-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathconfig.yaml
More file actions
83 lines (79 loc) · 1.71 KB
/
Copy pathconfig.yaml
File metadata and controls
83 lines (79 loc) · 1.71 KB
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
environment: development
log_level: INFO
llm:
providers:
- name: nvidia_nim
type: nvidia_nim
api_base: "https://integrate.api.nvidia.com/v1"
api_key_env: "NVIDIA_NIM_API_KEY"
models:
- "nvidia/nemotron-3-ultra"
priority: 1
- name: openai
type: openai
api_base: "https://api.openai.com/v1"
api_key_env: "OPENAI_API_KEY"
models:
- "gpt-4o"
priority: 2
- name: azure_openai
type: azure_openai
api_base: ""
api_key_env: "AZURE_OPENAI_API_KEY"
endpoint_env: "AZURE_OPENAI_ENDPOINT"
models:
- "gpt-4o"
priority: 3
- name: ollama
type: ollama
api_base: "http://localhost:11434/v1"
api_key_env: ""
models:
- "llama3.1:8b"
- "codellama:7b"
priority: 4
- name: llama_cpp
type: llama_cpp
api_base: "http://localhost:8080/v1"
api_key_env: ""
models:
- "llama-3.1-8b-instruct"
priority: 5
fallback_chain:
- "nvidia_nim"
- "openai"
- "azure_openai"
- "ollama"
- "llama_cpp"
defaults:
temperature: 0.3
max_tokens: 4000
timeout_seconds: 60
agents:
planner:
temperature: 0.2
max_tokens: 2000
timeout_seconds: 30
coder:
temperature: 0.3
max_tokens: 4000
timeout_seconds: 60
reviewer:
temperature: 0.1
max_tokens: 3000
timeout_seconds: 30
quality_threshold: 70
tester:
temperature: 0.2
max_tokens: 3000
timeout_seconds: 60
coverage_threshold: 80
sandbox:
cpu_timeout_seconds: 10
memory_limit_mb: 512
production_mode: false
orchestrator:
halt_on_review_failure: true
max_retries: 2
retry_backoff_base: 2.0
timeout_seconds: 120