[Misc] Fix client.py in case workload has model null and client has default_model

[ronaldosaheki]

Pull Request Description

Currently when workload file constant.jsonl has model:null, even if we set default_model in client.py, it will be then use Model:None/null and ignore the default_model and throw the error:

ERROR:root:Request 2: Error (BadRequestError): Error code: 400 - {'object': 'error', 'message': "[{'type': 'string_type', 'loc': ('body', 'model'), 'msg': 'Input should be a valid string', 'input': None}]", 'type': 'BadRequestError', 'param': None, 'code': 400}

With the fix, the client default_model is used in case workload file has model: null

{"timestamp": 5000, "requests": [{"prompt": "Certainly, here is the
continuation of the agreement:\n\nTHIS AGREEMENT constitutes the entire
agreement between the parties and supersedes all prior negotiations,
...
Authorized Signature]\n[Insert Authorized Printed Name]\n[Insert
Date]\n\n[Insert Client Name]\n\n---\n\n[Insert Authorized
Signature]\n[Insert Authorized Printed Name]\n[Insert Date]", "model":
null, "prompt_length": 477, "output_length": 7}]}

Running successfully:

export API_KEY=${API_KEY}
python3 client.py \
--workload-path "../generator/output/constant.jsonl" \
--endpoint "http://localhost:8000" \
--model deepseek-llm-7b-chat \
--api-key ${API_KEY} \
--streaming \
--output-file-path output.jsonl 
...<snippet>
INFO:root:Request 296: Starting streaming request to http://localhost:8000
INFO:root:Request 82: Completed successfully. Tokens: 2527, Latency: 214.43s
INFO:httpx:HTTP Request: POST http://localhost:8000/v1/chat/completions "HTTP/1.1 200 OK"
WARNING:root:Prepare to launch 1 streaming tasks after 0.9986288547515869
INFO:root:Request 297: Starting streaming request to http://localhost:8000
INFO:root:Request 124: Completed successfully. Tokens: 457, Latency: 173.07s
INFO:httpx:HTTP Request: POST http://localhost:8000/v1/chat/completions "HTTP/1.1 200 OK"
WARNING:root:Prepare to launch 1 streaming tasks after 0.9988501071929932
INFO:root:Request 298: Starting streaming request to http://localhost:8000
INFO:httpx:HTTP Request: POST http://localhost:8000/v1/chat/completions "HTTP/1.1 200 OK"
...</snippet>

Additional lint/changes:

• syntax fixes by editor removing empty spaces
• api-key should not be required, as we can deploy vllm without api-key

Important: Before submitting, please complete the description above and review the checklist below.

---

Contribution Guidelines (Expand for Details)

We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:

Pull Request Title Format

Your PR title should start with one of these prefixes to indicate the nature of the change:

• [Bug]: Corrections to existing functionality
• [CI]: Changes to build process or CI pipeline
• [Docs]: Updates or additions to documentation
• [API]: Modifications to aibrix's API or interface
• [CLI]: Changes or additions to the Command Line Interface
• [Misc]: For changes not covered above (use sparingly)

Note: For changes spanning multiple categories, use multiple prefixes in order of importance.

Submission Checklist

• PR title includes appropriate prefix(es)
• Changes are clearly explained in the PR description
• New and existing tests pass successfully
• Code adheres to project style and best practices
• Documentation updated to reflect changes (if applicable)
• Thorough testing completed, no regressions introduced

By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.

[happyandslow]

LGTM