|
|
| from __future__ import annotations
|
|
|
| import os
|
|
|
| from .tool_schemas import TOOL_SCHEMAS
|
| from .tool_schemas import think as THINK_SCHEMA
|
|
|
| MODEL_ID = os.environ.get(
|
| "BORDERLESS_MODEL_ID", "Qwen/Qwen3.6-27B:featherless-ai"
|
| )
|
| INFERENCE_MODE = os.environ.get("BORDERLESS_INFERENCE_MODE", "hub").strip().lower()
|
| ENABLE_THINKING = os.environ.get("BORDERLESS_ENABLE_THINKING", "1").strip().lower() in {
|
| "1",
|
| "true",
|
| "yes",
|
| }
|
| GPU_DURATION = max(
|
| 30,
|
| min(
|
| 300,
|
| int(os.environ.get("BORDERLESS_GPU_DURATION", "60")),
|
| ),
|
| )
|
| MAX_TOOL_ROUNDS = int(os.environ.get("BORDERLESS_MAX_TOOL_ROUNDS", "7"))
|
|
|
| TOOLS = TOOL_SCHEMAS
|
| THINK_TOOLS = [THINK_SCHEMA]
|
|
|
|
|
| def local_inference_enabled() -> bool:
|
| return INFERENCE_MODE == "local"
|
|
|
|
|
| def hub_token_available() -> bool:
|
| return bool(os.environ.get("HF_TOKEN", "").strip())
|
|
|
