amp-server/proxy_config.yaml at main · YougLin-dev/amp-server · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
endpoints:
  - path: "/api/provider/openai/v1/responses"
    target_url: "https://api.openai.com/v1/responses"
    method: "POST"
    response_type: "stream"
    custom_headers: {}
    forward_request_headers:
      - "authorization"
      - "content-type"
      - "user-agent"
      - "accept"
      - "accept-encoding"
    forward_response_headers:
      - "content-type"
      - "cache-control"
    enabled: true

  - path: "/api/provider/anthropic/v1/messages"
    target_url: "https://api.anthropic.com/v1/messages"
    method: "POST"
    response_type: "stream"
    custom_headers: {}
    forward_request_headers:
      - "authorization"
      - "content-type"
      - "user-agent"
      - "accept"
      - "accept-encoding"
      - "anthropic-version"
      - "x-api-key"
    forward_response_headers:
      - "content-type"
      - "cache-control"
    enabled: true

  - path: "/api/tab/llm-proxy"
    target_url: "https://ampcode.com/api/tab/llm-proxy"
    method: "POST"
    response_type: "sse"
    custom_headers: {}
    forward_request_headers:
      - "authorization"
      - "user-agent"
      - "x-amp-feature"
      - "accept-language"
      - "sec-fetch-mode"
    forward_response_headers:
      - "alt-svc"
      - "content-security-policy"
      - "fireworks-backend-host"
      - "fireworks-cached-prompt-tokens"
      - "fireworks-deployment"
      - "fireworks-generation-queue-duration"
      - "fireworks-num-concurrent-requests"
      - "fireworks-prefill-duration"
      - "fireworks-prefill-queue-duration"
      - "fireworks-prompt-tokens"
      - "fireworks-sampling-options"
      - "fireworks-server-time-to-first-token"
      - "fireworks-speculation-matched-tokens"
      - "fireworks-speculation-prompt-tokens"
      - "fireworks-tokenizer-duration"
      - "fireworks-tokenizer-queue-duration"
    enabled: true

  # Google Generative Language (gemini)
  # Matches: /api/provider/google/v1beta1/publishers/google/models/<model>:generateContent
  # For example: /api/provider/google/v1beta1/publishers/google/models/gemini-2.5-flash-lite-preview-09-2025:generateContent
  # Captures the remainder after /models/ as "rest"; the server derives {model} = rest.split(":").next()
  - path: "/api/provider/google/v1beta1/publishers/google/models/{*rest}"
    target_url: "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent"
    method: "POST"
    response_type: "stream"
    custom_headers: {}
    forward_request_headers:
      - "content-type"
      - "user-agent"
      - "accept"
      - "accept-encoding"
    forward_response_headers:
      - "content-type"
      - "cache-control"
    enabled: true