fix: use full paths to files in workspace context prompt

[ErikBjare]

Fixes #328 #329

---

Important

Updates get_workspace_prompt to use full file paths and removes unused import in gptme/prompts.py.

• Behavior:
  • get_workspace_prompt in gptme/prompts.py now uses full file paths instead of file names in the workspace context prompt.
  • Logs an error and exits if a file specified in the project config does not exist.
• Imports:
  • Removes unused glob import from gptme/prompts.py.

^{This description was created by for d15d533. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to 3bbbd96 in 19 seconds

More details

• Looked at 45 lines of code in 1 files
• Skipped 0 files when reviewing.
• Skipped posting 3 drafted comments based on config settings.

1. gptme/prompts.py:271

• Draft comment:
  The addition of the markdown header # Workspace Context resolves issue 328 by clearly separating the workspace context section from the previous heading.
• Reason this comment was not posted:
  Confidence changes required: 0%
  The PR resolves the issue by adding a markdown header to the workspace context section, which was missing before. This aligns with the requirement to separate it from the previous heading.

2. gptme/prompts.py:259

• Draft comment:
  Switching from glob.glob to workspace.glob is a good change as it aligns with the use of Path objects and ensures full paths are used.
• Reason this comment was not posted:
  Confidence changes required: 0%
  The PR changes the method of file globbing from glob.glob to workspace.glob, which is more appropriate for Path objects and ensures full paths are used.

3. gptme/prompts.py:263

• Draft comment:
  The error message correctly reflects the use of file globs, improving clarity when a specified file pattern does not match any files.
• Reason this comment was not posted:
  Confidence changes required: 0%
  The PR correctly changes the error message to reflect the use of file globs instead of individual files.

Workflow ID: wflow_KpkHG22ZsUOpWlsX

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[ellipsis-dev]

❌ Changes requested. Incremental review on d15d533 in 35 seconds

More details

• Looked at 45 lines of code in 1 files
• Skipped 0 files when reviewing.
• Skipped posting 0 drafted comments based on config settings.

Workflow ID: wflow_5I5nv174FTKVlNZq

---

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.

[ellipsis-dev]

workspace.glob(fileglob) returns a generator, not a list. Convert it to a list before extending files to avoid potential issues.

Suggested change

	if new_files := workspace.glob(fileglob):
	if new_files := list(workspace.glob(fileglob)):

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 0% with 10 lines in your changes missing coverage. Please review.

Project coverage is 72.68%. Comparing base (2343ab6) to head (d15d533).
Report is 1 commits behind head on master.

✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
gptme/prompts.py	0.00%	10 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #330      +/-   ##
==========================================
+ Coverage   70.65%   72.68%   +2.03%     
==========================================
  Files          67       67              
  Lines        4951     4954       +3     
==========================================
+ Hits         3498     3601     +103     
+ Misses       1453     1353     -100     

Flag	Coverage Δ
anthropic/claude-3-haiku-20240307	70.83% <0.00%> (+0.17%)	⬆️
openai/gpt-4o-mini	69.43% <0.00%> (?)

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.