/.github/loop/PRIORITIES.md

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)

1. Add a smallest first-agent runnable reference (#3914) — #3912 closed the durable agent-run checkpoint/resume item (#3902), leaving only Next-phase internal depth items in the queue. The North Star currently says developer adoption is the gap, and the README/website/blog canon all lead with the same services → agents → workflows story. Keep the queue balanced by giving builders a tiny no-secret first-agent example between micro new helloworld and the full examples/support 0→hero app, linked from README, website getting-started, and examples, with CI proving the transcript/path works without provider keys.
2. Broaden provider streaming and keep chat/A2A streaming end to end (#3903) — streaming is the next developer-visible seam in the inner loop. Real chat and long-running A2A tasks need token streaming to stay coherent from provider → ai.Stream → micro chat → A2A message/stream, with mock/default CI coverage plus key-gated live provider checks and safe fallback for non-streaming providers.
3. Trace agent runs as OpenTelemetry spans (#3908) — the blog/README/roadmap story promises an operable harness, and the developer on-ramp now includes chat, inspect, and run-history checkpoints. The next observability gap is production-grade trace correlation for RunInfo: steps, tool calls, delegation, status, durations, and failures should be visible as spans while defaulting to no-op when tracing is not configured.

Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the architecture-review pass.