@e2edev/e2e 0.7.0 → 0.8.0

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.
Files changed (195) hide show
  1. package/README.md +8 -3
  2. package/dist/agent/act-validation.d.ts +7 -4
  3. package/dist/agent/act-validation.d.ts.map +1 -1
  4. package/dist/agent/act-validation.js +18 -3
  5. package/dist/agent/act-validation.js.map +1 -1
  6. package/dist/agent/act.d.ts +2 -2
  7. package/dist/agent/act.d.ts.map +1 -1
  8. package/dist/agent/act.js +228 -51
  9. package/dist/agent/act.js.map +1 -1
  10. package/dist/agent/default-agent.d.ts +1 -1
  11. package/dist/agent/default-agent.d.ts.map +1 -1
  12. package/dist/agent/default-agent.js +19 -84
  13. package/dist/agent/default-agent.js.map +1 -1
  14. package/dist/agent/executor.d.ts +7 -0
  15. package/dist/agent/executor.d.ts.map +1 -1
  16. package/dist/agent/executor.js.map +1 -1
  17. package/dist/agent/index.d.ts.map +1 -1
  18. package/dist/agent/index.js +14 -6
  19. package/dist/agent/index.js.map +1 -1
  20. package/dist/agent/invocation.d.ts +1 -8
  21. package/dist/agent/invocation.d.ts.map +1 -1
  22. package/dist/agent/invocation.js +7 -51
  23. package/dist/agent/invocation.js.map +1 -1
  24. package/dist/agent/ledger.d.ts.map +1 -1
  25. package/dist/agent/ledger.js +10 -1
  26. package/dist/agent/ledger.js.map +1 -1
  27. package/dist/agent/loop-guards.d.ts +21 -0
  28. package/dist/agent/loop-guards.d.ts.map +1 -1
  29. package/dist/agent/loop-guards.js +48 -0
  30. package/dist/agent/loop-guards.js.map +1 -1
  31. package/dist/agent/model/sdk.d.ts +18 -0
  32. package/dist/agent/model/sdk.d.ts.map +1 -1
  33. package/dist/agent/model/sdk.js +9 -3
  34. package/dist/agent/model/sdk.js.map +1 -1
  35. package/dist/agent/observation-budget.d.ts +27 -0
  36. package/dist/agent/observation-budget.d.ts.map +1 -0
  37. package/dist/agent/observation-budget.js +43 -0
  38. package/dist/agent/observation-budget.js.map +1 -0
  39. package/dist/agent/observation.d.ts +40 -7
  40. package/dist/agent/observation.d.ts.map +1 -1
  41. package/dist/agent/observation.js +56 -11
  42. package/dist/agent/observation.js.map +1 -1
  43. package/dist/agent/phases.d.ts +1 -1
  44. package/dist/agent/phases.d.ts.map +1 -1
  45. package/dist/agent/phases.js +11 -13
  46. package/dist/agent/phases.js.map +1 -1
  47. package/dist/agent/primitives.d.ts +14 -2
  48. package/dist/agent/primitives.d.ts.map +1 -1
  49. package/dist/agent/primitives.js +98 -54
  50. package/dist/agent/primitives.js.map +1 -1
  51. package/dist/agent/screen-update.d.ts +47 -0
  52. package/dist/agent/screen-update.d.ts.map +1 -0
  53. package/dist/agent/screen-update.js +222 -0
  54. package/dist/agent/screen-update.js.map +1 -0
  55. package/dist/agent/step-cache.d.ts +38 -10
  56. package/dist/agent/step-cache.d.ts.map +1 -1
  57. package/dist/agent/step-cache.js +86 -45
  58. package/dist/agent/step-cache.js.map +1 -1
  59. package/dist/agent/tool-loop.d.ts.map +1 -1
  60. package/dist/agent/tool-loop.js +27 -4
  61. package/dist/agent/tool-loop.js.map +1 -1
  62. package/dist/cache/decide.d.ts +4 -3
  63. package/dist/cache/decide.d.ts.map +1 -1
  64. package/dist/cache/decide.js.map +1 -1
  65. package/dist/cli/index.d.ts.map +1 -1
  66. package/dist/cli/index.js +2 -0
  67. package/dist/cli/index.js.map +1 -1
  68. package/dist/cli/init/engines.d.ts +2 -3
  69. package/dist/cli/init/engines.d.ts.map +1 -1
  70. package/dist/cli/init/engines.js +3 -4
  71. package/dist/cli/init/engines.js.map +1 -1
  72. package/dist/cli/signals.d.ts +3 -3
  73. package/dist/cli/signals.js +3 -3
  74. package/dist/config/agent.d.ts +6 -2
  75. package/dist/config/agent.d.ts.map +1 -1
  76. package/dist/config/agent.js +6 -2
  77. package/dist/config/agent.js.map +1 -1
  78. package/dist/config/load.d.ts +2 -2
  79. package/dist/config/load.js +2 -2
  80. package/dist/config/resolve.d.ts +16 -4
  81. package/dist/config/resolve.d.ts.map +1 -1
  82. package/dist/config/resolve.js +105 -39
  83. package/dist/config/resolve.js.map +1 -1
  84. package/dist/engine/contract.d.ts +6 -1
  85. package/dist/engine/contract.d.ts.map +1 -1
  86. package/dist/engine/contract.js.map +1 -1
  87. package/dist/engine/index.d.ts +56 -4
  88. package/dist/engine/index.d.ts.map +1 -1
  89. package/dist/engine/index.js +25 -5
  90. package/dist/engine/index.js.map +1 -1
  91. package/dist/engine/session.d.ts.map +1 -1
  92. package/dist/engine/session.js +6 -0
  93. package/dist/engine/session.js.map +1 -1
  94. package/dist/engine/surface.d.ts +6 -2
  95. package/dist/engine/surface.d.ts.map +1 -1
  96. package/dist/internal/options.d.ts +9 -0
  97. package/dist/internal/options.d.ts.map +1 -0
  98. package/dist/internal/options.js +27 -0
  99. package/dist/internal/options.js.map +1 -0
  100. package/dist/locator/expression.js +1 -1
  101. package/dist/locator/expression.js.map +1 -1
  102. package/dist/locator/screen.d.ts.map +1 -1
  103. package/dist/locator/screen.js +4 -2
  104. package/dist/locator/screen.js.map +1 -1
  105. package/dist/report/build.d.ts +2 -1
  106. package/dist/report/build.d.ts.map +1 -1
  107. package/dist/report/build.js +2 -0
  108. package/dist/report/build.js.map +1 -1
  109. package/dist/report/list-model.d.ts +8 -5
  110. package/dist/report/list-model.d.ts.map +1 -1
  111. package/dist/report/list.d.ts +12 -2
  112. package/dist/report/list.d.ts.map +1 -1
  113. package/dist/report/list.js +54 -16
  114. package/dist/report/list.js.map +1 -1
  115. package/dist/report/running-tree.d.ts +5 -4
  116. package/dist/report/running-tree.d.ts.map +1 -1
  117. package/dist/report/running-tree.js +8 -7
  118. package/dist/report/running-tree.js.map +1 -1
  119. package/dist/run/artifacts.d.ts.map +1 -1
  120. package/dist/run/artifacts.js +20 -2
  121. package/dist/run/artifacts.js.map +1 -1
  122. package/dist/run/events.d.ts +14 -7
  123. package/dist/run/events.d.ts.map +1 -1
  124. package/dist/run/events.js +7 -7
  125. package/dist/run/events.js.map +1 -1
  126. package/dist/run/execute.d.ts +24 -5
  127. package/dist/run/execute.d.ts.map +1 -1
  128. package/dist/run/execute.js +67 -25
  129. package/dist/run/execute.js.map +1 -1
  130. package/dist/run/fixtures.d.ts +6 -1
  131. package/dist/run/fixtures.d.ts.map +1 -1
  132. package/dist/run/fixtures.js +0 -1
  133. package/dist/run/fixtures.js.map +1 -1
  134. package/dist/run/in-process.d.ts +1 -1
  135. package/dist/run/in-process.d.ts.map +1 -1
  136. package/dist/run/in-process.js +6 -3
  137. package/dist/run/in-process.js.map +1 -1
  138. package/dist/run/records.d.ts +14 -1
  139. package/dist/run/records.d.ts.map +1 -1
  140. package/dist/run/runner.d.ts +13 -5
  141. package/dist/run/runner.d.ts.map +1 -1
  142. package/dist/run/runner.js +58 -52
  143. package/dist/run/runner.js.map +1 -1
  144. package/dist/run/scheduler.d.ts +4 -6
  145. package/dist/run/scheduler.d.ts.map +1 -1
  146. package/dist/run/scheduler.js +50 -23
  147. package/dist/run/scheduler.js.map +1 -1
  148. package/dist/run/serial.d.ts +2 -4
  149. package/dist/run/serial.d.ts.map +1 -1
  150. package/dist/run/serial.js +4 -2
  151. package/dist/run/serial.js.map +1 -1
  152. package/dist/run/steps.d.ts +25 -0
  153. package/dist/run/steps.d.ts.map +1 -1
  154. package/dist/run/steps.js +12 -0
  155. package/dist/run/steps.js.map +1 -1
  156. package/dist/run/unit-runner.d.ts +7 -2
  157. package/dist/run/unit-runner.d.ts.map +1 -1
  158. package/dist/run/units.d.ts +8 -0
  159. package/dist/run/units.d.ts.map +1 -1
  160. package/dist/run/units.js +11 -0
  161. package/dist/run/units.js.map +1 -1
  162. package/dist/run/worker/entry.js +1 -0
  163. package/dist/run/worker/entry.js.map +1 -1
  164. package/dist/run/worker/handle.d.ts +1 -1
  165. package/dist/run/worker/handle.d.ts.map +1 -1
  166. package/dist/run/worker/handle.js +1 -1
  167. package/dist/run/worker/handle.js.map +1 -1
  168. package/dist/run/worker/protocol.d.ts +2 -0
  169. package/dist/run/worker/protocol.d.ts.map +1 -1
  170. package/dist/run/worker/protocol.js.map +1 -1
  171. package/dist/run/worker/session.d.ts +2 -0
  172. package/dist/run/worker/session.d.ts.map +1 -1
  173. package/dist/run/worker/session.js +1 -0
  174. package/dist/run/worker/session.js.map +1 -1
  175. package/dist/telemetry/telemetry.d.ts +2 -3
  176. package/dist/telemetry/telemetry.d.ts.map +1 -1
  177. package/dist/telemetry/telemetry.js +2 -3
  178. package/dist/telemetry/telemetry.js.map +1 -1
  179. package/dist/types.d.ts +103 -35
  180. package/dist/types.d.ts.map +1 -1
  181. package/package.json +2 -6
  182. package/skills/e2e/SKILL.md +0 -2
  183. package/skills/e2e/references/agent.md +20 -12
  184. package/skills/e2e/references/debugging.md +3 -1
  185. package/skills/e2e/references/running.md +4 -3
  186. package/skills/e2e/references/setup.md +11 -9
  187. package/skills/e2e/references/writing-tests.md +6 -5
  188. package/dist/internal/trace.d.ts +0 -18
  189. package/dist/internal/trace.d.ts.map +0 -1
  190. package/dist/internal/trace.js +0 -46
  191. package/dist/internal/trace.js.map +0 -1
  192. package/dist/run/public.d.ts +0 -19
  193. package/dist/run/public.d.ts.map +0 -1
  194. package/dist/run/public.js +0 -11
  195. package/dist/run/public.js.map +0 -1
@@ -1,46 +0,0 @@
1
- /**
2
- * Live agent tracing for iterating on agentic tests: `E2E_DEBUG=agent` streams
3
- * every invocation phase, model selection, and locate-candidate outcome to
4
- * stderr as it happens, from whichever process runs the attempt. This is a
5
- * debugging aid, not telemetry: the report stays the canonical record.
6
- */
7
- import { sanitizeText, truncateUtf8 } from './errors.js';
8
- /**
9
- * Parsed on first use, not at import, so tests and embedders can set
10
- * `E2E_DEBUG` after this module loads but before the first trace call.
11
- */
12
- let cachedFlags;
13
- function flags() {
14
- cachedFlags ??= new Set((process.env['E2E_DEBUG'] ?? '')
15
- .split(',')
16
- .map((flag) => flag.trim())
17
- .filter((flag) => flag !== ''));
18
- return cachedFlags;
19
- }
20
- function agentTraceEnabled() {
21
- return flags().has('agent') || flags().has('all');
22
- }
23
- /** `E2E_DEBUG=observations` additionally dumps every observation the model sees. */
24
- function observationTraceEnabled() {
25
- return flags().has('observations') || flags().has('all');
26
- }
27
- /**
28
- * Writes one bounded, sanitized trace line when agent tracing is on. Takes a
29
- * thunk so call sites in polling loops pay nothing while tracing is off.
30
- */
31
- export function agentTrace(message) {
32
- if (!agentTraceEnabled())
33
- return;
34
- process.stderr.write(`[e2e agent] ${truncateUtf8(sanitizeText(message()), 2_000)}\n`);
35
- }
36
- /**
37
- * Dumps one full observation as the model will receive it. The text is
38
- * already redacted and size-bounded by the observation pipeline, so the dump
39
- * needs no further truncation to stay safe.
40
- */
41
- export function observationTrace(header, text) {
42
- if (!observationTraceEnabled())
43
- return;
44
- process.stderr.write(`[e2e observation] ${header()}\n${text}\n[e2e observation] end\n`);
45
- }
46
- //# sourceMappingURL=trace.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"trace.js","sourceRoot":"","sources":["../../src/internal/trace.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,EAAE,YAAY,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAEzD;;;GAGG;AACH,IAAI,WAA4C,CAAC;AAEjD,SAAS,KAAK;IACZ,WAAW,KAAK,IAAI,GAAG,CACrB,CAAC,OAAO,CAAC,GAAG,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC;SAC7B,KAAK,CAAC,GAAG,CAAC;SACV,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;SAC1B,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,EAAE,CAAC,CACjC,CAAC;IACF,OAAO,WAAW,CAAC;AACrB,CAAC;AAED,SAAS,iBAAiB;IACxB,OAAO,KAAK,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,KAAK,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;AACpD,CAAC;AAED,oFAAoF;AACpF,SAAS,uBAAuB;IAC9B,OAAO,KAAK,EAAE,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,KAAK,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;AAC3D,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,UAAU,CAAC,OAAqB;IAC9C,IAAI,CAAC,iBAAiB,EAAE;QAAE,OAAO;IACjC,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,eAAe,YAAY,CAAC,YAAY,CAAC,OAAO,EAAE,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;AACxF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,gBAAgB,CAAC,MAAoB,EAAE,IAAY;IACjE,IAAI,CAAC,uBAAuB,EAAE;QAAE,OAAO;IACvC,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,qBAAqB,MAAM,EAAE,KAAK,IAAI,2BAA2B,CAAC,CAAC;AAC1F,CAAC"}
@@ -1,19 +0,0 @@
1
- /**
2
- * Programmatic host surface (`@e2edev/e2e/run`): run the runner in-process and stream
3
- * structured events, without shelling out to the CLI. This is how an
4
- * embedding host — a hosted platform, a CI wrapper, an IDE — drives runs.
5
- *
6
- * The CLI is a thin consumer of exactly this surface; nothing here is
7
- * CLI-only. The surface is host tooling, not part of sdk-0.1: it can grow in
8
- * minors, and `report.json` (report-1) stays the canonical record of a run.
9
- */
10
- export { run } from './runner.ts';
11
- export type { RunOptions, RunOutcome } from './runner.ts';
12
- export type { RunEvent, RunEventFact, RunEventHeader, RunEventOf, RunEventResult, RunEventSink, RunExitCode, RunStatus, SetupStep, } from './events.ts';
13
- export type { ArtifactProducer, ArtifactRecord, AttemptRecord, ResultRecord, ResultStatus, RunError, SerialAttemptRecord, SerialGroupRecord, SerialMemberRecord, } from './records.ts';
14
- export type { StepAgentDetails, StepCacheInfo, StepEvent, StepKind, StepMetrics, StepModelInfo, StepProgress, StepRecord, } from './steps.ts';
15
- export type { Report1Document } from '../report/build.ts';
16
- export type { ErrorCategory, ErrorPhase, SerializedError } from '../internal/errors.ts';
17
- export type { TestIdentity } from '../collect/collect.ts';
18
- export type { SkipInfo } from '../collect/select.ts';
19
- //# sourceMappingURL=public.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"public.d.ts","sourceRoot":"","sources":["../../src/run/public.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,GAAG,EAAE,MAAM,aAAa,CAAC;AAClC,YAAY,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAC1D,YAAY,EACV,QAAQ,EACR,YAAY,EACZ,cAAc,EACd,UAAU,EACV,cAAc,EACd,YAAY,EACZ,WAAW,EACX,SAAS,EACT,SAAS,GACV,MAAM,aAAa,CAAC;AACrB,YAAY,EACV,gBAAgB,EAChB,cAAc,EACd,aAAa,EACb,YAAY,EACZ,YAAY,EACZ,QAAQ,EACR,mBAAmB,EACnB,iBAAiB,EACjB,kBAAkB,GACnB,MAAM,cAAc,CAAC;AACtB,YAAY,EACV,gBAAgB,EAChB,aAAa,EACb,SAAS,EACT,QAAQ,EACR,WAAW,EACX,aAAa,EACb,YAAY,EACZ,UAAU,GACX,MAAM,YAAY,CAAC;AACpB,YAAY,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAI1D,YAAY,EAAE,aAAa,EAAE,UAAU,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAC;AACxF,YAAY,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAC1D,YAAY,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAC"}
@@ -1,11 +0,0 @@
1
- /**
2
- * Programmatic host surface (`@e2edev/e2e/run`): run the runner in-process and stream
3
- * structured events, without shelling out to the CLI. This is how an
4
- * embedding host — a hosted platform, a CI wrapper, an IDE — drives runs.
5
- *
6
- * The CLI is a thin consumer of exactly this surface; nothing here is
7
- * CLI-only. The surface is host tooling, not part of sdk-0.1: it can grow in
8
- * minors, and `report.json` (report-1) stays the canonical record of a run.
9
- */
10
- export { run } from './runner.js';
11
- //# sourceMappingURL=public.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"public.js","sourceRoot":"","sources":["../../src/run/public.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,GAAG,EAAE,MAAM,aAAa,CAAC"}