项目文件夹

文件
Codex 49c6fe51e2
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
Update architect priority queue
2026-06-27 18:33:36 +00:00

2.2 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.

Now (ranked)

  1. Streaming end to end (#3012) — ai.Stream through micro chat, the agent RPC, and A2A message/stream; scope to chat + one provider first. Roadmap → Next and now the highest-value lifecycle seam after durable agent resume shipped.
  2. Registry disconnection detection (#2956) — readiness/health when a service silently loses its registry connection. Community-requested production reliability; keeps the service substrate operable because agents depend on discovery.
  3. Agent observability spans (#3182) — export RunInfo as OpenTelemetry spans for agent runs, model calls, tool calls, delegation, and failures. Roadmap → Next; makes the now-durable harness inspectable in production.
  4. Execution lifecycle hooks & metadata (#2980) — before/after-tool, retry, and failure hooks; first check overlap with the shipped run-timeline / OpenTelemetry work and scope to what's not already covered.

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