{"_id":"@ai-operations/cord-adapter","name":"@ai-operations/cord-adapter","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@ai-operations/cord-adapter","version":"0.1.0","description":"CORD safety gate adapter for AI Operations OS — 14-dimension constitutional AI scoring with SPARK integration","private":false,"main":"dist/index.js","types":"dist/index.d.ts","scripts":{"build":"tsc","clean":"rm -rf dist"},"dependencies":{"@ai-operations/shared-types":"*","@ai-operations/ops-storage":"*"},"optionalDependencies":{"cord-engine":"^4.3.0"},"devDependencies":{"typescript":"^5.7.0"},"repository":{"type":"git","url":"git+https://github.com/zanderone1980/ai-operations-os.git","directory":"packages/cord-adapter"},"bugs":{"url":"https://github.com/zanderone1980/ai-operations-os/issues"},"author":{"name":"Alex Pinkevich","email":"alex@zanderpinkdesign.com"},"license":"MIT","publishConfig":{"registry":"https://registry.npmjs.org","access":"public"},"keywords":["ai-ops","ai-agents","workflow","automation","safety"],"_id":"@ai-operations/cord-adapter@0.1.0","gitHead":"5479e60c372e0d4d5269e3fd1f87915563e9a87d","homepage":"https://github.com/zanderone1980/ai-operations-os#readme","_nodeVersion":"22.22.0","_npmVersion":"10.9.4","dist":{"integrity":"sha512-f2Mxu6dsoFDeZFJO9B3n76u2g5+kGLeHsW6aPW3GrcLVqTVmAwkksYQyCsjJHa44sNI+Ad7qwyHsiA4V9c6d9w==","shasum":"f940f829bc7e6aee92f919f171567baefc565899","tarball":"https://registry.npmjs.org/@ai-operations/cord-adapter/-/cord-adapter-0.1.0.tgz","fileCount":18,"unpackedSize":60801,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQC44/0lScqQqcDAEF1hN7CajCDSDneBUHWjzkukVSSxaQIhAJqVJ88Cd9Fvzk103gg2U3nhj8Nh2BMbQfU1/nFRAoL9"}]},"_npmUser":{"name":"alexpinkone","email":"pinkevich1980@gmail.com"},"directories":{},"maintainers":[{"name":"alexpinkone","email":"pinkevich1980@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/cord-adapter_0.1.0_1773153575571_0.6761681579880507"},"_hasShrinkwrap":false}},"time":{"created":"2026-03-10T14:39:35.448Z","0.1.0":"2026-03-10T14:39:35.742Z","modified":"2026-03-10T14:39:36.009Z"},"maintainers":[{"name":"alexpinkone","email":"pinkevich1980@gmail.com"}],"description":"CORD safety gate adapter for AI Operations OS — 14-dimension constitutional AI scoring with SPARK integration","homepage":"https://github.com/zanderone1980/ai-operations-os#readme","keywords":["ai-ops","ai-agents","workflow","automation","safety"],"repository":{"type":"git","url":"git+https://github.com/zanderone1980/ai-operations-os.git","directory":"packages/cord-adapter"},"author":{"name":"Alex Pinkevich","email":"alex@zanderpinkdesign.com"},"bugs":{"url":"https://github.com/zanderone1980/ai-operations-os/issues"},"license":"MIT","readme":"# @ai-operations/cord-adapter\n\n> CORD safety gate, policy simulation, and forensic timeline analysis for AI Operations OS.\n\nPart of [AI Operations OS](https://github.com/zanderone1980/ai-operations-os) — autonomous business workflow orchestration with safety enforcement.\n\n## Install\n\n```\nnpm install @ai-operations/cord-adapter\n```\n\n`cord-engine` is an optional dependency. When not installed, `CordSafetyGate` defaults to ALLOW for all evaluations so the system can operate in permissive mode.\n\n## Quick Start\n\n```ts\nimport { CordSafetyGate, PolicySimulator } from '@ai-operations/cord-adapter';\n\nconst gate = new CordSafetyGate();\nconst result = gate.evaluateAction('gmail', 'send', { to: 'user@example.com', subject: 'Hi' });\n\nif (result.decision === 'BLOCK') {\n  console.error('Action blocked:', result.reasons);\n}\n```\n\n## API\n\n### `CordSafetyGate`\n\nWraps cord-engine to evaluate proposed connector actions against safety policies before execution. Gracefully degrades to ALLOW when cord-engine is not installed.\n\n```ts\nconstructor()\nevaluateAction(connector: string, operation: string, input: Record<string, unknown>): SafetyResult\nisAvailable(): boolean\n```\n\n- `SafetyResult` — `{ decision: CordDecision; score: number; reasons: string[]; hardBlock: boolean }`\n- `CordDecision` — `'ALLOW' | 'CONTAIN' | 'CHALLENGE' | 'BLOCK'`\n\nOperations are mapped to CORD tool categories: `communication`, `publication`, `destructive`, `scheduling`, `financial`, `readonly`.\n\n### `PolicySimulator`\n\nDry-run safety evaluation for projected actions. Runs a batch of actions through CordSafetyGate without executing them.\n\n```ts\nconstructor(gate?: CordSafetyGate)\nsimulate(actions: ProjectedAction[]): SimulationReport\n```\n\n```ts\nconst sim = new PolicySimulator();\nconst report = sim.simulate([\n  { connector: 'gmail', operation: 'send', input: { to: 'a@b.com' } },\n  { connector: 'shopify', operation: 'refund', input: { amount: 200 } },\n]);\nconsole.log(report.summary);     // { ALLOW: 1, CONTAIN: 1 }\nconsole.log(report.allAllowed);   // false\nconsole.log(report.hasHardBlock); // false\n```\n\n- `SimulationReport` — `{ entries, summary, maxScore, hasHardBlock, allAllowed }`\n\n### `ForensicEngine`\n\nSession-level forensic timeline analysis. Loads a task's full execution history from storage and builds a chronological, color-coded timeline for audit and debugging.\n\n```ts\nconstructor(stores?: Stores)\nasync loadSession(sessionId: string): Promise<void>\nbuildTimeline(): ForensicTimeline\nrenderTimeline(): void   // Colored CLI output\ngetTimeline(): ForensicTimeline | null\n```\n\n- `TimelineEvent` — `{ timestamp, category, label, detail?, connector?, operation?, cordDecision?, cordScore? }`\n- Event categories: `action | decision | approval | error | system`\n\n## Related Packages\n\n- [`@ai-operations/shared-types`](../shared-types) — CordDecision, ActionReceipt types\n- [`@ai-operations/ops-core`](../ops-core) — WorkflowEngine uses CordSafetyGate as its SafetyGate\n- [`@ai-operations/ops-storage`](../ops-storage) — ForensicEngine reads session data from stores\n- [`@ai-operations/ops-policy`](../ops-policy) — Policy rules complementing CORD evaluation\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-e92c388a50a9ff799bffa163093561c2"}