Implement ollama e2e test case

[Patrisam]

增加了Ollama的e2e测试

---

Added Ollama’s e2e test

[codecov-commenter]

Codecov Report

:white_check_mark: All modified and coverable lines are covered by tests. :white_check_mark: Project coverage is 43.46%. Comparing base (810ef8f) to head (1734987).

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #3082      +/-   ##
==========================================
+ Coverage   43.42%   43.46%   +0.03%     
==========================================
  Files          82       82              
  Lines       10922    10922              
==========================================
+ Hits         4743     4747       +4     
+ Misses       5850     5848       -2     
+ Partials      329      327       -2     

see 2 files with indirect coverage changes

:rocket: New features to boost your workflow:

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

[Patrisam]

希望社区同学能够提供一些帮助？我很愿意解决这个问题。

---

I hope classmates in the community can provide some help? I'd love to resolve this issue.

[hanxiantao]

@Patrisam ollama的e2e测试已经修复了（具体改动点你可以看下，根据ai-proxy插件文档进行核对下），azure的e2e测试按照上面的流程也提交在这个pr中，执行通过后，我这边再进行review

有几个建议：

1）不要修改pr的描述的格式，请参考：https://github.com/alibaba/higress/pull/2815

2）先根据Higress官方文档本地搭建下Higress的环境，了解下Higress如何使用及相关概念

3）可以把这个e2e测试本地部署并执行一下，在部署完Higress后，需要部署mock-server（test/e2e/conformance/base/llm-mock.yaml）和e2e对应的case，示例如下：

apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: wasmplugin-ai-proxy-ollama
  namespace: higress-conformance-ai-backend
spec:
  ingressClassName: higress
  rules:
    - host: "ollama.e2e.host"
      http:
        paths:
          - pathType: Prefix
            path: "/"
            backend:
              service:
                name: llm-mock-service
                port:
                  number: 3000
---
apiVersion: extensions.higress.io/v1alpha1
kind: WasmPlugin
metadata:
  name: ai-proxy
  namespace: higress-system
spec:
  defaultConfigDisable: true
  phase: UNSPECIFIED_PHASE
  priority: 100
  matchRules:
    - config:
        provider:
          apiTokens:
            - fake_token
          modelMapping:
            "gpt-3": gemma3
            "*": gemma3
          type: ollama
          ollamaServerHost: llm-mock-service.higress-conformance-ai-backend.svc.cluster.local
          ollamaServerPort: 3000
      ingress:
        - higress-conformance-ai-backend/wasmplugin-ai-proxy-ollama
  # 本地和在线跑e2e测试的区别主要是在这里
  url: oci://higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/ai-proxy:1.0.0

这样可以本地更好的进行验证