run402-mcp/sdk/dist/namespaces/errors.types.js

MCP server for Run402 — full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. Paid with x402/MPP. Includes $0.03 image generation.

/**
 * Request/response types for the `errors` namespace — the release-error-rollup
 * query surface (`GET /projects/v1/:project_id/errors` and
 * `GET /projects/v1/:project_id/errors/:fingerprint_id`).
 *
 * The platform keeps a durable, grouped error memory: every 5xx at the
 * gateway's invoke choke points is fingerprinted (normalization-first, so the
 * identity is deploy-stable) and collapsed into one hot row per distinct
 * failure. The read is **verdict-first**: the page leads with a computed
 * promote-vs-revert verdict for the release you name, then the grouped rows.
 *
 * The verdict math is the GATEWAY'S — never recomputed client-side. The SDK
 * never fingerprints, never re-baselines, never re-counts `new_fingerprints`.
 * It passes the envelope through untouched (index signatures keep unknown
 * future fields), and `watch` polls this surface and reads
 * `verdict.new_fingerprints` as the truth.
 *
 * Baseline semantics: `baseline_release_id` is the previous ACTIVE release by
 * ACTIVATION HISTORY (`releases.activated_at`, re-stamped on every activation),
 * NOT lineage — so after A→B→(rollback)→A→C, C's baseline is A and fingerprints
 * first seen under B are not misattributed to C. Cursors are OPAQUE keyset
 * tokens: store `next_cursor` and pass it back as `{ cursor }`, never parse it.
 */
export {};
//# sourceMappingURL=errors.types.js.map