feat(openai): add WebSocket mode for Responses API

[taigrr]

Add WebSocket transport support for the OpenAI Responses API, enabling lower-latency persistent connections for tool-call-heavy workflows.

Key features:

• wsTransport manages WebSocket connection lifecycle with automatic reconnection before the 60-minute connection limit
• previous_response_id auto-chaining for incremental continuation
• generate:false warmup support via GenerateWarmup provider option
• Falls back to HTTP transparently on WebSocket connection failure
• One in-flight response at a time per connection (mutex-protected)

New provider options:

• WithWebSocket() enables WebSocket mode (requires WithUseResponsesAPI)
• PreviousResponseID on ResponsesProviderOptions for explicit chaining
• GenerateWarmup on ResponsesProviderOptions for prefill/warmup

The WebSocket events use the same JSON structure as HTTP SSE events, so both Generate() and Stream() reuse existing event parsing logic.

No changes to the LanguageModel interface or consumer-facing API.

• I have read CONTRIBUTING.md.
• I have created a discussion that was approved by a maintainer (for new features).

[andreynering]

Just giving this a try. Some tool calls are failing. It always says:

response error:  (code:  )