mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-09-20 00:48:00 +00:00
7fb8f96b82
A key with scope=[AUTO] could previously: 1. request ANY concrete model id directly (hasScopeModel/checkModelScope treated AUTO as a wildcard) 2. see the full 56-model list on /v1/models (intersectModels considered AUTO as grant-everything) AUTO now only authorizes the AUTO routing mode. Direct requests to a specific model require an explicit scope entry. Also carries agentrouter.lua WAF fingerprint headers (Origin/Referer/ X-Requested-With) already staged on this branch. Tests: TestHasScopeModelWithSourcePrefix updated; full suite green.
213 lines
8.3 KiB
Lua
213 lines
8.3 KiB
Lua
local adapter = {}
|
||
|
||
adapter.name = "agentrouter"
|
||
adapter.version = "1.0.0"
|
||
adapter.endpoint = "/chat/completions"
|
||
adapter.headers = {}
|
||
|
||
-- AgentRouter 的阿里云 WAF 按三重维度校验：出口 IP（必须海外）、
|
||
-- TLS 指纹（JS/Go HTTP 层与 curl 不同）、浏览器指纹 header 集。
|
||
-- 纯 UA 已不够：WAF 拦 12 种 agent CLI UA 中的 10 种（全 405 HTML），
|
||
-- 只有同时带 Origin: qwen.ai + Referer + X-Requested-With 才放行，
|
||
-- 且同 IP 短时间连续 3+ 次请求会被速率封禁，靠 adapter 侧低频调用 +
|
||
-- llmsproxy 的 prefFailStep 冷却自然限制，来源无法控制速率。
|
||
local default_ua = "QwenCode/0.2.0 (linux; x64)"
|
||
|
||
-- AgentRouter fronts Claude models (claude-opus-4-8), and Claude upstreams
|
||
-- enforce Anthropic's tool id rule ^[a-zA-Z0-9_-]{1,64}$ by rejecting the WHOLE
|
||
-- request. Plain OpenAI does not, so an id minted by a permissive model (e.g.
|
||
-- "bash:0" from moonshotai/kimi-k3) is replayed here by the client and kills
|
||
-- every turn. See anthropic.lua / openai.lua for the same helper: Lua adapters
|
||
-- have no shared prelude, so each carries its own copy.
|
||
local TOOL_ID_MAX = 64
|
||
|
||
local function safe_tool_id(id)
|
||
if type(id) ~= "string" or id == "" then return id end
|
||
local clean = string.gsub(id, "[^A-Za-z0-9_-]", "_")
|
||
if clean == id and #clean <= TOOL_ID_MAX then
|
||
return clean
|
||
end
|
||
local digest = string.sub(sha256_hex(id), 1, 8)
|
||
local keep = TOOL_ID_MAX - #digest - 1
|
||
if #clean > keep then clean = string.sub(clean, 1, keep) end
|
||
return clean .. "_" .. digest
|
||
end
|
||
|
||
function adapter.transform_request(raw_body)
|
||
local ok, req = pcall(json.decode, raw_body)
|
||
if not ok then return raw_body end
|
||
req.disable_thinking = nil
|
||
req.extra_body = nil
|
||
if req.messages then
|
||
for _, msg in ipairs(req.messages) do
|
||
msg.reasoning_content = nil
|
||
if msg.tool_call_id ~= nil then
|
||
msg.tool_call_id = safe_tool_id(msg.tool_call_id)
|
||
end
|
||
if type(msg.tool_calls) == "table" then
|
||
for _, tc in ipairs(msg.tool_calls) do
|
||
if type(tc) == "table" and tc.id ~= nil then
|
||
tc.id = safe_tool_id(tc.id)
|
||
end
|
||
end
|
||
end
|
||
end
|
||
end
|
||
return json.encode(req)
|
||
end
|
||
|
||
-- 注入 Authorization + 官方客户端 User-Agent
|
||
function adapter.build_headers(meta)
|
||
local ua = default_ua
|
||
local meta_ua = (meta.source or {}).meta and (meta.source).meta.user_agent
|
||
if meta_ua and meta_ua ~= "" then
|
||
ua = meta_ua
|
||
end
|
||
return {
|
||
["Content-Type"] = "application/json",
|
||
["Authorization"] = "Bearer " .. meta.api_key,
|
||
["User-Agent"] = ua,
|
||
-- QwenCode client fingerprint: WAF rejects bare UA without these.
|
||
["Accept"] = "application/json, text/plain, */*",
|
||
["Accept-Language"] = "zh-CN,zh;q=0.9",
|
||
["Origin"] = "https://qwen.ai",
|
||
["Referer"] = "https://qwen.ai/",
|
||
["X-Requested-With"] = "XMLHttpRequest",
|
||
["Connection"] = "keep-alive",
|
||
}
|
||
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 = safe_tool_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
|
||
|
||
-- usage-only terminal chunk (empty choices + usage): forward it so the
|
||
-- gateway emits exact token counts (and cache fields when present).
|
||
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
|
||
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 delta.reasoning_content then
|
||
unified.reasoning_content = delta.reasoning_content
|
||
end
|
||
if delta.tool_calls then
|
||
-- Sanitize outbound too: a dirty id must never enter a client session,
|
||
-- because the client replays it to every other source. Only the first
|
||
-- fragment of a streamed call carries an id; later argument fragments
|
||
-- have none and must stay id-less for index-based accumulation.
|
||
for _, tc in ipairs(delta.tool_calls) do
|
||
if type(tc) == "table" and tc.id ~= nil then
|
||
tc.id = safe_tool_id(tc.id)
|
||
end
|
||
end
|
||
unified.tool_calls = delta.tool_calls
|
||
end
|
||
if uses ~= nil then
|
||
unified.usage = uses
|
||
end
|
||
return json.encode(unified)
|
||
end
|
||
|
||
-- 错误收敛：前置 WAF 会返回整页 HTML（阿里云盾），JSON 时为 new-api 风格
|
||
function adapter.transform_error(status, body)
|
||
local low = string.lower(body or "")
|
||
if string.sub(low, 1, 9) == "<!doctype" or string.find(low, "<html", 1, true) then
|
||
return "blocked by AgentRouter WAF"
|
||
end
|
||
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
|