apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 17:26:23 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(story-3.5): add cloud-mode LLM model selection with token quota enforcement

Browse source 
Implement system-managed model catalog, subscription tier enforcement,
atomic token quota tracking, and frontend cloud/self-hosted conditional
rendering. Apply all 20 BMAD code review patches including security
fixes (cross-user API key hijack), race condition mitigation (atomic SQL
UPDATE), and SSE mid-stream quota error handling.

Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
This commit is contained in:
Vonic 2026-04-14 17:01:21 +07:00
parent e7382b26de
commit c1776b3ec8
19 changed files with 1003 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

28
surfsense_backend/app/config/global_llm_config.example.yaml
View file

@ -52,6 +52,9 @@ global_llm_configs:
model_name: "gpt-4-turbo-preview"
api_key: "sk-your-openai-api-key-here"
api_base: ""
tier_required: "pro" # free | pro | enterprise
cost_per_1k_input_tokens: 0.01
cost_per_1k_output_tokens: 0.03
# Rate limits for load balancing (requests/tokens per minute)
rpm: 500 # Requests per minute
tpm: 100000 # Tokens per minute
@ -71,6 +74,9 @@ global_llm_configs:
model_name: "claude-3-opus-20240229"
api_key: "sk-ant-your-anthropic-api-key-here"
api_base: ""
tier_required: "pro"
cost_per_1k_input_tokens: 0.015
cost_per_1k_output_tokens: 0.075
rpm: 1000
tpm: 100000
litellm_params:
@ -88,6 +94,9 @@ global_llm_configs:
model_name: "gpt-3.5-turbo"
api_key: "sk-your-openai-api-key-here"
api_base: ""
tier_required: "free"
cost_per_1k_input_tokens: 0.0005
cost_per_1k_output_tokens: 0.0015
rpm: 3500 # GPT-3.5 has higher rate limits
tpm: 200000
litellm_params:
@ -105,6 +114,9 @@ global_llm_configs:
model_name: "deepseek-chat"
api_key: "your-deepseek-api-key-here"
api_base: "https://api.deepseek.com/v1"
tier_required: "free"
cost_per_1k_input_tokens: 0.0001
cost_per_1k_output_tokens: 0.0002
rpm: 60
tpm: 100000
litellm_params:
@ -134,6 +146,9 @@ global_llm_configs:
api_key: "your-azure-api-key-here"
api_base: "https://your-resource.openai.azure.com"
api_version: "2024-02-15-preview" # Azure API version
tier_required: "pro"
cost_per_1k_input_tokens: 0.005
cost_per_1k_output_tokens: 0.015
rpm: 1000
tpm: 150000
litellm_params:
@ -156,6 +171,9 @@ global_llm_configs:
api_key: "your-azure-api-key-here"
api_base: "https://your-resource.openai.azure.com"
api_version: "2024-02-15-preview"
tier_required: "pro"
cost_per_1k_input_tokens: 0.01
cost_per_1k_output_tokens: 0.03
rpm: 500
tpm: 100000
litellm_params:
@ -174,6 +192,9 @@ global_llm_configs:
model_name: "llama3-70b-8192"
api_key: "your-groq-api-key-here"
api_base: ""
tier_required: "pro"
cost_per_1k_input_tokens: 0.00059
cost_per_1k_output_tokens: 0.00079
rpm: 30 # Groq has lower rate limits on free tier
tpm: 14400
litellm_params:
@ -191,6 +212,9 @@ global_llm_configs:
model_name: "MiniMax-M2.5"
api_key: "your-minimax-api-key-here"
api_base: "https://api.minimax.io/v1"
tier_required: "free"
cost_per_1k_input_tokens: 0.001
cost_per_1k_output_tokens: 0.003
rpm: 60
tpm: 100000
litellm_params:
@ -347,6 +371,10 @@ global_vision_llm_configs:
# - system_instructions: Custom prompt or empty string to use defaults
# - use_default_system_instructions: true = use SURFSENSE_SYSTEM_INSTRUCTIONS when system_instructions is empty
# - citations_enabled: true = include citation instructions, false = include anti-citation instructions
# - tier_required: "free" | "pro" | "enterprise" — subscription tier needed to use this model.
# If omitted, tier is inferred from model_name via pattern matching (fragile).
# - cost_per_1k_input_tokens / cost_per_1k_output_tokens: Optional cost metadata for display.
# Not used for billing (token quota is flat), but shown in the UI for transparency.
# - All standard LiteLLM providers are supported
# - rpm/tpm: Optional rate limits for load balancing (requests/tokens per minute)
# These help the router distribute load evenly and avoid rate limit errors