Maven/internal/vision/vision_test.go

package vision

import (
	"bytes"
	"context"
	"encoding/json"
	"errors"
	"image"
	"image/png"
	"io"
	"net/http"
	"net/http/httptest"
	"strings"
	"sync/atomic"
	"testing"
	"time"

	"github.com/kami/maven/internal/media"
)

func testImage(t *testing.T) media.Image {
	t.Helper()
	var buf bytes.Buffer
	if err := png.Encode(&buf, image.NewRGBA(image.Rect(0, 0, 32, 32))); err != nil {
		t.Fatal(err)
	}
	im, err := media.PrepareImage(buf.Bytes(), "test", 32)
	if err != nil {
		t.Fatal(err)
	}
	return im
}

func TestDisabledAlwaysRefuses(t *testing.T) {
	_, err := Disabled{}.Describe(context.Background(), testImage(t), "что тут?")
	if !errors.Is(err, ErrDisabled) {
		t.Fatalf("got %v, want ErrDisabled", err)
	}
}

// The whole reason this package has its own HTTP client instead of reusing
// internal/llm.Client: a vision endpoint that is not on this box is refused.
func TestNewLocalRefusesNonPrivateEndpoints(t *testing.T) {
	bad := []string{
		"https://api.openai.com",
		"http://8.8.8.8:8080",
		"https://vision.example.com", // a name could resolve anywhere
		"ftp://127.0.0.1:8080",       // wrong scheme
		"",                           // nothing to talk to
	}
	for _, ep := range bad {
		if _, err := NewLocal(Config{Endpoint: ep}); err == nil {
			t.Errorf("NewLocal(%q) was accepted", ep)
		}
	}
}

func TestNewLocalAcceptsLocalEndpoints(t *testing.T) {
	for _, ep := range []string{"http://127.0.0.1:8081", "http://localhost:8081/", "http://192.168.1.104:8081", "http://[::1]:8081"} {
		p, err := NewLocal(Config{Endpoint: ep})
		if err != nil {
			t.Errorf("NewLocal(%q): %v", ep, err)
			continue
		}
		if strings.HasSuffix(p.Endpoint(), "/") {
			t.Errorf("trailing slash kept: %q", p.Endpoint())
		}
	}
}

func TestDescribeSendsImageAsDataURIAndReturnsText(t *testing.T) {
	var gotBody map[string]any
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		if r.URL.Path != "/v1/chat/completions" {
			t.Errorf("path = %s", r.URL.Path)
		}
		raw, _ := io.ReadAll(r.Body)
		if err := json.Unmarshal(raw, &gotBody); err != nil {
			t.Errorf("unmarshal request: %v", err)
		}
		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"  На картинке кот  "}}]}`))
	}))
	defer srv.Close()

	p, err := NewLocal(Config{Endpoint: srv.URL, Model: "qwen-vl"})
	if err != nil {
		t.Fatal(err)
	}
	text, err := p.Describe(context.Background(), testImage(t), "кто на фото?")
	if err != nil {
		t.Fatalf("describe: %v", err)
	}
	if text != "На картинке кот" {
		t.Errorf("text = %q (should be trimmed)", text)
	}

	msgs, ok := gotBody["messages"].([]any)
	if !ok || len(msgs) != 1 {
		t.Fatalf("messages = %#v", gotBody["messages"])
	}
	parts, ok := msgs[0].(map[string]any)["content"].([]any)
	if !ok || len(parts) != 2 {
		t.Fatalf("content parts = %#v", msgs[0])
	}
	if got := parts[0].(map[string]any)["text"]; got != "кто на фото?" {
		t.Errorf("prompt = %v", got)
	}
	url := parts[1].(map[string]any)["image_url"].(map[string]any)["url"].(string)
	if !strings.HasPrefix(url, "data:image/jpeg;base64,") {
		t.Errorf("image not sent as a jpeg data uri: %.40s", url)
	}
}

func TestDescribeUsesDefaultPromptWhenNoQuestion(t *testing.T) {
	var sentPrompt string
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		var body struct {
			Messages []struct {
				Content []struct {
					Text string `json:"text"`
				} `json:"content"`
			} `json:"messages"`
		}
		_ = json.NewDecoder(r.Body).Decode(&body)
		sentPrompt = body.Messages[0].Content[0].Text
		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"ок"}}]}`))
	}))
	defer srv.Close()

	p, err := NewLocal(Config{Endpoint: srv.URL, Prompt: "Опиши по-русски."})
	if err != nil {
		t.Fatal(err)
	}
	if _, err := p.Describe(context.Background(), testImage(t), "   "); err != nil {
		t.Fatal(err)
	}
	if sentPrompt != "Опиши по-русски." {
		t.Errorf("prompt = %q", sentPrompt)
	}
}

// A Thinking model sometimes leaves content empty and puts the answer in
// reasoning_content; internal/llm has the same fallback and vision needs it too.
func TestDescribeFallsBackToReasoningContent(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","reasoning_content":"схема платы"}}]}`))
	}))
	defer srv.Close()
	p, _ := NewLocal(Config{Endpoint: srv.URL})
	text, err := p.Describe(context.Background(), testImage(t), "")
	if err != nil {
		t.Fatal(err)
	}
	if text != "схема платы" {
		t.Errorf("text = %q", text)
	}
}

func TestDescribeErrors(t *testing.T) {
	t.Run("no choices", func(t *testing.T) {
		srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
			_, _ = w.Write([]byte(`{"choices":[]}`))
		}))
		defer srv.Close()
		p, _ := NewLocal(Config{Endpoint: srv.URL})
		if _, err := p.Describe(context.Background(), testImage(t), ""); !errors.Is(err, ErrEmptyReply) {
			t.Errorf("got %v, want ErrEmptyReply", err)
		}
	})
	t.Run("server error", func(t *testing.T) {
		srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
			w.WriteHeader(http.StatusInternalServerError)
		}))
		defer srv.Close()
		p, _ := NewLocal(Config{Endpoint: srv.URL})
		if _, err := p.Describe(context.Background(), testImage(t), ""); err == nil {
			t.Error("500 was not an error")
		}
	})
	t.Run("empty image", func(t *testing.T) {
		p, _ := NewLocal(Config{Endpoint: "http://127.0.0.1:1"})
		if _, err := p.Describe(context.Background(), media.Image{}, ""); !errors.Is(err, media.ErrEmpty) {
			t.Errorf("got %v, want media.ErrEmpty", err)
		}
	})
	t.Run("context cancelled", func(t *testing.T) {
		srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
			time.Sleep(200 * time.Millisecond)
			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"поздно"}}]}`))
		}))
		defer srv.Close()
		p, _ := NewLocal(Config{Endpoint: srv.URL})
		ctx, cancel := context.WithTimeout(context.Background(), 10*time.Millisecond)
		defer cancel()
		if _, err := p.Describe(ctx, testImage(t), ""); err == nil {
			t.Error("cancelled context returned no error")
		}
	})
}

// checkPrivate validates the configured literal and used to validate nothing
// else. A 302 from the local llama-server would have sent the photo, as a data
// URI in the POST body, wherever the redirect named.
func TestLocalProviderDoesNotFollowARedirect(t *testing.T) {
	var elsewhere int32
	away := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		atomic.AddInt32(&elsewhere, 1)
		_, _ = io.WriteString(w, `{"choices":[{"message":{"content":"leaked"}}]}`)
	}))
	defer away.Close()
	local := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		http.Redirect(w, r, away.URL+"/v1/chat/completions", http.StatusFound)
	}))
	defer local.Close()

	p, err := NewLocal(Config{Endpoint: local.URL})
	if err != nil {
		t.Fatal(err)
	}
	im := media.Image{JPEG: []byte{0xFF, 0xD8, 0xFF}}
	if _, err := p.Describe(context.Background(), im, "что это"); err == nil {
		t.Fatal("a redirected describe must fail, not follow")
	}
	if n := atomic.LoadInt32(&elsewhere); n != 0 {
		t.Fatalf("the image was sent to the redirect target %d time(s)", n)
	}
}

// The reply is read through a cap. A stuck endpoint should not cost the daemon
// its memory.
func TestLocalProviderCapsTheReply(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		w.Header().Set("Content-Type", "application/json")
		_, _ = io.WriteString(w, `{"choices":[{"message":{"content":"`)
		for written := 0; written < MaxReplyBytes+(1<<20); written += 1 << 16 {
			if _, err := io.WriteString(w, strings.Repeat("a", 1<<16)); err != nil {
				return
			}
		}
	}))
	defer srv.Close()
	p, err := NewLocal(Config{Endpoint: srv.URL})
	if err != nil {
		t.Fatal(err)
	}
	im := media.Image{JPEG: []byte{0xFF, 0xD8, 0xFF}}
	if _, err := p.Describe(context.Background(), im, ""); err == nil {
		t.Fatal("an unbounded reply must fail rather than being read whole")
	}
}

// ValidateEndpoint is what config calls at startup, and it must agree with the
// constructor.
func TestValidateEndpointMatchesTheConstructor(t *testing.T) {
	for _, raw := range []string{"http://127.0.0.1:8081", "http://localhost:8081/"} {
		if err := ValidateEndpoint(raw); err != nil {
			t.Errorf("ValidateEndpoint(%q) = %v", raw, err)
		}
	}
	for _, raw := range []string{"http://8.8.8.8:8081", "http://vision.example.com", "ftp://127.0.0.1"} {
		if err := ValidateEndpoint(raw); err == nil {
			t.Errorf("ValidateEndpoint(%q) accepted a non-private endpoint", raw)
		}
		if _, err := NewLocal(Config{Endpoint: raw}); err == nil {
			t.Errorf("NewLocal(%q) accepted what ValidateEndpoint should refuse", raw)
		}
	}
}