mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-11-12 20:27:23 +00:00
chore(adapters): 移除非官方调用方式的适配器，保留官方适配器与模板
移除 4 个靠伪造客户端身份/绕过 WAF 才能工作的适配器，内核不再发行任何 非官方调用方式： - opencodezen / opencode / opencodego：靠 x-opencode-* 客户端指纹冒充官方 客户端；zen 免费池明确要求「free tier can only be used in OpenCode」 - agentrouter：伪造 Origin: qwen.ai + Referer + X-Requested-With 绕过阿里云 WAF 保留 12 个官方适配器（openai/deepseek/anthropic/gemini/github/groq/mistral/ ollama/kimicode/qwen38/sensenova/trae），其中 sensenova/qwen38 实测零伪装特征。 本地保留两处：adapters/_local_archive/（gitignored 非递归子目录，不加载） 与线上 /etc/llmsproxy/adapters/（adapter_dir 权威副本，cp -f 不删文件）。 测试同步：删除仅服务于被移除适配器的 11 个测试函数与 usage_cost_test.go； 改写 2 处借 opencode 之名的 provider 测试为用 openai 的 HTML 错误页压缩能力 验证同一契约（适配器钩子拥有错误格式、原文不外泄）。 验证：go test -tags luajit ./... 全绿；二进制内 x-opencode-client / QwenCode/0.2.0 / qwen.ai 等指纹字符串计数归零。
This commit is contained in:
JianFeeeee
@ -1,212 +0,0 @@
|
||||
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
|
||||
@ -1,243 +0,0 @@
|
||||
local adapter = {}
|
||||
|
||||
adapter.name = "opencode"
|
||||
adapter.version = "1.0.0"
|
||||
adapter.endpoint = "/chat/completions"
|
||||
|
||||
-- opencode.ai zen 网关按客户端指纹（UA + x-opencode-* 头）路由请求池：
|
||||
-- 缺少 x-opencode-client/session/request/project 身份头的请求会被判为匿名
|
||||
-- 客户端，x-preview-f-free 等模型在带 tools 时上游直接失败——流式返回单
|
||||
-- chunk "finish_reason":"network_error" 空 content，非流式返回 503
|
||||
-- "Endpoint is unavailable"，表现为"空回复"。因此除 UA 外必须附带
|
||||
-- x-opencode-* 身份头；session/request 每请求派生唯一值（见 build_headers）。
|
||||
adapter.headers = {
|
||||
["User-Agent"] = "opencode/1.18.21 ai-sdk/provider-utils/4.0.23 runtime/bun/1.3.14",
|
||||
}
|
||||
|
||||
-- 每请求生成身份头。沙箱无 os/math，用 meta.timestamp + 请求体哈希派生：
|
||||
-- 同秒内重复请求 id 相同可接受（zen 只校验存在性，不校验格式）。
|
||||
local function rand_id(prefix, seed)
|
||||
return prefix .. string.sub(sha256_hex(seed), 1, 24)
|
||||
end
|
||||
|
||||
function adapter.build_headers(meta)
|
||||
local ts = tostring(meta.timestamp or "")
|
||||
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
|
||||
["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. (meta.source and meta.source.name or "")), 1, 32),
|
||||
["x-opencode-session"] = rand_id("ses_", "session|" .. ts),
|
||||
["x-opencode-request"] = rand_id("msg_", "request|" .. ts .. "|" .. tostring(meta.body or "")),
|
||||
}
|
||||
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
|
||||
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 stricter upstreams (OpenCode Go:
|
||||
-- "stream_options should be set along with stream"), which failed every
|
||||
-- non-stream call. Only attach it when the request actually streams.
|
||||
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
|
||||
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).
|
||||
--
|
||||
-- This is the common shape for agent clients: an assistant
|
||||
-- turn whose content is only [thinking, toolCall] serialises
|
||||
-- to content:[] with tool_calls — exactly the case that used
|
||||
-- to vanish here. Emit "" instead, which zen accepts.
|
||||
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
|
||||
|
||||
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 ""
|
||||
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,
|
||||
}
|
||||
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
|
||||
-- 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
|
||||
@ -1,354 +0,0 @@
|
||||
local adapter = {}
|
||||
|
||||
adapter.name = "opencodego"
|
||||
adapter.version = "1.0.0"
|
||||
adapter.endpoint = "/chat/completions"
|
||||
|
||||
-- OpenCode Go（包月订阅端点，https://opencode.ai/zen/go/v1）
|
||||
--
|
||||
-- 与 OpenCode Zen（opencodezen.lua，https://opencode.ai/zen/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（Go）服务包月订阅池。上游**强制要求**
|
||||
-- `x-opencode-session` 头，缺失直接 400 "MissingSessionID"。
|
||||
-- * Go 的 thinking 模型（deepseek-v4.1-flash 等）**必须回传** assistant 轮的
|
||||
-- `reasoning_content`，否则 400：
|
||||
-- The `reasoning_content` in the thinking mode must be passed back to the API.
|
||||
-- 这是本适配器与 Zen 适配器最关键的差异 —— Zen 会剥掉它，Go 必须原样保留。
|
||||
-- * Go 上游对协议更严格：非流式请求带 `stream_options` 会被拒
|
||||
-- （"stream_options should be set along with stream"）。
|
||||
--
|
||||
-- 同样需要 opencode 客户端指纹（UA + x-opencode-*）才能被正确识别与路由。
|
||||
adapter.headers = {
|
||||
["User-Agent"] = "opencode/1.18.21 ai-sdk/provider-utils/4.0.23 runtime/bun/1.3.14",
|
||||
}
|
||||
|
||||
-- 每请求生成身份头。沙箱无 os/math，用 meta.timestamp + 请求体哈希派生：
|
||||
-- 同秒内重复请求 id 相同可接受（zen 只校验存在性，不校验格式）。
|
||||
local function rand_id(prefix, seed)
|
||||
return prefix .. string.sub(sha256_hex(seed), 1, 24)
|
||||
end
|
||||
|
||||
-- 会话指纹：取历史里**第一条 user 消息**。
|
||||
--
|
||||
-- 为什么不直接用客户端的会话 id：实测抓包（tcpdump 抓 127.0.0.1:8081 的真实
|
||||
-- agent 请求）确认通用 OpenAI 客户端**根本不发**任何会话标识 —— body 里没有
|
||||
-- user / session_id / conversation_id / metadata，请求头也只有 X-Stainless-*
|
||||
-- （OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套 x-opencode-session
|
||||
-- 是它自己的概念，通用客户端无从转发。
|
||||
--
|
||||
-- 退而求其次但要够用：历史被逐轮重放，**第一条 user 消息在整个会话里恒定**，
|
||||
-- 用它做指纹即可得到"每会话一个 session"，而不是"每源一个 session"。
|
||||
-- 拿不到时（无 user 消息）返回空串，调用方回退到按源稳定。
|
||||
local function conversation_fingerprint(body)
|
||||
if type(body) ~= "string" or body == "" then return "" end
|
||||
local ok, req = pcall(json.decode, body)
|
||||
if not ok or type(req) ~= "table" then return "" end
|
||||
for _, m in ipairs(req.messages or {}) do
|
||||
if type(m) == "table" and m.role == "user" then
|
||||
local c = m.content
|
||||
if type(c) == "string" then
|
||||
if c ~= "" then return c end
|
||||
elseif type(c) == "table" then
|
||||
for _, part in ipairs(c) do
|
||||
if type(part) == "table" and part.type == "text" and part.text then
|
||||
return part.text
|
||||
end
|
||||
end
|
||||
end
|
||||
return ""
|
||||
end
|
||||
end
|
||||
return ""
|
||||
end
|
||||
|
||||
-- session_seed 决定上游会话号（x-opencode-session 的种子）。
|
||||
--
|
||||
-- 优先级：
|
||||
-- 1) 客户端自带的会话标识（meta.client_session）——pi 等在开启
|
||||
-- compat.sendSessionAffinityHeaders 后会发 x-session-affinity，
|
||||
-- 这是平台真实的会话 id，整个会话恒定且天然按会话隔离。
|
||||
-- 2) 退路：历史里**第一条 user 消息**做会话指纹。
|
||||
-- 3) 再退：只按源固定（连 user 消息都没有时）。
|
||||
--
|
||||
-- 为什么需要 2/3：通用 OpenAI 客户端默认**根本不发**会话标识 —— 实测抓包
|
||||
-- （tcpdump 抓 127.0.0.1:8081 真实 agent 请求）确认 body 里没有
|
||||
-- user / session_id / conversation_id / metadata，请求头也只有
|
||||
-- X-Stainless-*（OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套
|
||||
-- x-opencode-session 是它自己的概念，通用客户端无从转发。
|
||||
--
|
||||
-- 为什么必须稳定：上游前缀缓存是**会话级**的。会话号每请求一变，
|
||||
-- 缓存永不命中（实测：固定会号第 2 次命中 5888，每请求换会号则恒为 0）。
|
||||
local function session_seed(meta)
|
||||
local src = (meta.source and meta.source.name) or ""
|
||||
local base = "session|llmsproxy|" .. src
|
||||
local cs = meta.client_session
|
||||
if type(cs) == "string" and cs ~= "" then
|
||||
return base .. "|client|" .. cs
|
||||
end
|
||||
return base .. "|" .. conversation_fingerprint(meta.body)
|
||||
end
|
||||
|
||||
function adapter.build_headers(meta)
|
||||
local ts = tostring(meta.timestamp or "")
|
||||
local src = (meta.source and meta.source.name) or ""
|
||||
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
|
||||
["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. src), 1, 32),
|
||||
-- session 必须**按源稳定**，不能每请求换：上游的前缀缓存在同一 session
|
||||
-- 内才复用。实测（同一段 6032 token 提示词）：
|
||||
-- 固定 session -> 第 2 次命中 5888/6032，cached_tokens=5888
|
||||
-- 每请求换 session -> 永远 0 命中
|
||||
-- 原先用 meta.timestamp 派生，等于每请求都是新会话，缓存永远无效，
|
||||
-- 上游也无法做会话亲和路由。
|
||||
["x-opencode-session"] = rand_id("ses_", session_seed(meta)),
|
||||
-- request id 仍每请求唯一（它只是请求标识，不参与缓存键）
|
||||
["x-opencode-request"] = rand_id("msg_", "request|" .. ts .. "|" .. tostring(meta.body or "")),
|
||||
}
|
||||
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
|
||||
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
|
||||
-- Go 的 thinking 模式**必须**回传 reasoning_content：剥掉它会让
|
||||
-- 上游直接 400（"The `reasoning_content` in the thinking mode must
|
||||
-- be passed back to the API"），agent 的每一轮都会失败。
|
||||
-- 注意：与 opencodezen.lua 的行为**相反**，不要在这里剥。
|
||||
--
|
||||
-- 但绝大多数客户端（pi 等）根本不保存也不回传 reasoning，只保留
|
||||
-- 工具调用本身。上游只在“带 tool_calls 的助手轮”上校验这个字段，
|
||||
-- 实测**空串即可通过校验**，所以缺省时补空串：既满足上游的
|
||||
-- 一致性要求，又不伪造任何推理内容（用户看到的 reasoning 仍然是
|
||||
-- 上游本轮真实返回的）。
|
||||
if msg.role == "assistant"
|
||||
and type(msg.tool_calls) == "table" and #msg.tool_calls > 0
|
||||
and msg.reasoning_content == nil then
|
||||
msg.reasoning_content = ""
|
||||
end
|
||||
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
|
||||
|
||||
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
|
||||
-- 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
|
||||
@ -1,342 +0,0 @@
|
||||
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"）。
|
||||
adapter.headers = {
|
||||
["User-Agent"] = "opencode/1.18.21 ai-sdk/provider-utils/4.0.23 runtime/bun/1.3.14",
|
||||
}
|
||||
|
||||
-- 每请求生成身份头。沙箱无 os/math，用 meta.timestamp + 请求体哈希派生：
|
||||
-- 同秒内重复请求 id 相同可接受（zen 只校验存在性，不校验格式）。
|
||||
local function rand_id(prefix, seed)
|
||||
return prefix .. string.sub(sha256_hex(seed), 1, 24)
|
||||
end
|
||||
|
||||
-- 会话指纹：取历史里**第一条 user 消息**。
|
||||
--
|
||||
-- 为什么不直接用客户端的会话 id：实测抓包（tcpdump 抓 127.0.0.1:8081 的真实
|
||||
-- agent 请求）确认通用 OpenAI 客户端**根本不发**任何会话标识 —— body 里没有
|
||||
-- user / session_id / conversation_id / metadata，请求头也只有 X-Stainless-*
|
||||
-- （OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套 x-opencode-session
|
||||
-- 是它自己的概念，通用客户端无从转发。
|
||||
--
|
||||
-- 退而求其次但要够用：历史被逐轮重放，**第一条 user 消息在整个会话里恒定**，
|
||||
-- 用它做指纹即可得到"每会话一个 session"，而不是"每源一个 session"。
|
||||
-- 拿不到时（无 user 消息）返回空串，调用方回退到按源稳定。
|
||||
local function conversation_fingerprint(body)
|
||||
if type(body) ~= "string" or body == "" then return "" end
|
||||
local ok, req = pcall(json.decode, body)
|
||||
if not ok or type(req) ~= "table" then return "" end
|
||||
for _, m in ipairs(req.messages or {}) do
|
||||
if type(m) == "table" and m.role == "user" then
|
||||
local c = m.content
|
||||
if type(c) == "string" then
|
||||
if c ~= "" then return c end
|
||||
elseif type(c) == "table" then
|
||||
for _, part in ipairs(c) do
|
||||
if type(part) == "table" and part.type == "text" and part.text then
|
||||
return part.text
|
||||
end
|
||||
end
|
||||
end
|
||||
return ""
|
||||
end
|
||||
end
|
||||
return ""
|
||||
end
|
||||
|
||||
-- session_seed 决定上游会话号（x-opencode-session 的种子）。
|
||||
--
|
||||
-- 优先级：
|
||||
-- 1) 客户端自带的会话标识（meta.client_session）——pi 等在开启
|
||||
-- compat.sendSessionAffinityHeaders 后会发 x-session-affinity，
|
||||
-- 这是平台真实的会话 id，整个会话恒定且天然按会话隔离。
|
||||
-- 2) 退路：历史里**第一条 user 消息**做会话指纹。
|
||||
-- 3) 再退：只按源固定（连 user 消息都没有时）。
|
||||
--
|
||||
-- 为什么需要 2/3：通用 OpenAI 客户端默认**根本不发**会话标识 —— 实测抓包
|
||||
-- （tcpdump 抓 127.0.0.1:8081 真实 agent 请求）确认 body 里没有
|
||||
-- user / session_id / conversation_id / metadata，请求头也只有
|
||||
-- X-Stainless-*（OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套
|
||||
-- x-opencode-session 是它自己的概念，通用客户端无从转发。
|
||||
--
|
||||
-- 为什么必须稳定：上游前缀缓存是**会话级**的。会话号每请求一变，
|
||||
-- 缓存永不命中（实测：固定会号第 2 次命中 5888，每请求换会号则恒为 0）。
|
||||
local function session_seed(meta)
|
||||
local src = (meta.source and meta.source.name) or ""
|
||||
local base = "session|llmsproxy|" .. src
|
||||
local cs = meta.client_session
|
||||
if type(cs) == "string" and cs ~= "" then
|
||||
return base .. "|client|" .. cs
|
||||
end
|
||||
return base .. "|" .. conversation_fingerprint(meta.body)
|
||||
end
|
||||
|
||||
function adapter.build_headers(meta)
|
||||
local ts = tostring(meta.timestamp or "")
|
||||
local src = (meta.source and meta.source.name) or ""
|
||||
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
|
||||
["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. src), 1, 32),
|
||||
-- session 必须**按源稳定**，不能每请求换：上游的前缀缓存在同一 session
|
||||
-- 内才复用。实测（同一段 6032 token 提示词）：
|
||||
-- 固定 session -> 第 2 次命中 5888/6032，cached_tokens=5888
|
||||
-- 每请求换 session -> 永远 0 命中
|
||||
-- 原先用 meta.timestamp 派生，等于每请求都是新会话，缓存永远无效，
|
||||
-- 上游也无法做会话亲和路由。
|
||||
["x-opencode-session"] = rand_id("ses_", session_seed(meta)),
|
||||
-- request id 仍每请求唯一（它只是请求标识，不参与缓存键）
|
||||
["x-opencode-request"] = rand_id("msg_", "request|" .. ts .. "|" .. tostring(meta.body or "")),
|
||||
}
|
||||
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
|
||||
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
|
||||
|
||||
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
|
||||
-- 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