ModelRouter/internal/lua/adapters/deepseek.lua

local adapter = {}

adapter.name = "deepseek"
adapter.version = "2.1.0"
adapter.endpoint = "/chat/completions"
adapter.headers = {}

function adapter.transform_request(raw_body)
    local ok, req = pcall(json.decode, raw_body)
    if not ok then return raw_body end

    -- V4 已替换 legacy 模型名（deepseek-chat/reasoner 2026-07-24 停用）
    req.model = req.model or "deepseek-v4-flash"
    if req.model == "deepseek-chat" or req.model == "deepseek-reasoner" then
        req.model = "deepseek-v4-flash"
    end
    req.stream = req.stream or false
    -- 中立的 thinking 语义 → DeepSeek 自己的协议写法。
    -- 客户端说「关掉思考」时 thinking.enabled == false；上游的表达方式是
    -- extra_body.thinking.type = "disabled"。v2 之前这里读的是内核私有字段
    -- req.disable_thinking，而那个字段曾被内核泄漏进本函数收到的 body。
    if type(req.thinking) == "table" and req.thinking.enabled == false then
        req.extra_body = req.extra_body or {}
        req.extra_body.thinking = { type = "disabled" }
    elseif type(req.thinking) == "table" and req.thinking.budget_tokens ~= nil then
        req.extra_body = req.extra_body or {}
        req.extra_body.thinking = { type = "enabled", budget_tokens = req.thinking.budget_tokens }
    end
    req.thinking = nil

    -- V4 thinking 模式要求：带 tool_calls 的 assistant 消息必须回传 reasoning_content。
    -- OpenAI 兼容客户端不会发该字段，补空串即可通过校验。
    if req.messages then
        for _, msg in ipairs(req.messages) do
            if msg.role == "assistant" and msg.tool_calls and msg.tool_calls[1] then
                if msg.reasoning_content == nil then
                    msg.reasoning_content = ""
                end
            end
        end
    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
        unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens or 0
        unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
        if resp.usage.prompt_tokens_details and resp.usage.prompt_tokens_details.cached_tokens ~= nil then
            unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_tokens_details.cached_tokens }
        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 = 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). 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,
            prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens or 0,
            prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0,
        }
        if chunk.usage.prompt_tokens_details and chunk.usage.prompt_tokens_details.cached_tokens ~= nil then
            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_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
    if delta.reasoning_content then
        unified.reasoning_content = delta.reasoning_content
    end
    if delta.tool_calls then
        unified.tool_calls = delta.tool_calls
    end
    return json.encode(unified)
end

-- 错误收敛：DeepSeek 走标准 OpenAI 信封 {error:{message,...}}
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" and type(e.message) == "string" then
        return e.message
    end
    return nil
end

return adapter