ModelRouter/internal/lua/adapters/sensenova.lua

-- sensenova API format adapter
-- streaming: delta only has reasoning_content, no content field
-- non-streaming: has both content and reasoning_content

local adapter = {}
adapter.name = "sensenova"
adapter.version = "1.0.0"
adapter.endpoint = "/chat/completions"
adapter.headers = {}

-- Same as openai - strip provider-specific fields
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
        end
    end
    return json.encode(req)
end

-- Same as openai - extract content from response
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
            elseif ch.message.reasoning then
                -- sensenova-6.8-flash-lite 用 reasoning 字段而不是 reasoning_content
                unified.reasoning_content = ch.message.reasoning
            end
        end
        unified.finish_reason = ch.finish_reason or ""
    end

    return json.encode(unified)
end

-- Sensenova-specific stream handling
-- Upstream puts content in reasoning_content only (no content field)
-- Also sends finish_reason="" (empty string) on every chunk
function adapter.transform_stream_chunk(raw_chunk)
    local ok, chunk = pcall(json.decode, raw_chunk)
    if not ok then return "" end

    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 {}

    -- Sensenova: delta has reasoning_content (deepseek-v4-flash) or reasoning
    -- (sensenova-6.8-flash-lite) but no content field
    local content = delta.content or ""
    if content == "" and (delta.reasoning_content or delta.reasoning) then
        content = delta.reasoning_content or delta.reasoning
    end

    -- Sensenova: finish_reason is "" on every chunk, "stop" on last
    local fr = chunk.choices[1].finish_reason
    local done = (fr == "stop" or fr == "length")

    local unified = {
        content = content,
        done = done,
    }
    if chunk.choices[1].finish_reason and chunk.choices[1].finish_reason ~= "" then
        unified.finish_reason = chunk.choices[1].finish_reason
    end
    if delta.tool_calls then
        unified.tool_calls = delta.tool_calls
    end
    if uses ~= nil then
        unified.usage = uses
    end

    return json.encode(unified)
end

-- 错误收敛：sensenova 为 OpenAI 风格 {error:{message,...}}；
-- 配额类错误单独点出便于客户端识别重置周期。
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 status == 429 and type(e.code) == "string"
        and e.code == "insufficient_quota" then
        return "workspace quota exhausted (resets periodically)"
    end
    if type(e.message) == "string" then return e.message end
    return nil
end

return adapter