feat: micro go cli

2026-04-25 07:00:48 +09:00 · 2026-01-29 02:55:21 +07:00
parent 0e56c85233
commit 31cb75702c
13 changed files with 475 additions and 3403 deletions
@@ -8,8 +8,17 @@ export interface ErrorResponse {
 }

 export const errorMiddleware = new Elysia({ name: 'error' })
-  .onError(({ code, error, set }) => {
-    console.error('[Error]', code, error)
+  .onError(({ code, error, set, request }) => {
+    const url = new URL(request.url)
+    const status = set.status ?? 500
+    const message = error instanceof Error ? error.message : String(error)
+    console.error('[Error]', {
+      method: request.method,
+      path: url.pathname,
+      code,
+      status,
+      message,
+    })

    switch (code) {
      case 'VALIDATION':
@@ -37,6 +37,12 @@ const ScheduleBody = z.object({

 export const chatModule = new Elysia({ prefix: '/chat' })
  .post('/', async ({ body }) => {
+    console.log('[Chat] request', {
+      type: 'chat',
+      clientType: body.clientType,
+      model: body.model,
+      baseUrl: body.baseUrl,
+    })
    const { ask } = createAgent({
      apiKey: body.apiKey,
      baseUrl: body.baseUrl,
@@ -49,14 +55,33 @@ export const chatModule = new Elysia({ prefix: '/chat' })
      platforms: body.platforms,
      currentPlatform: body.currentPlatform,
    })
-    return await ask({
-      messages: body.messages as unknown as ModelMessage[],
-      query: body.query,
-    })
+    try {
+      const result = await ask({
+        messages: body.messages as unknown as ModelMessage[],
+        query: body.query,
+      })
+      console.log('[Chat] response', { type: 'chat', messages: result.messages?.length ?? 0 })
+      return result
+    } catch (error) {
+      console.error('[Chat] error', {
+        type: 'chat',
+        clientType: body.clientType,
+        model: body.model,
+        baseUrl: body.baseUrl,
+        error,
+      })
+      throw error
+    }
  }, {
    body: ChatBody,
  })
  .post('/stream', async function* ({ body }) {
+    console.log('[Chat] request', {
+      type: 'stream',
+      clientType: body.clientType,
+      model: body.model,
+      baseUrl: body.baseUrl,
+    })
    const { stream } = createAgent({
      apiKey: body.apiKey,
      baseUrl: body.baseUrl,
@@ -69,23 +94,35 @@ export const chatModule = new Elysia({ prefix: '/chat' })
      platforms: body.platforms,
      currentPlatform: body.currentPlatform,
    })
-    const streanGenerator = stream({
-      messages: body.messages as unknown as ModelMessage[],
-      query: body.query,
-    })
-    while (true) {
-      const chunk = await streanGenerator.next()
-      if (chunk.done) {
-        yield sse({
-          type: 'done',
-          data: chunk.value,
-        })
-        break
-      }
-      yield sse({
-        type: 'delta',
-        data: chunk.value
+    try {
+      const streanGenerator = stream({
+        messages: body.messages as unknown as ModelMessage[],
+        query: body.query,
      })
+      while (true) {
+        const chunk = await streanGenerator.next()
+        if (chunk.done) {
+          console.log('[Chat] response', { type: 'stream', messages: chunk.value?.messages?.length ?? 0 })
+          yield sse({
+            type: 'done',
+            data: chunk.value,
+          })
+          break
+        }
+        yield sse({
+          type: 'delta',
+          data: chunk.value
+        })
+      }
+    } catch (error) {
+      console.error('[Chat] error', {
+        type: 'stream',
+        clientType: body.clientType,
+        model: body.model,
+        baseUrl: body.baseUrl,
+        error,
+      })
+      throw error
    }
  }, {
    body: ChatBody,
@@ -0,0 +1,357 @@
+package main
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"encoding/json"
+	"flag"
+	"fmt"
+	"io"
+	"log"
+	"net/http"
+	"os"
+	"strings"
+	"time"
+
+	"github.com/memohai/memoh/internal/chat"
+	"github.com/memohai/memoh/internal/config"
+)
+
+type cliOptions struct {
+	configPath string
+	username   string
+	password   string
+	timeout    time.Duration
+	apiBaseURL string
+	jwtToken   string
+}
+
+func main() {
+	opts := parseFlags()
+	ctx := context.Background()
+
+	cfg, err := config.Load(opts.configPath)
+	if err != nil {
+		log.Fatalf("load config: %v", err)
+	}
+	if strings.TrimSpace(opts.apiBaseURL) == "" {
+		opts.apiBaseURL = defaultAPIBaseURL(cfg.Server.Addr)
+	}
+	if strings.TrimSpace(opts.apiBaseURL) == "" {
+		log.Fatalf("api url is required")
+	}
+	opts.apiBaseURL = normalizeBaseURL(opts.apiBaseURL)
+
+	jwtToken := strings.TrimSpace(opts.jwtToken)
+	client := &http.Client{Timeout: opts.timeout}
+	if jwtToken == "" {
+		username, password, err := resolveLoginCredentials(opts, cfg)
+		if err != nil {
+			log.Fatalf("resolve login: %v", err)
+		}
+		loginCtx := ctx
+		if opts.timeout > 0 {
+			var cancel context.CancelFunc
+			loginCtx, cancel = context.WithTimeout(ctx, opts.timeout)
+			defer cancel()
+		}
+		jwtToken, err = resolveJWTToken(loginCtx, client, opts.apiBaseURL, username, password)
+		if err != nil {
+			log.Fatalf("resolve jwt: %v", err)
+		}
+	}
+
+	query := strings.TrimSpace(strings.Join(flag.Args(), " "))
+	if query != "" {
+		if err := sendChat(ctx, client, opts.apiBaseURL, jwtToken, query); err != nil {
+			log.Fatalf("chat failed: %v", err)
+		}
+		return
+	}
+	if err := runInteractive(ctx, client, opts.apiBaseURL, jwtToken); err != nil {
+		log.Fatalf("chat failed: %v", err)
+	}
+}
+
+func parseFlags() cliOptions {
+	var opts cliOptions
+	defaultConfig := os.Getenv("CONFIG_PATH")
+	if strings.TrimSpace(defaultConfig) == "" {
+		defaultConfig = config.DefaultConfigPath
+	}
+
+	flag.StringVar(&opts.configPath, "config", defaultConfig, "Path to config.toml")
+	flag.StringVar(&opts.username, "username", "", "Username for login")
+	flag.StringVar(&opts.password, "password", "", "Password for login (or set MEMOH_PASSWORD)")
+	flag.StringVar(&opts.jwtToken, "jwt", "", "JWT token (optional)")
+	flag.StringVar(&opts.apiBaseURL, "api-url", "", "API server base URL (e.g. http://127.0.0.1:8080)")
+	flag.DurationVar(&opts.timeout, "timeout", 30*time.Second, "Request timeout")
+	flag.Parse()
+
+	return opts
+}
+
+func normalizeBaseURL(value string) string {
+	return strings.TrimRight(strings.TrimSpace(value), "/")
+}
+
+func defaultAPIBaseURL(addr string) string {
+	trimmed := strings.TrimSpace(addr)
+	if trimmed == "" {
+		return ""
+	}
+	if strings.HasPrefix(trimmed, "http://") || strings.HasPrefix(trimmed, "https://") {
+		return normalizeBaseURL(trimmed)
+	}
+	if strings.HasPrefix(trimmed, ":") {
+		return "http://127.0.0.1" + trimmed
+	}
+	return "http://" + trimmed
+}
+
+func resolveLoginCredentials(opts cliOptions, cfg config.Config) (string, string, error) {
+	username := strings.TrimSpace(opts.username)
+	if username == "" {
+		username = strings.TrimSpace(cfg.Admin.Username)
+	}
+	if username == "" {
+		return "", "", fmt.Errorf("username is required for login")
+	}
+
+	password := strings.TrimSpace(opts.password)
+	if password == "" {
+		password = strings.TrimSpace(os.Getenv("MEMOH_PASSWORD"))
+	}
+	if password == "" {
+		if candidate := strings.TrimSpace(cfg.Admin.Password); candidate != "" && candidate != "change-your-password-here" {
+			password = candidate
+		}
+	}
+	if password == "" {
+		return "", "", fmt.Errorf("password is required; pass --password or set MEMOH_PASSWORD")
+	}
+	return username, password, nil
+}
+
+func resolveJWTToken(ctx context.Context, client *http.Client, baseURL, username, password string) (string, error) {
+	resp, err := loginForToken(ctx, client, baseURL, username, password)
+	if err != nil {
+		return "", err
+	}
+	if strings.TrimSpace(resp.AccessToken) == "" {
+		return "", fmt.Errorf("login succeeded but token missing")
+	}
+	return resp.AccessToken, nil
+}
+
+type loginRequest struct {
+	Username string `json:"username"`
+	Password string `json:"password"`
+}
+
+type loginResponse struct {
+	AccessToken string `json:"access_token"`
+	TokenType   string `json:"token_type"`
+	ExpiresAt   string `json:"expires_at"`
+	UserID      string `json:"user_id"`
+	Username    string `json:"username"`
+}
+
+func loginForToken(ctx context.Context, client *http.Client, baseURL, username, password string) (loginResponse, error) {
+	body, err := json.Marshal(loginRequest{
+		Username: username,
+		Password: password,
+	})
+	if err != nil {
+		return loginResponse{}, err
+	}
+	url := normalizeBaseURL(baseURL) + "/auth/login"
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
+	if err != nil {
+		return loginResponse{}, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := client.Do(req)
+	if err != nil {
+		return loginResponse{}, err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		payload, _ := io.ReadAll(resp.Body)
+		return loginResponse{}, fmt.Errorf("login failed: %s", strings.TrimSpace(string(payload)))
+	}
+
+	var parsed loginResponse
+	if err := json.NewDecoder(resp.Body).Decode(&parsed); err != nil {
+		return loginResponse{}, err
+	}
+	return parsed, nil
+}
+
+func runInteractive(ctx context.Context, client *http.Client, baseURL, jwtToken string) error {
+	reader := bufio.NewScanner(os.Stdin)
+	reader.Buffer(make([]byte, 0, 64*1024), 2*1024*1024)
+
+	fmt.Fprint(os.Stdout, "You: ")
+	for reader.Scan() {
+		line := strings.TrimSpace(reader.Text())
+		if line == "" {
+			fmt.Fprint(os.Stdout, "You: ")
+			continue
+		}
+		lower := strings.ToLower(line)
+		if lower == "exit" || lower == "quit" {
+			return nil
+		}
+		if err := sendChat(ctx, client, baseURL, jwtToken, line); err != nil {
+			return err
+		}
+		fmt.Fprint(os.Stdout, "You: ")
+	}
+	return reader.Err()
+}
+
+func sendChat(ctx context.Context, client *http.Client, baseURL, jwtToken, query string) error {
+	return streamAPIChat(ctx, client, baseURL, jwtToken, chat.ChatRequest{Query: query})
+}
+
+func streamAPIChat(ctx context.Context, client *http.Client, baseURL, jwtToken string, req chat.ChatRequest) error {
+	body, err := json.Marshal(req)
+	if err != nil {
+		return err
+	}
+	url := baseURL + "/chat/stream"
+	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
+	if err != nil {
+		return err
+	}
+	httpReq.Header.Set("Content-Type", "application/json")
+	httpReq.Header.Set("Accept", "text/event-stream")
+	httpReq.Header.Set("Authorization", "Bearer "+jwtToken)
+
+	resp, err := client.Do(httpReq)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		payload, _ := io.ReadAll(resp.Body)
+		return fmt.Errorf("api server error: %s", strings.TrimSpace(string(payload)))
+	}
+
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Buffer(make([]byte, 0, 64*1024), 2*1024*1024)
+
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if line == "" || strings.HasPrefix(line, "event:") {
+			continue
+		}
+		if !strings.HasPrefix(line, "data:") {
+			continue
+		}
+		data := strings.TrimSpace(strings.TrimPrefix(line, "data:"))
+		if data == "" || data == "[DONE]" {
+			break
+		}
+		if text, ok := extractStreamText([]byte(data)); ok {
+			fmt.Fprint(os.Stdout, text)
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		return err
+	}
+	fmt.Fprintln(os.Stdout)
+	return nil
+}
+
+func renderMessageContent(raw interface{}) (string, bool) {
+	switch v := raw.(type) {
+	case string:
+		return v, true
+	case []interface{}:
+		parts := make([]string, 0, len(v))
+		for _, item := range v {
+			if text, ok := renderMessageContent(item); ok && strings.TrimSpace(text) != "" {
+				parts = append(parts, text)
+			}
+		}
+		if len(parts) > 0 {
+			return strings.Join(parts, ""), true
+		}
+	case map[string]interface{}:
+		if text, ok := v["text"].(string); ok && strings.TrimSpace(text) != "" {
+			return text, true
+		}
+		if text, ok := v["content"].(string); ok && strings.TrimSpace(text) != "" {
+			return text, true
+		}
+		if kind, ok := v["type"].(string); ok && kind == "text" {
+			if text, ok := v["text"].(string); ok {
+				return text, true
+			}
+		}
+	}
+	return "", false
+}
+
+func extractStreamText(raw []byte) (string, bool) {
+	var payload interface{}
+	if err := json.Unmarshal(raw, &payload); err != nil {
+		return "", false
+	}
+	return extractTextFromPayload(payload)
+}
+
+func extractTextFromPayload(payload interface{}) (string, bool) {
+	switch v := payload.(type) {
+	case string:
+		if strings.TrimSpace(v) == "" {
+			return "", false
+		}
+		return v, true
+	case []interface{}:
+		parts := make([]string, 0, len(v))
+		for _, item := range v {
+			if text, ok := extractTextFromPayload(item); ok && strings.TrimSpace(text) != "" {
+				parts = append(parts, text)
+			}
+		}
+		if len(parts) > 0 {
+			return strings.Join(parts, ""), true
+		}
+	case map[string]interface{}:
+		if text, ok := v["textDelta"].(string); ok && strings.TrimSpace(text) != "" {
+			return text, true
+		}
+		if text, ok := v["text"].(string); ok && strings.TrimSpace(text) != "" {
+			return text, true
+		}
+		if content, ok := v["content"]; ok {
+			if text, ok := renderMessageContent(content); ok {
+				return text, true
+			}
+		}
+		if delta, ok := v["delta"]; ok {
+			if text, ok := extractTextFromPayload(delta); ok {
+				return text, true
+			}
+		}
+		if data, ok := v["data"]; ok {
+			if text, ok := extractTextFromPayload(data); ok {
+				return text, true
+			}
+		}
+		if msg, ok := v["message"]; ok {
+			if text, ok := extractTextFromPayload(msg); ok {
+				return text, true
+			}
+		}
+	}
+	return "", false
+}
@@ -959,20 +959,12 @@ const docTemplate = `{
        },
        "/models/enable-as/{enableAs}": {
            "get": {
-                "description": "Get the model that is enabled for a specific purpose (chat, memory, embedding)\nGet the default model configured for a specific purpose (chat, memory, or embedding)",
+                "description": "Get the model that is enabled for a specific purpose (chat, memory, embedding)",
                "tags": [
-                    "models",
                    "models"
                ],
-                "summary": "Get default model by enable_as",
+                "summary": "Get model by enable_as",
                "parameters": [
-                    {
-                        "type": "string",
-                        "description": "Enable as value (chat, memory, embedding)",
-                        "name": "enableAs",
-                        "in": "path",
-                        "required": true
-                    },
                    {
                        "type": "string",
                        "description": "Enable as value (chat, memory, embedding)",
@@ -2499,11 +2491,11 @@ const docTemplate = `{

 // SwaggerInfo holds exported Swagger Info so clients can modify it
 var SwaggerInfo = &swag.Spec{
-	Version:          "",
+	Version:          "1.0.0",
 	Host:             "",
 	BasePath:         "",
 	Schemes:          []string{},
-	Title:            "",
+	Title:            "Memoh API",
 	Description:      "",
 	InfoInstanceName: "swagger",
 	SwaggerTemplate:  docTemplate,
@@ -1,7 +1,9 @@
 {
    "swagger": "2.0",
    "info": {
-        "contact": {}
+        "title": "Memoh API",
+        "contact": {},
+        "version": "1.0.0"
    },
    "paths": {
        "/auth/login": {
@@ -948,20 +950,12 @@
        },
        "/models/enable-as/{enableAs}": {
            "get": {
-                "description": "Get the model that is enabled for a specific purpose (chat, memory, embedding)\nGet the default model configured for a specific purpose (chat, memory, or embedding)",
+                "description": "Get the model that is enabled for a specific purpose (chat, memory, embedding)",
                "tags": [
-                    "models",
                    "models"
                ],
-                "summary": "Get default model by enable_as",
+                "summary": "Get model by enable_as",
                "parameters": [
-                    {
-                        "type": "string",
-                        "description": "Enable as value (chat, memory, embedding)",
-                        "name": "enableAs",
-                        "in": "path",
-                        "required": true
-                    },
                    {
                        "type": "string",
                        "description": "Enable as value (chat, memory, embedding)",
@@ -499,6 +499,8 @@ definitions:
    type: object
 info:
  contact: {}
+  title: Memoh API
+  version: 1.0.0
 paths:
  /auth/login:
    post:
@@ -1210,15 +1212,9 @@ paths:
      - models
  /models/enable-as/{enableAs}:
    get:
-      description: |-
-        Get the model that is enabled for a specific purpose (chat, memory, embedding)
-        Get the default model configured for a specific purpose (chat, memory, or embedding)
+      description: Get the model that is enabled for a specific purpose (chat, memory,
+        embedding)
      parameters:
-      - description: Enable as value (chat, memory, embedding)
-        in: path
-        name: enableAs
-        required: true
-        type: string
      - description: Enable as value (chat, memory, embedding)
        in: path
        name: enableAs
@@ -1241,10 +1237,9 @@ paths:
          description: Internal Server Error
          schema:
            $ref: '#/definitions/handlers.ErrorResponse'
-      summary: Get default model by enable_as
+      summary: Get model by enable_as
      tags:
      - models
-      - models
  /models/model/{modelId}:
    delete:
      description: Delete a model configuration by its model_id field (e.g., gpt-4)
@@ -7,7 +7,6 @@ require (
 	github.com/containerd/containerd/api v1.10.0
 	github.com/containerd/containerd/v2 v2.2.1
 	github.com/containerd/errdefs v1.0.0
-	github.com/firebase/genkit/go v1.4.0
 	github.com/golang-jwt/jwt/v5 v5.3.0
 	github.com/google/uuid v1.6.0
 	github.com/jackc/pgx/v5 v5.8.0
@@ -25,8 +24,6 @@ require (
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/Microsoft/hcsshim v0.14.0-rc.1 // indirect
-	github.com/bahlo/generic-list-go v0.2.0 // indirect
-	github.com/buger/jsonparser v1.1.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/containerd/cgroups/v3 v3.1.2 // indirect
 	github.com/containerd/continuity v0.4.5 // indirect
@@ -53,22 +50,17 @@ require (
 	github.com/go-openapi/swag/stringutils v0.25.4 // indirect
 	github.com/go-openapi/swag/typeutils v0.25.4 // indirect
 	github.com/go-openapi/swag/yamlutils v0.25.4 // indirect
-	github.com/goccy/go-yaml v1.17.1 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
-	github.com/google/dotprompt/go v0.0.0-20251014011017-8d056e027254 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/google/jsonschema-go v0.3.0 // indirect
-	github.com/invopop/jsonschema v0.13.0 // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
 	github.com/jackc/puddle/v2 v2.2.2 // indirect
 	github.com/klauspost/compress v1.18.3 // indirect
 	github.com/labstack/gommon v0.4.2 // indirect
-	github.com/mailru/easyjson v0.9.0 // indirect
 	github.com/mattn/go-colorable v0.1.14 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
-	github.com/mbleigh/raymond v0.0.0-20250414171441-6b3a58ab9e0a // indirect
 	github.com/moby/locker v1.0.1 // indirect
 	github.com/moby/sys/mountinfo v0.7.2 // indirect
 	github.com/moby/sys/sequential v0.6.0 // indirect
@@ -83,17 +75,12 @@ require (
 	github.com/sirupsen/logrus v1.9.4 // indirect
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/valyala/fasttemplate v1.2.2 // indirect
-	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
-	github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb // indirect
-	github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 // indirect
-	github.com/xeipuuv/gojsonschema v1.2.0 // indirect
 	github.com/yosida95/uritemplate/v3 v3.0.2 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.64.0 // indirect
 	go.opentelemetry.io/otel v1.39.0 // indirect
 	go.opentelemetry.io/otel/metric v1.39.0 // indirect
-	go.opentelemetry.io/otel/sdk v1.39.0 // indirect
 	go.opentelemetry.io/otel/trace v1.39.0 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/mod v0.32.0 // indirect
@@ -10,10 +10,6 @@ github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERo
 github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/Microsoft/hcsshim v0.14.0-rc.1 h1:qAPXKwGOkVn8LlqgBN8GS0bxZ83hOJpcjxzmlQKxKsQ=
 github.com/Microsoft/hcsshim v0.14.0-rc.1/go.mod h1:hTKFGbnDtQb1wHiOWv4v0eN+7boSWAHyK/tNAaYZL0c=
-github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=
-github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=
-github.com/buger/jsonparser v1.1.1 h1:2PnMjfWD7wBILjqQbt530v576A/cAbQvEW9gGIpYMUs=
-github.com/buger/jsonparser v1.1.1/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -57,8 +53,6 @@ github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1m
 github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
-github.com/firebase/genkit/go v1.4.0 h1:CP1hNWk7z0hosyY53zMH6MFKFO1fMLtj58jGPllQo6I=
-github.com/firebase/genkit/go v1.4.0/go.mod h1:HX6m7QOaGc3MDNr/DrpQZrzPLzxeuLxrkTvfFtCYlGw=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
 github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
 github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
@@ -70,7 +64,7 @@ github.com/go-openapi/jsonreference v0.21.4 h1:24qaE2y9bx/q3uRK/qN+TDwbok1NhbSmG
 github.com/go-openapi/jsonreference v0.21.4/go.mod h1:rIENPTjDbLpzQmQWCj5kKj3ZlmEh+EFVbz3RTUh30/4=
 github.com/go-openapi/spec v0.22.3 h1:qRSmj6Smz2rEBxMnLRBMeBWxbbOvuOoElvSvObIgwQc=
 github.com/go-openapi/spec v0.22.3/go.mod h1:iIImLODL2loCh3Vnox8TY2YWYJZjMAKYyLH2Mu8lOZs=
-github.com/go-openapi/swag v0.23.1 h1:lpsStH0n2ittzTnbaSloVZLuB5+fvSY/+hnagBjSNZU=
+github.com/go-openapi/swag v0.19.15 h1:D2NRCBzS9/pEY3gP9Nl8aDqGUcPFrwG2p+CNFrLyrCM=
 github.com/go-openapi/swag/conv v0.25.4 h1:/Dd7p0LZXczgUcC/Ikm1+YqVzkEeCc9LnOWjfkpkfe4=
 github.com/go-openapi/swag/conv v0.25.4/go.mod h1:3LXfie/lwoAv0NHoEuY1hjoFAYkvlqI/Bn5EQDD3PPU=
 github.com/go-openapi/swag/jsonname v0.25.4 h1:bZH0+MsS03MbnwBXYhuTttMOqk+5KcQ9869Vye1bNHI=
@@ -91,8 +85,6 @@ github.com/go-openapi/testify/enable/yaml/v2 v2.0.2 h1:0+Y41Pz1NkbTHz8NngxTuAXxE
 github.com/go-openapi/testify/enable/yaml/v2 v2.0.2/go.mod h1:kme83333GCtJQHXQ8UKX3IBZu6z8T5Dvy5+CW3NLUUg=
 github.com/go-openapi/testify/v2 v2.0.2 h1:X999g3jeLcoY8qctY/c/Z8iBHTbwLz7R2WXd6Ub6wls=
 github.com/go-openapi/testify/v2 v2.0.2/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
-github.com/goccy/go-yaml v1.17.1 h1:LI34wktB2xEE3ONG/2Ar54+/HJVBriAGJ55PHls4YuY=
-github.com/goccy/go-yaml v1.17.1/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
@@ -113,8 +105,6 @@ github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QD
 github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
 github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
-github.com/google/dotprompt/go v0.0.0-20251014011017-8d056e027254 h1:okN800+zMJOGHLJCgry+OGzhhtH6YrjQh1rluHmOacE=
-github.com/google/dotprompt/go v0.0.0-20251014011017-8d056e027254/go.mod h1:k8cjJAQWc//ac/bMnzItyOFbfT01tgRTZGgxELCuxEQ=
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
@@ -128,8 +118,6 @@ github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/invopop/jsonschema v0.13.0 h1:KvpoAJWEjR3uD9Kbm2HWJmqsEaHt8lBUpd0qHcIi21E=
-github.com/invopop/jsonschema v0.13.0/go.mod h1:ffZ5Km5SWWRAIN6wbDXItl95euhFz2uON45H2qjYt+0=
 github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
 github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
 github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 h1:iCEnooe7UlwOQYpKFhBabPMi4aNAfoODPEFNiAnClxo=
@@ -152,14 +140,10 @@ github.com/labstack/echo/v4 v4.15.0 h1:hoRTKWcnR5STXZFe9BmYun9AMTNeSbjHi2vtDuADJ
 github.com/labstack/echo/v4 v4.15.0/go.mod h1:xmw1clThob0BSVRX1CRQkGQ/vjwcpOMjQZSZa9fKA/c=
 github.com/labstack/gommon v0.4.2 h1:F8qTUNXgG1+6WQmqoUWnz8WiEU60mXVVw0P4ht1WRA0=
 github.com/labstack/gommon v0.4.2/go.mod h1:QlUFxVM+SNXhDL/Z7YhocGIBYOiwB0mXm1+1bAPHPyU=
-github.com/mailru/easyjson v0.9.0 h1:PrnmzHw7262yW8sTBwxi1PdJA3Iw/EKBa8psRf7d9a4=
-github.com/mailru/easyjson v0.9.0/go.mod h1:1+xMtQp2MRNVL/V1bOzuP3aP8VNwRW55fQUto+XFtTU=
 github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=
 github.com/mattn/go-colorable v0.1.14/go.mod h1:6LmQG8QLFO4G5z1gPvYEzlUgJ2wF+stgPZH1UqBm1s8=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
-github.com/mbleigh/raymond v0.0.0-20250414171441-6b3a58ab9e0a h1:v2cBA3xWKv2cIOVhnzX/gNgkNXqiHfUgJtA3r61Hf7A=
-github.com/mbleigh/raymond v0.0.0-20250414171441-6b3a58ab9e0a/go.mod h1:Y6ghKH+ZijXn5d9E7qGGZBmjitx7iitZdQiIW97EpTU=
 github.com/moby/locker v1.0.1 h1:fOXqR41zeveg4fFODix+1Ch4mj/gT0NE1XJbp/epuBg=
 github.com/moby/locker v1.0.1/go.mod h1:S7SDdo5zpBK84bzzVlKr2V0hz+7x9hWbYC/kq7oQppc=
 github.com/moby/sys/mountinfo v0.7.2 h1:1shs6aH5s4o5H2zQLn796ADW1wMrIwHsyJ2v9KouLrg=
@@ -212,15 +196,6 @@ github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6Kllzaw
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
 github.com/valyala/fasttemplate v1.2.2 h1:lxLXG0uE3Qnshl9QyaK6XJxMXlQZELvChBOCmQD0Loo=
 github.com/valyala/fasttemplate v1.2.2/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
-github.com/wk8/go-ordered-map/v2 v2.1.8 h1:5h/BUHu93oj4gIdvHHHGsScSTMijfx5PeYkE/fJgbpc=
-github.com/wk8/go-ordered-map/v2 v2.1.8/go.mod h1:5nJHM5DyteebpVlHnWMV0rPz6Zp7+xBAnxjb1X5vnTw=
-github.com/xeipuuv/gojsonpointer v0.0.0-20180127040702-4e3ac2762d5f/go.mod h1:N2zxlSyiKSe5eX1tZViRH5QA0qijqEDrYZiPEAiq3wU=
-github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb h1:zGWFAtiMcyryUHoUjUJX0/lt1H2+i2Ka2n+D3DImSNo=
-github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb/go.mod h1:N2zxlSyiKSe5eX1tZViRH5QA0qijqEDrYZiPEAiq3wU=
-github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 h1:EzJWgHovont7NscjpAxXsDA8S8BMYve8Y5+7cuRE7R0=
-github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415/go.mod h1:GwrjFmJcFw6At/Gs6z4yjiIwzuJ1/+UwLxMQDVQXShQ=
-github.com/xeipuuv/gojsonschema v1.2.0 h1:LhYJRs+L4fBtjZUfuSZIKGeVu0QRy8e5Xi7D17UxZ74=
-github.com/xeipuuv/gojsonschema v1.2.0/go.mod h1:anYRn/JVcOK2ZgGU+IjEV4nwlhoK5sQluxsYJ78Id3Y=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
@@ -241,8 +216,6 @@ go.opentelemetry.io/otel/sdk/metric v1.39.0 h1:cXMVVFVgsIf2YL6QkRF4Urbr/aMInf+2W
 go.opentelemetry.io/otel/sdk/metric v1.39.0/go.mod h1:xq9HEVH7qeX69/JnwEfp6fVq5wosJsY1mt4lLfYdVew=
 go.opentelemetry.io/otel/trace v1.39.0 h1:2d2vfpEDmCJ5zVYz7ijaJdOF59xLomrvj7bjt6/qCJI=
 go.opentelemetry.io/otel/trace v1.39.0/go.mod h1:88w4/PnZSazkGzz/w84VHpQafiU4EtqqlVdxWy+rNOA=
-go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
-go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
 go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
@@ -62,6 +62,7 @@ func (r *Resolver) Chat(ctx context.Context, req ChatRequest) (ChatResponse, err
 	if strings.TrimSpace(req.UserID) == "" {
 		return ChatResponse{}, fmt.Errorf("user id is required")
 	}
+	skipHistory := req.MaxContextLoadTime < 0

 	chatModel, provider, err := r.selectChatModel(ctx, req)
 	if err != nil {
@@ -83,9 +84,12 @@ func (r *Resolver) Chat(ctx context.Context, req ChatRequest) (ChatResponse, err
 		language = req.Language
 	}

-	messages, err := r.loadHistoryMessages(ctx, req.UserID, maxContextLoadTime)
-	if err != nil {
-		return ChatResponse{}, err
+	var messages []GatewayMessage
+	if !skipHistory {
+		messages, err = r.loadHistoryMessages(ctx, req.UserID, maxContextLoadTime)
+		if err != nil {
+			return ChatResponse{}, err
+		}
 	}
 	if len(req.Messages) > 0 {
 		messages = append(messages, req.Messages...)
@@ -142,6 +146,7 @@ func (r *Resolver) StreamChat(ctx context.Context, req ChatRequest) (<-chan Stre
 			errChan <- fmt.Errorf("user id is required")
 			return
 		}
+		skipHistory := req.MaxContextLoadTime < 0

 		chatModel, provider, err := r.selectChatModel(ctx, req)
 		if err != nil {
@@ -166,10 +171,13 @@ func (r *Resolver) StreamChat(ctx context.Context, req ChatRequest) (<-chan Stre
 			language = req.Language
 		}

-		messages, err := r.loadHistoryMessages(ctx, req.UserID, maxContextLoadTime)
-		if err != nil {
-			errChan <- err
-			return
+		var messages []GatewayMessage
+		if !skipHistory {
+			messages, err = r.loadHistoryMessages(ctx, req.UserID, maxContextLoadTime)
+			if err != nil {
+				errChan <- err
+				return
+			}
 		}
 		if len(req.Messages) > 0 {
 			messages = append(messages, req.Messages...)
@@ -225,6 +233,7 @@ func (r *Resolver) postChat(ctx context.Context, payload agentGatewayRequest) (a
 		return agentGatewayResponse{}, err
 	}
 	url := r.gatewayBaseURL + "/chat"
+	fmt.Println("url", url)
 	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
 	if err != nil {
 		return agentGatewayResponse{}, err
@@ -257,15 +257,6 @@ func (h *ModelsHandler) DeleteByModelID(c echo.Context) error {
 // @Failure 404 {object} ErrorResponse
 // @Failure 500 {object} ErrorResponse
 // @Router /models/enable-as/{enableAs} [get]
-// GetByEnableAs godoc
-// @Summary Get default model by enable_as
-// @Description Get the default model configured for a specific purpose (chat, memory, or embedding)
-// @Tags models
-// @Param enableAs path string true "Enable as value (chat, memory, embedding)"
-// @Success 200 {object} models.GetResponse
-// @Failure 400 {object} ErrorResponse
-// @Failure 404 {object} ErrorResponse
-// @Router /models/enable-as/{enableAs} [get]
 func (h *ModelsHandler) GetByEnableAs(c echo.Context) error {
 	enableAs := c.Param("enableAs")
 	if enableAs == "" {
@@ -1,5 +1,8 @@
 package handlers

+// @title Memoh API
+// @version 1.0.0
+
 import (
 	"net/http"
 	"os"
@@ -18,7 +18,6 @@
  },
  "dependencies": {
    "@elysiajs/eden": "^1.4.6",
-    "@memoh/api": "workspace:*",
    "@memoh/shared": "workspace:*",
    "elysia": "latest",
    "commander": "^12.1.0",