fix: deepseek provider and gptme-eval docker improvements

[ErikBjare]

• Skip file handling for deepseek provider (does not support files)
• Make eval results directory configurable via EVAL_RESULTS_DIR env var
• Configure eval results directory in gptme-eval docker container

---

Important

Skip file handling for deepseek provider and make eval results directory configurable in gptme-eval Docker setup.

• Behavior:
  • Skip file handling for deepseek provider in _process_file() in llm_openai.py.
  • Make eval results directory configurable via EVAL_RESULTS_DIR environment variable in main.py.
• Docker:
  • Set EVAL_RESULTS_DIR in Dockerfile.eval to /app/eval_results.

^{This description was created by for cdf56fa. It will automatically update as commits are pushed.}

[ellipsis-dev]

❌ Changes requested. Reviewed everything up to cdf56fa in 59 seconds

More details

• Looked at 63 lines of code in 3 files
• Skipped 0 files when reviewing.
• Skipped posting 1 drafted comments based on config settings.

1. gptme/llm/llm_openai.py:174

• Draft comment:
  Consider updating the comment to clarify that the function returns early if the provider is deepseek. This improves readability.
• Reason this comment was not posted:
  Confidence changes required: 20%
  The check for model.provider == "deepseek" is correct, but the comment should be updated to reflect that the function returns early if the provider is deepseek. This is a minor readability improvement.

Workflow ID: wflow_dcfZxhKA5WMO4Qcs

---

Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 85.71429% with 1 line in your changes missing coverage. Please review.

Project coverage is 72.42%. Comparing base (7a797cf) to head (cdf56fa).

✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
gptme/llm/llm_openai.py	75.00%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##           master     #270   +/-   ##
=======================================
  Coverage   72.42%   72.42%           
=======================================
  Files          64       64           
  Lines        4319     4323    +4     
=======================================
+ Hits         3128     3131    +3     
- Misses       1191     1192    +1     

Flag	Coverage Δ
anthropic/claude-3-haiku-20240307	71.10% <42.85%> (-0.12%)	⬇️
openai/gpt-4o-mini	71.06% <85.71%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

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

---

🚨 Try these New Features:

• JS Bundle Analysis - Avoid shipping oversized bundles