@evolvingmachines/evolve 0.0.65 → 0.0.67-train-harness-wave-2026-09-25.20260926.e00a8a6d

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.
Files changed (153) hide show
  1. package/dist/{chunk-DK2MGUPB.js → chunk-DI6LPW2B.js} +2 -2
  2. package/dist/cli/index.cjs +29 -29
  3. package/dist/cli/index.d.cts +3 -3
  4. package/dist/cli/index.d.ts +3 -3
  5. package/dist/cli/index.js +18 -18
  6. package/dist/index.cjs +64 -60
  7. package/dist/index.d.cts +297 -18
  8. package/dist/index.d.ts +297 -18
  9. package/dist/index.js +48 -44
  10. package/dist/{types-B_qmzlMk.d.cts → types-Dj0iMl5V.d.cts} +70 -90
  11. package/dist/{types-B_qmzlMk.d.ts → types-Dj0iMl5V.d.ts} +70 -90
  12. package/harness-capabilities.json +285 -0
  13. package/package.json +9 -6
  14. package/skills/create-adapter/SKILL.md +71 -26
  15. package/skills/create-task/SKILL.md +124 -66
  16. package/skills/evolve/SKILL.md +37 -20
  17. package/skills/evolve-evals/SKILL.md +142 -69
  18. package/skills/evolve-evals/references/cli-reference/agent.md +76 -0
  19. package/skills/evolve-evals/references/cli-reference/analysis.md +78 -0
  20. package/skills/evolve-evals/references/cli-reference/analyze.md +97 -0
  21. package/skills/evolve-evals/references/cli-reference/auth.md +96 -0
  22. package/skills/evolve-evals/references/cli-reference/check.md +157 -0
  23. package/skills/evolve-evals/references/cli-reference/dataset.md +154 -0
  24. package/skills/evolve-evals/references/cli-reference/filesystem.md +168 -0
  25. package/skills/evolve-evals/references/cli-reference/index.md +149 -0
  26. package/skills/evolve-evals/references/cli-reference/job.md +198 -0
  27. package/skills/evolve-evals/references/cli-reference/run.md +188 -0
  28. package/skills/evolve-evals/references/cli-reference/secrets.md +77 -0
  29. package/skills/evolve-evals/references/cli-reference/session.md +56 -0
  30. package/skills/evolve-evals/references/cli-reference/skill.md +52 -0
  31. package/skills/evolve-evals/references/cli-reference/skills.md +85 -0
  32. package/skills/evolve-evals/references/cli-reference/trial.md +115 -0
  33. package/skills/evolve-evals/references/cli-reference/upload.md +72 -0
  34. package/skills/evolve-evals/references/core-concepts/agents.md +101 -0
  35. package/skills/evolve-evals/references/core-concepts/analyze.md +143 -0
  36. package/skills/evolve-evals/references/core-concepts/check.md +116 -0
  37. package/skills/evolve-evals/references/core-concepts/compatibility.md +39 -0
  38. package/skills/evolve-evals/references/core-concepts/compose.md +103 -0
  39. package/skills/evolve-evals/references/core-concepts/datasets.md +234 -0
  40. package/skills/evolve-evals/references/core-concepts/index.md +52 -0
  41. package/skills/evolve-evals/references/core-concepts/jobs.md +223 -0
  42. package/skills/evolve-evals/references/core-concepts/models.md +73 -0
  43. package/skills/evolve-evals/references/core-concepts/multi-step.md +93 -0
  44. package/skills/evolve-evals/references/core-concepts/rewardkit.md +341 -0
  45. package/skills/evolve-evals/references/core-concepts/sandboxes.md +73 -0
  46. package/skills/evolve-evals/references/core-concepts/secrets.md +86 -0
  47. package/skills/evolve-evals/references/core-concepts/sharing.md +81 -0
  48. package/skills/evolve-evals/references/core-concepts/skills.md +100 -0
  49. package/skills/evolve-evals/references/core-concepts/task-config.md +169 -0
  50. package/skills/evolve-evals/references/core-concepts/task-environment.md +127 -0
  51. package/skills/evolve-evals/references/core-concepts/task-reference.md +191 -0
  52. package/skills/evolve-evals/references/core-concepts/task-verifiers.md +209 -0
  53. package/skills/evolve-evals/references/core-concepts/tasks.md +90 -0
  54. package/skills/evolve-evals/references/core-concepts/teams.md +128 -0
  55. package/skills/evolve-evals/references/core-concepts/trial-outputs.md +225 -0
  56. package/skills/evolve-evals/references/core-concepts/trials.md +129 -0
  57. package/skills/evolve-evals/references/core-concepts/upload-sdk-session.md +240 -0
  58. package/skills/evolve-evals/references/core-concepts/upload.md +166 -0
  59. package/skills/evolve-evals/references/dashboard/checks.md +54 -0
  60. package/skills/evolve-evals/references/dashboard/datasets.md +65 -0
  61. package/skills/evolve-evals/references/dashboard/jobs.md +106 -0
  62. package/skills/evolve-evals/references/dashboard/traces.md +54 -0
  63. package/skills/evolve-evals/references/dashboard/trial-viewer.md +77 -0
  64. package/skills/evolve-evals/references/getting-started/first-task.md +228 -0
  65. package/skills/evolve-evals/references/getting-started/installation.md +79 -0
  66. package/skills/evolve-evals/references/getting-started/quick-start.md +100 -0
  67. package/skills/evolve-evals/references/index.md +58 -0
  68. package/skills/evolve-evals/references/sdk/http.md +110 -0
  69. package/skills/evolve-evals/references/sdk/python.md +108 -0
  70. package/skills/evolve-evals/references/sdk/typescript.md +104 -0
  71. package/skills/evolve-evals/references/sdk-reference/agents.md +75 -0
  72. package/skills/evolve-evals/references/sdk-reference/analyses.md +125 -0
  73. package/skills/evolve-evals/references/sdk-reference/auth.md +171 -0
  74. package/skills/evolve-evals/references/sdk-reference/checks.md +146 -0
  75. package/skills/evolve-evals/references/sdk-reference/datasets.md +170 -0
  76. package/skills/evolve-evals/references/sdk-reference/error-codes.md +231 -0
  77. package/skills/evolve-evals/references/sdk-reference/errors.md +98 -0
  78. package/skills/evolve-evals/references/sdk-reference/filesystem.md +166 -0
  79. package/skills/evolve-evals/references/sdk-reference/index.md +161 -0
  80. package/skills/evolve-evals/references/sdk-reference/jobs.md +250 -0
  81. package/skills/evolve-evals/references/sdk-reference/meta.md +54 -0
  82. package/skills/evolve-evals/references/sdk-reference/methods/agents.md +154 -0
  83. package/skills/evolve-evals/references/sdk-reference/methods/analyses.md +211 -0
  84. package/skills/evolve-evals/references/sdk-reference/methods/auth.md +257 -0
  85. package/skills/evolve-evals/references/sdk-reference/methods/checks.md +462 -0
  86. package/skills/evolve-evals/references/sdk-reference/methods/datasets.md +687 -0
  87. package/skills/evolve-evals/references/sdk-reference/methods/filesystem.md +527 -0
  88. package/skills/evolve-evals/references/sdk-reference/methods/jobs.md +1023 -0
  89. package/skills/evolve-evals/references/sdk-reference/methods/meta.md +213 -0
  90. package/skills/evolve-evals/references/sdk-reference/methods/secrets.md +157 -0
  91. package/skills/evolve-evals/references/sdk-reference/methods/skills.md +125 -0
  92. package/skills/evolve-evals/references/sdk-reference/methods/trials.md +371 -0
  93. package/skills/evolve-evals/references/sdk-reference/secrets.md +104 -0
  94. package/skills/evolve-evals/references/sdk-reference/skills.md +66 -0
  95. package/skills/evolve-evals/references/sdk-reference/trials.md +164 -0
  96. package/skills/evolve-evals/references/sdk-reference/types.md +1255 -0
  97. package/skills/publish/SKILL.md +103 -79
  98. package/skills/rewardkit/SKILL.md +78 -23
  99. package/spec/openapi.yaml +164 -160
  100. package/skills/evolve-evals/references/cli-reference/agent.mdx +0 -79
  101. package/skills/evolve-evals/references/cli-reference/analysis.mdx +0 -160
  102. package/skills/evolve-evals/references/cli-reference/analyze.mdx +0 -84
  103. package/skills/evolve-evals/references/cli-reference/auth.mdx +0 -133
  104. package/skills/evolve-evals/references/cli-reference/check.mdx +0 -263
  105. package/skills/evolve-evals/references/cli-reference/dataset.mdx +0 -151
  106. package/skills/evolve-evals/references/cli-reference/index.mdx +0 -108
  107. package/skills/evolve-evals/references/cli-reference/job.mdx +0 -278
  108. package/skills/evolve-evals/references/cli-reference/run.mdx +0 -204
  109. package/skills/evolve-evals/references/cli-reference/secrets.mdx +0 -95
  110. package/skills/evolve-evals/references/cli-reference/skill.mdx +0 -61
  111. package/skills/evolve-evals/references/cli-reference/skills.mdx +0 -81
  112. package/skills/evolve-evals/references/cli-reference/trial.mdx +0 -181
  113. package/skills/evolve-evals/references/cli-reference/upload.mdx +0 -36
  114. package/skills/evolve-evals/references/core-concepts/agents.mdx +0 -106
  115. package/skills/evolve-evals/references/core-concepts/analyze.mdx +0 -86
  116. package/skills/evolve-evals/references/core-concepts/check.mdx +0 -64
  117. package/skills/evolve-evals/references/core-concepts/datasets.mdx +0 -138
  118. package/skills/evolve-evals/references/core-concepts/index.mdx +0 -42
  119. package/skills/evolve-evals/references/core-concepts/jobs.mdx +0 -151
  120. package/skills/evolve-evals/references/core-concepts/models.mdx +0 -68
  121. package/skills/evolve-evals/references/core-concepts/sandboxes.mdx +0 -52
  122. package/skills/evolve-evals/references/core-concepts/secrets.mdx +0 -41
  123. package/skills/evolve-evals/references/core-concepts/sharing.mdx +0 -35
  124. package/skills/evolve-evals/references/core-concepts/skills.mdx +0 -42
  125. package/skills/evolve-evals/references/core-concepts/tasks.mdx +0 -216
  126. package/skills/evolve-evals/references/core-concepts/teams.mdx +0 -36
  127. package/skills/evolve-evals/references/core-concepts/trial-outputs.mdx +0 -117
  128. package/skills/evolve-evals/references/core-concepts/trials.mdx +0 -103
  129. package/skills/evolve-evals/references/core-concepts/upload.mdx +0 -93
  130. package/skills/evolve-evals/references/dashboard/checks.mdx +0 -21
  131. package/skills/evolve-evals/references/dashboard/datasets.mdx +0 -24
  132. package/skills/evolve-evals/references/dashboard/jobs.mdx +0 -65
  133. package/skills/evolve-evals/references/dashboard/traces.mdx +0 -17
  134. package/skills/evolve-evals/references/dashboard/trial-viewer.mdx +0 -30
  135. package/skills/evolve-evals/references/getting-started/installation.mdx +0 -56
  136. package/skills/evolve-evals/references/getting-started/quick-start.mdx +0 -94
  137. package/skills/evolve-evals/references/index.mdx +0 -48
  138. package/skills/evolve-evals/references/sdk/python.mdx +0 -161
  139. package/skills/evolve-evals/references/sdk/typescript.mdx +0 -163
  140. package/skills/evolve-evals/references/sdk-reference/agents.mdx +0 -108
  141. package/skills/evolve-evals/references/sdk-reference/analyses.mdx +0 -222
  142. package/skills/evolve-evals/references/sdk-reference/auth.mdx +0 -116
  143. package/skills/evolve-evals/references/sdk-reference/checks.mdx +0 -300
  144. package/skills/evolve-evals/references/sdk-reference/datasets.mdx +0 -346
  145. package/skills/evolve-evals/references/sdk-reference/errors.mdx +0 -210
  146. package/skills/evolve-evals/references/sdk-reference/index.mdx +0 -60
  147. package/skills/evolve-evals/references/sdk-reference/jobs.mdx +0 -822
  148. package/skills/evolve-evals/references/sdk-reference/meta.mdx +0 -52
  149. package/skills/evolve-evals/references/sdk-reference/skills.mdx +0 -69
  150. package/skills/evolve-evals/references/sdk-reference/trials.mdx +0 -302
  151. package/skills/evolve-evals/references/sdk-reference/types.mdx +0 -274
  152. package/skills/evolve-evals/references/snippets/global-options.mdx +0 -13
  153. package/skills/evolve-evals/references/snippets/list-flags.mdx +0 -23
@@ -1,5 +1,5 @@
1
1
  #!/usr/bin/env node
2
- import { T as Trial, a as TrialAnalysis, A as AgentInput, J as JobCreate, P as PublishDatasetInput, D as DatasetVersion, b as DatasetImport, C as Check, c as JobEvent, d as DatasetFailedTask, e as DatasetImportProgress, R as Rubric, f as JobSecretInline, g as JobSecretRef, h as TraceEvent } from '../types-B_qmzlMk.cjs';
2
+ import { T as Trial, a as TrialAnalysis, A as AgentInput, J as JobCreate, P as PublishDatasetInput, D as DatasetVersion, b as DatasetImport, C as Check, c as JobEvent, d as DatasetFailedTask, e as DatasetImportProgress, R as Rubric, f as JobSecretInline, g as JobSecretRef, h as TraceEvent } from '../types-Dj0iMl5V.cjs';
3
3
 
4
4
  /**
5
5
  * evolve — the CLI for Evolve hosted datasets & jobs.
@@ -252,8 +252,8 @@ declare function analysisResultLines(runs: Trial[]): string[];
252
252
  * | Fail | N/A | Cost ($)) with an errored task's row dashed, then one
253
253
  * `❌ task: reason` line per failed task and the total agent cost — their
254
254
  * `_render_checks_table` / `_render_check_summary`. A task that is still
255
- * queued or running has no verdict yet and prints its status in the
256
- * outcome column.
255
+ * queued or running has no result yet: its status prints in the OUTCOME
256
+ * column of the one-task table and beside its name in the summary table.
257
257
  */
258
258
  declare function checkResultLines(check: Check): string[];
259
259
  /** The record head for `check show` and the verb's return: id, status, source, policy, then Harbor's tables. */
@@ -1,5 +1,5 @@
1
1
  #!/usr/bin/env node
2
- import { T as Trial, a as TrialAnalysis, A as AgentInput, J as JobCreate, P as PublishDatasetInput, D as DatasetVersion, b as DatasetImport, C as Check, c as JobEvent, d as DatasetFailedTask, e as DatasetImportProgress, R as Rubric, f as JobSecretInline, g as JobSecretRef, h as TraceEvent } from '../types-B_qmzlMk.js';
2
+ import { T as Trial, a as TrialAnalysis, A as AgentInput, J as JobCreate, P as PublishDatasetInput, D as DatasetVersion, b as DatasetImport, C as Check, c as JobEvent, d as DatasetFailedTask, e as DatasetImportProgress, R as Rubric, f as JobSecretInline, g as JobSecretRef, h as TraceEvent } from '../types-Dj0iMl5V.js';
3
3
 
4
4
  /**
5
5
  * evolve — the CLI for Evolve hosted datasets & jobs.
@@ -252,8 +252,8 @@ declare function analysisResultLines(runs: Trial[]): string[];
252
252
  * | Fail | N/A | Cost ($)) with an errored task's row dashed, then one
253
253
  * `❌ task: reason` line per failed task and the total agent cost — their
254
254
  * `_render_checks_table` / `_render_check_summary`. A task that is still
255
- * queued or running has no verdict yet and prints its status in the
256
- * outcome column.
255
+ * queued or running has no result yet: its status prints in the OUTCOME
256
+ * column of the one-task table and beside its name in the summary table.
257
257
  */
258
258
  declare function checkResultLines(check: Check): string[];
259
259
  /** The record head for `check show` and the verb's return: id, status, source, policy, then Harbor's tables. */