fix(dependency): Add missing orjson dependency for ORJSONResponse

[IAMDAVID0920]

📋 PR Title Format

The PR title should follow the format:

type(scope): concise message (max 50 chars)

Where:

• type is one of: feat, fix, docs, refactor, perf, test, chore.
• scope is optional and describes the part of the codebase affected (e.g., auth, ui, api).
• concise message is a short description of the change (max 50 chars).

📝 Change Type

Please select the type of change this PR introduces (choose one or more):

• feat: New feature.
• fix: Bug fix.
• docs: Documentation only changes.
• refactor: A code change that neither fixes a bug nor adds a feature.
• perf: Performance improvement.
• test: Adding missing tests or correcting existing tests.
• chore: Maintenance tasks (e.g., updating dependencies).

💡 Description

The code uses ORJSONResponse from FastAPI which requires the orjson package, but it is not listed in dependencies. This causes AssertionError: orjson must be installed to use ORJSONResponse when making non-streaming requests stream: false

Reproducible from local M1 Mac when i try to follow the example, here are my reproducible steps

> Terminal 1
parallax run -m Qwen/Qwen3-0.6B -n 2
> Terminal 2
parallax join --port 3000
> Terminal 3
parallax join --port 3003
> Terminal 4
curl http://localhost:3001/v1/chat/completions \                                                                                           ─╯
-H "Content-Type: application/json" \
-d '{"messages": [{"role":"user", "content":"Hello!"}], "stream": false}'

Nov 07 22:32:43.934 [ERROR   ] http_server.py:409        Error processing non-streaming request 6875ece1-6c66-4d8e-8807-83f1b1b94b32: orjson must be installed to use ORJSONResponse
INFO:     ::1:55944 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error
Nov 07 22:32:43.937 [ERROR   ] server.py:183             Error in chat completion: Expecting value: line 1 column 1 (char 0)
Traceback (most recent call last):
  File "/Users/dingyunguo/work/parallax/src/parallax/p2p/server.py", line 180, in chat_completion
    ).json()
      ^^^^^^
  File "/Users/dingyunguo/work/parallax/venv/lib/python3.12/site-packages/httpx/_models.py", line 832, in json
    return jsonlib.loads(self.content, **kwargs)                                                                                                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/python@3.12/3.12.4/Frameworks/Python.framework/Versions/3.12/lib/python3.12/json/__init__.py", line 346, in loads       return _default_decoder.decode(s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^                                                                                                              File "/opt/homebrew/Cellar/python@3.12/3.12.4/Frameworks/Python.framework/Versions/3.12/lib/python3.12/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())                                                                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/python@3.12/3.12.4/Frameworks/Python.framework/Versions/3.12/lib/python3.12/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/Users/dingyunguo/work/parallax/src/parallax/server/http_server.py", line 406, in v1_chat_completions
    return ORJSONResponse(status_code=200, content=response)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/dingyunguo/work/parallax/venv/lib/python3.12/site-packages/starlette/responses.py", line 189, in __init__
    super().__init__(content, status_code, headers, media_type, background)
  File "/Users/dingyunguo/work/parallax/venv/lib/python3.12/site-packages/starlette/responses.py", line 46, in __init__
    self.body = self.render(content)
                ^^^^^^^^^^^^^^^^^^^^
  File "/Users/dingyunguo/work/parallax/venv/lib/python3.12/site-packages/fastapi/responses.py", line 45, in render
    assert orjson is not None, "orjson must be installed to use ORJSONResponse"
           ^^^^^^^^^^^^^^^^^^
AssertionError: orjson must be installed to use ORJSONResponse

Proved that after installed orjson, the curl can return proper response

❯ curl http://localhost:3001/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"messages": [{"role":"user", "content":"Hello!"}], "stream": false}'
{"id":"06b00462-1908-4811-9a43-8ae0865544a0","object":"chat.completion","model":"default","created":1762573046.6555982,"choices":[{"index":0,"logprobs":null,"finish_reason":"stop","matched_stop":0,"messages":{"role":"assistant","content":"<think>\nOkay, the user just said \"Hello!\" so I need to respond appropriately. Let me think about the best way to greet them. Since they used \"Hello,\" maybe a simple and friendly reply would work. I should make sure to acknowledge their message and offer help. Let me check if there's any specific context I should consider, but since there isn't, a general response is good. I'll go with something like \"Hello! How can I assist you today?\" to keep it open and helpful.\n</think>\n\nHello! How can I assist you today? 😊","reasoning_content":null,"tool_calls":null}}],"usage":{"prompt_tokens":10,"total_tokens":126,"completion_tokens":116}}

Key Changes

1. Add orjson to pyproject.toml, i didn't specify a version though, i let pip to resolve that for me, but if we want to be more conservative i can try to fix with orjson>=<minimum version>

🔗 Related Issues

List any issues this PR closes or relates to:

• Closes [Bug]: 500 Internal Server Error when stream is set to false #200

✅ Checklist

Please ensure the following points are addressed before merging:

• I have performed a self-review of my own code.
• I have added/updated tests that prove my fix or feature works (if applicable).
• I have updated the documentation (if necessary).
• My code follows the project's style guidelines.