Streaming chunks still have different IDs when they should have the same ID in v0.6.87 #221
Description
This is the same issue as reported previously.
When using v0.6.87 (tested on both Windows 11 and macOS 15), chunk IDs are still incrementing. The only difference when using v0.6.87 is that the OpenAI C# SDK (v2.3.0) doesn't bother anymore and successfully streams the response, whereas the Go SDK (both 1.12 and 2.0.2) still fails processing the result after heaving read all chunks.
Sample response:
data: {"model":"qwen2.5-1.5b-instruct-generic-gpu","choices":[{"delta":{"role":"assistant","content":"\n","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"message":{"role":"assistant","content":"\n","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"index":0,"finish_reason":null,"finish_details":null,"logprobs":null}],"usage":null,"system_fingerprint":null,"service_tier":null,"created":1754980336,"CreatedAt":"2025-08-12T06:32:16+00:00","id":"chat.id.1","StreamEvent":null,"IsDelta":false,"Successful":true,"error":null,"HttpStatusCode":0,"HeaderValues":null,"object":"chat.completion.chunk"}
data: {"model":"qwen2.5-1.5b-instruct-generic-gpu","choices":[{"delta":{"role":"assistant","content":"Moon","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"message":{"role":"assistant","content":"Moon","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"index":1,"finish_reason":null,"finish_details":null,"logprobs":null}],"usage":null,"system_fingerprint":null,"service_tier":null,"created":1754980336,"CreatedAt":"2025-08-12T06:32:16+00:00","id":"chat.id.2","StreamEvent":null,"IsDelta":false,"Successful":true,"error":null,"HttpStatusCode":0,"HeaderValues":null,"object":"chat.completion.chunk"}
data: {"model":"qwen2.5-1.5b-instruct-generic-gpu","choices":[{"delta":{"role":"assistant","content":"light","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"message":{"role":"assistant","content":"light","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"index":2,"finish_reason":null,"finish_details":null,"logprobs":null}],"usage":null,"system_fingerprint":null,"service_tier":null,"created":1754980336,"CreatedAt":"2025-08-12T06:32:16+00:00","id":"chat.id.3","StreamEvent":null,"IsDelta":false,"Successful":true,"error":null,"HttpStatusCode":0,"HeaderValues":null,"object":"chat.completion.chunk"}
data: {"model":"qwen2.5-1.5b-instruct-generic-gpu","choices":[{"delta":{"role":"assistant","content":" bath","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"message":{"role":"assistant","content":" bath","name":null,"tool_call_id":null,"function_call":null,"tool_calls":[]},"index":3,"finish_reason":null,"finish_details":null,"logprobs":null}],"usage":null,"system_fingerprint":null,"service_tier":null,"created":1754980336,"CreatedAt":"2025-08-12T06:32:16+00:00","id":"chat.id.4","StreamEvent":null,"IsDelta":false,"Successful":true,"error":null,"HttpStatusCode":0,"HeaderValues":null,"object":"chat.completion.chunk"}