Codex
99e5e76de1
2.4 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)
- Propagate agent run cancellation and deadlines through model and tool calls (#3544) — cross-provider conformance now has scheduled CI, env-selectable AtlasCloud coverage, and phase-labelled pass/skip/fail output, so the highest-value remaining Now-phase gap is predictable failure semantics. Tool retries are in place, but the lifecycle still needs cancellation/deadline propagation across agent runs, model calls, tool calls, plan/delegate, and flow handoffs so services → agents → workflows fail safely instead of becoming opaque loops.
- Emit OpenTelemetry spans for agent run timelines (#3525) — recent work made runs inspectable, correlated trace metadata through scheduled dispatch, verified restart resume, added opt-in tool retries, and hardened provider conformance. The next Next-phase step is to turn that RunInfo foundation into standard OTel spans for agent runs, model calls, tool calls, checkpoint/resume, cancellation/deadlines, and failures. This keeps
micro runsuseful while making the harness observable in the systems developers already run.
Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the architecture-review pass.