Enable prompt preview validation and smoke commands

This commit is contained in:
2026-11-10 16:59:28 +00:00
parent 8cc298d092
commit 8e1e073731
4 changed files with 184 additions and 37 deletions

View File

@@ -3,11 +3,13 @@ package cli
import (
"context"
"fmt"
"net/http"
"reflect"
"strings"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/config"
"gitea.maximumdirect.net/eric/audita/v3/internal/framework/llm"
"gitea.maximumdirect.net/eric/audita/v3/internal/prompts"
"go.maximumdirect.net/ckconfig"
"go.maximumdirect.net/ckprompt"
commandkit "go.maximumdirect.net/commandkit"
@@ -16,7 +18,10 @@ import (
"go.maximumdirect.net/releasekit/buildinfo"
)
type invocationState struct{ engines []engineEntry }
type invocationState struct {
engines []engineEntry
client *http.Client
}
type engineEntry struct {
selection ckconfig.Selection
engine *pk.Engine
@@ -50,7 +55,11 @@ func loadPromptEngine(ctx context.Context, selection ckconfig.Selection, input s
if err != nil {
return nil, err
}
runtime, err := llm.NewRuntime(ctx, loaded, nil)
var client *http.Client
if state != nil {
client = state.client
}
runtime, err := llm.NewRuntime(ctx, loaded, client)
if err != nil {
return nil, err
}
@@ -61,14 +70,37 @@ func loadPromptEngine(ctx context.Context, selection ckconfig.Selection, input s
}
func buildApplication(extra ...commandkit.Declaration) (*commandkit.App, error) {
return buildApplicationWithClient(nil, extra...)
}
func buildApplicationWithClient(client *http.Client, extra ...commandkit.Declaration) (*commandkit.App, error) {
appScope := ckconfig.FromConfigKit("app", "Audita application settings.", loadApplication)
appScope.Features.Overrides = true
promptScope := ckprompt.ConfigScope(loadPromptEngine)
configCommand := ckconfig.Command(ckconfig.Suite[struct{}, *invocationState]{NewState: func() *invocationState { return &invocationState{} }, Scopes: []ckconfig.Scope[struct{}, *invocationState]{appScope, promptScope}})
configCommand := ckconfig.Command(ckconfig.Suite[struct{}, *invocationState]{NewState: func() *invocationState { return &invocationState{client: client} }, Scopes: []ckconfig.Scope[struct{}, *invocationState]{appScope, promptScope}})
definitions := ckprompt.WithNamespaces(ckprompt.FromEngine(loadPromptEngine), pk.Namespaces{})
definitions.NewState = func() *invocationState { return &invocationState{} }
definitions.NewState = func() *invocationState { return &invocationState{client: client} }
definitions = ckprompt.WithRequestValidation(definitions, loadPromptEngine, func(_ context.Context, seed ckprompt.ValidationRequest, _ struct{}, _ *invocationState) (pk.RunRequest, error) {
return applicationPromptRequest(seed.Request, seed.Namespaces), nil
})
definitions = ckprompt.WithRequestPreparation(definitions, loadPromptEngine, func(_ context.Context, seed ckprompt.PreparationRequest, _ struct{}, _ *invocationState) (pk.RunRequest, error) {
return applicationPromptRequest(seed.Request, seed.Namespaces), nil
})
definitions = ckprompt.WithSmokeTesting(definitions, loadPromptEngine, nil)
declarations := []commandkit.Declaration{configCommand, commandkit.Completion("audita"), processCommand()}
declarations = append(declarations, ckprompt.Declarations(definitions)...)
declarations = append(declarations, extra...)
return commandkit.New(commandkit.Identity{Name: "audita", Version: buildinfo.Version()}, declarations...)
}
// applicationPromptRequest supplies instructions only for Audita's maintained prompts.
func applicationPromptRequest(request pk.RunRequest, namespaces *pk.Namespaces) pk.RunRequest {
id := request.PromptID
if !strings.Contains(id, "/") && namespaces != nil && namespaces.Prompt != "" {
id = namespaces.Prompt + "/" + id
}
if _, ok := prompts.LookupMetadata(id); ok {
request.Vars = prompts.WithSharedVariables(request.Vars)
}
return request
}

View File

@@ -3,12 +3,16 @@ package cli
import (
"bytes"
"context"
"encoding/json"
"io"
"net/http"
"os"
"path/filepath"
"strings"
"testing"
commandkit "go.maximumdirect.net/commandkit"
pk "go.maximumdirect.net/promptkit"
)
func TestNativeConfigurationAndResourceCommands(t *testing.T) {
@@ -75,3 +79,118 @@ func TestExplicitEmptyConfigurationPathFails(t *testing.T) {
t.Fatal("explicit empty path accepted")
}
}
func TestRequestInspectionAndExplicitSmokeUseSameSources(t *testing.T) {
dir := t.TempDir()
file := filepath.Join(dir, "config.yml")
if err := os.WriteFile(file, []byte("version: 3\n"), 0644); err != nil {
t.Fatal(err)
}
resources := `backends:
- id: local
endpoint: https://example.invalid/v1
smoke_tests:
default_profile: fixture
authentication:
kind: none
profiles:
- id: fixture
backend: local
model: sample
collections:
audita:
prompts:
- id: modules.grammar.proposal
messages:
- role: user
content: 'Replacement {{.HardeningPolicy}} {{.SectionJSON}}'
output:
format: text
validation_mode: none
`
if err := os.WriteFile(filepath.Join(dir, "prompts.yml"), []byte(resources), 0644); err != nil {
t.Fatal(err)
}
calls := 0
client := &http.Client{Transport: roundTripFunc(func(req *http.Request) (*http.Response, error) {
calls++
body := `{}`
if req.Method == http.MethodPost {
requestBody, err := io.ReadAll(req.Body)
if err != nil {
t.Fatal(err)
}
content := "PROMPTKIT_OK"
if strings.Contains(string(requestBody), "response_format") {
content = `{"status":"ok"}`
}
encoded, err := json.Marshal(content)
if err != nil {
t.Fatal(err)
}
body = `{"model":"sample","choices":[{"message":{"content":` + string(encoded) + `}}]}`
}
return &http.Response{StatusCode: 200, Header: make(http.Header), Body: io.NopCloser(strings.NewReader(body)), Request: req}, nil
})}
app, err := buildApplicationWithClient(client)
if err != nil {
t.Fatal(err)
}
execute := func(args ...string) (commandkit.Outcome, string, string) {
t.Helper()
var out, stderr bytes.Buffer
result := app.Execute(context.Background(), args, commandkit.Streams{Out: &out, Err: &stderr})
return result, out.String(), stderr.String()
}
common := []string{"--config", file, "--llm-profile", "fixture"}
args := append([]string{"promptkit", "show", "prepared", "audita/modules.grammar.proposal"}, common...)
args = append(args, "--llm-var", "SectionJSON=[]", "--llm-var", "HardeningPolicy=custom-instruction")
outcome, out, stderr := execute(args...)
if outcome.Status != 0 || !strings.Contains(out, "Replacement custom-instruction") {
t.Fatalf("preview status=%d out=%q err=%q", outcome.Status, out, stderr)
}
args = append([]string{"promptkit", "requirements", "validate", "audita/validators.editorial_review"}, common...)
args = append(args, "--llm-var", `PayloadJSON=[{"correction_index":1,"original_segment_text":"teh cat","corrected_segment_text":"the cat"}]`, "--llm-var", "TranscriptDescriptionBlock=")
outcome, out, stderr = execute(args...)
if outcome.Status != 0 {
t.Fatalf("validator status=%d out=%q err=%q", outcome.Status, out, stderr)
}
validatorPreview := append([]string{"promptkit", "show", "prepared", "audita/validators.editorial_review"}, common...)
validatorPreview = append(validatorPreview, "--llm-var", `PayloadJSON=[{"correction_index":1,"original_segment_text":"teh cat","corrected_segment_text":"the cat"}]`, "--llm-var", "TranscriptDescriptionBlock=")
outcome, out, stderr = execute(validatorPreview...)
if outcome.Status != 0 || !strings.Contains(out, "teh cat") {
t.Fatalf("validator preview status=%d out=%q err=%q", outcome.Status, out, stderr)
}
if calls != 0 {
t.Fatalf("inspection made %d provider calls", calls)
}
outcome, out, stderr = execute("promptkit", "test", "reachability", "--config", file, "--llm-backend", "local")
if outcome.Status != 0 || calls == 0 {
t.Fatalf("smoke status=%d calls=%d out=%q err=%q", outcome.Status, calls, out, stderr)
}
previous := calls
outcome, out, stderr = execute("promptkit", "test", "all", "--config", file, "--llm-backend", "local", "--llm-profile", "fixture", "--format=json")
if outcome.Status != 0 || calls <= previous || !strings.Contains(out, "structured_output") || !strings.Contains(out, "text_inference") {
t.Fatalf("aggregate status=%d calls=%d out=%q err=%q", outcome.Status, calls, out, stderr)
}
}
type roundTripFunc func(*http.Request) (*http.Response, error)
func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) { return f(req) }
func TestRequestDefaultsRespectNamespaceAndCallerVariables(t *testing.T) {
request := pk.RunRequest{PromptID: "modules.grammar.proposal", Vars: map[string]string{"HardeningPolicy": "caller"}}
result := applicationPromptRequest(request, &pk.Namespaces{Prompt: "audita"})
if result.Vars["HardeningPolicy"] != "caller" || result.Vars["ProposalContract"] == "" {
t.Fatalf("variables=%v", result.Vars)
}
if _, changed := request.Vars["ProposalContract"]; changed {
t.Fatal("input variables mutated")
}
generic := pk.RunRequest{PromptID: "generic", Vars: map[string]string{"x": "y"}}
result = applicationPromptRequest(generic, nil)
if len(result.Vars) != 1 || result.Vars["x"] != "y" {
t.Fatalf("generic request changed: %v", result.Vars)
}
}