Define correction repair response and conversation replay
This commit is contained in:
150
internal/framework/llm/conversation_test.go
Normal file
150
internal/framework/llm/conversation_test.go
Normal file
@@ -0,0 +1,150 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.maximumdirect.net/eric/audita/v3/internal/core/config"
|
||||
"gitea.maximumdirect.net/eric/audita/v3/internal/framework/responseschema"
|
||||
ck "go.maximumdirect.net/configkit"
|
||||
pk "go.maximumdirect.net/promptkit"
|
||||
)
|
||||
|
||||
func TestNativeConversationReplayWithRepairContract(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
files := map[string]string{
|
||||
"config.yml": "version: 3\n",
|
||||
"prompts.yml": `profiles:
|
||||
- id: proposal-profile
|
||||
endpoint: https://example.invalid/v1
|
||||
model: proposal-model
|
||||
- id: repair-profile
|
||||
endpoint: https://example.invalid/v1
|
||||
model: repair-model
|
||||
prompts:
|
||||
- id: proposal-fixture
|
||||
messages:
|
||||
- role: system
|
||||
content: 'System {{.Subject}}'
|
||||
- role: user
|
||||
content: 'Proposal {{.Subject}}'
|
||||
output:
|
||||
format: json
|
||||
validation_mode: json_schema
|
||||
schema_path: correction_set.v1.json
|
||||
- id: repair-fixture
|
||||
messages:
|
||||
- role: user
|
||||
content: 'Repair {{.Finding}}'
|
||||
output:
|
||||
format: text
|
||||
validation_mode: none
|
||||
`,
|
||||
}
|
||||
for name, content := range files {
|
||||
if err := os.WriteFile(filepath.Join(dir, name), []byte(content), 0644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
loaded, err := config.Load(ck.Input{Source: ck.File(filepath.Join(dir, "config.yml"))}, "")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var requests []struct {
|
||||
Model string `json:"model"`
|
||||
Messages []struct{ Role, Content string } `json:"messages"`
|
||||
ResponseFormat map[string]any `json:"response_format"`
|
||||
}
|
||||
outputs := []string{`{"corrections":[]}`, `{"proposal_ref":1,"action":"revise","correction":{"id":1,"original_text":" ","corrected_text":"","confidence":0.8}}`, `{"proposal_ref":1,"action":"withdraw","correction":null}`}
|
||||
transport := transportFunc(func(r *http.Request) (*http.Response, error) {
|
||||
var request struct {
|
||||
Model string `json:"model"`
|
||||
Messages []struct{ Role, Content string } `json:"messages"`
|
||||
ResponseFormat map[string]any `json:"response_format"`
|
||||
}
|
||||
if err := json.NewDecoder(r.Body).Decode(&request); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
requests = append(requests, request)
|
||||
content, _ := json.Marshal(outputs[len(requests)-1])
|
||||
body := fmt.Sprintf(`{"model":%q,"choices":[{"message":{"content":%s}}]}`, request.Model, content)
|
||||
return &http.Response{StatusCode: 200, Header: make(http.Header), Body: io.NopCloser(strings.NewReader(body)), Request: r}, nil
|
||||
})
|
||||
runtime, err := NewRuntime(context.Background(), loaded, &http.Client{Transport: transport})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ctx := context.Background()
|
||||
base := pk.RunRequest{PromptID: "proposal-fixture", ProfileID: "proposal-profile", Vars: map[string]string{"Subject": "source"}}
|
||||
original, err := runtime.Engine.PrepareExecution(ctx, base)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
prefix := original.Details().Messages
|
||||
initial, err := runtime.Engine.RunPrepared(ctx, original)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
suffix := []pk.RenderedMessage{{Role: pk.RoleAssistant, Content: initial.RawOutput}}
|
||||
contract, err := OutputContract(responseschema.CorrectionRepairKey, 0)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, finding := range []string{"first", "second"} {
|
||||
instruction, err := runtime.Engine.Prepare(ctx, pk.RunRequest{PromptID: "repair-fixture", ProfileID: "repair-profile", Vars: map[string]string{"Finding": finding}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
suffix = append(suffix, instruction.Messages...)
|
||||
req := base
|
||||
req.ProfileID = "repair-profile"
|
||||
req.AppendedMessages = suffix
|
||||
req.Validation = contract
|
||||
handle, err := runtime.Engine.PrepareExecution(ctx, req)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
details := handle.Details()
|
||||
if !reflect.DeepEqual(details.Messages[:len(prefix)], prefix) || !reflect.DeepEqual(details.Messages[len(prefix):], suffix) {
|
||||
t.Fatalf("prepared conversation = %#v", details.Messages)
|
||||
}
|
||||
result, err := runtime.Engine.RunPrepared(ctx, handle)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !result.Validation.IsValid {
|
||||
t.Fatalf("invalid result: %+v", result.Validation)
|
||||
}
|
||||
suffix = append(suffix, pk.RenderedMessage{Role: pk.RoleAssistant, Content: result.RawOutput})
|
||||
}
|
||||
if len(requests) != 3 || requests[0].Model != "proposal-model" || requests[1].Model != "repair-model" || requests[2].Model != "repair-model" {
|
||||
t.Fatalf("models: %+v", requests)
|
||||
}
|
||||
for i, wantLen := range []int{2, 4, 6} {
|
||||
req := requests[i]
|
||||
if len(req.Messages) != wantLen {
|
||||
t.Fatalf("request %d messages: %+v", i, req.Messages)
|
||||
}
|
||||
for j, message := range req.Messages {
|
||||
if message.Role != string(append(prefix, suffix...)[j].Role) || message.Content != append(prefix, suffix...)[j].Content {
|
||||
t.Fatalf("request %d message %d: %+v", i, j, message)
|
||||
}
|
||||
}
|
||||
encoded, _ := json.Marshal(req.ResponseFormat)
|
||||
expected := "corrections"
|
||||
if i > 0 {
|
||||
expected = "proposal_ref"
|
||||
}
|
||||
if !strings.Contains(string(encoded), expected) {
|
||||
t.Fatalf("request %d contract: %s", i, encoded)
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user