mirror of
https://github.com/browser-use/browser-use.git
synced 2026-10-02 04:04:36 +08:00
XiaoHuo888andClaude
d8580caf01
Registers ChatOrcaRouter (provider='orcarouter'), an OpenAI-compatible BaseChatModel mirroring the existing ChatOpenRouter wiring, so the model gateway is usable as a first-class provider: - browser_use/llm/orcarouter/chat.py + serializer.py - Registered in browser_use/llm/__init__.py and browser_use/__init__.py - Token-cost guard: never attribute upstream prices to the gateway - .env.example ORCAROUTER_API_KEY entry - tests/ci/test_orcarouter.py and examples/models/orcarouter.py Co-Authored-By: Claude <noreply@anthropic.com>
Codebase Structure
The code structure inspired by https://github.com/Netflix/dispatch.
Very good structure on how to make a scalable codebase is also in this repo.
Just a brief document about how we should structure our backend codebase.
Code Structure
src/
/<service name>/
models.py
services.py
prompts.py
views.py
utils.py
routers.py
/_<subservice name>/
Service.py
Always a single file, except if it becomes too long - more than ~500 lines, split it into _subservices
Views.py
Always split the views into two parts
# All
...
# Requests
...
# Responses
...
If too long → split into multiple files
Prompts.py
Single file; if too long → split into multiple files (one prompt per file or so)
Routers.py
Never split into more than one file