@evolvingmachines/evolve 0.0.63 → 0.0.65
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/chunk-DK2MGUPB.js +427 -0
- package/dist/cli/index.cjs +39 -39
- package/dist/cli/index.d.cts +1 -1
- package/dist/cli/index.d.ts +1 -1
- package/dist/cli/index.js +30 -30
- package/dist/index.cjs +47 -47
- package/dist/index.d.cts +2 -2
- package/dist/index.d.ts +2 -2
- package/dist/index.js +22 -22
- package/dist/{types-LYvFBfCo.d.cts → types-B_qmzlMk.d.cts} +125 -5
- package/dist/{types-LYvFBfCo.d.ts → types-B_qmzlMk.d.ts} +125 -5
- package/package.json +4 -4
- package/skills/evolve-evals/SKILL.md +1 -1
- package/skills/evolve-evals/references/cli-reference/analyze.mdx +11 -1
- package/skills/evolve-evals/references/cli-reference/job.mdx +6 -1
- package/skills/evolve-evals/references/core-concepts/analyze.mdx +2 -2
- package/skills/evolve-evals/references/core-concepts/sharing.mdx +1 -1
- package/skills/evolve-evals/references/core-concepts/teams.mdx +3 -3
- package/skills/evolve-evals/references/core-concepts/upload.mdx +2 -0
- package/skills/evolve-evals/references/dashboard/checks.mdx +7 -1
- package/skills/evolve-evals/references/dashboard/jobs.mdx +4 -4
- package/skills/evolve-evals/references/dashboard/traces.mdx +2 -2
- package/skills/evolve-evals/references/dashboard/trial-viewer.mdx +1 -1
- package/skills/evolve-evals/references/sdk-reference/analyses.mdx +27 -0
- package/skills/evolve-evals/references/sdk-reference/jobs.mdx +16 -5
- package/skills/evolve-evals/references/sdk-reference/types.mdx +2 -1
- package/spec/openapi.yaml +313 -13
- package/dist/chunk-B4QFLLPV.js +0 -427
package/dist/index.d.cts
CHANGED
|
@@ -4,8 +4,8 @@ import { ZodType, z } from 'zod';
|
|
|
4
4
|
export { E2BConfig, E2BProvider, createE2BProvider } from '@evolvingmachines/e2b';
|
|
5
5
|
export { DaytonaConfig, DaytonaProvider, createDaytonaProvider } from '@evolvingmachines/daytona';
|
|
6
6
|
export { ModalConfig, ModalProvider, createModalProvider } from '@evolvingmachines/modal';
|
|
7
|
-
import { U as UsageReading, i as JobVisibility, G as GatewayUsageEvent, j as JobShareRequest, k as JobShares, T as Trial, l as Job, h as TraceEvent, a as TrialAnalysis, C as Check, m as TaskCheck, H as HostedErrorCode, n as DatasetsClient, o as AgentsClient, p as JobsClient, S as SkillsClient, q as TrialsClient, r as AnalysesClient, s as ChecksClient, O as OrgsClient, t as CapabilityDocument, u as HostedClientConfig, v as AuthClient } from './types-
|
|
8
|
-
export { w as AGENT_EFFORT_SUPPORT_VALUES, x as ANALYSIS_ARTIFACT_STREAMS, y as ANALYSIS_STATUSES, z as ActiveDataset, B as AgentArm, E as AgentArmInput, F as AgentCapability, I as AgentDatasetStats, K as AgentEffortSupport, L as AgentInfo, A as AgentInput, M as AgentList, N as AgentModelOption, Q as AgentPage, V as AgentResult, W as AgentSource, X as AgentSourceInput, Y as AgentUpsertInput, Z as AnalysisArtifactStream, _ as AnalysisCheck, $ as AnalysisEvidence, a0 as AnalysisFailure, a1 as AnalysisLabel, a2 as AnalysisList, a3 as AnalysisPage, a4 as AnalysisStatus, a5 as AnalysisTranscript, a6 as AnalysisTranscriptOptions, a7 as AnalyzeConfig, a8 as AnalyzeConfigInput, a9 as
|
|
7
|
+
import { U as UsageReading, i as JobVisibility, G as GatewayUsageEvent, j as JobShareRequest, k as JobShares, T as Trial, l as Job, h as TraceEvent, a as TrialAnalysis, C as Check, m as TaskCheck, H as HostedErrorCode, n as DatasetsClient, o as AgentsClient, p as JobsClient, S as SkillsClient, q as TrialsClient, r as AnalysesClient, s as ChecksClient, O as OrgsClient, t as CapabilityDocument, u as HostedClientConfig, v as AuthClient } from './types-B_qmzlMk.cjs';
|
|
8
|
+
export { w as AGENT_EFFORT_SUPPORT_VALUES, x as ANALYSIS_ARTIFACT_STREAMS, y as ANALYSIS_STATUSES, z as ActiveDataset, B as AgentArm, E as AgentArmInput, F as AgentCapability, I as AgentDatasetStats, K as AgentEffortSupport, L as AgentInfo, A as AgentInput, M as AgentList, N as AgentModelOption, Q as AgentPage, V as AgentResult, W as AgentSource, X as AgentSourceInput, Y as AgentUpsertInput, Z as AnalysisArtifactStream, _ as AnalysisCheck, $ as AnalysisEvidence, a0 as AnalysisFailure, a1 as AnalysisLabel, a2 as AnalysisList, a3 as AnalysisPage, a4 as AnalysisStatus, a5 as AnalysisTranscript, a6 as AnalysisTranscriptOptions, a7 as AnalyzeConfig, a8 as AnalyzeConfigInput, a9 as AnalyzeDefaults, aa as ApiKey, ab as AttemptPhase, ac as AuthStatus, ad as Awaitable, ae as CHECK_STATUSES, af as CheckDefaults, ag as CheckLabel, ah as CheckRow, ai as CheckRowList, aj as CheckRowPage, ak as CheckTaskTally, al as CompareCell, am as CompareCoverage, an as CompareJobAggregate, ao as CompareResponse, ap as CompareTaskRow, aq as Dataset, b as DatasetImport, ar as DatasetImportFailure, as as DatasetImportList, at as DatasetImportPage, e as DatasetImportProgress, au as DatasetImportStatus, av as DatasetList, aw as DatasetPage, ax as DatasetPatch, ay as DatasetPreflight, az as DatasetRef, aA as DatasetSelector, aB as DatasetSource, D as DatasetVersion, aC as DatasetVersionArchiveSource, aD as DatasetVersionArchiveUrlSource, aE as DatasetVersionGitSource, aF as DatasetVersionHubSource, aG as DatasetVersionSource, aH as DatasetVersionState, aI as DownloadDatasetOptions, aJ as DownloadJobOptions, aK as EVAL_SANDBOX_PROVIDERS, aL as EvalAgent, aM as EvalModelInfo, aN as EvalSandboxProvider, aO as EvalStepResult, aP as ExceptionInfo, aQ as FilesystemArchiveOptions, aR as FilesystemBox, aS as FilesystemCapture, aT as FilesystemChange, aU as FilesystemChanges, aV as FilesystemChangesOptions, aW as FilesystemEntry, aX as FilesystemListOptions, aY as FilesystemListing, aZ as FilesystemReadOptions, a_ as FilesystemSearchHit, a$ as FilesystemSearchOptions, b0 as FilesystemSearchResult, b1 as FilesystemSource, b2 as FilesystemState, b3 as FilesystemStatus, b4 as FilesystemStreamEvent, b5 as FilesystemStreamOptions, b6 as FilesystemWatchResult, b7 as GATEWAY_TRACE_SEQ_BASE, b8 as GatewayUsage, b9 as GetDatasetOptions, ba as GrepJobOptions, bb as HOSTED_ERROR_CODES, bc as ImportPhase, bd as ImportPhaseProgress, be as ImportWarning, bf as InfraFailureSignature, bg as JOB_LIST_KINDS, bh as JOB_LIST_SCOPES, bi as JobAnalysisStats, J as JobCreate, bj as JobDeleteResult, c as JobEvent, bk as JobFailure, bl as JobGrepGroup, bm as JobGrepPage, bn as JobImport, bo as JobImportFailure, bp as JobImportList, bq as JobImportPage, br as JobImportPhaseName, bs as JobImportPhaseProgress, bt as JobImportProgress, bu as JobImportSkippedTrial, bv as JobImportSource, bw as JobList, bx as JobListItem, by as JobListItemList, bz as JobListItemPage, bA as JobListKind, bB as JobListScope, bC as JobPage, bD as JobShareEmail, bE as JobShareLink, bF as JobStats, bG as JobStatus, bH as JobTaskLink, bI as JobTaskRollup, bJ as JobTaskRollupList, bK as JobTaskRollupPage, bL as JobViewer, bM as JobWatch, bN as JudgeResult, bO as ListAgentsOptions, bP as ListAnalysesOptions, bQ as ListDatasetsOptions, bR as ListImportsOptions, bS as ListJobImportsOptions, bT as ListJobTasksOptions, bU as ListJobsOptions, bV as ListSkillsOptions, bW as ListTrialFilesOptions, bX as ListTrialsOptions, bY as ManagedProviderCapability, bZ as OrgInvite, b_ as OrgInviteCreated, b$ as OrgJoined, c0 as OrgMember, c1 as OrgQuota, c2 as OrgRole, c3 as OrgUsage, c4 as Organization, c5 as OrganizationDetail, c6 as Page, c7 as PageOptions, c8 as PassAtKGroup, c9 as PassAtKPoint, ca as PreflightDatasetInput, cb as PreflightDeferredCheck, cc as PreflightManifestVerdict, cd as PreflightTaskVerdict, ce as ProviderCapability, P as PublishDatasetInput, cf as PublishDatasetOptions, cg as RegradeRequest, ch as ResumeRequest, ci as RetryRequest, R as Rubric, cj as RubricCriterion, ck as RunFilesystem, cl as SANDBOX_LOG_STREAMS, cm as SandboxLogEvent, cn as SandboxLogLine, co as SandboxLogLines, cp as SandboxLogOptions, cq as SandboxLogStream, cr as SandboxProcs, cs as SkillLock, ct as SkillUpload, cu as SkillUploadList, cv as SkillUploadPage, cw as SourceJob, cx as SpendSource, cy as StartJobOptions, cz as StatusVocabulary, cA as StopResponse, cB as TASK_LINKED_BY, cC as TASK_LINK_REASONS, cD as TRIAL_ARTIFACT_STREAMS, cE as TRIAL_STATUSES, cF as Task, cG as TaskCheckTranscript, cH as TaskLinkReason, cI as TaskLinkedBy, cJ as TaskNote, cK as TaskPackageFiles, cL as TaskPackageFilesystemStatus, cM as TaskProviderVerdict, cN as TimingInfo, cO as TraceEventPage, cP as TraceOptions, cQ as TrialArtifactStream, cR as TrialCounts, cS as TrialFile, cT as TrialFilePage, cU as TrialFileRange, cV as TrialGpuCost, cW as TrialList, cX as TrialPage, cY as TrialStatus, cZ as TrialStatusTally, c_ as TrialTaskLink, c$ as TrialUploadProvenance, d0 as UploadJobOptions, d1 as UploadProvenance, d2 as UploadSkillOptions, d3 as UpstreamStatus, d4 as VerifierEnvironmentMode, d5 as VerifierResult, d6 as WatchAnalysisOptions, d7 as WatchImportOptions, d8 as WatchJobImportOptions, d9 as WatchJobOptions, da as gatewayUsageOf, db as isHostedErrorCode, dc as passAtK } from './types-B_qmzlMk.cjs';
|
|
9
9
|
|
|
10
10
|
/**
|
|
11
11
|
* The one skills resolver.
|
package/dist/index.d.ts
CHANGED
|
@@ -4,8 +4,8 @@ import { ZodType, z } from 'zod';
|
|
|
4
4
|
export { E2BConfig, E2BProvider, createE2BProvider } from '@evolvingmachines/e2b';
|
|
5
5
|
export { DaytonaConfig, DaytonaProvider, createDaytonaProvider } from '@evolvingmachines/daytona';
|
|
6
6
|
export { ModalConfig, ModalProvider, createModalProvider } from '@evolvingmachines/modal';
|
|
7
|
-
import { U as UsageReading, i as JobVisibility, G as GatewayUsageEvent, j as JobShareRequest, k as JobShares, T as Trial, l as Job, h as TraceEvent, a as TrialAnalysis, C as Check, m as TaskCheck, H as HostedErrorCode, n as DatasetsClient, o as AgentsClient, p as JobsClient, S as SkillsClient, q as TrialsClient, r as AnalysesClient, s as ChecksClient, O as OrgsClient, t as CapabilityDocument, u as HostedClientConfig, v as AuthClient } from './types-
|
|
8
|
-
export { w as AGENT_EFFORT_SUPPORT_VALUES, x as ANALYSIS_ARTIFACT_STREAMS, y as ANALYSIS_STATUSES, z as ActiveDataset, B as AgentArm, E as AgentArmInput, F as AgentCapability, I as AgentDatasetStats, K as AgentEffortSupport, L as AgentInfo, A as AgentInput, M as AgentList, N as AgentModelOption, Q as AgentPage, V as AgentResult, W as AgentSource, X as AgentSourceInput, Y as AgentUpsertInput, Z as AnalysisArtifactStream, _ as AnalysisCheck, $ as AnalysisEvidence, a0 as AnalysisFailure, a1 as AnalysisLabel, a2 as AnalysisList, a3 as AnalysisPage, a4 as AnalysisStatus, a5 as AnalysisTranscript, a6 as AnalysisTranscriptOptions, a7 as AnalyzeConfig, a8 as AnalyzeConfigInput, a9 as
|
|
7
|
+
import { U as UsageReading, i as JobVisibility, G as GatewayUsageEvent, j as JobShareRequest, k as JobShares, T as Trial, l as Job, h as TraceEvent, a as TrialAnalysis, C as Check, m as TaskCheck, H as HostedErrorCode, n as DatasetsClient, o as AgentsClient, p as JobsClient, S as SkillsClient, q as TrialsClient, r as AnalysesClient, s as ChecksClient, O as OrgsClient, t as CapabilityDocument, u as HostedClientConfig, v as AuthClient } from './types-B_qmzlMk.js';
|
|
8
|
+
export { w as AGENT_EFFORT_SUPPORT_VALUES, x as ANALYSIS_ARTIFACT_STREAMS, y as ANALYSIS_STATUSES, z as ActiveDataset, B as AgentArm, E as AgentArmInput, F as AgentCapability, I as AgentDatasetStats, K as AgentEffortSupport, L as AgentInfo, A as AgentInput, M as AgentList, N as AgentModelOption, Q as AgentPage, V as AgentResult, W as AgentSource, X as AgentSourceInput, Y as AgentUpsertInput, Z as AnalysisArtifactStream, _ as AnalysisCheck, $ as AnalysisEvidence, a0 as AnalysisFailure, a1 as AnalysisLabel, a2 as AnalysisList, a3 as AnalysisPage, a4 as AnalysisStatus, a5 as AnalysisTranscript, a6 as AnalysisTranscriptOptions, a7 as AnalyzeConfig, a8 as AnalyzeConfigInput, a9 as AnalyzeDefaults, aa as ApiKey, ab as AttemptPhase, ac as AuthStatus, ad as Awaitable, ae as CHECK_STATUSES, af as CheckDefaults, ag as CheckLabel, ah as CheckRow, ai as CheckRowList, aj as CheckRowPage, ak as CheckTaskTally, al as CompareCell, am as CompareCoverage, an as CompareJobAggregate, ao as CompareResponse, ap as CompareTaskRow, aq as Dataset, b as DatasetImport, ar as DatasetImportFailure, as as DatasetImportList, at as DatasetImportPage, e as DatasetImportProgress, au as DatasetImportStatus, av as DatasetList, aw as DatasetPage, ax as DatasetPatch, ay as DatasetPreflight, az as DatasetRef, aA as DatasetSelector, aB as DatasetSource, D as DatasetVersion, aC as DatasetVersionArchiveSource, aD as DatasetVersionArchiveUrlSource, aE as DatasetVersionGitSource, aF as DatasetVersionHubSource, aG as DatasetVersionSource, aH as DatasetVersionState, aI as DownloadDatasetOptions, aJ as DownloadJobOptions, aK as EVAL_SANDBOX_PROVIDERS, aL as EvalAgent, aM as EvalModelInfo, aN as EvalSandboxProvider, aO as EvalStepResult, aP as ExceptionInfo, aQ as FilesystemArchiveOptions, aR as FilesystemBox, aS as FilesystemCapture, aT as FilesystemChange, aU as FilesystemChanges, aV as FilesystemChangesOptions, aW as FilesystemEntry, aX as FilesystemListOptions, aY as FilesystemListing, aZ as FilesystemReadOptions, a_ as FilesystemSearchHit, a$ as FilesystemSearchOptions, b0 as FilesystemSearchResult, b1 as FilesystemSource, b2 as FilesystemState, b3 as FilesystemStatus, b4 as FilesystemStreamEvent, b5 as FilesystemStreamOptions, b6 as FilesystemWatchResult, b7 as GATEWAY_TRACE_SEQ_BASE, b8 as GatewayUsage, b9 as GetDatasetOptions, ba as GrepJobOptions, bb as HOSTED_ERROR_CODES, bc as ImportPhase, bd as ImportPhaseProgress, be as ImportWarning, bf as InfraFailureSignature, bg as JOB_LIST_KINDS, bh as JOB_LIST_SCOPES, bi as JobAnalysisStats, J as JobCreate, bj as JobDeleteResult, c as JobEvent, bk as JobFailure, bl as JobGrepGroup, bm as JobGrepPage, bn as JobImport, bo as JobImportFailure, bp as JobImportList, bq as JobImportPage, br as JobImportPhaseName, bs as JobImportPhaseProgress, bt as JobImportProgress, bu as JobImportSkippedTrial, bv as JobImportSource, bw as JobList, bx as JobListItem, by as JobListItemList, bz as JobListItemPage, bA as JobListKind, bB as JobListScope, bC as JobPage, bD as JobShareEmail, bE as JobShareLink, bF as JobStats, bG as JobStatus, bH as JobTaskLink, bI as JobTaskRollup, bJ as JobTaskRollupList, bK as JobTaskRollupPage, bL as JobViewer, bM as JobWatch, bN as JudgeResult, bO as ListAgentsOptions, bP as ListAnalysesOptions, bQ as ListDatasetsOptions, bR as ListImportsOptions, bS as ListJobImportsOptions, bT as ListJobTasksOptions, bU as ListJobsOptions, bV as ListSkillsOptions, bW as ListTrialFilesOptions, bX as ListTrialsOptions, bY as ManagedProviderCapability, bZ as OrgInvite, b_ as OrgInviteCreated, b$ as OrgJoined, c0 as OrgMember, c1 as OrgQuota, c2 as OrgRole, c3 as OrgUsage, c4 as Organization, c5 as OrganizationDetail, c6 as Page, c7 as PageOptions, c8 as PassAtKGroup, c9 as PassAtKPoint, ca as PreflightDatasetInput, cb as PreflightDeferredCheck, cc as PreflightManifestVerdict, cd as PreflightTaskVerdict, ce as ProviderCapability, P as PublishDatasetInput, cf as PublishDatasetOptions, cg as RegradeRequest, ch as ResumeRequest, ci as RetryRequest, R as Rubric, cj as RubricCriterion, ck as RunFilesystem, cl as SANDBOX_LOG_STREAMS, cm as SandboxLogEvent, cn as SandboxLogLine, co as SandboxLogLines, cp as SandboxLogOptions, cq as SandboxLogStream, cr as SandboxProcs, cs as SkillLock, ct as SkillUpload, cu as SkillUploadList, cv as SkillUploadPage, cw as SourceJob, cx as SpendSource, cy as StartJobOptions, cz as StatusVocabulary, cA as StopResponse, cB as TASK_LINKED_BY, cC as TASK_LINK_REASONS, cD as TRIAL_ARTIFACT_STREAMS, cE as TRIAL_STATUSES, cF as Task, cG as TaskCheckTranscript, cH as TaskLinkReason, cI as TaskLinkedBy, cJ as TaskNote, cK as TaskPackageFiles, cL as TaskPackageFilesystemStatus, cM as TaskProviderVerdict, cN as TimingInfo, cO as TraceEventPage, cP as TraceOptions, cQ as TrialArtifactStream, cR as TrialCounts, cS as TrialFile, cT as TrialFilePage, cU as TrialFileRange, cV as TrialGpuCost, cW as TrialList, cX as TrialPage, cY as TrialStatus, cZ as TrialStatusTally, c_ as TrialTaskLink, c$ as TrialUploadProvenance, d0 as UploadJobOptions, d1 as UploadProvenance, d2 as UploadSkillOptions, d3 as UpstreamStatus, d4 as VerifierEnvironmentMode, d5 as VerifierResult, d6 as WatchAnalysisOptions, d7 as WatchImportOptions, d8 as WatchJobImportOptions, d9 as WatchJobOptions, da as gatewayUsageOf, db as isHostedErrorCode, dc as passAtK } from './types-B_qmzlMk.js';
|
|
9
9
|
|
|
10
10
|
/**
|
|
11
11
|
* The one skills resolver.
|