package gateway

import (
	"context"
	"encoding/base64"
	"net/http"
	"strings"
	"testing"

	"git.yeij.top/AskaEth/Cyrene_v2/internal/auth"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/multimodal/voice"
)

// audioStubVoice 是一个 VoiceService，为 REST /api/v1/audio/* handler
// 测试返回固定的 STT/TTS 结果。
type audioStubVoice struct {
	sttText   string
	sttErr    error
	ttsAudio  voice.Audio
	ttsErr    error
	gotAudio  voice.Audio
	gotText   string
	sttCalled bool
	ttsCalled bool

	cloneVoiceID string
	cloneErr     error
	cloneCalled  bool
	gotCloneURL  string
	gotClonePfx  string
	gotInstr     string
}

func (s *audioStubVoice) STT(ctx context.Context, audio voice.Audio) (string, error) {
	s.sttCalled = true
	s.gotAudio = audio
	return s.sttText, s.sttErr
}

func (s *audioStubVoice) TTS(ctx context.Context, text string) (voice.Audio, error) {
	s.ttsCalled = true
	s.gotText = text
	s.gotInstr = voice.TTSInstructionFromContext(ctx)
	return s.ttsAudio, s.ttsErr
}

func (s *audioStubVoice) CloneVoice(ctx context.Context, referenceURL, prefix string) (string, error) {
	s.cloneCalled = true
	s.gotCloneURL = referenceURL
	s.gotClonePfx = prefix
	return s.cloneVoiceID, s.cloneErr
}

// PrimaryActive 让本替身**实现**网关的 `personaVoice` 扩展并报告"按 persona 选发音
// 的那一级正在生效"（复审 r3 P2-2）。
//
// 🔴 它存在是为了让"关闭态不查库"那条用例的变异**真能打红**：此前 `audioStubVoice`
// 不实现 `PrimaryActive`，于是拦下 persona 读取的只有 `s.voice.(personaVoice)` 这个
// **类型断言**，把 `&& pv.PrimaryActive()` 摘掉用例照样绿 —— 等于那条变异没被覆盖。
// 现在类型断言会通过，拦住它的只剩这个布尔值。要表达"未生效"的替身请用
// `inactivePersonaVoice`（`voice_emotiontts_test.go`）。
func (s *audioStubVoice) PrimaryActive() bool { return true }

func TestHandleTranscribe(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{sttText: "你好世界"}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/transcribe", map[string]any{
		"audio":  base64.StdEncoding.EncodeToString([]byte("raw")),
		"format": "wav",
	}, token)
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
	}
	if !sv.sttCalled {
		t.Fatal("STT not called")
	}
	if string(sv.gotAudio.Data) != "raw" || sv.gotAudio.Format != "wav" {
		t.Errorf("audio = %+v, want format wav / data raw", sv.gotAudio)
	}
	env2 := decodeBody(t, body)
	if got := string(env2["data"]); got == "" {
		t.Errorf("data envelope empty: %s", body)
	}
}

func TestHandleTranscribe_AuthRequired(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{sttText: "x"}
	env.srv.SetVoice(sv)

	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/transcribe", map[string]any{
		"audio": base64.StdEncoding.EncodeToString([]byte("raw")),
	}, "")
	if resp.StatusCode != http.StatusUnauthorized {
		t.Fatalf("status = %d, want 401 (body=%s)", resp.StatusCode, body)
	}
}

func TestHandleTranscribe_EmptyAudio(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{sttText: "x"}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/transcribe", map[string]any{
		"audio": base64.StdEncoding.EncodeToString([]byte("")),
	}, token)
	if resp.StatusCode != http.StatusBadRequest {
		t.Fatalf("status = %d, want 400 (body=%s)", resp.StatusCode, body)
	}
}

func TestHandleSpeech(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{ttsAudio: voice.Audio{Format: "wav", Data: []byte("audio-bytes")}}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
		"text": "你好",
	}, token)
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
	}
	if ct := resp.Header.Get("Content-Type"); ct != "audio/wav" {
		t.Errorf("Content-Type = %q, want audio/wav", ct)
	}
	if string(body) != "audio-bytes" {
		t.Errorf("body = %q, want audio-bytes", body)
	}
	if !sv.ttsCalled || sv.gotText != "你好" {
		t.Errorf("TTS got text = %q (called=%v), want 你好", sv.gotText, sv.ttsCalled)
	}
}

func TestHandleSpeech_EmptyText(t *testing.T) {
	env := newEnv(t, nil, false)
	env.srv.SetVoice(&audioStubVoice{})

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
		"text": "  ",
	}, token)
	if resp.StatusCode != http.StatusBadRequest {
		t.Fatalf("status = %d, want 400 (body=%s)", resp.StatusCode, body)
	}
}

func TestHandleSpeech_InstructionPassthrough(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{ttsAudio: voice.Audio{Format: "wav", Data: []byte("audio-bytes")}}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
		"text":        "你好，我是昔涟",
		"instruction": "语气开朗俏皮，像女朋友撒娇",
	}, token)
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
	}
	if !sv.ttsCalled {
		t.Fatal("TTS not called")
	}
	if sv.gotText != "你好，我是昔涟" {
		t.Errorf("TTS text = %q, want 你好，我是昔涟", sv.gotText)
	}
	if sv.gotInstr != "语气开朗俏皮，像女朋友撒娇" {
		t.Errorf("instruction threaded = %q, want the per-request instruction", sv.gotInstr)
	}
}

func TestHandleSpeech_NoInstruction(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{ttsAudio: voice.Audio{Format: "wav", Data: []byte("audio-bytes")}}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, _ := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
		"text": "你好",
	}, token)
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("status = %d, want 200", resp.StatusCode)
	}
	if sv.gotInstr != "" {
		t.Errorf("instruction = %q, want empty when not supplied", sv.gotInstr)
	}
}

func TestHandleVoiceClone(t *testing.T) {
	env := newEnv(t, nil, false)
	sv := &audioStubVoice{cloneVoiceID: "cosyvoice-v3-flash-cyrene-abc123"}
	env.srv.SetVoice(sv)

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
		"url":    "https://example.com/ref.wav",
		"prefix": "xilian",
	}, token)
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
	}
	if !sv.cloneCalled {
		t.Fatal("CloneVoice not called")
	}
	if sv.gotCloneURL != "https://example.com/ref.wav" || sv.gotClonePfx != "xilian" {
		t.Errorf("clone url/prefix = %q / %q, want the request values", sv.gotCloneURL, sv.gotClonePfx)
	}
	env2 := decodeBody(t, body)
	if got := string(env2["data"]); got == "" {
		t.Errorf("data envelope empty: %s", body)
	}
	if !strings.Contains(string(env2["data"]), "cosyvoice-v3-flash-cyrene-abc123") {
		t.Errorf("voiceId missing: %s", body)
	}
}

func TestHandleVoiceClone_AuthRequired(t *testing.T) {
	env := newEnv(t, nil, false)
	env.srv.SetVoice(&audioStubVoice{})

	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
		"url": "https://example.com/ref.wav",
	}, "")
	if resp.StatusCode != http.StatusUnauthorized {
		t.Fatalf("status = %d, want 401 (body=%s)", resp.StatusCode, body)
	}
}

func TestHandleVoiceClone_EmptyURL(t *testing.T) {
	env := newEnv(t, nil, false)
	env.srv.SetVoice(&audioStubVoice{})

	token := env.token(t, auth.RoleOwner)
	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
		"url": "  ",
	}, token)
	if resp.StatusCode != http.StatusBadRequest {
		t.Fatalf("status = %d, want 400 (body=%s)", resp.StatusCode, body)
	}
}