Doesn't work with openai?

[omkarb-sg]

When I got Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead. I updated my config file to also include

{
    "version": "1.0",
    "base_url": "https://api.openai.com/v1",
    "main_model": "gpt-5-nano-2025-08-07",
    "cluster_model": "gpt-5-nano-2025-08-07",
    "default_output": "docs",
    "max_tokens": 32768,
    "max_completion_tokens": 32768, <-- Here
    "max_token_per_module": 36369,
    "max_token_per_leaf_module": 16000,
    "max_depth": 5
}

But still failed with same error.
Here is my config:

$ codewiki config show

CodeWiki Configuration
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Credentials
  API Key:          sk-p...VOQA (in system keychain)

API Settings
  Base URL:         https://api.openai.com/v1
  Main Model:       gpt-5-nano-2025-08-07
  Cluster Model:    gpt-5-nano-2025-08-07
  Fallback Model:   glm-4p5

Output Settings
  Default Output:   docs

Token Settings
  Max Tokens:              32768
  Max Token/Module:        36369
  Max Token/Leaf Module:   16000

Decomposition Settings
  Max Depth:               5

Agent Instructions
  Using defaults (no custom settings)

Configuration file: C:\Users\<user>\.codewiki\config.json

$ codewiki generate --create-branch --github-pages --verbose
[1/4] Validating configuration...
✓ Configuration valid
[2/4] Validating repository...
✓ Repository valid: <repo>
[17:46:43] Detected languages: JavaScript (13 files)
✓ Output directory: C:\Users\<user>\Desktop\Projects\<project>\docs
[3/4] Creating git branch...
✓ Created branch: docs/codewiki-20260302-174643
[4/4] Generating documentation...

[17:46:43] Max tokens: 32768
[17:46:43] Max token/module: 36369
[17:46:43] Max token/leaf module: 16000
[17:46:43] Max depth: 5

[00:00] Phase 1/5: Dependency Analysis
[00:00]   Initializing dependency analyzer...
[00:00]   Parsing source files...
[00:00]   Found 22 leaf nodes
[00:00]   Dependency Analysis complete (0.4s)

[00:00] Phase 2/5: Module Clustering
[00:00]   Clustering modules with LLM...
✗ Module clustering failed: Error code: 400 - {'error': {'message': "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", 'type': 'invalid_request_error', 'param': 'max_tokens', 'code': 'unsupported_parameter'}}
✗ Traceback: Traceback (most recent call last):
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\cli\adapters\doc_generator.py", line 216, in _run_backend_generation
    module_tree = cluster_modules(leaf_nodes, components, backend_config)
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\src\be\cluster_modules.py", line 62, in cluster_modules
    response = call_llm(prompt, config, model=config.cluster_model)
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\src\be\llm_services.py", line 80, in call_llm
    response = client.chat.completions.create(
        model=model,
    ...<2 lines>...
        max_tokens=config.max_tokens
    )
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\openai\_utils\_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\openai\resources\chat\completions\completions.py", line 1204, in create
    return self._post(
           ~~~~~~~~~~^
        "/chat/completions",
        ^^^^^^^^^^^^^^^^^^^^
    ...<47 lines>...
        stream_cls=Stream[ChatCompletionChunk],
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\openai\_base_client.py", line 1297, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\openai\_base_client.py", line 1070, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", 'type': 'invalid_request_error', 'param': 'max_tokens', 'code': 'unsupported_parameter'}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\cli\commands\generate.py", line 368, in generate_command
    job = generator.generate()
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\cli\adapters\doc_generator.py", line 148, in generate
    asyncio.run(self._run_backend_generation(backend_config))
    ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\asyncio\runners.py", line 204, in run
    return runner.run(main)
           ~~~~~~~~~~^^^^^^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\asyncio\runners.py", line 127, in run
    return self._loop.run_until_complete(task)
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\asyncio\base_events.py", line 719, in run_until_complete
    return future.result()
           ~~~~~~~~~~~~~^^
  File "C:\Users\<user>\AppData\Local\Programs\Python\Python314\Lib\site-packages\codewiki\cli\adapters\doc_generator.py", line 225, in _run_backend_generation
    raise APIError(f"Module clustering failed: {e}")
codewiki.cli.utils.errors.APIError: Module clustering failed: Error code: 400 - {'error': {'message': "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", 'type': 'invalid_request_error', 'param': 'max_tokens', 'code': 'unsupported_parameter'}}