fix: add maxTokens to serve mode

[samirtahir91]

📑 Description

We need to set maxTokens for serve mode, this is not set by default like it is with k8sgpt auth, which defaults to 2048.
Backends like google gemini and googlevertexai fail without setting maxTokens when running in serve mode (so including k8sgpt operator).

This PR adds a new environment variable K8SGPT_MAX_TOKENS which you can set for serve, the default is set to 2048 if unset

✅ Checks

• My pull request adheres to the code style of this project
• My code requires changes to the documentation
• I have updated the documentation as required
• All the tests have passed

ℹ Additional Information

The k8sgpt operator will need to be updated to set maxTokens and providerId also in the k8sgpt CRD spec - injecting the env vars - see k8sgpt-ai/k8sgpt-operator#545

[samirtahir91]

@AlexsJones Could you review please?

[samirtahir91]

@AlexsJones - Are you happy to merge?

[AlexsJones]

Thanks for this, I think it's a good first step

[samirtahir91]

Thanks for this, I think it's a good first step

No worries 😃, once merged can you review the change for the operator to adopt this in k8sgpt-ai/k8sgpt-operator#545

[samirtahir91]

@AlexsJones Can you merge this please?

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 12 lines in your changes missing coverage. Please review.

Project coverage is 34.65%. Comparing base (173e4dc) to head (9f68d30).
Report is 27 commits behind head on main.

Files with missing lines	Patch %	Lines
cmd/serve/serve.go	0.00%	12 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1280      +/-   ##
==========================================
- Coverage   34.76%   34.65%   -0.12%     
==========================================
  Files          94       95       +1     
  Lines        6342     6417      +75     
==========================================
+ Hits         2205     2224      +19     
- Misses       4046     4100      +54     
- Partials       91       93       +2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.