ModelRouter/internal/lua/adapters/github.lua

local adapter = {}

adapter.name = "github"
adapter.version = "2.0.0"
adapter.endpoint = "/chat/completions"
adapter.headers = {}

-- GitHub Models: Azure-like endpoint, auth via Bearer token (PAT)
-- BaseURL example: https://models.inference.ai.azure.com
function adapter.transform_request(raw_body)
    local ok, req = pcall(json.decode, raw_body)
    if not ok then return raw_body end
    req.model = req.model or "gpt-4o"
    req.temperature = req.temperature or 0.7
    req.max_tokens = req.max_tokens or 4096
    req.stream = req.stream or false
    -- The gateway's private control fields are GONE from the body (v2): the
    -- neutral `thinking` field carries that intent and each adapter maps it in
    -- its own protocol terms. These upstreams have no thinking switch at all,
    -- so the field is simply dropped here — which is what the nil-ing below
    -- used to do, except the field being dropped is no longer the kernel's
    -- private one.
    req.thinking = nil
    req.extra_body = nil
    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 ""
            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,
        }
        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
    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：GitHub Models 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