{"campaign_id":"native-interaction-20261010-omarchy","candidate":{"build_sha256":"514e2b2bb169e1e60737d3a6c688266faffbb549556c6a1f5ebc4d5fd7fa1058","channel":"released","identity_complete":true,"label":"ibara 0.2.1-1 on Omarchy"},"comparison":null,"correction":null,"groups":[{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":3,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":3,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":3,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":3,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Long Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Long Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Long Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Long Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Long Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Long Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Long Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Long Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Short Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Short Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Short Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Short Unicode save, checked batches"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Short Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Short Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Short Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Short Unicode save, single calls"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Synthetic browser form"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Synthetic browser form"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Synthetic browser form"},{"benchmark_mode":"scripted","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Synthetic browser form"}],"kind":"benchmark","limitations":["Scripted system diagnostic; no fresh-agent productivity, model ranking or qualified comparison baseline claim.","One fixed desktop and bridge route per environment; no cross-platform speed comparison.","Timings include bridge transport, expectation settlement and returned observations; they are not pure target input latency.","Frame and shadow targets are probed deliberately; unsupported outcomes remain in the denominator.","Exact file bytes and trusted fixture events independently verify outputs; observation trials witness the owned native window, not correctness of every captured pixel.","Continuous video, physical takeover and stream frame-age measurements are absent.","Original receipts remain private; public output contains sanitized aggregates.","Public workflow metrics are means and counts; full per-call timing and frame-cost measurements are retained privately.","Long-text UI settlement uses a bounded prefix; complete independent saved-byte readback is the unchanged correctness oracle.","Matched save routes use twelve checked native actions. Changing API usage is not a product binary improvement.","Single-call routes precede batches within each pair; order is not randomized and caches are not reset. Active durations include recording and independent-oracle overhead.","Confirmation counts include every selected workflow; exploratory and changed harness records have separate source scopes.","Original exploratory reported-attribution summaries remain unchanged and separate. Confirmation explicitly declares independent attribution.","Halla is a shared eight-logical-CPU collector. Unrelated project workers and load average near15 were observed during Ubuntu round22; later partial CPU logging captured above90% aggregate busy during round24. Per-attempt overlap is not fully measured. Timings are descriptive, not a controlled host-isolation experiment.","Per-workflow confirmation p95 is withheld below20 samples; paired saving is computed only for same-round successful single/batch pairs, with full outcome coverage retained.","Round03 executed two of60 planned workflows before collection interruption. Round04 long-text UI expectations stopped before saving. Round05 retained one refused filename hotkey as unknown.","Round06 overlapped a Halla warehouse recovery import and is excluded from the clean stability cohort; rounds07,16,17 use the same frozen harness.","Single-call and checked-batch route timings are separate descriptive measurements. No qualified comparison delta is published; full same-repeat timing analysis remains a separately scoped numerical artifact."],"measured_at":{"end":"2026-10-11T01:29:19.568003+00:00","start":"2026-10-10T23:31:15.512488+00:00"},"methodology":"Three fixed-source confirmation rounds per environment each contain four repetitions of eight workflows;96 executed attempts per environment. Exploratory and changed calibration recipes are retained separately. Exact released target builds, source copies, native receipts, collector timings, independent file or trusted-fixture oracles and cleanup witnesses are retained. Failures remain in scope. The same frozen harness is used throughout each confirmation cohort. This is a scripted diagnostic, not a causal binary performance or agent comparison.","metrics":[{"denominator":96,"name":"Verified task completion","numerator":84,"population":"scripted attempts","sample_count":96,"statistic":"ratio","unit":"fraction","value":0.875},{"denominator":null,"name":"Attempt duration","numerator":null,"population":"scripted: Attempt summaries with duration_ms measured","sample_count":96,"statistic":"mean","unit":"ms","value":12223.349333145961},{"denominator":null,"name":"Tool calls","numerator":null,"population":"scripted: Attempt summaries with tool_calls measured","sample_count":96,"statistic":"mean","unit":"count","value":14.75},{"denominator":null,"name":"Model tokens","numerator":null,"population":"scripted: Attempt summaries with tokens measured","sample_count":0,"statistic":"mean","unit":"count","value":null},{"denominator":null,"name":"Measured model cost","numerator":null,"population":"scripted: Attempt summaries with cost_usd measured","sample_count":0,"statistic":"mean","unit":"USD","value":null}],"provenance":{"snapshot_sha256":"abda65b749aa4402e192ab87331f3d767585c22f54c94f142064ee15f039476a","source_sha256":null,"source_url":null,"type":"warehouse_snapshot"},"qualification":{"classification":"diagnostic","completed_cells":0,"eligible_for_comparison":false,"mode_counts":[{"counts":{"attempted":96,"blocked":0,"failed":12,"not_run":0,"passed":84,"planned":96,"safe_refusal":0,"unknown":0},"mode":"scripted"}],"planned_cells":0,"reasons":["An observed attempt is outside the frozen matrix.","Diagnostic evidence is not an accepted comparison baseline.","Exactly one frozen campaign manifest is required.","The frozen matrix has missing, duplicate or unplanned attempts; valid failures remain counted.","The planned machine, workflow, mode and seed matrix is unavailable."]},"revision":1,"schema_version":"1.0","sealed_at":"2026-10-11T01:30:33.394019+00:00","suite":{"label":"Native interaction and exact-output workflows","version":"native-diagnostic-confirmation-v1"},"title":"Omarchy native benchmark confirmation","totals":{"attempted":96,"blocked":0,"failed":12,"not_run":0,"passed":84,"planned":96,"safe_refusal":0,"unknown":0}}