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)
- CI-verify the getting-started 0→1 and 0→hero contract (#4428) — Developer adoption is the current goal, and the README/website promise scaffold → run → call plus a no-secret services → agents → workflows path. Keep that on-ramp as a CI-verifiable contract with clear failure boundaries so first-agent success stays weighted alongside harness depth.
- Handle AtlasCloud plan-delegate partial tool calls (#4431) — Recent live conformance showed AtlasCloud/minimax can stop at a partial XML-style tool call, leaving delegation without the required task/notify side effects. Fix this focused provider/tool-call seam next so cross-provider hardening covers the services → agents → workflows loop without masking failed delegation as success.
Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the architecture-review pass.