jaakko/agentic-studio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

CodeBench: kierroskohtainen output-dir + tiivistetty Go golden example

Browse Source 
- runPipeline saa round-parametrin, dir: model__scenario__r1, __r2 jne.
- todo-go.md testit 6→4 (poistettu list+update toisteiset), 466→370 riviä
This commit is contained in:
jaakko
2026-04-14 20:57:50 +03:00
parent 01364b7031
commit 8fc31f2a53
2 changed files with 16 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
kipina-codebench/benchmark.mjs
View File

@@ -308,7 +308,7 @@ function starsForScore(score) {
}
// === Pipeline: yhdelle mallille ja skenaariolle ===
async function runPipeline(model, scenario) {
async function runPipeline(model, scenario, round = 1) {
const result = {
model, scenario: scenario.id,
reqOk: false, specOk: false, specEntities: 0,
@@ -321,7 +321,8 @@ async function runPipeline(model, scenario) {
};
const timings = [];
const { system: CODE_SYSTEM, promptName, profile } = getCodePromptForModel(model);
const dir = `${OUTPUT_DIR}/${model.replace(/[/:]/g, '_')}__${scenario.id}`;
const roundSuffix = ROUNDS > 1 ? `__r${round}` : '';
const dir = `${OUTPUT_DIR}/${model.replace(/[/:]/g, '_')}__${scenario.id}${roundSuffix}`;
mkdirSync(dir, { recursive: true });
try {
@@ -651,7 +652,7 @@ async function main() {
for (const scenario of scenarios) {
const roundLabel = ROUNDS > 1 ? ` [${round}/${ROUNDS}]` : '';
console.log(`\n━━━ ${model} × ${scenario.id}${roundLabel} ━━━`);
const r = await runPipeline(model, scenario);
const r = await runPipeline(model, scenario, round);
if (ROUNDS > 1) r.round = round;
results.push(r);

117
kipina-codebench/golden-examples/todo-go.md
View File

@@ -302,16 +302,13 @@ import (
"net/http/httptest"
"strings"
"testing"
_ "modernc.org/sqlite"
)
func setupTestServer(t *testing.T) (*httptest.Server, *sql.DB) {
t.Helper()
db, err := sql.Open("sqlite", ":memory:")
if err != nil {
t.Fatal(err)
}
if err != nil { t.Fatal(err) }
InitDB(db)
return httptest.NewServer(NewRouter(db)), db
}
@@ -320,147 +317,57 @@ func TestCreateTodo(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
resp, err := http.Post(ts.URL+"/todos", "application/json",
strings.NewReader(`{"title":"Buy groceries","priority":2}`))
if err != nil {
t.Fatal(err)
}
if err != nil { t.Fatal(err) }
defer resp.Body.Close()
if resp.StatusCode != http.StatusCreated {
t.Fatalf("expected 201, got %d", resp.StatusCode)
}
if resp.StatusCode != http.StatusCreated { t.Fatalf("expected 201, got %d", resp.StatusCode) }
var body map[string]interface{}
json.NewDecoder(resp.Body).Decode(&body)
if body["title"] != "Buy groceries" {
t.Fatalf("expected title 'Buy groceries', got %v", body["title"])
}
if body["id"] == nil {
t.Fatal("expected id to be present")
}
}
func TestListTodos(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
http.Post(ts.URL+"/todos", "application/json",
strings.NewReader(`{"title":"Listable task"}`))
resp, err := http.Get(ts.URL + "/todos")
if err != nil {
t.Fatal(err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Fatalf("expected 200, got %d", resp.StatusCode)
}
var body []map[string]interface{}
json.NewDecoder(resp.Body).Decode(&body)
if len(body) < 1 {
t.Fatal("expected at least 1 todo")
}
if body["title"] != "Buy groceries" { t.Fatalf("expected 'Buy groceries', got %v", body["title"]) }
if body["id"] == nil { t.Fatal("expected id") }
}
func TestGetTodoByID(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
resp, _ := http.Post(ts.URL+"/todos", "application/json",
strings.NewReader(`{"title":"Fetchable task"}`))
var created map[string]interface{}
json.NewDecoder(resp.Body).Decode(&created)
resp.Body.Close()
id := created["id"].(float64)
resp, err := http.Get(ts.URL + "/todos/" + fmt.Sprintf("%.0f", id))
if err != nil {
t.Fatal(err)
}
resp, _ = http.Get(ts.URL + "/todos/" + fmt.Sprintf("%.0f", id))
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Fatalf("expected 200, got %d", resp.StatusCode)
}
var body map[string]interface{}
json.NewDecoder(resp.Body).Decode(&body)
if body["id"] != id {
t.Fatalf("expected id %.0f, got %v", id, body["id"])
}
if resp.StatusCode != http.StatusOK { t.Fatalf("expected 200, got %d", resp.StatusCode) }
}
func TestGetTodoNotFound(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
resp, err := http.Get(ts.URL + "/todos/99999")
if err != nil {
t.Fatal(err)
}
resp, _ := http.Get(ts.URL + "/todos/99999")
defer resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Fatalf("expected 404, got %d", resp.StatusCode)
}
}
func TestUpdateTodo(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
resp, _ := http.Post(ts.URL+"/todos", "application/json",
strings.NewReader(`{"title":"Old title"}`))
var created map[string]interface{}
json.NewDecoder(resp.Body).Decode(&created)
resp.Body.Close()
id := created["id"].(float64)
req, _ := http.NewRequest(http.MethodPut, ts.URL+"/todos/"+fmt.Sprintf("%.0f", id),
strings.NewReader(`{"title":"New title"}`))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatal(err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Fatalf("expected 200, got %d", resp.StatusCode)
}
var body map[string]interface{}
json.NewDecoder(resp.Body).Decode(&body)
if body["title"] != "New title" {
t.Fatalf("expected 'New title', got %v", body["title"])
}
if resp.StatusCode != http.StatusNotFound { t.Fatalf("expected 404, got %d", resp.StatusCode) }
}
func TestDeleteTodo(t *testing.T) {
ts, db := setupTestServer(t)
defer ts.Close()
defer db.Close()
resp, _ := http.Post(ts.URL+"/todos", "application/json",
strings.NewReader(`{"title":"Deletable task"}`))
var created map[string]interface{}
json.NewDecoder(resp.Body).Decode(&created)
resp.Body.Close()
id := created["id"].(float64)
req, _ := http.NewRequest(http.MethodDelete, ts.URL+"/todos/"+fmt.Sprintf("%.0f", id), nil)
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatal(err)
}
resp, _ = http.DefaultClient.Do(req)
defer resp.Body.Close()
if resp.StatusCode != http.StatusNoContent {
t.Fatalf("expected 204, got %d", resp.StatusCode)
}
if resp.StatusCode != http.StatusNoContent { t.Fatalf("expected 204, got %d", resp.StatusCode) }
resp, _ = http.Get(ts.URL + "/todos/" + fmt.Sprintf("%.0f", id))
defer resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Fatalf("expected 404 after delete, got %d", resp.StatusCode)
}
if resp.StatusCode != http.StatusNotFound { t.Fatalf("expected 404 after delete, got %d", resp.StatusCode) }
}
```