Chat Completions Openai Compatible

An existing OpenAI-SDK codebase is being pointed at DeepSeek. The integrator leaves base_url at the OpenAI default and only swaps the API key, expecting deepseek-chat to respond.

Set base_url to https://api.deepseek.com (the OpenAI SDK reuses the same client; only base_url and api_key change). Requests otherwise keep the OpenAI-compatible /chat/completions shape. Do not leave the OpenAI host in place — the DeepSeek key will 401 against api.openai.com.

A latency-sensitive autocomplete feature is wired to model=deepseek-reasoner for every keystroke 'because it is smarter'.

Route latency-sensitive, low-reasoning tasks to deepseek-chat; reserve deepseek-reasoner for tasks that benefit from chain-of-thought. deepseek-reasoner emits extra reasoning_content tokens and is slower/costlier per call — do not use it as the default for high-frequency lightweight requests.

deepseek-chat is called with stream=true. The client reads SSE chunks but ignores the terminating [DONE] sentinel and treats the first empty delta as end-of-stream.

Accumulate choices[].delta.content across chunks; treat the literal data: [DONE] line as the terminal marker (OpenAI-compatible SSE). Do not end on the first empty/role-only delta — the first chunk often carries role with empty content.