feat: no login experience and prem tokens

surfsense_backend/app/config/__init__.py

@@ -42,7 +42,25 @@ def load_global_llm_configs():
     try:
         with open(global_config_file, encoding="utf-8") as f:
             data = yaml.safe_load(f)
-            return data.get("global_llm_configs", [])
+            configs = data.get("global_llm_configs", [])
+
+        seen_slugs: dict[str, int] = {}
+        for cfg in configs:
+            cfg.setdefault("billing_tier", "free")
+            cfg.setdefault("anonymous_enabled", False)
+            cfg.setdefault("seo_enabled", False)
+
+            if cfg.get("seo_enabled") and cfg.get("seo_slug"):
+                slug = cfg["seo_slug"]
+                if slug in seen_slugs:
+                    print(
+                        f"Warning: Duplicate seo_slug '{slug}' in global LLM configs "
+                        f"(ids {seen_slugs[slug]} and {cfg.get('id')})"
+                    )
+                else:
+                    seen_slugs[slug] = cfg.get("id", 0)
+
+        return configs
     except Exception as e:
         print(f"Warning: Failed to load global LLM configs: {e}")
         return []
@@ -307,6 +325,36 @@ class Config:
         os.getenv("STRIPE_RECONCILIATION_BATCH_SIZE", "100")
     )
 
+    # Premium token quota settings
+    PREMIUM_TOKEN_LIMIT = int(os.getenv("PREMIUM_TOKEN_LIMIT", "5000000"))
+    STRIPE_PREMIUM_TOKEN_PRICE_ID = os.getenv("STRIPE_PREMIUM_TOKEN_PRICE_ID")
+    STRIPE_TOKENS_PER_UNIT = int(os.getenv("STRIPE_TOKENS_PER_UNIT", "1000000"))
+    STRIPE_TOKEN_BUYING_ENABLED = (
+        os.getenv("STRIPE_TOKEN_BUYING_ENABLED", "FALSE").upper() == "TRUE"
+    )
+
+    # Anonymous / no-login mode settings
+    NOLOGIN_MODE_ENABLED = os.getenv("NOLOGIN_MODE_ENABLED", "FALSE").upper() == "TRUE"
+    ANON_TOKEN_LIMIT = int(os.getenv("ANON_TOKEN_LIMIT", "1000000"))
+    ANON_TOKEN_WARNING_THRESHOLD = int(
+        os.getenv("ANON_TOKEN_WARNING_THRESHOLD", "800000")
+    )
+    ANON_TOKEN_QUOTA_TTL_DAYS = int(os.getenv("ANON_TOKEN_QUOTA_TTL_DAYS", "30"))
+    ANON_MAX_UPLOAD_SIZE_MB = int(os.getenv("ANON_MAX_UPLOAD_SIZE_MB", "5"))
+
+    # Default quota reserve tokens when not specified per-model
+    QUOTA_MAX_RESERVE_PER_CALL = int(os.getenv("QUOTA_MAX_RESERVE_PER_CALL", "8000"))
+
+    # Abuse prevention: concurrent stream cap and CAPTCHA
+    ANON_MAX_CONCURRENT_STREAMS = int(os.getenv("ANON_MAX_CONCURRENT_STREAMS", "2"))
+    ANON_CAPTCHA_REQUEST_THRESHOLD = int(
+        os.getenv("ANON_CAPTCHA_REQUEST_THRESHOLD", "5")
+    )
+
+    # Cloudflare Turnstile CAPTCHA
+    TURNSTILE_ENABLED = os.getenv("TURNSTILE_ENABLED", "FALSE").upper() == "TRUE"
+    TURNSTILE_SECRET_KEY = os.getenv("TURNSTILE_SECRET_KEY", "")
+
     # Auth
     AUTH_TYPE = os.getenv("AUTH_TYPE")
     REGISTRATION_ENABLED = os.getenv("REGISTRATION_ENABLED", "TRUE").upper() == "TRUE"

surfsense_backend/app/config/global_llm_config.example.yaml

@@ -48,6 +48,11 @@ global_llm_configs:
   - id: -1
     name: "Global GPT-4 Turbo"
     description: "OpenAI's GPT-4 Turbo with default prompts and citations"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "gpt-4-turbo"
+    quota_reserve_tokens: 4000
     provider: "OPENAI"
     model_name: "gpt-4-turbo-preview"
     api_key: "sk-your-openai-api-key-here"
@@ -67,6 +72,11 @@ global_llm_configs:
   - id: -2
     name: "Global Claude 3 Opus"
     description: "Anthropic's most capable model with citations"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "claude-3-opus"
+    quota_reserve_tokens: 4000
     provider: "ANTHROPIC"
     model_name: "claude-3-opus-20240229"
     api_key: "sk-ant-your-anthropic-api-key-here"
@@ -84,6 +94,11 @@ global_llm_configs:
   - id: -3
     name: "Global GPT-3.5 Turbo (Fast)"
     description: "Fast responses without citations for quick queries"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "gpt-3.5-turbo-fast"
+    quota_reserve_tokens: 2000
     provider: "OPENAI"
     model_name: "gpt-3.5-turbo"
     api_key: "sk-your-openai-api-key-here"
@@ -101,6 +116,11 @@ global_llm_configs:
   - id: -4
     name: "Global DeepSeek Chat (Chinese)"
     description: "DeepSeek optimized for Chinese language responses"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "deepseek-chat-chinese"
+    quota_reserve_tokens: 4000
     provider: "DEEPSEEK"
     model_name: "deepseek-chat"
     api_key: "your-deepseek-api-key-here"
@@ -128,6 +148,11 @@ global_llm_configs:
   - id: -5
     name: "Global Azure GPT-4o"
     description: "Azure OpenAI GPT-4o deployment"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "azure-gpt-4o"
+    quota_reserve_tokens: 4000
     provider: "AZURE"
     # model_name format for Azure: azure/<your-deployment-name>
     model_name: "azure/gpt-4o-deployment"
@@ -151,6 +176,11 @@ global_llm_configs:
   - id: -6
     name: "Global Azure GPT-4 Turbo"
     description: "Azure OpenAI GPT-4 Turbo deployment"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "azure-gpt-4-turbo"
+    quota_reserve_tokens: 4000
     provider: "AZURE"
     model_name: "azure/gpt-4-turbo-deployment"
     api_key: "your-azure-api-key-here"
@@ -170,6 +200,11 @@ global_llm_configs:
   - id: -7
     name: "Global Groq Llama 3"
     description: "Ultra-fast Llama 3 70B via Groq"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "groq-llama-3"
+    quota_reserve_tokens: 8000
     provider: "GROQ"
     model_name: "llama3-70b-8192"
     api_key: "your-groq-api-key-here"
@@ -187,6 +222,11 @@ global_llm_configs:
   - id: -8
     name: "Global MiniMax M2.5"
     description: "MiniMax M2.5 with 204K context window and competitive pricing"
+    billing_tier: "free"
+    anonymous_enabled: true
+    seo_enabled: true
+    seo_slug: "minimax-m2.5"
+    quota_reserve_tokens: 4000
     provider: "MINIMAX"
     model_name: "MiniMax-M2.5"
     api_key: "your-minimax-api-key-here"
@@ -365,3 +405,13 @@ global_vision_llm_configs:
 # - Only use vision-capable models (GPT-4o, Gemini, Claude 3, etc.)
 # - Lower temperature (0.3) is recommended for accurate screenshot analysis
 # - Lower max_tokens (1000) is sufficient since autocomplete produces short suggestions
+#
+# TOKEN QUOTA & ANONYMOUS ACCESS NOTES:
+# - billing_tier: "free" or "premium". Controls whether registered users need premium token quota.
+# - anonymous_enabled: true/false. Whether the model appears in the public no-login catalog.
+# - seo_enabled: true/false. Whether a /free/<seo_slug> landing page is generated.
+# - seo_slug: Stable URL slug for SEO pages. Must be unique. Do NOT change once public.
+# - seo_title: Optional HTML title tag override for the model's /free/<slug> page.
+# - seo_description: Optional meta description override for the model's /free/<slug> page.
+# - quota_reserve_tokens: Tokens reserved before each LLM call for quota enforcement.
+#   Independent of litellm_params.max_tokens. Used by the token quota service.