mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-09-20 17:07:59 +00:00
c9c09b2ba2
两处都源于同一次排查：pi 到底有没有带会话标识、超窗为什么触发不了压缩。 ## 1) 客户端会话 id：pi 一直在发，只是被配置关掉了 之前结论是「通用客户端不发会话 id」——只对了一半。pi 有会话 id，且能发： pi-ai 的 createClient 在 compat.sendSessionAffinityHeaders 为真时，会把 平台会话 id（uuidv7，整个会话恒定）放到 x-session-affinity / x-client-request-id / session_id 上。该开关默认 false，而 llmsproxy 的 provider 配置里没开，所以此前一直收不到。 现在网关按优先级采纳：x-session-affinity → x-session-id → session_id → body 的 prompt_cache_key，并把值经 types.ChatRequest.ClientSession 传到 适配器 meta.client_session。适配器的会号种子优先级变为： 客户端会话 id > 首条 user 消息指纹 > 按源固定。 刻意不采纳 x-client-request-id：名字含 request，部分客户端每请求都换， 拿它当会话会让上游前缀缓存永不命中（pi 总会同时发 x-session-affinity，够用）。 实测：抓 127.0.0.1:8081 的真实 pi 请求，配置打开后收到 x-session-affinity = session_id = x-client-request-id = <子会话 uuid>。 上游缓存确为会话级隔离（同前缀、不同会号：A 冷→命中，B 首次仍为 0）， 两个不同 header 值互不命中，反证网关确实采纳了客户端会话 id。 ## 2) 超窗消息必须「干净」，否则被同链的限流措辞反向封杀 pi 的 isContextOverflow 先查 NON_OVERFLOW_PATTERNS（/rate limit/、 /too many requests/、Bedrock 前缀），命中就直接判为「非超窗」——**即使 消息里已经有 context_length_exceeded**，pi 也不会压缩重试。 而 AUTO 链的失败消息天生是多 tier 原因的拼接，超窗 tier（gozen 400 maximum context length）常与配额/限流 tier（429 token plan exhausted、 cooling、no free slot）同时出现。此前把 tier 明细原样拼在归一化标记后面， 等于让一条限流 tier 的措辞反过来封杀超窗识别。 现在超窗走独立的干净消息： context_length_exceeded: context window is full; reduce the length of the messages (gozen/deepseek-v4.1-flash) 只留超窗措辞 + 超窗源名，不带任何其它 tier 的文本。 测试：TestOverflowMessageSurvivesRateLimitedSiblingTier 用 pi 的完整判定 顺序（先 NON_OVERFLOW 后 OVERFLOW）断言同链限流 tier 不再封杀超窗识别； TestClientSessionFromRequestHeaders / TestClientRequestIDIsNotUsedAsSession / TestOpenCodePrefersClientSessionID 覆盖会话采纳与优先级。
328 lines
15 KiB
Lua
328 lines
15 KiB
Lua
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
|
||
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
|