mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-09-20 00:48:00 +00:00
The gateway hardcoded "stop" on every terminating stream chunk, so tool-call rounds reported finish_reason=stop and length caps were invisible to clients. UnifiedChunk now carries finish_reason; adapters emit it (with empty-string finish reasons like sensenova treated as non-terminal), standardSSEChunk passes it through for un-adapted upstreams, [DONE] no longer emits a duplicate reason-less done chunk, and both streaming paths emit the real reason with "stop" as fallback. Also vendor sensenova/agentrouter adapters into the repo: they were WebUI-only uploads and a deploy sync silently removed them while live AUTO-chain slots still referenced them.
187 lines
7.2 KiB
Lua
187 lines
7.2 KiB
Lua
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;因此失去全部 content 的
|
||
-- 消息整条丢弃,避免上游 "unknown variant `image_url`, expected `text`"。
|
||
-- 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
|
||
if type(req.stream_options) ~= "table" then req.stream_options = {} end
|
||
req.stream_options.include_usage = true
|
||
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
|
||
drop = true
|
||
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
|
||
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,
|
||
}
|
||
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
|
||
|
||
return adapter
|