ai-zero-token 1.0.7 → 1.0.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +8 -0
- package/README.md +146 -395
- package/README.zh-CN.md +258 -0
- package/dist/cli/commands/serve.js +1 -0
- package/dist/core/providers/http-client.js +1 -1
- package/dist/core/services/auth-service.js +98 -7
- package/dist/core/services/config-service.js +15 -3
- package/dist/core/services/image-service.js +2 -7
- package/dist/core/services/version-service.js +18 -13
- package/dist/core/store/settings-store.js +6 -0
- package/dist/server/admin-page.js +1018 -103
- package/dist/server/app.js +68 -2
- package/dist/server/index.js +17 -2
- package/package.json +2 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 1.0.8 - 2026-04-29
|
|
4
|
+
|
|
5
|
+
- Removed local Free-plan blocking for image generation and editing; upstream account limits now decide availability.
|
|
6
|
+
- Switched image request orchestration to `gpt-5.4-mini` while keeping the requested image model on the `image_generation` tool.
|
|
7
|
+
- Increased the default gateway request body limit to 32 MiB and added `AZT_BODY_LIMIT_MB` for large JSON base64 image inputs.
|
|
8
|
+
- Updated the management-page update command to `npm install -g ai-zero-token`.
|
|
9
|
+
- Reworked the README into a cleaner open-source project format and added `README.zh-CN.md` for Simplified Chinese.
|
|
10
|
+
|
|
3
11
|
## 1.0.7 - 2026-04-29
|
|
4
12
|
|
|
5
13
|
- Added JSON `POST /v1/images/edits` support for image-to-image workflows with URL, base64 data URL, or raw base64 image references.
|
package/README.md
CHANGED
|
@@ -1,507 +1,258 @@
|
|
|
1
1
|
# AI Zero Token
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[English](README.md) | [简体中文](README.zh-CN.md)
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
Local-first OpenAI-compatible gateway for ChatGPT/Codex OAuth accounts.
|
|
6
6
|
|
|
7
|
-
|
|
7
|
+
AI Zero Token provides a local CLI, web console, and HTTP gateway that expose saved ChatGPT/Codex account capabilities through OpenAI-style endpoints. It is designed for local single-user workflows, prototyping, automation, and OpenAI-compatible clients.
|
|
8
8
|
|
|
9
|
-
-
|
|
10
|
-
- `POST /v1/images/edits`
|
|
11
|
-
- `POST /v1/responses`
|
|
12
|
-
- `POST /v1/chat/completions`
|
|
13
|
-
- `GET /v1/models`
|
|
9
|
+
> This is an experimental local tool. It is not an official OpenAI product and is not recommended as a production multi-tenant gateway.
|
|
14
10
|
|
|
15
|
-
|
|
11
|
+
## Features
|
|
16
12
|
|
|
17
|
-
|
|
13
|
+
- OpenAI-compatible local API:
|
|
14
|
+
- `GET /v1/models`
|
|
15
|
+
- `POST /v1/responses`
|
|
16
|
+
- `POST /v1/chat/completions`
|
|
17
|
+
- `POST /v1/images/generations`
|
|
18
|
+
- `POST /v1/images/edits`
|
|
19
|
+
- ChatGPT/Codex OAuth login with local token refresh.
|
|
20
|
+
- Multi-account management in the web console.
|
|
21
|
+
- Account JSON import/export, including selected batch export.
|
|
22
|
+
- Apply a saved account to local Codex by backing up and updating `~/.codex/auth.json`.
|
|
23
|
+
- `gpt-image-2` image generation and JSON image editing through the ChatGPT internal Responses path.
|
|
24
|
+
- Optional quota-exhaustion auto switch to the next saved API account with available quota.
|
|
25
|
+
- Optional upstream proxy configuration for OAuth, model refresh, and gateway forwarding.
|
|
26
|
+
- Local model discovery from the Codex model cache with manual refresh support.
|
|
18
27
|
|
|
19
|
-
|
|
20
|
-
- 启动 `azt start` 后即可获得本地管理页和本地网关,适合脚本、前端和自动化流程接入
|
|
21
|
-
- 支持多账号保存、切换当前账号、查看账号套餐 plan,以及当前账号是否支持生图
|
|
22
|
-
- 支持账号 JSON 批量导入/勾选导出,并可一键把已保存账号应用到本机 Codex
|
|
23
|
-
- 模型列表会优先同步本机 `~/.codex/models_cache.json`,不需要每次为新模型重新 build
|
|
24
|
-
- 管理页会每 10 分钟自动同步额度快照和版本状态,并提示当前版本是否可更新
|
|
25
|
-
- `free` 账号会在管理页直接预警,并在网关层明确拦截生图请求
|
|
28
|
+
## Architecture
|
|
26
29
|
|
|
27
|
-
|
|
30
|
+

|
|
28
31
|
|
|
29
|
-
|
|
32
|
+
AI Zero Token keeps account tokens and gateway settings in local state, exposes OpenAI-compatible HTTP endpoints, and forwards requests to the selected ChatGPT/Codex OAuth account. The web console reads the same local state, so account switching, Codex auth application, proxy settings, and automatic switching are all controlled from one local place.
|
|
30
33
|
|
|
31
|
-
##
|
|
34
|
+
## Quick Start
|
|
32
35
|
|
|
33
36
|
```bash
|
|
34
37
|
npm install -g ai-zero-token
|
|
35
38
|
azt start
|
|
36
39
|
```
|
|
37
40
|
|
|
38
|
-
|
|
41
|
+
The command starts the local web console and gateway:
|
|
39
42
|
|
|
40
43
|
```text
|
|
44
|
+
http://127.0.0.1:8787
|
|
41
45
|
http://127.0.0.1:8787/v1
|
|
42
46
|
```
|
|
43
47
|
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-

|
|
47
|
-
|
|
48
|
-
## 生图结果预览
|
|
49
|
-
|
|
50
|
-
下图通过 AI Zero Token 本地网关调用 `POST /v1/images/generations` 生成,模型为 `gpt-image-2`。
|
|
51
|
-
|
|
52
|
-

|
|
53
|
-
|
|
54
|
-
## 为什么做这个项目
|
|
55
|
-
|
|
56
|
-
如果你只是想在自己的电脑上更低门槛地接入主流 LLM,现实里通常会遇到这几个问题:
|
|
57
|
-
|
|
58
|
-
- 已经有产品订阅,但还没有开发者 API 方案
|
|
59
|
-
- 想把能力接入自己的脚本、前端、本地工作流,但不想每次都手工操作网页
|
|
60
|
-
- 想统一本地调用方式,而不是每家产品各写一套接入逻辑
|
|
61
|
-
- 想学习 OAuth、CLI、网关、npm CLI、桌面端这类真实工程能力
|
|
62
|
-
|
|
63
|
-
AI Zero Token 就是围绕这些问题设计的。
|
|
64
|
-
|
|
65
|
-
## 它能解决什么
|
|
66
|
-
|
|
67
|
-
- 想把 ChatGPT 的图片生成能力接到自己的前端、小工具或脚本里
|
|
68
|
-
- 想先用本地网关验证产品原型,而不是一上来就重做整套后端
|
|
69
|
-
- 想统一成 OpenAI 风格接口,减少接入成本
|
|
70
|
-
- 想研究一条完整的 OAuth -> token -> 本地状态 -> 网关 -> 上游请求链路
|
|
71
|
-
|
|
72
|
-
## 架构概览
|
|
73
|
-
|
|
74
|
-

|
|
75
|
-
|
|
76
|
-
## 当前能做什么
|
|
77
|
-
|
|
78
|
-
- 通过 `POST /v1/images/generations` 代理 `gpt-image-2` 生图请求
|
|
79
|
-
- 通过 OpenAI Codex OAuth 登录
|
|
80
|
-
- 在本地保存 `access_token` 和 `refresh_token`
|
|
81
|
-
- 支持保存多个账号 profile,并手动切换当前生效账号
|
|
82
|
-
- 在 token 过期时自动刷新
|
|
83
|
-
- 通过 `azt start` 一键启动本地 HTTP 网关和管理页面
|
|
84
|
-
- 在管理页面里完成多账号登录、查看账号状态、切换当前账号、切换默认模型、测试接口
|
|
85
|
-
- 模型列表优先读取本机 Codex 最新缓存,并支持在 CLI / 管理页手动同步
|
|
86
|
-
- 暴露 OpenAI 风格接口:
|
|
87
|
-
- `GET /v1/models`
|
|
88
|
-
- `POST /v1/responses`
|
|
89
|
-
- `POST /v1/chat/completions`
|
|
90
|
-
- `POST /v1/images/generations`
|
|
91
|
-
|
|
92
|
-
## 适合谁用
|
|
48
|
+
Use any non-empty API key value when a client requires one. Authentication is handled by the local gateway.
|
|
93
49
|
|
|
94
|
-
|
|
95
|
-
- 想把 `gpt-image-2` 生图接口直接接给脚本、前端或自动化流程的人
|
|
96
|
-
- 想做自己的 AI 网关、AI CLI、AI 桌面端的人
|
|
97
|
-
- 想学习一条完整 OAuth -> token -> CLI -> HTTP API 链路的人
|
|
98
|
-
- 想把 AI 能力接入脚本、前端或自动化流程的人
|
|
50
|
+
## Web Console
|
|
99
51
|
|
|
52
|
+
The web console is the recommended entry point:
|
|
100
53
|
|
|
101
|
-
|
|
54
|
+
- Log in with OpenAI Codex OAuth.
|
|
55
|
+
- Import one or more account JSON files.
|
|
56
|
+
- Switch the active account.
|
|
57
|
+
- Export one account or selected accounts.
|
|
58
|
+
- Apply a saved account to local Codex.
|
|
59
|
+
- Configure the default text model and upstream proxy.
|
|
60
|
+
- Enable automatic account switching when the active API account has exhausted its recorded quota.
|
|
61
|
+
- Test `models`, `responses`, `chat.completions`, `images.generations`, and `images.edits`.
|
|
102
62
|
|
|
103
|
-
|
|
104
|
-
- Bun 可用于开发和直接运行源码
|
|
105
|
-
- 终端网络需要可访问:
|
|
106
|
-
- `https://auth.openai.com`
|
|
107
|
-
- `https://chatgpt.com`
|
|
63
|
+

|
|
108
64
|
|
|
109
|
-
##
|
|
65
|
+
## API Usage
|
|
110
66
|
|
|
111
|
-
###
|
|
112
|
-
|
|
113
|
-
克隆仓库并安装依赖:
|
|
67
|
+
### Models
|
|
114
68
|
|
|
115
69
|
```bash
|
|
116
|
-
|
|
117
|
-
cd AI-Zero-Token
|
|
118
|
-
npm install
|
|
70
|
+
curl http://127.0.0.1:8787/v1/models
|
|
119
71
|
```
|
|
120
72
|
|
|
121
|
-
|
|
73
|
+
### Responses
|
|
122
74
|
|
|
123
75
|
```bash
|
|
124
|
-
|
|
76
|
+
curl http://127.0.0.1:8787/v1/responses \
|
|
77
|
+
-H "content-type: application/json" \
|
|
78
|
+
-d '{"model":"gpt-5.4","input":"Reply with OK only."}'
|
|
125
79
|
```
|
|
126
80
|
|
|
127
|
-
###
|
|
128
|
-
|
|
129
|
-
如果你只是想把它当作本地 CLI 和本地网关使用,可以直接全局安装:
|
|
81
|
+
### Chat Completions
|
|
130
82
|
|
|
131
83
|
```bash
|
|
132
|
-
|
|
84
|
+
curl http://127.0.0.1:8787/v1/chat/completions \
|
|
85
|
+
-H "content-type: application/json" \
|
|
86
|
+
-d '{
|
|
87
|
+
"model": "gpt-5.4",
|
|
88
|
+
"messages": [
|
|
89
|
+
{
|
|
90
|
+
"role": "user",
|
|
91
|
+
"content": "Reply with OK only."
|
|
92
|
+
}
|
|
93
|
+
]
|
|
94
|
+
}'
|
|
133
95
|
```
|
|
134
96
|
|
|
135
|
-
|
|
97
|
+
### Image Generation
|
|
136
98
|
|
|
137
99
|
```bash
|
|
138
|
-
|
|
139
|
-
|
|
100
|
+
curl http://127.0.0.1:8787/v1/images/generations \
|
|
101
|
+
-H "content-type: application/json" \
|
|
102
|
+
-d '{
|
|
103
|
+
"model": "gpt-image-2",
|
|
104
|
+
"prompt": "A clean product photo of a red apple on a white background.",
|
|
105
|
+
"size": "1024x1024",
|
|
106
|
+
"quality": "low",
|
|
107
|
+
"response_format": "b64_json"
|
|
108
|
+
}'
|
|
140
109
|
```
|
|
141
110
|
|
|
142
|
-
|
|
111
|
+
The gateway returns an OpenAI-style response with `data[].b64_json`.
|
|
143
112
|
|
|
144
|
-
-
|
|
113
|
+

|
|
145
114
|
|
|
146
|
-
|
|
115
|
+
### Image Editing
|
|
147
116
|
|
|
148
|
-
|
|
117
|
+
`/v1/images/edits` currently supports JSON requests with URL, data URL, or raw base64 image references:
|
|
149
118
|
|
|
150
119
|
```bash
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
|
|
154
|
-
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
120
|
+
curl http://127.0.0.1:8787/v1/images/edits \
|
|
121
|
+
-H "content-type: application/json" \
|
|
122
|
+
-d '{
|
|
123
|
+
"model": "gpt-image-2",
|
|
124
|
+
"prompt": "Use this reference image and create a cleaner product advertisement version.",
|
|
125
|
+
"images": [
|
|
126
|
+
{
|
|
127
|
+
"image_url": "data:image/png;base64,REPLACE_WITH_IMAGE_BASE64"
|
|
128
|
+
}
|
|
129
|
+
],
|
|
130
|
+
"size": "1024x1024",
|
|
131
|
+
"quality": "low",
|
|
132
|
+
"response_format": "b64_json"
|
|
133
|
+
}'
|
|
164
134
|
```
|
|
165
135
|
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
接下来在管理页里完成这几件事:
|
|
136
|
+
More examples are available in [docs/API_USAGE.md](docs/API_USAGE.md).
|
|
169
137
|
|
|
170
|
-
|
|
171
|
-
- 查看当前账号状态和过期时间
|
|
172
|
-
- 在已保存账号之间切换当前使用账号
|
|
173
|
-
- 切换默认模型
|
|
174
|
-
- 直接测试 `models`、`responses`、`chat.completions`
|
|
175
|
-
- 直接测试 `images.generations` 生图接口
|
|
138
|
+
## Account Management
|
|
176
139
|
|
|
177
|
-
|
|
140
|
+
AI Zero Token stores account state locally under:
|
|
178
141
|
|
|
179
142
|
```text
|
|
180
|
-
|
|
143
|
+
~/.ai-zero-token/.state
|
|
181
144
|
```
|
|
182
145
|
|
|
183
|
-
|
|
146
|
+
The web console supports:
|
|
184
147
|
|
|
185
|
-
-
|
|
148
|
+
- OAuth login.
|
|
149
|
+
- JSON import from a single profile, an array, or a `profiles` bundle.
|
|
150
|
+
- Single-account export.
|
|
151
|
+
- Selected batch export using checkboxes.
|
|
152
|
+
- Account deletion and active-account switching.
|
|
186
153
|
|
|
187
|
-
|
|
154
|
+
Exported account JSON includes authentication tokens and should be treated as a secret.
|
|
188
155
|
|
|
189
|
-
|
|
190
|
-
|
|
191
|
-
```bash
|
|
192
|
-
AZT_CORS_ORIGIN=http://127.0.0.1:8124 azt start
|
|
193
|
-
```
|
|
156
|
+
### Apply to Codex
|
|
194
157
|
|
|
195
|
-
|
|
158
|
+
The `Apply to Codex` action writes the selected account to:
|
|
196
159
|
|
|
197
|
-
```
|
|
198
|
-
|
|
199
|
-
```
|
|
200
|
-
|
|
201
|
-
如果你当前还没有全局命令,也可以把上面的 `azt` 临时替换成:
|
|
202
|
-
|
|
203
|
-
```bash
|
|
204
|
-
bun src/cli.ts
|
|
205
|
-
```
|
|
206
|
-
|
|
207
|
-
例如:`bun src/cli.ts start`
|
|
208
|
-
|
|
209
|
-
## 网关使用说明
|
|
210
|
-
|
|
211
|
-
如果你主要把 AI Zero Token 当作本地网关来使用,推荐只记住一个命令:
|
|
212
|
-
|
|
213
|
-
### 1. 启动
|
|
214
|
-
|
|
215
|
-
```bash
|
|
216
|
-
azt start
|
|
160
|
+
```text
|
|
161
|
+
~/.codex/auth.json
|
|
217
162
|
```
|
|
218
163
|
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
- 触发 OpenAI Codex OAuth 登录并新增账号
|
|
222
|
-
- 查看当前账号、已保存账号列表、过期时间、token 摘要
|
|
223
|
-
- 查看账号套餐 plan 和当前账号是否支持生图
|
|
224
|
-
- 在多个已保存账号之间切换当前使用账号
|
|
225
|
-
- 在“新增账号”里选择 OAuth 登录,或粘贴外部账号 JSON 批量导入
|
|
226
|
-
- 导出单个账号,或勾选多个账号后批量导出所选账号 JSON
|
|
227
|
-
- 将任一已保存账号“应用到 Codex”,自动备份并更新本机 `~/.codex/auth.json`
|
|
228
|
-
- 删除单个本地账号,或一键清空全部本地账号
|
|
229
|
-
- 切换默认模型
|
|
230
|
-
- 测试 `models` / `responses` / `chat.completions`
|
|
231
|
-
- 测试 `images.generations`
|
|
232
|
-
|
|
233
|
-
管理页里邮箱默认脱敏显示,需要手动点击“查看邮箱”才会显示明文。
|
|
234
|
-
|
|
235
|
-
导出的账号 JSON 包含完整 `access_token` 和 `refresh_token`,等同于账号登录凭据,只适合在可信环境中传递。
|
|
236
|
-
|
|
237
|
-
账号卡片里的“应用到 Codex”会把该账号的 `access_token`、`refresh_token`、`id_token` 和 `account_id` 写入本机 Codex 的 `~/.codex/auth.json`。写入前会自动备份原文件;新开的 Codex 会话会使用该账号。
|
|
164
|
+
Before writing, the existing file is backed up as `auth.json.azt-backup-*`. New Codex sessions will use the applied account.
|
|
238
165
|
|
|
239
|
-
|
|
166
|
+
## Configuration
|
|
240
167
|
|
|
241
|
-
|
|
168
|
+
Default listener:
|
|
242
169
|
|
|
243
170
|
```text
|
|
244
|
-
|
|
171
|
+
0.0.0.0:8787
|
|
245
172
|
```
|
|
246
173
|
|
|
247
|
-
|
|
174
|
+
Local gateway base URL:
|
|
248
175
|
|
|
249
176
|
```text
|
|
250
|
-
http://127.0.0.1:8787
|
|
177
|
+
http://127.0.0.1:8787/v1
|
|
251
178
|
```
|
|
252
179
|
|
|
253
|
-
|
|
180
|
+
Restrict browser CORS origins:
|
|
254
181
|
|
|
255
|
-
```
|
|
256
|
-
|
|
182
|
+
```bash
|
|
183
|
+
AZT_CORS_ORIGIN=http://127.0.0.1:8124 azt start
|
|
257
184
|
```
|
|
258
185
|
|
|
259
|
-
|
|
260
|
-
|
|
261
|
-
客户端或 SDK 里把 Base URL 改成:
|
|
186
|
+
Multiple origins can be separated by commas:
|
|
262
187
|
|
|
263
|
-
```
|
|
264
|
-
http://127.0.0.1:
|
|
188
|
+
```bash
|
|
189
|
+
AZT_CORS_ORIGIN=http://127.0.0.1:8124,http://localhost:3000 azt start
|
|
265
190
|
```
|
|
266
191
|
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
### 3. 查看模型列表
|
|
270
|
-
|
|
271
|
-
OpenAI 风格模型接口:
|
|
192
|
+
The persistent state directory can be overridden with:
|
|
272
193
|
|
|
273
194
|
```bash
|
|
274
|
-
|
|
195
|
+
AI_ZERO_TOKEN_HOME=/path/to/home azt start
|
|
275
196
|
```
|
|
276
197
|
|
|
277
|
-
|
|
198
|
+
The web console settings are persisted in the same local state directory. The quota auto-switch option is stored as `autoSwitch.enabled`; when enabled, the gateway uses the latest saved quota snapshot and moves API traffic away from the active account once that snapshot shows a quota window is exhausted.
|
|
278
199
|
|
|
279
|
-
|
|
200
|
+
The default request body limit is `32 MiB`, which is intended to make JSON base64 image references practical for local image editing. You can override it with:
|
|
280
201
|
|
|
281
202
|
```bash
|
|
282
|
-
|
|
283
|
-
-H "content-type: application/json" \
|
|
284
|
-
-d '{"model":"gpt-5.4","input":"请只回复 OK"}'
|
|
203
|
+
AZT_BODY_LIMIT_MB=64 azt start
|
|
285
204
|
```
|
|
286
205
|
|
|
287
|
-
|
|
206
|
+
## Image Limits
|
|
288
207
|
|
|
289
|
-
|
|
290
|
-
curl http://127.0.0.1:8787/v1/responses \
|
|
291
|
-
-H "content-type: application/json" \
|
|
292
|
-
-d '{"model":"gpt-5.4","instructions":"你是一个简洁助手","input":"请只回复 OK"}'
|
|
293
|
-
```
|
|
208
|
+
ChatGPT Images availability and limits are controlled by the upstream account. Free accounts can attempt image generation, but rate limits and feature availability are stricter than paid plans and are not published as fixed public numbers. The gateway forwards image requests and surfaces the upstream response, for example `usage_limit_reached` with reset information.
|
|
294
209
|
|
|
295
|
-
|
|
210
|
+
Image requests use `gpt-5.4-mini` as the internal orchestration model and pass the requested image model, such as `gpt-image-2`, to the `image_generation` tool.
|
|
296
211
|
|
|
297
|
-
|
|
298
|
-
curl http://127.0.0.1:8787/v1/chat/completions \
|
|
299
|
-
-H "content-type: application/json" \
|
|
300
|
-
-d '{
|
|
301
|
-
"model": "gpt-5.4",
|
|
302
|
-
"messages": [
|
|
303
|
-
{
|
|
304
|
-
"role": "user",
|
|
305
|
-
"content": "请只回复 OK"
|
|
306
|
-
}
|
|
307
|
-
]
|
|
308
|
-
}'
|
|
309
|
-
```
|
|
212
|
+
For JSON image editing, base64 payloads are about 33% larger than the original image. With the default `32 MiB` body limit, a raw image around `24 MiB` is the practical upper bound before JSON overhead. For larger images or batch workflows, prefer a reachable image URL.
|
|
310
213
|
|
|
311
|
-
|
|
214
|
+
## Limitations
|
|
312
215
|
|
|
313
|
-
|
|
216
|
+
- This project is intended for local single-user use.
|
|
217
|
+
- Streaming request fields are recognized, but full streaming parity is not implemented for every endpoint.
|
|
218
|
+
- `/v1/images/generations` currently returns `b64_json`; hosted image URLs are not supported.
|
|
219
|
+
- `/v1/images/generations` does not support `n > 1`.
|
|
220
|
+
- `/v1/images/edits` currently supports JSON only. `multipart/form-data`, `mask`, and `file_id` are not yet supported.
|
|
221
|
+
- Very large base64 JSON requests are constrained by `AZT_BODY_LIMIT_MB` and local memory.
|
|
222
|
+
- OpenAI Responses API compatibility is partial and focused on common local client workflows.
|
|
314
223
|
|
|
315
|
-
|
|
316
|
-
|
|
317
|
-
|
|
318
|
-
|
|
319
|
-
|
|
320
|
-
|
|
321
|
-
"size": "1024x1024",
|
|
322
|
-
"quality": "low",
|
|
323
|
-
"response_format": "b64_json"
|
|
324
|
-
}'
|
|
325
|
-
```
|
|
224
|
+
## Security
|
|
225
|
+
|
|
226
|
+
- Access tokens, refresh tokens, and ID tokens are equivalent to login credentials.
|
|
227
|
+
- Do not expose the gateway to untrusted networks.
|
|
228
|
+
- Do not share exported account JSON outside trusted environments.
|
|
229
|
+
- Review files under `~/.ai-zero-token/.state` and `~/.codex/auth.json` before copying or publishing local data.
|
|
326
230
|
|
|
327
|
-
|
|
328
|
-
如果请求里不显式传 `model`,当前默认会使用 `gpt-image-2`。
|
|
231
|
+
## Development
|
|
329
232
|
|
|
330
|
-
|
|
233
|
+
Install dependencies:
|
|
331
234
|
|
|
332
235
|
```bash
|
|
333
|
-
|
|
334
|
-
-H "content-type: application/json" \
|
|
335
|
-
-d '{
|
|
336
|
-
"model": "gpt-image-2",
|
|
337
|
-
"prompt": "参考这张图,生成一张更适合科技产品广告的版本。",
|
|
338
|
-
"images": [
|
|
339
|
-
{
|
|
340
|
-
"image_url": "data:image/png;base64,替换为你的图片base64"
|
|
341
|
-
}
|
|
342
|
-
],
|
|
343
|
-
"size": "1024x1024",
|
|
344
|
-
"quality": "low",
|
|
345
|
-
"response_format": "b64_json"
|
|
346
|
-
}'
|
|
236
|
+
npm install
|
|
347
237
|
```
|
|
348
238
|
|
|
349
|
-
|
|
350
|
-
|
|
351
|
-
- `plus` 或更高套餐账号可正常调用 `images.generations` / `images.edits`
|
|
352
|
-
- `free` 账号不支持生图,网关会直接返回明确错误,而不是继续请求上游
|
|
353
|
-
- 管理页会显示当前账号的 `plan` 和“生图能力”状态
|
|
354
|
-
- 当当前账号是 `free` 且你选中 `Images` 测试时,“发送请求”按钮会被直接禁用
|
|
355
|
-
|
|
356
|
-
### 6. 当前支持的接口
|
|
357
|
-
|
|
358
|
-
- `GET /_gateway/health`
|
|
359
|
-
- `GET /_gateway/status`
|
|
360
|
-
- `GET /_gateway/models`
|
|
361
|
-
- `POST /_gateway/models/refresh`
|
|
362
|
-
- `GET /_gateway/admin/config`
|
|
363
|
-
- `POST /_gateway/admin/login`
|
|
364
|
-
- `POST /_gateway/admin/logout`
|
|
365
|
-
- `POST /_gateway/admin/profiles/activate`
|
|
366
|
-
- `POST /_gateway/admin/profiles/remove`
|
|
367
|
-
- `PUT /_gateway/admin/settings`
|
|
368
|
-
- `GET /v1/models`
|
|
369
|
-
- `POST /v1/responses`
|
|
370
|
-
- `POST /v1/chat/completions`
|
|
371
|
-
- `POST /v1/images/generations`
|
|
372
|
-
- `POST /v1/images/edits`
|
|
373
|
-
|
|
374
|
-
### 7. 当前支持的主要参数
|
|
375
|
-
|
|
376
|
-
`POST /v1/responses` 当前主要支持:
|
|
377
|
-
|
|
378
|
-
- `model`
|
|
379
|
-
- `input`
|
|
380
|
-
- `instructions`
|
|
381
|
-
- `stream`
|
|
382
|
-
- `tools`
|
|
383
|
-
- `tool_choice`
|
|
384
|
-
- `include`
|
|
385
|
-
- `text`
|
|
386
|
-
- `store`
|
|
387
|
-
- `parallel_tool_calls`
|
|
388
|
-
- `experimental_codex.body`
|
|
389
|
-
- `experimental_codex.allow_unknown_model`
|
|
390
|
-
- `experimental_codex.include_raw`
|
|
391
|
-
|
|
392
|
-
`POST /v1/chat/completions` 当前主要支持:
|
|
393
|
-
|
|
394
|
-
- `model`
|
|
395
|
-
- `messages`
|
|
396
|
-
- `tools`
|
|
397
|
-
- `tool_choice`
|
|
398
|
-
- `response_format`
|
|
399
|
-
- `temperature`
|
|
400
|
-
- `top_p`
|
|
401
|
-
- `presence_penalty`
|
|
402
|
-
- `frequency_penalty`
|
|
403
|
-
- `metadata`
|
|
404
|
-
- `stop`
|
|
405
|
-
- `store`
|
|
406
|
-
- `parallel_tool_calls`
|
|
407
|
-
|
|
408
|
-
`POST /v1/images/generations` 当前主要支持:
|
|
409
|
-
|
|
410
|
-
- `prompt`
|
|
411
|
-
- `model`
|
|
412
|
-
- `n`
|
|
413
|
-
- `size`
|
|
414
|
-
- `quality`
|
|
415
|
-
- `background`
|
|
416
|
-
- `output_format`
|
|
417
|
-
- `output_compression`
|
|
418
|
-
- `moderation`
|
|
419
|
-
- `response_format`
|
|
420
|
-
- `user`
|
|
421
|
-
|
|
422
|
-
`POST /v1/images/edits` 当前主要支持 JSON 请求:
|
|
423
|
-
|
|
424
|
-
- `prompt`
|
|
425
|
-
- `images`
|
|
426
|
-
- `image`
|
|
427
|
-
- `model`
|
|
428
|
-
- `n`
|
|
429
|
-
- `size`
|
|
430
|
-
- `quality`
|
|
431
|
-
- `background`
|
|
432
|
-
- `output_format`
|
|
433
|
-
- `output_compression`
|
|
434
|
-
- `moderation`
|
|
435
|
-
- `response_format`
|
|
436
|
-
- `user`
|
|
437
|
-
|
|
438
|
-
其中 `images` / `image` 支持 `image_url`,可以是 `https://...` URL、`data:image/...;base64,...`,或裸 base64 字符串。
|
|
439
|
-
|
|
440
|
-
### 8. 当前限制
|
|
441
|
-
|
|
442
|
-
- `stream=true` 目前只识别,不返回真实流式结果
|
|
443
|
-
- 还没有完整覆盖 OpenAI Responses API 的全部字段
|
|
444
|
-
- `chat.completions` 暂不支持 `n > 1`
|
|
445
|
-
- `images.generations` 暂不支持 `n > 1`
|
|
446
|
-
- `images.generations` 当前只返回 `b64_json`,暂不支持托管图片 `url`
|
|
447
|
-
- `images.generations` 当前只透传 GPT Image 路径,不兼容 DALL·E 专有参数
|
|
448
|
-
- `images.edits` 当前只支持 `application/json`,暂不支持 `multipart/form-data`、`mask` 和 `file_id`
|
|
449
|
-
- `images.generations` / `images.edits` 对账号套餐有要求;`free` 账号会被网关直接拦截并返回“不支持图片生成”
|
|
450
|
-
- 网关当前默认面向本地单用户使用
|
|
451
|
-
|
|
452
|
-
## 兼容说明
|
|
453
|
-
|
|
454
|
-
代码里仍然保留了 `login`、`status`、`models`、`profiles`、`ask`、`serve`、`clear` 等 CLI 命令,主要用于调试、兼容和后续扩展。
|
|
455
|
-
|
|
456
|
-
账号 JSON 也可以通过 CLI 导入/导出:
|
|
239
|
+
Run from source:
|
|
457
240
|
|
|
458
241
|
```bash
|
|
459
|
-
|
|
460
|
-
azt profiles export active ./profile.json
|
|
461
|
-
azt profiles export all ./profiles.json
|
|
462
|
-
azt profiles export "openai-codex:<accountId>" ./profile.json
|
|
242
|
+
bun src/cli.ts start
|
|
463
243
|
```
|
|
464
244
|
|
|
465
|
-
|
|
245
|
+
Validate:
|
|
466
246
|
|
|
467
247
|
```bash
|
|
468
|
-
|
|
248
|
+
npm run typecheck
|
|
249
|
+
npm run build
|
|
469
250
|
```
|
|
470
251
|
|
|
471
|
-
|
|
472
|
-
|
|
473
|
-
如果你在使用过程中遇到安装问题、账号切换问题、生图异常,或者想交流自己的接入场景,可以通过下面两种方式联系我:
|
|
474
|
-
|
|
475
|
-
- GitHub Issues: [https://github.com/fchangjun/AI-Zero-Token/issues](https://github.com/fchangjun/AI-Zero-Token/issues)
|
|
476
|
-
- 微信交流:先加我微信,备注 `AI Zero Token`,我会再拉你进交流群
|
|
477
|
-
|
|
478
|
-
如果你已经把二维码放到仓库里,可以直接查看:
|
|
479
|
-
|
|
480
|
-

|
|
481
|
-
|
|
482
|
-
## 本地状态
|
|
483
|
-
|
|
484
|
-
项目会在仓库目录下写入:
|
|
485
|
-
|
|
486
|
-
- `.state/store.json`
|
|
487
|
-
- `.state/settings.json`
|
|
488
|
-
|
|
489
|
-
它们分别用于保存:
|
|
252
|
+
CLI packaging and release notes are documented in [BUILD_CLI.md](BUILD_CLI.md). User-facing changes are tracked in [CHANGELOG.md](CHANGELOG.md).
|
|
490
253
|
|
|
491
|
-
|
|
492
|
-
- 默认模型和服务配置
|
|
254
|
+
## Project Status
|
|
493
255
|
|
|
494
|
-
|
|
256
|
+
AI Zero Token is evolving quickly. The current focus is a reliable local gateway, account transfer workflows, and image generation/editing compatibility for OpenAI-style clients.
|
|
495
257
|
|
|
496
|
-
|
|
497
|
-
CLI 命令解析和命令分发
|
|
498
|
-
- `src/core/`
|
|
499
|
-
核心业务逻辑
|
|
500
|
-
- `src/core/services/`
|
|
501
|
-
认证、模型、聊天、配置服务
|
|
502
|
-
- `src/core/store/`
|
|
503
|
-
本地状态读写
|
|
504
|
-
- `src/core/providers/openai-codex/`
|
|
505
|
-
OpenAI Codex provider 实现
|
|
506
|
-
- `src/server/`
|
|
507
|
-
本地 HTTP 网关
|
|
258
|
+
Issues and feature requests: [GitHub Issues](https://github.com/fchangjun/AI-Zero-Token/issues)
|