// Package vllm provides an Adapter for OpenAI-compatible inference engines
// such as vLLM and SGLang via the /v1/chat/completions SSE endpoint.
package vllm

import (
	"bufio"
	"bytes"
	"context"
	"encoding/json"
	"fmt"
	"io"
	"net/http"
	"net/url"
	"strings"
	"time"

	"go.uber.org/zap"

	"iop/apps/node/internal/runtime"
	"iop/packages/go/config"
)

const Name = "vllm"

type Vllm struct {
	instanceName     string
	endpoint         string
	capacity         int
	maxQueue         int
	queueTimeoutMS   int
	requestTimeoutMS int
	client           *http.Client
	logger           *zap.Logger
}

// New creates a vLLM adapter. The optional instanceName is the registry
// instance key used to disambiguate multiple vLLM instances on the same node.
func New(cfg config.VllmConf, logger *zap.Logger, instanceName ...string) *Vllm {
	endpoint := strings.TrimRight(cfg.Endpoint, "/")
	name := Name
	if len(instanceName) > 0 && instanceName[0] != "" {
		name = instanceName[0]
	}
	return &Vllm{
		instanceName:     name,
		endpoint:         endpoint,
		capacity:         cfg.Capacity,
		maxQueue:         cfg.MaxQueue,
		queueTimeoutMS:   cfg.QueueTimeoutMS,
		requestTimeoutMS: cfg.RequestTimeoutMS,
		client:           &http.Client{},
		logger:           logger,
	}
}

func (v *Vllm) Name() string { return Name }

func (v *Vllm) Capabilities(ctx context.Context) (runtime.Capabilities, error) {
	probeCtx, cancel := context.WithTimeout(ctx, 2*time.Second)
	defer cancel()
	targets, err := v.fetchTargets(probeCtx)
	status := runtime.ProviderStatusAvailable
	if err != nil {
		status = runtime.ProviderStatusUnavailable
	}
	return runtime.Capabilities{
		AdapterName:      Name,
		InstanceKey:      v.instanceName,
		Targets:          targets,
		MaxConcurrency:   effectiveCapacity(v.capacity, 8),
		MaxQueue:         v.maxQueue,
		QueueTimeoutMS:   v.queueTimeoutMS,
		RequestTimeoutMS: v.requestTimeoutMS,
		ProviderStatus:   runtime.NormalizeProviderStatus(status),
	}, nil
}

func effectiveCapacity(capacity, defaultVal int) int {
	if capacity <= 0 {
		return defaultVal
	}
	return capacity
}

func (v *Vllm) Execute(ctx context.Context, spec runtime.ExecutionSpec, sink runtime.EventSink) error {
	if v.endpoint == "" {
		return fmt.Errorf("vllm adapter: endpoint is required")
	}
	model := strings.TrimSpace(spec.Target)
	if model == "" {
		model = stringInput(spec.Input, "model")
	}
	if model == "" {
		return fmt.Errorf("vllm adapter: target/model is required")
	}
	messages := messagesFromInput(spec.Input)
	if len(messages) == 0 {
		return fmt.Errorf("vllm adapter: messages are required")
	}

	if err := sink.Emit(ctx, runtime.RuntimeEvent{
		RunID:     spec.RunID,
		Type:      runtime.EventTypeStart,
		Timestamp: time.Now(),
	}); err != nil {
		return err
	}

	chatReq := vllmChatRequest{
		Model:    model,
		Messages: messages,
		Stream:   true,
	}
	body, err := json.Marshal(chatReq)
	if err != nil {
		return fmt.Errorf("vllm adapter: marshal request: %w", err)
	}
	req, err := http.NewRequestWithContext(ctx, http.MethodPost, joinURL(v.endpoint, "/v1/chat/completions"), bytes.NewReader(body))
	if err != nil {
		return fmt.Errorf("vllm adapter: build request: %w", err)
	}
	req.Header.Set("Content-Type", "application/json")

	v.logger.Info("vllm adapter executing",
		zap.String("run_id", spec.RunID),
		zap.String("target", model),
		zap.String("endpoint", v.endpoint),
	)
	resp, err := v.client.Do(req)
	if err != nil {
		_ = emitError(ctx, sink, spec.RunID, fmt.Sprintf("vllm request failed: %v", err))
		return fmt.Errorf("vllm adapter: request: %w", err)
	}
	defer resp.Body.Close()
	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		msg := readLimited(resp.Body, 4096)
		if msg == "" {
			msg = resp.Status
		}
		_ = emitError(ctx, sink, spec.RunID, fmt.Sprintf("vllm returned %s: %s", resp.Status, msg))
		return fmt.Errorf("vllm adapter: non-2xx response: %s", resp.Status)
	}

	scanner := bufio.NewScanner(resp.Body)
	outputTokens := 0
	for scanner.Scan() {
		line := scanner.Text()
		if !strings.HasPrefix(line, "data: ") {
			continue
		}
		payload := strings.TrimPrefix(line, "data: ")
		if payload == "[DONE]" {
			return sink.Emit(ctx, runtime.RuntimeEvent{
				RunID:   spec.RunID,
				Type:    runtime.EventTypeComplete,
				Message: "vllm chat complete",
				Usage: &runtime.UsageStats{
					OutputTokens: outputTokens,
				},
				Timestamp: time.Now(),
			})
		}
		var chunk vllmChatChunk
		if err := json.Unmarshal([]byte(payload), &chunk); err != nil {
			continue
		}
		if len(chunk.Choices) == 0 {
			continue
		}
		content := chunk.Choices[0].Delta.Content
		if content != "" {
			outputTokens += len(strings.Fields(content))
			if err := sink.Emit(ctx, runtime.RuntimeEvent{
				RunID:     spec.RunID,
				Type:      runtime.EventTypeDelta,
				Delta:     content,
				Timestamp: time.Now(),
			}); err != nil {
				return err
			}
		}
	}
	if err := scanner.Err(); err != nil {
		_ = emitError(ctx, sink, spec.RunID, fmt.Sprintf("vllm stream scan failed: %v", err))
		return fmt.Errorf("vllm adapter: scan stream: %w", err)
	}
	_ = emitError(ctx, sink, spec.RunID, "vllm stream ended without [DONE]")
	return fmt.Errorf("vllm adapter: stream ended without [DONE]")
}

// ProbeProvider checks the availability of the vLLM (or OpenAI-compatible, e.g., SGLang) endpoint
// and the presence of the target model using the OpenAI-compatible /v1/models endpoint.
func (v *Vllm) ProbeProvider(ctx context.Context, target string) (runtime.ProviderProbeResult, error) {
	probeCtx, cancel := context.WithTimeout(ctx, 2*time.Second)
	defer cancel()

	targets, err := v.fetchTargets(probeCtx)

	result := runtime.ProviderProbeResult{
		AdapterName: Name,
		InstanceKey: v.instanceName,
		Target:      target,
	}

	if err != nil {
		result.Status = runtime.NormalizeProviderStatus(runtime.ProviderStatusUnavailable)
		result.Detail = err.Error()
		return result, nil
	}

	result.Targets = targets

	if target == "" {
		result.Status = runtime.NormalizeProviderStatus(runtime.ProviderStatusAvailable)
		return result, nil
	}

	found := false
	for _, t := range targets {
		if t == target {
			found = true
			break
		}
	}

	if found {
		result.Status = runtime.NormalizeProviderStatus(runtime.ProviderStatusAvailable)
	} else {
		result.Status = runtime.NormalizeProviderStatus(runtime.ProviderStatusUnavailable)
		result.Detail = fmt.Sprintf("target model %q not found in provider models", target)
	}

	return result, nil
}

func (v *Vllm) fetchTargets(ctx context.Context) ([]string, error) {
	if v.endpoint == "" {
		return nil, fmt.Errorf("vllm adapter: endpoint is required")
	}
	req, err := http.NewRequestWithContext(ctx, http.MethodGet, joinURL(v.endpoint, "/v1/models"), nil)
	if err != nil {
		return nil, fmt.Errorf("build request: %w", err)
	}
	resp, err := v.client.Do(req)
	if err != nil {
		return nil, fmt.Errorf("request failed: %w", err)
	}
	defer resp.Body.Close()
	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		return nil, fmt.Errorf("status code %d", resp.StatusCode)
	}
	var models vllmModelsResponse
	if err := json.NewDecoder(resp.Body).Decode(&models); err != nil {
		return nil, fmt.Errorf("decode response: %w", err)
	}
	out := make([]string, 0, len(models.Data))
	for _, model := range models.Data {
		if model.ID != "" {
			out = append(out, model.ID)
		}
	}
	return out, nil
}

func messagesFromInput(input map[string]any) []vllmMessage {
	if raw, ok := input["messages"].([]any); ok {
		out := make([]vllmMessage, 0, len(raw))
		for _, item := range raw {
			m, ok := item.(map[string]any)
			if !ok {
				continue
			}
			role, _ := m["role"].(string)
			content, _ := m["content"].(string)
			role = strings.TrimSpace(role)
			content = strings.TrimSpace(content)
			if role == "" || content == "" {
				continue
			}
			out = append(out, vllmMessage{Role: role, Content: content})
		}
		if len(out) > 0 {
			return out
		}
	}
	if prompt := strings.TrimSpace(stringInput(input, "prompt")); prompt != "" {
		return []vllmMessage{{Role: "user", Content: prompt}}
	}
	return nil
}

func emitError(ctx context.Context, sink runtime.EventSink, runID, msg string) error {
	return sink.Emit(ctx, runtime.RuntimeEvent{
		RunID:     runID,
		Type:      runtime.EventTypeError,
		Error:     msg,
		Timestamp: time.Now(),
	})
}

func stringInput(input map[string]any, key string) string {
	if input == nil {
		return ""
	}
	if v, ok := input[key].(string); ok {
		return v
	}
	return ""
}

func joinURL(baseURL, path string) string {
	u, err := url.Parse(baseURL)
	if err != nil {
		return strings.TrimRight(baseURL, "/") + path
	}
	u.Path = strings.TrimRight(u.Path, "/") + path
	return u.String()
}

func readLimited(r io.Reader, limit int64) string {
	b, _ := io.ReadAll(io.LimitReader(r, limit))
	return strings.TrimSpace(string(b))
}

type vllmChatRequest struct {
	Model    string       `json:"model"`
	Messages []vllmMessage `json:"messages"`
	Stream   bool         `json:"stream"`
}

type vllmMessage struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

type vllmChatChunk struct {
	Choices []struct {
		Delta struct {
			Content string `json:"content"`
		} `json:"delta"`
	} `json:"choices"`
}

type vllmModelsResponse struct {
	Data []struct {
		ID string `json:"id"`
	} `json:"data"`
}