mirror of
https://github.com/callstack/agent-device.git
synced 2026-09-14 20:06:34 +08:00
8cce0ef6b8
* test: ratchet mutation score over enumerated decision kernels Adds a Stryker (vitest runner) mutation lane scoped to the decision kernels, a per-module baseline with tool/config provenance, and a ratchet that only lets scores rise. Non-gating until two consecutive stable weekly sweeps. Refs #1415 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore: declare the mutation test-scope seam for production-export analysis Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: own kernel tests in the mutation registry and ship the #1430 lane envelope - restore bench:help-conformance, broken by a formatting-path edit - kernel test files select their module on PRs (registry `tests` + workflow paths), asserted to reach the kernel through the import graph - every mutation run writes the standard scheduled-lane artifact envelope - move src/utils/__tests__/errors.test.ts beside its source per the mirror rule Refs #1415, #1430 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: derive kernel test ownership and land the scheduled-lane health monitor Ownership of a kernel's tests is now computed from the static import graph (scripts/mutation/ownership.ts) instead of a hand-listed set, so a test that reaches a kernel indirectly -- src/__tests__/daemon-error.test.ts through src/daemon.ts -- selects that kernel on a PR. The PR lane triggers on every src test and shards the derived modules, keeping wall clock at one module. The lane envelope (#1430) is now written on every exit path with the stage it reached, so a crash before any mutant runs is distinguishable from a lane that never ran. Adds the derived cadence monitor (scripts/lane-health, daily workflow): scheduled lanes are enumerated from .github/workflows/ and reported dark, failing, or never-run against their own cron cadence. * fix: merge only Stryker reports from a shard directory The shard artifacts now carry the lane envelope beside mutation.json, and the merge globbed every .json under the download path, so the ratchet job fed the envelope to the report parser and died after the mutants had already run. * fix(mutation): fail on incomplete shard sets and envelope pre-run failures Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(mutation): downgrade a passing envelope when a later lane step fails Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(mutation): shard by registry, defer the PR lane, drop the bundled watcher Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * docs: describe registry sharding and the deferred PR mutation lane Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(mutation): make the pre-graduation tooling exception select real mutants Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(mutation): give the worktree fixture commits their own identity Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Michał Pierzchała <thymikee@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
70 lines
2.3 KiB
TypeScript
70 lines
2.3 KiB
TypeScript
// Standard artifact envelope for scheduled lanes (issue #1430).
|
|
//
|
|
// A scheduled lane can go dark or drift for weeks while PR CI stays green, so
|
|
// every artifact it uploads must say — without a human reading logs — which
|
|
// commit produced it, which tool/config version measured it, how long it took,
|
|
// and whether it passed. Freshness monitoring reads `finishedAt`/`result`; drift
|
|
// analysis reads `tool`/`configHash`.
|
|
//
|
|
// Lanes that adopt the envelope later should import this module rather than
|
|
// re-deriving the field names.
|
|
|
|
export const LANE_ENVELOPE_SCHEMA_VERSION = 1;
|
|
|
|
export type LaneResult = 'pass' | 'fail';
|
|
|
|
export type LaneEnvelope<T> = {
|
|
schemaVersion: number;
|
|
/** Stable lane id — the metric key freshness/health jobs group by. */
|
|
lane: string;
|
|
commit: string;
|
|
ref: string | undefined;
|
|
runUrl: string | undefined;
|
|
/** Tool versions, or content hashes where a version is not enough. */
|
|
tool: Record<string, string>;
|
|
configHash: string;
|
|
/** Only lanes with randomized input record a seed; `null` states "not applicable". */
|
|
seed: string | null;
|
|
startedAt: string;
|
|
finishedAt: string;
|
|
durationMs: number;
|
|
result: LaneResult;
|
|
/** Lane-specific payload; kept separate so the envelope shape stays stable. */
|
|
data: T;
|
|
};
|
|
|
|
export type LaneEnvelopeInput<T> = {
|
|
lane: string;
|
|
commit: string;
|
|
tool: Record<string, string>;
|
|
configHash: string;
|
|
startedAtMs: number;
|
|
result: LaneResult;
|
|
data: T;
|
|
seed?: string | null;
|
|
now?: number;
|
|
};
|
|
|
|
export function laneEnvelope<T>(input: LaneEnvelopeInput<T>): LaneEnvelope<T> {
|
|
const finished = input.now ?? Date.now();
|
|
const { GITHUB_SERVER_URL, GITHUB_REPOSITORY, GITHUB_RUN_ID, GITHUB_REF_NAME } = process.env;
|
|
return {
|
|
schemaVersion: LANE_ENVELOPE_SCHEMA_VERSION,
|
|
lane: input.lane,
|
|
commit: input.commit,
|
|
ref: GITHUB_REF_NAME,
|
|
runUrl:
|
|
GITHUB_SERVER_URL && GITHUB_REPOSITORY && GITHUB_RUN_ID
|
|
? `${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}`
|
|
: undefined,
|
|
tool: input.tool,
|
|
configHash: input.configHash,
|
|
seed: input.seed ?? null,
|
|
startedAt: new Date(input.startedAtMs).toISOString(),
|
|
finishedAt: new Date(finished).toISOString(),
|
|
durationMs: Math.max(0, finished - input.startedAtMs),
|
|
result: input.result,
|
|
data: input.data,
|
|
};
|
|
}
|