Codex
3fb54b662f
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.
Work queue (ranked)
- Stabilize AtlasCloud agent conformance marker retry (#4348) — The durable-agent checkpoint issue has shipped, so the highest-value open Now-phase gap is the live provider conformance failure found in Harness (E2E): AtlasCloud completes the tool/delegate path but can omit the required conformance marker after retry. Fixing this protects the cross-provider promise behind first-agent trust without broad API or architecture change.
- Trace agent RunInfo in OpenTelemetry spans (#4315) — After the live conformance regression is stable, the highest Next-phase operability gap is connecting existing run metadata to traces so real agent runs can be debugged across steps, tool calls, delegation, failures, services, and flows without inventing a new surface.
Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the architecture-review pass.