Co-authored-by: Codex <codex@openai.com>
2.1 KiB
Priorities
The ranked work queue for the autonomous improvement loop. The architecture-review pass (the architect) owns this file: each run it turns the roadmap plus an internal scan (gaps in the services → agents → workflows lifecycle, API coherence, drift, tech debt, test and DX friction) into a single ordered list — highest-value first — and links each item to a tracking issue. The hourly continuous-improvement pass works the top item whose issue is still open. So the architect decides what, and the increment loop builds it.
Reading / editing. An item is done when its linked issue closes (the increment
that builds it adds Closes #<issue>). Roadmap phase (Now → Next → Later) is the
primary ordering; internal findings are interleaved by value, not kept in a
separate list. The human can reorder this list — or the issues — at any time to
redirect the loop; direction always wins.
Off-limits to the loop (the architect proposes these as notes, never as queue items the loop can auto-merge): brand/positioning copy, breaking public-API changes, architectural rewrites. Those go to the human.
Developer experience (ranked)
- Expose run inspection in the CLI inner loop (#3297) — the canon promises scaffold → run → chat → inspect → deploy, and recent work added run timelines, trace correlation, and a
micro runsfoothold; with conformance scheduling, failure/backoff hardening, the deploy contract, and the support reference now shipped, this is the highest-value remaining DX seam in the Now/ongoing roadmap until local agent/flow activity is documented and CI-tested as an actionable inspect step. - Add durable agent run checkpoint and resume (#3306) — once the remaining inspection seam is closed, the highest-value Next-roadmap item is making agent loops resumable like flows so long-running work can survive restarts without unsafe replay or hidden state loss.
Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the architecture-review pass.