fix: zen adapter strips multimodal parts (upstream is text-only)

internal/lua/adapters/opencode.lua

@@ -13,15 +13,39 @@ adapter.headers = {
 }
 
 -- OpenAI /chat/completions format (pass-through, strip provider-specific fields)
+-- zen 上游 schema 只接受 text content part（无视觉/音频能力）：多模态 part
+-- （image_url / input_audio / file 等）一律剥离；因此失去全部 content 的
+-- 消息整条丢弃，避免上游 "unknown variant `image_url`, expected `text`"。
 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
+        local kept = {}
         for _, msg in ipairs(req.messages) do
             msg.reasoning_content = nil
+            local drop = false
+            if type(msg.content) == "table" then
+                local parts = {}
+                for _, part in ipairs(msg.content) do
+                    if type(part) == "table" and part.type ~= nil and part.type ~= "text" then
+                        -- multimodal part not supported by zen
+                    else
+                        table.insert(parts, part)
+                    end
+                end
+                if #parts == 0 then
+                    drop = true
+                else
+                    msg.content = parts
+                end
+            end
+            if not drop then
+                table.insert(kept, msg)
+            end
         end
+        req.messages = kept
     end
     return json.encode(req)
 end