mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-11-07 09:47:23 +00:00
Phase 2 收尾(入向)。ChatRequest 从"客户端发什么就是什么"改为
UnifiedRequest(最大集合)的别名,内核真正用上了那个超集类型。
改掉的具体缺陷:
1. 私有字段泄漏归零(v1 的核心问题)
v1 的 disable_thinking 是内核私有开关,却被序列化进交给适配器的 body,
迫使 10 个适配器各自写 req.disable_thinking = nil 来清理。
现在它是中立的 thinking 字段({enabled, budget_tokens}),客户端与
适配器都认这个词:
- gateway/chat.go:thinkingFromClient() 把 disable_thinking 翻译成
thinking.enabled=false;冲突时中立字段优先(它能带预算,布尔不能)
- deepseek.lua:thinking.enabled=false → extra_body.thinking.type=disabled
- anthropic.lua:thinking.enabled=true + budget → 原生 {type,budget_tokens}
(enabled=false 时不传该字段——Anthropic 没有 type=disabled 这个写法)
- 其余 7 个适配器:把"清理内核私有字段"改成"清理中立字段"
2. Tools/ToolChoice 改 json.RawMessage
原为 []interface{}(OpenAI 原始形状 = 内核在假设某个协议)。
内核从不解释工具 schema——它原样交给适配器,所以原始形状不损失任何
内核侧统一性。ToolDef 结构化类型保留在包内供新适配器选用。
3. 删除 MarshalJSON 后门
v1 手工 splice ExtraBody 进 OpenAI 形状的 body;现在 ExtraBody 是
UnifiedRequest 上一个正正经经声明的字段。
渐进迁移:ChatRequest 保留为别名(不是新类型),49 处引用零改动编译,
语义变更不被机械改名淹没。
测试:新增 thinking_test.go(翻译链 4 例 + 泄漏回归 + tools 透传);
vm_test.go 两处迁移到中立语义。golden 字节级未漂移。
180 lines
7.2 KiB
Lua
180 lines
7.2 KiB
Lua
local adapter = {}
|
||
|
||
adapter.name = "kimicode"
|
||
adapter.version = "1.0.0"
|
||
adapter.endpoint = "/v1/chat/completions"
|
||
adapter.headers = {}
|
||
|
||
-- KimiCode / Kimi K2 属于 OpenAI 兼容协议;但部分云端 API 会校验调用方
|
||
-- "app"(只放行特定 agent),要求每次请求带上按 secret 计算的应用签名。
|
||
-- 这里演示 build_headers 钩子:基于 timestamp + 请求体哈希生成签名头。
|
||
--
|
||
-- 配置要求(source.meta):
|
||
-- meta:
|
||
-- app_id: <申请到的 app id>
|
||
-- app_key: <你的 key(由网关的 base_url 复用 api_key 亦可)>
|
||
-- app_secret: <签名密钥>
|
||
-- app_agent: code-agent # 若云端要求声明 agent 身份
|
||
function adapter.transform_request(raw_body)
|
||
local ok, req = pcall(json.decode, raw_body)
|
||
if not ok then return raw_body end
|
||
req.model = req.model or "kimi-k2"
|
||
-- The gateway's private control fields are GONE from the body (v2): the
|
||
-- neutral `thinking` field carries that intent and each adapter maps it in
|
||
-- its own protocol terms. These upstreams have no thinking switch at all,
|
||
-- so the field is simply dropped here — which is what the nil-ing below
|
||
-- used to do, except the field being dropped is no longer the kernel's
|
||
-- private one.
|
||
req.thinking = nil
|
||
req.extra_body = nil
|
||
return json.encode(req)
|
||
end
|
||
|
||
-- 可选的动态签名钩子。meta 由 Go 注入:
|
||
-- meta.url / meta.method / meta.body / meta.api_key / meta.timestamp / meta.source.meta
|
||
function adapter.build_headers(meta)
|
||
local h = {
|
||
["Content-Type"] = "application/json",
|
||
["X-App-Id"] = tostring((meta.source.meta or {}).app_id or ""),
|
||
["X-Timestamp"] = tostring(meta.timestamp),
|
||
}
|
||
local agent = (meta.source.meta or {}).app_agent
|
||
if agent and agent ~= "" then
|
||
h["X-Agent"] = agent
|
||
end
|
||
-- 校验 app:通常要求 Authorization 用 app secret 派生签名
|
||
local secret = (meta.source.meta or {}).app_secret
|
||
local api_key = meta.source.meta and meta.source.meta.api_key or meta.api_key
|
||
if secret and secret ~= "" then
|
||
local body_hash = sha256_hex(meta.body)
|
||
local sign_string = tostring(meta.timestamp) .. meta.method .. meta.url .. body_hash
|
||
local sign = hmac_sha256_hex(secret, sign_string)
|
||
h["Authorization"] = "Bearer " .. api_key
|
||
h["X-App-Sign"] = sign
|
||
else
|
||
h["Authorization"] = "Bearer " .. api_key
|
||
end
|
||
return h
|
||
end
|
||
|
||
function adapter.transform_response(raw_body)
|
||
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
|
||
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 ""
|
||
if ch.message.reasoning_content then
|
||
unified.reasoning_content = ch.message.reasoning_content
|
||
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). 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,
|
||
}
|
||
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 }
|
||
elseif (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
|
||
uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
|
||
end
|
||
end
|
||
|
||
if not chunk.choices or #chunk.choices == 0 then
|
||
if uses ~= nil then
|
||
-- usage-only chunk is not a content/finish signal; the gateway
|
||
-- emits its own terminal stop chunk and merges this usage.
|
||
return json.encode({ usage = uses, done = false })
|
||
end
|
||
return ""
|
||
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
|
||
if delta.reasoning_content then
|
||
unified.reasoning_content = delta.reasoning_content
|
||
end
|
||
if delta.tool_calls then
|
||
unified.tool_calls = delta.tool_calls
|
||
end
|
||
return json.encode(unified)
|
||
end
|
||
|
||
-- 错误收敛:kimi 网关为 OpenAI 风格 {error:{message,...}}
|
||
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" and type(e.message) == "string" then
|
||
return e.message
|
||
end
|
||
return nil
|
||
end
|
||
|
||
return adapter
|