adapters: 支持多模态(对照 llmsproxy)

- ollama: content 数组拆分文本/images(base64),映射到 Ollama messages.images;
  流式透传 reasoning_content 与增量 tool_calls
- anthropic: OpenAI content(字符串/数组) 转 Anthropic blocks(文本 + image{source})
  + thinking/空 arguments tool_use/input_json_delta 流
- openai 透传 adapter 已保留多模态 content 数组(验收确认)
- 新增多模态单测:ollama images / anthropic image.source / openai passthrough

验证: go test ./... 27 包 0 失败;Windows 交叉编译通过;部署后服务健康
This commit is contained in:
root
2026-08-10 12:17:15 +08:00
parent f960fde785
commit 27183312ad
3 changed files with 157 additions and 7 deletions

View File

@ -11,13 +11,42 @@ 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)拆成文本/图片块
local function collect_blocks(content)
if type(content) == "string" then
return { { type = "text", text = content } }
end
local blocks = {}
for _, p in ipairs(content or {}) do
if p.type == "text" then
table.insert(blocks, { type = "text", 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(blocks, { type = "image", source = { type = "base64", media_type = mt or "image/png", data = b64 } })
else
table.insert(blocks, { type = "image", source = { type = "url", url = p.image_url.url } })
end
end
end
return blocks
end
local function text_of(content)
if type(content) == "string" then return content end
local t = ""
for _, p in ipairs(content or {}) do
if p.type == "text" and p.text then t = t .. p.text end
end
return t
end
local msgs = {}
local system = ""
for _, m in ipairs(req.messages or {}) do
if m.role == "system" then
system = system .. m.content .. "\n"
system = system .. text_of(m.content) .. "\n"
else
table.insert(msgs, { role = m.role, content = m.content })
table.insert(msgs, { role = m.role, content = collect_blocks(m.content) })
end
end
@ -74,12 +103,41 @@ function adapter.transform_stream_chunk(raw_chunk)
if chunk.type == "message_delta" then
return json.encode({ content = "", done = (chunk.delta and chunk.delta.stop_reason ~= nil) })
end
if chunk.type == "content_block_start" and chunk.content_block
and chunk.content_block.type == "tool_use" then
-- first fragment of a tool call: emit index + id + name, empty args
return json.encode({
content = "", done = false,
tool_calls = { {
index = chunk.index or 0,
id = chunk.content_block.id or "",
type = "function",
["function"] = { name = chunk.content_block.name or "", arguments = "" }
} }
})
end
if chunk.type == "content_block_delta" and chunk.delta then
if chunk.delta.type == "input_json_delta" then
-- incremental JSON fragment; clients accumulate across chunks
local unified = { content = "", done = false, tool_calls = { {
index = chunk.index or 0,
id = "",
type = "function",
["function"] = { name = "", arguments = chunk.delta.partial_json or "" }
} } }
return json.encode(unified)
end
if chunk.delta.type == "thinking_delta" and chunk.delta.thinking then
return json.encode({ content = "", done = false, reasoning_content = chunk.delta.thinking })
end
return json.encode({ content = chunk.delta.text or "", done = false })
end
if chunk.type == "message_stop" then
return json.encode({ content = "", done = true })
end
if chunk.type == "content_block_stop" then
return json.encode({ content = "", done = false })
end
return ""
end