Skip to content

Persist research stages and resume shadow and human decisions safely - #596

Merged
Pigbibi merged 2 commits into
mainfrom
codex/research-resume-20260909
Sep 8, 2026
Merged

Persist research stages and resume shadow and human decisions safely#596
Pigbibi merged 2 commits into
mainfrom
codex/research-resume-20260909

Conversation

@Pigbibi

@Pigbibi Pigbibi commented Sep 8, 2026

Copy link
Copy Markdown
Contributor

Interrupted research currently loses completed work, and the normal automation cycle cannot resume a candidate's first console delivery after a checkpoint. Persist each existing promotion-ticket stage under the frozen input, code, parameter, cost and validator identity. Resume completed results, keep unknown outcomes parked, and reuse terminal tickets instead of starting another experiment.

Research, console decision recovery and the local decision CLI share the same directory lock. A new optional admission callback runs under that lock only for new experiments, before any model request; existing tickets bypass admission. Normal automation and the actionable runner use the saved path, including a narrowly scoped first-delivery recovery.

Forward shadow can remain pending until its observation window completes. A dedicated read-only callback resumes only at its saved deadline and validates paired evidence, including predecessor receipts. The original drift observation can expire while this existing experiment waits: only its verified shadow or human-decision tail may continue, without repeating diagnosis, optimization, backtest or an unknown console POST. New experiments still require fresh drift evidence. Human acceptance grants only intent, never live authority. The reusable drift workflow adopts the published Codex-only AAB revision without changing its schedule or data collection.

Validation: isolated, network-blocked 298 tests and 37 subtests passed; workflow test, actionlint, Ruff and diff checks passed. Independent review covered normal-caller recovery and admission, then 28 shadow checks plus four regression cases for decisions after stale observations. CN's actual calling path passed with the new optional reader. No live model, console or broker calls. Directory locking covers one shared filesystem; the concrete observation reader remains responsible for real data provenance, source/parameter binding and the full forward calendar window.

Pigbibi and others added 2 commits September 9, 2026 03:25
@Pigbibi Pigbibi changed the title feat(research): resume bounded experiments and serialize admission Persist research stages and resume shadow and human decisions safely Sep 8, 2026
@Pigbibi
Pigbibi merged commit b565424 into main Sep 8, 2026
1 check passed
@Pigbibi
Pigbibi deleted the codex/research-resume-20260909 branch September 8, 2026 19:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant