skip to content
$worker

harness-e2e

v0.9.2-experimental

Measure Harness capability, retain reproducible evidence, and expose the E2E dashboard.

Experimental

Published as experimental by its release pipeline. It installs and resolves like any other worker, but its interface may change without notice.

iiiverified
63 installs0 in 7d0 today
install
$iii trigger compose::add worker=harness-e2e@0.9.2-experimental
  • macOS: arm64
  • Linux: arm64 · armv7 · x64

exact versions are immutable; binary and bundle artifacts are digest-pinned.

functions

34

e2e::archive

function

Persist a completed execution through private iii storage and idempotent history.

request
  • execution_idstringrequired
  • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
response
  • archiveobjectrequired
    • archive_idstringrequired
    • created_atstringrequired
    • execution_idstringrequired
    • expires_atstring
    • identity_sha256stringrequired
    • manifestobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • manifest_backupobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
  • duplicate_ingestionbooleanrequired
  • historyobjectrequired
    • archiveobjectrequired
      • archive_idstringrequired
      • created_atstringrequired
      • execution_idstringrequired
      • expires_atstring
      • identity_sha256stringrequired
      • manifestobjectrequired
        … expand 6 nested
        • bucketstringrequired
        • keystringrequired
        • media_typestringrequired
        • sha256stringrequired
        • size_bytesinteger· uint64requiredmin 0
        • uristringrequired
      • manifest_backupobjectrequired
        … expand 6 nested
        • bucketstringrequired
        • keystringrequired
        • media_typestringrequired
        • sha256stringrequired
        • size_bytesinteger· uint64requiredmin 0
        • uristringrequired
      • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
    • baseline_comparablebooleanrequired
    • case_countinteger· uint32requiredmin 0
    • e2e_repositorystringrequired
    • e2e_revisionstringrequired
    • execution_idstringrequired
    • identity_sha256stringrequired
    • ingestion_idstringrequired
    • lanestringrequired
    • occurred_atstringrequired
    • passedbooleanrequired
    • result_contract_sha256stringrequired
    • scoring_profile_sha256stringrequired
    • stack_modestringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • subject_revisionstringrequired

e2e::archive-head

function

Verify availability and immutable metadata for an archived execution.

request
  • execution_idstringrequired
response
  • archiveobjectrequired
    • archive_idstringrequired
    • created_atstringrequired
    • execution_idstringrequired
    • expires_atstring
    • identity_sha256stringrequired
    • manifestobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • manifest_backupobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
  • availabilitystringrequiredenum: available, expired
  • verified_atstringrequired

e2e::archive-restore

function

Restore and verify an archived execution from its immutable manifest.

request
  • execution_idstringrequired
response
  • archiveobjectrequired
    • archive_idstringrequired
    • created_atstringrequired
    • execution_idstringrequired
    • expires_atstring
    • identity_sha256stringrequired
    • manifestobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • manifest_backupobjectrequired
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
  • availabilitystringrequiredenum: available, expired
  • restored_filesinteger· uint32requiredmin 0
  • restored_from_backupbooleanrequired
  • restored_rootstring

e2e::cancel

function

Request idempotent cancellation and cleanup of an E2E execution.

request
  • execution_idstringrequired
response
  • acceptedbooleanrequired
  • execution_idstringrequired
  • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,

e2e::compare

function

Compare two completed executions when their identities are eligible.

request
  • baselinestring

    Reviewed baseline file to load thresholds from. Omit to use the checked-in `config/baselines/default.json` when it exists, falling back to the code-default thresholds. Ignored when `policy` is set.

  • from_execution_idstringrequired
  • policyany of

    Explicit policy override. Omit to gate on the reviewed baseline.

    any of (2)
    variant 1
    • baseline_idstring

      Identifier of the reviewed baseline these thresholds came from, when one was loaded. Absent when the code-default thresholds are in effect.

    • regressionall of
      … expand 1 nested
      all of (1)
      variant 1
      • cost_increase_rationumber· doublerequired
      • deliverable_success_dropnumber· doublerequired
      • p95_turns_increase_rationumber· doublerequired
      • structural_integrity_dropnumber· doublerequired
      • technical_failure_increasenumber· doublerequired
      • wall_time_increase_rationumber· doublerequired
    • scenario_overridesobject

      Per-scenario partial threshold overrides carried from the reviewed baseline.

    variant 2
    valuenull
  • to_execution_idstringrequired
response
  • artifactsobject[]required
    • idstringrequired
    • kindstringrequired
    • media_typestringrequired
    • pathstringrequired
    • sha256stringrequired
    • size_bytesinteger· uint64requiredmin 0
  • comparisonobjectrequired
    • baseline_idstring

      Reviewed baseline the regression thresholds came from; absent when the code-default thresholds gated this comparison.

    • casesobject[]required
      • complexity_tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
      • deltaobjectrequired
        … expand 16 nested
        • consumptionobject

          Descriptive only; these deltas never create a regression gate.

        • deliverable_success_rateany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • flaky_rateany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • median_scoreany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p50_cost_usdany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p50_turnsany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p50_wall_time_msany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p50_work_amplificationany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p95_cost_usdany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p95_turnsany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p95_wall_time_msany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • p95_work_amplificationany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • retry_rateany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • structural_integrity_rateany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • technical_failure_rateany of
          … expand 2 nested
          any of (2)
          variant 1
          • absolutenumber· doublerequired
          • relative_rationumber· double
          variant 2
          valuenull
        • unavailableobject
      • fromobjectrequired
        … expand 18 nested
        • consumptionall of

          Includes every observed run, even those excluded from quality comparison.

          … expand 1 nested
          all of (1)
          variant 1
          • completed_runsinteger· uint32requiredmin 0
          • observed_runsinteger· uint32requiredmin 0
          • p50_function_callsnumber· double
          • p50_total_tokensnumber· double
          • p95_function_callsnumber· double
          • p95_total_tokensnumber· double
          • tokens_per_completionnumber· double
          • total_tokens_consumedinteger· uint64min 0
          • unavailableobjectrequired
        • deliverable_successany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • excluded_infrastructure_runsinteger· uint32requiredmin 0
        • flaky_ratenumber· double
        • included_runsinteger· uint32requiredmin 0
        • median_scorenumber· double
        • p50_cost_usdnumber· double
        • p50_turnsnumber· double
        • p50_wall_time_msnumber· double
        • p50_work_amplificationnumber· double
        • p95_cost_usdnumber· double
        • p95_turnsnumber· double
        • p95_wall_time_msnumber· double
        • p95_work_amplificationnumber· double
        • retry_ratenumber· double
        • structural_integrityany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • technical_failureany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • unavailableobject
      • from_run_idsstring[]required
      • keyobjectrequired
        … expand 7 nested
        • case_idstringrequired
        • contract_sha256stringrequired
        • executionobjectrequired
          … expand 7 nested
          • e2e_repositorystring
          • judge_modelstring
          • judge_providerstring
          • lanestringrequired
          • stack_modestringrequired
          • subject_modelstringrequired
          • subject_providerstringrequired
        • inputs_sha256stringrequired
        • scenario_idstringrequired
        • scenario_versioninteger· uint32requiredmin 0
        • seedinteger· uint64requiredmin 0
      • regressionsobject[]required
        … expand 11 nested
        • blockingbooleanrequired
        • case_idstringrequired
        • dimensionstringrequiredenum: deliverable, structural_integrity, technical_reliability, cost, wall_time, turns
        • maturitystring
        • n_frominteger· uint32min 0
        • n_tointeger· uint32min 0
        • observed_deltanumber· doublerequired
        • reasonstringrequired
        • scenario_idstringrequired
        • statisticstring
        • thresholdnumber· doublerequired
      • toobjectrequired
        … expand 18 nested
        • consumptionall of

          Includes every observed run, even those excluded from quality comparison.

          … expand 1 nested
          all of (1)
          variant 1
          • completed_runsinteger· uint32requiredmin 0
          • observed_runsinteger· uint32requiredmin 0
          • p50_function_callsnumber· double
          • p50_total_tokensnumber· double
          • p95_function_callsnumber· double
          • p95_total_tokensnumber· double
          • tokens_per_completionnumber· double
          • total_tokens_consumedinteger· uint64min 0
          • unavailableobjectrequired
        • deliverable_successany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • excluded_infrastructure_runsinteger· uint32requiredmin 0
        • flaky_ratenumber· double
        • included_runsinteger· uint32requiredmin 0
        • median_scorenumber· double
        • p50_cost_usdnumber· double
        • p50_turnsnumber· double
        • p50_wall_time_msnumber· double
        • p50_work_amplificationnumber· double
        • p95_cost_usdnumber· double
        • p95_turnsnumber· double
        • p95_wall_time_msnumber· double
        • p95_work_amplificationnumber· double
        • retry_ratenumber· double
        • structural_integrityany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • technical_failureany of
          … expand 2 nested
          any of (2)
          variant 1
          • ci95_lowernumber· doublerequired
          • ci95_uppernumber· doublerequired
          • ratenumber· doublerequired
          • sample_sizeinteger· uint32requiredmin 0
          • successesinteger· uint32requiredmin 0
          variant 2
          valuenull
        • unavailableobject
      • to_run_idsstring[]required
    • cohortobjectrequired
      • excluded_casesobject[]required
        … expand 4 nested
        • case_idstringrequired
        • reasonsstring[]required
        • scenario_idstringrequired
        • sidestringrequiredenum: from, to
      • excluded_runsobject[]required
        … expand 6 nested
        • attempt_idstringrequired
        • case_idstringrequired
        • reasonstringrequired
        • run_idstringrequired
        • scenario_idstringrequired
        • sidestringrequiredenum: from, to
      • included_case_idsstring[]required
    • comparablebooleanrequired
    • comparison_idstringrequired
    • from_execution_idstringrequired
    • from_revisionstring
    • gate_passedbooleanrequired
    • reasonsstring[]required
    • regressionsobject[]required
      • blockingbooleanrequired
      • case_idstringrequired
      • dimensionstringrequiredenum: deliverable, structural_integrity, technical_reliability, cost, wall_time, turns
      • maturitystring
      • n_frominteger· uint32min 0
      • n_tointeger· uint32min 0
      • observed_deltanumber· doublerequired
      • reasonstringrequired
      • scenario_idstringrequired
      • statisticstring
      • thresholdnumber· doublerequired
    • to_execution_idstringrequired
    • to_revisionstring

e2e::dashboard::catalog-get

function

Read models and scenarios when the execution dialog opens.

request
  • urlstring
response
  • local_scenariosobject[]required
    • idstringrequired
    • source_pathstringrequired
    • source_sha256stringrequired
    • titlestringrequired
    • versioninteger· uint32requiredmin 0
  • modelsobject[]required
    • idstringrequired
    • providerstringrequired
  • scenariosstring[]required
  • urlstringrequired

e2e::dashboard::evaluated-versions-list

function

List immutable evaluated-system versions and their exact evaluation cohorts.

request
  • cohort_idstring
response
  • cohortsobject[]required
    • idstringrequired
    • judge_modelstring
    • judge_providerstring
    • lanestringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
  • revisionstringrequired
  • versionsobject[]required
    • cohort_idstringrequired
    • completed_atstringrequired
    • execution_countinteger· uintrequiredmin 0
    • idstringrequired
    • labelstringrequired
    • stack_modestringrequired

e2e::dashboard::execution-get

function

Read one retained execution summary and its diagnostic report.

request
  • execution_idstringrequired
response
  • detailunknownrequired
  • manifestobjectrequired
    • executionsunknown[]required
    • last_updatestringrequired
    • modestringrequired
    • next_cursorstring
    • repo_urlstringrequired
    • retentionobjectrequired
      • detailsinteger· uintrequiredmin 0
      • summariesinteger· uintrequiredmin 0
    • totalinteger· uintrequiredmin 0

e2e::dashboard::executions-list

function

List compact retained execution summaries with server-side filters and cursor pagination.

request
  • cursorstring
  • eventstring
  • idsstring[]
  • ids_csvstring
  • limitinteger· uint16min 0
  • querystring
  • statusstring
response
  • executionsunknown[]required
  • last_updatestringrequired
  • modestringrequired
  • next_cursorstring
  • repo_urlstringrequired
  • retentionobjectrequired
    • detailsinteger· uintrequiredmin 0
    • summariesinteger· uintrequiredmin 0
  • totalinteger· uintrequiredmin 0

e2e::dashboard::local-scenario-create

function

Validate and save one local-only Markdown scenario, then return its compiled identity.

request
  • file_namestringrequired

    One UTF-8 `.md` file name, without a directory. Use letters, numbers, spaces, hyphens, or underscores; its stem becomes `local_<safe_id>`. Existing files are rejected instead of overwritten.

  • sourcestringrequired

    Complete Markdown test definition. It must contain one H1 followed by the required H2 sections in order and contain positive `### Name (N%)` validations totaling exactly 100%.

response
  • scenarioobjectrequired
    • author_versioninteger· uint32min 0
    • behavior_sha256string
    • case_idstringrequired
    • characterizationobjectrequired
      • human_horizonall of
        … expand 1 nested
        all of (1)
        variant 1
        • basisall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: unknown, author_estimate, measured
        • max_minutesinteger· uint32min 0
        • min_minutesinteger· uint32min 0
      • realismall of
        … expand 1 nested
        all of (1)
        variant 1
        • executionall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: synthetic, realistic_simulator, frozen_real_artifact
        • shadowall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: none, read_only
    • classificationobjectrequired
      • methodstringrequiredenum: capability_v2
      • profileobjectrequired
        … expand 16 nested
        • agent_owned_decompositionboolean
        • ambiguity_levelinteger· uint8requiredmin 0
        • artifact_countinteger· uint8requiredmin 0
        • coherent_long_horizonboolean
        • compensable_mutationsinteger· uint8min 0
        • coordination_edgesinteger· uint16requiredmin 0
        • dependency_depthinteger· uint8requiredmin 0
        • durable_resume_cyclesinteger· uint8min 0
        • external_systemsinteger· uint8requiredmin 0
        • material_invalidation_eventsinteger· uint8min 0
        • parallel_branchesinteger· uint8requiredmin 0
        • planning_depthinteger· uint8requiredmin 0
        • replan_loopsinteger· uint8min 0
        • state_transitionsinteger· uint16requiredmin 0
        • validation_loopsinteger· uint8requiredmin 0
        • wake_cyclesinteger· uint8requiredmin 0
      • tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
    • compiled_sha256string
    • complexityobjectrequired
      • agent_owned_decompositionboolean
      • ambiguity_levelinteger· uint8requiredmin 0
      • artifact_countinteger· uint8requiredmin 0
      • coherent_long_horizonboolean
      • compensable_mutationsinteger· uint8min 0
      • coordination_edgesinteger· uint16requiredmin 0
      • dependency_depthinteger· uint8requiredmin 0
      • durable_resume_cyclesinteger· uint8min 0
      • external_systemsinteger· uint8requiredmin 0
      • material_invalidation_eventsinteger· uint8min 0
      • parallel_branchesinteger· uint8requiredmin 0
      • planning_depthinteger· uint8requiredmin 0
      • replan_loopsinteger· uint8min 0
      • state_transitionsinteger· uint16requiredmin 0
      • validation_loopsinteger· uint8requiredmin 0
      • wake_cyclesinteger· uint8requiredmin 0
    • contract_sha256stringrequired
    • deliverable_contractobjectrequired
      • artifactsobject[]required
        … expand 5 nested
        • idstringrequired
        • kindstringrequired
        • max_size_bytesinteger· uint64requiredmin 0
        • media_typestringrequired
        • schemaunknownrequired
      • capture_before_cleanupbooleanrequired
      • invariantsobject[]required
        … expand 2 nested
        • descriptionstringrequired
        • idstringrequired
      • provenance_requiredbooleanrequired
    • inputs_sha256stringrequired
    • originstringrequiredenum: built_in, markdown, local
    • required_capabilitiesstring[]required
    • resource_envelopeobjectrequired
      • executionobjectrequired
        … expand 5 nested
        • max_output_tokensinteger· uint64min 0
        • max_total_tokensinteger· uint64min 0

          Shared Harness token budget. `None` leaves the Harness budget unbounded for this scenario.

        • max_turnsinteger· uint32requiredmin 0
        • max_validation_retriesinteger· uint32min 0

          Optional per-session cap for post-turn validation denials. `None` preserves the Harness-configured default.

        • stuck_timeout_secondsinteger· uint64requiredmin 0

          Stop only after this many seconds without observable useful progress. Large scenarios have no fixed wall-clock deadline.

      • workflowany of
        … expand 2 nested
        any of (2)
        variant 1
        • max_cost_usdnumber· double
        • max_nodesinteger· uint16requiredmin 0
        • max_parallelinteger· uint16requiredmin 0
        • max_total_tokensinteger· uint64min 0
        • step_timeout_secondsinteger· uint64requiredmin 0
        • technical_retriesinteger· uint8requiredmin 0
        • workflow_timeout_secondsinteger· uint64requiredmin 0
        variant 2
        valuenull
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
    • source_pathstring
    • source_sha256string
    • titlestring

e2e::dashboard::plan-control

function

Configure, export and execute saved plans, and inspect or cancel their composed executions.

request
one of (4)
variant 1
  • actionstringrequiredenum: requirements
  • plan_idstringrequired
variant 2
  • actionstringrequiredenum: export
  • plan_idstringrequired
variant 3
  • actionstringrequiredenum: execution
  • execution_idstringrequired
variant 4
  • actionstringrequiredenum: cancel
  • execution_idstringrequired
response
empty object

e2e::dashboard::plan-create

function

Create a draft local plan with an explicit small test scope.

request
  • duplicate_ofstring
  • judge_modelstring
  • judge_providerstring
  • labelstring
  • modelstringrequired
  • providerstringrequired
  • purposestring
  • runsinteger· uint32min 0
  • scenariosstring[]required
  • seedinteger· uint64min 0
  • technical_retriesinteger· uint8min 0
  • template_idstring
  • urlstringrequired
response
  • baseline_execution_idstring
  • candidate_execution_idsstring[]required
  • candidate_labelsobjectrequired
  • compatiblebooleanrequired
  • created_atstringrequired
  • idstringrequired
  • incomplete_execution_idsstring[]required
  • judge_modelstringrequired
  • judge_providerstringrequired
  • labelstringrequired
  • last_attempt_idstring
  • lockedbooleanrequired
  • modelstringrequired
  • protected_executor_requiredbooleanrequired
  • providerstringrequired
  • purposestringrequired
  • runsinteger· uint32requiredmin 0
  • scenario_idsstring[]required
  • scenariosobject[]required
    • case_idstringrequired
    • complexity_tierstringrequired
    • contract_sha256stringrequired
    • inputs_sha256stringrequired
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
  • schema_versioninteger· uint32requiredmin 0
  • scope_hashstringrequired
  • seedinteger· uint64min 0
  • statestringrequiredenum: draft, baseline_running, baseline_ready, candidate_running, comparison_ready
  • technical_retriesinteger· uint8requiredmin 0
  • template_idstring
  • updated_atstringrequired
  • urlstringrequired

e2e::dashboard::plan-get

function

Read one local plan.

request
  • plan_idstringrequired
response
  • baseline_execution_idstring
  • candidate_execution_idsstring[]required
  • candidate_labelsobjectrequired
  • compatiblebooleanrequired
  • created_atstringrequired
  • idstringrequired
  • incomplete_execution_idsstring[]required
  • judge_modelstringrequired
  • judge_providerstringrequired
  • labelstringrequired
  • last_attempt_idstring
  • lockedbooleanrequired
  • modelstringrequired
  • protected_executor_requiredbooleanrequired
  • providerstringrequired
  • purposestringrequired
  • runsinteger· uint32requiredmin 0
  • scenario_idsstring[]required
  • scenariosobject[]required
    • case_idstringrequired
    • complexity_tierstringrequired
    • contract_sha256stringrequired
    • inputs_sha256stringrequired
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
  • schema_versioninteger· uint32requiredmin 0
  • scope_hashstringrequired
  • seedinteger· uint64min 0
  • statestringrequiredenum: draft, baseline_running, baseline_ready, candidate_running, comparison_ready
  • technical_retriesinteger· uint8requiredmin 0
  • template_idstring
  • updated_atstringrequired
  • urlstringrequired

e2e::dashboard::plan-run-start

function

Start a baseline or candidate from a locked local plan.

request
  • idempotency_keystringrequired
  • plan_idstring
  • rolestringrequiredenum: baseline, candidate
response
  • baseline_execution_idstring
  • candidate_execution_idsstring[]required
  • candidate_labelsobjectrequired
  • compatiblebooleanrequired
  • created_atstringrequired
  • idstringrequired
  • incomplete_execution_idsstring[]required
  • judge_modelstringrequired
  • judge_providerstringrequired
  • labelstringrequired
  • last_attempt_idstring
  • lockedbooleanrequired
  • modelstringrequired
  • protected_executor_requiredbooleanrequired
  • providerstringrequired
  • purposestringrequired
  • runsinteger· uint32requiredmin 0
  • scenario_idsstring[]required
  • scenariosobject[]required
    • case_idstringrequired
    • complexity_tierstringrequired
    • contract_sha256stringrequired
    • inputs_sha256stringrequired
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
  • schema_versioninteger· uint32requiredmin 0
  • scope_hashstringrequired
  • seedinteger· uint64min 0
  • statestringrequiredenum: draft, baseline_running, baseline_ready, candidate_running, comparison_ready
  • technical_retriesinteger· uint8requiredmin 0
  • template_idstring
  • updated_atstringrequired
  • urlstringrequired

e2e::dashboard::plan-update

function

Update an unlocked local plan or rename retained candidates.

request
  • candidate_labelsobject
  • judge_modelstring
  • judge_providerstring
  • labelstring
  • modelstring
  • plan_idstring
  • providerstring
  • purposestring
  • runsinteger· uint32min 0
  • scenariosstring[]
  • seedinteger· uint64min 0
  • technical_retriesinteger· uint8min 0
  • urlstring
response
  • baseline_execution_idstring
  • candidate_execution_idsstring[]required
  • candidate_labelsobjectrequired
  • compatiblebooleanrequired
  • created_atstringrequired
  • idstringrequired
  • incomplete_execution_idsstring[]required
  • judge_modelstringrequired
  • judge_providerstringrequired
  • labelstringrequired
  • last_attempt_idstring
  • lockedbooleanrequired
  • modelstringrequired
  • protected_executor_requiredbooleanrequired
  • providerstringrequired
  • purposestringrequired
  • runsinteger· uint32requiredmin 0
  • scenario_idsstring[]required
  • scenariosobject[]required
    • case_idstringrequired
    • complexity_tierstringrequired
    • contract_sha256stringrequired
    • inputs_sha256stringrequired
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
  • schema_versioninteger· uint32requiredmin 0
  • scope_hashstringrequired
  • seedinteger· uint64min 0
  • statestringrequiredenum: draft, baseline_running, baseline_ready, candidate_running, comparison_ready
  • technical_retriesinteger· uint8requiredmin 0
  • template_idstring
  • updated_atstringrequired
  • urlstringrequired

e2e::dashboard::plans-list

function

List local plans and their baseline/candidate lifecycle.

request
empty object
response
  • master_planunknownrequired
  • modestringrequired
  • plansobject[]required
    • baseline_execution_idstring
    • candidate_execution_idsstring[]required
    • candidate_labelsobjectrequired
    • compatiblebooleanrequired
    • created_atstringrequired
    • idstringrequired
    • incomplete_execution_idsstring[]required
    • judge_modelstringrequired
    • judge_providerstringrequired
    • labelstringrequired
    • last_attempt_idstring
    • lockedbooleanrequired
    • modelstringrequired
    • protected_executor_requiredbooleanrequired
    • providerstringrequired
    • purposestringrequired
    • runsinteger· uint32requiredmin 0
    • scenario_idsstring[]required
    • scenariosobject[]required
      • case_idstringrequired
      • complexity_tierstringrequired
      • contract_sha256stringrequired
      • inputs_sha256stringrequired
      • scenario_idstringrequired
      • scenario_versioninteger· uint32requiredmin 0
      • seedinteger· uint64requiredmin 0
    • schema_versioninteger· uint32requiredmin 0
    • scope_hashstringrequired
    • seedinteger· uint64min 0
    • statestringrequiredenum: draft, baseline_running, baseline_ready, candidate_running, comparison_ready
    • technical_retriesinteger· uint8requiredmin 0
    • template_idstring
    • updated_atstringrequired
    • urlstringrequired

e2e::dashboard::run-cancel

function

Cancel the active local E2E execution.

request
empty object
response
  • defaultsobjectrequired
    • judge_modelstringrequired
    • judge_providerstringrequired
    • modelstringrequired
    • providerstringrequired
    • runsinteger· uint32requiredmin 0
    • seedinteger· uint64min 0
    • technical_retriesinteger· uint8requiredmin 0
    • urlstringrequired
  • jobany of
    any of (2)
    variant 1
    • completed_atstringrequired
    • errorstringrequired
    • idstringrequired
    • labelstringrequired
    • logstringrequired
    • log_frominteger· uint64requiredmin 0
    • log_offsetinteger· uint64requiredmin 0
    • log_truncatedbooleanrequired
    • requestobjectrequired
      … expand 10 nested
      • judge_modelstring
      • judge_providerstring
      • labelstring
      • modelstringrequired
      • providerstringrequired
      • runsinteger· uint32requiredmin 0
      • scenariosstring[]required
      • seedinteger· uint64min 0
      • technical_retriesinteger· uint8requiredmin 0
      • urlstringrequired
    • returncodeinteger· int32
    • started_atstringrequired
    • statusstringrequiredenum: running, cancelling, cancelled, completed, failed
    variant 2
    valuenull

e2e::dashboard::run-start

function

Start one local E2E execution.

request
  • judge_modelstring
  • judge_providerstring
  • labelstring
  • modelstringrequired
  • providerstringrequired
  • runsinteger· uint32requiredmin 0
  • scenariosstring[]required
  • seedinteger· uint64min 0
  • technical_retriesinteger· uint8requiredmin 0
  • urlstringrequired
response
  • defaultsobjectrequired
    • judge_modelstringrequired
    • judge_providerstringrequired
    • modelstringrequired
    • providerstringrequired
    • runsinteger· uint32requiredmin 0
    • seedinteger· uint64min 0
    • technical_retriesinteger· uint8requiredmin 0
    • urlstringrequired
  • jobany of
    any of (2)
    variant 1
    • completed_atstringrequired
    • errorstringrequired
    • idstringrequired
    • labelstringrequired
    • logstringrequired
    • log_frominteger· uint64requiredmin 0
    • log_offsetinteger· uint64requiredmin 0
    • log_truncatedbooleanrequired
    • requestobjectrequired
      … expand 10 nested
      • judge_modelstring
      • judge_providerstring
      • labelstring
      • modelstringrequired
      • providerstringrequired
      • runsinteger· uint32requiredmin 0
      • scenariosstring[]required
      • seedinteger· uint64min 0
      • technical_retriesinteger· uint8requiredmin 0
      • urlstringrequired
    • returncodeinteger· int32
    • started_atstringrequired
    • statusstringrequiredenum: running, cancelling, cancelled, completed, failed
    variant 2
    valuenull

e2e::dashboard::run-status

function

Read local execution state and only the unread log suffix.

request
  • afterinteger· uint64min 0
response
  • defaultsobjectrequired
    • judge_modelstringrequired
    • judge_providerstringrequired
    • modelstringrequired
    • providerstringrequired
    • runsinteger· uint32requiredmin 0
    • seedinteger· uint64min 0
    • technical_retriesinteger· uint8requiredmin 0
    • urlstringrequired
  • jobany of
    any of (2)
    variant 1
    • completed_atstringrequired
    • errorstringrequired
    • idstringrequired
    • labelstringrequired
    • logstringrequired
    • log_frominteger· uint64requiredmin 0
    • log_offsetinteger· uint64requiredmin 0
    • log_truncatedbooleanrequired
    • requestobjectrequired
      … expand 10 nested
      • judge_modelstring
      • judge_providerstring
      • labelstring
      • modelstringrequired
      • providerstringrequired
      • runsinteger· uint32requiredmin 0
      • scenariosstring[]required
      • seedinteger· uint64min 0
      • technical_retriesinteger· uint8requiredmin 0
      • urlstringrequired
    • returncodeinteger· int32
    • started_atstringrequired
    • statusstringrequiredenum: running, cancelling, cancelled, completed, failed
    variant 2
    valuenull

e2e::dashboard::test-history-get

function

Read local metric history for one test version, with provider-grouped execution and judge models, without comparison actions.

request
  • case_idstring
  • cursorstring
  • judge_modelstring
  • judge_providerstring
  • limitinteger· uint16min 0
  • resultstring
  • subject_modelstring
  • subject_providerstring
  • system_version_idstring
  • test_idstring
  • test_versioninteger· uint32min 0
response
  • available_versionsobject[]required
    • execution_countinteger· uintrequiredmin 0
    • last_seenstring
    • run_countinteger· uintrequiredmin 0
    • versioninteger· uint32requiredmin 0
  • casesstring[]required
  • current_versioninteger· uint32min 0

    The contract's current version, which may have no executions yet.

  • judge_modelsobject[]required
    • modelsstring[]required
    • providerstringrequired
  • next_cursorstring
  • observationsobject[]required
    • assessment_profile_sha256stringrequired
    • assessment_summaryobjectrequired

      Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

      • assessment_countinteger· uintrequiredmin 0
      • assessment_outcomesobjectrequired
        … expand 6 nested
        • errorinteger· uintrequiredmin 0
        • failedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • partialinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
      • asset_countinteger· uintrequiredmin 0
      • asset_validation_outcomesobjectrequired
        … expand 10 nested
        • invalidinteger· uintrequiredmin 0
        • malformedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • not_producedinteger· uintrequiredmin 0
        • oversizedinteger· uintrequiredmin 0
        • removed_during_cleanupinteger· uintrequiredmin 0
        • unexpectedinteger· uintrequiredmin 0
        • unreadableinteger· uintrequiredmin 0
        • unsafe_pathinteger· uintrequiredmin 0
        • validinteger· uintrequiredmin 0
      • evidence_reference_countinteger· uintrequiredmin 0
      • run_countinteger· uintrequiredmin 0
      • system_statusesobjectrequired
        … expand 7 nested
        • hard_gate_failedinteger· uintrequiredmin 0
        • infrastructure_errorinteger· uintrequiredmin 0
        • judge_errorinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • resource_limitinteger· uintrequiredmin 0
        • subject_errorinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
    • case_idstringrequired
    • cohort_idstringrequired
    • completed_atstringrequired
    • contract_sha256stringrequired
    • engine_revisionstring
    • evaluated_version_idstring
    • execution_idstringrequired
    • harness_revisionstring
    • judge_modelstring
    • judge_providerstring
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_function_call_errorsnumber· double
    • median_function_callsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • median_turnsnumber· double
    • run_countinteger· uintrequiredmin 0
    • scenario_versioninteger· uint32requiredmin 0
    • scored_runsinteger· uintrequiredmin 0
    • seedinteger· uint64min 0
    • stack_modestringrequired
    • statusstringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • system_labelstringrequired
    • system_revisionstring
    • system_version_idstring
  • seriesobject[]required
    • assessment_profile_sha256stringrequired
    • case_idstringrequired
    • cohort_idstringrequired
    • contract_sha256stringrequired
    • engine_revisionstring
    • execution_countinteger· uintrequiredmin 0
    • harness_revisionstring
    • idstringrequired
    • judge_modelstring
    • judge_providerstring
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_function_call_errorsnumber· double
    • median_function_callsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • median_turnsnumber· double
    • run_countinteger· uintrequiredmin 0
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64min 0
    • stack_modestringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • system_labelstringrequired
    • system_revisionstring
    • system_version_idstring
  • subject_modelsobject[]required
    • modelsstring[]required
    • providerstringrequired
  • subjectsstring[]required
  • systemsobject[]required
    • idstringrequired
    • labelstringrequired
  • test_idstringrequired
  • test_versioninteger· uint32requiredmin 0

    The version whose executions are shown (the latest with evidence by default).

  • totalinteger· uintrequiredmin 0

e2e::dashboard::test-version-get

function

Read one test version across two immutable evaluated-system versions.

request
  • cohort_idstringrequired
  • from_version_idstringrequired
  • test_idstringrequired
  • test_versioninteger· uint32requiredmin 0
  • to_version_idstringrequired
response
  • compatibilitystringrequired
  • compatibility_reasonsstring[]required
  • deltaobjectrequired
    • cost_usdnumber· double
    • duration_secondsnumber· double
    • scorenumber· double
    • tokensnumber· double
  • fromany of
    any of (2)
    variant 1
    • assessment_summaryobjectrequired

      Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

      … expand 7 nested
      • assessment_countinteger· uintrequiredmin 0
      • assessment_outcomesobjectrequired
        … expand 6 nested
        • errorinteger· uintrequiredmin 0
        • failedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • partialinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
      • asset_countinteger· uintrequiredmin 0
      • asset_validation_outcomesobjectrequired
        … expand 10 nested
        • invalidinteger· uintrequiredmin 0
        • malformedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • not_producedinteger· uintrequiredmin 0
        • oversizedinteger· uintrequiredmin 0
        • removed_during_cleanupinteger· uintrequiredmin 0
        • unexpectedinteger· uintrequiredmin 0
        • unreadableinteger· uintrequiredmin 0
        • unsafe_pathinteger· uintrequiredmin 0
        • validinteger· uintrequiredmin 0
      • evidence_reference_countinteger· uintrequiredmin 0
      • run_countinteger· uintrequiredmin 0
      • system_statusesobjectrequired
        … expand 7 nested
        • hard_gate_failedinteger· uintrequiredmin 0
        • infrastructure_errorinteger· uintrequiredmin 0
        • judge_errorinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • resource_limitinteger· uintrequiredmin 0
        • subject_errorinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
    • case_countinteger· uintrequiredmin 0
    • evaluated_version_idstringrequired
    • execution_countinteger· uintrequiredmin 0
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • outcomesobjectrequired
      … expand 4 nested
      • hard_gate_failedinteger· uintrequiredmin 0
      • infra_failedinteger· uintrequiredmin 0
      • passedinteger· uintrequiredmin 0
      • technical_failedinteger· uintrequiredmin 0
    • pass_ratenumber· double
    • samplesobjectrequired
      … expand 5 nested
      • cost_usdinteger· uintrequiredmin 0
      • duration_secondsinteger· uintrequiredmin 0
      • scoreinteger· uintrequiredmin 0
      • tokensinteger· uintrequiredmin 0
      • turnsinteger· uintrequiredmin 0
    • scored_runsinteger· uintrequiredmin 0
    • total_runsinteger· uintrequiredmin 0
    variant 2
    valuenull
  • from_observationsobject[]required
    • assessment_profile_sha256stringrequired
    • assessment_summaryobjectrequired

      Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

      • assessment_countinteger· uintrequiredmin 0
      • assessment_outcomesobjectrequired
        … expand 6 nested
        • errorinteger· uintrequiredmin 0
        • failedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • partialinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
      • asset_countinteger· uintrequiredmin 0
      • asset_validation_outcomesobjectrequired
        … expand 10 nested
        • invalidinteger· uintrequiredmin 0
        • malformedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • not_producedinteger· uintrequiredmin 0
        • oversizedinteger· uintrequiredmin 0
        • removed_during_cleanupinteger· uintrequiredmin 0
        • unexpectedinteger· uintrequiredmin 0
        • unreadableinteger· uintrequiredmin 0
        • unsafe_pathinteger· uintrequiredmin 0
        • validinteger· uintrequiredmin 0
      • evidence_reference_countinteger· uintrequiredmin 0
      • run_countinteger· uintrequiredmin 0
      • system_statusesobjectrequired
        … expand 7 nested
        • hard_gate_failedinteger· uintrequiredmin 0
        • infrastructure_errorinteger· uintrequiredmin 0
        • judge_errorinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • resource_limitinteger· uintrequiredmin 0
        • subject_errorinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
    • case_idstringrequired
    • cohort_idstringrequired
    • completed_atstringrequired
    • contract_sha256stringrequired
    • engine_revisionstring
    • evaluated_version_idstring
    • execution_idstringrequired
    • harness_revisionstring
    • judge_modelstring
    • judge_providerstring
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_function_call_errorsnumber· double
    • median_function_callsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • median_turnsnumber· double
    • run_countinteger· uintrequiredmin 0
    • scenario_versioninteger· uint32requiredmin 0
    • scored_runsinteger· uintrequiredmin 0
    • seedinteger· uint64min 0
    • stack_modestringrequired
    • statusstringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • system_labelstringrequired
    • system_revisionstring
    • system_version_idstring
  • test_idstringrequired
  • test_versioninteger· uint32requiredmin 0
  • toany of
    any of (2)
    variant 1
    • assessment_summaryobjectrequired

      Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

      … expand 7 nested
      • assessment_countinteger· uintrequiredmin 0
      • assessment_outcomesobjectrequired
        … expand 6 nested
        • errorinteger· uintrequiredmin 0
        • failedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • partialinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
      • asset_countinteger· uintrequiredmin 0
      • asset_validation_outcomesobjectrequired
        … expand 10 nested
        • invalidinteger· uintrequiredmin 0
        • malformedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • not_producedinteger· uintrequiredmin 0
        • oversizedinteger· uintrequiredmin 0
        • removed_during_cleanupinteger· uintrequiredmin 0
        • unexpectedinteger· uintrequiredmin 0
        • unreadableinteger· uintrequiredmin 0
        • unsafe_pathinteger· uintrequiredmin 0
        • validinteger· uintrequiredmin 0
      • evidence_reference_countinteger· uintrequiredmin 0
      • run_countinteger· uintrequiredmin 0
      • system_statusesobjectrequired
        … expand 7 nested
        • hard_gate_failedinteger· uintrequiredmin 0
        • infrastructure_errorinteger· uintrequiredmin 0
        • judge_errorinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • resource_limitinteger· uintrequiredmin 0
        • subject_errorinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
    • case_countinteger· uintrequiredmin 0
    • evaluated_version_idstringrequired
    • execution_countinteger· uintrequiredmin 0
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • outcomesobjectrequired
      … expand 4 nested
      • hard_gate_failedinteger· uintrequiredmin 0
      • infra_failedinteger· uintrequiredmin 0
      • passedinteger· uintrequiredmin 0
      • technical_failedinteger· uintrequiredmin 0
    • pass_ratenumber· double
    • samplesobjectrequired
      … expand 5 nested
      • cost_usdinteger· uintrequiredmin 0
      • duration_secondsinteger· uintrequiredmin 0
      • scoreinteger· uintrequiredmin 0
      • tokensinteger· uintrequiredmin 0
      • turnsinteger· uintrequiredmin 0
    • scored_runsinteger· uintrequiredmin 0
    • total_runsinteger· uintrequiredmin 0
    variant 2
    valuenull
  • to_observationsobject[]required
    • assessment_profile_sha256stringrequired
    • assessment_summaryobjectrequired

      Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

      • assessment_countinteger· uintrequiredmin 0
      • assessment_outcomesobjectrequired
        … expand 6 nested
        • errorinteger· uintrequiredmin 0
        • failedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • partialinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
      • asset_countinteger· uintrequiredmin 0
      • asset_validation_outcomesobjectrequired
        … expand 10 nested
        • invalidinteger· uintrequiredmin 0
        • malformedinteger· uintrequiredmin 0
        • not_evaluatedinteger· uintrequiredmin 0
        • not_producedinteger· uintrequiredmin 0
        • oversizedinteger· uintrequiredmin 0
        • removed_during_cleanupinteger· uintrequiredmin 0
        • unexpectedinteger· uintrequiredmin 0
        • unreadableinteger· uintrequiredmin 0
        • unsafe_pathinteger· uintrequiredmin 0
        • validinteger· uintrequiredmin 0
      • evidence_reference_countinteger· uintrequiredmin 0
      • run_countinteger· uintrequiredmin 0
      • system_statusesobjectrequired
        … expand 7 nested
        • hard_gate_failedinteger· uintrequiredmin 0
        • infrastructure_errorinteger· uintrequiredmin 0
        • judge_errorinteger· uintrequiredmin 0
        • passedinteger· uintrequiredmin 0
        • resource_limitinteger· uintrequiredmin 0
        • subject_errorinteger· uintrequiredmin 0
        • unavailableinteger· uintrequiredmin 0
    • case_idstringrequired
    • cohort_idstringrequired
    • completed_atstringrequired
    • contract_sha256stringrequired
    • engine_revisionstring
    • evaluated_version_idstring
    • execution_idstringrequired
    • harness_revisionstring
    • judge_modelstring
    • judge_providerstring
    • median_cost_usdnumber· double
    • median_duration_secondsnumber· double
    • median_function_call_errorsnumber· double
    • median_function_callsnumber· double
    • median_scorenumber· double
    • median_tokensnumber· double
    • median_turnsnumber· double
    • run_countinteger· uintrequiredmin 0
    • scenario_versioninteger· uint32requiredmin 0
    • scored_runsinteger· uintrequiredmin 0
    • seedinteger· uint64min 0
    • stack_modestringrequired
    • statusstringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • system_labelstringrequired
    • system_revisionstring
    • system_version_idstring

e2e::dashboard::tests-list

function

List the versioned test catalog with compact A/B results and stable pagination.

request
  • cohort_idstring
  • cursorstring
  • from_version_idstring
  • limitinteger· uint16min 0
  • querystring
  • to_version_idstring
response
  • next_cursorstring
  • revisionstringrequired
  • rowsobject[]required
    • available_versionsobject[]required
      • execution_countinteger· uintrequiredmin 0
      • last_seenstring
      • run_countinteger· uintrequiredmin 0
      • versioninteger· uint32requiredmin 0
    • calibrationany of
      any of (2)
      variant 1
      • compatible_sample_countinteger· uintrequiredmin 0
      • maturitystringrequired
      variant 2
      valuenull
    • characterizationany of
      any of (2)
      variant 1
      • human_horizonall of
        … expand 1 nested
        all of (1)
        variant 1
        • basisall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: unknown, author_estimate, measured
        • max_minutesinteger· uint32min 0
        • min_minutesinteger· uint32min 0
      • realismall of
        … expand 1 nested
        all of (1)
        variant 1
        • executionall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: synthetic, realistic_simulator, frozen_real_artifact
        • shadowall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: none, read_only
      variant 2
      valuenull
    • complexityany of
      any of (2)
      variant 1
      • methodstringrequiredenum: capability_v2
      • profileobjectrequired
        … expand 16 nested
        • agent_owned_decompositionboolean
        • ambiguity_levelinteger· uint8requiredmin 0
        • artifact_countinteger· uint8requiredmin 0
        • coherent_long_horizonboolean
        • compensable_mutationsinteger· uint8min 0
        • coordination_edgesinteger· uint16requiredmin 0
        • dependency_depthinteger· uint8requiredmin 0
        • durable_resume_cyclesinteger· uint8min 0
        • external_systemsinteger· uint8requiredmin 0
        • material_invalidation_eventsinteger· uint8min 0
        • parallel_branchesinteger· uint8requiredmin 0
        • planning_depthinteger· uint8requiredmin 0
        • replan_loopsinteger· uint8min 0
        • state_transitionsinteger· uint16requiredmin 0
        • validation_loopsinteger· uint8requiredmin 0
        • wake_cyclesinteger· uint8requiredmin 0
      • tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
      variant 2
      valuenull
    • current_versioninteger· uint32min 0
    • lifecyclestringrequired
    • resultany of
      any of (2)
      variant 1
      • compatibilitystringrequired
      • compatibility_reasonsstring[]required
      • deltaobjectrequired
        … expand 4 nested
        • cost_usdnumber· double
        • duration_secondsnumber· double
        • scorenumber· double
        • tokensnumber· double
      • fromany of
        … expand 2 nested
        any of (2)
        variant 1
        • assessment_summaryobjectrequired

          Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

          … expand 7 nested
          • assessment_countinteger· uintrequiredmin 0
          • assessment_outcomesobjectrequired
            … expand 6 nested
            • errorinteger· uintrequiredmin 0
            • failedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • partialinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
          • asset_countinteger· uintrequiredmin 0
          • asset_validation_outcomesobjectrequired
            … expand 10 nested
            • invalidinteger· uintrequiredmin 0
            • malformedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • not_producedinteger· uintrequiredmin 0
            • oversizedinteger· uintrequiredmin 0
            • removed_during_cleanupinteger· uintrequiredmin 0
            • unexpectedinteger· uintrequiredmin 0
            • unreadableinteger· uintrequiredmin 0
            • unsafe_pathinteger· uintrequiredmin 0
            • validinteger· uintrequiredmin 0
          • evidence_reference_countinteger· uintrequiredmin 0
          • run_countinteger· uintrequiredmin 0
          • system_statusesobjectrequired
            … expand 7 nested
            • hard_gate_failedinteger· uintrequiredmin 0
            • infrastructure_errorinteger· uintrequiredmin 0
            • judge_errorinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • resource_limitinteger· uintrequiredmin 0
            • subject_errorinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
        • case_countinteger· uintrequiredmin 0
        • evaluated_version_idstringrequired
        • execution_countinteger· uintrequiredmin 0
        • median_cost_usdnumber· double
        • median_duration_secondsnumber· double
        • median_scorenumber· double
        • median_tokensnumber· double
        • outcomesobjectrequired
          … expand 4 nested
          • hard_gate_failedinteger· uintrequiredmin 0
          • infra_failedinteger· uintrequiredmin 0
          • passedinteger· uintrequiredmin 0
          • technical_failedinteger· uintrequiredmin 0
        • pass_ratenumber· double
        • samplesobjectrequired
          … expand 5 nested
          • cost_usdinteger· uintrequiredmin 0
          • duration_secondsinteger· uintrequiredmin 0
          • scoreinteger· uintrequiredmin 0
          • tokensinteger· uintrequiredmin 0
          • turnsinteger· uintrequiredmin 0
        • scored_runsinteger· uintrequiredmin 0
        • total_runsinteger· uintrequiredmin 0
        variant 2
        valuenull
      • from_observationsobject[]required
        … expand 30 nested
        • assessment_profile_sha256stringrequired
        • assessment_summaryobjectrequired

          Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

          … expand 7 nested
          • assessment_countinteger· uintrequiredmin 0
          • assessment_outcomesobjectrequired
            … expand 6 nested
            • errorinteger· uintrequiredmin 0
            • failedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • partialinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
          • asset_countinteger· uintrequiredmin 0
          • asset_validation_outcomesobjectrequired
            … expand 10 nested
            • invalidinteger· uintrequiredmin 0
            • malformedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • not_producedinteger· uintrequiredmin 0
            • oversizedinteger· uintrequiredmin 0
            • removed_during_cleanupinteger· uintrequiredmin 0
            • unexpectedinteger· uintrequiredmin 0
            • unreadableinteger· uintrequiredmin 0
            • unsafe_pathinteger· uintrequiredmin 0
            • validinteger· uintrequiredmin 0
          • evidence_reference_countinteger· uintrequiredmin 0
          • run_countinteger· uintrequiredmin 0
          • system_statusesobjectrequired
            … expand 7 nested
            • hard_gate_failedinteger· uintrequiredmin 0
            • infrastructure_errorinteger· uintrequiredmin 0
            • judge_errorinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • resource_limitinteger· uintrequiredmin 0
            • subject_errorinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
        • case_idstringrequired
        • cohort_idstringrequired
        • completed_atstringrequired
        • contract_sha256stringrequired
        • engine_revisionstring
        • evaluated_version_idstring
        • execution_idstringrequired
        • harness_revisionstring
        • judge_modelstring
        • judge_providerstring
        • median_cost_usdnumber· double
        • median_duration_secondsnumber· double
        • median_function_call_errorsnumber· double
        • median_function_callsnumber· double
        • median_scorenumber· double
        • median_tokensnumber· double
        • median_turnsnumber· double
        • run_countinteger· uintrequiredmin 0
        • scenario_versioninteger· uint32requiredmin 0
        • scored_runsinteger· uintrequiredmin 0
        • seedinteger· uint64min 0
        • stack_modestringrequired
        • statusstringrequired
        • subject_modelstringrequired
        • subject_providerstringrequired
        • system_labelstringrequired
        • system_revisionstring
        • system_version_idstring
      • test_idstringrequired
      • test_versioninteger· uint32requiredmin 0
      • toany of
        … expand 2 nested
        any of (2)
        variant 1
        • assessment_summaryobjectrequired

          Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

          … expand 7 nested
          • assessment_countinteger· uintrequiredmin 0
          • assessment_outcomesobjectrequired
            … expand 6 nested
            • errorinteger· uintrequiredmin 0
            • failedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • partialinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
          • asset_countinteger· uintrequiredmin 0
          • asset_validation_outcomesobjectrequired
            … expand 10 nested
            • invalidinteger· uintrequiredmin 0
            • malformedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • not_producedinteger· uintrequiredmin 0
            • oversizedinteger· uintrequiredmin 0
            • removed_during_cleanupinteger· uintrequiredmin 0
            • unexpectedinteger· uintrequiredmin 0
            • unreadableinteger· uintrequiredmin 0
            • unsafe_pathinteger· uintrequiredmin 0
            • validinteger· uintrequiredmin 0
          • evidence_reference_countinteger· uintrequiredmin 0
          • run_countinteger· uintrequiredmin 0
          • system_statusesobjectrequired
            … expand 7 nested
            • hard_gate_failedinteger· uintrequiredmin 0
            • infrastructure_errorinteger· uintrequiredmin 0
            • judge_errorinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • resource_limitinteger· uintrequiredmin 0
            • subject_errorinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
        • case_countinteger· uintrequiredmin 0
        • evaluated_version_idstringrequired
        • execution_countinteger· uintrequiredmin 0
        • median_cost_usdnumber· double
        • median_duration_secondsnumber· double
        • median_scorenumber· double
        • median_tokensnumber· double
        • outcomesobjectrequired
          … expand 4 nested
          • hard_gate_failedinteger· uintrequiredmin 0
          • infra_failedinteger· uintrequiredmin 0
          • passedinteger· uintrequiredmin 0
          • technical_failedinteger· uintrequiredmin 0
        • pass_ratenumber· double
        • samplesobjectrequired
          … expand 5 nested
          • cost_usdinteger· uintrequiredmin 0
          • duration_secondsinteger· uintrequiredmin 0
          • scoreinteger· uintrequiredmin 0
          • tokensinteger· uintrequiredmin 0
          • turnsinteger· uintrequiredmin 0
        • scored_runsinteger· uintrequiredmin 0
        • total_runsinteger· uintrequiredmin 0
        variant 2
        valuenull
      • to_observationsobject[]required
        … expand 30 nested
        • assessment_profile_sha256stringrequired
        • assessment_summaryobjectrequired

          Objective assessment totals for a set of runs. Every count is derived from deterministic evidence: hard gates, deterministic criteria, and asset validation.

          … expand 7 nested
          • assessment_countinteger· uintrequiredmin 0
          • assessment_outcomesobjectrequired
            … expand 6 nested
            • errorinteger· uintrequiredmin 0
            • failedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • partialinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
          • asset_countinteger· uintrequiredmin 0
          • asset_validation_outcomesobjectrequired
            … expand 10 nested
            • invalidinteger· uintrequiredmin 0
            • malformedinteger· uintrequiredmin 0
            • not_evaluatedinteger· uintrequiredmin 0
            • not_producedinteger· uintrequiredmin 0
            • oversizedinteger· uintrequiredmin 0
            • removed_during_cleanupinteger· uintrequiredmin 0
            • unexpectedinteger· uintrequiredmin 0
            • unreadableinteger· uintrequiredmin 0
            • unsafe_pathinteger· uintrequiredmin 0
            • validinteger· uintrequiredmin 0
          • evidence_reference_countinteger· uintrequiredmin 0
          • run_countinteger· uintrequiredmin 0
          • system_statusesobjectrequired
            … expand 7 nested
            • hard_gate_failedinteger· uintrequiredmin 0
            • infrastructure_errorinteger· uintrequiredmin 0
            • judge_errorinteger· uintrequiredmin 0
            • passedinteger· uintrequiredmin 0
            • resource_limitinteger· uintrequiredmin 0
            • subject_errorinteger· uintrequiredmin 0
            • unavailableinteger· uintrequiredmin 0
        • case_idstringrequired
        • cohort_idstringrequired
        • completed_atstringrequired
        • contract_sha256stringrequired
        • engine_revisionstring
        • evaluated_version_idstring
        • execution_idstringrequired
        • harness_revisionstring
        • judge_modelstring
        • judge_providerstring
        • median_cost_usdnumber· double
        • median_duration_secondsnumber· double
        • median_function_call_errorsnumber· double
        • median_function_callsnumber· double
        • median_scorenumber· double
        • median_tokensnumber· double
        • median_turnsnumber· double
        • run_countinteger· uintrequiredmin 0
        • scenario_versioninteger· uint32requiredmin 0
        • scored_runsinteger· uintrequiredmin 0
        • seedinteger· uint64min 0
        • stack_modestringrequired
        • statusstringrequired
        • subject_modelstringrequired
        • subject_providerstringrequired
        • system_labelstringrequired
        • system_revisionstring
        • system_version_idstring
      variant 2
      valuenull
    • selected_versioninteger· uint32min 0
    • specany of
      any of (2)
      variant 1
      • criteriaobject[]required
        … expand 6 nested
        • descriptionstringrequired
        • dimensionstringrequiredenum: deliverable, structural_integrity, efficiency, robustness, e2e_infrastructure
        • idstringrequired
        • kindstringrequiredenum: required_check, signal, asset_validation
        • policystringrequiredenum: hard_gate, advisory
        • weightinteger· uint8requiredmin 0
      • denied_functionsstring[]required
      • executionobjectrequired
        … expand 5 nested
        • max_output_tokensinteger· uint64min 0
        • max_total_tokensinteger· uint64min 0

          Shared Harness token budget. `None` leaves the Harness budget unbounded for this scenario.

        • max_turnsinteger· uint32requiredmin 0
        • max_validation_retriesinteger· uint32min 0

          Optional per-session cap for post-turn validation denials. `None` preserves the Harness-configured default.

        • stuck_timeout_secondsinteger· uint64requiredmin 0

          Stop only after this many seconds without observable useful progress. Large scenarios have no fixed wall-clock deadline.

      • promptstringrequired

        The prompt as materialized for a representative run: run-scoped paths resolve against a catalog namespace, never a real execution.

      • summarystring

        Editorial description; absent until the scenario defines a `SUMMARY`.

      variant 2
      valuenull
    • test_idstringrequired
  • totalinteger· uintrequiredmin 0

e2e::fault-evaluate

function

Classify a protected supervisor's fault journal against canonical execution evidence.

request
  • execution_idstringrequired
  • journalobjectrequired
    • actionsobject[]required
      • action_idstringrequired
      • applied_atstring
      • detailstring
      • kindstringrequiredenum: delay_call, fail_first_attempt, malformed_result, throttle_burst, duplicate_event, child_timeout,
      • recovered_atstring
      • statusstringrequiredenum: recovered, unrecovered, not_triggered, injector_failed
    • cancellation_observedbooleanrequired
    • cleanup_completedbooleanrequired
    • cleanup_evidenceobject
    • completed_atstringrequired
    • execution_idstringrequired
    • infrastructure_failuresstring[]
    • lanestringrequired
    • observed_work_amplificationnumber· double
    • profile_sha256stringrequired
    • results_sha256string
    • started_atstringrequired
  • planobjectrequired
    • actionsobject[]required
      • action_idstringrequired
      • duration_msinteger· uint64min 0
      • kindstringrequiredenum: delay_call, fail_first_attempt, malformed_result, throttle_burst, duplicate_event, child_timeout,
      • sequenceinteger· uint32requiredmin 0
      • targetstringrequired
      • trigger_attemptinteger· uint32min 0
    • expected_outcomeone ofrequired
      one of (2)
      variant 1
      valuestringenum: recovered, cancelled
      variant 2
      valuestringenum: degraded
    • profile_idstringrequired
    • profile_sha256stringrequired
    • seedinteger· uint64requiredmin 0
  • profileobjectrequired
    • cancellationany of
      any of (2)
      variant 1
      • after_actionstringrequired
      • grace_period_msinteger· uint64min 0
      variant 2
      valuenull
    • child_timeout_msinteger· uint64min 0
    • delayed_callsobject[]
      • delay_msinteger· uint64requiredmin 0
      • occurrencesinteger· uint8min 0
      • targetstringrequired
    • duplicate_eventsboolean
    • expected_outcomeall of
      all of (1)
      variant 1
      one of (2)
      variant 1
      valuestringenum: recovered, cancelled
      variant 2
      valuestringenum: degraded
    • fail_first_attemptstring[]
    • malformed_resultsstring[]

      The supervisor corrupts the result payload of the first call to each named target: the subject receives undecodable, contract-breaking bytes exactly once per target.

    • max_work_amplificationnumber· doublerequired
    • out_of_order_resultsboolean
    • profile_idstringrequired
    • seedinteger· uint64requiredmin 0
    • throttle_burstany of
      any of (2)
      variant 1
      • responsesinteger· uint8requiredmin 0
      • spacing_msinteger· uint64requiredmin 0
      • targetstringrequired
      variant 2
      valuenull
    • transient_disconnectany of
      any of (2)
      variant 1
      • after_actionstringrequired
      • duration_msinteger· uint64requiredmin 0
      • targetstringrequired
      variant 2
      valuenull
response
  • cancellation_observedbooleanrequired
  • classificationstringrequiredenum: correct_recovery, excessive_recovery, incorrect_result, structural_failure, infrastructure_failure
  • cleanup_completedbooleanrequired
  • deliverable_correctboolean
  • execution_idstringrequired
  • max_work_amplificationnumber· doublerequired
  • observed_work_amplificationnumber· double
  • planned_actionsinteger· uint32requiredmin 0
  • profile_idstringrequired
  • profile_sha256stringrequired
  • reasonsstring[]required
  • recovered_actionsinteger· uint32requiredmin 0
  • results_sha256string
  • structural_integrityboolean

e2e::fault-plan

function

Materialize a deterministic, versioned fault plan for a protected supervisor.

request
  • profileobjectrequired
    • cancellationany of
      any of (2)
      variant 1
      • after_actionstringrequired
      • grace_period_msinteger· uint64min 0
      variant 2
      valuenull
    • child_timeout_msinteger· uint64min 0
    • delayed_callsobject[]
      • delay_msinteger· uint64requiredmin 0
      • occurrencesinteger· uint8min 0
      • targetstringrequired
    • duplicate_eventsboolean
    • expected_outcomeall of
      all of (1)
      variant 1
      one of (2)
      variant 1
      valuestringenum: recovered, cancelled
      variant 2
      valuestringenum: degraded
    • fail_first_attemptstring[]
    • malformed_resultsstring[]

      The supervisor corrupts the result payload of the first call to each named target: the subject receives undecodable, contract-breaking bytes exactly once per target.

    • max_work_amplificationnumber· doublerequired
    • out_of_order_resultsboolean
    • profile_idstringrequired
    • seedinteger· uint64requiredmin 0
    • throttle_burstany of
      any of (2)
      variant 1
      • responsesinteger· uint8requiredmin 0
      • spacing_msinteger· uint64requiredmin 0
      • targetstringrequired
      variant 2
      valuenull
    • transient_disconnectany of
      any of (2)
      variant 1
      • after_actionstringrequired
      • duration_msinteger· uint64requiredmin 0
      • targetstringrequired
      variant 2
      valuenull
response
  • actionsobject[]required
    • action_idstringrequired
    • duration_msinteger· uint64min 0
    • kindstringrequiredenum: delay_call, fail_first_attempt, malformed_result, throttle_burst, duplicate_event, child_timeout,
    • sequenceinteger· uint32requiredmin 0
    • targetstringrequired
    • trigger_attemptinteger· uint32min 0
  • expected_outcomeone ofrequired
    one of (2)
    variant 1
    valuestringenum: recovered, cancelled
    variant 2
    valuestringenum: degraded
  • profile_idstringrequired
  • profile_sha256stringrequired
  • seedinteger· uint64requiredmin 0

e2e::history-list

function

List hash-validated E2E history records from the iii database worker.

request
  • lanestring
  • limitinteger· uint16min 0
response
  • recordsobject[]required
    • archiveobjectrequired
      • archive_idstringrequired
      • created_atstringrequired
      • execution_idstringrequired
      • expires_atstring
      • identity_sha256stringrequired
      • manifestobjectrequired
        … expand 6 nested
        • bucketstringrequired
        • keystringrequired
        • media_typestringrequired
        • sha256stringrequired
        • size_bytesinteger· uint64requiredmin 0
        • uristringrequired
      • manifest_backupobjectrequired
        … expand 6 nested
        • bucketstringrequired
        • keystringrequired
        • media_typestringrequired
        • sha256stringrequired
        • size_bytesinteger· uint64requiredmin 0
        • uristringrequired
      • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
    • baseline_comparablebooleanrequired
    • case_countinteger· uint32requiredmin 0
    • e2e_repositorystringrequired
    • e2e_revisionstringrequired
    • execution_idstringrequired
    • identity_sha256stringrequired
    • ingestion_idstringrequired
    • lanestringrequired
    • occurred_atstringrequired
    • passedbooleanrequired
    • result_contract_sha256stringrequired
    • scoring_profile_sha256stringrequired
    • stack_modestringrequired
    • subject_modelstringrequired
    • subject_providerstringrequired
    • subject_revisionstringrequired

e2e::results-get

function

Get the immutable result and manifest of an E2E execution.

request
  • execution_idstringrequired
response
  • archiveany of
    any of (2)
    variant 1
    • archive_idstringrequired
    • created_atstringrequired
    • execution_idstringrequired
    • expires_atstring
    • identity_sha256stringrequired
    • manifestobjectrequired
      … expand 6 nested
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • manifest_backupobjectrequired
      … expand 6 nested
      • bucketstringrequired
      • keystringrequired
      • media_typestringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      • uristringrequired
    • retention_classstringrequiredenum: temporary, pull_request, longitudinal, canonical
    variant 2
    valuenull
  • execution_idstringrequired
  • manifestany of
    any of (2)
    variant 1
    • control_planeobjectrequired
      … expand 1 nested
      • functionsobject[]required
        … expand 4 nested
        • function_idstringrequired
        • request_schemaunknownrequired
        • response_schemaunknownrequired
        • sha256stringrequired
    • executionobjectrequired
      … expand 4 nested
      • completed_atstringrequired
      • execution_idstringrequired
      • lanestringrequired
      • started_atstringrequired
    • judgeany of
      … expand 2 nested
      any of (2)
      variant 1
      • context_windowinteger· uint64requiredmin 0
      • max_output_tokensinteger· uint64requiredmin 0
      • modelstringrequired
      • providerstringrequired
      • supports_toolsboolean
      • supports_visionboolean
      variant 2
      valuenull
    • observation_contractany of
      … expand 2 nested
      any of (2)
      variant 1
      • attemptinteger· uint32requiredmin 0
      • correlationobjectrequired
        … expand 3 nested
        • deployment_idstringrequired
        • operation_idstringrequired
        • systemstringrequired
      • modeobjectrequired
        … expand 2 nested
        • decisionstringrequiredenum: observe_only
        • environmentstringrequiredenum: demonstration
      • planobjectrequired
        … expand 4 nested
        • catalog_sha256stringrequired
        • idstringrequired
        • revisionstringrequired
        • sha256stringrequired
      • runnerobjectrequired
        … expand 3 nested
        • namestringrequired
        • revisionstringrequired
        • versionstringrequired
      • selected_casesobject[]required
        … expand 6 nested
        • case_idstringrequired
        • contract_sha256stringrequired
        • inputs_sha256stringrequired
        • scenario_idstringrequired
        • scenario_versioninteger· uint32requiredmin 0
        • seedinteger· uint64requiredmin 0
      • targetobjectrequired
        … expand 3 nested
        • applicationstringrequired
        • stackone ofrequired
          … expand 2 nested
          one of (2)
          variant 1
          • modestringrequiredenum: source
          • workers_repositorystringrequired
          • workers_revisionstringrequired
          variant 2
          • modestringrequiredenum: registry
          • stack_lock_digeststringrequired
          • stack_versionsobjectrequired
        • versionstringrequired
      variant 2
      valuenull
    • subjectobjectrequired
      … expand 6 nested
      • context_windowinteger· uint64requiredmin 0
      • max_output_tokensinteger· uint64requiredmin 0
      • modelstringrequired
      • providerstringrequired
      • supports_toolsboolean
      • supports_visionboolean
    • system_under_testobjectrequired
      … expand 7 nested
      • contract_hashesobjectrequired
      • e2e_repositorystringrequired
      • e2e_revisionstringrequired
      • engine_revisionstring
      • engine_versionstringrequired
      • harness_versionstringrequired
      • stackone ofrequired
        … expand 2 nested
        one of (2)
        variant 1
        • modestringrequiredenum: source
        • workers_repositorystringrequired
        • workers_revisionstringrequired
        variant 2
        • modestringrequiredenum: registry
        • stack_lock_digeststringrequired
        • stack_versionsobjectrequired
    • worker_contractsobject[]
      … expand 3 nested
      • function_idstringrequired
      • request_schema_sha256stringrequired
      • response_schema_sha256stringrequired
    variant 2
    valuenull
  • observationany of
    any of (2)
    variant 1
    • evidenceobjectrequired
      … expand 3 nested
      • artifactsobject[]
        … expand 6 nested
        • idstringrequired
        • kindstringrequired
        • media_typestringrequired
        • pathstringrequired
        • sha256stringrequired
        • size_bytesinteger· uint64requiredmin 0
      • manifest_sha256string
      • results_sha256string
    • identityobjectrequired
      … expand 4 nested
      • executionobjectrequired
        … expand 6 nested
        • attemptinteger· uint32requiredmin 0
        • completed_atstringrequired
        • idstringrequired
        • request_sha256stringrequired
        • run_contract_sha256stringrequired
        • started_atstringrequired
      • planobjectrequired
        … expand 4 nested
        • catalog_sha256stringrequired
        • idstringrequired
        • revisionstringrequired
        • sha256stringrequired
      • runnerobjectrequired
        … expand 3 nested
        • namestringrequired
        • revisionstringrequired
        • versionstringrequired
      • targetobjectrequired
        … expand 3 nested
        • applicationstringrequired
        • stackone ofrequired
          … expand 2 nested
          one of (2)
          variant 1
          • modestringrequiredenum: source
          • workers_repositorystringrequired
          • workers_revisionstringrequired
          variant 2
          • modestringrequiredenum: registry
          • stack_lock_digeststringrequired
          • stack_versionsobjectrequired
        • versionstringrequired
    • modeobjectrequired
      … expand 2 nested
      • decisionstringrequiredenum: observe_only
      • environmentstringrequiredenum: demonstration
    • outcomeobjectrequired
      … expand 5 nested
      • control_phasestringrequired
      • data_availabilitystringrequiredenum: complete, partial, unavailable
      • errorstring
      • objectivestringrequiredenum: passed, hard_gate_failed, technical_failed, infrastructure_failed, cancelled, unsupported_plan
      • passedboolean
    • provenanceobjectrequired
      … expand 3 nested
      • subject_modelstringrequired
      • subject_providerstringrequired
      • system_under_testany of
        … expand 2 nested
        any of (2)
        variant 1
        • contract_hashesobjectrequired
        • e2e_repositorystringrequired
        • e2e_revisionstringrequired
        • engine_revisionstring
        • engine_versionstringrequired
        • harness_versionstringrequired
        • stackone ofrequired
          … expand 2 nested
          one of (2)
          variant 1
          • modestringrequiredenum: source
          • workers_repositorystringrequired
          • workers_revisionstringrequired
          variant 2
          • modestringrequiredenum: registry
          • stack_lock_digeststringrequired
          • stack_versionsobjectrequired
        variant 2
        valuenull
    • samplesobject[]required
      … expand 12 nested
      • attempt_idstringrequired
      • case_idstringrequired
      • data_availabilitystringrequiredenum: complete, partial, unavailable
      • derivationsobject[]
        … expand 4 nested
        • formulastringrequired
        • formula_versionstringrequired
        • metricstringrequired
        • originstringrequiredenum: observed, derived_from_observed
      • metric_valuesobject
      • metricsany of
        … expand 2 nested
        any of (2)
        variant 1
        • child_sessionsinteger· uint64min 0
        • child_turnsinteger· uint64min 0
        • cost_usdnumber· double
        • critical_path_msinteger· uint64min 0
        • effective_fan_outinteger· uint64min 0
        • function_call_errorsinteger· uint64min 0
        • function_callsinteger· uint64min 0
        • input_tokensinteger· uint64min 0
        • minimum_expected_workinteger· uint64requiredmin 0
        • observed_complexityobjectrequired
          … expand 11 nested
          • ambiguity_levelinteger· uint64min 0
          • artifact_countinteger· uint64min 0
          • coordination_edgesinteger· uint64min 0
          • dependency_depthinteger· uint64min 0
          • external_systemsinteger· uint64min 0
          • parallel_branchesinteger· uint64min 0
          • planning_depthinteger· uint64min 0
          • state_transitionsinteger· uint64min 0
          • unavailableobject
          • validation_loopsinteger· uint64min 0
          • wake_cyclesinteger· uint64min 0
        • observed_workinteger· uint64min 0
        • output_tokensinteger· uint64min 0
        • root_turnsinteger· uint64min 0
        • technical_attemptsinteger· uint32requiredmin 0
        • total_tokensinteger· uint64min 0
        • transient_resumesinteger· uint64min 0
        • unavailableobject
        • validation_retriesinteger· uint64min 0
        • wake_resumesinteger· uint64min 0
        • wall_time_msinteger· uint64requiredmin 0
        • work_amplificationnumber· double
        variant 2
        valuenull
      • originstringrequiredenum: observed, derived_from_observed
      • run_idstringrequired
      • scenario_idstringrequired
      • scenario_versioninteger· uint32requiredmin 0
      • seedinteger· uint64requiredmin 0
      • statusstringrequiredenum: passed, hard_gate_failed, subject_error, judge_error, resource_limit, infrastructure_error
    • schemastringrequired
    variant 2
    valuenull
  • observation_artifactany of
    any of (2)
    variant 1
    • idstringrequired
    • kindstringrequired
    • media_typestringrequired
    • pathstringrequired
    • sha256stringrequired
    • size_bytesinteger· uint64requiredmin 0
    variant 2
    valuenull
  • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
  • reportany of
    any of (2)
    variant 1
    • assessment_contractobjectrequired
      … expand 1 nested
      • runsobject[]required
        … expand 5 nested
        • assessmentsobject[]
          … expand 9 nested
          • criterion_idstringrequired
          • dimensionstringrequiredenum: deliverable, structural_integrity, efficiency, robustness, e2e_infrastructure
          • evidenceobject[]
            … expand 3 nested
            • artifact_idstringrequired
            • artifact_sha256stringrequired
            • locatorstring
          • kindstringrequiredenum: required_check, signal, asset_validation
          • outcomestringrequiredenum: passed, failed, partial, not_evaluated, unavailable, error
          • policystringrequiredenum: hard_gate, advisory
          • scoreany of
            … expand 2 nested
            any of (2)
            variant 1
            • awardedinteger· uint8requiredmin 0
            • possibleinteger· uint8requiredmin 0
            variant 2
            valuenull
          • summarystringrequired
          • targetobjectrequired
            … expand 2 nested
            • idstringrequired
            • kindstringrequiredenum: criterion
        • assetsobject[]
          … expand 4 nested
          • asset_idstringrequired
          • evidenceobject[]
            … expand 3 nested
            • artifact_idstringrequired
            • artifact_sha256stringrequired
            • locatorstring
          • outcomestringrequiredenum: valid, invalid, malformed, oversized, not_produced, unreadable,
          • summarystringrequired
        • attempt_idstringrequired
        • run_idstringrequired
        • system_statusstringrequiredenum: unavailable, passed, hard_gate_failed, subject_error, judge_error, resource_limit,
    • engine_revisionstring
    • executionobjectrequired
      … expand 4 nested
      • completed_atstringrequired
      • execution_idstringrequired
      • lanestringrequired
      • started_atstringrequired
    • judgeany of
      … expand 2 nested
      any of (2)
      variant 1
      • context_windowinteger· uint64requiredmin 0
      • max_output_tokensinteger· uint64requiredmin 0
      • modelstringrequired
      • providerstringrequired
      • supports_toolsboolean
      • supports_visionboolean
      variant 2
      valuenull
    • manifestany of
      … expand 2 nested
      any of (2)
      variant 1
      • idstringrequired
      • kindstringrequired
      • media_typestringrequired
      • pathstringrequired
      • sha256stringrequired
      • size_bytesinteger· uint64requiredmin 0
      variant 2
      valuenull
    • objective_outcomestringrequiredenum: passed, failed, inconclusive
    • observation_contractany of
      … expand 2 nested
      any of (2)
      variant 1
      • attemptinteger· uint32requiredmin 0
      • correlationobjectrequired
        … expand 3 nested
        • deployment_idstringrequired
        • operation_idstringrequired
        • systemstringrequired
      • modeobjectrequired
        … expand 2 nested
        • decisionstringrequiredenum: observe_only
        • environmentstringrequiredenum: demonstration
      • planobjectrequired
        … expand 4 nested
        • catalog_sha256stringrequired
        • idstringrequired
        • revisionstringrequired
        • sha256stringrequired
      • runnerobjectrequired
        … expand 3 nested
        • namestringrequired
        • revisionstringrequired
        • versionstringrequired
      • selected_casesobject[]required
        … expand 6 nested
        • case_idstringrequired
        • contract_sha256stringrequired
        • inputs_sha256stringrequired
        • scenario_idstringrequired
        • scenario_versioninteger· uint32requiredmin 0
        • seedinteger· uint64requiredmin 0
      • targetobjectrequired
        … expand 3 nested
        • applicationstringrequired
        • stackone ofrequired
          … expand 2 nested
          one of (2)
          variant 1
          • modestringrequiredenum: source
          • workers_repositorystringrequired
          • workers_revisionstringrequired
          variant 2
          • modestringrequiredenum: registry
          • stack_lock_digeststringrequired
          • stack_versionsobjectrequired
        • versionstringrequired
      variant 2
      valuenull
    • passedbooleanrequired
    • persistence_errorsstring[]
    • redactionall of
      … expand 1 nested
      all of (1)
      variant 1
      • redacted_fieldsinteger· uint32requiredmin 0
      • redacted_valuesinteger· uint32requiredmin 0
      • rulesstring[]required
    • report_statestringrequiredenum: complete, partial
    • result_contract_sha256stringrequired
    • scenariosobject[]required
      … expand 9 nested
      • aggregateobjectrequired
        … expand 30 nested
        • completed_runsinteger· uint32requiredmin 0
        • completion_evidence_coveragenumber· double
        • completion_ratenumber· double
        • costobjectrequired
          … expand 2 nested
          • subject_usdnumber· double
          • total_usdnumber· double
        • deferred_runsinteger· uint32requiredmin 0
        • execution_reliabilitynumber· double
        • failed_attempt_tokensinteger· uint64min 0
        • median_scorenumber· double

          Compatibility alias for `objective_median_score`.

        • objective_median_scorenumber· double
        • objective_score_coveragenumber· double
        • objective_scored_runsinteger· uint32requiredmin 0
        • observed_runsinteger· uint32requiredmin 0
        • pass_ratenumber· doublerequired
        • passed_runsinteger· uint32requiredmin 0
        • planned_runsinteger· uint32requiredmin 0
        • quality_coveragenumber· double
        • quality_score_completednumber· double
        • quality_scored_completed_runsinteger· uint32requiredmin 0
        • required_passesinteger· uint32requiredmin 0
        • robustnessobjectrequired
          … expand 13 nested
          • cost_per_successful_deliverablenumber· double
          • deliverable_success_ratenumber· double
          • eligiblebooleanrequired
          • flaky_ratenumber· double
          • median_wall_time_msnumber· double
          • minimum_sample_sizeinteger· uint32requiredmin 0
          • p95_wall_time_msinteger· uint64min 0
          • sample_sizeinteger· uint32requiredmin 0
          • structural_integrity_ratenumber· double
          • tail_minimum_sample_sizeinteger· uint32requiredmin 0
          • technical_failure_ratenumber· double
          • unavailableobject
          • wall_time_variancenumber· double
        • runsinteger· uint32requiredmin 0

          Compatibility alias for `observed_runs`.

        • scored_runsinteger· uint32requiredmin 0

          Compatibility alias for `objective_scored_runs`.

        • task_incomplete_runsinteger· uint32requiredmin 0
        • technical_failuresinteger· uint32requiredmin 0
        • technical_invalid_runsinteger· uint32requiredmin 0
        • technical_valid_runsinteger· uint32requiredmin 0
        • tokens_completed_p50number· double
        • tokens_per_completionnumber· double
        • total_tokens_consumedinteger· uint64min 0
        • undetermined_runsinteger· uint32requiredmin 0
      • caseany of
        … expand 2 nested
        any of (2)
        variant 1
        • case_idstringrequired
        • characterizationall of
          … expand 1 nested
          all of (1)
          variant 1
          • human_horizonall of
            … expand 1 nested
            all of (1)
            variant 1
            • basisall of
              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: unknown, author_estimate, measured
            • max_minutesinteger· uint32min 0
            • min_minutesinteger· uint32min 0
          • realismall of
            … expand 1 nested
            all of (1)
            variant 1
            • executionall of
              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: synthetic, realistic_simulator, frozen_real_artifact
            • shadowall of
              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: none, read_only
        • complexityobjectrequired
          … expand 3 nested
          • methodstringrequiredenum: capability_v2
          • profileobjectrequired
            … expand 16 nested
            • agent_owned_decompositionboolean
            • ambiguity_levelinteger· uint8requiredmin 0
            • artifact_countinteger· uint8requiredmin 0
            • coherent_long_horizonboolean
            • compensable_mutationsinteger· uint8min 0
            • coordination_edgesinteger· uint16requiredmin 0
            • dependency_depthinteger· uint8requiredmin 0
            • durable_resume_cyclesinteger· uint8min 0
            • external_systemsinteger· uint8requiredmin 0
            • material_invalidation_eventsinteger· uint8min 0
            • parallel_branchesinteger· uint8requiredmin 0
            • planning_depthinteger· uint8requiredmin 0
            • replan_loopsinteger· uint8min 0
            • state_transitionsinteger· uint16requiredmin 0
            • validation_loopsinteger· uint8requiredmin 0
            • wake_cyclesinteger· uint8requiredmin 0
          • tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
        • deliverable_contractobjectrequired
          … expand 4 nested
          • artifactsobject[]required
            … expand 5 nested
            • idstringrequired
            • kindstringrequired
            • max_size_bytesinteger· uint64requiredmin 0
            • media_typestringrequired
            • schemaunknownrequired
          • capture_before_cleanupbooleanrequired
          • invariantsobject[]required
            … expand 2 nested
            • descriptionstringrequired
            • idstringrequired
          • provenance_requiredbooleanrequired
        • inputsunknownrequired
        • inputs_sha256stringrequired
        • required_capabilitiesstring[]required
        • scenario_idstringrequired
        • scenario_versioninteger· uint32requiredmin 0
        • seedinteger· uint64requiredmin 0
        • workobjectrequired
          … expand 1 nested
          • minimum_expected_workinteger· uint64requiredmin 0
        variant 2
        valuenull
      • case_idstring
      • deferral_reasonstring
      • execution_policyobjectrequired
        … expand 5 nested
        • max_output_tokensinteger· uint64min 0
        • max_total_tokensinteger· uint64min 0

          Shared Harness token budget. `None` leaves the Harness budget unbounded for this scenario.

        • max_turnsinteger· uint32requiredmin 0
        • max_validation_retriesinteger· uint32min 0

          Optional per-session cap for post-turn validation denials. `None` preserves the Harness-configured default.

        • stuck_timeout_secondsinteger· uint64requiredmin 0

          Stop only after this many seconds without observable useful progress. Large scenarios have no fixed wall-clock deadline.

      • passedbooleanrequired
      • runsobject[]required
        … expand 31 nested
        • attempt_idstringrequired
        • attempt_numberinteger· uint32requiredmin 0
        • auditany of

          Advisory behavioral audit over the captured transcript and metrics. Never contributes to score, status, gates, or longitudinal inputs.

          … expand 2 nested
          any of (2)
          variant 1
          • analyzerany of
            … expand 2 nested
            any of (2)
            variant 1
            • analyzerstringrequired
            • input_sha256stringrequired
            • modelstring
            • providerstring
            variant 2
            valuenull
          • analyzer_errorstring
          • analyzer_statusone ofrequired
            … expand 3 nested
            one of (3)
            variant 1
            valuestringenum: completed, failed
            variant 2
            valuestringenum: not_configured
            variant 3
            valuestringenum: no_transcript
          • analyzer_usageany of
            … expand 2 nested
            any of (2)
            variant 1
            • cost_usdnumber· double
            • input_tokensinteger· uint64min 0
            • latency_msinteger· uint64min 0
            • output_tokensinteger· uint64min 0
            variant 2
            valuenull
          • flagsobject[]required
            … expand 6 nested
            • confidencenumber· double
            • evidenceobject[]
              … expand 3 nested
              • detailstringrequired

                Sanitized, bounded description. Never contains secret material.

              • function_idstring
              • message_indexinteger· uintmin 0

                Index of the transcript message the observation anchors to.

            • kindone ofrequired
              … expand 5 nested
              one of (5)
              variant 1
              valuestringenum: verifier_tampering
              variant 2
              valuestringenum: out_of_scope_session_access
              variant 3
              valuestringenum: secret_exposure
              variant 4
              valuestringenum: destructive_action
              variant 5
              valuestringenum: anomalous_work
            • severitystringrequiredenum: info, warning, critical
            • sourcestringrequiredenum: deterministic, analyzer
            • summarystringrequired
          variant 2
          valuenull
        • completionstringrequiredenum: completed, task_incomplete, undetermined
        • costobjectrequired
          … expand 2 nested
          • subject_usdnumber· double
          • total_usdnumber· double
        • criteriaobject[]required
          … expand 5 nested
          • awardedinteger· uint8min 0
          • descriptionstring
          • idstringrequired
          • possibleinteger· uint8requiredmin 0
          • reasonstringrequired
        • deliverablesobject[]
          … expand 12 nested
          • artifactany of
            … expand 2 nested
            any of (2)
            variant 1
            • idstringrequired
            • kindstringrequired
            • media_typestringrequired
            • pathstringrequired
            • sha256stringrequired
            • size_bytesinteger· uint64requiredmin 0
            variant 2
            valuenull
          • content_formatstringrequiredenum: json, text_utf8
          • content_sha256stringrequired
          • content_size_bytesinteger· uint64requiredmin 0
          • idstringrequired
          • invariantsobject[]required
            … expand 3 nested
            • idstringrequired
            • passedbooleanrequired
            • reasonstringrequired
          • kindstringrequired
          • media_typestringrequired
          • previewunknownrequired
          • provenanceobject[]required
            … expand 3 nested
            • kindstringrequired
            • relationstringrequired
            • source_idstringrequired
          • provenance_validbooleanrequired
          • schema_validbooleanrequired
        • dimensionsobject[]
          … expand 3 nested
          • dimensionstringrequiredenum: deliverable, structural_integrity, efficiency, robustness, e2e_infrastructure
          • passedboolean
          • signalsunknownrequired
        • efficiencyany of
          … expand 2 nested
          any of (2)
          variant 1
          • child_sessionsinteger· uint64min 0
          • child_turnsinteger· uint64min 0
          • cost_usdnumber· double
          • critical_path_msinteger· uint64min 0
          • effective_fan_outinteger· uint64min 0
          • function_call_errorsinteger· uint64min 0
          • function_callsinteger· uint64min 0
          • input_tokensinteger· uint64min 0
          • minimum_expected_workinteger· uint64requiredmin 0
          • observed_complexityobjectrequired
            … expand 11 nested
            • ambiguity_levelinteger· uint64min 0
            • artifact_countinteger· uint64min 0
            • coordination_edgesinteger· uint64min 0
            • dependency_depthinteger· uint64min 0
            • external_systemsinteger· uint64min 0
            • parallel_branchesinteger· uint64min 0
            • planning_depthinteger· uint64min 0
            • state_transitionsinteger· uint64min 0
            • unavailableobject
            • validation_loopsinteger· uint64min 0
            • wake_cyclesinteger· uint64min 0
          • observed_workinteger· uint64min 0
          • output_tokensinteger· uint64min 0
          • root_turnsinteger· uint64min 0
          • technical_attemptsinteger· uint32requiredmin 0
          • total_tokensinteger· uint64min 0
          • transient_resumesinteger· uint64min 0
          • unavailableobject
          • validation_retriesinteger· uint64min 0
          • wake_resumesinteger· uint64min 0
          • wall_time_msinteger· uint64requiredmin 0
          • work_amplificationnumber· double
          variant 2
          valuenull
        • evaluatorsobjectrequired
          … expand 2 nested
          • completionstringrequiredenum: not_required, pending, available, unavailable
          • qualitystringrequiredenum: not_required, pending, available, unavailable
        • evidenceobject[]
          … expand 6 nested
          • idstringrequired
          • kindstringrequired
          • media_typestringrequired
          • pathstringrequired
          • sha256stringrequired
          • size_bytesinteger· uint64requiredmin 0
        • failuresobject[]
          … expand 7 nested
          • codestring
          • contaminationall of
            … expand 1 nested
            all of (1)
            variant 1
            valuestringenum: none, case, execution
          • domainstringrequiredenum: subject, judge, resource, e2e_infrastructure
          • messagestringrequired
          • phasestringrequiredenum: setup, execute, collect, evaluate, cleanup
          • retry_scopeall of
            … expand 1 nested
            all of (1)
            variant 1
            valuestringenum: none, same_slot
          • statusall ofrequired

            The failure's original classification, independent of the primary run status.

            … expand 1 nested
            all of (1)
            variant 1
            valuestringenum: passed, hard_gate_failed, subject_error, judge_error, resource_limit, infrastructure_error
        • instruction_adherenceany of
          … expand 2 nested
          any of (2)
          variant 1
          • analyzerany of
            … expand 2 nested
            any of (2)
            variant 1
            • analyzerstringrequired
            • input_sha256stringrequired
            • modelstring
            • providerstring
            variant 2
            valuenull
          • analyzer_usageany of
            … expand 2 nested
            any of (2)
            variant 1
            • cost_usdnumber· double
            • input_tokensinteger· uint64min 0
            • latency_msinteger· uint64min 0
            • output_tokensinteger· uint64min 0
            variant 2
            valuenull
          • availabilitystringrequiredenum: available, unavailable, failed
          • requirementsobject[]
            … expand 6 nested
            • confidencenumber· doublerequired
            • evidencestring[]
            • followedbooleanrequired
            • idstringrequired
            • instructionstringrequired
            • reasonstringrequired
          • scoreinteger· uint8min 0
          • summarystringrequired
          variant 2
          valuenull
        • markdown_executionany of
          … expand 2 nested
          any of (2)
          variant 1
          • behavior_sha256stringrequired
          • compiled_sha256stringrequired
          • materialized_plan_sha256string
          • phasesobject[]required
            … expand 6 nested
            • input_sha256stringrequired
            • phasestringrequired
            • reasonstring
            • session_idstring
            • statusstringrequiredenum: pending, completed, failed, skipped
            • transcript_sha256string
          • pipeline_completebooleanrequired
          • prompt_sha256stringrequired
          • source_pathstringrequired
          • source_sha256stringrequired
          variant 2
          valuenull
        • metricsany of
          … expand 2 nested
          any of (2)
          variant 1
          • by_sessionobject[]required
            … expand 16 nested
            • cache_read_tokensinteger· uint64min 0
            • cache_write_tokensinteger· uint64min 0
            • contextunknown
            • cost_usdnumber· double
            • depthinteger· uint32requiredmin 0
            • function_call_errorsinteger· uint64requiredmin 0
            • function_callsinteger· uint64requiredmin 0
            • input_tokensinteger· uint64min 0
            • output_tokensinteger· uint64min 0
            • parent_session_idstring
            • reasoning_tokensinteger· uint64min 0
            • session_idstringrequired
            • transient_resumesinteger· uint64min 0
            • turnsinteger· uint64requiredmin 0
            • validation_retriesinteger· uint64min 0
            • wake_resumesinteger· uint64min 0
          • completebooleanrequired
          • root_session_idstringrequired
          • totalsobjectrequired
            … expand 13 nested
            • cache_read_tokensinteger· uint64min 0
            • cache_write_tokensinteger· uint64min 0
            • cost_usdnumber· double
            • function_call_errorsinteger· uint64requiredmin 0
            • function_callsinteger· uint64requiredmin 0
            • input_tokensinteger· uint64min 0
            • output_tokensinteger· uint64min 0
            • reasoning_tokensinteger· uint64min 0
            • sessionsinteger· uint64requiredmin 0
            • transient_resumesinteger· uint64min 0
            • turnsinteger· uint64requiredmin 0
            • validation_retriesinteger· uint64min 0
            • wake_resumesinteger· uint64min 0
          • tracesunknown
          variant 2
          valuenull
        • objective_scoreinteger· uint8min 0
        • promptstringrequired
        • quality_score_completedinteger· uint8min 0
        • retry_attemptsobject[]
          … expand 24 nested
          • attempt_idstringrequired
          • attempt_numberinteger· uint32requiredmin 0
          • completionstringrequiredenum: completed, task_incomplete, undetermined
          • costobjectrequired
            … expand 2 nested
            • subject_usdnumber· double
            • total_usdnumber· double
          • deliverablesobject[]
            … expand 12 nested
            • artifactany of
              … expand 2 nested
              any of (2)
              variant 1
              • idstringrequired
              • kindstringrequired
              • media_typestringrequired
              • pathstringrequired
              • sha256stringrequired
              • size_bytesinteger· uint64requiredmin 0
              variant 2
              valuenull
            • content_formatstringrequiredenum: json, text_utf8
            • content_sha256stringrequired
            • content_size_bytesinteger· uint64requiredmin 0
            • idstringrequired
            • invariantsobject[]required
              … expand 3 nested
              • idstringrequired
              • passedbooleanrequired
              • reasonstringrequired
            • kindstringrequired
            • media_typestringrequired
            • previewunknownrequired
            • provenanceobject[]required
              … expand 3 nested
              • kindstringrequired
              • relationstringrequired
              • source_idstringrequired
            • provenance_validbooleanrequired
            • schema_validbooleanrequired
          • dimensionsobject[]
            … expand 3 nested
            • dimensionstringrequiredenum: deliverable, structural_integrity, efficiency, robustness, e2e_infrastructure
            • passedboolean
            • signalsunknownrequired
          • efficiencyany of
            … expand 2 nested
            any of (2)
            variant 1
            • child_sessionsinteger· uint64min 0
            • child_turnsinteger· uint64min 0
            • cost_usdnumber· double
            • critical_path_msinteger· uint64min 0
            • effective_fan_outinteger· uint64min 0
            • function_call_errorsinteger· uint64min 0
            • function_callsinteger· uint64min 0
            • input_tokensinteger· uint64min 0
            • minimum_expected_workinteger· uint64requiredmin 0
            • observed_complexityobjectrequired
              … expand 11 nested
              • ambiguity_levelinteger· uint64min 0
              • artifact_countinteger· uint64min 0
              • coordination_edgesinteger· uint64min 0
              • dependency_depthinteger· uint64min 0
              • external_systemsinteger· uint64min 0
              • parallel_branchesinteger· uint64min 0
              • planning_depthinteger· uint64min 0
              • state_transitionsinteger· uint64min 0
              • unavailableobject
              • validation_loopsinteger· uint64min 0
              • wake_cyclesinteger· uint64min 0
            • observed_workinteger· uint64min 0
            • output_tokensinteger· uint64min 0
            • root_turnsinteger· uint64min 0
            • technical_attemptsinteger· uint32requiredmin 0
            • total_tokensinteger· uint64min 0
            • transient_resumesinteger· uint64min 0
            • unavailableobject
            • validation_retriesinteger· uint64min 0
            • wake_resumesinteger· uint64min 0
            • wall_time_msinteger· uint64requiredmin 0
            • work_amplificationnumber· double
            variant 2
            valuenull
          • evaluatorsobjectrequired
            … expand 2 nested
            • completionstringrequiredenum: not_required, pending, available, unavailable
            • qualitystringrequiredenum: not_required, pending, available, unavailable
          • evidenceobject[]
            … expand 6 nested
            • idstringrequired
            • kindstringrequired
            • media_typestringrequired
            • pathstringrequired
            • sha256stringrequired
            • size_bytesinteger· uint64requiredmin 0
          • failuresobject[]required
            … expand 7 nested
            • codestring
            • contaminationall of
              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: none, case, execution
            • domainstringrequiredenum: subject, judge, resource, e2e_infrastructure
            • messagestringrequired
            • phasestringrequiredenum: setup, execute, collect, evaluate, cleanup
            • retry_scopeall of
              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: none, same_slot
            • statusall ofrequired

              The failure's original classification, independent of the primary run status.

              … expand 1 nested
              all of (1)
              variant 1
              valuestringenum: passed, hard_gate_failed, subject_error, judge_error, resource_limit, infrastructure_error
          • instruction_adherenceany of
            … expand 2 nested
            any of (2)
            variant 1
            • analyzerany of
              … expand 2 nested
              any of (2)
              variant 1
              • analyzerstringrequired
              • input_sha256stringrequired
              • modelstring
              • providerstring
              variant 2
              valuenull
            • analyzer_usageany of
              … expand 2 nested
              any of (2)
              variant 1
              • cost_usdnumber· double
              • input_tokensinteger· uint64min 0
              • latency_msinteger· uint64min 0
              • output_tokensinteger· uint64min 0
              variant 2
              valuenull
            • availabilitystringrequiredenum: available, unavailable, failed
            • requirementsobject[]
              … expand 6 nested
              • confidencenumber· doublerequired
              • evidencestring[]
              • followedbooleanrequired
              • idstringrequired
              • instructionstringrequired
              • reasonstringrequired
            • scoreinteger· uint8min 0
            • summarystringrequired
            variant 2
            valuenull
          • markdown_executionany of
            … expand 2 nested
            any of (2)
            variant 1
            • behavior_sha256stringrequired
            • compiled_sha256stringrequired
            • materialized_plan_sha256string
            • phasesobject[]required
              … expand 6 nested
              • input_sha256stringrequired
              • phasestringrequired
              • reasonstring
              • session_idstring
              • statusstringrequiredenum: pending, completed, failed, skipped
              • transcript_sha256string
            • pipeline_completebooleanrequired
            • prompt_sha256stringrequired
            • source_pathstringrequired
            • source_sha256stringrequired
            variant 2
            valuenull
          • metricsany of
            … expand 2 nested
            any of (2)
            variant 1
            • by_sessionobject[]required
              … expand 16 nested
              • cache_read_tokensinteger· uint64min 0
              • cache_write_tokensinteger· uint64min 0
              • contextunknown
              • cost_usdnumber· double
              • depthinteger· uint32requiredmin 0
              • function_call_errorsinteger· uint64requiredmin 0
              • function_callsinteger· uint64requiredmin 0
              • input_tokensinteger· uint64min 0
              • output_tokensinteger· uint64min 0
              • parent_session_idstring
              • reasoning_tokensinteger· uint64min 0
              • session_idstringrequired
              • transient_resumesinteger· uint64min 0
              • turnsinteger· uint64requiredmin 0
              • validation_retriesinteger· uint64min 0
              • wake_resumesinteger· uint64min 0
            • completebooleanrequired
            • root_session_idstringrequired
            • totalsobjectrequired
              … expand 13 nested
              • cache_read_tokensinteger· uint64min 0
              • cache_write_tokensinteger· uint64min 0
              • cost_usdnumber· double
              • function_call_errorsinteger· uint64requiredmin 0
              • function_callsinteger· uint64requiredmin 0
              • input_tokensinteger· uint64min 0
              • output_tokensinteger· uint64min 0
              • reasoning_tokensinteger· uint64min 0
              • sessionsinteger· uint64requiredmin 0
              • transient_resumesinteger· uint64min 0
              • turnsinteger· uint64requiredmin 0
              • validation_retriesinteger· uint64min 0
              • wake_resumesinteger· uint64min 0
            • tracesunknown
            variant 2
            valuenull
          • objective_scoreinteger· uint8min 0
          • quality_score_completedinteger· uint8min 0
          • run_idstringrequired
          • scenario_flowany of
            … expand 2 nested
            any of (2)
            variant 1
            • checkpointobjectrequired
              … expand 6 nested
              • idstringrequired
              • kindstringrequired
              • media_typestringrequired
              • pathstringrequired
              • sha256stringrequired
              • size_bytesinteger· uint64requiredmin 0
            • cleanupobjectrequired
              … expand 3 nested
              • duration_msinteger· uint64requiredmin 0
              • failurestring
              • statusstringrequiredenum: succeeded, failed
            • definition_sha256stringrequired
            • snapshotunknownrequired
            variant 2
            valuenull
          • semantic_testsobject[]
            … expand 22 nested
            • activationone ofrequired
              … expand 3 nested
              one of (3)
              variant 1
              • policystringrequiredenum: always
              variant 2
              • conditionsobject[]required
                … expand 3 nested
                • equalsbooleanrequired
                • node_idstringrequired
                • portstringrequired
              • policystringrequiredenum: all
              variant 3
              • conditionsobject[]required
                … expand 3 nested
                • equalsbooleanrequired
                • node_idstringrequired
                • portstringrequired
              • policystringrequiredenum: any
            • assetsobject[]
              … expand 9 nested
              • artifactobjectrequired
                … expand 6 nested
                • idstringrequired
                • kindstringrequired
                • media_typestringrequired
                • pathstringrequired
                • sha256stringrequired
                • size_bytesinteger· uint64requiredmin 0
              • content_sha256stringrequired
              • idstringrequired
              • kindstringrequired
              • media_typestringrequired
              • namespaced_idstringrequired
              • previewunknownrequired
              • preview_truncatedbooleanrequired
              • size_bytesinteger· uint64requiredmin 0
            • completed_atstring
            • cost_usdnumber· double
            • dependenciesstring[]required
            • dependency_policystringrequiredenum: succeeded, terminal
            • duration_msinteger· uint64requiredmin 0
            • evaluationsobject[]
              … expand 5 nested
              • evidence_idsstring[]
              • idstringrequired
              • outcomestringrequiredenum: passed, failed, advisory, not_evaluated
              • scorenumber· double
              • summarystringrequired
            • failuresobject[]
              … expand 3 nested
              • messagestringrequired
              • phasestringrequiredenum: preflight, execute, capture, persist, evaluate, cleanup,
              • technicalbooleanrequired
            • hard_gatesobject[]
              … expand 4 nested
              • evidence_idsstring[]
              • idstringrequired
              • passedbooleanrequired
              • reasonstringrequired
            • harness_session_idstring
            • metricsunknown
            • node_idstringrequired
            • outputsobject
            • redactionall of
              … expand 1 nested
              all of (1)
              variant 1
              • redacted_fieldsinteger· uint32requiredmin 0
              • redacted_valuesinteger· uint32requiredmin 0
              • rulesstring[]required
            • requiredbooleanrequired
            • skip_reasonstring
            • started_atstring
            • statusstringrequiredenum: pending, running, succeeded, hard_gate_failed, failed, skipped,
            • step_typestringrequired
            • step_versioninteger· uint32requiredmin 0
            • transcriptunknown
          • session_idstringrequired
          • statusstringrequiredenum: passed, hard_gate_failed, subject_error, judge_error, resource_limit, infrastructure_error
          • technicalstringrequiredenum: valid, technical_invalid
          • transcriptunknown
          • validation_scoreinteger· uint8min 0
          • wall_time_msinteger· uint64requiredmin 0
        • run_idstringrequired
        • scenario_flowany of

          Evidence-only flow identity emitted by Rust. This value is never accepted as runner input and cannot reconstruct executable configuration.

          … expand 2 nested
          any of (2)
          variant 1
          • checkpointobjectrequired
            … expand 6 nested
            • idstringrequired
            • kindstringrequired
            • media_typestringrequired
            • pathstringrequired
            • sha256stringrequired
            • size_bytesinteger· uint64requiredmin 0
          • cleanupobjectrequired
            … expand 3 nested
            • duration_msinteger· uint64requiredmin 0
            • failurestring
            • statusstringrequiredenum: succeeded, failed
          • definition_sha256stringrequired
          • snapshotunknownrequired
          variant 2
          valuenull
        • scenario_measurementsobject[]
          … expand 4 nested
          • idstringrequired
          • originstringrequiredenum: observed, derived_from_observed
          • unitstringrequired
          • valuenumber· doublerequired
        • scoreinteger· uint8min 0
        • semantic_testsobject[]

          Semantic tests executed inside a code-defined composite scenario. Product requests, polling and captures stay inside these meaningful test units.

          … expand 22 nested
          • activationone ofrequired
            … expand 3 nested
            one of (3)
            variant 1
            • policystringrequiredenum: always
            variant 2
            • conditionsobject[]required
              … expand 3 nested
              • equalsbooleanrequired
              • node_idstringrequired
              • portstringrequired
            • policystringrequiredenum: all
            variant 3
            • conditionsobject[]required
              … expand 3 nested
              • equalsbooleanrequired
              • node_idstringrequired
              • portstringrequired
            • policystringrequiredenum: any
          • assetsobject[]
            … expand 9 nested
            • artifactobjectrequired
              … expand 6 nested
              • idstringrequired
              • kindstringrequired
              • media_typestringrequired
              • pathstringrequired
              • sha256stringrequired
              • size_bytesinteger· uint64requiredmin 0
            • content_sha256stringrequired
            • idstringrequired
            • kindstringrequired
            • media_typestringrequired
            • namespaced_idstringrequired
            • previewunknownrequired
            • preview_truncatedbooleanrequired
            • size_bytesinteger· uint64requiredmin 0
          • completed_atstring
          • cost_usdnumber· double
          • dependenciesstring[]required
          • dependency_policystringrequiredenum: succeeded, terminal
          • duration_msinteger· uint64requiredmin 0
          • evaluationsobject[]
            … expand 5 nested
            • evidence_idsstring[]
            • idstringrequired
            • outcomestringrequiredenum: passed, failed, advisory, not_evaluated
            • scorenumber· double
            • summarystringrequired
          • failuresobject[]
            … expand 3 nested
            • messagestringrequired
            • phasestringrequiredenum: preflight, execute, capture, persist, evaluate, cleanup,
            • technicalbooleanrequired
          • hard_gatesobject[]
            … expand 4 nested
            • evidence_idsstring[]
            • idstringrequired
            • passedbooleanrequired
            • reasonstringrequired
          • harness_session_idstring
          • metricsunknown
          • node_idstringrequired
          • outputsobject
          • redactionall of
            … expand 1 nested
            all of (1)
            variant 1
            • redacted_fieldsinteger· uint32requiredmin 0
            • redacted_valuesinteger· uint32requiredmin 0
            • rulesstring[]required
          • requiredbooleanrequired
          • skip_reasonstring
          • started_atstring
          • statusstringrequiredenum: pending, running, succeeded, hard_gate_failed, failed, skipped,
          • step_typestringrequired
          • step_versioninteger· uint32requiredmin 0
          • transcriptunknown
        • session_idstringrequired
        • statusstringrequiredenum: passed, hard_gate_failed, subject_error, judge_error, resource_limit, infrastructure_error
        • technicalstringrequiredenum: valid, technical_invalid
        • transcriptunknown
        • validation_scoreinteger· uint8min 0

          Explicit Markdown validation score. Mirrors `score` for Markdown-authored scenarios while keeping the legacy aggregate field compatible.

        • wall_time_msinteger· uint64requiredmin 0
        • worker_contractsobject[]

          Exact request/response schemas observed after this scenario's setup. Run-scoped fixture functions cannot be observed in the suite preflight, so attempts retain them here and the suite folds them into the manifest.

          … expand 3 nested
          • function_idstringrequired
          • request_schema_sha256stringrequired
          • response_schema_sha256stringrequired
      • scenario_idstringrequired
      • scenario_versioninteger· uint32min 0
    • schema_versioninteger· uint32requiredmin 0
    • scoring_profile_sha256stringrequired
    • slot_start_deadline_secondsinteger· uint64min 0

      Soft scheduling deadline: prevents starting slots after this interval.

    • subjectobjectrequired
      … expand 6 nested
      • context_windowinteger· uint64requiredmin 0
      • max_output_tokensinteger· uint64requiredmin 0
      • modelstringrequired
      • providerstringrequired
      • supports_toolsboolean
      • supports_visionboolean
    • system_under_testobjectrequired
      … expand 7 nested
      • contract_hashesobjectrequired
      • e2e_repositorystringrequired
      • e2e_revisionstringrequired
      • engine_revisionstring
      • engine_versionstringrequired
      • harness_versionstringrequired
      • stackone ofrequired
        … expand 2 nested
        one of (2)
        variant 1
        • modestringrequiredenum: source
        • workers_repositorystringrequired
        • workers_revisionstringrequired
        variant 2
        • modestringrequiredenum: registry
        • stack_lock_digeststringrequired
        • stack_versionsobjectrequired
    variant 2
    valuenull
  • request_sha256stringrequired
  • result_pathstring
  • run_contract_sha256string

e2e::results-list

function

List durable E2E executions using comparable identity filters.

request
  • lanestring
  • limitinteger· uint16min 0
  • scenario_idany of
    any of (2)
    variant 1
    valuestring
    variant 2
    valuenull
response
  • executionsobject[]required
    • active_attemptany of
      any of (2)
      variant 1
      • attempt_idstringrequired
      • resume_state_pathstring
      • resume_state_sha256string
      • run_idstring
      • scenario_idstringrequired
      • session_idstringrequired
      variant 2
      valuenull
    • cancel_requestedbooleanrequired
    • errorstring
    • execution_idstringrequired
    • journal_progressobjectrequired
      • active_attempt_idstring
      • attempts_finishedinteger· uint64requiredmin 0
      • attempts_startedinteger· uint64requiredmin 0
      • committed_eventsinteger· uint64requiredmin 0
      • last_event_sha256string
      • phasestring
      • planned_slotsinteger· uint64requiredmin 0
      • runs_committedinteger· uint64requiredmin 0
      • slots_deferredinteger· uint64requiredmin 0
      • subject_observations_committedinteger· uint64requiredmin 0
      • terminalbooleanrequired
      • terminal_reasonstring
      • terminal_stateany of
        … expand 2 nested
        any of (2)
        variant 1
        valuestringenum: completed, failed, cancelled, needs_reconciliation, unsupported
        variant 2
        valuenull
    • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
    • terminalbooleanrequired
    • transitionsobject[]required
      • atstringrequired
      • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
      • reasonstringrequired
    • updated_atstringrequired

e2e::retention-sweep

function

Delete expired E2E objects and tombstone their history records.

request
  • beforestringrequired
  • dry_runboolean
  • limitinteger· uint16min 0
response
  • deleted_archivesstring[]required
  • dry_runbooleanrequired
  • inspectedinteger· uint32requiredmin 0

e2e::run

function

Admit an asynchronous, idempotent E2E execution.

request
  • audit_modelstring

    Opt-in behavioral audit analyzer; supply model and provider together.

  • audit_providerstring
  • idempotency_keystringrequired
  • judge_modelstring

    Auxiliary model for Markdown scenarios only (validators, instruction adherence, setup and cleanup); supply model and provider together.

  • judge_providerstring
  • labelstring
  • lanestring
  • modelstringrequired
  • progress_interval_secondsinteger· uint64min 0
  • providerstringrequired
  • rotating_seedsinteger[]· uint64min 0
  • run_contractany of
    any of (2)
    variant 1
    • attemptinteger· uint32requiredmin 0
    • correlationobjectrequired
      … expand 3 nested
      • deployment_idstringrequired
      • operation_idstringrequired
      • systemstringrequired
    • modeobjectrequired
      … expand 2 nested
      • decisionstringrequiredenum: observe_only
      • environmentstringrequiredenum: demonstration
    • planobjectrequired
      … expand 4 nested
      • catalog_sha256stringrequired
      • idstringrequired
      • revisionstringrequired
      • sha256stringrequired
    • runnerobjectrequired
      … expand 3 nested
      • namestringrequired
      • revisionstringrequired
      • versionstringrequired
    • selected_casesobject[]required
      … expand 6 nested
      • case_idstringrequired
      • contract_sha256stringrequired
      • inputs_sha256stringrequired
      • scenario_idstringrequired
      • scenario_versioninteger· uint32requiredmin 0
      • seedinteger· uint64requiredmin 0
    • targetobjectrequired
      … expand 3 nested
      • applicationstringrequired
      • stackone ofrequired
        … expand 2 nested
        one of (2)
        variant 1
        • modestringrequiredenum: source
        • workers_repositorystringrequired
        • workers_revisionstringrequired
        variant 2
        • modestringrequiredenum: registry
        • stack_lock_digeststringrequired
        • stack_versionsobjectrequired
      • versionstringrequired
    variant 2
    valuenull
  • runsinteger· uint32min 0
  • scenariosstring[]
  • seedinteger· uint64min 0
  • slot_start_deadline_secondsinteger· uint64min 0

    Soft scheduling budget, resolved before request hashing/admission.

  • technical_retriesinteger· uint8min 0
response
  • duplicatebooleanrequired
  • execution_idstringrequired
  • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
  • request_sha256stringrequired
  • run_contract_sha256string

e2e::scenarios-authoring-guide

function

Explain how the Harness can author a local Markdown E2E test, including the exact template, validation rules, persistence behavior, and separate create/list/run workflow. Call this before e2e::scenarios-create.

request
empty object
response
  • create_functionstringrequired

    Function that validates and persists one new local definition.

  • creation_starts_executionbooleanrequired

    Always false: persistence and execution are separate operations.

  • file_name_rulesstring[]required

    File-name requirements enforced by the worker.

  • list_functionstringrequired

    Function that returns the complete built-in and local scenario catalog.

  • max_source_bytesinteger· uintrequiredmin 0

    Maximum accepted UTF-8 Markdown source size.

  • overwrites_existing_filebooleanrequired

    Existing files are never silently replaced.

  • required_h2_sectionsstring[]required

    Required H2 headings, in their exact order.

  • run_functionstringrequired

    Separate function used only when the user explicitly asks to execute.

  • schemastringrequired

    Versioned shape of this guidance response.

  • storage_directorystringrequired

    Worker-data-relative directory where definitions are persisted.

  • summarystringrequired

    Short statement of what local authoring is for.

  • templatestringrequired

    Copy-ready valid Markdown source.

  • validation_rulesstring[]required

    Rules for weighted H3 validation criteria.

  • workflowstring[]required

    Recommended safe sequence for an agent authoring a local test.

e2e::scenarios-create

function

Create one local Markdown E2E test after validating its complete authoring contract. This persists a definition outside Git and never starts an execution; call e2e::run separately only when execution is explicitly requested.

request
  • file_namestringrequired

    One UTF-8 `.md` file name, without a directory. Use letters, numbers, spaces, hyphens, or underscores; its stem becomes `local_<safe_id>`. Existing files are rejected instead of overwritten.

  • sourcestringrequired

    Complete Markdown test definition. It must contain one H1 followed by the required H2 sections in order and contain positive `### Name (N%)` validations totaling exactly 100%.

response
  • scenarioobjectrequired
    • author_versioninteger· uint32min 0
    • behavior_sha256string
    • case_idstringrequired
    • characterizationobjectrequired
      • human_horizonall of
        … expand 1 nested
        all of (1)
        variant 1
        • basisall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: unknown, author_estimate, measured
        • max_minutesinteger· uint32min 0
        • min_minutesinteger· uint32min 0
      • realismall of
        … expand 1 nested
        all of (1)
        variant 1
        • executionall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: synthetic, realistic_simulator, frozen_real_artifact
        • shadowall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: none, read_only
    • classificationobjectrequired
      • methodstringrequiredenum: capability_v2
      • profileobjectrequired
        … expand 16 nested
        • agent_owned_decompositionboolean
        • ambiguity_levelinteger· uint8requiredmin 0
        • artifact_countinteger· uint8requiredmin 0
        • coherent_long_horizonboolean
        • compensable_mutationsinteger· uint8min 0
        • coordination_edgesinteger· uint16requiredmin 0
        • dependency_depthinteger· uint8requiredmin 0
        • durable_resume_cyclesinteger· uint8min 0
        • external_systemsinteger· uint8requiredmin 0
        • material_invalidation_eventsinteger· uint8min 0
        • parallel_branchesinteger· uint8requiredmin 0
        • planning_depthinteger· uint8requiredmin 0
        • replan_loopsinteger· uint8min 0
        • state_transitionsinteger· uint16requiredmin 0
        • validation_loopsinteger· uint8requiredmin 0
        • wake_cyclesinteger· uint8requiredmin 0
      • tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
    • compiled_sha256string
    • complexityobjectrequired
      • agent_owned_decompositionboolean
      • ambiguity_levelinteger· uint8requiredmin 0
      • artifact_countinteger· uint8requiredmin 0
      • coherent_long_horizonboolean
      • compensable_mutationsinteger· uint8min 0
      • coordination_edgesinteger· uint16requiredmin 0
      • dependency_depthinteger· uint8requiredmin 0
      • durable_resume_cyclesinteger· uint8min 0
      • external_systemsinteger· uint8requiredmin 0
      • material_invalidation_eventsinteger· uint8min 0
      • parallel_branchesinteger· uint8requiredmin 0
      • planning_depthinteger· uint8requiredmin 0
      • replan_loopsinteger· uint8min 0
      • state_transitionsinteger· uint16requiredmin 0
      • validation_loopsinteger· uint8requiredmin 0
      • wake_cyclesinteger· uint8requiredmin 0
    • contract_sha256stringrequired
    • deliverable_contractobjectrequired
      • artifactsobject[]required
        … expand 5 nested
        • idstringrequired
        • kindstringrequired
        • max_size_bytesinteger· uint64requiredmin 0
        • media_typestringrequired
        • schemaunknownrequired
      • capture_before_cleanupbooleanrequired
      • invariantsobject[]required
        … expand 2 nested
        • descriptionstringrequired
        • idstringrequired
      • provenance_requiredbooleanrequired
    • inputs_sha256stringrequired
    • originstringrequiredenum: built_in, markdown, local
    • required_capabilitiesstring[]required
    • resource_envelopeobjectrequired
      • executionobjectrequired
        … expand 5 nested
        • max_output_tokensinteger· uint64min 0
        • max_total_tokensinteger· uint64min 0

          Shared Harness token budget. `None` leaves the Harness budget unbounded for this scenario.

        • max_turnsinteger· uint32requiredmin 0
        • max_validation_retriesinteger· uint32min 0

          Optional per-session cap for post-turn validation denials. `None` preserves the Harness-configured default.

        • stuck_timeout_secondsinteger· uint64requiredmin 0

          Stop only after this many seconds without observable useful progress. Large scenarios have no fixed wall-clock deadline.

      • workflowany of
        … expand 2 nested
        any of (2)
        variant 1
        • max_cost_usdnumber· double
        • max_nodesinteger· uint16requiredmin 0
        • max_parallelinteger· uint16requiredmin 0
        • max_total_tokensinteger· uint64min 0
        • step_timeout_secondsinteger· uint64requiredmin 0
        • technical_retriesinteger· uint8requiredmin 0
        • workflow_timeout_secondsinteger· uint64requiredmin 0
        variant 2
        valuenull
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
    • source_pathstring
    • source_sha256string
    • titlestring

e2e::scenarios-list

function

List every built-in, committed Markdown, and local E2E test with its immutable contract, origin, capabilities, complexity, and materialized case. Call e2e::scenarios-authoring-guide before authoring a new local test.

request
  • seedinteger· uint64min 0

    Optional deterministic seed used to materialize each listed test case. Omit it to use each scenario's canonical seed.

response
  • catalog_sha256stringrequired
  • runnerobjectrequired
    • namestringrequired
    • revisionstringrequired
    • versionstringrequired
  • scenariosobject[]required
    • author_versioninteger· uint32min 0
    • behavior_sha256string
    • case_idstringrequired
    • characterizationobjectrequired
      • human_horizonall of
        … expand 1 nested
        all of (1)
        variant 1
        • basisall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: unknown, author_estimate, measured
        • max_minutesinteger· uint32min 0
        • min_minutesinteger· uint32min 0
      • realismall of
        … expand 1 nested
        all of (1)
        variant 1
        • executionall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: synthetic, realistic_simulator, frozen_real_artifact
        • shadowall of
          … expand 1 nested
          all of (1)
          variant 1
          valuestringenum: none, read_only
    • classificationobjectrequired
      • methodstringrequiredenum: capability_v2
      • profileobjectrequired
        … expand 16 nested
        • agent_owned_decompositionboolean
        • ambiguity_levelinteger· uint8requiredmin 0
        • artifact_countinteger· uint8requiredmin 0
        • coherent_long_horizonboolean
        • compensable_mutationsinteger· uint8min 0
        • coordination_edgesinteger· uint16requiredmin 0
        • dependency_depthinteger· uint8requiredmin 0
        • durable_resume_cyclesinteger· uint8min 0
        • external_systemsinteger· uint8requiredmin 0
        • material_invalidation_eventsinteger· uint8min 0
        • parallel_branchesinteger· uint8requiredmin 0
        • planning_depthinteger· uint8requiredmin 0
        • replan_loopsinteger· uint8min 0
        • state_transitionsinteger· uint16requiredmin 0
        • validation_loopsinteger· uint8requiredmin 0
        • wake_cyclesinteger· uint8requiredmin 0
      • tierstringrequiredenum: l0_atomic, l1_sequential, l2_stateful, l3_concurrent, l4_coordinated, l5_adaptive
    • compiled_sha256string
    • complexityobjectrequired
      • agent_owned_decompositionboolean
      • ambiguity_levelinteger· uint8requiredmin 0
      • artifact_countinteger· uint8requiredmin 0
      • coherent_long_horizonboolean
      • compensable_mutationsinteger· uint8min 0
      • coordination_edgesinteger· uint16requiredmin 0
      • dependency_depthinteger· uint8requiredmin 0
      • durable_resume_cyclesinteger· uint8min 0
      • external_systemsinteger· uint8requiredmin 0
      • material_invalidation_eventsinteger· uint8min 0
      • parallel_branchesinteger· uint8requiredmin 0
      • planning_depthinteger· uint8requiredmin 0
      • replan_loopsinteger· uint8min 0
      • state_transitionsinteger· uint16requiredmin 0
      • validation_loopsinteger· uint8requiredmin 0
      • wake_cyclesinteger· uint8requiredmin 0
    • contract_sha256stringrequired
    • deliverable_contractobjectrequired
      • artifactsobject[]required
        … expand 5 nested
        • idstringrequired
        • kindstringrequired
        • max_size_bytesinteger· uint64requiredmin 0
        • media_typestringrequired
        • schemaunknownrequired
      • capture_before_cleanupbooleanrequired
      • invariantsobject[]required
        … expand 2 nested
        • descriptionstringrequired
        • idstringrequired
      • provenance_requiredbooleanrequired
    • inputs_sha256stringrequired
    • originstringrequiredenum: built_in, markdown, local
    • required_capabilitiesstring[]required
    • resource_envelopeobjectrequired
      • executionobjectrequired
        … expand 5 nested
        • max_output_tokensinteger· uint64min 0
        • max_total_tokensinteger· uint64min 0

          Shared Harness token budget. `None` leaves the Harness budget unbounded for this scenario.

        • max_turnsinteger· uint32requiredmin 0
        • max_validation_retriesinteger· uint32min 0

          Optional per-session cap for post-turn validation denials. `None` preserves the Harness-configured default.

        • stuck_timeout_secondsinteger· uint64requiredmin 0

          Stop only after this many seconds without observable useful progress. Large scenarios have no fixed wall-clock deadline.

      • workflowany of
        … expand 2 nested
        any of (2)
        variant 1
        • max_cost_usdnumber· double
        • max_nodesinteger· uint16requiredmin 0
        • max_parallelinteger· uint16requiredmin 0
        • max_total_tokensinteger· uint64min 0
        • step_timeout_secondsinteger· uint64requiredmin 0
        • technical_retriesinteger· uint8requiredmin 0
        • workflow_timeout_secondsinteger· uint64requiredmin 0
        variant 2
        valuenull
    • scenario_idstringrequired
    • scenario_versioninteger· uint32requiredmin 0
    • seedinteger· uint64requiredmin 0
    • source_pathstring
    • source_sha256string
    • titlestring
  • schemastringrequired

e2e::status

function

Read the durable phase and progress of an E2E execution.

request
  • execution_idstringrequired
response
  • active_attemptany of
    any of (2)
    variant 1
    • attempt_idstringrequired
    • resume_state_pathstring
    • resume_state_sha256string
    • run_idstring
    • scenario_idstringrequired
    • session_idstringrequired
    variant 2
    valuenull
  • cancel_requestedbooleanrequired
  • errorstring
  • execution_idstringrequired
  • journal_progressobjectrequired
    • active_attempt_idstring
    • attempts_finishedinteger· uint64requiredmin 0
    • attempts_startedinteger· uint64requiredmin 0
    • committed_eventsinteger· uint64requiredmin 0
    • last_event_sha256string
    • phasestring
    • planned_slotsinteger· uint64requiredmin 0
    • runs_committedinteger· uint64requiredmin 0
    • slots_deferredinteger· uint64requiredmin 0
    • subject_observations_committedinteger· uint64requiredmin 0
    • terminalbooleanrequired
    • terminal_reasonstring
    • terminal_stateany of
      any of (2)
      variant 1
      valuestringenum: completed, failed, cancelled, needs_reconciliation, unsupported
      variant 2
      valuenull
  • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
  • terminalbooleanrequired
  • transitionsobject[]required
    • atstringrequired
    • phasestringrequiredenum: requested, admitted, preflighting, materializing, setting_up, executing,
    • reasonstringrequired
  • updated_atstringrequired

e2e::ui-content

function

Serve the Harness E2E injectable Console assets.

request
  • pathstringrequired
response
  • contentstringrequired
  • content_typestringrequired

triggers

1

e2e::dashboard::changed

trigger

A local E2E execution started, produced progress, or reached a terminal state.

invocation
empty object
return
valueunknown