iop/apps/edge/internal/openai/responses_handler.go

package openai

import (
	"encoding/json"
	"fmt"
	"net/http"
	"strconv"
	"strings"
	"time"

	"go.uber.org/zap"

	edgeservice "iop/apps/edge/internal/service"
)

func (s *Server) handleResponses(w http.ResponseWriter, r *http.Request) {
	if r.Method != http.MethodPost {
		writeError(w, http.StatusMethodNotAllowed, "method_not_allowed", "method not allowed")
		return
	}
	defer r.Body.Close()

	var req responsesRequest
	if err := decodeResponsesRequest(json.NewDecoder(r.Body), &req); err != nil {
		writeError(w, http.StatusBadRequest, "invalid_request_error", err.Error())
		return
	}

	if req.Stream {
		writeError(w, http.StatusBadRequest, "invalid_request_error", "streaming is not supported for /v1/responses")
		return
	}
	if req.Background {
		writeError(w, http.StatusBadRequest, "invalid_request_error", "background is not supported for /v1/responses")
		return
	}

	inputStr, err := parseResponsesInput(req.Input)
	if err != nil {
		writeError(w, http.StatusBadRequest, "invalid_request_error", err.Error())
		return
	}

	prompt := buildResponsesPrompt(req.Instructions, inputStr)
	outputPolicy := s.resolveOutputPolicy(prompt)
	if instruction := strictOutputContractInstruction(outputPolicy); instruction != "" {
		prompt = instruction + "\n" + prompt
	}

	runMeta, workspace, err := parseOpenAIMetadata(req.Metadata)
	if err != nil {
		writeError(w, http.StatusBadRequest, "invalid_request_error", err.Error())
		return
	}

	dispatch, ok := s.resolveRouteDispatch(req.Model)
	if !ok {
		writeError(w, http.StatusBadRequest, "invalid_request_error", "model is required")
		return
	}
	if err := validateWorkspaceForRoute(dispatch, workspace); err != nil {
		writeError(w, http.StatusBadRequest, "invalid_request_error", err.Error())
		return
	}
	var defaultThinkingTokenBudget int
	if catalogEntry := s.findProviderPoolEntry(req.Model); catalogEntry != nil {
		applyModelCatalogGenerationPolicyToResponses(&req, *catalogEntry)
		if catalogEntry.DefaultThinkingTokenBudget > 0 {
			defaultThinkingTokenBudget = catalogEntry.DefaultThinkingTokenBudget
		}
	}

	runMeta["openai_model"] = req.Model
	runMeta["openai_stream"] = fmt.Sprintf("%t", req.Stream)
	runMeta["strict_output"] = fmt.Sprintf("%t", outputPolicy.Strict)
	input := map[string]any{"prompt": prompt}
	if defaultThinkingTokenBudget > 0 {
		input["think"] = true
		input["thinking_token_budget"] = defaultThinkingTokenBudget
	} else if outputPolicy.Strict {
		input["think"] = false
	}
	if options := req.providerOptions(); len(options) > 0 {
		input["options"] = options
	}

	s.logger.Info("openai responses input",
		zap.String("model", req.Model),
		zap.String("target", dispatch.Target),
		zap.String("adapter", dispatch.Adapter),
		zap.Bool("strict_output", outputPolicy.Strict),
		zap.String("xml_completion_tool", outputPolicy.XMLCompletionTool),
		zap.Bool("contract_instruction", outputPolicy.ContractInstruction),
		zap.Int("prompt_len", len(prompt)),
	)

	estimate := estimateInputTokens(prompt, runMeta, nil, nil)
	contextClass := classifyContext(estimate, s.longContextThreshold())
	runMeta["estimated_input_tokens"] = strconv.Itoa(estimate)
	runMeta["context_class"] = contextClass

	handle, err := s.service.SubmitRun(r.Context(), edgeservice.SubmitRunRequest{
		NodeRef:              dispatch.NodeRef,
		ModelGroupKey:        strings.TrimSpace(req.Model),
		Adapter:              dispatch.Adapter,
		Target:               dispatch.Target,
		SessionID:            dispatch.SessionID,
		Workspace:            workspace,
		Prompt:               prompt,
		Input:                input,
		TimeoutSec:           dispatch.TimeoutSec,
		MaxQueue:             dispatch.MaxQueue,
		QueueTimeoutMS:       dispatch.QueueTimeoutMS,
		Metadata:             runMeta,
		EstimatedInputTokens: estimate,
		ContextClass:         contextClass,
		ProviderPool:         dispatch.ProviderPool,
	})
	if err != nil {
		writeError(w, http.StatusBadGateway, "node_dispatch_error", err.Error())
		return
	}
	defer handle.Close()

	s.logger.Info("openai responses dispatch",
		zap.String("run_id", handle.Dispatch().RunID),
		zap.String("node_id", handle.Dispatch().NodeID),
		zap.String("model_group", handle.Dispatch().ModelGroupKey),
		zap.String("adapter", handle.Dispatch().Adapter),
		zap.String("target", handle.Dispatch().Target),
		zap.Int("estimated_input_tokens", handle.Dispatch().EstimatedInputTokens),
		zap.String("context_class", handle.Dispatch().ContextClass),
		zap.String("queue_reason", handle.Dispatch().QueueReason),
	)

	s.completeResponse(w, r, req, handle, outputPolicy)
}

func decodeResponsesRequest(dec *json.Decoder, req *responsesRequest) error {
	var raw map[string]json.RawMessage
	if err := dec.Decode(&raw); err != nil {
		return fmt.Errorf("invalid JSON request")
	}
	for key := range raw {
		switch key {
		case "model", "input", "instructions", "stream", "background", "metadata", "max_output_tokens", "temperature", "top_p":
		default:
			return fmt.Errorf("%s is not supported for /v1/responses", key)
		}
	}
	normalized, err := json.Marshal(raw)
	if err != nil {
		return fmt.Errorf("invalid JSON request")
	}
	if err := json.Unmarshal(normalized, req); err != nil {
		return fmt.Errorf("invalid /v1/responses request format")
	}
	if req.MaxOutputTokens != nil && *req.MaxOutputTokens <= 0 {
		return fmt.Errorf("max_output_tokens must be greater than zero")
	}
	if req.Temperature != nil && (*req.Temperature < 0 || *req.Temperature > 2) {
		return fmt.Errorf("temperature must be between 0 and 2")
	}
	if req.TopP != nil && (*req.TopP < 0 || *req.TopP > 1) {
		return fmt.Errorf("top_p must be between 0 and 1")
	}
	return nil
}

func (s *Server) completeResponse(w http.ResponseWriter, r *http.Request, req responsesRequest, handle edgeservice.RunResult, outputPolicy strictOutputPolicy) {
	text, reasoning, _, _, usage, _, err := collectRunResult(r.Context(), handle.Stream(), handle.WaitTimeout())
	if err != nil {
		s.cancelRunOnHTTPGiveUp(handle.Dispatch(), err)
		writeError(w, httpStatusForRunError(err), "run_error", err.Error())
		return
	}
	text, reasoning, normalized := normalizeCompletionOutput(outputPolicy, text, reasoning, false)
	s.logger.Info("openai responses output",
		zap.String("run_id", handle.Dispatch().RunID),
		zap.Bool("strict_output", outputPolicy.Strict),
		zap.String("xml_completion_tool", outputPolicy.XMLCompletionTool),
		zap.Bool("normalized", normalized),
		zap.Int("content_len", len(text)),
		zap.Int("reasoning_len", len(reasoning)),
	)

	var u openAIUsage
	if usage != nil {
		u = *usage
	}

	writeJSON(w, http.StatusOK, responsesResponse{
		ID:         "resp-" + handle.Dispatch().RunID,
		Object:     "response",
		CreatedAt:  time.Now().Unix(),
		Model:      responseModel(req.Model, handle.Dispatch().Target),
		OutputText: text,
		Output: []responsesOutputItem{{
			Type: "message",
			Role: "assistant",
			Content: []responsesContentItem{{
				Type: "output_text",
				Text: text,
			}},
		}},
		Usage: u,
	})
}

func parseResponsesInput(raw json.RawMessage) (string, error) {
	if len(raw) == 0 {
		return "", fmt.Errorf("input is required")
	}
	var s string
	if err := json.Unmarshal(raw, &s); err != nil {
		return "", fmt.Errorf("input must be a string")
	}
	if strings.TrimSpace(s) == "" {
		return "", fmt.Errorf("input is required")
	}
	return s, nil
}

func buildResponsesPrompt(instructions, input string) string {
	instructions = strings.TrimSpace(instructions)
	if instructions == "" {
		return input
	}
	return instructions + "\n\n" + input
}

func parseOpenAIMetadata(raw json.RawMessage) (map[string]string, string, error) {
	if len(raw) == 0 || string(raw) == "null" {
		return make(map[string]string), "", nil
	}

	var rawMap map[string]json.RawMessage
	if err := json.Unmarshal(raw, &rawMap); err != nil {
		return nil, "", fmt.Errorf("metadata must be an object")
	}

	if len(rawMap) > 16 {
		return nil, "", fmt.Errorf("metadata must contain at most 16 keys")
	}

	flat := make(map[string]string, len(rawMap))
	var workspace string
	for key, rawValue := range rawMap {
		if len(key) > 64 {
			return nil, "", fmt.Errorf("metadata key %q exceeds 64 characters", key)
		}
		if key == "source" {
			return nil, "", fmt.Errorf("metadata.source is not supported")
		}
		if key == "workspace" {
			workspaceValue, err := metadataStringValue(key, rawValue)
			if err != nil {
				return nil, "", err
			}
			workspace = strings.TrimSpace(workspaceValue)
			continue
		}
		value, err := metadataStringValue(key, rawValue)
		if err != nil {
			return nil, "", err
		}
		flat[key] = value
	}

	return flat, workspace, nil
}

func metadataStringValue(key string, raw json.RawMessage) (string, error) {
	var value string
	if err := json.Unmarshal(raw, &value); err != nil {
		return "", fmt.Errorf("metadata.%s must be a string", key)
	}
	if len(value) > 512 {
		return "", fmt.Errorf("metadata.%s exceeds 512 characters", key)
	}
	return value, nil
}