/.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 memory compaction controls for long-running agents (#4765) — #4763 closed the live registered-agent micro chat --stream gap, and the recent run also over-invested in docs-link guards, AtlasCloud-specific repair, and plan/delegate edge hardening. The next highest-value user-facing gap is memory that survives beyond toy conversations without unbounded prompt growth: add opt-in compaction/summarization that preserves recent turns/tool results, stores an inspectable summary, and keeps Ask/stream/checkpoint behavior coherent without changing defaults.

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