{"campaign_id":"2026-10-08-incumbent-lifecycle-baseline","candidate":{"build_sha256":"1a2c7db0be83a8a8cd02f837ecfc8a0cdde92ec29425262d6c30f35a07958873","channel":"experimental","identity_complete":true,"label":"Incumbent plus lifecycle repair, private v14"},"comparison":null,"correction":null,"groups":[{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Browser and file attachments"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Browser form"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Document viewer"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Document viewer"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Download, edit and upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":1,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":1,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":1,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"File manager move and rename"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"File upload"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"File upload"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Interactive native input"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"BMAX B4 Plus","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Multiple applications and dialogs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Search and nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Search and nested scrolling"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK2","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"AcePC AK1","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Terminal CSV filtering"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"Frozen native reference recipe","scenario":"Terminal CSV filtering"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":17,"model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":29,"model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering"},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Dell Optiplex","fixture_seed":43,"model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering"},{"counts":{"attempted":0,"blocked":0,"failed":0,"not_run":127,"passed":0,"planned":127,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Not run","model":"Not run","scenario":"Planned but not run"}],"kind":"benchmark","limitations":["This incomplete campaign is diagnostic evidence, not an accepted comparison baseline. Its 42 passed, 16 unknown, 4 failed and 3 blocked original outcomes describe 65 attempted slots; 127 planned slots were not started. No improvement or general reliability claim is supported.","After a host crash, the root and coordinator execution ancestry used Codex CLI 0.162.0 instead of registered 0.161.0. Fifteen resumed fresh-agent contexts are affected. Direct child executable witnesses were not captured, and the process start time does not establish when the harness changed. All fresh-agent timing aggregates are withheld; original task results remain recorded.","The displayed measured_at evidence interval includes preparation and later assessment records; it is not the timed trial window. Primary execution began on 8 October 2026 at 22:24:14 UTC and had stopped by 9 October at 01:11:39 UTC, as recorded by the early-stop receipt. The campaign stopped early for the harness identity issue. The maximum cutoff was unchanged but not reached. Unstarted slots were not replayed or replaced, and no new campaign window was inferred.","The host crash lost four active agent contexts. Original bounded collectors and cleanup receipts were retained, but interruption coverage and exact crash timing are incomplete. Two earlier active trials were also affected by an explicit root interruption.","One editor save prompt required a person to save and close the test document before hand-back. That later recovery does not turn the original timed cleanup failure into success. An early-stop trial remains partial with its original outcome.","Three fresh editor trials were blocked before acquisition by a missing verification host field and a frozen retry fence despite a retry-safe validation response. Scripted OCR misses also caused original unknown outcomes; later visual diagnosis does not replace them.","Two CSV trials produced the correct filtered rows with CRLF line endings but failed an exact-byte oracle expecting LF, although that distinction was not stated in the public task goal. Two browser trials used native context menus to open the required tab but failed the frozen click-route oracle. These original failures remain visible.","Interactive-input measurement had a collector payload-shape defect in one scripted trial and missing scoped input-release witnesses in fresh trials. An independent later review verified one file-manager task, but its original unknown score remains unchanged. Post-task assessments never substitute for original scores.","Three planned fresh variants per workflow and computer are insufficient for precise reliability estimates. Missing coverage and early stopping prevent balanced comparisons across workflows or hardware. Scripted and fresh-agent results must remain separate.","Model tokens and cost were unavailable from the actor harness; unavailable values are not zero. Supplemental browser-capability checks are separate diagnostic evidence and are not included in this 192-slot primary matrix."],"measured_at":{"end":"2026-10-09T01:18:37.640384+00:00","start":"2026-10-08T11:41:06.846164+00:00"},"methodology":"Frozen matrix of twelve workflows on four physical computers: 48 scripted reference trials and 144 fresh-agent trials with seeds 17, 29 and 43. Fresh agents use GPT-6 Astra with ultra reasoning in separate contexts. Each trial has a 600-second and 60-call budget plus a separate 60-second cleanup deadline. The campaign stopped early after execution-harness identity drift was discovered; the original six-hour maximum was not reached or reset. All 192 planned slots remain: 19 scripted and 46 fresh-agent attempts were recorded, and 127 slots were not started. Native Ibara input was required. Independent fixture files, application events and retained native evidence determine original task outcomes. Workflow rows separate computer and execution mode. All fresh-agent timing is withheld because execution-harness identity was contradicted or unverified. Workflow successful-duration rows include passed attempts only; the overall scripted attempt-duration mean includes all 19 measured attempts. These timings are descriptive. Original outcomes and evidence remain unchanged.","metrics":[{"denominator":19,"name":"Verified task completion","numerator":13,"population":"scripted attempts","sample_count":19,"statistic":"ratio","unit":"fraction","value":0.6842105263157895},{"denominator":46,"name":"Verified task completion","numerator":29,"population":"fresh_agent attempts","sample_count":46,"statistic":"ratio","unit":"fraction","value":0.6304347826086957},{"denominator":null,"name":"Attempt duration","numerator":null,"population":"scripted: Attempt summaries with duration_ms measured","sample_count":19,"statistic":"mean","unit":"ms","value":42199.36968421053},{"denominator":null,"name":"Tool calls","numerator":null,"population":"scripted: Attempt summaries with tool_calls measured","sample_count":19,"statistic":"mean","unit":"count","value":15.31578947368421},{"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},{"denominator":null,"name":"Tool calls","numerator":null,"population":"fresh_agent: Attempt summaries with tool_calls measured","sample_count":46,"statistic":"mean","unit":"count","value":16.0},{"denominator":null,"name":"Model tokens","numerator":null,"population":"fresh_agent: Attempt summaries with tokens measured","sample_count":0,"statistic":"mean","unit":"count","value":null},{"denominator":null,"name":"Measured model cost","numerator":null,"population":"fresh_agent: Attempt summaries with cost_usd measured","sample_count":0,"statistic":"mean","unit":"USD","value":null}],"provenance":{"snapshot_sha256":"799ecc24f7725c6ac903591e8762d5aa738f1d9d4fc68eb5926e1ccff3d689b2","source_sha256":null,"source_url":null,"type":"warehouse_snapshot"},"qualification":{"classification":"incomplete_benchmark","completed_cells":65,"eligible_for_comparison":false,"mode_counts":[{"counts":{"attempted":19,"blocked":0,"failed":0,"not_run":29,"passed":13,"planned":48,"safe_refusal":0,"unknown":6},"mode":"scripted"},{"counts":{"attempted":46,"blocked":3,"failed":4,"not_run":98,"passed":29,"planned":144,"safe_refusal":0,"unknown":10},"mode":"fresh_agent"}],"planned_cells":192,"reasons":["An attempt has an unknown independent goal outcome.","An attempt lacks one exact artifact-backed independent outcome and cleanup witness.","An attempt lacks original native observations and measured budget, intervention, effect and data-integrity counters.","An attempt required external intervention and is not an independent comparison trial.","The frozen matrix has missing, duplicate or unplanned attempts; valid failures remain counted.","The registered execution harness is contradicted or unverified by scoped post-recovery ancestry evidence; fresh-agent timings are withheld."]},"revision":1,"schema_version":"1.0","sealed_at":"2026-10-09T01:31:37.950692+00:00","suite":{"label":"Twelve complete browser, native and mixed workflows","version":"12-workflows-v1"},"title":"Incumbent computer-use diagnostic campaign","totals":{"attempted":65,"blocked":3,"failed":4,"not_run":127,"passed":42,"planned":192,"safe_refusal":0,"unknown":16},"workflow_results":[{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Browser and file attachments","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Browser and file attachments","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Browser and file attachments","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Browser and file attachments","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser and file attachments","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Browser form","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Browser form","successful_duration":{"max":93073.326,"measured":1,"median":93073.326,"min":93073.326,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Browser form","successful_duration":{"max":50243.904,"measured":1,"median":50243.904,"min":50243.904,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Browser form","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Browser form","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Document viewer","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Document viewer","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Document viewer","successful_duration":{"max":30272.854,"measured":1,"median":30272.854,"min":30272.854,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Document viewer","successful_duration":{"max":19586.815000000002,"measured":1,"median":19586.815000000002,"min":19586.815000000002,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Document viewer","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Download, edit and upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Download, edit and upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Download, edit and upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Download, edit and upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Download, edit and upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery","successful_duration":{"max":53661.278000000006,"measured":1,"median":53661.278000000006,"min":53661.278000000006,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery","successful_duration":{"max":27542.873,"measured":1,"median":27542.873,"min":27542.873,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Editor, save, reopen and delivery","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":3,"failed":0,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Editor, save, reopen and delivery","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"File manager move and rename","successful_duration":{"max":68984.02,"measured":1,"median":68984.02,"min":68984.02,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"File manager move and rename","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"File manager move and rename","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"File manager move and rename","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"File manager move and rename","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"File upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"File upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"File upload","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"File upload","successful_duration":{"max":24730.965,"measured":1,"median":24730.965,"min":24730.965,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"File upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"File upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"File upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"File upload","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Interactive native input","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Interactive native input","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Interactive native input","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Interactive native input","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":3,"safe_refusal":0,"unknown":3},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Interactive native input","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Multiple applications and dialogs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Multiple applications and dialogs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Multiple applications and dialogs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Multiple applications and dialogs","successful_duration":{"max":36380.449,"measured":1,"median":36380.449,"min":36380.449,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":1},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Multiple applications and dialogs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Overlays, frames and tabs","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":1,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":1,"not_run":0,"passed":2,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Overlays, frames and tabs","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Search and nested scrolling","successful_duration":{"max":58931.805,"measured":1,"median":58931.805,"min":58931.805,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Search and nested scrolling","successful_duration":{"max":48586.327,"measured":1,"median":48586.327,"min":48586.327,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Search and nested scrolling","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Search and nested scrolling","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":0,"not_run":0,"passed":3,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":2,"passed":1,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Search and nested scrolling","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"Frozen native reference recipe","scenario":"Terminal CSV filtering","successful_duration":{"max":29194.252,"measured":1,"median":29194.252,"min":29194.252,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"Frozen native reference recipe","scenario":"Terminal CSV filtering","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":1,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"Frozen native reference recipe","scenario":"Terminal CSV filtering","successful_duration":{"max":null,"measured":0,"median":null,"min":null,"missing":0,"unit":"ms"}},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"Frozen native reference recipe","scenario":"Terminal CSV filtering","successful_duration":{"max":19513.866,"measured":1,"median":19513.866,"min":19513.866,"missing":0,"unit":"ms"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK1","model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"AcePC AK2","model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":0,"blocked":0,"failed":0,"not_run":3,"passed":0,"planned":3,"safe_refusal":0,"unknown":0},"environment":"BMAX B4 Plus","model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}},{"benchmark_mode":"fresh_agent","counts":{"attempted":3,"blocked":0,"failed":2,"not_run":0,"passed":1,"planned":3,"safe_refusal":0,"unknown":0},"environment":"Dell Optiplex","model":"GPT-6 Astra, ultra reasoning","scenario":"Terminal CSV filtering","successful_duration":{"unit":"ms","withheld":"execution_harness_identity"}}]}