micro--go-micro
Asim Aslam
29 行
2.2 KiB
Markdown
29 行
2.2 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. **Harden agent loop failure handling** ([#3391](https://github.com/micro/go-micro/issues/3391)) — now that scheduled cross-provider agent conformance shipped, close the next Now-phase reliability gap: context deadlines, cancellation, provider timeouts/rate limits, retry/backoff boundaries, and safe mid-run failure semantics across model calls, tool execution, plan/delegate, and guardrails. This makes the service-as-tool harness operable under real provider conditions before layering more agentic depth on top.
|
|
2. **CI-verify 0-to-1 and 0-to-hero developer flows** ([#3392](https://github.com/micro/go-micro/issues/3392)) — preserve the getting-started contract as an executable harness covering scaffold → run → call plus the multi-service/agent path through chat, inspection, and deploy dry-run where practical. This keeps the CLI-first inner loop aligned with the README, website, and roadmap while the harness evolves.
|
|
|
|
_Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
|
|
architecture-review pass._
|