micro--go-micro
Codex
eeaac92742
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
30 行
3.4 KiB
Markdown
30 行
3.4 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. **Make AtlasCloud live conformance exercise the guarded delegate path** ([#3990](https://github.com/micro/go-micro/issues/3990)) — #3993 shipped the highest-priority adoption wayfinding gap by surfacing first-agent and 0→hero next steps from `micro new`, so the queue should not re-run #3983. The current top risk is a live provider-conformance regression in the Now-phase “battle-tested across providers” contract: AtlasCloud completed the model/tool path but skipped the guarded delegation attempt, leaving the harness unable to prove delegation refusal behavior across providers.
|
|
2. **Make AtlasCloud plan/delegate complete required tasks before notification** ([#3991](https://github.com/micro/go-micro/issues/3991)) — the same scheduled live harness exposed a 0→hero correctness seam: the conductor emitted the delegated notification side effect while required task-creation plan steps remained unfinished. This is ranked just behind #3990 because it protects the services → agents → workflows story users now discover through the CLI and should fail safely before side effects or recover before checkpoint validation.
|
|
3. **Broaden provider streaming and keep chat/A2A streaming end to end** ([#3903](https://github.com/micro/go-micro/issues/3903)) — once the live conformance regressions are fixed, streaming remains the highest developer-visible Next-phase seam. Real chat and long-running A2A tasks need token streaming to stay coherent from provider → `ai.Stream` → `micro chat` → A2A `message/stream`, with mock/default CI coverage plus key-gated live provider checks and safe fallback for non-streaming providers.
|
|
4. **Trace agent runs as OpenTelemetry spans** ([#3908](https://github.com/micro/go-micro/issues/3908)) — the blog/README/roadmap story promises an operable harness, and the developer on-ramp now includes chat, inspect, and run-history checkpoints. The next observability gap is production-grade trace correlation for `RunInfo`: steps, tool calls, delegation, status, durations, and failures should be visible as spans while defaulting to no-op when tracing is not configured.
|
|
_Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
|
|
architecture-review pass._
|