Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c27a04b0e7 |
@@ -21,7 +21,7 @@ changes, architectural rewrites. Those go to the human.
|
||||
|
||||
## Work queue (ranked)
|
||||
|
||||
1. **Align architecture docs with the agent harness lifecycle** ([#4092](https://github.com/micro/go-micro/issues/4092)) — the first-agent on-ramp, install troubleshooting, preflight, and after-run doctor seams are now covered, but the website architecture page still reads like a pre-agent distributed-systems overview. Refresh it so newcomers see one coherent services → agents → workflows runtime: registry/server/client as the service substrate, `model`/`store` as state, `ai`/`agent` as the tool-calling loop, `flow` as durable deterministic orchestration, and MCP/A2A gateways as interop. Add a focused docs/wayfinding assertion so the architecture story keeps pointing back to AI integration, first-agent, and 0→hero.
|
||||
1. **Promote agent doctor in the first-agent debug loop** ([#4086](https://github.com/micro/go-micro/issues/4086)) — install troubleshooting and preflight now cover the before-run adoption seams; next close the after-run recovery seam for newcomers whose first agent starts but chat, gateway, registration, provider settings, or run history misbehave. Link `micro agent doctor` from the first-agent and debugging path, distinguish it from install troubleshooting and `micro agent preflight`, and add a focused CLI/docs harness assertion so the scaffold → run → chat → inspect recovery checkpoint stays discoverable.
|
||||
|
||||
_Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
|
||||
architecture-review pass._
|
||||
|
||||
@@ -33,10 +33,9 @@ After it passes:
|
||||
- Walk the full 0→hero lifecycle: https://go-micro.dev/docs/guides/zero-to-hero.html
|
||||
|
||||
Use live-provider chat when you are ready for real model behavior:
|
||||
micro agent preflight # before micro run: prerequisites
|
||||
micro agent preflight
|
||||
micro run
|
||||
micro chat
|
||||
micro agent doctor # after micro run: chat/gateway/inspect recovery
|
||||
micro inspect agent <name>`
|
||||
|
||||
func init() {
|
||||
@@ -81,7 +80,7 @@ for live-provider chat and inspect/debugging.`,
|
||||
},
|
||||
{
|
||||
Name: "doctor",
|
||||
Usage: "Diagnose chat, gateway, registration, provider, and inspect recovery after micro run",
|
||||
Usage: "Diagnose chat and inspect recovery after micro run",
|
||||
Flags: []cli.Flag{
|
||||
&cli.StringFlag{Name: "gateway", Value: "http://localhost:8080", Usage: "Gateway URL started by micro run"},
|
||||
},
|
||||
|
||||
@@ -40,10 +40,10 @@ const docsWayfinding = `First-agent and 0→hero docs:
|
||||
3. Your First Agent
|
||||
https://go-micro.dev/docs/guides/your-first-agent.html
|
||||
Build a service-backed agent, then use:
|
||||
micro agent preflight # before micro run: prerequisites
|
||||
micro agent preflight
|
||||
micro run
|
||||
micro chat
|
||||
micro agent doctor # after micro run: chat/gateway/inspect recovery
|
||||
micro agent doctor
|
||||
|
||||
4. Debugging your agent
|
||||
https://go-micro.dev/docs/guides/debugging-agents.html
|
||||
|
||||
@@ -64,10 +64,10 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
|
||||
"your-first-agent.html",
|
||||
"debugging-agents.html",
|
||||
"zero-to-hero.html",
|
||||
"micro agent preflight # before micro run: prerequisites",
|
||||
"micro agent preflight",
|
||||
"micro run",
|
||||
"micro chat",
|
||||
"micro agent doctor # after micro run: chat/gateway/inspect recovery",
|
||||
"micro agent doctor",
|
||||
"micro inspect agent",
|
||||
} {
|
||||
if !strings.Contains(out.String(), want) {
|
||||
@@ -79,13 +79,6 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
|
||||
if !strings.Contains(agent.Usage, "micro agent demo") {
|
||||
t.Fatalf("micro agent help should advertise the no-secret demo; usage was %q", agent.Usage)
|
||||
}
|
||||
doctor := subcommandByName(t, agent, "doctor")
|
||||
for _, want := range []string{"chat", "gateway", "registration", "provider", "inspect", "after micro run"} {
|
||||
if !strings.Contains(doctor.Usage, want) {
|
||||
t.Fatalf("micro agent doctor usage should advertise after-run recovery for %q; usage was %q", want, doctor.Usage)
|
||||
}
|
||||
}
|
||||
|
||||
demo := subcommandByName(t, agent, "demo")
|
||||
out.Reset()
|
||||
if err := demo.Action(cli.NewContext(app, nil, nil)); err != nil {
|
||||
@@ -95,9 +88,8 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
|
||||
"No-secret first-agent demo",
|
||||
"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1",
|
||||
"provider-free",
|
||||
"micro agent preflight # before micro run: prerequisites",
|
||||
"micro agent preflight",
|
||||
"micro chat",
|
||||
"micro agent doctor # after micro run: chat/gateway/inspect recovery",
|
||||
"micro inspect agent <name>",
|
||||
"your-first-agent.html",
|
||||
"debugging-agents.html",
|
||||
|
||||
@@ -17,21 +17,9 @@ micro inspect ... # read the recorded run or workflow history
|
||||
|
||||
Debug the lifecycle in the same order Go Micro runs it: first prove the service is
|
||||
registered and callable, then inspect the agent run that chose tools, then inspect
|
||||
any workflow that handed off to the agent.
|
||||
|
||||
Use the recovery command that matches where you are in the first-agent journey:
|
||||
|
||||
| Checkpoint | When to use it | Command |
|
||||
| --- | --- | --- |
|
||||
| Install troubleshooting | `micro` is not installed, not on `PATH`, or the shell cannot run it. | [Install troubleshooting](install-troubleshooting.html) |
|
||||
| Preflight before `micro run` | You have not started the local runtime yet and want to verify Go, CLI, provider-key, and gateway-port prerequisites. | `micro agent preflight` |
|
||||
| Doctor after `micro run` | `micro run` is active, but chat, the `/agent` gateway, agent registration, provider settings, or inspect/run history is not behaving. | `micro agent doctor` |
|
||||
|
||||
`micro agent preflight` is read-only and runs before the first local run; failed
|
||||
checks include `Fix:` and `Next:` lines for Go, CLI installation, provider-key
|
||||
setup, and the local gateway port. Once `micro run` is already up, switch to
|
||||
`micro agent doctor` so the recovery output follows the live gateway, chat
|
||||
settings, registered agents, provider configuration, and inspectable run history.
|
||||
any workflow that handed off to the agent. If the first local run fails before a
|
||||
chat turn, run `micro agent preflight`; failed checks include `Fix:` and `Next:`
|
||||
lines for Go, CLI installation, provider-key setup, and the local gateway port.
|
||||
|
||||
## 1. Reproduce one small turn
|
||||
|
||||
|
||||
@@ -53,11 +53,7 @@ Run the read-only first-agent preflight before starting the walkthrough. The sam
|
||||
micro agent preflight
|
||||
```
|
||||
|
||||
It checks Go 1.24+, the `micro` binary, provider-key setup, and the default local gateway port without contacting a provider. Failed checks include a `Fix:` line and a `Next:` line that points back to this guide, the no-secret walkthrough, or the debugging guide. Use it before `micro run`; if `micro run` is already active but `micro chat`, the `/agent` gateway, registration, provider settings, or inspect history is failing, run the after-run recovery check instead:
|
||||
|
||||
```sh
|
||||
micro agent doctor
|
||||
```
|
||||
It checks Go 1.24+, the `micro` binary, provider-key setup, and the default local gateway port without contacting a provider. Failed checks include a `Fix:` line and a `Next:` line that points back to this guide, the no-secret walkthrough, or the debugging guide.
|
||||
|
||||
## 1. Create a workspace
|
||||
|
||||
|
||||
Reference in New Issue
Block a user