/internal/docs/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. Agent: durable Ask/StreamAsk checkpoint and resume (#3349) — the remaining Next-phase durable agent-loop gap. Flows already checkpoint deterministic work, and tool-aware StreamAsk has now shipped; long-running agent runs still cannot resume after process/transport interruption without risking duplicate tool calls or lost guardrail state. Add additive checkpoint/resume plumbing for agent runs that persists messages, tool calls/results, step counters, approvals, and terminal/error state, reusing the flow checkpoint mental model where practical.
2. Add human-in-the-loop pause and resume for agent workflows (#3329) — after memory compaction and tool-aware streaming shipped, close the next operability gap for scheduled/looping work: durable pending-input states that let humans approve or provide context and then resume the same service/agent/workflow runtime.
3. gateway/a2a: multiple typed skills per agent card (#3342) — the a2a gateway now has the full task lifecycle (send/stream/get/cancel/resubscribe, push config, multi-turn, input-required); the remaining gap is skill granularity. Card only ever advertises one synthetic "chat" skill with services flattened into tags. Let an agent advertise N typed skills and route per skill, so domain-routing agents expose their real capabilities over A2A through the gateway instead of a hand-rolled handler.

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