secert updated

controllers/assistantController.go

@@ -112,6 +112,13 @@ func (ctl *AssistantController) Ask(c *fiber.Ctx) error {
 		if errors.As(err, &tooFast) {
 			return assistantRefuse(c, http.StatusTooManyRequests, err.Error())
 		}
+		// The provider's quota, as opposed to our own limiter above. Same status
+		// for the same reason — it is not a bad question, it is a busy minute —
+		// and the message is ours rather than Groq's, which names our billing
+		// account and the tokens-per-minute arithmetic behind it.
+		if errors.Is(err, utils.ErrBusy) {
+			return assistantRefuse(c, http.StatusTooManyRequests, utils.ErrBusy.Error())
+		}
 		return assistantRefuse(c, http.StatusBadRequest, err.Error())
 	}
 

controllers/assistantHTTP_test.go

@@ -3,9 +3,9 @@ package controllers
 import (
 	"context"
 	"encoding/json"
+	"hash/crc32"
 	"io"
 	"net/http/httptest"
-	"os"
 	"strconv"
 	"strings"
 	"testing"
@@ -179,9 +179,24 @@ func buildApp(t *testing.T, chat utils.Chat) (*fiber.App, *fakeShop) {
 	return app, shop
 }
 
+// webSession mints a session for THIS test's own user.
+//
+// One user id across the file put every test in one rate-limit bucket — six
+// questions and then 429 for ten seconds — so the suite passed test by test and
+// failed when run together, which is the worst way round: green locally, red in
+// CI, and the failure blamed on the model.
+//
+// A per-test user is also the truthful shape. The limiter is per person, and
+// two tests are two people.
 func webSession(t *testing.T) string {
 	t.Helper()
-	token, _, err := utils.MintWebToken(testCaller, time.Now())
+
+	claims := testCaller
+	// Stable across runs and distinct per test, so a failure names the same
+	// user every time. The fakes key on tenant, never on this.
+	claims.Userid = testCaller.Userid + int(crc32.ChecksumIEEE([]byte(t.Name()))%10_000)
+
+	token, _, err := utils.MintWebToken(claims, time.Now())
 	if err != nil {
 		t.Fatalf("minting a session: %v", err)
 	}
@@ -306,20 +321,9 @@ func TestStatusNamesTheMissingVariable(t *testing.T) {
 func liveHTTPChat(t *testing.T) utils.Chat {
 	t.Helper()
 
-	// Defaults exactly as production does, so this proves three variables are
-	// enough rather than working around the question.
-	provider := strings.ToLower(strings.TrimSpace(os.Getenv("ASSISTANT_PROVIDER")))
-	model := strings.TrimSpace(os.Getenv("ASSISTANT_MODEL"))
-	if provider == "" && model != "" {
-		provider = "openai"
-	}
-
-	cfg := config.AssistantConfig{
-		Provider: provider,
-		BaseURL:  os.Getenv("ASSISTANT_BASE_URL"),
-		APIKey:   os.Getenv("ASSISTANT_API_KEY"),
-		Balanced: model,
-	}
+	// Read exactly as production reads it, so this proves the shipped defaults
+	// work rather than quietly testing a configuration of its own.
+	cfg := config.AssistantFromEnv()
 	if !cfg.Enabled() {
 		t.Skipf("no model configured: %s", cfg.Why())
 	}