredFields": ["level", "redactionApplied"],
-      "fieldDefinitions": {
-        "level": {
-          "type": "string",
-          "allowedValues": ["public", "internal", "restricted"],
-          "description": "Privacy classification level."
-        },
-        "redactionApplied": {
-          "type": "boolean",
-          "description": "Indicates whether privacy sanitization modified payload content."
-        },
-        "redactionReasons": {
-          "type": "array",
-          "items": "string",
-          "description": "Redaction reason tags such as private-tag or token-like-value."
-        }
-      }
-    }
-  },
-  "retrievalContract": {
-    "sessionStartPayload": ["id", "adapterId", "eventType", "timestamp", "title", "summary"],
-    "onDemandPayload": ["detail", "tags", "privacy"],
-    "progressiveDisclosure": true
-  }
-}

package/GEMINI.md

@@ -1 +0,0 @@
-@AGENTS.md

package/benchmarks/README.md

@@ -1,60 +0,0 @@
-# Benchmarks
-
-Reproducible measurement suites for this repository. Release-facing claims must point to tracked JSON evidence under `benchmarks/results/` or to deterministic benchmark commands that print machine-readable output.
-
-## Folder Structure
-
-```text
-benchmarks/
-|-- anti-halu/              Provider-free anti-hallucination fixtures and scorer
-|-- compact-natural-mode/   Response compression fixtures and scorer
-|-- runtime-token-saver/    ASCX command-output compression fixtures
-|-- token-usage/            Provider token-counting and cache simulation benchmark
-|-- results/                Tracked release evidence JSON
-`-- README.md
-```
-
-## Active Benchmarks
-
-| Suite | Folder | Status | Output |
-| --- | --- | --- | --- |
-| Token usage baseline | `token-usage/` | Historical release evidence | `results/baseline-{YYYY-MM-DD}.json` |
-| Cache simulation | `token-usage/` | Historical release evidence | `results/cache-phase-2-{YYYY-MM-DD}.json` |
-| Anti-halu benchmark | `anti-halu/` | Active deterministic gate | `results/anti-halu-phase-3-{YYYY-MM-DD}.json` |
-| ASCX runtime token saver | `runtime-token-saver/` | Active deterministic gate | stdout via `npm run benchmark:ascx` |
-| Compact Natural Mode | `compact-natural-mode/` | Active deterministic gate | stdout via `npm run benchmark:compact-natural` |
-| Release benchmark bundle | `results/` | Active integrity gate | `results/release-bundle-{semver}.json` |
-
-## Running Benchmarks
-
-Use the package scripts for active gates:
-
-```bash
-npm run benchmark:adaptive-context
-npm run benchmark:ascx
-npm run benchmark:compact-natural
-npm run benchmark:anti-halu
-npm run build:release-bundle
-npm run audit:release-bundle
-```
-
-See `benchmarks/token-usage/README.md` for the provider token-counting benchmark details.
-
-## Reproducibility Requirements
-
-1. Use Node 22 or the runtime version documented by the current package metadata.
-2. Do not add runtime dependencies to the core package for benchmark-only work. Benchmark tooling belongs in `devDependencies`.
-3. Keep JSON output deterministic where possible. If timestamps or host facts vary, isolate them in metadata fields.
-4. Include schema version, timestamp, and tooling version when a result file is tracked so older evidence remains interpretable.
-
-## Result Files Convention
-
-- Track release evidence under `benchmarks/results/*.json`.
-- Use `{suite-name}-{YYYY-MM-DD}.json` or `{suite-name}-{semver}.json`.
-- Do not store raw API responses, secrets, tokens, or user data.
-- Historical phase outcomes are consolidated in `docs/archive/HISTORY.md`.
-- Live benchmark reporting rules are in `docs/benchmark-reference.md`.
-
-## Why This Exists
-
-Claims such as "40% token saving" or "rule adherence improved" need reproducible evidence. These suites are the comparator surface for README, changelog, release, and planning claims.