feat(ai-proxy): support OpenAI-compatible image and audio model Mapping

[daixijun]

Ⅰ. Describe what this PR did

增加 Openai 兼容 Provider 对图片生成、图片编辑、音频处理等接口对模型 Mapping 的能力

Ⅱ. Does this pull request fix one issue?

fixes #2338

Ⅲ. Why don't you add test cases (unit test/integration test)?

Ⅳ. Describe how to verify it

envoy.yaml 内容

# File generated by hgctl. Modify as required.

admin:
  address:
    socket_address:
      protocol: TCP
      address: 0.0.0.0
      port_value: 9901
static_resources:
  listeners:
    - name: listener_0
      address:
        socket_address:
          protocol: TCP
          address: 0.0.0.0
          port_value: 10000
      filter_chains:
        - filters:
            - name: envoy.filters.network.http_connection_manager
              typed_config:
                "@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
                scheme_header_transformation:
                  scheme_to_overwrite: https
                stat_prefix: ingress_http
                # Output envoy logs to stdout
                access_log:
                  - name: envoy.access_loggers.stdout
                    typed_config:
                      "@type": type.googleapis.com/envoy.extensions.access_loggers.stream.v3.StdoutAccessLog
                # Modify as required
                route_config:
                  name: local_route
                  virtual_hosts:
                    - name: local_service
                      domains: ["*"]
                      routes:
                        - match:
                            prefix: "/"
                          route:
                            cluster: google
                            timeout: 300s
                http_filters:
                  - name: wasmtest
                    typed_config:
                      "@type": type.googleapis.com/udpa.type.v1.TypedStruct
                      type_url: type.googleapis.com/envoy.extensions.filters.http.wasm.v3.Wasm
                      value:
                        config:
                          name: wasmtest
                          vm_config:
                            runtime: envoy.wasm.runtime.v8
                            code:
                              local:
                                filename: /etc/envoy/plugin.wasm
                          configuration:
                            "@type": "type.googleapis.com/google.protobuf.StringValue"
                            value: |
                              {
                                "provider": {
                                    "type": "openai",
                                    "openaiCustomUrl": "generativelanguage.googleapis.com/v1beta/openai/",
                                    "modelMapping": {
                                      "gpt-image-1": "imagen-3.0-generate-002"
                                    },
                                    "apiTokens": [
                                        "{YOUR-API-KEY}"
                                    ]
                                }
                              }
                  - name: envoy.filters.http.router
                    typed_config:
                      "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
  clusters:
    - name: google
      connect_timeout: 30s
      type: LOGICAL_DNS
      dns_lookup_family: V4_ONLY
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: google
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: generativelanguage.googleapis.com
                      port_value: 443
      transport_socket:
        name: envoy.transport_sockets.tls
        typed_config:
          "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
          "sni": "generativelanguage.googleapis.com"

docker-compose.yaml 文件内容如下

services:
  envoy:
    image: higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/gateway:v2.1.3
    entrypoint: /usr/local/bin/envoy
    command: -c /etc/envoy/envoy.yaml --component-log-level wasm:debug
    networks:
      - wasmtest
    ports:
      - '10000:10000'
    volumes:
      - ./envoy.yaml:/etc/envoy/envoy.yaml
      - ./plugin.wasm:/etc/envoy/plugin.wasm

networks:
  wasmtest: {}

使用 openai 的 gpt-image-1 模型请求 gemini ，验证请求是否会被正确 mapping 到 imagen-3.0-generate-002 模型

curl -v "http://localhost:10000/v1/images/generations" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "gpt-image-1",
        "prompt": "a portrait of a sheepadoodle wearing a cape",
        "response_format": "b64_json",
        "n": 1, 
        "size": "1024x1024"      
      }' | jq -r '.data[0].b64_json' | base64 --decode > gemini-image.jpeg

wasm 日志如下

生成的效果图

Ⅴ. Special notes for reviews

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 46.01%. Comparing base (ef31e09) to head (0292650).
Report is 529 commits behind head on main.

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #2341       +/-   ##
===========================================
+ Coverage   35.91%   46.01%   +10.10%     
===========================================
  Files          69       81       +12     
  Lines       11576    13010     +1434     
===========================================
+ Hits         4157     5986     +1829     
+ Misses       7104     6678      -426     
- Partials      315      346       +31     

see 78 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[CH3CHO]

LGTM