@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 +1,286 @@
|
|
|
1
|
+
import assert from "node:assert/strict";
|
|
2
|
+
import { mkdtemp, readFile, rm } from "node:fs/promises";
|
|
3
|
+
import { tmpdir } from "node:os";
|
|
4
|
+
import { join } from "node:path";
|
|
5
|
+
import test from "node:test";
|
|
6
|
+
import { Effect } from "effect";
|
|
7
|
+
import { PipelinePortErrorV2, pipelineCheckpointDescriptorDigestV2, pipelineScientificIdentityDigestV2 } from "../case-pipeline-protocol-v2.js";
|
|
8
|
+
import { makePortableCheckpointStoreV2, repositoryBehaviorMapDigestV2, runCasePipelineV2 } from "../services/case-pipeline-v2/service.js";
|
|
9
|
+
import { makePortableRepositoryBundleV2 } from "../services/repository-bundle/service.js";
|
|
10
|
+
const sha = "a".repeat(64);
|
|
11
|
+
const repository = {
|
|
12
|
+
repositoryId: "repo-1",
|
|
13
|
+
repository: "velum-labs/routekit",
|
|
14
|
+
commitSha: "b".repeat(40),
|
|
15
|
+
treeSha: "c".repeat(40)
|
|
16
|
+
};
|
|
17
|
+
const map = {
|
|
18
|
+
version: 1,
|
|
19
|
+
repository: {
|
|
20
|
+
root: "/ignored/runtime/path",
|
|
21
|
+
requestedRef: repository.commitSha,
|
|
22
|
+
commit: repository.commitSha,
|
|
23
|
+
tree: repository.treeSha
|
|
24
|
+
},
|
|
25
|
+
packages: [],
|
|
26
|
+
publicSurfaces: [],
|
|
27
|
+
protocols: [],
|
|
28
|
+
tests: [],
|
|
29
|
+
testBindings: [],
|
|
30
|
+
commands: [],
|
|
31
|
+
historyEpisodes: [],
|
|
32
|
+
workloadSignals: [],
|
|
33
|
+
blindSpots: []
|
|
34
|
+
};
|
|
35
|
+
const identity = {
|
|
36
|
+
version: 2,
|
|
37
|
+
repository,
|
|
38
|
+
caseId: "case-1",
|
|
39
|
+
coverageCellId: "cell-1",
|
|
40
|
+
dimension: {
|
|
41
|
+
id: "routing",
|
|
42
|
+
description: "Routing behavior",
|
|
43
|
+
includes: ["explicit behavior"],
|
|
44
|
+
excludes: ["unrelated formatting"]
|
|
45
|
+
},
|
|
46
|
+
source: {
|
|
47
|
+
referenceCommitSha: "d".repeat(40),
|
|
48
|
+
referenceTaskDigest: sha,
|
|
49
|
+
basisDigest: "e".repeat(64)
|
|
50
|
+
},
|
|
51
|
+
modelPlan: [
|
|
52
|
+
"seed-author",
|
|
53
|
+
"specification-author",
|
|
54
|
+
"specification-reviewer",
|
|
55
|
+
"oracle-author",
|
|
56
|
+
"control-author",
|
|
57
|
+
"adversary-author",
|
|
58
|
+
"oracle-critic",
|
|
59
|
+
"admission-reviewer"
|
|
60
|
+
].map((role) => ({
|
|
61
|
+
role: role,
|
|
62
|
+
model: "openai/fake",
|
|
63
|
+
reasoningEffort: "high",
|
|
64
|
+
maximumCalls: 100,
|
|
65
|
+
maximumOutputTokens: 65_536
|
|
66
|
+
})),
|
|
67
|
+
policy: {
|
|
68
|
+
foundryPolicyVersion: "foundry-v2",
|
|
69
|
+
admissionPolicyVersion: "admission-v1",
|
|
70
|
+
repositoryModelDigest: repositoryBehaviorMapDigestV2(map),
|
|
71
|
+
oracleRepetitions: 2,
|
|
72
|
+
oracleConcurrency: 2,
|
|
73
|
+
foldLimit: 2
|
|
74
|
+
},
|
|
75
|
+
budget: {
|
|
76
|
+
maximumModelCalls: 100,
|
|
77
|
+
maximumWallTimeMs: 60_000,
|
|
78
|
+
maximumArtifactBytes: 16 * 1024 * 1024
|
|
79
|
+
}
|
|
80
|
+
};
|
|
81
|
+
const portFailure = (port, operation) => new PipelinePortErrorV2({
|
|
82
|
+
port,
|
|
83
|
+
operation,
|
|
84
|
+
detail: `${port} ${operation} failed`,
|
|
85
|
+
retryable: false
|
|
86
|
+
});
|
|
87
|
+
const makePorts = (stored) => ({
|
|
88
|
+
repository: {
|
|
89
|
+
materialize: () => Effect.void,
|
|
90
|
+
verify: () => Effect.void
|
|
91
|
+
},
|
|
92
|
+
model: {
|
|
93
|
+
complete: () => Effect.fail(portFailure("model", "unexpected-call"))
|
|
94
|
+
},
|
|
95
|
+
checkpoints: {
|
|
96
|
+
list: () => Effect.succeed(stored.map(({ descriptor }) => descriptor)),
|
|
97
|
+
read: (descriptor) => {
|
|
98
|
+
const found = stored.find(({ descriptor: candidate }) => candidate.checkpointId === descriptor.checkpointId);
|
|
99
|
+
return found === undefined
|
|
100
|
+
? Effect.fail(portFailure("checkpoint", "read"))
|
|
101
|
+
: Effect.succeed(found.bytes);
|
|
102
|
+
},
|
|
103
|
+
put: (descriptor, bytes) => {
|
|
104
|
+
stored.push({ descriptor, bytes });
|
|
105
|
+
return Effect.succeed(descriptor);
|
|
106
|
+
}
|
|
107
|
+
},
|
|
108
|
+
artifacts: {
|
|
109
|
+
put: (descriptor) => Effect.succeed(descriptor),
|
|
110
|
+
read: () => Effect.fail(portFailure("artifact", "read"))
|
|
111
|
+
},
|
|
112
|
+
execution: {
|
|
113
|
+
run: () => Effect.fail(portFailure("execution", "run"))
|
|
114
|
+
},
|
|
115
|
+
progress: {
|
|
116
|
+
emit: () => Effect.void
|
|
117
|
+
},
|
|
118
|
+
clock: {
|
|
119
|
+
now: Effect.succeed(new Date("2026-09-11T00:00:00.000Z")),
|
|
120
|
+
sleep: () => Effect.void
|
|
121
|
+
}
|
|
122
|
+
});
|
|
123
|
+
test("portable runner appends one accepted terminal head after the durable admit result", async () => {
|
|
124
|
+
const firstRoot = await mkdtemp(join(tmpdir(), "routekit-foundry-v2-terminal-a-"));
|
|
125
|
+
const secondRoot = await mkdtemp(join(tmpdir(), "routekit-foundry-v2-terminal-b-"));
|
|
126
|
+
const stored = [];
|
|
127
|
+
const admit = {
|
|
128
|
+
version: 1,
|
|
129
|
+
stage: "admit",
|
|
130
|
+
parentDigest: sha,
|
|
131
|
+
createdAt: "2026-09-11T00:00:00.000Z",
|
|
132
|
+
verdict: "admitted",
|
|
133
|
+
reasons: [],
|
|
134
|
+
benchmarkCase: {},
|
|
135
|
+
evidence: {
|
|
136
|
+
validCount: 1,
|
|
137
|
+
wrongCount: 1,
|
|
138
|
+
heldOutWrongCount: 1,
|
|
139
|
+
semanticKills: ["wrong-1"]
|
|
140
|
+
}
|
|
141
|
+
};
|
|
142
|
+
try {
|
|
143
|
+
const first = await Effect.runPromise(makePortableCheckpointStoreV2({
|
|
144
|
+
identity,
|
|
145
|
+
runtimeRoot: firstRoot,
|
|
146
|
+
attemptGeneration: 1,
|
|
147
|
+
ports: makePorts(stored)
|
|
148
|
+
}));
|
|
149
|
+
await Effect.runPromise(first.store.writeStage("admit", admit));
|
|
150
|
+
assert.deepEqual(JSON.parse(await readFile(first.store.stagePath("admit"), "utf8")), admit, "the V1 admit result is durable before terminalization");
|
|
151
|
+
const stageHead = first.descriptors().at(-1);
|
|
152
|
+
assert.ok(stageHead);
|
|
153
|
+
assert.equal(stageHead.kind, "stage");
|
|
154
|
+
const accepted = await Effect.runPromise(first.completeAdmit(admit));
|
|
155
|
+
const replay = await Effect.runPromise(first.completeAdmit(admit));
|
|
156
|
+
assert.deepEqual(replay, accepted);
|
|
157
|
+
assert.equal(stored.length, 2);
|
|
158
|
+
assert.equal(accepted.kind, "terminal");
|
|
159
|
+
assert.equal(accepted.stage, "admit");
|
|
160
|
+
assert.equal(accepted.parentDigest, pipelineCheckpointDescriptorDigestV2(stageHead));
|
|
161
|
+
assert.deepEqual(first.descriptors().at(-1), accepted);
|
|
162
|
+
assert.equal(first.descriptors().filter(({ kind }) => kind === "terminal").length, 1);
|
|
163
|
+
const replacement = await Effect.runPromise(makePortableCheckpointStoreV2({
|
|
164
|
+
identity,
|
|
165
|
+
runtimeRoot: secondRoot,
|
|
166
|
+
attemptGeneration: 2,
|
|
167
|
+
ports: makePorts(stored)
|
|
168
|
+
}));
|
|
169
|
+
const replacementReplay = await Effect.runPromise(replacement.completeAdmit(admit));
|
|
170
|
+
assert.deepEqual(replacementReplay, accepted);
|
|
171
|
+
await assert.rejects(Effect.runPromise(replacement.completeAdmit({
|
|
172
|
+
...admit,
|
|
173
|
+
verdict: "rejected",
|
|
174
|
+
reasons: ["replacement changed the durable result"]
|
|
175
|
+
})), /terminal checkpoint replay conflicts with the durable admit result/i);
|
|
176
|
+
assert.equal(stored.length, 2, "replacement resume must not replace or extend the terminal head");
|
|
177
|
+
assert.deepEqual(replacement.descriptors().at(-1), accepted);
|
|
178
|
+
}
|
|
179
|
+
finally {
|
|
180
|
+
await Promise.all([
|
|
181
|
+
rm(firstRoot, { recursive: true, force: true }),
|
|
182
|
+
rm(secondRoot, { recursive: true, force: true })
|
|
183
|
+
]);
|
|
184
|
+
}
|
|
185
|
+
});
|
|
186
|
+
test("portable runner resumes accepted terminal work at a different runtime path", async () => {
|
|
187
|
+
const firstRoot = await mkdtemp(join(tmpdir(), "routekit-foundry-v2-a-"));
|
|
188
|
+
const secondRoot = await mkdtemp(join(tmpdir(), "routekit-foundry-v2-b-"));
|
|
189
|
+
const stored = [];
|
|
190
|
+
try {
|
|
191
|
+
const identityDigest = pipelineScientificIdentityDigestV2(identity);
|
|
192
|
+
const payload = Buffer.from(JSON.stringify({
|
|
193
|
+
version: 2,
|
|
194
|
+
action: "write",
|
|
195
|
+
stage: "admit",
|
|
196
|
+
value: {
|
|
197
|
+
version: 1,
|
|
198
|
+
stage: "admit",
|
|
199
|
+
parentDigest: sha,
|
|
200
|
+
createdAt: "2026-09-11T00:00:00.000Z",
|
|
201
|
+
verdict: "admitted",
|
|
202
|
+
reasons: [],
|
|
203
|
+
benchmarkCase: {}
|
|
204
|
+
}
|
|
205
|
+
}), "utf8");
|
|
206
|
+
const payloadDigest = await crypto.subtle.digest("SHA-256", payload);
|
|
207
|
+
stored.push({
|
|
208
|
+
descriptor: {
|
|
209
|
+
version: 2,
|
|
210
|
+
checkpointId: "checkpoint-1",
|
|
211
|
+
identityDigest,
|
|
212
|
+
attemptGeneration: 1,
|
|
213
|
+
sequence: 1,
|
|
214
|
+
kind: "terminal",
|
|
215
|
+
stage: "admit",
|
|
216
|
+
parentDigest: identityDigest,
|
|
217
|
+
payloadDigest: Buffer.from(payloadDigest).toString("hex"),
|
|
218
|
+
payloadBytes: payload.byteLength,
|
|
219
|
+
createdAt: "2026-09-11T00:00:00.000Z"
|
|
220
|
+
},
|
|
221
|
+
bytes: payload
|
|
222
|
+
});
|
|
223
|
+
/*
|
|
224
|
+
* A deliberately incomplete admit payload is rejected by the existing V1
|
|
225
|
+
* schema and regenerated. The proof here is that restore reaches the V1
|
|
226
|
+
* implementation through the new port layer without path-identity failure;
|
|
227
|
+
* the fake model then fails closed instead of silently accepting it.
|
|
228
|
+
*/
|
|
229
|
+
const first = await Effect.runPromise(runCasePipelineV2({
|
|
230
|
+
identity,
|
|
231
|
+
runtimeRoot: firstRoot,
|
|
232
|
+
attemptGeneration: 2,
|
|
233
|
+
map,
|
|
234
|
+
ports: makePorts(stored)
|
|
235
|
+
}));
|
|
236
|
+
const second = await Effect.runPromise(runCasePipelineV2({
|
|
237
|
+
identity,
|
|
238
|
+
runtimeRoot: secondRoot,
|
|
239
|
+
attemptGeneration: 3,
|
|
240
|
+
map,
|
|
241
|
+
ports: makePorts(stored)
|
|
242
|
+
}));
|
|
243
|
+
assert.equal(first.identityDigest, second.identityDigest);
|
|
244
|
+
assert.notEqual(first.runtimeRoot, second.runtimeRoot);
|
|
245
|
+
assert.match(first.result.state.reason ?? "", /accepted terminal checkpoint is already the immutable chain head/i);
|
|
246
|
+
assert.match(second.result.state.reason ?? "", /accepted terminal checkpoint is already the immutable chain head/i);
|
|
247
|
+
assert.doesNotMatch(first.result.state.reason ?? "", /different pipeline identity/i);
|
|
248
|
+
}
|
|
249
|
+
finally {
|
|
250
|
+
await Promise.all([
|
|
251
|
+
rm(firstRoot, { recursive: true, force: true }),
|
|
252
|
+
rm(secondRoot, { recursive: true, force: true })
|
|
253
|
+
]);
|
|
254
|
+
}
|
|
255
|
+
});
|
|
256
|
+
test("portable repository bundle is deterministic and path-safe", () => {
|
|
257
|
+
const input = {
|
|
258
|
+
admitted: true,
|
|
259
|
+
sourceCommitSha: identity.repository.commitSha,
|
|
260
|
+
artifacts: [
|
|
261
|
+
{
|
|
262
|
+
path: ".routekit/evals/b.json",
|
|
263
|
+
kind: "public-metadata",
|
|
264
|
+
mediaType: "application/json",
|
|
265
|
+
content: "{}\n"
|
|
266
|
+
},
|
|
267
|
+
{
|
|
268
|
+
path: ".routekit/evals/a.eval.ts",
|
|
269
|
+
kind: "eval-definition",
|
|
270
|
+
mediaType: "text/typescript",
|
|
271
|
+
content: "export {};\n"
|
|
272
|
+
}
|
|
273
|
+
]
|
|
274
|
+
};
|
|
275
|
+
const first = makePortableRepositoryBundleV2(input);
|
|
276
|
+
const second = makePortableRepositoryBundleV2({
|
|
277
|
+
...input,
|
|
278
|
+
artifacts: [...input.artifacts].reverse()
|
|
279
|
+
});
|
|
280
|
+
assert.deepEqual(first, second);
|
|
281
|
+
assert.deepEqual(first.files.map(({ path }) => path), [".routekit/evals/a.eval.ts", ".routekit/evals/b.json"]);
|
|
282
|
+
assert.throws(() => makePortableRepositoryBundleV2({
|
|
283
|
+
...input,
|
|
284
|
+
artifacts: [{ ...input.artifacts[0], path: "../secret" }]
|
|
285
|
+
}));
|
|
286
|
+
});
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export {};
|