package chat

import (
	"context"
	"encoding/json"
	"errors"
	"io"
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"
	"time"
)

// ollamaServer mocks /api/chat + /api/tags. Captures last request body.
func ollamaServer(t *testing.T, status int, respBody string) (*httptest.Server, *string) {
	t.Helper()
	captured := ""
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		switch r.URL.Path {
		case "/api/tags":
			w.WriteHeader(200)
			_, _ = w.Write([]byte(`{"models":[{"name":"qwen3.5:latest"}]}`))
			return
		case "/api/chat":
			bs, _ := io.ReadAll(r.Body)
			captured = string(bs)
			w.WriteHeader(status)
			_, _ = w.Write([]byte(respBody))
			return
		default:
			w.WriteHeader(404)
		}
	}))
	t.Cleanup(srv.Close)
	return srv, &captured
}

func TestOllama_ChatHappyPath(t *testing.T) {
	resp := `{
		"model": "qwen3.5:latest",
		"message": {"content": "ok"},
		"done": true,
		"prompt_eval_count": 7,
		"eval_count": 3
	}`
	srv, captured := ollamaServer(t, 200, resp)
	o := NewOllama(srv.URL, 5*time.Second)

	out, err := o.Chat(context.Background(), Request{
		Model:    "qwen3.5:latest",
		Messages: []Message{{Role: "user", Content: "hi"}},
	})
	if err != nil {
		t.Fatalf("Chat: %v", err)
	}
	if out.Content != "ok" {
		t.Errorf("Content = %q, want ok", out.Content)
	}
	if out.InputTokens != 7 || out.OutputTokens != 3 {
		t.Errorf("tokens = (%d, %d), want (7, 3)", out.InputTokens, out.OutputTokens)
	}

	// Verify captured request shape: stream=false, options.temperature
	// surfaced.
	var sent map[string]any
	if err := json.Unmarshal([]byte(*captured), &sent); err != nil {
		t.Fatalf("parse captured: %v", err)
	}
	if sent["stream"] != false {
		t.Errorf("stream should be false, got %v", sent["stream"])
	}
}

func TestOllama_StripsExplicitPrefix(t *testing.T) {
	srv, captured := ollamaServer(t, 200, `{"message":{"content":""},"done":true}`)
	o := NewOllama(srv.URL, 5*time.Second)
	_, err := o.Chat(context.Background(), Request{Model: "ollama/qwen3.5:latest"})
	if err != nil {
		t.Fatalf("Chat: %v", err)
	}
	var sent map[string]any
	_ = json.Unmarshal([]byte(*captured), &sent)
	if sent["model"] != "qwen3.5:latest" {
		t.Errorf("upstream model = %v, want qwen3.5:latest (prefix stripped)", sent["model"])
	}
}

func TestOllama_FormatJSON(t *testing.T) {
	srv, captured := ollamaServer(t, 200, `{"message":{"content":"{}"},"done":true}`)
	o := NewOllama(srv.URL, 5*time.Second)
	_, _ = o.Chat(context.Background(), Request{Model: "qwen3.5:latest", Format: "json"})
	if !strings.Contains(*captured, `"format":"json"`) {
		t.Errorf("Format=json should set top-level format=json; captured=%s", *captured)
	}
}

func TestOllama_Available(t *testing.T) {
	srv, _ := ollamaServer(t, 200, "{}")
	o := NewOllama(srv.URL, 5*time.Second)
	if !o.Available() {
		t.Errorf("server is up; Available should be true")
	}
}

func TestOllama_UpstreamError(t *testing.T) {
	srv, _ := ollamaServer(t, 500, `{"error":"out of memory"}`)
	o := NewOllama(srv.URL, 5*time.Second)
	_, err := o.Chat(context.Background(), Request{Model: "qwen3.5:latest"})
	if !errors.Is(err, ErrUpstream) {
		t.Errorf("500 should ErrUpstream; got %v", err)
	}
}

func TestOllamaCloud_FlattenMessages(t *testing.T) {
	system, prompt := flattenMessages([]Message{
		{Role: "system", Content: "You are helpful."},
		{Role: "user", Content: "hi"},
		{Role: "assistant", Content: "hello!"},
		{Role: "user", Content: "how are you?"},
	})
	if system != "You are helpful." {
		t.Errorf("system = %q, want 'You are helpful.'", system)
	}
	if !strings.Contains(prompt, "User: hi") || !strings.Contains(prompt, "Assistant: hello!") || !strings.Contains(prompt, "User: how are you?") {
		t.Errorf("prompt missing role tags: %q", prompt)
	}
}