micro--go-micro
Asim Aslam
29 行
2.3 KiB
Markdown
29 行
2.3 KiB
Markdown
# 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](../../ROADMAP.md) 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. **CI-verify cross-provider agent conformance** ([#3537](https://github.com/micro/go-micro/issues/3537)) — retry/backoff resilience and durable checkpoint/resume have shipped, so the highest-value remaining Now-phase gap is proving the same services → agents → workflows scenario works across every supported model provider. This keeps the harness honest where provider drift most directly breaks developer trust: model calls, tool calls, skip/pass/fail reporting, and CI-safe execution when credentials are absent.
|
|
2. **Emit OpenTelemetry spans for agent run timelines** ([#3525](https://github.com/micro/go-micro/issues/3525)) — recent work made runs inspectable, correlated trace metadata through scheduled dispatch, verified restart resume, and added opt-in tool retries; the next step is to turn that RunInfo foundation into standard OTel spans for agent runs, model calls, tool calls, checkpoint/resume, and failures. This keeps `micro runs` useful while making the harness observable in the systems developers already run.
|
|
|
|
_Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
|
|
architecture-review pass._
|