diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md index 2d4b9655c5..36f9bbc40a 100644 --- a/docs/my-website/docs/proxy/config_settings.md +++ b/docs/my-website/docs/proxy/config_settings.md @@ -383,6 +383,8 @@ router_settings: | CIRCLE_OIDC_TOKEN_V2 | Version 2 of the OpenID Connect token for CircleCI | CLOUDZERO_API_KEY | CloudZero API key for authentication | CLOUDZERO_CONNECTION_ID | CloudZero connection ID for data submission +| CLOUDZERO_EXPORT_INTERVAL_MINUTES | Interval in minutes for CloudZero data export operations +| CLOUDZERO_MAX_FETCHED_DATA_RECORDS | Maximum number of data records to fetch from CloudZero | CLOUDZERO_TIMEZONE | Timezone for date handling (default: UTC) | CONFIG_FILE_PATH | File path for configuration file | CONFIDENT_API_KEY | API key for DeepEval integration @@ -415,6 +417,7 @@ router_settings: | DEFAULT_ALLOWED_FAILS | Maximum failures allowed before cooling down a model. Default is 3 | DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS | Default maximum tokens for Anthropic chat completions. Default is 4096 | DEFAULT_BATCH_SIZE | Default batch size for operations. Default is 512 +| DEFAULT_CLIENT_DISCONNECT_CHECK_TIMEOUT_SECONDS | Timeout in seconds for checking client disconnection. Default is 1 | DEFAULT_COOLDOWN_TIME_SECONDS | Duration in seconds to cooldown a model after failures. Default is 5 | DEFAULT_CRON_JOB_LOCK_TTL_SECONDS | Time-to-live for cron job locks in seconds. Default is 60 (1 minute) | DEFAULT_FAILURE_THRESHOLD_PERCENT | Threshold percentage of failures to cool down a deployment. Default is 0.5 (50%) @@ -441,6 +444,10 @@ router_settings: | DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET | Default high reasoning effort thinking budget. Default is 4096 | DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET | Default low reasoning effort thinking budget. Default is 1024 | DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET | Default medium reasoning effort thinking budget. Default is 2048 +| DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET | Default minimal reasoning effort thinking budget. Default is 512 +| DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH | Default minimal reasoning effort thinking budget for Gemini 2.5 Flash. Default is 512 +| DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH_LITE | Default minimal reasoning effort thinking budget for Gemini 2.5 Flash Lite. Default is 512 +| DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_PRO | Default minimal reasoning effort thinking budget for Gemini 2.5 Pro. Default is 512 | DEFAULT_REDIS_SYNC_INTERVAL | Default Redis synchronization interval in seconds. Default is 1 | DEFAULT_REPLICATE_GPU_PRICE_PER_SECOND | Default price per second for Replicate GPU. Default is 0.001400 | DEFAULT_REPLICATE_POLLING_DELAY_SECONDS | Default delay in seconds for Replicate polling. Default is 1