Files
devplacepy/devplacepy/services/openai_gateway/config.py
T
retoor 8a48e3ef85
DevPlace CI / test (push) Failing after 3h10m39s
Keep composers usable, group actions and notifications, and drop the tool-count cap
Comment and post layouts stay full width on small screens. Secondary actions live in the More menu. Notifications can be grouped and throttled, and Enter can submit when that profile setting is on. Emulated-tool models accept large catalogs, with reserved names aliased on the wire and the catalog cached per owner. A dropped service-worker navigation is retried once. The test server waits 120s to finish importing before it is stopped.
2026-11-12 15:29:27 +01:00

55 lines
1.6 KiB
Python

# retoor <retoor@molodetz.nl>
UPSTREAM_URL_DEFAULT = "https://api.deepseek.com/chat/completions"
MODEL_DEFAULT = "deepseek-v4-flash"
TIMEOUT_DEFAULT = 300
TIMEOUT_MIN = 300
INSTANCES_DEFAULT = 4
AUTH_THROTTLE_MAX_FAILURES_DEFAULT = 10
AUTH_THROTTLE_WINDOW_SECONDS_DEFAULT = 60
SYSTEM_PREAMBLE_DEFAULT = ""
THINKING_DEFAULT = False
VISION_URL_DEFAULT = "https://openrouter.ai/api/v1/chat/completions"
VISION_MODEL_DEFAULT = "google/gemma-4-31b-it"
VISION_CACHE_SIZE_DEFAULT = 256
EMBED_URL_DEFAULT = "https://openrouter.ai/api/v1/embeddings"
EMBED_MODEL_DEFAULT = "qwen/qwen3-embedding-8b"
IMAGE_URL_DEFAULT = "https://openrouter.ai/api/v1/images"
IMAGE_MODEL_DEFAULT = "black-forest-labs/flux.2-pro"
IMAGE_PRICE_PER_CALL_DEFAULT = 0.04
VISION_INSTRUCTION = (
"Describe this image in detail. Note objects, people, scene, any visible "
"text, layout, colors, and anything else that could be relevant for "
"answering questions about it. Be specific but concise."
)
PRICE_CACHE_HIT_PER_M_DEFAULT = 0.0028
PRICE_CACHE_MISS_PER_M_DEFAULT = 0.14
PRICE_OUTPUT_PER_M_DEFAULT = 0.28
VISION_PRICE_INPUT_PER_M_DEFAULT = 0.0
VISION_PRICE_OUTPUT_PER_M_DEFAULT = 0.0
EMBED_PRICE_INPUT_PER_M_DEFAULT = 0.01
RSEARCH_COST_PER_CALL_DEFAULT = 0.0
USAGE_RETENTION_HOURS_DEFAULT = 720
MAX_RETRIES_DEFAULT = 2
RETRY_BACKOFF_MS_DEFAULT = 250
CIRCUIT_THRESHOLD_DEFAULT = 5
CIRCUIT_COOLDOWN_SECONDS_DEFAULT = 30
MODEL_CONTEXT_MAP_DEFAULT = {
"deepseek-v4-flash": 1_048_576,
"deepseek-v4-pro": 1_048_576,
"deepseek-chat": 1_048_576,
"deepseek-reasoner": 1_048_576,
"google/gemma-3-12b-it": 8192,
"google/gemma-4-31b-it": 262144,
}