@velum-labs/routekit-eval-setup 1.3.2 → 1.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/adapters/authoring-responses-request.d.ts +5 -0
- package/dist/adapters/authoring-responses-request.js +38 -0
- package/dist/adapters/evaluation-evidence-freshness.d.ts +7 -0
- package/dist/adapters/evaluation-evidence-freshness.js +76 -0
- package/dist/adapters/git-task-history.d.ts +67 -0
- package/dist/adapters/git-task-history.js +171 -0
- package/dist/adapters/integrated-repository-history.d.ts +21 -0
- package/dist/adapters/integrated-repository-history.js +175 -0
- package/dist/adapters/repository-command-diagnostic.d.ts +8 -0
- package/dist/adapters/repository-command-diagnostic.js +46 -0
- package/dist/adapters/repository-command-evidence.d.ts +13 -0
- package/dist/adapters/repository-command-evidence.js +102 -0
- package/dist/adapters/repository-command-runner.d.ts +238 -0
- package/dist/adapters/repository-command-runner.js +1483 -0
- package/dist/adapters/repository-import-context.d.ts +47 -0
- package/dist/adapters/repository-import-context.js +469 -0
- package/dist/adapters/repository-node-test-reporter.d.ts +3 -0
- package/dist/adapters/repository-node-test-reporter.js +27 -0
- package/dist/adapters/repository-review-evidence.d.ts +39 -0
- package/dist/adapters/repository-review-evidence.js +632 -0
- package/dist/adapters/repository-seed-selection.d.ts +7 -0
- package/dist/adapters/repository-seed-selection.js +79 -0
- package/dist/adapters/repository-solution-edits.d.ts +49 -0
- package/dist/adapters/repository-solution-edits.js +136 -0
- package/dist/adapters/repository-vitest-phase-adapter.d.ts +8 -0
- package/dist/adapters/repository-vitest-phase-adapter.js +310 -0
- package/dist/adapters/repository-vitest-reporter.d.ts +24 -0
- package/dist/adapters/repository-vitest-reporter.js +314 -0
- package/dist/adapters/strict-authoring-schema.d.ts +5 -0
- package/dist/adapters/strict-authoring-schema.js +158 -0
- package/dist/adapters/test-discovery.d.ts +30 -0
- package/dist/adapters/test-discovery.js +124 -0
- package/dist/adapters/typescript-repository-index.d.ts +51 -0
- package/dist/adapters/typescript-repository-index.js +226 -0
- package/dist/agentic-capabilities-protocol.d.ts +1373 -0
- package/dist/agentic-capabilities-protocol.js +786 -0
- package/dist/case-checkpoint-store.d.ts +29 -0
- package/dist/case-checkpoint-store.js +133 -0
- package/dist/case-pipeline-protocol-v2.d.ts +184 -0
- package/dist/case-pipeline-protocol-v2.js +193 -0
- package/dist/case-pipeline-protocol.d.ts +2626 -0
- package/dist/case-pipeline-protocol.js +371 -0
- package/dist/effect-api.d.ts +74 -10
- package/dist/effect-api.js +56 -6
- package/dist/errors.d.ts +31 -0
- package/dist/errors.js +10 -0
- package/dist/eval-capability-execution-envelope.d.ts +64 -0
- package/dist/eval-capability-execution-envelope.js +98 -0
- package/dist/eval-capability-policy.d.ts +90 -0
- package/dist/eval-capability-policy.js +107 -0
- package/dist/eval-event-log.d.ts +140 -0
- package/dist/eval-event-log.js +220 -0
- package/dist/evaluation-authoring-policy.d.ts +18 -0
- package/dist/evaluation-authoring-policy.js +19 -0
- package/dist/evaluation-authoring-validation.d.ts +22 -0
- package/dist/evaluation-authoring-validation.js +72 -0
- package/dist/evaluation-evidence.d.ts +20 -0
- package/dist/evaluation-evidence.js +319 -0
- package/dist/evaluation-grader-calibration-protocol.d.ts +108 -0
- package/dist/evaluation-grader-calibration-protocol.js +80 -0
- package/dist/evaluation-grader-calibration.d.ts +18 -0
- package/dist/evaluation-grader-calibration.js +334 -0
- package/dist/evaluation-grading-policy.d.ts +24 -0
- package/dist/evaluation-grading-policy.js +54 -0
- package/dist/evaluation-proposal-policy.d.ts +4 -0
- package/dist/evaluation-proposal-policy.js +91 -0
- package/dist/evaluation-source-retrieval.d.ts +68 -0
- package/dist/evaluation-source-retrieval.js +513 -0
- package/dist/evaluation-structure-policy.d.ts +29 -0
- package/dist/evaluation-structure-policy.js +138 -0
- package/dist/index.d.ts +124 -17
- package/dist/index.js +69 -11
- package/dist/inspection.js +2 -3
- package/dist/project-artifacts.d.ts +7 -2
- package/dist/project-artifacts.js +49 -136
- package/dist/project-authoring.d.ts +66 -5
- package/dist/project-authoring.js +783 -109
- package/dist/project-contracts.d.ts +419 -84
- package/dist/project-contracts.js +160 -52
- package/dist/project-store.js +2 -1
- package/dist/project-workflow.d.ts +5 -4
- package/dist/project-workflow.js +154 -35
- package/dist/repository-adversary-protocol.d.ts +64 -0
- package/dist/repository-adversary-protocol.js +105 -0
- package/dist/repository-behavior-protocol.d.ts +188 -0
- package/dist/repository-behavior-protocol.js +202 -0
- package/dist/repository-benchmark-protocol.d.ts +487 -0
- package/dist/repository-benchmark-protocol.js +96 -0
- package/dist/repository-execution-protocol.d.ts +150 -0
- package/dist/repository-execution-protocol.js +38 -0
- package/dist/repository-fixture-instructions.d.ts +3 -0
- package/dist/repository-fixture-instructions.js +91 -0
- package/dist/repository-fixture-protocol.d.ts +79 -0
- package/dist/repository-fixture-protocol.js +79 -0
- package/dist/repository-foundry-plan-protocol.d.ts +118 -0
- package/dist/repository-foundry-plan-protocol.js +296 -0
- package/dist/repository-foundry-progress-protocol.d.ts +52 -0
- package/dist/repository-foundry-progress-protocol.js +52 -0
- package/dist/repository-improvement-protocol.d.ts +100 -0
- package/dist/repository-improvement-protocol.js +106 -0
- package/dist/repository-language-model-protocol.d.ts +43 -0
- package/dist/repository-language-model-protocol.js +146 -0
- package/dist/repository-oracle-coverage-protocol.d.ts +18 -0
- package/dist/repository-oracle-coverage-protocol.js +39 -0
- package/dist/repository-oracle-execution-binding.d.ts +27 -0
- package/dist/repository-oracle-execution-binding.js +59 -0
- package/dist/repository-oracle-protocol.d.ts +230 -0
- package/dist/repository-oracle-protocol.js +156 -0
- package/dist/repository-oracle-scope-policy.d.ts +22 -0
- package/dist/repository-oracle-scope-policy.js +92 -0
- package/dist/repository-quality-policy.d.ts +15 -0
- package/dist/repository-quality-policy.js +357 -0
- package/dist/repository-routing-benchmark-protocol.d.ts +176 -0
- package/dist/repository-routing-benchmark-protocol.js +103 -0
- package/dist/repository-routing-model-protocol.d.ts +36 -0
- package/dist/repository-routing-model-protocol.js +89 -0
- package/dist/repository-routing-plan-protocol.d.ts +112 -0
- package/dist/repository-routing-plan-protocol.js +58 -0
- package/dist/repository-routing-quality-policy.d.ts +9 -0
- package/dist/repository-routing-quality-policy.js +191 -0
- package/dist/repository-seed-qualification-progress-protocol.d.ts +205 -0
- package/dist/repository-seed-qualification-progress-protocol.js +28 -0
- package/dist/repository-semantic-calibration-protocol.d.ts +768 -0
- package/dist/repository-semantic-calibration-protocol.js +276 -0
- package/dist/repository-semantic-calibration.d.ts +163 -0
- package/dist/repository-semantic-calibration.js +581 -0
- package/dist/repository-specification-contract-facts-protocol.d.ts +224 -0
- package/dist/repository-specification-contract-facts-protocol.js +276 -0
- package/dist/repository-specification-critique-protocol.d.ts +189 -0
- package/dist/repository-specification-critique-protocol.js +103 -0
- package/dist/repository-task-family-protocol.d.ts +24 -0
- package/dist/repository-task-family-protocol.js +37 -0
- package/dist/repository-task-seed-protocol.d.ts +384 -0
- package/dist/repository-task-seed-protocol.js +236 -0
- package/dist/repository-trajectory-protocol.d.ts +20 -0
- package/dist/repository-trajectory-protocol.js +42 -0
- package/dist/service.js +1 -1
- package/dist/services/adversary/service.d.ts +64 -0
- package/dist/services/adversary/service.js +330 -0
- package/dist/services/benchmark-compiler/service.d.ts +450 -0
- package/dist/services/benchmark-compiler/service.js +9 -0
- package/dist/services/budgeted-model/service.d.ts +118 -0
- package/dist/services/budgeted-model/service.js +460 -0
- package/dist/services/case-authoring/service.d.ts +163 -0
- package/dist/services/case-authoring/service.js +1456 -0
- package/dist/services/case-finalization/service.d.ts +283 -0
- package/dist/services/case-finalization/service.js +370 -0
- package/dist/services/case-generation/service.d.ts +619 -0
- package/dist/services/case-generation/service.js +2628 -0
- package/dist/services/case-pipeline/service.d.ts +31 -0
- package/dist/services/case-pipeline/service.js +485 -0
- package/dist/services/case-pipeline-v2/service.d.ts +70 -0
- package/dist/services/case-pipeline-v2/service.js +477 -0
- package/dist/services/command-observability/service.d.ts +13 -0
- package/dist/services/command-observability/service.js +3 -0
- package/dist/services/dimension-labeling/service.d.ts +77 -0
- package/dist/services/dimension-labeling/service.js +188 -0
- package/dist/services/eval-candidate/service.d.ts +208 -0
- package/dist/services/eval-candidate/service.js +64 -0
- package/dist/services/eval-capabilities/service.d.ts +183 -0
- package/dist/services/eval-capabilities/service.js +1433 -0
- package/dist/services/eval-environment/service.d.ts +173 -0
- package/dist/services/eval-environment/service.js +127 -0
- package/dist/services/evidence-reconstruction/service.d.ts +36 -0
- package/dist/services/evidence-reconstruction/service.js +145 -0
- package/dist/services/fixture-builder/service.d.ts +62 -0
- package/dist/services/fixture-builder/service.js +36 -0
- package/dist/services/fixture-validation/service.d.ts +75 -0
- package/dist/services/fixture-validation/service.js +295 -0
- package/dist/services/foundry/service.d.ts +831 -0
- package/dist/services/foundry/service.js +442 -0
- package/dist/services/foundry-progress/service.d.ts +62 -0
- package/dist/services/foundry-progress/service.js +149 -0
- package/dist/services/foundry-v2/service.d.ts +54 -0
- package/dist/services/foundry-v2/service.js +28 -0
- package/dist/services/grounded-authoring/service.d.ts +126 -0
- package/dist/services/grounded-authoring/service.js +822 -0
- package/dist/services/historical-case/service.d.ts +722 -0
- package/dist/services/historical-case/service.js +177 -0
- package/dist/services/improvement-loop/service.d.ts +59 -0
- package/dist/services/improvement-loop/service.js +176 -0
- package/dist/services/language-model/service.d.ts +52 -0
- package/dist/services/language-model/service.js +194 -0
- package/dist/services/oracle-builder/service.d.ts +146 -0
- package/dist/services/oracle-builder/service.js +513 -0
- package/dist/services/oracle-coverage/service.d.ts +28 -0
- package/dist/services/oracle-coverage/service.js +50 -0
- package/dist/services/oracle-coverage-witness/service.d.ts +130 -0
- package/dist/services/oracle-coverage-witness/service.js +538 -0
- package/dist/services/pipeline-challenge/service.d.ts +551 -0
- package/dist/services/pipeline-challenge/service.js +427 -0
- package/dist/services/pipeline-controls/service.d.ts +130 -0
- package/dist/services/pipeline-controls/service.js +483 -0
- package/dist/services/pipeline-oracle/service.d.ts +8 -0
- package/dist/services/pipeline-oracle/service.js +256 -0
- package/dist/services/pipeline-seed/service.d.ts +298 -0
- package/dist/services/pipeline-seed/service.js +428 -0
- package/dist/services/pipeline-spec/service.d.ts +103 -0
- package/dist/services/pipeline-spec/service.js +619 -0
- package/dist/services/pipeline-tournament/service.d.ts +258 -0
- package/dist/services/pipeline-tournament/service.js +476 -0
- package/dist/services/quality-gate/service.d.ts +233 -0
- package/dist/services/quality-gate/service.js +136 -0
- package/dist/services/repository-bundle/service.d.ts +33 -0
- package/dist/services/repository-bundle/service.js +114 -0
- package/dist/services/repository-model/service.d.ts +105 -0
- package/dist/services/repository-model/service.js +250 -0
- package/dist/services/repository-public-artifact/service.d.ts +133 -0
- package/dist/services/repository-public-artifact/service.js +330 -0
- package/dist/services/routing-benchmark/service.d.ts +362 -0
- package/dist/services/routing-benchmark/service.js +96 -0
- package/dist/services/specification-critic/service.d.ts +92 -0
- package/dist/services/specification-critic/service.js +172 -0
- package/dist/services/task-family/service.d.ts +40 -0
- package/dist/services/task-family/service.js +55 -0
- package/dist/services/task-seed/service.d.ts +906 -0
- package/dist/services/task-seed/service.js +1406 -0
- package/dist/services/task-specification/service.d.ts +27 -0
- package/dist/services/task-specification/service.js +40 -0
- package/dist/services/trajectory-policy/service.d.ts +110 -0
- package/dist/services/trajectory-policy/service.js +216 -0
- package/dist/test/agentic-capabilities-protocol.test.d.ts +1 -0
- package/dist/test/agentic-capabilities-protocol.test.js +570 -0
- package/dist/test/agentic-capabilities.test.d.ts +1 -0
- package/dist/test/agentic-capabilities.test.js +1461 -0
- package/dist/test/agentic-environment.test.d.ts +1 -0
- package/dist/test/agentic-environment.test.js +213 -0
- package/dist/test/case-pipeline-foundation.test.d.ts +1 -0
- package/dist/test/case-pipeline-foundation.test.js +535 -0
- package/dist/test/case-pipeline-protocol-v2.test.d.ts +1 -0
- package/dist/test/case-pipeline-protocol-v2.test.js +124 -0
- package/dist/test/case-pipeline-v2.test.d.ts +1 -0
- package/dist/test/case-pipeline-v2.test.js +286 -0
- package/dist/test/case-pipeline.test.d.ts +1 -0
- package/dist/test/case-pipeline.test.js +851 -0
- package/dist/test/eval-capability-policy.test.d.ts +1 -0
- package/dist/test/eval-capability-policy.test.js +50 -0
- package/dist/test/eval-event-log.test.d.ts +1 -0
- package/dist/test/eval-event-log.test.js +125 -0
- package/dist/test/evaluation-evidence-freshness.test.d.ts +1 -0
- package/dist/test/evaluation-evidence-freshness.test.js +44 -0
- package/dist/test/evaluation-evidence.test.d.ts +1 -0
- package/dist/test/evaluation-evidence.test.js +230 -0
- package/dist/test/evaluation-grader-calibration.test.d.ts +1 -0
- package/dist/test/evaluation-grader-calibration.test.js +373 -0
- package/dist/test/evaluation-proposal-digest.test.d.ts +1 -0
- package/dist/test/evaluation-proposal-digest.test.js +187 -0
- package/dist/test/evaluation-source-retrieval.test.d.ts +1 -0
- package/dist/test/evaluation-source-retrieval.test.js +237 -0
- package/dist/test/evaluation-structure-policy.test.d.ts +1 -0
- package/dist/test/evaluation-structure-policy.test.js +196 -0
- package/dist/test/fixtures/repository-resource-panel.d.ts +39 -0
- package/dist/test/fixtures/repository-resource-panel.js +111 -0
- package/dist/test/fixtures/vitest-boundary-panel.d.ts +84 -0
- package/dist/test/fixtures/vitest-boundary-panel.js +120 -0
- package/dist/test/fixtures/vitest-phase-panel.d.ts +135 -0
- package/dist/test/fixtures/vitest-phase-panel.js +213 -0
- package/dist/test/fixtures/vitest-reporter-results.d.ts +76 -0
- package/dist/test/fixtures/vitest-reporter-results.js +94 -0
- package/dist/test/grounded-authoring.test.d.ts +1 -0
- package/dist/test/grounded-authoring.test.js +565 -0
- package/dist/test/integrated-repository-history.test.d.ts +1 -0
- package/dist/test/integrated-repository-history.test.js +227 -0
- package/dist/test/project-authoring.test.js +593 -43
- package/dist/test/project-workflow.test.js +419 -40
- package/dist/test/repository-authoring-artifacts.test.d.ts +1 -0
- package/dist/test/repository-authoring-artifacts.test.js +185 -0
- package/dist/test/repository-bundle.test.d.ts +1 -0
- package/dist/test/repository-bundle.test.js +52 -0
- package/dist/test/repository-case-generation.test.d.ts +1 -0
- package/dist/test/repository-case-generation.test.js +3465 -0
- package/dist/test/repository-command-diagnostic.test.d.ts +1 -0
- package/dist/test/repository-command-diagnostic.test.js +55 -0
- package/dist/test/repository-command-signals.test.d.ts +1 -0
- package/dist/test/repository-command-signals.test.js +124 -0
- package/dist/test/repository-fixture-scope-coverage.test.d.ts +1 -0
- package/dist/test/repository-fixture-scope-coverage.test.js +127 -0
- package/dist/test/repository-fixture-validation.test.d.ts +1 -0
- package/dist/test/repository-fixture-validation.test.js +362 -0
- package/dist/test/repository-foundry-progress.test.d.ts +1 -0
- package/dist/test/repository-foundry-progress.test.js +110 -0
- package/dist/test/repository-foundry-quality.test.d.ts +1 -0
- package/dist/test/repository-foundry-quality.test.js +1138 -0
- package/dist/test/repository-import-context.test.d.ts +1 -0
- package/dist/test/repository-import-context.test.js +354 -0
- package/dist/test/repository-model-authoring.test.d.ts +1 -0
- package/dist/test/repository-model-authoring.test.js +544 -0
- package/dist/test/repository-model.test.d.ts +1 -0
- package/dist/test/repository-model.test.js +2195 -0
- package/dist/test/repository-node-test-reporter.test.d.ts +1 -0
- package/dist/test/repository-node-test-reporter.test.js +104 -0
- package/dist/test/repository-oracle-concurrency.test.d.ts +1 -0
- package/dist/test/repository-oracle-concurrency.test.js +542 -0
- package/dist/test/repository-oracle-coverage-witness.test.d.ts +1 -0
- package/dist/test/repository-oracle-coverage-witness.test.js +511 -0
- package/dist/test/repository-oracle-coverage.test.d.ts +1 -0
- package/dist/test/repository-oracle-coverage.test.js +168 -0
- package/dist/test/repository-oracle-evidence.test.d.ts +1 -0
- package/dist/test/repository-oracle-evidence.test.js +185 -0
- package/dist/test/repository-oracle-plan.test.d.ts +1 -0
- package/dist/test/repository-oracle-plan.test.js +176 -0
- package/dist/test/repository-overlay-isolation.test.d.ts +1 -0
- package/dist/test/repository-overlay-isolation.test.js +85 -0
- package/dist/test/repository-preparation-cache.test.d.ts +1 -0
- package/dist/test/repository-preparation-cache.test.js +414 -0
- package/dist/test/repository-public-artifact.test.d.ts +1 -0
- package/dist/test/repository-public-artifact.test.js +273 -0
- package/dist/test/repository-qualification-diagnostics.test.d.ts +1 -0
- package/dist/test/repository-qualification-diagnostics.test.js +524 -0
- package/dist/test/repository-reference-authoring.test.d.ts +1 -0
- package/dist/test/repository-reference-authoring.test.js +1633 -0
- package/dist/test/repository-review-evidence-v2.test.d.ts +1 -0
- package/dist/test/repository-review-evidence-v2.test.js +183 -0
- package/dist/test/repository-review-evidence.test.d.ts +1 -0
- package/dist/test/repository-review-evidence.test.js +124 -0
- package/dist/test/repository-seed-exclusions.test.d.ts +1 -0
- package/dist/test/repository-seed-exclusions.test.js +96 -0
- package/dist/test/repository-seed-selection.test.d.ts +1 -0
- package/dist/test/repository-seed-selection.test.js +504 -0
- package/dist/test/repository-semantic-calibration.test.d.ts +1 -0
- package/dist/test/repository-semantic-calibration.test.js +688 -0
- package/dist/test/repository-solution-edits.test.d.ts +1 -0
- package/dist/test/repository-solution-edits.test.js +377 -0
- package/dist/test/repository-specification-budget.test.d.ts +1 -0
- package/dist/test/repository-specification-budget.test.js +171 -0
- package/dist/test/repository-specification-contract-checkpoint.test.d.ts +1 -0
- package/dist/test/repository-specification-contract-checkpoint.test.js +228 -0
- package/dist/test/repository-specification-contract-facts.test.d.ts +1 -0
- package/dist/test/repository-specification-contract-facts.test.js +177 -0
- package/dist/test/repository-trajectory-authoring.test.d.ts +1 -0
- package/dist/test/repository-trajectory-authoring.test.js +176 -0
- package/dist/test/repository-valid-control-plan.test.d.ts +1 -0
- package/dist/test/repository-valid-control-plan.test.js +45 -0
- package/dist/test/repository-vitest-phase.test.d.ts +1 -0
- package/dist/test/repository-vitest-phase.test.js +848 -0
- package/dist/test/repository-vitest-reporter.test.d.ts +1 -0
- package/dist/test/repository-vitest-reporter.test.js +158 -0
- package/dist/test/repository-workspace-build.test.d.ts +1 -0
- package/dist/test/repository-workspace-build.test.js +160 -0
- package/dist/test/strict-authoring-schema.test.d.ts +1 -0
- package/dist/test/strict-authoring-schema.test.js +169 -0
- package/package.json +48 -6
|
@@ -0,0 +1,258 @@
|
|
|
1
|
+
import { Effect } from "effect";
|
|
2
|
+
import { type PipelineStageRunV1, type PipelineStageInputV1, type TournamentCheckpointV1 } from "../../case-pipeline-protocol.js";
|
|
3
|
+
import { RepositoryFoundryError } from "../../errors.js";
|
|
4
|
+
import { RepositoryFoundryLanguageModel } from "../language-model/service.js";
|
|
5
|
+
/**
|
|
6
|
+
* Runs real, repeated isolated execution and hill-climbs only from measured
|
|
7
|
+
* escapes. Checkpoints are written after every accepted incumbent replacement.
|
|
8
|
+
*/
|
|
9
|
+
export declare const runPipelineTournamentCapabilityV1: (input: PipelineStageInputV1<TournamentCheckpointV1> & {
|
|
10
|
+
readonly maximumIterations?: number;
|
|
11
|
+
}) => Effect.Effect<{
|
|
12
|
+
readonly version: 1;
|
|
13
|
+
readonly valid: readonly {
|
|
14
|
+
readonly kind: "historical-reference" | "independent-valid" | "simplified-valid" | "behavior-preserving-valid" | "historical-defect" | "mutation" | "model-near-miss" | "reward-hacking";
|
|
15
|
+
readonly id: string;
|
|
16
|
+
readonly expectedClass: "valid" | "wrong";
|
|
17
|
+
readonly commit: string;
|
|
18
|
+
readonly family: string;
|
|
19
|
+
readonly fileOverrides?: readonly ({
|
|
20
|
+
readonly path: string;
|
|
21
|
+
readonly content: string;
|
|
22
|
+
} | {
|
|
23
|
+
readonly path: string;
|
|
24
|
+
readonly delete: true;
|
|
25
|
+
})[] | undefined;
|
|
26
|
+
}[];
|
|
27
|
+
readonly wrong: readonly {
|
|
28
|
+
readonly kind: "historical-reference" | "independent-valid" | "simplified-valid" | "behavior-preserving-valid" | "historical-defect" | "mutation" | "model-near-miss" | "reward-hacking";
|
|
29
|
+
readonly id: string;
|
|
30
|
+
readonly expectedClass: "valid" | "wrong";
|
|
31
|
+
readonly commit: string;
|
|
32
|
+
readonly family: string;
|
|
33
|
+
readonly fileOverrides?: readonly ({
|
|
34
|
+
readonly path: string;
|
|
35
|
+
readonly content: string;
|
|
36
|
+
} | {
|
|
37
|
+
readonly path: string;
|
|
38
|
+
readonly delete: true;
|
|
39
|
+
})[] | undefined;
|
|
40
|
+
}[];
|
|
41
|
+
readonly stage: "tournament";
|
|
42
|
+
readonly oracle: {
|
|
43
|
+
readonly version: 1;
|
|
44
|
+
readonly fixtures: readonly ({
|
|
45
|
+
readonly kind: "historical-regression";
|
|
46
|
+
readonly expectationMode: "changes";
|
|
47
|
+
readonly id: string;
|
|
48
|
+
readonly description: string;
|
|
49
|
+
readonly expectedBehavior: string;
|
|
50
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
51
|
+
readonly testPath: string;
|
|
52
|
+
} | {
|
|
53
|
+
readonly kind: "boundary";
|
|
54
|
+
readonly expectationMode: "changes" | "preserved";
|
|
55
|
+
readonly id: string;
|
|
56
|
+
readonly description: string;
|
|
57
|
+
readonly expectedBehavior: string;
|
|
58
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
59
|
+
readonly testPath: string;
|
|
60
|
+
} | {
|
|
61
|
+
readonly kind: "counterfactual";
|
|
62
|
+
readonly expectationMode: "changes";
|
|
63
|
+
readonly id: string;
|
|
64
|
+
readonly description: string;
|
|
65
|
+
readonly expectedBehavior: string;
|
|
66
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
67
|
+
readonly testPath: string;
|
|
68
|
+
} | {
|
|
69
|
+
readonly kind: "metamorphic";
|
|
70
|
+
readonly expectationMode: "preserved";
|
|
71
|
+
readonly id: string;
|
|
72
|
+
readonly description: string;
|
|
73
|
+
readonly expectedBehavior: string;
|
|
74
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
75
|
+
readonly testPath: string;
|
|
76
|
+
})[];
|
|
77
|
+
readonly caseId: string;
|
|
78
|
+
readonly hardFailurePolicy: "any-critical-hard-clause-fails";
|
|
79
|
+
readonly clauses: readonly ({
|
|
80
|
+
readonly kind: "candidate-policy";
|
|
81
|
+
readonly policyId: string;
|
|
82
|
+
readonly forbiddenPaths: readonly string[];
|
|
83
|
+
readonly id: string;
|
|
84
|
+
readonly critical: boolean;
|
|
85
|
+
readonly description: string;
|
|
86
|
+
} | {
|
|
87
|
+
readonly kind: "test-command";
|
|
88
|
+
readonly recipeId: string;
|
|
89
|
+
readonly expectedExitCode: number;
|
|
90
|
+
readonly fixtureIds: readonly string[];
|
|
91
|
+
readonly id: string;
|
|
92
|
+
readonly critical: boolean;
|
|
93
|
+
readonly description: string;
|
|
94
|
+
} | {
|
|
95
|
+
readonly kind: "json-field";
|
|
96
|
+
readonly id: string;
|
|
97
|
+
readonly description: string;
|
|
98
|
+
readonly critical: boolean;
|
|
99
|
+
readonly operator: "equals" | "present" | "absent";
|
|
100
|
+
readonly pointer: string;
|
|
101
|
+
readonly expectedJson?: string | undefined;
|
|
102
|
+
} | {
|
|
103
|
+
readonly kind: "ordered-events";
|
|
104
|
+
readonly id: string;
|
|
105
|
+
readonly description: string;
|
|
106
|
+
readonly critical: boolean;
|
|
107
|
+
readonly eventTypes: readonly string[];
|
|
108
|
+
readonly terminalEvent?: string | undefined;
|
|
109
|
+
} | {
|
|
110
|
+
readonly kind: "property";
|
|
111
|
+
readonly propertyId: string;
|
|
112
|
+
readonly fixtureIds: readonly string[];
|
|
113
|
+
readonly id: string;
|
|
114
|
+
readonly critical: boolean;
|
|
115
|
+
readonly description: string;
|
|
116
|
+
} | {
|
|
117
|
+
readonly kind: "differential";
|
|
118
|
+
readonly implementationIds: readonly string[];
|
|
119
|
+
readonly fixtureIds: readonly string[];
|
|
120
|
+
readonly id: string;
|
|
121
|
+
readonly critical: boolean;
|
|
122
|
+
readonly description: string;
|
|
123
|
+
} | {
|
|
124
|
+
readonly kind: "architecture";
|
|
125
|
+
readonly ruleId: string;
|
|
126
|
+
readonly expectedPaths: readonly string[];
|
|
127
|
+
readonly id: string;
|
|
128
|
+
readonly critical: boolean;
|
|
129
|
+
readonly description: string;
|
|
130
|
+
} | {
|
|
131
|
+
readonly kind: "transformation-completeness";
|
|
132
|
+
readonly ruleId: string;
|
|
133
|
+
readonly forbiddenLegacyPaths: readonly string[];
|
|
134
|
+
readonly requiredNewPaths: readonly string[];
|
|
135
|
+
readonly id: string;
|
|
136
|
+
readonly critical: boolean;
|
|
137
|
+
readonly description: string;
|
|
138
|
+
} | {
|
|
139
|
+
readonly kind: "semantic-residual";
|
|
140
|
+
readonly criterion: string;
|
|
141
|
+
readonly id: string;
|
|
142
|
+
readonly critical: boolean;
|
|
143
|
+
readonly description: string;
|
|
144
|
+
})[];
|
|
145
|
+
readonly solutions: readonly {
|
|
146
|
+
readonly kind: "historical-reference" | "independent-valid" | "simplified-valid" | "behavior-preserving-valid" | "historical-defect" | "mutation" | "model-near-miss" | "reward-hacking";
|
|
147
|
+
readonly id: string;
|
|
148
|
+
readonly expectedClass: "valid" | "wrong";
|
|
149
|
+
readonly family: string;
|
|
150
|
+
readonly commit?: string | undefined;
|
|
151
|
+
}[];
|
|
152
|
+
readonly observations: readonly {
|
|
153
|
+
readonly outcome: "pass" | "fail" | "unknown";
|
|
154
|
+
readonly solutionId: string;
|
|
155
|
+
readonly clauseId: string;
|
|
156
|
+
readonly repetition: number;
|
|
157
|
+
readonly detail: string;
|
|
158
|
+
readonly inconclusiveReason?: "unattributed-test-failure" | undefined;
|
|
159
|
+
}[];
|
|
160
|
+
readonly knownLimitations: readonly string[];
|
|
161
|
+
readonly executionBindingDigest?: string | undefined;
|
|
162
|
+
readonly executionRepetitions?: number | undefined;
|
|
163
|
+
};
|
|
164
|
+
readonly parentDigest: string;
|
|
165
|
+
readonly createdAt: string;
|
|
166
|
+
readonly adequacy: {
|
|
167
|
+
readonly version: 1;
|
|
168
|
+
readonly caseId: string;
|
|
169
|
+
readonly admitted: boolean;
|
|
170
|
+
readonly validSolutionCount: number;
|
|
171
|
+
readonly wrongSolutionCount: number;
|
|
172
|
+
readonly falseRejectedSolutionIds: readonly string[];
|
|
173
|
+
readonly falseAcceptedSolutionIds: readonly string[];
|
|
174
|
+
readonly unstableSolutionIds: readonly string[];
|
|
175
|
+
readonly unobservedClauseIds: readonly string[];
|
|
176
|
+
readonly insufficientObservationPairs: readonly string[];
|
|
177
|
+
readonly mutationFamilyKills: readonly {
|
|
178
|
+
readonly family: string;
|
|
179
|
+
readonly killed: number;
|
|
180
|
+
readonly total: number;
|
|
181
|
+
}[];
|
|
182
|
+
readonly rejectionReasons: readonly string[];
|
|
183
|
+
};
|
|
184
|
+
readonly suite: {
|
|
185
|
+
readonly version: 1;
|
|
186
|
+
readonly caseId: string;
|
|
187
|
+
readonly fixtures: readonly ({
|
|
188
|
+
readonly kind: "historical-regression";
|
|
189
|
+
readonly expectationMode: "changes";
|
|
190
|
+
readonly id: string;
|
|
191
|
+
readonly description: string;
|
|
192
|
+
readonly expectedBehavior: string;
|
|
193
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
194
|
+
readonly testPath: string;
|
|
195
|
+
} | {
|
|
196
|
+
readonly kind: "boundary";
|
|
197
|
+
readonly expectationMode: "changes" | "preserved";
|
|
198
|
+
readonly id: string;
|
|
199
|
+
readonly description: string;
|
|
200
|
+
readonly expectedBehavior: string;
|
|
201
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
202
|
+
readonly testPath: string;
|
|
203
|
+
} | {
|
|
204
|
+
readonly kind: "counterfactual";
|
|
205
|
+
readonly expectationMode: "changes";
|
|
206
|
+
readonly id: string;
|
|
207
|
+
readonly description: string;
|
|
208
|
+
readonly expectedBehavior: string;
|
|
209
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
210
|
+
readonly testPath: string;
|
|
211
|
+
} | {
|
|
212
|
+
readonly kind: "metamorphic";
|
|
213
|
+
readonly expectationMode: "preserved";
|
|
214
|
+
readonly id: string;
|
|
215
|
+
readonly description: string;
|
|
216
|
+
readonly expectedBehavior: string;
|
|
217
|
+
readonly source: "historical" | "generated" | "reviewed";
|
|
218
|
+
readonly testPath: string;
|
|
219
|
+
})[];
|
|
220
|
+
readonly overlays: readonly {
|
|
221
|
+
readonly path: string;
|
|
222
|
+
readonly content: string;
|
|
223
|
+
readonly fixtureIds: readonly string[];
|
|
224
|
+
}[];
|
|
225
|
+
};
|
|
226
|
+
readonly history: readonly {
|
|
227
|
+
readonly rejectionReasons: readonly string[];
|
|
228
|
+
readonly sequence: number;
|
|
229
|
+
readonly decision: "rejected" | "accepted";
|
|
230
|
+
readonly targeted: readonly string[];
|
|
231
|
+
readonly candidateAdequacy?: {
|
|
232
|
+
readonly version: 1;
|
|
233
|
+
readonly caseId: string;
|
|
234
|
+
readonly admitted: boolean;
|
|
235
|
+
readonly validSolutionCount: number;
|
|
236
|
+
readonly wrongSolutionCount: number;
|
|
237
|
+
readonly falseRejectedSolutionIds: readonly string[];
|
|
238
|
+
readonly falseAcceptedSolutionIds: readonly string[];
|
|
239
|
+
readonly unstableSolutionIds: readonly string[];
|
|
240
|
+
readonly unobservedClauseIds: readonly string[];
|
|
241
|
+
readonly insufficientObservationPairs: readonly string[];
|
|
242
|
+
readonly mutationFamilyKills: readonly {
|
|
243
|
+
readonly family: string;
|
|
244
|
+
readonly killed: number;
|
|
245
|
+
readonly total: number;
|
|
246
|
+
}[];
|
|
247
|
+
readonly rejectionReasons: readonly string[];
|
|
248
|
+
} | undefined;
|
|
249
|
+
}[];
|
|
250
|
+
readonly iterations: number;
|
|
251
|
+
readonly critiques?: readonly {
|
|
252
|
+
readonly solutionId: string;
|
|
253
|
+
readonly classification: "valid" | "wrong" | "uncertain";
|
|
254
|
+
readonly detail: string;
|
|
255
|
+
readonly violatedBehaviorIds: readonly string[];
|
|
256
|
+
}[] | undefined;
|
|
257
|
+
}, RepositoryFoundryError | import("../../case-pipeline-protocol.js").PipelineBudgetExhaustedError, RepositoryFoundryLanguageModel>;
|
|
258
|
+
export declare const runPipelineTournamentStageV1: PipelineStageRunV1<TournamentCheckpointV1>;
|