Compare commits

...

7 Commits

Author SHA1 Message Date
1be34557dd fix(trae): 登录失败真因 —— 虚构的「授权码交换」+ 空 client_id
用户报「TRAE 登录后显示失败」。定位到三处偏差,其中一处是核心缺陷:

① ★ **虚构了一次不存在的「授权码交换」**(核心)
   poll_login 的 trae 分支自己发明了一段逻辑:回调只带 code 时,拿
   exchange_body 去打 ExchangeToken。但:
     · ExchangeToken 的签名是 RefreshToken,不是 code;
     · exchange_body 里根本没有 {code} 占位符,那次替换是空操作;
     · client_id 当时是空串。
   于是稳定 400,日志回一句误导性的「Trae 授权码交换失败: 400」——
   把真因「上游走了 PKCE 流程」掩盖成「交换出错了」,排查方向完全错。

   按参考实现(trae-oauth.ts parseTraeCallbackDetailed)修正:带 code 的
   回调是**合法回调**,只是不支持的 PKCE 分支,必须明确报出来。
   删除虚构交换,两条路径共用 traeCallback 内建的 PKCE 判定。

② client_id 从空串改为实测真值 en1oxy7wnw8j9n(对齐参考 trae-product.ts
   的 clientId;ExchangeToken 请求体里 ClientID 必填,留空稳定 400)。

③ 两条路径(oauth_callback / poll_login)现在共用同一结论,不再漂移 ——
   这正是缺陷能藏住的原因:修复只覆盖一条、另一条继续错。

测试支撑:
- 新增 __set_loopback_probe(注入 loopback 回调文件),否则无法驱动
  poll_login 的 callback 分支(那才是真实登录走的路径)。
- 判据 4 条,全部做变异验证:
    TestTraePkceCallbackIsReportedNotExchanged  打 poll_login,断言没打 ExchangeToken 且点名 PKCE
    TestTraeExchangeSendsRealClientID           token 直传真调交换,请求体形状正确
    TestTraeClientIDIsNotBlank                  client_id 必须是实测真值
    TestTraeCallbackPathsAgreeOnPkce            两条路径必须共用 traeCallback
- 变异 2/2 咬住:client_id 改回空串 → 报红;虚构交换加回去 → 「实际打了 1 次
  ExchangeToken」。

★ 我在过程中自己犯的两个错(均由变异测试揭穿,已修正):
1. **判据打错了路径** —— 第一版打 oauth_callback(那条一直是对的),注入缺陷后
   判据**仍绿**。改成打 poll_login 才咬住。教训:判据必须打**真实被使用的那条
   路径**,否则等于没测。
2. **判据写错了契约** —— poll_login 用 HTTP 200 + json.state 表达终态,我按
   status != 200 断言,把正确的实现判成了错。

回归:go test -tags luajit ./... 10 包全绿。
2026-10-15 22:04:01 +08:00
9e5fec08b8 feat(opencode): Zen 免费层可用 —— 门禁四要素 + id 公式逆出
问题:localzen 源(opencode Zen)整个免费池恒 403 FreeTierError
("free tier can only be used from within OpenCode"),space-bunny-free
等免费模型全部失效。

排查(装官方 CLI 抓包 + 逆其本地 opencode.db,见下):门禁是**四条请求形状
条件**,与 TLS 指纹 / UA / 凭据来源 / system 内容 / 消息条数全部无关:

  1. 端点必须是 /inference/v1/chat/completions(原来打的 /zen/v1 恒 403)
  2. 必须同时发 x-opencode-session 与 x-opencode-session-id(值相同)
  3. tools 里必须有一个名为 read 的工具,且其 parameters.properties **非空**
     (实测:抽掉官方 11 个工具中任意一个仍 200,**只有抽掉 read 变 403**;
      properties 里放任意属性名即可,描述/$schema/required 都不需要;
      改成 properties:{} 或只有 type:object 则 403)
  4. stream 必须为 true(同 body 改 false 恒 403)

★ 两个 id 的 12 位 hex 段由**确定公式**给出(逆自 opencode.db 的 session 表,
用 11/12 条真实 id 逐条比对完全一致):

  MASK = 2^48-1 ; K = 0x1afffffffffffe   (注意不是 27<<48,两者差 2)
  session 段 = (K - now_ms*4096) & MASK   ← 倒计时式,Δseg/Δms ≡ -2^12
  request 段 = (now_ms*16) & MASK

  时间容差实测 ≥1 小时(-3600s 仍 200),故 os.time() 的秒精度足够;
  now_ms*4096 ≈ 7.3e15 < 2^53,在 double 安全整数范围内。

实现:
- id 生成换成上述公式(原用 sha256 派生,完全不符)
- 补 x-opencode-session-id;两个头同值
- 会话号按**整分钟桶**取:既满足门禁的倒计时公式,又保留上游前缀缓存命中
  (实测 cached_tokens: 256 生效)
- tools 兜底:客户端没带 tools 时注入带非空 properties 的 read 桩;
  用户自带 read 则原样保留,不覆盖其定义
- 强制 stream=true
- ★ transform_response 支持 SSE 聚合:免费层只能流式,而客户端可能发非流式,
  此时内核按客户端意图走 Chat/transform_response(期望 JSON)⇒ 必须自行把
  SSE 聚合成 chat.completion,否则报 "invalid character 'd'"

配置(已在生产落地):
- localzen base_url: /zen/v1 → /inference/v1(billing 规则同步)
- 免费模型 1 个 → 8 个(含 deepseek-v4.1-flash-free)
- 适配器移入 internal/lua/adapters/,随 deploy.sh 自动投放

判据(4 条):
- TestOpencodeZenAdapterE2E                       头公式/两头部同值/tools 兜底/不覆盖
- TestOpencodeZenAggregatesSSEForNonStreamClient   SSE → chat.completion 聚合
- TestOpencodeZenLiveE2E                          ★真上游:纯对话/自定义system/多轮/算术
- TestOpencodeZenLiveStreamThroughAdapter         ★真上游:完整流解析链(25 chunk)
  (后两条需 LLMSPROXY_LIVE_ZEN=1 + 真实凭据,默认 skip)

生产 e2e 实测:非流式返回 GW-NONSTREAM-OK(usage 含 cached_tokens 256);
流式原生 SSE 透传;多轮+工具返回正确结果(12*12=144 → 144+1=145)。

回归:go test -tags luajit ./... 10 包全绿。

★ 方法论教训(本轮绕了 4 轮、自我推翻 3 次):
- 一次只改一个变量。我多次同时改 system+条数+tools,拟合出"消息条数上限 3"
  这种假规律,后续每次反转都源于此 —— 真相是那些测试**都缺 tools**。
- 重放成功 ≠ 解释成功。第一次逐字节重放就 200,我却当"重放了官方刚发的请求",
  继续追 TLS 指纹/端点/形状。正确做法:一旦重放成功立刻做**单变量消去**。
- "毒药短语"陷阱:我二分到 963/964 字符精度锁定 Never use tools 是触发点,
  但它单独出现全 200 —— 真相是缺 read 的 properties。凡"某内容触发"的规律
  必须交叉验证。
2026-10-15 20:30:33 +08:00
68446fb6fe fix(vnc): noVNC 的 path 必须用相对名,否则 WebSocket 路径重复拼接
真实缺陷(白屏真因之一):view_url 里传了**站点根路径**作为 noVNC 的
path 参数:

  .../proxy/<id>/vnc.html?path=api%2Fplugins%2Fhttp%2Fchannels%2Fbrowser%2Fproxy%2F<id>%2Fwebsockify

但 noVNC 用 `new URL(path, location.href)` 解析它(app/ui.js 的 connect()),
即**相对 vnc.html 所在目录**解析,默认值就是相对名 "websockify"。传根路径
会被当相对路径 ⇒ 实际请求变成路径重复拼接:

  .../proxy/<id>/api/plugins/http/channels/browser/proxy/<id>/websockify

于是 WebSocket 永远连不上,noVNC 显示连接失败,页面看似白屏。

修法:只传相对名 path=websockify,与 noVNC 默认值一致。

★ 判据:必须解析**产品自己给出的 URL**(而不是测试里手拼)。我上一轮验证时
手拼 URL 并省掉了 path 参数(默认值恰好正确)⇒ 掩盖了这个真实缺陷。
新判据断言:path 存在、不以 / 开头、且 ResolveReference 后等于同级 websockify。
2026-10-15 20:30:33 +08:00
7e0a428c23 docs(plugins): 补「前缀代理」章节 —— 插件自起服务挂到网关同端口 2026-10-15 15:01:58 +08:00
7a8d97001c feat(插件代理): 同源反向代理 —— VNC 不再暴露额外端口
问题:登录返回的 view_url 是 http://127.0.0.1:60100/vnc.html,WebUI 直接把它
嵌进 iframe。远程运维打开必白屏 —— 127.0.0.1 在客户端指向客户端自己,且
websockify/x11vnc 只绑回环,换服务器 IP 也连不上(实测 LAN IP 访问 000)。

★ 教训:只验证"服务端截图有画面"就宣布 VNC 可用是不充分的。四层链路里
①X 渲染 ②noVNC 客户端渲染 一直是好的,白屏真因在第④层「客户端如何拿到地址」。

内核新增通用「插件前缀代理」能力(不是为 channels 写的专用反向代理):
- plugin.http 支持 prefix = true:声明前缀路由,承接所有子路径
- handler 返回 { proxy = "http://127.0.0.1:PORT" },内核每次请求都问一遍
  ⇒ 会话停止/过期后插件不再给目标,旧地址自然失效(撤销点唯一)
- 鉴权与角色门禁复用现有链路,无旁路
- statusRecorder 增加 Unwrap(),让 Hijack 穿透访问日志中间件(否则 WebSocket 升级失败)
- 目标只允许带显式端口的**字面回环 IP**(用户拍板方案 A):拒绝 https、localhost
  主机名、无端口、带 userinfo/path/query;理由是主机名可能被 hosts/DNS 改写
- 拒绝跨站 Origin(WebSocket 带环境 Cookie,否则第三方网页可借管理员会话开隧道)
- 不向插件后端转发 Authorization/Cookie/api_key

channels 接入:
- 新增 channels/browser/proxy/:session(prefix=true)
- 会话代号 = seq-随机8位,防猜到活跃会话
- view_url 改为网关同源路径,noVNC 的 WebSocket 走同前缀 /websockify
- 会话过期即回收浏览器栈并返回 404

判据(每条咬真实外部效应):
- 静态资源转发
- 真实 HTTP 101 升级 + 双向数据回传(只断言静态转发不够 —— 升级是白屏真考点)
- 网关凭据不泄漏(在服务端断言请求头)
- 非法目标全拒(公网/localhost/https/无端口/带 path、query、userinfo)
- 跨站 Origin 403
- 未鉴权 401、过期会话 404、非子路径 404

回归:go test -tags luajit ./... 9 包全绿
2026-10-15 14:57:13 +08:00
850920155a 避免部署构建占满临时文件系统 2026-10-15 13:01:58 +08:00
eaac0ef6b3 修复用量总计与渠道账本统计 2026-10-15 12:43:11 +08:00
17 changed files with 1474 additions and 61 deletions

View File

@ -36,8 +36,15 @@ readonly REPO_DIR="/home/program/llmsproxy"
readonly HEALTH_URL="http://127.0.0.1:8081/v1/models"
readonly BIN_NAME="llmsproxy"
# 构建目录在 /tmp(tmpfs 更快)
readonly TMP_DIR="/tmp/llmsproxy-deploy"
# 构建目录。默认落在仓库下的构建工作区,而不是 /tmp:本机 /tmp 是 8.8G
# tmpfs,实测被 Go 构建缓存占满后会让 go test/build 在链接阶段直接失败。
# 可用 LLMSPROXY_BUILD_DIR 覆盖;同一目录也被测试用作 GOTMPDIR。
readonly BUILD_SUBDIR=".build-work"
if [[ -n "${LLMSPROXY_BUILD_DIR:-}" ]]; then
readonly TMP_DIR="${LLMSPROXY_BUILD_DIR}"
else
readonly TMP_DIR="${REPO_DIR}/${BUILD_SUBDIR}"
fi
# 同文件系统暂存文件(用于原子 rename)
readonly STAGING_BIN="${TARGET_BIN}.staging"
readonly STAGING_CONFIG="${TARGET_CONFIG}.staging"
@ -142,7 +149,7 @@ build() {
mkdir -p "$TMP_DIR/bin"
cd "$REPO_DIR"
CGO_ENABLED=1 go build -tags luajit \
CGO_ENABLED=1 GOTMPDIR="$TMP_DIR" go build -tags luajit \
-trimpath \
-ldflags="-s -w" \
-o "$TMP_DIR/bin/$BIN_NAME" \

View File

@ -377,7 +377,48 @@ plugin.http = {
路径,未认证会跳登录页。
- 未声明的路径不会因为落在允许命名空间而被放行——不在 handler 表里就是 404。
### 5.6 在运行时安装/更新适配器(token 轮换)
### 5.6 前缀代理:把插件自起的服务挂到网关同端口
前节的自定义挂载点只能回答**由插件计算出来的内容**(`{status, headers, body/json}`)。
若插件自己起了一个 TCP/HTTP 服务(典型:服务端浏览器栈 + noVNC),客户端就需要
**字节级转发**,包括 **WebSocket 升级** —— 前者做不到。
为此声明 `prefix = true`,handler 每次请求返回一个**回环目标**:
```lua
plugin.http = {
{ path = "myplugin/proxy/:session", method = "GET", prefix = true,
roles = { "admin" }, handler = "proxy" },
}
function plugin.proxy(req)
-- 每次请求都问一遍:会话没了/过期了就返回 404,地址自然失效
if not sessionAlive(req.params.session) then
return { status = 404, json = { error = "no such session" } }
end
return { proxy = "http://127.0.0.1:60100" }
end
```
规则:
- **只能返回 `{ proxy = <目标> }`**,没有 `status` / `body`。写了 `status` 会被忽略。
- 目标必须是 **带显式端口的字面回环 IP**(`http://127.0.0.1:60100`)。
拒绝 `https://`、`localhost` 这类主机名、无端口、带 userinfo/path/query 的地址。
理由:主机名可能被 hosts / DNS / 代理环境改写;通用能力只接受确定性地址。
- 路由匹配同前缀下的**所有子路径**,`:param` 仍照常捕获,`req.path` 是完整
请求路径,子路径由插件自己从 `req.path` 里切。
- **鉴权先于代理**:`roles` / `keys` / `public` 语义与普通端点一致。
- **不转发网关凭据**:`Authorization`、`Cookie`、`api_key` 都不会传给后端服务。
- **拒绝跨站**:`Origin` 与网关自身 host 不一致返回 403。WebSocket 由浏览器
发起且自动带 Cookie,否则第三方网页可借管理员会话开隧道。
- **撤销点唯一**:handler 不再返回目标(或返回 404)即失效,内核不缓存目标。
客户端拿到的 URL 是**相对网关口**的绝对路径(如
`/api/plugins/http/myplugin/proxy/<id>/vnc.html`),因此远程访问、HTTPS 入口、
Cookie 鉴权都自然生效,无需暴露额外端口。
### 5.7 在运行时安装/更新适配器(token 轮换)
插件可以在运行时安装、改写**自己的**适配器 —— 这是"带自动轮换的认证"的实现
方式:拿着新 token 重写适配器源码,后续请求自然使用新逻辑(内核重建该适配器

View File

@ -0,0 +1,169 @@
package core
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"strings"
"sync/atomic"
"testing"
"llmsproxy/internal/lua"
)
// ★ TRAE 回调只带 code(PKCE 形态)时必须**明确报出**「暂不支持 PKCE」,
// 而不是去调 ExchangeToken 换一个不存在的码。
//
// 真实缺陷(用户报「登录后显示失败」):
// poll_login 的 trae 分支曾自己发明了一段「授权码交换」——把 {code} 塞进
// exchange_body 再打 ExchangeToken。但:
//
// · ExchangeToken 的签名是 RefreshToken,不是 code;
// · exchange_body 里根本没有 {code} 占位符,那次替换是空操作;
// · client_id 当时是空串。
//
// 于是稳定得到 400,日志回一句误导性的「Trae 授权码交换失败: 400」,
// 把真因「上游走了 PKCE 流程」掩盖成「交换出错了」——排查方向完全错。
//
// 参考实现(trae-oauth.ts parseTraeCallbackDetailed)的做法是:带 code 的回调
// 是**合法回调**,只是不支持的 PKCE 分支,必须明确报出来。
func TestTraePkceCallbackIsReportedNotExchanged(t *testing.T) {
h := newTraeHarness(t)
// ★ 必须打**真实登录用的那条路径**:poll_login(loopback 回调文件)。
// oauth_callback 那条一直是对的,判据打在那里会漏掉缺陷 —— 我第一版就
// 犯了这个错(变异测试揭穿:注入缺陷后那条判据仍绿)。
//
// poll_login 从 plugin.state.loopbacks[sessionId].file 读 {code,state},
// 故判据直接摆好那个文件再调 poll_login。
status, body := h.beginAndPollWithCallback(map[string]string{
"code": "PKCE_AUTH_CODE_XYZ",
})
// poll_login 的契约:终态用 HTTP 200 + json.state 表达(不是非 200 状态码)。
// 所以「失败」的判据是 state=failed,而不是 status != 200 —— 我第一版把
// 前者写成了后者,于是把正确的实现判成错。
if !strings.Contains(body, "state:failed") {
t.Fatalf("PKCE 回调应落定为 failed(poll_login 用 200+state 表达终态):status=%d body=%s",
status, body)
}
if n := atomic.LoadInt32(&h.exchHit); n != 0 {
t.Fatalf("不得去调 ExchangeToken —— 那是拿 code 换一个不存在的码(真实缺陷)。"+
"实际打了 %d 次", n)
}
// 错误信息必须指向真因(PKCE),而不是含糊的交换失败
blob := body
if !strings.Contains(blob, "PKCE") {
t.Fatalf("错误信息应点名 PKCE(让排查方向正确),实得 %q", blob)
}
if strings.Contains(blob, "授权码交换失败") {
t.Fatalf("不应再出现误导性的「授权码交换失败」:%q", blob)
}
t.Logf("✓ PKCE 回调被正确识别(poll_login 路径): %s", strings.TrimSpace(blob))
}
// ★ client_id 必须是实测真值 —— ExchangeToken 的请求体里 ClientID 是必填。
// 留空会让真实 token 直传场景的交换稳定 400(夹具自身也校验 ClientID 存在)。
func TestTraeExchangeSendsRealClientID(t *testing.T) {
h := newTraeHarness(t)
// 真实回调形态:带 refreshToken(token 直传)⇒ 会走 ExchangeToken。
// 夹具的 handler 已校验请求体含 ClientID / RefreshToken:<回调值> / ClientSecret。
status, body := h.beginAndCallback(map[string]string{
"refreshToken": "RT-FROM-CALLBACK",
"userInfo": `{"UserID":"u1","ScreenName":"tester","TenantID":"t1"}`,
})
if status != 200 {
t.Fatalf("token 直传回调应成功: status=%d body=%s", status, body)
}
if n := atomic.LoadInt32(&h.exchHit); n == 0 {
t.Fatal("token 直传场景必须真的调用 ExchangeToken")
}
t.Logf("✓ ExchangeToken 被调用 %d 次,请求体形状正确", atomic.LoadInt32(&h.exchHit))
}
// client_id 的真值必须是实测值 —— 这是「交换必然 400」的两个成因之一。
func TestTraeClientIDIsNotBlank(t *testing.T) {
b, err := readBundledChannels(t)
if err != nil {
t.Fatal(err)
}
src := string(b)
if !strings.Contains(src, `client_id = "en1oxy7wnw8j9n"`) {
t.Fatal("trae 的 client_id 必须是实测真值 en1oxy7wnw8j9n —— " +
"留空/占位会让 ExchangeToken 的 ClientID 为空而稳定 400")
}
}
// 两条路径(oauth_callback 与 poll_login 的 loopback)必须给**同一个**结论,
// 否则修复只覆盖一条、另一条继续漂移(这正是缺陷能藏住的原因)。
func TestTraeCallbackPathsAgreeOnPkce(t *testing.T) {
b, err := readBundledChannels(t)
if err != nil {
t.Fatal(err)
}
src := string(b)
// ① 不得再出现自己发明的交换(注释里说明历史的那句除外)
if strings.Contains(src, `cerr = "Trae 授权码交换失败`) {
t.Fatal("已删除的「授权码交换」又回来了 —— 那是拿 code 去 ExchangeToken," +
"必然 400 且把真因掩盖成交换失败")
}
// ② 两条路径都必须交给 traeCallback(它内建 PKCE 判定)
if n := strings.Count(src, "traeCallback(plat,"); n < 2 {
t.Fatalf("traeCallback 应被两条路径共用(当前 %d 处)—— 只有一条会漂移", n)
}
// ③ PKCE 判定必须仍在 traeCallback 内
if !strings.Contains(src, "本实现暂不支持该流程") {
t.Fatal("traeCallback 必须保留 PKCE 明确报错(参考实现的语义)")
}
}
// beginAndPollWithCallback 走**真实登录用的那条路径**:
// start_login 拿会话 → 摆好 loopback 回调文件(平台重定向的落地)→ poll_login。
//
// 与 beginAndCallback(打 oauth_callback)的区别很关键:poll_login 才是
// callback 流在服务端浏览器(VNC)场景下真正走的那条,真实缺陷就藏在它的
// trae 分支里。
func (h *traeHarness) beginAndPollWithCallback(cbQuery map[string]string) (int, string) {
h.t.Helper()
out, err := h.ps.InvokeHandler("channels", "start_login", &lua.HandlerRequest{
Method: "POST", Body: `{"platform":"trae"}`,
})
if err != nil {
h.t.Fatal(err)
}
j, ok := out.JSON.(map[string]interface{})
if !ok {
h.t.Fatalf("start_login 返回非对象: %#v", out.JSON)
}
sess := j["session"].(map[string]interface{})
sid, _ := sess["id"].(string)
nonce, _ := sess["nonce"].(string)
if sid == "" {
h.t.Fatalf("会话缺 id: %#v", sess)
}
// 摆好 loopback 回调文件(内容 = 平台重定向带回的 query)
rec := map[string]string{"state": nonce}
for k, v := range cbQuery {
rec[k] = v
}
b, _ := json.Marshal(rec)
cbPath := filepath.Join(h.t.TempDir(), "cb-"+sid+".json")
if err := os.WriteFile(cbPath, b, 0600); err != nil {
h.t.Fatal(err)
}
// 告诉插件「这个会话的 loopback 接收器把结果写在这里了」
if _, err := h.ps.Call("channels", "__set_loopback_probe", map[string]interface{}{
"session_id": sid, "file": cbPath,
}); err != nil {
h.t.Fatalf("设置 loopback 文件: %v", err)
}
res, err := h.ps.InvokeHandler("channels", "poll_login", &lua.HandlerRequest{
Method: "GET", Query: map[string]string{"id": sid},
})
if err != nil {
h.t.Fatal(err)
}
return res.Status, fmt.Sprintf("%v|%v", res.Body, res.JSON)
}

View File

@ -1,6 +1,7 @@
package core
import (
"net/url"
"strings"
"testing"
@ -53,14 +54,43 @@ func TestChannelsVncStackEndToEnd(t *testing.T) {
t.Fatalf("浏览器栈未能启动: %s", e)
}
view, _ := m["view_url"].(string)
if !strings.Contains(view, "vnc.html") {
t.Fatalf("应给出 noVNC 内嵌地址, 实得 %q", view)
if !strings.HasPrefix(view, "/api/plugins/http/channels/browser/proxy/") || !strings.Contains(view, "vnc.html") {
t.Fatalf("应给出同源 noVNC 内嵌地址,不能让远程客户端连服务器回环端口, 实得 %q", view)
}
sess := m["session"].(map[string]interface{})
if sess["cdp_port"] == nil {
t.Fatal("会话应带 CDP 端口(取凭据用)")
}
t.Logf("VNC 栈已起: %s (CDP %v)", view, sess["cdp_port"])
// ★ noVNC 用 `new URL(path, location.href)` 解析 path(ui.js 的 connect()),
// 即**相对 vnc.html 所在目录**解析,默认值就是相对名 'websockify'。
// 真实缺陷:传了站点根路径 ⇒ 路径被重复拼接,WebSocket 永远连不上,
// 页面看似白屏:
// .../proxy/<id>/api/plugins/http/channels/browser/proxy/<id>/websockify
// 本判据必须解析**产品自己给出的 URL**:我曾在验证时手拼 URL 并省掉
// path 参数(默认值恰好正确)⇒ 否定了真实缺陷。
u, perr := url.Parse(view)
if perr != nil {
t.Fatalf("view_url 不可解析: %v", perr)
}
q := u.Query()
wspath := q.Get("path")
if wspath == "" {
t.Fatal("view_url 必须显式声明 path=websockify:依赖 noVNC 隐式默认值" +
"会在 URL 形状变化时静默破裂")
}
if strings.HasPrefix(wspath, "/") {
t.Fatalf("path 必须是相对名(noVNC 相对 vnc.html 目录解析),"+
"以 / 开头会被当相对路径而重复拼接,实得 %q", wspath)
}
resolved := u.ResolveReference(&url.URL{Path: wspath})
pages := strings.TrimSuffix(u.Path, "/vnc.html")
if resolved.Path != pages+"/websockify" {
t.Fatalf("path 解析后应为 %q(同级 websockify),实得 %q —— 重复拼接即白屏根因",
pages+"/websockify", resolved.Path)
}
t.Logf("VNC 栈已起: %s → WebSocket %s (CDP %v)", view, resolved.Path, sess["cdp_port"])
// 收尾:回收浏览器栈(测试不留孤儿进程)
if _, err := ps.InvokeHandler("channels", "stop_browser", &lua.HandlerRequest{

View File

@ -55,6 +55,15 @@ func (g *Gateway) handlePluginHTTP(w http.ResponseWriter, r *http.Request) {
for i := range matches {
h := matches[i]
p, ok := matchHandlerPath(h.Path, rest)
if h.Prefix {
pattern := strings.Trim(h.Path, "/")
parts := strings.Split(strings.Trim(rest, "/"), "/")
n := len(strings.Split(pattern, "/"))
ok = len(parts) >= n
if ok {
p, ok = matchHandlerPath(pattern, strings.Join(parts[:n], "/"))
}
}
if !ok {
continue
}
@ -116,6 +125,16 @@ func (g *Gateway) handlePluginHTTP(w http.ResponseWriter, r *http.Request) {
writeError(w, http.StatusBadGateway, "plugin_error", err.Error())
return
}
if resp.Proxy != "" {
if !chosen.Prefix {
writeError(w, http.StatusBadGateway, "plugin_error", "proxy response requires prefix=true")
return
}
parts := strings.Split(strings.Trim(rest, "/"), "/")
n := len(strings.Split(strings.Trim(chosen.Path, "/"), "/"))
g.servePluginProxy(w, r, resp.Proxy, pluginHTTPPrefix+strings.Join(parts[:n], "/"))
return
}
lua.WriteHandlerResponse(w, resp)
}

View File

@ -0,0 +1,54 @@
package gateway
import (
"net"
"net/http"
"net/http/httputil"
"net/url"
"strings"
)
// servePluginProxy forwards a plugin-owned prefix to an explicit loopback
// origin. No destination or path may be supplied by the client. Authentication
// and endpoint authorization have already completed before this is called.
func (g *Gateway) servePluginProxy(w http.ResponseWriter, r *http.Request, target, prefix string) {
u, err := url.Parse(target)
if err != nil || u.Scheme != "http" || u.User != nil || u.RawQuery != "" || u.Fragment != "" || (u.Path != "" && u.Path != "/") {
writeError(w, http.StatusBadGateway, "plugin_proxy", "proxy must name a loopback HTTP origin")
return
}
ip := net.ParseIP(u.Hostname())
if ip == nil || !ip.IsLoopback() || u.Port() == "" {
writeError(w, http.StatusBadGateway, "plugin_proxy", "proxy requires a literal loopback address and port")
return
}
// WebSocket requests are browser-initiated and carry ambient cookies. Do not
// allow a foreign website to use an administrator's session to open a tunnel.
if origin := r.Header.Get("Origin"); origin != "" {
o, e := url.Parse(origin)
if e != nil || !strings.EqualFold(o.Host, r.Host) {
writeError(w, http.StatusForbidden, "forbidden", "cross-origin proxy request refused")
return
}
}
proxy := httputil.NewSingleHostReverseProxy(u)
director := proxy.Director
proxy.Director = func(out *http.Request) {
director(out)
out.URL.Path = strings.TrimPrefix(r.URL.Path, prefix)
if out.URL.Path == "" {
out.URL.Path = "/"
}
out.URL.RawPath = ""
out.Host = u.Host
out.Header.Del("Authorization")
out.Header.Del("Cookie")
q := out.URL.Query()
q.Del("api_key")
out.URL.RawQuery = q.Encode()
}
proxy.ErrorHandler = func(w http.ResponseWriter, r *http.Request, err error) {
writeError(w, http.StatusBadGateway, "plugin_proxy", "plugin service unavailable")
}
proxy.ServeHTTP(w, r)
}

View File

@ -0,0 +1,66 @@
package gateway
import (
"io"
"net/http"
"net/http/httptest"
"strings"
"testing"
)
func TestPluginProxyRejectsUnsafeTargetsAndOrigin(t *testing.T) {
g, _ := gatewayWithSpy(t)
for _, target := range []string{"http://example.com:80", "http://localhost:80", "https://127.0.0.1:80", "http://127.0.0.1", "http://u:p@127.0.0.1:80", "http://127.0.0.1:80/path", "http://127.0.0.1:80/?x=1"} {
rr := httptest.NewRecorder()
g.servePluginProxy(rr, httptest.NewRequest("GET", "http://gateway/api/plugins/http/relay/s/live.js", nil), target, "/api/plugins/http/relay/s")
if rr.Code != 502 {
t.Errorf("unsafe target %q accepted: %d", target, rr.Code)
}
}
rr := httptest.NewRecorder()
req := httptest.NewRequest("GET", "http://gateway/api/plugins/http/relay/s/websockify", nil)
req.Header.Set("Origin", "https://evil.example")
g.servePluginProxy(rr, req, "http://127.0.0.1:12345", "/api/plugins/http/relay/s")
if rr.Code != 403 {
t.Fatalf("foreign origin accepted: %d", rr.Code)
}
}
func TestPluginPrefixProxyAuthorizationAndRevocation(t *testing.T) {
backend := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { t.Error("denied request reached backend") }))
defer backend.Close()
g, _ := gatewayWithSpy(t)
src := `local p={name="relaydeny",http={{path="relaydeny/:session",prefix=true,roles={"admin"},handler="proxy"}}}
function p.proxy(req) return {status=404,body="expired session"} end
return p`
if err := g.core.Plugins().LoadSource("relaydeny", src); err != nil {
t.Fatal(err)
}
server := httptest.NewServer(g.Handler())
defer server.Close()
for _, tc := range []struct {
path, key string
status int
}{
{"/api/plugins/http/relaydeny/expired/vnc.html", "", 401},
{"/api/plugins/http/relaydeny/expired/vnc.html", "sk-test", 404},
{"/api/plugins/http/relaydeny-not-a-child/expired/vnc.html", "sk-test", 404},
} {
req, _ := http.NewRequest("GET", server.URL+tc.path, nil)
if tc.key != "" {
req.Header.Set("Authorization", "Bearer "+tc.key)
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatal(err)
}
b, _ := io.ReadAll(resp.Body)
resp.Body.Close()
if resp.StatusCode != tc.status {
t.Fatalf("%s got %d %s", tc.path, resp.StatusCode, b)
}
if tc.key != "" && strings.Contains(tc.path, "/expired/") && strings.Contains(tc.path, "/relaydeny/") && string(b) != "expired session" {
t.Fatalf("revocation response=%s", b)
}
}
}

View File

@ -0,0 +1,82 @@
package gateway
import (
"bufio"
"fmt"
"io"
"net"
"net/http"
"net/http/httptest"
"strings"
"testing"
)
// Drive the real authenticated plugin route, including the access-log wrapper.
// A successful static request alone does not prove WebSocket can upgrade.
func TestPluginPrefixProxyHTTPAndUpgrade(t *testing.T) {
backend := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.Header.Get("Authorization") != "" || r.Header.Get("Cookie") != "" || r.URL.Query().Get("api_key") != "" {
t.Error("gateway credentials leaked to plugin backend")
}
if r.URL.Path == "/websockify" {
c, b, err := w.(http.Hijacker).Hijack()
if err != nil {
t.Error(err)
return
}
defer c.Close()
fmt.Fprint(b, "HTTP/1.1 101 Switching Protocols\r\nConnection: Upgrade\r\nUpgrade: websocket\r\n\r\n")
b.Flush()
io.Copy(c, c)
return
}
fmt.Fprint(w, r.URL.Path+"?"+r.URL.RawQuery)
}))
defer backend.Close()
g, _ := gatewayWithSpy(t)
src := fmt.Sprintf(`local p={name="relay",http={{path="relay/:session",prefix=true,method="GET",roles={"admin"},handler="proxy"}}}
function p.proxy(req)
if req.params.session ~= "live" then return {status=404,body="expired"} end
return {proxy=%q}
end
return p`, backend.URL)
if err := g.core.Plugins().LoadSource("relay", src); err != nil {
t.Fatal(err)
}
server := httptest.NewServer(g.Handler())
defer server.Close()
req, _ := http.NewRequest("GET", server.URL+"/api/plugins/http/relay/live/app/main.js?x=1&api_key=sk-test", nil)
req.Header.Set("Authorization", "Bearer sk-test")
req.AddCookie(&http.Cookie{Name: "gw_key", Value: "sk-test"})
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatal(err)
}
body, _ := io.ReadAll(resp.Body)
resp.Body.Close()
if resp.StatusCode != 200 || string(body) != "/app/main.js?x=1" {
t.Fatalf("HTTP proxy: %d %s", resp.StatusCode, body)
}
c, err := net.Dial("tcp", strings.TrimPrefix(server.URL, "http://"))
if err != nil {
t.Fatal(err)
}
defer c.Close()
fmt.Fprintf(c, "GET /api/plugins/http/relay/live/websockify HTTP/1.1\r\nHost: %s\r\nAuthorization: Bearer sk-test\r\nConnection: Upgrade\r\nUpgrade: websocket\r\n\r\n", strings.TrimPrefix(server.URL, "http://"))
b := bufio.NewReader(c)
reply, err := http.ReadResponse(b, nil)
if err != nil {
t.Fatal(err)
}
if reply.StatusCode != 101 {
t.Fatalf("upgrade failed: %s", reply.Status)
}
c.Write([]byte("ping"))
got := make([]byte, 4)
if _, err = io.ReadFull(b, got); err != nil {
t.Fatal(err)
}
if string(got) != "ping" {
t.Fatalf("tunnel payload=%q", got)
}
}

View File

@ -187,6 +187,10 @@ type statusRecorder struct {
code int
}
// Unwrap preserves optional writer capabilities (notably Hijack for WebSocket)
// through the access-log middleware via http.ResponseController.
func (s *statusRecorder) Unwrap() http.ResponseWriter { return s.ResponseWriter }
func (s *statusRecorder) WriteHeader(code int) {
if s.code == 0 {
s.code = code

View File

@ -228,6 +228,26 @@ func incStatus(a *Stat, name string, r Req) {
}
}
// addStat merges an already aggregated row into a total. It deliberately
// includes failed requests without a model: routing can fail before a model is
// resolved, but that request still belongs in the gateway total.
func addStat(dst, src *Stat) {
if dst == nil || src == nil {
return
}
dst.Reqs += src.Reqs
dst.OK += src.OK
dst.Err += src.Err
dst.Tokens += src.Tokens
dst.Prompt += src.Prompt
dst.Compl += src.Compl
dst.LatSum += src.LatSum
dst.FirstByteSum += src.FirstByteSum
if src.LatMax > dst.LatMax {
dst.LatMax = src.LatMax
}
}
// LoadAudit primes the in-memory state from the audit file.
//
// The aggregates (totals, per-key/model/source rows, status counts and the
@ -1219,17 +1239,13 @@ func (s *Stats) Snapshot(limit int, key string) map[string]interface{} {
byModel = s.byKeyModel[key]
bySrc = s.byKeySrc[key]
}
for _, a := range byModel {
total.Reqs += a.Reqs
total.OK += a.OK
total.Err += a.Err
total.Tokens += a.Tokens
total.Prompt += a.Prompt
total.Compl += a.Compl
total.LatSum += a.LatSum
if a.LatMax > total.LatMax {
total.LatMax = a.LatMax
}
// The total is the sum of every recorded request, not the model rows.
// Routing failures are valid requests but may have no resolved model; deriving
// total from byModel silently dropped those 502/503 records. Use byKey, which
// is populated for every request (including an empty key), and keep the same
// scope as the selected key filter.
for _, a := range byKey {
addStat(&total, a)
}
bs := make([]agrRow, 0, len(s.byStatus))
for code, st := range s.byStatus {

View File

@ -560,3 +560,17 @@ func TestAuditRotationThresholds(t *testing.T) {
t.Fatalf("total audit budget = %d, want 256 MiB", total)
}
}
func TestSnapshotTotalIncludesRequestsWithoutModel(t *testing.T) {
s := NewStats(100)
s.Record(Req{Key: "k", Status: 200, OK: true})
s.Record(Req{Key: "k", Model: "m", Status: 200, OK: true, Prompt: 3, Compl: 2})
snap := s.Snapshot(0, "")
total, ok := snap["total"].(Stat)
if !ok {
t.Fatalf("total missing: %#v", snap["total"])
}
if total.Reqs != 2 || total.OK != 2 || total.Tokens != 5 {
t.Fatalf("total must include model-less requests: %#v", total)
}
}

View File

@ -0,0 +1,213 @@
package lua
import (
"bytes"
"encoding/json"
"fmt"
"io"
"net/http"
"os"
"os/exec"
"strings"
"testing"
"time"
)
// 真上游 e2e:用适配器产出的头 + body 直打 opencode /inference/v1。
// 需要真实凭据(从生产配置解密),故用 LLMSPROXY_LIVE_ZEN=1 显式开启。
func TestOpencodeZenLiveE2E(t *testing.T) {
if os.Getenv("LLMSPROXY_LIVE_ZEN") != "1" {
t.Skip("设 LLMSPROXY_LIVE_ZEN=1 开启真上游 e2e")
}
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
if err != nil {
t.Fatal(err)
}
vm := NewVM(t.TempDir())
defer vm.Stop()
if err := vm.LoadAdapterSource("opencodezen", string(src)); err != nil {
t.Fatal(err)
}
// 取生产凭据(解密)
out, err := exec.Command("/usr/local/bin/llmsproxy", "-show-secrets",
"-config", "/etc/llmsproxy/config.yaml").Output()
if err != nil {
t.Fatal(err)
}
apiKey := ""
for _, l := range strings.Split(string(out), "\n") {
if strings.HasPrefix(l, "source localzen") {
if i := strings.Index(l, "api_key="); i >= 0 {
apiKey = strings.TrimSpace(l[i+len("api_key="):])
}
}
}
if apiKey == "" {
t.Fatal("未取到 localzen 凭据")
}
cases := []struct {
name string
body string
want string
}{
{"纯对话(无 tools,靠适配器兜底注入)",
`{"model":"deepseek-v4.1-flash-free","stream":true,"max_tokens":60,
"messages":[{"role":"user","content":"reply with exactly: ADAPTER-OK"}]}`, "ADAPTER-OK"},
{"带自定义 system",
`{"model":"deepseek-v4.1-flash-free","stream":true,"max_tokens":60,
"messages":[{"role":"system","content":"You are terse."},{"role":"user","content":"reply with exactly: SYS-OK"}]}`, "SYS-OK"},
{"多轮",
`{"model":"deepseek-v4.1-flash-free","stream":true,"max_tokens":60,
"messages":[{"role":"user","content":"a"},{"role":"assistant","content":"b"},{"role":"user","content":"reply with exactly: MULTI-OK"}]}`, "MULTI-OK"},
{"算术(验证真推理)",
`{"model":"deepseek-v4.1-flash-free","stream":true,"max_tokens":60,
"messages":[{"role":"user","content":"What is 17*23? Reply with just the number."}]}`, "391"},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
body, err := vm.Transform("opencodezen", "transform_request", tc.body)
if err != nil {
t.Fatal(err)
}
h, err := vm.BuildHeaders("opencodezen", map[string]interface{}{
"timestamp": time.Now().Unix(), "body": body,
})
if err != nil {
t.Fatal(err)
}
req, _ := http.NewRequest("POST",
"https://opencode.ai/inference/v1/chat/completions", bytes.NewReader([]byte(body)))
for k, v := range h {
req.Header.Set(k, v)
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", "Bearer "+apiKey)
cl := &http.Client{Timeout: 90 * time.Second}
resp, err := cl.Do(req)
if err != nil {
t.Fatal(err)
}
raw, _ := io.ReadAll(resp.Body)
resp.Body.Close()
if resp.StatusCode != 200 {
t.Fatalf("HTTP %d: %s", resp.StatusCode, string(raw)[:min(300, len(raw))])
}
// 上游现在返回 SSE(适配器强制 stream=true);判据需自己拼 delta.content。
got := ""
for _, line := range strings.Split(string(raw), "\n") {
line = strings.TrimSpace(line)
if !strings.HasPrefix(line, "data: ") {
continue
}
p := strings.TrimPrefix(line, "data: ")
if p == "[DONE]" {
continue
}
var d struct {
Choices []struct {
Delta struct{ Content string } `json:"delta"`
} `json:"choices"`
}
if json.Unmarshal([]byte(p), &d) != nil || len(d.Choices) == 0 {
continue
}
got += d.Choices[0].Delta.Content
}
if got == "" {
t.Fatalf("未从 SSE 解出内容;原始=%s", string(raw)[:min(300, len(raw))])
}
if !strings.Contains(got, tc.want) {
t.Fatalf("回复 %q 不含 %q", got, tc.want)
}
t.Logf("✓ %s → %q", tc.name, strings.TrimSpace(got))
})
}
fmt.Println("真上游 e2e 全部通过")
}
// 经适配器完整转换链:上游 SSE → transform_stream_chunk → 统一格式。
// 上一条判据直接读原始 SSE,只证明"上游放行";这条证明"适配器能解析"。
func TestOpencodeZenLiveStreamThroughAdapter(t *testing.T) {
if os.Getenv("LLMSPROXY_LIVE_ZEN") != "1" {
t.Skip("设 LLMSPROXY_LIVE_ZEN=1 开启")
}
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
if err != nil {
t.Fatal(err)
}
vm := NewVM(t.TempDir())
defer vm.Stop()
if err := vm.LoadAdapterSource("opencodezen", string(src)); err != nil {
t.Fatal(err)
}
out, _ := exec.Command("/usr/local/bin/llmsproxy", "-show-secrets",
"-config", "/etc/llmsproxy/config.yaml").Output()
apiKey := ""
for _, l := range strings.Split(string(out), "\n") {
if strings.HasPrefix(l, "source localzen") {
if i := strings.Index(l, "api_key="); i >= 0 {
apiKey = strings.TrimSpace(l[i+len("api_key="):])
}
}
}
body, _ := vm.Transform("opencodezen", "transform_request",
`{"model":"deepseek-v4.1-flash-free","stream":true,"max_tokens":60,
"messages":[{"role":"user","content":"reply with exactly: CHAIN-OK"}]}`)
h, _ := vm.BuildHeaders("opencodezen", map[string]interface{}{
"timestamp": time.Now().Unix(), "body": body})
req, _ := http.NewRequest("POST",
"https://opencode.ai/inference/v1/chat/completions", bytes.NewReader([]byte(body)))
for k, v := range h {
req.Header.Set(k, v)
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", "Bearer "+apiKey)
resp, err := (&http.Client{Timeout: 90 * time.Second}).Do(req)
if err != nil {
t.Fatal(err)
}
raw, _ := io.ReadAll(resp.Body)
resp.Body.Close()
if resp.StatusCode != 200 {
t.Fatalf("HTTP %d: %s", resp.StatusCode, string(raw)[:min(300, len(raw))])
}
// 逐行喂给适配器的流解析器,累积统一格式的 content
joined := ""
n := 0
for _, line := range strings.Split(string(raw), "\n") {
line = strings.TrimSpace(line)
if !strings.HasPrefix(line, "data: ") || line == "data: [DONE]" {
continue
}
// 内核喂给适配器的是**已剥掉 data: 前缀**的载荷(见 provider.go:
// strings.TrimPrefix(line, "data:")),判据必须对齐这个契约。
payload := strings.TrimSpace(strings.TrimPrefix(line, "data:"))
unified, err := vm.Transform("opencodezen", "transform_stream_chunk", payload)
if err != nil {
t.Fatalf("transform_stream_chunk: %v (%s)", err, line[:min(120, len(line))])
}
if unified == "" || unified == "{}" {
continue
}
var u struct {
Content string `json:"content"`
}
if json.Unmarshal([]byte(unified), &u) == nil {
joined += u.Content
n++
}
}
if n == 0 {
t.Fatal("适配器未解出任何 chunk(流解析链断了)")
}
if !strings.Contains(joined, "CHAIN-OK") {
t.Fatalf("经适配器链的内容 %q 不含 CHAIN-OK(chunk 数=%d)", joined, n)
}
t.Logf("✓ 完整链:%d 个 chunk,内容=%q", n, strings.TrimSpace(joined))
}

View File

@ -0,0 +1,156 @@
package lua
import (
"encoding/json"
"strings"
"testing"
)
// E2E:加载改后的适配器,验证 (1) 头含两个 session 头且值相同;(2) id 段服从公式;
// (3) 无 tools 的请求被注入 read 桩且 properties 非空。
func TestOpencodeZenAdapterE2E(t *testing.T) {
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
if err != nil {
t.Fatal(err)
}
vm := NewVM(t.TempDir())
defer vm.Stop()
if err := vm.LoadAdapterSource("opencodezen", string(src)); err != nil {
t.Fatalf("加载失败: %v", err)
}
t.Run("头:两个 session 头同值", func(t *testing.T) {
h, err := vm.BuildHeaders("opencodezen", map[string]interface{}{"timestamp": int64(1792065049)})
if err != nil {
t.Fatal(err)
}
s1, s2 := h["x-opencode-session"], h["x-opencode-session-id"]
if s1 == "" || s2 == "" {
t.Fatalf("两个 session 头都必须存在: %#v", h)
}
if s1 != s2 {
t.Fatalf("必须同值: %q vs %q", s1, s2)
}
if !strings.HasPrefix(s1, "ses_") || len(s1) != 4+12+14 {
t.Fatalf("session 形状应为 ses_+12hex+14base62: %q (len=%d)", s1, len(s1))
}
if len(h["x-opencode-request"]) != 4+12+14 || !strings.HasPrefix(h["x-opencode-request"], "msg_") {
t.Fatalf("request 形状: %q", h["x-opencode-request"])
}
if !strings.Contains(h["User-Agent"], "opencode/1.19.0") {
t.Fatalf("UA 应为 1.19.0: %q", h["User-Agent"])
}
t.Logf("session=%s request=%s", s1, h["x-opencode-request"])
// 公式校验:段 = (K - bucket_ms*4096) & MASK,其中 bucket 已对齐到整分钟
// (适配器按分钟桶取会话号,以保留上游前缀缓存命中)。
// ⚠️ 判据必须算**同一个桶**,不能拿原始 ms 去比 —— 那会把正确的实现判成错。
seg := s1[4:16]
ms := int64(1792065049) * 1000
bucket := ms - (ms % 60000)
want := (int64(0x1afffffffffffe) - bucket*4096) & 0xFFFFFFFFFFFF
if got := seg; got != fmtHex12(want) {
t.Fatalf("session 段公式不符: got=%s want=%s (bucket=%d)", got, fmtHex12(want), bucket)
}
})
t.Run("tools 兜底:无 tools 时注入 read", func(t *testing.T) {
out, err := vm.Transform("opencodezen", "transform_request",
`{"model":"m","stream":true,"messages":[{"role":"user","content":"hi"}]}`)
if err != nil {
t.Fatal(err)
}
var req map[string]interface{}
if err := json.Unmarshal([]byte(out), &req); err != nil {
t.Fatal(err)
}
ts, _ := req["tools"].([]interface{})
if len(ts) == 0 {
t.Fatalf("必须注入 tools: %s", out)
}
found := false
for _, x := range ts {
fn := x.(map[string]interface{})["function"].(map[string]interface{})
if fn["name"] == "read" {
p, _ := fn["parameters"].(map[string]interface{})
props, _ := p["properties"].(map[string]interface{})
if len(props) == 0 {
t.Fatalf("read 的 properties 必须非空(门禁要求): %s", out)
}
found = true
}
}
if !found {
t.Fatalf("必须含名为 read 的工具: %s", out)
}
})
t.Run("tools 保留:用户自带 read 不被覆盖", func(t *testing.T) {
in := `{"model":"m","stream":true,"messages":[{"role":"user","content":"hi"}],
"tools":[{"type":"function","function":{"name":"read","description":"MY","parameters":{"type":"object","properties":{"a":{"type":"string"}}}}}]}`
out, err := vm.Transform("opencodezen", "transform_request", in)
if err != nil {
t.Fatal(err)
}
var req map[string]interface{}
json.Unmarshal([]byte(out), &req)
ts, _ := req["tools"].([]interface{})
if len(ts) != 1 {
t.Fatalf("不应追加(已有 read): %s", out)
}
fn := ts[0].(map[string]interface{})["function"].(map[string]interface{})
if fn["description"] != "MY" {
t.Fatalf("用户定义被覆盖: %s", out)
}
})
}
func fmtHex12(v int64) string {
const hex = "0123456789abcdef"
out := make([]byte, 12)
for i := 11; i >= 0; i-- {
out[i] = hex[v&0xF]
v >>= 4
}
return string(out)
}
// ★ 免费层只能流式(适配器强制 stream=true),而内核在客户端要非流式时
// 会调 transform_response(期望 JSON)⇒ 适配器必须能把 SSE 聚合回非流式对象。
// 这条判据钉住那个聚合:真实 SSE 片段 → 完整 chat.completion。
func TestOpencodeZenAggregatesSSEForNonStreamClient(t *testing.T) {
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
if err != nil {
t.Fatal(err)
}
vm := NewVM(t.TempDir())
defer vm.Stop()
if err := vm.LoadAdapterSource("opencodezen", string(src)); err != nil {
t.Fatal(err)
}
// 模仿上游真实 SSE(含 reasoning_content 与 usage 末帧)
sse := `data: {"id":"x1","object":"chat.completion.chunk","created":1,"model":"m","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"think "}}]}
data: {"id":"x1","object":"chat.completion.chunk","created":1,"model":"m","choices":[{"index":0,"delta":{"content":"HELLO"}}]}
data: {"id":"x1","object":"chat.completion.chunk","created":1,"model":"m","choices":[{"index":0,"delta":{"content":" WORLD"},"finish_reason":"stop"}]}
data: {"id":"x1","object":"chat.completion.chunk","created":1,"model":"m","choices":[],"usage":{"prompt_tokens":7,"completion_tokens":2,"total_tokens":9}}
data: [DONE]
`
out, err := vm.Transform("opencodezen", "transform_response", sse)
if err != nil {
t.Fatal(err)
}
var u map[string]interface{}
if err := json.Unmarshal([]byte(out), &u); err != nil {
t.Fatalf("聚合产物不是 JSON: %v (%s)", err, out)
}
if u["content"] != "HELLO WORLD" {
t.Fatalf("content 应为 'HELLO WORLD',实得 %v", u["content"])
}
tu, _ := u["token_usage"].(map[string]interface{})
if tu == nil || tu["prompt"] != float64(7) {
t.Fatalf("usage 应透传: %v", u["token_usage"])
}
if u["finish_reason"] != "stop" {
t.Fatalf("finish_reason 应为 stop: %v", u["finish_reason"])
}
t.Logf("聚合 OK: content=%v usage=%v finish=%v", u["content"], tu, u["finish_reason"])
}

View File

@ -0,0 +1,484 @@
local adapter = {}
adapter.name = "opencodezen"
adapter.version = "1.0.0"
adapter.endpoint = "/chat/completions"
-- OpenCode Zen(按量付费端点,https://opencode.ai/zen/v1)
--
-- 与 OpenCode Go(opencodego.lua,https://opencode.ai/zen/go/v1)是两个不同的
-- 服务,行为要求并不相同,因此各有专用适配器:
--
-- * 本适配器(Zen)服务免费池 / 按量付费池。免费模型必须带 opencode 客户端
-- 指纹(UA + x-opencode-*),否则上游拒绝:"free tier can only be used in
-- OpenCode"。Zen 的免费池以非 thinking 模型为主,历史上回传
-- reasoning_content 会引出上游报错,故这里剥掉(Go 侧相反,见 opencodego.lua)。
-- * Go 订阅读者请看 opencodego.lua:那边**必须**回传 reasoning_content,
-- 否则 thinking 模式直接 400。
--
-- 缺 x-opencode-client/session/request/project 身份头会被判为匿名客户端,
-- 部分模型在带 tools 时上游直接失败(流式返回单 chunk
-- "finish_reason":"network_error" 空 content,非流式 503
-- "Endpoint is unavailable",表现为"空回复")。
-- ============================================================================
-- ★ opencode Zen 免费层门禁(2026-10-15 实测解出,逐条对齐官方 CLI)
--
-- 上游对免费池有**三个**必须同时满足的条件,缺任一则 403 FreeTierError
-- ("free tier can only be used from within OpenCode"),与 UA / TLS 指纹 / 凭据来源
-- 均无关:
--
-- 1. 端点必须是 /inference/v1/chat/completions(不是 /zen/v1)
-- —— 由源的 base_url 决定,不在本适配器内。
-- 2. 必须同时发 x-opencode-session **与** x-opencode-session-id(值相同)。
-- 两个 id 的 12 位 hex 段由**确定公式**给出(见下),不是随机数;
-- 时间容差实测 ≥ 60 秒,故 os.time() 的秒精度足够。
-- 3. 请求的 tools 里必须有一个名为 read 的工具,且其 parameters.properties
-- **非空**。这是唯一的 tools 要求:实测抽掉官方 11 个工具中的任意一个均为
-- 200,**只有抽掉 read 变 403**;且 properties 里放任意属性名即可,
-- 描述文字 / $schema / required 都不需要(properties 为空对象则 403)。
-- ⇒ 无 tools 的纯对话请求会被拒,故 transform_request 需兜底注入桩工具。
-- 4. **stream 必须为 true**:实测同为合法请求,stream=false 恒 403、stream=true 恒 200
-- (包括 max_tokens 20/60/200/1000/32000 均 200)。
-- ⇒ 非流式请求会被拒,故 transform_request 强制 stream=true。
--
-- 明确**不影响**通过的(均实测):system 内容(含无 system)、消息条数
-- (2/3/4/6 条均 200)、凭据(Bearer public 与普通 API key 均可)、
-- x-opencode-project / x-opencode-client / UA 里的 opencode/ 前缀。
--
-- ⚠️ 参考实现 dsh-our-free-model 的门禁桩(bash + read,但无真实 properties)
-- 恰好卡在第 3 条上 —— 即它「伪装需跟进上游更新」的真实原因。
adapter.headers = {
["User-Agent"] = "opencode/1.19.0 ai-sdk/provider-utils/4.0.23 runtime/bun/1.3.14",
}
-- rand_id:按官方的 48-bit 公式生成 12 位 hex 段 + 14 位 base62 随机段。
--
-- 公式逆自官方 CLI 本地库(~/.local/share/opencode/opencode.db 的 session 表,
-- 用 11/12 条真实 id 逐条比对完全一致):
--
-- MASK = 2^48 - 1
-- K = 0x1afffffffffffe (注意不是 27<<48,两者差 2)
-- session 段 = (K - now_ms * 4096) & MASK ← **倒计时式**:Δseg/Δms ≡ -4096
-- request 段 = (now_ms * 16) & MASK
--
-- 为什么是「倒计时」而不是时间戳:0x1afffffffffffe 减去 ms*2^12,所以 seg 随
-- 时间**递减**。用 f"{ms:012x}" 之类的正向写法必然不对(我为此错过一轮)。
--
-- ⚠️ 精度:now_ms*4096 ≈ 7.3e15 < 2^53 ≈ 9.0e15,在 double 安全整数范围内,
-- 故 LuaJIT 的默认数字类型(double)直接算即可,无需大整数库。
local B62 = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
local MASK48 = 281474976710655 -- 2^48 - 1
local ID_K = 0x1afffffffffffe
local function rand_tail(n)
local out = {}
for i = 1, n do
local v = 0
if math and math.random then
v = math.random(1, 62)
else
-- 无 math 时用时间做退化熵源:只要唯一,不要求密码学强度。
v = (os.time() * 7 + i * 13) % 62 + 1
end
out[i] = B62:sub(v, v)
end
return table.concat(out)
end
-- now_ms:毫秒。沙箱只有 os.time()(秒)与 os.clock()(CPU 时间,无用),
-- 而上游时间容差实测 ≥ 60 秒,故秒精度足够;毫秒位补 0。
-- meta.timestamp 由内核给出(同为秒),优先用它以便同一请求内自洽。
local function now_ms(meta)
local t = tonumber(meta and meta.timestamp) or (os.time and os.time()) or 0
return t * 1000
end
local function rand_id(prefix, ms, kind)
local seg
if kind == "session" then
seg = (ID_K - ms * 4096) % (MASK48 + 1)
else
seg = (ms * 16) % (MASK48 + 1)
end
-- %012x:12 位十六进制,不足补零
return prefix .. string.format("%012x", seg) .. rand_tail(14)
end
-- session_bucket_ms 决定上游会话号的**稳定周期**(按整分钟对齐)。
--
-- 为什么需要稳定:上游前缀缓存是会话级的(实测:同一段 6032 token 提示词,
-- 固定会号第 2 次命中 5888;每请求换会号则恒为 0 命中)。而免费层门禁要求
-- x-opencode-session 的 12 位 hex 段服从「倒计时」公式(见 rand_id 注释),
-- 所以不能真的「随便挑一个固定值」,只能选一个**时间桶**。
--
-- 取整分钟(而非秒):同一分钟内的所有请求共享一个会话号 ⇒ 既保留缓存命中,
-- 又不超出上游的时间容差。实测容差 ≥ 1 小时(-3600s 仍 200),
-- 所以一分钟桶有很大余量,即便上游收紧到几分钟也仍然安全。
local function session_bucket_ms(meta)
local ms = now_ms(meta)
return ms - (ms % 60000)
end
function adapter.build_headers(meta)
local ms = now_ms(meta)
local bucket = session_bucket_ms(meta)
-- 免费层要求两个头都在且值相同(对齐官方 CLI;缺任一个则 403)。
local sid = rand_id("ses_", bucket, "session")
return {
["User-Agent"] = adapter.headers["User-Agent"],
["x-opencode-client"] = "cli",
-- project 固定:同网关实例共享一个工作区身份(非门禁必需,但官方也发)
["x-opencode-project"] = "global",
["x-opencode-session"] = sid,
-- ★ 两个都要:上游对免费池同时校验 x-opencode-session 与这个头。
["x-opencode-session-id"] = sid,
-- request id 每请求唯一(不参与缓存键),用当前时间而非桶,避免同桶内重复
["x-opencode-request"] = rand_id("msg_", ms, "request"),
}
end
-- ============================================================================
-- ★ 免费层 tools 兜底:上游要求 tools 里必须有一个名为 read、且
-- parameters.properties 非空的工具(实测唯一要求;抽掉它即 403)。
-- 纯对话请求(客户端没传 tools)会被拒,故这里注入一个桩工具。
--
-- 只补缺,不改用户已有的 tools:用户自带 read 时原样透传(官方 CLI 就是这么发的),
-- 用户带的其它工具保留不动。
local FREE_GATE_TOOL = "read"
local function ensure_free_gate_tool(req)
local tools = req.tools
if type(tools) ~= "table" then tools = {} req.tools = tools end
for _, t in ipairs(tools) do
if type(t) == "table" then
local fn = t["function"]
-- 注意:function 是 Lua 关键字,必须用 req["function"] 形式取下标。
if type(fn) == "table" and fn.name == FREE_GATE_TOOL then
local p = fn.parameters
-- 已有 read 但 properties 为空 ⇒ 补上;否则原样保留用户定义。
if type(p) == "table" and type(p.properties) == "table"
and next(p.properties) ~= nil then
return
end
fn.parameters = { type = "object",
properties = { filePath = { type = "string", description = "Path to read" } } }
return
end
end
end
tools[#tools + 1] = {
type = "function",
["function"] = {
name = FREE_GATE_TOOL,
description = "Read a file from the local filesystem.",
parameters = { type = "object",
properties = { filePath = { type = "string", description = "Path to read" } },
required = { "filePath" } },
},
}
end
-- OpenAI /chat/completions format (pass-through, strip provider-specific fields)
-- zen 上游 schema 只接受 text content part(无视觉/音频能力):多模态 part
-- (image_url / input_audio / file 等)一律剥离。剥离后 content 变空的消息
-- 若不再携带 tool_calls / tool_call_id 才整条丢弃(避免上游
-- "unknown variant `image_url`, expected `text`");带工具调用的必须保留,
-- 否则会把紧随其后的 tool 结果变成孤儿,模型会反复重发同一个调用。
-- zen 上游角色白名单只有 system / user / assistant / tool / latest_reminder:
-- OpenAI 的 developer(及 function 等)不在其中,直接透传会触发上游
-- "unknown variant `developer`, expected one of ..." 错误;统一归一化为 system。
local ROLE_WHITELIST = {
system = true,
user = true,
assistant = true,
tool = true,
latest_reminder = true,
}
function adapter.transform_request(raw_body)
local ok, req = pcall(json.decode, raw_body)
if not ok then return raw_body end
-- ★ 免费层 gate:tools 里必须有 read(且 parameters.properties 非空)。
-- 放在最前面:它决定本请求会不会被 403,与后面的字段清理无关。
-- 对所有模型都注入:免费池与付费池共用同一层形状检查,多一个桩工具无害
-- (官方 CLI 本来也带全套工具),但缺了它会让免费模型整体失效。
ensure_free_gate_tool(req)
-- ★ 免费层只接受流式:实测 stream=false 恒 403(同样 body 改 true 即 200)。
-- 转成流式由上游以 SSE 回应,内核本就会聚合/透传流式响应,故对客户端透明。
req.stream = true
req.disable_thinking = nil
req.extra_body = nil
-- stream_options is only valid alongside stream:true; sending it on a
-- non-streaming request is rejected by strict upstreams.
if req.stream then
if type(req.stream_options) ~= "table" then req.stream_options = {} end
req.stream_options.include_usage = true
end
if req.messages then
local kept = {}
for _, msg in ipairs(req.messages) do
if type(msg.role) == "string" and not ROLE_WHITELIST[msg.role] then
msg.role = "system"
end
-- Zen 免费池不接受回传 reasoning_content(Go 侧相反)
msg.reasoning_content = nil
local drop = false
if type(msg.content) == "table" then
local parts = {}
for _, part in ipairs(msg.content) do
if type(part) == "table" and part.type ~= nil and part.type ~= "text" then
-- multimodal part not supported by zen
else
table.insert(parts, part)
end
end
if #parts == 0 then
-- Content collapsed to nothing after stripping unsupported
-- parts. A message that still carries a tool call must
-- NEVER be dropped: the very next message is its tool
-- result, and dropping the call orphans that result. The
-- model then sees a result for a call it never made and
-- re-issues the same tool call on every turn (observed as
-- an infinite "repeated tool call" loop).
if (type(msg.tool_calls) == "table" and #msg.tool_calls > 0)
or msg.tool_call_id ~= nil then
msg.content = ""
else
drop = true
end
else
msg.content = parts
end
end
if not drop then
table.insert(kept, msg)
end
end
req.messages = kept
end
return json.encode(req)
end
-- ★ aggregate_sse:把 SSE 流(openai chat.completion.chunk 形状)聚合成一个非流式
-- 响应对象,供 transform_response 在「客户端要非流式、上游却回流式」时使用。
-- 返回 JSON 字符串;无法聚合(无任何 chunk)时返回 nil。
--
-- 只处理 content / reasoning_content / finish_reason / usage 四类增量:
-- 它们覆盖了内核需要从响应里取的全部字段(正文、结束原因、token 计数)。
local function aggregate_sse(raw)
local content, reasoning, finish = {}, {}, ""
local usage, id, model, created = nil, nil, nil, nil
local seen = false
for line in (raw .. "\n"):gmatch("([^\n]*)\n") do
local s = line:gsub("^%s+", ""):gsub("%s+$", "")
if s:sub(1, 5) == "data:" then
local payload = s:sub(6):gsub("^%s+", "")
if payload ~= "" and payload ~= "[DONE]" then
local ok, d = pcall(json.decode, payload)
if ok and type(d) == "table" then
seen = true
id = id or d.id
model = model or d.model
created = created or d.created
if type(d.usage) == "table" then usage = d.usage end
local ch = d.choices and d.choices[1]
if type(ch) == "table" then
if ch.finish_reason and ch.finish_reason ~= "" then
finish = ch.finish_reason
end
local dl = ch.delta
if type(dl) == "table" then
if type(dl.content) == "string" then content[#content + 1] = dl.content end
if type(dl.reasoning_content) == "string" then
reasoning[#reasoning + 1] = dl.reasoning_content
end
end
end
end
end
end
end
if not seen then return nil end
local msg = { role = "assistant", content = table.concat(content) }
local rc = table.concat(reasoning)
if rc ~= "" then msg.reasoning_content = rc end
local out = {
id = id or "", object = "chat.completion", created = created or 0, model = model or "",
choices = { { index = 0, message = msg, finish_reason = finish ~= "" and finish or "stop" } },
}
if usage then out.usage = usage end
local ok2, enc = pcall(json.encode, out)
if not ok2 then return nil end
return enc
end
function adapter.transform_response(raw_body)
-- ★ 免费层只接受 stream=true(见文件头门禁第 4 条),所以本适配器把每个请求
-- 都改成了流式 —— 但内核是按**客户端意图**选路径的:客户端发非流式时,
-- 内核走 Provider.Chat 并调本函数(期望 JSON),而上游回的是 SSE。
-- 若在这里直接 json.decode 就会得到 "invalid character 'd'" 错误。
--
-- 因此本函数必须先识别 SSE 并自行聚合,再走原来的 JSON 路径。
-- 这样保持内核对上游协议无感(内核不知道也不该知道上游选了流式)。
if type(raw_body) == "string" and (raw_body:sub(1, 6) == "data: " or raw_body:find("\ndata: ", 1, true)) then
local aggregated = aggregate_sse(raw_body)
if aggregated ~= nil then
local ok2, resp2 = pcall(json.decode, aggregated)
if ok2 and type(resp2) == "table" then raw_body = aggregated end
end
end
local ok, resp = pcall(json.decode, raw_body)
if not ok or resp == nil then return raw_body end
local unified = {
content = "",
finish_reason = "",
token_usage = { prompt = 0, completion = 0, total = 0 }
}
if type(resp.usage) == "table" then
unified.token_usage.prompt = resp.usage.prompt_tokens or 0
unified.token_usage.completion = resp.usage.completion_tokens or 0
unified.token_usage.total = resp.usage.total_tokens or 0
local hit = 0
if type(resp.usage.prompt_tokens_details) == "table" and resp.usage.prompt_tokens_details.cached_tokens ~= nil then
hit = resp.usage.prompt_tokens_details.cached_tokens
unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
end
if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
if hit == 0 then
unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
end
end
-- 上游报告输出里有多少是思考 token。不给客户端的话,无法判断
-- completion_tokens 里多少是「可见回答」、多少是「思考」(都按输出计费)。
local ctd = resp.usage.completion_tokens_details
if type(ctd) == "table" and ctd.reasoning_tokens ~= nil then
unified.token_usage.completion_tokens_details = { reasoning_tokens = ctd.reasoning_tokens }
end
end
-- 本次调用的费用,上游放在**顶层**且是**字符串**(如 "0"、"0.0012")。
-- Go 订阅是包月制,恒为 "0";只有 Zen 按量付费模型才有信息量。
-- 原样透传:网关不解析、不换算、不汇总 —— 它只是上游事实的搬运者。
if resp.cost ~= nil then
unified.cost = tostring(resp.cost)
end
if type(resp.choices) == "table" and #resp.choices > 0 then
local ch = resp.choices[1]
if type(ch.message) == "table" then
unified.content = ch.message.content or ""
local reasoning = ch.message.reasoning_content or ch.message.reasoning
if reasoning then
unified.reasoning_content = reasoning
end
if type(ch.message.tool_calls) == "table" then
local tcs = {}
for _, tc in ipairs(ch.message.tool_calls) do
local args_ok, args = pcall(json.decode, tc["function"].arguments)
if not args_ok then args = {} end
table.insert(tcs, {
id = tc.id,
type = tc.type or "function",
name = tc["function"].name,
arguments = args
})
end
unified.tool_calls = tcs
end
end
unified.finish_reason = ch.finish_reason or ""
end
return json.encode(unified)
end
function adapter.transform_stream_chunk(raw_chunk)
local ok, chunk = pcall(json.decode, raw_chunk)
if not ok then return "" end
-- OpenAI-style streams may attach usage to a chunk with empty choices
-- (the final usage chunk). Preserve it; the gateway emits it as the
-- terminal usage chunk. Note: keys must match Go's TokenUsage json tags
-- (prompt/completion/total); the gateway re-emits standard *_tokens.
local uses = nil
if type(chunk.usage) == "table" then
uses = {
prompt = chunk.usage.prompt_tokens or chunk.usage.prompt or 0,
completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
total = chunk.usage.total_tokens or chunk.usage.total or 0,
}
-- 独立字段与 prompt_tokens_details **并存**透传,不要写成 elseif:
-- 上游命中缓存时两者都发,非流式路径也是两个都带。写成 elseif 会让
-- 流式丢掉 prompt_cache_hit_tokens/miss,与同一源的**非流式**产出不一致
-- (dsh 优先读 details,但只认独立字段的老客户端会看不到缓存)。
if type(chunk.usage.prompt_tokens_details) == "table" and chunk.usage.prompt_tokens_details.cached_tokens ~= nil then
uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
end
if (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
if uses.prompt_tokens_details == nil then
uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
end
end
local ctd = chunk.usage.completion_tokens_details
if type(ctd) == "table" and ctd.reasoning_tokens ~= nil then
uses.completion_tokens_details = { reasoning_tokens = ctd.reasoning_tokens }
end
end
if not chunk.choices or #chunk.choices == 0 then
-- 空 choices 的帧既不是内容也不是结束信号。上游发两种:
-- {"choices":[],"usage":{...}} —— 终帧用量
-- {"choices":[],"cost":"0"} —— 单独的费用帧
-- 两者可能落在同一帧上,必须都转出去;早退只带 usage 会把费用丢干净。
local out = { done = false }
if uses ~= nil then out.usage = uses end
if chunk.cost ~= nil then out.cost = tostring(chunk.cost) end
if uses == nil and chunk.cost == nil then return "" end
return json.encode(out)
end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
local finish = (type(fr) == "string" and fr ~= "") and fr or nil
local unified = {
content = delta.content or "",
done = (finish ~= nil)
}
if finish then
unified.finish_reason = finish
end
if uses ~= nil then
unified.usage = uses
end
-- zen 用 reasoning 字段承载推理文本(OpenAI 惯例是 reasoning_content)
local reasoning = delta.reasoning_content or delta.reasoning
if reasoning then
unified.reasoning_content = reasoning
end
if delta.tool_calls then
-- pass raw streaming fragments through; OpenAI clients accumulate index+id+name+arguments
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
-- 错误收敛(可选钩子):zen 错误信封固定为 {error={type,message}};
-- 免费池限流 FreeUsageLimitError 单独标注。返回 nil 走通用兜底。
function adapter.transform_error(status, body)
local ok, resp = pcall(json.decode, body)
if not ok or type(resp) ~= "table" then return nil end
local e = resp.error
if type(e) ~= "table" then return nil end
if e.type == "FreeUsageLimitError" then
return "zen free pool quota exhausted"
end
return e.message
end
return adapter

View File

@ -100,6 +100,8 @@ type handlerRequest struct {
// handlerResponse is what a Lua handler returns.
type handlerResponse struct {
// Proxy is a loopback HTTP origin. The gateway owns streaming and upgrades.
Proxy string
Status int
Headers map[string]string
Body string
@ -180,6 +182,9 @@ func parseHandlerResponse(v interface{}) (*handlerResponse, error) {
return nil, fmt.Errorf("status must be a number, got %T", s)
}
}
if target, ok := m["proxy"].(string); ok {
out.Proxy = target
}
if b, ok := m["body"].(string); ok {
out.Body = b
}
@ -196,9 +201,9 @@ func parseHandlerResponse(v interface{}) (*handlerResponse, error) {
// return. A table carrying ONLY a status is not: `{status=204}` is the normal
// way to answer with no body, and treating it as an error would make the
// correct spelling unusable.
if out.Body == "" && out.JSON == nil && out.Headers == nil && len(m) == 0 {
if out.Body == "" && out.JSON == nil && out.Headers == nil && out.Proxy == "" && len(m) == 0 {
return nil, fmt.Errorf("handler returned an empty table; return " +
"{status=…, body=…}, {status=…, json=…}, or {status=…} for no body")
"{status=…, body=…}, {status=…, json=…}, {status=…, proxy=…}, or {status=…} for no body")
}
return out, nil
}

View File

@ -2359,6 +2359,8 @@ type HTTPHandler struct {
// Path is the route suffix under /api/plugins/http/. It may contain ":name"
// segments, captured into request.params.
Path string `json:"path"`
// Prefix claims this path and its descendants for a streaming proxy handler.
Prefix bool `json:"prefix,omitempty"`
// Method is the HTTP method; "" or GET. Only GET/POST/PUT/DELETE/PATCH are
// accepted — an arbitrary verb would need a switch in the router for no gain.
Method string `json:"method,omitempty"`
@ -2483,7 +2485,7 @@ func readPluginHTTP(L *golua.State) []HTTPHandler {
continue
}
ctx.strictKeys(h, "http[]", "path", "method", "handler", "description",
"roles", "keys", "public")
"roles", "keys", "public", "prefix")
dh := HTTPHandler{
Path: decString(h, "path"),
Method: decString(h, "method"),
@ -2504,6 +2506,9 @@ func readPluginHTTP(L *golua.State) []HTTPHandler {
}
dh.Handler = name
}
if p, ok := h["prefix"].(bool); ok {
dh.Prefix = p
}
if p, ok := h["public"].(bool); ok {
dh.Public = p
}

View File

@ -52,7 +52,7 @@ plugin.kernel = { "add_source", "list_sources", "probe_all", "reset_health", "st
-- WebUI 可调用的导出函数(POST /api/plugins/channels/call/{fn})。
-- set_endpoints 让运维把渠道端点指向自建代理/镜像;测试用它打假上游。
plugin.exports = { "set_endpoints", "account_add", "account_list", "account_update", "account_delete", "account_test", "account_refresh", "account_reorder", "account_reset", "account_retest", "account_adopt", "model_list", "model_refresh", "model_set_disabled", "model_set_disabled_many", "model_set_all_disabled", "model_clear_dead", "provider_status", "provider_set_enabled", "provider_get_order", "provider_set_order", "credits_claim_all", "credits_status", "credits_balances", "credits_permanent_lock", "backup_export", "backup_import", "backup_status", "auto_checkin", "gateway_get_enabled", "gateway_set_enabled", "usage_token_ledger", "usage_badge", "usage_badge_preference", "onboarding_status", "onboarding_claim", "__trae_derive_probe", "__codearts_sign_probe", "__qoder_machine_probe", "__qoder_refresh_probe", "__codearts_dpop_probe", "__codearts_cred_probe", "__codearts_adapter_sign_probe", "__sync_source_probe", "__trae_solo_probe", "__adapter_install_probe", "__store_dir_probe", "__is_model_gone_probe", "__rank_accounts_probe", "__inject_refresh_platform_probe", "__clear_capabilities_probe", "__qoder_claim_outcome_probe", "__is_free_probe", "__claim_covers_probe", "__schedule_probe", "__parse_capability_probe", "__inject_capability_probe", "__ttl_reset_probe", "__ttl_probe", "__ttl_invalidate_probe", "__serial_probe", "__serial_release_probe", "__set_legacy_cred_probe", "__read_cred_probe", "__clear_all_creds_probe", "credits_tier_probe", "__set_lock_permanent_probe", "__set_expiring_window_probe", "__expiring_window_probe", "__record_dead_probe", "__catalog_gate_probe", "__catalog_gate_fail_probe", "credits_capability", "claims_capable" }
plugin.exports = { "set_endpoints", "account_add", "account_list", "account_update", "account_delete", "account_test", "account_refresh", "account_reorder", "account_reset", "account_retest", "account_adopt", "model_list", "model_refresh", "model_set_disabled", "model_set_disabled_many", "model_set_all_disabled", "model_clear_dead", "provider_status", "provider_set_enabled", "provider_get_order", "provider_set_order", "credits_claim_all", "credits_status", "credits_balances", "credits_permanent_lock", "backup_export", "backup_import", "backup_status", "auto_checkin", "gateway_get_enabled", "gateway_set_enabled", "usage_token_ledger", "usage_badge", "usage_badge_preference", "onboarding_status", "onboarding_claim", "__trae_derive_probe", "__codearts_sign_probe", "__qoder_machine_probe", "__qoder_refresh_probe", "__codearts_dpop_probe", "__codearts_cred_probe", "__codearts_adapter_sign_probe", "__sync_source_probe", "__trae_solo_probe", "__adapter_install_probe", "__store_dir_probe", "__set_loopback_probe", "__is_model_gone_probe", "__rank_accounts_probe", "__inject_refresh_platform_probe", "__clear_capabilities_probe", "__qoder_claim_outcome_probe", "__is_free_probe", "__claim_covers_probe", "__schedule_probe", "__parse_capability_probe", "__inject_capability_probe", "__ttl_reset_probe", "__ttl_probe", "__ttl_invalidate_probe", "__serial_probe", "__serial_release_probe", "__set_legacy_cred_probe", "__read_cred_probe", "__clear_all_creds_probe", "credits_tier_probe", "__set_lock_permanent_probe", "__set_expiring_window_probe", "__expiring_window_probe", "__record_dead_probe", "__catalog_gate_probe", "__catalog_gate_fail_probe", "credits_capability", "claims_capable" }
@ -194,7 +194,9 @@ local PLATFORMS = {
mode = "trae",
exchange_url = "https://api.trae.com.cn/cloudide/api/v3/trae/oauth/ExchangeToken",
exchange_body = '{"ClientID":"{client_id}","RefreshToken":"{refresh_token}","ClientSecret":"-","UserID":""}',
client_id = "", -- 参考用 product.clientId;TRAE 回调直传形态不强制,留空
client_id = "en1oxy7wnw8j9n", -- 实测值(对齐参考 trae-product.ts 的 clientId)
-- ↑ 这个值**不是**可选的:ExchangeToken 的请求体里 ClientID 是必填,
-- 留空会让交换稳定 400(详见文件内 traeCallback 的注释)。
},
},
@ -4269,11 +4271,28 @@ local function spawnBrowser(start_url)
return nil, "浏览器 CDP 无应答(:" .. tostring(cdpPort) .. "):" .. tostring(why)
end
b.pids = pids
b.session = { display = disp, vnc = vport, ws = wport, cdp = cdpPort, pass = pass, seq = seq }
local host = (plugin.state.settings and plugin.state.settings.vnc_host) or "127.0.0.1"
-- 同源代理不再需要 vnc_host;后端仍只监听回环。
local sess = tostring(seq) .. "-" .. pass:sub(1, 8)
b.session = { display = disp, vnc = vport, ws = wport, cdp = cdpPort, pass = pass, seq = seq, sess = sess,
expires_at = (os.time and os.time() or 0) + 900 }
-- 代理入口:把 noVNC 视图路径经网关回传,而不是让客户端去连 VNC 端口。
-- 客户端可能来自另一台机器(127.0.0.1 指向客户端自己)且 websockify 只绑回环,
-- 所以只能由网关同端口转发;插件只提供回环目标与绝对路径,不处理传输。
local base = "/api/plugins/http/channels/browser/proxy/" .. sess
-- noVNC 用 `new URL(path, location.href)` 解析 path(ui.js 的 connect()),
-- 即**相对 vnc.html 所在目录**解析,默认值就是相对名 'websockify'。
-- 曾传站点根路径(/api/.../websockify)→ 被当相对路径 ⇒ 路径重复拼接:
-- .../proxy/<id>/api/plugins/http/channels/browser/proxy/<id>/websockify
-- 于是 WebSocket 永远连不上(noVNC 显示连接失败,页面看似白屏)。
-- 只用相对名,与 noVNC 默认值一致。
local proxyPath = base .. "/vnc.html?autoconnect=1&resize=scale&password=" .. pass
.. "&path=websockify"
return {
view_url = ("http://%s:%d/vnc.html?autoconnect=1&host=%s&port=%d&password=%s"):format(
host, wport, host, wport, pass),
view_url = proxyPath,
proxy_path = proxyPath,
proxy_url = base .. "/vnc.html",
session_id = sess,
vnc_target = ("http://127.0.0.1:%d"):format(wport),
password = pass,
cdp_port = cdpPort,
display = disp,
@ -4826,25 +4845,19 @@ function plugin.poll_login(req)
elseif s.platform == "trae" then
-- Trae:回调把 token 直接放在 query 里(refreshToken/userJwt/userInfo),
-- 故把整个回调 query 交给 traeCallback(它在两条路径上共用)。
--
-- ★ 这里曾经有一段**自己发明的**「授权码交换」:回调只带 code 时,拿
-- exchange_body 去 ExchangeToken。那是错的,而且是稳定 400:
-- · ExchangeToken 的签名是 RefreshToken,不是 code;
-- · exchange_body 里根本没有 {code} 占位符,替换是空操作。
-- 结果是日志回一句误导性的「授权码交换失败: 400」,把真因
-- 「上游走了 PKCE 流程」掩盖成「交换出错了」。
--
-- 按参考实现(trae-oauth.ts parseTraeCallbackDetailed)的做法:
-- 带 code 的回调是**合法回调**,只是我们不支持的 PKCE 分支,
-- 要**明确报出来**而不是尝试一个不存在的交换。
-- traeCallback 已内建这个判定(返回「上游返回了 PKCE 授权码…」)。
credential, account, cerr = traeCallback(plat, cb, s)
if not credential and code ~= "" then
-- 回调只给了 code(PKCE 形态)→ 用 exchange 端点的标准交换
local body = (plat.callback.exchange_body or "")
:gsub("{client_id}", plat.callback.client_id or "")
:gsub("{code}", code)
:gsub("{port}", tostring(gatewayPort()))
local resp, err = __llmsproxy_http({ url = plat.callback.exchange_url,
method = "POST", headers = { ["Content-Type"] = "application/json" }, body = body })
if err or not resp or resp.status ~= 200 then
cerr = "Trae 授权码交换失败: " .. tostring(err or (resp and resp.status))
else
local ok, rec = pcall(json.decode, resp.body or "")
local access = ok and type(rec) == "table"
and (rec.Token or rec.token or rec.AccessToken or rec.access_token)
if not access then cerr = "Trae 授权码交换响应缺少 Token"
else credential, account, cerr = json.encode({ access_token = access }), "trae", nil end
end
end
else
-- Gemini 等标准 OAuth:表单交换(必带 client_secret,见 token_body 注释)
local body = (plat.callback.token_body or "")
@ -6251,6 +6264,9 @@ plugin.http = {
roles = { "admin" }, description = "浏览器栈依赖预检(缺什么、装哪个包)" },
{ path = "channels/browser/status", method = "GET", handler = "browser_status",
roles = { "admin" }, description = "服务端浏览器会话状态" },
{ path = "channels/browser/proxy/:session", method = "GET", prefix = true,
handler = "browser_proxy", roles = { "admin" },
description = "把会话的 noVNC 静态资源与 WebSocket 经网关同端口转发(不暴露 VNC 端口)" },
{ path = "channels/browser/collect", method = "POST", handler = "collect_credentials",
roles = { "admin" }, description = "从服务端浏览器取凭据(CDP)" },
{ path = "channels/browser/stop", method = "POST", handler = "stop_browser",
@ -7110,27 +7126,24 @@ function plugin.usage_token_ledger(req)
if key ~= "" then
url = url .. "&key=" .. (key:len() <= 6 and key or ("***" .. key:sub(-6)))
end
local resp, err = __llmsproxy_http({ url = url, method = "GET", timeout_ms = 4000 })
local headers = {}
if key ~= "" then
headers["Authorization"] = "Bearer " .. key
end
local resp, err = __llmsproxy_http({ url = url, method = "GET", timeout_ms = 4000, headers = headers })
if err or not resp or resp.status ~= 200 then
return { status = 200, json = { ok = true, snapshot = { available = false,
error = err or (resp and tostring(resp.status) or "no response") } } }
return { status = 503, json = { ok = false, error = "usage snapshot unavailable: " .. tostring(err or (resp and resp.status or "no response")) } }
end
local ok, rec = pcall(json.decode, resp.body or "")
if not ok or type(rec) ~= "table" then
return { status = 200, json = { ok = true, snapshot = { available = false, error = "stats 无法解析" } } }
end
-- 汇总 token 总量(兼容 stats 的不同形状)
local prompt, completion, requests = 0, 0, 0
local rows = rec.requests or rec.rows or rec.data or {}
if type(rows) == "table" then
for _, r in ipairs(rows) do
if type(r) == "table" then
prompt = prompt + (tonumber(r.prompt_tokens) or 0)
completion = completion + (tonumber(r.completion_tokens) or 0)
requests = requests + 1
end
end
return { status = 502, json = { ok = false, error = "usage snapshot 无法解析" } }
end
-- 汇总 token 总量。/api/stats 的聚合在 `total` 下,不在顶层数组中。
-- 之前错误地遍历 rec.requests/rows/data,导致该端点永远返回 0。
local total = type(rec.total) == "table" and rec.total or {}
local prompt = tonumber(total.prompt_tokens) or 0
local completion = tonumber(total.completion_tokens) or 0
local requests = tonumber(total.reqs) or 0
return { status = 200, json = { ok = true, snapshot = { available = true,
tokens = { prompt = prompt, completion = completion, total = prompt + completion },
requests = requests, raw = rec } } }
@ -7488,6 +7501,24 @@ function plugin.browser_status(req)
return { status = 200, json = { ok = true, running = s ~= nil, session = s } }
end
-- browser_proxy:前缀代理的每次请求入口。
-- 只回答「当前会话的回环目标」;回收后 session 为空,地址即失效(404),
-- 未运行的会话 id 也不会被转发(防目录穿越与跨会话探测)。
function plugin.browser_proxy(req)
sweepSessions()
local b = browserStack()
local s = b.session
local want = req and req.params and req.params.session or nil
if s and s.expires_at and s.expires_at <= os.time() then
reapBrowser()
s = nil
end
if not s or not s.ws or not s.sess or s.sess ~= want then
return { status = 404, json = { error = "没有这个浏览器会话" } }
end
return { proxy = ("http://127.0.0.1:%d"):format(s.ws) }
end
function plugin.inject_platforms(req)
local args = bodyOf(req)
if args.platforms == nil then args = req end
@ -9524,6 +9555,23 @@ function plugin.__store_dir_probe()
return { json = { store_dir = storeDir() } }
end
-- plugin.__set_loopback_probe:只给测试用 —— 把某会话的 loopback 回调文件
-- 指到测试摆好的路径,以便直接驱动 poll_login 的 callback 分支。
--
-- 为什么需要它:callback 流的真实登录走 poll_login(读 loopback 文件),
-- 而那个文件平时由插件自己起的 python 接收器写入。判据要验的正是**这条路径**
-- 的转码/交换行为(真实缺陷曾藏在它的 trae 分支里),但测试不起真实接收器,
-- 故需要这个注入点。生产代码不会调用它。
function plugin.__set_loopback_probe(args)
args = args or {}
local sid = tostring(args.session_id or "")
local file = tostring(args.file or "")
if sid == "" or file == "" then return { json = { error = "need session_id and file" } } end
if type(plugin.state.loopbacks) ~= "table" then plugin.state.loopbacks = {} end
plugin.state.loopbacks[sid] = { file = file }
return { json = { ok = true, session_id = sid, file = file } }
end
-- plugin.credits_tier_probe:只给测试用 —— 单账号的余额分档结果。
-- 暴露 expiring/permanent/tier/usable 四个值,让判据能逐条钉住分档规则
-- (含"失效包必须跳过""到期未知归永久""锁定永久积分时只剩永久的号不可用")。