Demonstrate PromptKit catalogs and smoke tests

This commit is contained in:
2026-10-17 19:06:05 +00:00
parent 079576361b
commit 35e958c210
4 changed files with 127 additions and 8 deletions

View File

@@ -12,6 +12,10 @@ go run . config diff --scope app --config fixtures/before.yml --against-config f
go run . config diff --scope promptkit --config fixtures/before.yml --against-config fixtures/after.yml --campaign spring
go run . promptkit list prompts --config fixtures/before.yml --campaign spring
go run . promptkit list profiles --config fixtures/after.yml --campaign autumn --format yaml
go run . promptkit list backends --campaign spring
go run . promptkit list namespaces --campaign spring
go run . promptkit list collections --campaign spring
go run . promptkit list prompts --namespace field-notes --campaign spring
go run . promptkit show prompt briefing --campaign spring --format yaml
go run . promptkit show profile spring --campaign spring
go run . promptkit requirements show briefing --campaign spring
@@ -19,6 +23,8 @@ go run . promptkit requirements show briefing --campaign spring --var mode=full
go run . promptkit requirements validate briefing --campaign spring --input topic=fixtures/topic.txt
go run . promptkit requirements validate briefing --campaign spring --input topic=fixtures/topic.txt --var mode=full --input notes=fixtures/notes.txt --format yaml
go run . promptkit requirements validate briefing --campaign spring
go run . promptkit test text_inference --campaign spring --prompt briefing --profile spring
go run . promptkit test all --campaign spring --prompt briefing --profile spring
go run . session restore session-42 --campaign spring
```
@@ -38,11 +44,36 @@ on both sides and reports the native engine change under the spring profile.
The application input check requires `--limit=0` when `--campaign` is supplied.
Catalogs use the same selection-aware loader: the prompt catalog includes
`briefing` version `1`, and the profile catalog includes the selected `autumn`
profile. The example's shared run cache keys successful results by the complete
supplied configuration/overlay selection and the supplied campaign, including
presence. The campaign override is applied through ConfigKit before loading.
These are choices for this example's loader and do not define a CommandKit cache
policy.
profile. Prompt inspection uses an ID only; its optional version is descriptive
metadata in the report, not a selector. The synthetic `field-notes` collection
provides one backend, profile, and prompt for collection discovery and native
namespace filtering. The example's shared run cache keys successful results by
the complete supplied configuration/overlay selection and the supplied
campaign, including presence. The campaign override is applied through ConfigKit
before loading. These are choices for this example's loader and do not define a
CommandKit cache policy.
Smoke testing is explicitly wired with `ckprompt.WithSmokeTesting` and its
optional request builder is nil, so CommandKit forwards the selected native
request. Applications that need to adjust the request can provide a typed
builder that starts with the seed and returns the chosen native request:
```go
definitions = ckprompt.WithSmokeTesting(definitions, loadEngine,
func(ctx context.Context, seed ckprompt.SmokeRequest, input *inspectionInput, state *runCache) (promptkit.SmokeTestRequest, error) {
request := seed.Request
request.ProfileID = "spring"
return request, nil
})
```
The example injects a small in-memory `promptkit.LLMClient` through its shared
run state. Catalog, inspection, and requirements commands do not call it;
inference smoke commands do. No model service or credentials are required.
Native HTTP checks may retain unsupported or not-applicable observations because
the example does not configure a network probe. An aggregate smoke command can
return an operational outcome for a native diagnostic while still delivering
the complete aggregate report.
The first requirements command reports incomplete discovery: PromptKit records
the conditional `notes` input and a missing `mode` issue. Supplying `mode=full`

View File

@@ -40,6 +40,18 @@ type applicationCacheKey struct {
// chooses to pass it to its loaders.
type runCache struct {
applications map[applicationCacheKey]*configkit.Result[appConfiguration]
llmClient promptkit.LLMClient
}
type exampleLLMClient struct {
calls *int
}
func (client *exampleLLMClient) Generate(context.Context, promptkit.GenerateRequest) (*promptkit.GenerateResponse, error) {
if client.calls != nil {
(*client.calls)++
}
return &promptkit.GenerateResponse{Content: "Example response."}, nil
}
type restoreInput struct {
@@ -110,6 +122,20 @@ func loadPromptEngine(ctx context.Context, selection ckconfig.Selection, input *
return nil, err
}
engineConfig := configkit.Mapping("campaign "+name, map[string]any{
"collections": map[string]any{
"field-notes": map[string]any{
"release_version": "1",
"backends": map[string]any{"demo": map[string]any{"endpoint": "https://example.invalid/v1"}},
"profiles": map[string]any{"assistant": map[string]any{"backend": "field-notes/demo", "model": "example-model"}},
"prompts": map[string]any{"briefing": map[string]any{
"version": "1",
"default_profile": "field-notes/assistant",
"inputs": []any{map[string]any{"name": "topic", "required": true, "content_type": "text/plain", "description": "Topic to brief"}},
"messages": []any{map[string]any{"role": "user", "content": "Write a concise briefing about {{.topic}}."}},
"output": map[string]any{"format": "text", "validation_mode": "none"},
}},
},
},
"profiles": map[string]any{chosen.ProfileID: map[string]any{
"endpoint": "https://example.invalid/v1",
"model": chosen.Model,
@@ -125,7 +151,11 @@ func loadPromptEngine(ctx context.Context, selection ckconfig.Selection, input *
"output": map[string]any{"format": "text", "validation_mode": "none"},
}},
})
return promptkit.NewEngine(promptkit.Config{Sources: promptkit.ConfigurationSources{Main: &configkit.Input{Source: engineConfig}}})
var client promptkit.LLMClient = &exampleLLMClient{}
if cache != nil && cache.llmClient != nil {
client = cache.llmClient
}
return promptkit.NewEngine(promptkit.Config{Sources: promptkit.ConfigurationSources{Main: &configkit.Input{Source: engineConfig}}}, promptkit.WithLLMClient(client))
}
func selectedCampaign(configuration appConfiguration, supplied commandkit.Supplied[string]) (string, campaign, error) {
@@ -166,11 +196,18 @@ func buildValidationRequest(ctx context.Context, seed ckprompt.ValidationRequest
}
func newApp() (*commandkit.App, error) {
return newAppWithLLMClient(&exampleLLMClient{})
}
func newAppWithLLMClient(client promptkit.LLMClient) (*commandkit.App, error) {
if client == nil {
client = &exampleLLMClient{}
}
limitDefault := 0
limitFlag := commandkit.ValueFlag(commandkit.FlagMeta{Name: "limit", Usage: "Override the application item limit."}, &limitDefault, strconv.Atoi,
func(input **inspectionInput, value commandkit.Supplied[int]) { (*input).Limit = value })
inputFactory := func() *inspectionInput { return &inspectionInput{} }
stateFactory := func() *runCache { return &runCache{} }
stateFactory := func() *runCache { return &runCache{llmClient: client} }
appScope := ckconfig.FromConfigKit("app", "Application settings.", loadApplicationConfig)
engineScope := ckprompt.ConfigScope(loadPromptEngine)
@@ -195,6 +232,7 @@ func newApp() (*commandkit.App, error) {
definitions.NewState = stateFactory
definitions.Selectors = []commandkit.Flag[*inspectionInput]{campaignSelector()}
definitions = ckprompt.WithRequestValidation(definitions, loadPromptEngine, buildValidationRequest)
definitions = ckprompt.WithSmokeTesting(definitions, loadPromptEngine, nil)
definitionCommand := ckprompt.Command(definitions)
store := map[string]session{

View File

@@ -311,6 +311,45 @@ func TestPromptKitScopeDiffAndCatalogsUseSelectedCampaign(t *testing.T) {
}
}
func TestComposedCatalogsAndSmokeUseInjectedClientOnlyForInference(t *testing.T) {
calls := 0
app, err := newAppWithLLMClient(&exampleLLMClient{calls: &calls})
if err != nil {
t.Fatal(err)
}
commands := [][]string{
{"promptkit", "list", "backends", "--campaign", "spring"},
{"promptkit", "list", "namespaces", "--campaign", "spring"},
{"promptkit", "list", "collections", "--campaign", "spring"},
{"promptkit", "list", "prompts", "--namespace", "field-notes", "--campaign", "spring"},
{"promptkit", "show", "prompt", "briefing", "--campaign", "spring"},
{"promptkit", "requirements", "show", "briefing", "--campaign", "spring"},
}
for _, args := range commands {
var output bytes.Buffer
outcome := app.Execute(context.Background(), args, commandkit.Streams{Out: &output, Err: io.Discard})
if outcome.Kind != commandkit.OutcomeSuccess {
t.Errorf("metadata command %q outcome = %#v; output %q", args, outcome, output.String())
}
if output.Len() == 0 {
t.Errorf("metadata command %q produced no report", args)
}
}
if calls != 0 {
t.Fatalf("metadata and requirements commands invoked the LLM client %d times", calls)
}
var output bytes.Buffer
outcome := app.Execute(context.Background(), []string{"promptkit", "test", "all", "--campaign", "spring", "--prompt", "briefing", "--profile", "spring"}, commandkit.Streams{Out: &output, Err: io.Discard})
if output.Len() == 0 || !bytes.Contains(output.Bytes(), []byte("tests:")) {
t.Fatalf("aggregate smoke report missing: outcome=%#v output=%q", outcome, output.String())
}
if calls == 0 {
t.Fatalf("smoke command did not use the injected LLM client: outcome=%#v output=%q", outcome, output.String())
}
}
func composedReportValue(t *testing.T, data []byte, category string, fields ...string) *yaml.Node {
t.Helper()
var document yaml.Node