mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-11-07 09:47:23 +00:00
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。
This commit is contained in:
@ -19,7 +19,7 @@ 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 := os.ReadFile("../../adapters/_local/opencodezen.lua")
|
||||
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@ -134,7 +134,7 @@ func TestOpencodeZenLiveStreamThroughAdapter(t *testing.T) {
|
||||
if os.Getenv("LLMSPROXY_LIVE_ZEN") != "1" {
|
||||
t.Skip("设 LLMSPROXY_LIVE_ZEN=1 开启")
|
||||
}
|
||||
src, err := os.ReadFile("../../adapters/_local/opencodezen.lua")
|
||||
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
@ -2,7 +2,6 @@ package lua
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
@ -10,7 +9,7 @@ import (
|
||||
// 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 := os.ReadFile("../../adapters/_local/opencodezen.lua")
|
||||
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@ -119,7 +118,7 @@ func fmtHex12(v int64) string {
|
||||
// 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 := os.ReadFile("../../adapters/_local/opencodezen.lua")
|
||||
src, err := bundledAdapters.ReadFile("adapters/opencodezen.lua")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
484
internal/lua/adapters/opencodezen.lua
Normal file
484
internal/lua/adapters/opencodezen.lua
Normal 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
|
||||
Reference in New Issue
Block a user