mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-09-20 08:57:57 +00:00
The prior usage-passthrough fix only covered openai/opencode; the same empty-choices+usage drop bug remained in the 5 sibling OpenAI-compatible adapters, and non-OpenAI providers (anthropic/gemini/ollama) never surfaced streaming usage at all. - deepseek/github/groq/kimicode/mistral: preserve usage on empty-choices chunks and attach it to normal chunks (same pattern as openai.lua) - anthropic: emit usage from message_start (prompt) and message_delta (completion); gateway merges split usage additively - gemini: read usageMetadata in the stream path - ollama: fix non-streaming key (usage -> token_usage, matches UnifiedResponse json tag) and read prompt_eval_count/eval_count; surface counts from the done stream chunk - gateway: mergeUsage combines usage across chunks (non-zero fields win, total recomputed from prompt+completion) so split usage doesn't lose the prompt half; single-chunk case (OpenAI) preserved exactly - usage-only chunks: done=false (no redundant terminal stop), matching the Go fallback standardSSEChunk
144 lines
4.7 KiB
Lua
144 lines
4.7 KiB
Lua
local adapter = {}
|
||
|
||
adapter.name = "gemini"
|
||
adapter.version = "2.0.0"
|
||
adapter.endpoint = "/v1/models"
|
||
adapter.headers = {}
|
||
|
||
-- Gemini API: POST /v1/models/{model}:generateContent
|
||
-- Auth: API key in query param ?key=XXX or Authorization: Bearer XXX
|
||
function adapter.transform_request(raw_body)
|
||
local ok, req = pcall(json.decode, raw_body)
|
||
if not ok then return raw_body end
|
||
|
||
-- 将 OpenAI 风格 content(字符串或 [{type:*}] 数组)拆成 Gemini parts
|
||
local function to_parts(content)
|
||
if type(content) == "string" then
|
||
return { { text = content } }
|
||
end
|
||
local parts = {}
|
||
for _, p in ipairs(content or {}) do
|
||
if p.type == "text" then
|
||
table.insert(parts, { text = p.text })
|
||
elseif p.type == "image_url" and type(p.image_url) == "table" and p.image_url.url then
|
||
local mt, b64 = string.match(p.image_url.url, "^data:([^,]+);base64,(.+)$")
|
||
if b64 then
|
||
table.insert(parts, { inline_data = { mime_type = mt or "image/png", data = b64 } })
|
||
end
|
||
end
|
||
end
|
||
return parts
|
||
end
|
||
|
||
local contents = {}
|
||
for _, m in ipairs(req.messages or {}) do
|
||
table.insert(contents, {
|
||
role = (m.role == "assistant") and "model" or m.role,
|
||
parts = to_parts(m.content)
|
||
})
|
||
end
|
||
|
||
local gemini_req = {
|
||
contents = contents,
|
||
generationConfig = {
|
||
temperature = req.temperature or 0.7,
|
||
maxOutputTokens = req.max_tokens or 4096,
|
||
}
|
||
}
|
||
|
||
if req.stream then
|
||
gemini_req.stream = true
|
||
end
|
||
|
||
return json.encode(gemini_req)
|
||
end
|
||
|
||
-- Gemini 的 endpoint 动态拼接:/v1/models/{model}:generateContent
|
||
function adapter.transform_response(raw_body)
|
||
local ok, resp = pcall(json.decode, raw_body)
|
||
if not ok then return raw_body end
|
||
|
||
local unified = {
|
||
content = "",
|
||
finish_reason = "",
|
||
token_usage = { prompt = 0, completion = 0, total = 0 }
|
||
}
|
||
|
||
if resp.usageMetadata then
|
||
unified.token_usage.prompt = resp.usageMetadata.promptTokenCount or 0
|
||
unified.token_usage.completion = resp.usageMetadata.candidatesTokenCount or 0
|
||
unified.token_usage.total = resp.usageMetadata.totalTokenCount or 0
|
||
end
|
||
|
||
if resp.candidates and #resp.candidates > 0 then
|
||
local cand = resp.candidates[1]
|
||
if cand.content and cand.content.parts then
|
||
for _, part in ipairs(cand.content.parts) do
|
||
if part.text then
|
||
unified.content = unified.content .. part.text
|
||
end
|
||
end
|
||
end
|
||
if cand.finishReason then
|
||
unified.finish_reason = cand.finishReason
|
||
end
|
||
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
|
||
|
||
-- Gemini attaches usageMetadata to the final chunk (alongside or after
|
||
-- candidates). Keys map to Go's TokenUsage json tags (prompt/...).
|
||
local uses = nil
|
||
if type(chunk.usageMetadata) == "table" then
|
||
local p = chunk.usageMetadata.promptTokenCount or 0
|
||
local c = chunk.usageMetadata.candidatesTokenCount or 0
|
||
local t = chunk.usageMetadata.totalTokenCount or 0
|
||
if p > 0 or c > 0 or t > 0 then
|
||
uses = { prompt = p, completion = c, total = t }
|
||
end
|
||
end
|
||
|
||
if not chunk.candidates or #chunk.candidates == 0 then
|
||
if uses ~= nil then
|
||
return json.encode({ usage = uses, done = false })
|
||
end
|
||
return ""
|
||
end
|
||
local cand = chunk.candidates[1]
|
||
local unified = { content = "", done = (cand.finishReason ~= nil) }
|
||
local reasoning = ""
|
||
local tools = {}
|
||
if cand.content and cand.content.parts then
|
||
for _, part in ipairs(cand.content.parts) do
|
||
if part.text then
|
||
unified.content = (unified.content or "") .. part.text
|
||
elseif part.reasoning_content then
|
||
reasoning = reasoning .. part.reasoning_content
|
||
elseif part.functionCall then
|
||
table.insert(tools, {
|
||
index = #tools,
|
||
id = part.functionCall.id or ("call_" .. #tools),
|
||
type = "function",
|
||
["function"] = {
|
||
name = part.functionCall.name or "",
|
||
arguments = part.functionCall.args or "{}"
|
||
}
|
||
})
|
||
end
|
||
end
|
||
end
|
||
if reasoning ~= "" then unified.reasoning_content = reasoning end
|
||
if #tools > 0 then unified.tool_calls = tools end
|
||
if uses ~= nil then
|
||
unified.usage = uses
|
||
end
|
||
return json.encode(unified)
|
||
end
|
||
|
||
return adapter
|