@openpond/evals 0.11.21 → 0.12.1
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/README.md +12 -0
- package/dist/artifact-verification.js +2 -0
- package/dist/connected-evidence/codex-command-observations.js +81 -0
- package/dist/connected-evidence/contracts.js +13 -0
- package/dist/connected-evidence/git-file-contracts.js +16 -0
- package/dist/connected-evidence/git-file-proof.js +86 -0
- package/dist/connected-evidence/git-starting-state.js +81 -0
- package/dist/connected-evidence/git.js +2 -0
- package/dist/connected-evidence/imports.js +2 -1
- package/dist/connected-evidence/index.js +1 -0
- package/dist/connected-evidence/normalize.js +1 -0
- package/dist/connected-evidence/sources/claude-branches.js +34 -1
- package/dist/connected-evidence/sources/claude-code.js +1 -1
- package/dist/connected-evidence/sources/codex-metadata.js +33 -0
- package/dist/connected-evidence/sources/codex.js +16 -2
- package/dist/graders.js +10 -4
- package/dist/javascript-verifier.js +1 -0
- package/dist/native-conversations/codex-window-inventory.js +6 -7
- package/dist/native-conversations/collector-acquisition.js +17 -6
- package/dist/native-conversations/collector-source-cache.js +1 -1
- package/dist/native-conversations/collector-store.js +27 -2
- package/dist/native-conversations/collector.js +4 -3
- package/dist/native-conversations/git-assets.js +61 -0
- package/dist/native-conversations/history.js +7 -0
- package/dist/native-conversations/index.js +2 -0
- package/dist/native-conversations/selection.js +57 -0
- package/dist/native-conversations/supervisor.js +2 -0
- package/dist/prepared-process-isolation.js +131 -0
- package/dist/rewards.js +17 -5
- package/dist/tasksets.js +7 -0
- package/dist/types/artifact-verification.d.ts.map +1 -1
- package/dist/types/benchmarks.d.ts +22 -22
- package/dist/types/benchmarks.d.ts.map +1 -1
- package/dist/types/builtin-benchmarks/harness-refiner.d.ts +40 -35
- package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
- package/dist/types/compatibility.d.ts.map +1 -1
- package/dist/types/conformance.d.ts +98 -88
- package/dist/types/conformance.d.ts.map +1 -1
- package/dist/types/connected-evidence/codex-command-observations.d.ts +15 -0
- package/dist/types/connected-evidence/codex-command-observations.d.ts.map +1 -0
- package/dist/types/connected-evidence/collector-coverage-contracts.d.ts +6 -6
- package/dist/types/connected-evidence/collector-coverage-contracts.d.ts.map +1 -1
- package/dist/types/connected-evidence/contracts.d.ts +80 -58
- package/dist/types/connected-evidence/contracts.d.ts.map +1 -1
- package/dist/types/connected-evidence/git-file-contracts.d.ts +18 -0
- package/dist/types/connected-evidence/git-file-contracts.d.ts.map +1 -0
- package/dist/types/connected-evidence/git-file-proof.d.ts +13 -0
- package/dist/types/connected-evidence/git-file-proof.d.ts.map +1 -0
- package/dist/types/connected-evidence/git-starting-state.d.ts +28 -0
- package/dist/types/connected-evidence/git-starting-state.d.ts.map +1 -0
- package/dist/types/connected-evidence/git.d.ts +3 -0
- package/dist/types/connected-evidence/git.d.ts.map +1 -0
- package/dist/types/connected-evidence/imports.d.ts.map +1 -1
- package/dist/types/connected-evidence/index.d.ts +1 -0
- package/dist/types/connected-evidence/index.d.ts.map +1 -1
- package/dist/types/connected-evidence/normalize.d.ts +1 -0
- package/dist/types/connected-evidence/normalize.d.ts.map +1 -1
- package/dist/types/connected-evidence/python-correctness.d.ts +38 -38
- package/dist/types/connected-evidence/python-correctness.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/claude-branches.d.ts +1 -0
- package/dist/types/connected-evidence/sources/claude-branches.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/claude-code.d.ts +25 -15
- package/dist/types/connected-evidence/sources/claude-code.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/codex-authorization.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/codex-metadata.d.ts +10 -0
- package/dist/types/connected-evidence/sources/codex-metadata.d.ts.map +1 -0
- package/dist/types/connected-evidence/sources/codex.d.ts +25 -15
- package/dist/types/connected-evidence/sources/codex.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/grok-build.d.ts +25 -15
- package/dist/types/connected-evidence/sources/grok-build.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/history.d.ts +50 -30
- package/dist/types/connected-evidence/sources/history.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/opencode.d.ts +25 -15
- package/dist/types/connected-evidence/sources/opencode.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/pi.d.ts +25 -15
- package/dist/types/connected-evidence/sources/pi.d.ts.map +1 -1
- package/dist/types/connected-evidence/sources/usage.d.ts.map +1 -1
- package/dist/types/connected-evidence/usage-summary.d.ts.map +1 -1
- package/dist/types/deterministic-graders.d.ts.map +1 -1
- package/dist/types/environment-execution-services-contract.d.ts +19 -19
- package/dist/types/environment-execution-services-contract.d.ts.map +1 -1
- package/dist/types/environment-execution-services.d.ts.map +1 -1
- package/dist/types/evidence/authoring.d.ts.map +1 -1
- package/dist/types/evidence/conformance.d.ts +98 -98
- package/dist/types/evidence/conformance.d.ts.map +1 -1
- package/dist/types/evidence/contracts.d.ts +183 -183
- package/dist/types/evidence/contracts.d.ts.map +1 -1
- package/dist/types/evidence/eligibility.d.ts +160 -160
- package/dist/types/evidence/eligibility.d.ts.map +1 -1
- package/dist/types/evidence/index.d.ts.map +1 -1
- package/dist/types/execution-contracts.d.ts +118 -110
- package/dist/types/execution-contracts.d.ts.map +1 -1
- package/dist/types/execution-receipts.d.ts.map +1 -1
- package/dist/types/experiments.d.ts +96 -96
- package/dist/types/experiments.d.ts.map +1 -1
- package/dist/types/graders.d.ts +38 -35
- package/dist/types/graders.d.ts.map +1 -1
- package/dist/types/harness-experiment-source.d.ts.map +1 -1
- package/dist/types/harness.d.ts.map +1 -1
- package/dist/types/human-review/comparison.d.ts +189 -189
- package/dist/types/human-review/comparison.d.ts.map +1 -1
- package/dist/types/human-review/contracts.d.ts +178 -178
- package/dist/types/human-review/contracts.d.ts.map +1 -1
- package/dist/types/human-review/execution.d.ts +53 -53
- package/dist/types/human-review/execution.d.ts.map +1 -1
- package/dist/types/human-review/handoff.d.ts +43 -43
- package/dist/types/human-review/handoff.d.ts.map +1 -1
- package/dist/types/human-review/index.d.ts.map +1 -1
- package/dist/types/human-review/local-publication.d.ts +4 -4
- package/dist/types/human-review/local-publication.d.ts.map +1 -1
- package/dist/types/human-review/repository.d.ts.map +1 -1
- package/dist/types/human-review/results.d.ts +8 -8
- package/dist/types/human-review/results.d.ts.map +1 -1
- package/dist/types/human-review/service.d.ts +292 -292
- package/dist/types/human-review/service.d.ts.map +1 -1
- package/dist/types/human-review/task-proposals.d.ts +2 -2
- package/dist/types/human-review/task-proposals.d.ts.map +1 -1
- package/dist/types/index.d.ts.map +1 -1
- package/dist/types/javascript-environment-attempt.d.ts.map +1 -1
- package/dist/types/javascript-environment-contract.d.ts +39 -39
- package/dist/types/javascript-environment-contract.d.ts.map +1 -1
- package/dist/types/javascript-environment-node.d.ts.map +1 -1
- package/dist/types/javascript-environment.d.ts +14 -14
- package/dist/types/javascript-environment.d.ts.map +1 -1
- package/dist/types/javascript-isolate-node.d.ts.map +1 -1
- package/dist/types/javascript-isolate-process-entry.d.ts.map +1 -1
- package/dist/types/javascript-isolate-process.d.ts.map +1 -1
- package/dist/types/javascript-isolate.d.ts.map +1 -1
- package/dist/types/javascript-verifier-contract.d.ts.map +1 -1
- package/dist/types/javascript-verifier-node.d.ts.map +1 -1
- package/dist/types/javascript-verifier-worker.d.ts.map +1 -1
- package/dist/types/javascript-verifier.d.ts +1 -0
- package/dist/types/javascript-verifier.d.ts.map +1 -1
- package/dist/types/learned-preference.d.ts +10 -10
- package/dist/types/learned-preference.d.ts.map +1 -1
- package/dist/types/learning/acceptance-group.d.ts +44 -44
- package/dist/types/learning/acceptance-group.d.ts.map +1 -1
- package/dist/types/learning/acceptance-plan.d.ts +8 -8
- package/dist/types/learning/acceptance-plan.d.ts.map +1 -1
- package/dist/types/learning/admission.d.ts +38 -36
- package/dist/types/learning/admission.d.ts.map +1 -1
- package/dist/types/learning/assets.d.ts +2 -2
- package/dist/types/learning/assets.d.ts.map +1 -1
- package/dist/types/learning/authoring-service.d.ts +11 -9
- package/dist/types/learning/authoring-service.d.ts.map +1 -1
- package/dist/types/learning/authoring.d.ts +46 -38
- package/dist/types/learning/authoring.d.ts.map +1 -1
- package/dist/types/learning/batch-service.d.ts +75 -68
- package/dist/types/learning/batch-service.d.ts.map +1 -1
- package/dist/types/learning/budgeted-reward-fixtures.d.ts.map +1 -1
- package/dist/types/learning/contracts.d.ts +314 -290
- package/dist/types/learning/contracts.d.ts.map +1 -1
- package/dist/types/learning/errors.d.ts.map +1 -1
- package/dist/types/learning/grade-judge-budget.d.ts.map +1 -1
- package/dist/types/learning/grade-worker.d.ts.map +1 -1
- package/dist/types/learning/index.d.ts.map +1 -1
- package/dist/types/learning/intake-contracts.d.ts +10 -10
- package/dist/types/learning/intake-contracts.d.ts.map +1 -1
- package/dist/types/learning/intake-csv.d.ts.map +1 -1
- package/dist/types/learning/intake-history.d.ts.map +1 -1
- package/dist/types/learning/intake-service.d.ts.map +1 -1
- package/dist/types/learning/intake-text.d.ts.map +1 -1
- package/dist/types/learning/intake.d.ts.map +1 -1
- package/dist/types/learning/iteration-budget.d.ts.map +1 -1
- package/dist/types/learning/iteration-candidate-decision.d.ts +16 -16
- package/dist/types/learning/iteration-candidate-decision.d.ts.map +1 -1
- package/dist/types/learning/iteration-dispatch-commands.d.ts.map +1 -1
- package/dist/types/learning/iteration-dispatch-contracts.d.ts +4 -4
- package/dist/types/learning/iteration-dispatch-contracts.d.ts.map +1 -1
- package/dist/types/learning/iteration-dispatch-worker.d.ts.map +1 -1
- package/dist/types/learning/iteration-eligibility.d.ts +1 -1
- package/dist/types/learning/iteration-eligibility.d.ts.map +1 -1
- package/dist/types/learning/iteration-reservation-cancellation.d.ts.map +1 -1
- package/dist/types/learning/iteration-reservation-contracts.d.ts.map +1 -1
- package/dist/types/learning/iteration-reservation-service.d.ts.map +1 -1
- package/dist/types/learning/iteration-training-parent.d.ts.map +1 -1
- package/dist/types/learning/judge-budget.d.ts +1 -1
- package/dist/types/learning/judge-budget.d.ts.map +1 -1
- package/dist/types/learning/model-judge.d.ts.map +1 -1
- package/dist/types/learning/nightly-schedule.d.ts.map +1 -1
- package/dist/types/learning/operations.d.ts +312 -298
- package/dist/types/learning/operations.d.ts.map +1 -1
- package/dist/types/learning/policy-inspection.d.ts.map +1 -1
- package/dist/types/learning/rating-reward-fixture.d.ts.map +1 -1
- package/dist/types/learning/repository.d.ts +197 -180
- package/dist/types/learning/repository.d.ts.map +1 -1
- package/dist/types/learning/reward-authoring.d.ts.map +1 -1
- package/dist/types/learning/reward-calibration-closure.d.ts +252 -244
- package/dist/types/learning/reward-calibration-closure.d.ts.map +1 -1
- package/dist/types/learning/reward-calibration.d.ts +62 -62
- package/dist/types/learning/reward-calibration.d.ts.map +1 -1
- package/dist/types/learning/reward-check-budget.d.ts.map +1 -1
- package/dist/types/learning/reward-check-service.d.ts.map +1 -1
- package/dist/types/learning/reward-check-worker.d.ts.map +1 -1
- package/dist/types/learning/reward-checks.d.ts +30 -28
- package/dist/types/learning/reward-checks.d.ts.map +1 -1
- package/dist/types/learning/reward-fixture-executor.d.ts.map +1 -1
- package/dist/types/learning/schedule-contracts.d.ts +3 -3
- package/dist/types/learning/schedule-contracts.d.ts.map +1 -1
- package/dist/types/learning/schedule-service.d.ts +2 -2
- package/dist/types/learning/schedule-service.d.ts.map +1 -1
- package/dist/types/learning/schedule-worker.d.ts.map +1 -1
- package/dist/types/learning/service.d.ts +3 -3
- package/dist/types/learning/service.d.ts.map +1 -1
- package/dist/types/learning/task-queue-inspection.d.ts.map +1 -1
- package/dist/types/learning/training-handoff.d.ts +9 -9
- package/dist/types/learning/training-handoff.d.ts.map +1 -1
- package/dist/types/learning/transport.d.ts +2203 -2179
- package/dist/types/learning/transport.d.ts.map +1 -1
- package/dist/types/metric-policy.d.ts +6 -6
- package/dist/types/metric-policy.d.ts.map +1 -1
- package/dist/types/metrics-node.d.ts.map +1 -1
- package/dist/types/metrics.d.ts.map +1 -1
- package/dist/types/model-improvement-qualification.d.ts +17 -17
- package/dist/types/model-improvement-qualification.d.ts.map +1 -1
- package/dist/types/native-conversations/appimage-runtime.d.ts.map +1 -1
- package/dist/types/native-conversations/codex-window-inventory.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-acquisition.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-branches.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-calendar-gate.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-contracts.d.ts +3 -0
- package/dist/types/native-conversations/collector-contracts.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-coverage.d.ts +2 -2
- package/dist/types/native-conversations/collector-coverage.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-cron.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-destinations.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-errors.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-progress.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-schedule.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-service-files.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-snapshots.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-source-cache.d.ts +2 -2
- package/dist/types/native-conversations/collector-source-cache.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-store.d.ts.map +1 -1
- package/dist/types/native-conversations/collector-sync-requests.d.ts.map +1 -1
- package/dist/types/native-conversations/collector.d.ts.map +1 -1
- package/dist/types/native-conversations/contracts.d.ts.map +1 -1
- package/dist/types/native-conversations/database.d.ts.map +1 -1
- package/dist/types/native-conversations/discovery.d.ts.map +1 -1
- package/dist/types/native-conversations/git-assets.d.ts +32 -0
- package/dist/types/native-conversations/git-assets.d.ts.map +1 -0
- package/dist/types/native-conversations/history.d.ts +1 -0
- package/dist/types/native-conversations/history.d.ts.map +1 -1
- package/dist/types/native-conversations/index.d.ts +2 -0
- package/dist/types/native-conversations/index.d.ts.map +1 -1
- package/dist/types/native-conversations/location.d.ts.map +1 -1
- package/dist/types/native-conversations/openclaw-cold-archive.d.ts.map +1 -1
- package/dist/types/native-conversations/openclaw-database.d.ts.map +1 -1
- package/dist/types/native-conversations/readiness.d.ts.map +1 -1
- package/dist/types/native-conversations/selection.d.ts +32 -0
- package/dist/types/native-conversations/selection.d.ts.map +1 -0
- package/dist/types/native-conversations/source-locations.d.ts.map +1 -1
- package/dist/types/native-conversations/supervisor.d.ts.map +1 -1
- package/dist/types/native-conversations/titles.d.ts.map +1 -1
- package/dist/types/native-harness-experiment-attempt.d.ts.map +1 -1
- package/dist/types/preferences.d.ts +22 -22
- package/dist/types/preferences.d.ts.map +1 -1
- package/dist/types/prepared-process-isolation.d.ts +5 -0
- package/dist/types/prepared-process-isolation.d.ts.map +1 -0
- package/dist/types/profile-evaluation-comparisons.d.ts +18 -18
- package/dist/types/profile-evaluation-comparisons.d.ts.map +1 -1
- package/dist/types/profile-evaluation-execution.d.ts.map +1 -1
- package/dist/types/profile-evaluation-reports.d.ts +2 -2
- package/dist/types/profile-evaluation-reports.d.ts.map +1 -1
- package/dist/types/profile-evaluation-suites.d.ts.map +1 -1
- package/dist/types/profile-evaluation-target.d.ts.map +1 -1
- package/dist/types/profile-evaluations.d.ts +15 -15
- package/dist/types/profile-evaluations.d.ts.map +1 -1
- package/dist/types/profile-external-evaluation.d.ts +84 -84
- package/dist/types/profile-external-evaluation.d.ts.map +1 -1
- package/dist/types/profile-source-candidate.d.ts.map +1 -1
- package/dist/types/review-conformance.d.ts +58 -58
- package/dist/types/review-conformance.d.ts.map +1 -1
- package/dist/types/rewards.d.ts +110 -101
- package/dist/types/rewards.d.ts.map +1 -1
- package/dist/types/rollouts.d.ts +16 -16
- package/dist/types/rollouts.d.ts.map +1 -1
- package/dist/types/runs.d.ts +22 -22
- package/dist/types/runs.d.ts.map +1 -1
- package/dist/types/sql-execution-contract.d.ts +3 -3
- package/dist/types/sql-execution-contract.d.ts.map +1 -1
- package/dist/types/sql-execution-engine.d.ts.map +1 -1
- package/dist/types/sql-execution-node.d.ts.map +1 -1
- package/dist/types/sql-execution-process-entry.d.ts.map +1 -1
- package/dist/types/task-schema-validation.d.ts.map +1 -1
- package/dist/types/task-schema.d.ts.map +1 -1
- package/dist/types/task-value-validator.d.ts.map +1 -1
- package/dist/types/taskset-run-contract.d.ts +26 -26
- package/dist/types/taskset-run-contract.d.ts.map +1 -1
- package/dist/types/tasksets.d.ts +89 -69
- package/dist/types/tasksets.d.ts.map +1 -1
- package/dist/types/telemetry/index.d.ts.map +1 -1
- package/dist/types/telemetry-analysis.d.ts +6 -6
- package/dist/types/telemetry-analysis.d.ts.map +1 -1
- package/dist/types/telemetry-bundle.d.ts +42 -42
- package/dist/types/telemetry-bundle.d.ts.map +1 -1
- package/dist/types/telemetry-catalog.d.ts +67 -67
- package/dist/types/telemetry-catalog.d.ts.map +1 -1
- package/dist/types/telemetry.d.ts +44 -44
- package/dist/types/telemetry.d.ts.map +1 -1
- package/package.json +6 -1
- package/schemas/learning/v1/binding.schema.json +8 -0
- package/schemas/learning/v1/command-request.schema.json +12 -0
- package/schemas/learning/v1/decision.schema.json +5 -1
- package/schemas/learning/v1/definition.schema.json +4 -0
- package/schemas/learning/v1/draft.schema.json +8 -0
- package/schemas/learning/v1/evidence.schema.json +4 -0
- package/schemas/learning/v1/example-submission.schema.json +4 -0
- package/schemas/learning/v1/grade.schema.json +5 -1
- package/schemas/learning/v1/package.schema.json +117 -93
- package/schemas/learning/v1/reward_check.schema.json +2 -1
package/dist/types/graders.d.ts
CHANGED
|
@@ -5,12 +5,12 @@ export declare const ModelJudgeTransportPolicySchema: z.ZodObject<{
|
|
|
5
5
|
schemaVersion: z.ZodLiteral<"openpond.modelJudgeTransportPolicy.v1">;
|
|
6
6
|
responseFormat: z.ZodLiteral<"judgment_json_schema">;
|
|
7
7
|
reasoningEffort: z.ZodEnum<{
|
|
8
|
-
|
|
8
|
+
high: "high";
|
|
9
9
|
low: "low";
|
|
10
|
+
max: "max";
|
|
10
11
|
medium: "medium";
|
|
11
|
-
|
|
12
|
+
off: "off";
|
|
12
13
|
xhigh: "xhigh";
|
|
13
|
-
max: "max";
|
|
14
14
|
}>;
|
|
15
15
|
maximumOutputTokens: z.ZodNumber;
|
|
16
16
|
}, z.core.$strict>;
|
|
@@ -30,12 +30,12 @@ export declare const ModelJudgeReceiptSchema: z.ZodObject<{
|
|
|
30
30
|
schemaVersion: z.ZodLiteral<"openpond.modelJudgeTransportPolicy.v1">;
|
|
31
31
|
responseFormat: z.ZodLiteral<"judgment_json_schema">;
|
|
32
32
|
reasoningEffort: z.ZodEnum<{
|
|
33
|
-
|
|
33
|
+
high: "high";
|
|
34
34
|
low: "low";
|
|
35
|
+
max: "max";
|
|
35
36
|
medium: "medium";
|
|
36
|
-
|
|
37
|
+
off: "off";
|
|
37
38
|
xhigh: "xhigh";
|
|
38
|
-
max: "max";
|
|
39
39
|
}>;
|
|
40
40
|
maximumOutputTokens: z.ZodNumber;
|
|
41
41
|
}, z.core.$strict>>;
|
|
@@ -48,8 +48,8 @@ export declare const GraderEvidenceContentSchema: z.ZodObject<{
|
|
|
48
48
|
graderId: z.ZodString;
|
|
49
49
|
graderVersion: z.ZodString;
|
|
50
50
|
status: z.ZodOptional<z.ZodEnum<{
|
|
51
|
-
pending: "pending";
|
|
52
51
|
failed: "failed";
|
|
52
|
+
pending: "pending";
|
|
53
53
|
scored: "scored";
|
|
54
54
|
unavailable: "unavailable";
|
|
55
55
|
}>>;
|
|
@@ -57,12 +57,12 @@ export declare const GraderEvidenceContentSchema: z.ZodObject<{
|
|
|
57
57
|
passed: z.ZodBoolean;
|
|
58
58
|
rewardEligible: z.ZodBoolean;
|
|
59
59
|
failureClass: z.ZodNullable<z.ZodEnum<{
|
|
60
|
-
|
|
61
|
-
grader_failure: "grader_failure";
|
|
60
|
+
cancelled: "cancelled";
|
|
62
61
|
environment_failure: "environment_failure";
|
|
62
|
+
grader_failure: "grader_failure";
|
|
63
63
|
infrastructure_failure: "infrastructure_failure";
|
|
64
|
+
policy_failure: "policy_failure";
|
|
64
65
|
timeout: "timeout";
|
|
65
|
-
cancelled: "cancelled";
|
|
66
66
|
}>>;
|
|
67
67
|
feedback: z.ZodArray<z.ZodString>;
|
|
68
68
|
visibleEvidenceRefs: z.ZodArray<z.ZodString>;
|
|
@@ -82,12 +82,12 @@ export declare const GraderEvidenceContentSchema: z.ZodObject<{
|
|
|
82
82
|
schemaVersion: z.ZodLiteral<"openpond.modelJudgeTransportPolicy.v1">;
|
|
83
83
|
responseFormat: z.ZodLiteral<"judgment_json_schema">;
|
|
84
84
|
reasoningEffort: z.ZodEnum<{
|
|
85
|
-
|
|
85
|
+
high: "high";
|
|
86
86
|
low: "low";
|
|
87
|
+
max: "max";
|
|
87
88
|
medium: "medium";
|
|
88
|
-
|
|
89
|
+
off: "off";
|
|
89
90
|
xhigh: "xhigh";
|
|
90
|
-
max: "max";
|
|
91
91
|
}>;
|
|
92
92
|
maximumOutputTokens: z.ZodNumber;
|
|
93
93
|
}, z.core.$strict>>;
|
|
@@ -101,8 +101,8 @@ export declare const GraderEvidenceSchema: z.ZodObject<{
|
|
|
101
101
|
graderId: z.ZodString;
|
|
102
102
|
graderVersion: z.ZodString;
|
|
103
103
|
status: z.ZodOptional<z.ZodEnum<{
|
|
104
|
-
pending: "pending";
|
|
105
104
|
failed: "failed";
|
|
105
|
+
pending: "pending";
|
|
106
106
|
scored: "scored";
|
|
107
107
|
unavailable: "unavailable";
|
|
108
108
|
}>>;
|
|
@@ -110,12 +110,12 @@ export declare const GraderEvidenceSchema: z.ZodObject<{
|
|
|
110
110
|
passed: z.ZodBoolean;
|
|
111
111
|
rewardEligible: z.ZodBoolean;
|
|
112
112
|
failureClass: z.ZodNullable<z.ZodEnum<{
|
|
113
|
-
|
|
114
|
-
grader_failure: "grader_failure";
|
|
113
|
+
cancelled: "cancelled";
|
|
115
114
|
environment_failure: "environment_failure";
|
|
115
|
+
grader_failure: "grader_failure";
|
|
116
116
|
infrastructure_failure: "infrastructure_failure";
|
|
117
|
+
policy_failure: "policy_failure";
|
|
117
118
|
timeout: "timeout";
|
|
118
|
-
cancelled: "cancelled";
|
|
119
119
|
}>>;
|
|
120
120
|
feedback: z.ZodArray<z.ZodString>;
|
|
121
121
|
visibleEvidenceRefs: z.ZodArray<z.ZodString>;
|
|
@@ -135,12 +135,12 @@ export declare const GraderEvidenceSchema: z.ZodObject<{
|
|
|
135
135
|
schemaVersion: z.ZodLiteral<"openpond.modelJudgeTransportPolicy.v1">;
|
|
136
136
|
responseFormat: z.ZodLiteral<"judgment_json_schema">;
|
|
137
137
|
reasoningEffort: z.ZodEnum<{
|
|
138
|
-
|
|
138
|
+
high: "high";
|
|
139
139
|
low: "low";
|
|
140
|
+
max: "max";
|
|
140
141
|
medium: "medium";
|
|
141
|
-
|
|
142
|
+
off: "off";
|
|
142
143
|
xhigh: "xhigh";
|
|
143
|
-
max: "max";
|
|
144
144
|
}>;
|
|
145
145
|
maximumOutputTokens: z.ZodNumber;
|
|
146
146
|
}, z.core.$strict>>;
|
|
@@ -172,6 +172,9 @@ export type CustomVerifierRunner = (input: {
|
|
|
172
172
|
task: TaskRecord;
|
|
173
173
|
evidence: AttemptEvidence;
|
|
174
174
|
}) => Promise<Omit<GraderEvidence, "schemaVersion" | "graderId" | "graderVersion" | "contentHash">>;
|
|
175
|
+
/** Scope is part of the immutable grader. An absent scope applies to every
|
|
176
|
+
* task; an explicit scope is never inferred from answer content or metadata. */
|
|
177
|
+
export declare function gradersForTask<T extends Pick<GraderSpec, "taskIds">>(graders: readonly T[], task: Pick<TaskRecord, "id">): T[];
|
|
175
178
|
export declare function gradeEvidence(input: {
|
|
176
179
|
task: TaskRecord;
|
|
177
180
|
evidence: AttemptEvidence;
|
|
@@ -189,18 +192,18 @@ declare const GradeSummarySchema: z.ZodObject<{
|
|
|
189
192
|
passed: z.ZodBoolean;
|
|
190
193
|
rewardEligible: z.ZodBoolean;
|
|
191
194
|
failureClass: z.ZodNullable<z.ZodEnum<{
|
|
192
|
-
|
|
193
|
-
grader_failure: "grader_failure";
|
|
195
|
+
cancelled: "cancelled";
|
|
194
196
|
environment_failure: "environment_failure";
|
|
197
|
+
grader_failure: "grader_failure";
|
|
195
198
|
infrastructure_failure: "infrastructure_failure";
|
|
199
|
+
policy_failure: "policy_failure";
|
|
196
200
|
timeout: "timeout";
|
|
197
|
-
cancelled: "cancelled";
|
|
198
201
|
}>>;
|
|
199
202
|
gradingStatus: z.ZodEnum<{
|
|
203
|
+
not_configured: "not_configured";
|
|
200
204
|
pending: "pending";
|
|
201
205
|
scored: "scored";
|
|
202
206
|
unscorable: "unscorable";
|
|
203
|
-
not_configured: "not_configured";
|
|
204
207
|
}>;
|
|
205
208
|
}, z.core.$strict>;
|
|
206
209
|
/** Shared ordinary grading policy. Results must match the declared population;
|
|
@@ -215,18 +218,18 @@ export declare const TaskGradeSchema: z.ZodObject<{
|
|
|
215
218
|
passed: z.ZodBoolean;
|
|
216
219
|
rewardEligible: z.ZodBoolean;
|
|
217
220
|
failureClass: z.ZodNullable<z.ZodEnum<{
|
|
218
|
-
|
|
219
|
-
grader_failure: "grader_failure";
|
|
221
|
+
cancelled: "cancelled";
|
|
220
222
|
environment_failure: "environment_failure";
|
|
223
|
+
grader_failure: "grader_failure";
|
|
221
224
|
infrastructure_failure: "infrastructure_failure";
|
|
225
|
+
policy_failure: "policy_failure";
|
|
222
226
|
timeout: "timeout";
|
|
223
|
-
cancelled: "cancelled";
|
|
224
227
|
}>>;
|
|
225
228
|
gradingStatus: z.ZodEnum<{
|
|
229
|
+
not_configured: "not_configured";
|
|
226
230
|
pending: "pending";
|
|
227
231
|
scored: "scored";
|
|
228
232
|
unscorable: "unscorable";
|
|
229
|
-
not_configured: "not_configured";
|
|
230
233
|
}>;
|
|
231
234
|
schemaVersion: z.ZodLiteral<"openpond.taskGrade.v1">;
|
|
232
235
|
taskHash: z.ZodString;
|
|
@@ -237,8 +240,8 @@ export declare const TaskGradeSchema: z.ZodObject<{
|
|
|
237
240
|
graderId: z.ZodString;
|
|
238
241
|
graderVersion: z.ZodString;
|
|
239
242
|
status: z.ZodOptional<z.ZodEnum<{
|
|
240
|
-
pending: "pending";
|
|
241
243
|
failed: "failed";
|
|
244
|
+
pending: "pending";
|
|
242
245
|
scored: "scored";
|
|
243
246
|
unavailable: "unavailable";
|
|
244
247
|
}>>;
|
|
@@ -246,12 +249,12 @@ export declare const TaskGradeSchema: z.ZodObject<{
|
|
|
246
249
|
passed: z.ZodBoolean;
|
|
247
250
|
rewardEligible: z.ZodBoolean;
|
|
248
251
|
failureClass: z.ZodNullable<z.ZodEnum<{
|
|
249
|
-
|
|
250
|
-
grader_failure: "grader_failure";
|
|
252
|
+
cancelled: "cancelled";
|
|
251
253
|
environment_failure: "environment_failure";
|
|
254
|
+
grader_failure: "grader_failure";
|
|
252
255
|
infrastructure_failure: "infrastructure_failure";
|
|
256
|
+
policy_failure: "policy_failure";
|
|
253
257
|
timeout: "timeout";
|
|
254
|
-
cancelled: "cancelled";
|
|
255
258
|
}>>;
|
|
256
259
|
feedback: z.ZodArray<z.ZodString>;
|
|
257
260
|
visibleEvidenceRefs: z.ZodArray<z.ZodString>;
|
|
@@ -271,12 +274,12 @@ export declare const TaskGradeSchema: z.ZodObject<{
|
|
|
271
274
|
schemaVersion: z.ZodLiteral<"openpond.modelJudgeTransportPolicy.v1">;
|
|
272
275
|
responseFormat: z.ZodLiteral<"judgment_json_schema">;
|
|
273
276
|
reasoningEffort: z.ZodEnum<{
|
|
274
|
-
|
|
277
|
+
high: "high";
|
|
275
278
|
low: "low";
|
|
279
|
+
max: "max";
|
|
276
280
|
medium: "medium";
|
|
277
|
-
|
|
281
|
+
off: "off";
|
|
278
282
|
xhigh: "xhigh";
|
|
279
|
-
max: "max";
|
|
280
283
|
}>;
|
|
281
284
|
maximumOutputTokens: z.ZodNumber;
|
|
282
285
|
}, z.core.$strict>>;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"graders.d.ts","sourceRoot":"","sources":["
|
|
1
|
+
{"version":3,"file":"graders.d.ts","sourceRoot":"","sources":["../../src/graders.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAGxB,OAAO,KAAK,EAA2B,UAAU,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAErF,OAAO,EAAE,2BAA2B,EAAE,0BAA0B,EAAE,MAAM,4BAA4B,CAAC;AAErG,eAAO,MAAM,+BAA+B;;;;;;;;;;;;kBAKjC,CAAC;AACZ,MAAM,MAAM,yBAAyB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,+BAA+B,CAAC,CAAC;AAExF,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAezB,CAAC;AAEZ,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAa7B,CAAC;AACZ,eAAO,MAAM,oBAAoB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAAkF,CAAC;AAEpH,MAAM,MAAM,eAAe,GAAG;IAC5B,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAChC,gBAAgB,EAAE,MAAM,EAAE,CAAC;IAC3B,YAAY,EAAE,MAAM,EAAE,CAAC;IACvB,mBAAmB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACrC,CAAC;AACF,MAAM,MAAM,gBAAgB,GAAG,CAAC,KAAK,EAAE;IAAE,MAAM,EAAE,OAAO,CAAC,UAAU,EAAE;QAAE,IAAI,EAAE,aAAa,CAAA;KAAE,CAAC,CAAC;IAAC,IAAI,EAAE,UAAU,CAAC;IAAC,QAAQ,EAAE,eAAe,CAAC;IAAC,gBAAgB,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IAAC,MAAM,CAAC,EAAE,WAAW,CAAA;CAAE,KAAK,OAAO,CAAC,IAAI,CAAC,cAAc,EAAE,eAAe,GAAG,UAAU,GAAG,eAAe,GAAG,aAAa,CAAC,CAAC,CAAC;AACxT,MAAM,MAAM,oBAAoB,GAAG,CAAC,KAAK,EAAE;IAAE,MAAM,EAAE,OAAO,CAAC,UAAU,EAAE;QAAE,IAAI,EAAE,iBAAiB,CAAA;KAAE,CAAC,CAAC;IAAC,IAAI,EAAE,UAAU,CAAC;IAAC,QAAQ,EAAE,eAAe,CAAA;CAAE,KAAK,OAAO,CAAC,IAAI,CAAC,cAAc,EAAE,eAAe,GAAG,UAAU,GAAG,eAAe,GAAG,aAAa,CAAC,CAAC,CAAC;AAEvP;gFACgF;AAChF,wBAAgB,cAAc,CAAC,CAAC,SAAS,IAAI,CAAC,UAAU,EAAE,SAAS,CAAC,EAAE,OAAO,EAAE,SAAS,CAAC,EAAE,EAAE,IAAI,EAAE,IAAI,CAAC,UAAU,EAAE,IAAI,CAAC,GAAG,CAAC,EAAE,CAE9H;AAED,wBAAsB,aAAa,CAAC,KAAK,EAAE;IACzC,IAAI,EAAE,UAAU,CAAC;IACjB,QAAQ,EAAE,eAAe,CAAC;IAC1B,oFAAoF;IACpF,gBAAgB,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IAClD,OAAO,EAAE,UAAU,EAAE,CAAC;IACtB,UAAU,CAAC,EAAE,gBAAgB,CAAC;IAC9B,cAAc,CAAC,EAAE,oBAAoB,CAAC;IACtC,OAAO,CAAC,EAAE,SAAS,GAAG,qBAAqB,CAAC;IAC5C,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC,CA2B5B;AA8BD,MAAM,MAAM,cAAc,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,oBAAoB,CAAC,CAAC;AAElE,QAAA,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;kBAIb,CAAC;AAEZ;6EAC6E;AAC7E,wBAAgB,qBAAqB,CAAC,KAAK,EAAE;IAC3C,OAAO,EAAE,aAAa,CAAC,IAAI,CAAC,UAAU,EAAE,IAAI,GAAG,SAAS,GAAG,QAAQ,GAAG,UAAU,GAAG,gBAAgB,CAAC,CAAC,CAAC;IACtG,UAAU,EAAE,aAAa,CAAC,IAAI,CAAC,cAAc,EAAE,UAAU,GAAG,eAAe,GAAG,OAAO,GAAG,QAAQ,GAAG,gBAAgB,GAAG,cAAc,GAAG,QAAQ,CAAC,CAAC,CAAC;IAClJ,mBAAmB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACrC,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,kBAAkB,CAAC,CA0BrC;AAED,eAAO,MAAM,eAAe;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAId,CAAC;AACf,MAAM,MAAM,SAAS,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,eAAe,CAAC,CAAC;AAExD,wBAAsB,iBAAiB,CAAC,KAAK,EAAE,UAAU,CAAC,OAAO,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,SAAS,CAAC,CAMtG;AAED;+EAC+E;AAC/E,wBAAgB,eAAe,CAAC,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,OAAO,aAAa,CAAC,CAAC,CAAC,CAAC,EAAE,MAAM,GAAG,UAAU,GAAG,SAAS,CAAC,GAAG,SAAS,CAW5I"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"harness-experiment-source.d.ts","sourceRoot":"","sources":["
|
|
1
|
+
{"version":3,"file":"harness-experiment-source.d.ts","sourceRoot":"","sources":["../../src/harness-experiment-source.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AACxB,OAAO,EAA6D,KAAK,aAAa,EAAE,KAAK,cAAc,EAAE,KAAK,eAAe,EAAE,MAAM,mBAAmB,CAAC;AAE7J;2EAC2E;AAC3E,eAAO,MAAM,uCAAuC;;;;;;;;;;kBAIzC,CAAC;AACZ,MAAM,MAAM,iCAAiC,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,uCAAuC,CAAC,CAAC;AACxG,eAAO,MAAM,sCAAsC,KAAK,CAAC;AAEzD,wBAAgB,sCAAsC,CAAC,MAAM,EAAE;IAAE,aAAa,EAAE,aAAa,CAAC;IAAC,cAAc,EAAE,cAAc,CAAA;CAAE,GAAG,OAAO,CAGxI;AAED;gFACgF;AAChF,eAAO,MAAM,gCAAgC,EAAE,WAAW,CAAC,MAAM,CAE/D,CAAC;AAEH,wBAAgB,gCAAgC,CAAC,MAAM,EAAE;IACvD,aAAa,EAAE,aAAa,CAAC;IAC7B,cAAc,EAAE,cAAc,CAAC;CAChC,GAAG,eAAe,EAAE,CAIpB;AAED;gFACgF;AAChF,wBAAgB,qCAAqC,CAAC,MAAM,EAAE;IAC5D,aAAa,EAAE,aAAa,CAAC;IAC7B,cAAc,EAAE,cAAc,CAAC;CAChC,GAAG,eAAe,EAAE,CAepB"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"harness.d.ts","sourceRoot":"","sources":["
|
|
1
|
+
{"version":3,"file":"harness.d.ts","sourceRoot":"","sources":["../../src/harness.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAExB,OAAO,EAGL,kBAAkB,EAClB,0BAA0B,EAI1B,KAAK,WAAW,EAChB,KAAK,eAAe,EACrB,MAAM,mBAAmB,CAAC;AAE3B,OAAO,EAEL,KAAK,cAAc,EACnB,KAAK,WAAW,EACjB,MAAM,WAAW,CAAC;AAEnB,cAAc,2BAA2B,CAAC;AAE1C,MAAM,MAAM,YAAY,GAAG;IAAE,EAAE,EAAE,MAAM,CAAC;IAAC,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;CAAE,CAAC;AAE7E,MAAM,WAAW,cAAc;IAC7B,MAAM,CAAC,KAAK,EAAE;QACZ,QAAQ,EAAE,WAAW,CAAC;QACtB,MAAM,EAAE,MAAM,CAAC;QACf,IAAI,EAAE,MAAM,CAAC;QACb,MAAM,EAAE,WAAW,CAAC;KACrB,GAAG,OAAO,CAAC,YAAY,CAAC,CAAC;IAC1B,KAAK,CACH,KAAK,EAAE,YAAY,EACnB,KAAK,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,WAAW,CAAA;KAAE,GAC3C,OAAO,CAAC,IAAI,CAAC,CAAC;IACjB,IAAI,CACF,KAAK,EAAE,YAAY,EACnB,MAAM,EAAE,WAAW,EACnB,MAAM,EAAE,WAAW,GAClB,OAAO,CAAC,eAAe,CAAC,CAAC;IAC5B,OAAO,CACL,KAAK,EAAE,YAAY,EACnB,MAAM,EAAE,WAAW,GAClB,OAAO,CAAC;QACT,YAAY,EAAE,CAAC,CAAC,KAAK,CAAC,OAAO,0BAA0B,CAAC,EAAE,CAAC;QAC3D,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;KACnC,CAAC,CAAC;IACH,OAAO,CAAC,KAAK,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;CAC7C;AAED,MAAM,MAAM,qBAAqB,GAAG;IAClC,QAAQ,EAAE,WAAW,CAAC;IACtB,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,CAAC;AAEF,MAAM,MAAM,sBAAsB,GAAG;IACnC,OAAO,EAAE,cAAc,CAAC;IACxB,KAAK,EAAE,CAAC,CAAC,KAAK,CAAC,OAAO,kBAAkB,CAAC,CAAC;IAC1C,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;CACjC,CAAC;AAEF,MAAM,WAAW,eAAe;IAC9B,OAAO,CAAC,KAAK,EAAE,qBAAqB,GAAG,OAAO,CAAC,sBAAsB,CAAC,CAAC;CACxE;AAED,MAAM,WAAW,gBAAgB;IAC/B,GAAG,CAAC,KAAK,EAAE;QACT,QAAQ,EAAE,WAAW,CAAC;QACtB,OAAO,EAAE,MAAM,EAAE,CAAC;QAClB,KAAK,EAAE,MAAM,EAAE,CAAC;QAChB,WAAW,EAAE,MAAM,CAAC;QACpB,MAAM,CAAC,EAAE,WAAW,CAAC;KACtB,GAAG,OAAO,CAAC,sBAAsB,EAAE,CAAC,CAAC;CACvC;AAED,wBAAsB,sBAAsB,CAAC,KAAK,EAAE;IAClD,QAAQ,EAAE,WAAW,CAAC;IACtB,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,WAAW,EAAE,CAAC;IACvB,OAAO,EAAE,cAAc,CAAC;IACxB,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,GAAG,CAAC,EAAE,MAAM,MAAM,CAAC;CACpB,GAAG,OAAO,CAAC,sBAAsB,CAAC,CA8JlC"}
|