Fix groq model config to use service_tier auto
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Updated Groq model configs to use the correct provider and set
service_tier to auto for all Groq models.
- **Bug Fixes**
- Fixed provider field for Groq models.
- Added service_tier: auto to Groq model configs.
- Updated model loading to use ChatGroq with service_tier support.
<!-- End of auto-generated description by cubic. -->
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Refactored the DOM processing tree to simplify element extraction,
improve attribute handling, and remove unnecessary performance metrics
and optimizations.
- **Refactors**
- Cleaned up and streamlined DOM tree code, removing debug metrics and
redundant logic.
- Improved clickable element string formatting and attribute
deduplication for token efficiency.
- Updated file system to only create `todo.md` by default.
- Adjusted tests and documentation to match new file system and DOM
extraction behavior.
<!-- End of auto-generated description by cubic. -->
Auto-generated PR for: eval-runner-status-updates
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Added runner progress tracking to the evaluation workflow, sending
status updates to the backend at key stages and on completion.
- **New Features**
- Workflow now registers runner start and completion status with the
backend API.
- Service code sends progress updates for each task stage, including
errors.
<!-- End of auto-generated description by cubic. -->
- Added validation for START_INDEX and TOTAL_TASKS to ensure they are numeric, with default values set to prevent errors.
- Improved logging for task range calculations and runner ID generation, including warnings for non-numeric inputs.
- Enhanced evaluation output handling with comprehensive error capture and logging, ensuring better debugging information is available.
- Implemented checks for the existence of evaluation logs and provided statistics for better visibility into evaluation outcomes.
- Added support for dynamic runner ID generation that aligns with GitHub Actions patterns, incorporating start index from environment variables.
- Updated the evaluation script to send detailed progress updates, including task range and total assigned tasks, to the tracking API.
- Improved error handling and logging for runner registration and completion updates to ensure reliability during evaluations.
- Moved the formatting and evaluation stages outside the browser session block to ensure they are executed regardless of session state.
- Updated error handling for evaluation and server save stages to maintain consistent logging and task result management.
- Ensured that server save attempts are always made, improving reliability in task completion.
Auto-generated PR for: eval include runner link
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Added support for passing the GitHub workflow run URL through the
evaluation pipeline for better tracking and visibility.
- **New Features**
- The workflow URL is now constructed and passed as a command-line
argument.
- The evaluation service accepts and stores the workflow URL for each
run.
<!-- End of auto-generated description by cubic. -->
- Update DOM element highlighting from *[index]* to <new>[index]</new>
- Update system prompts to reflect new <new> tag format
- Provides clearer semantic meaning for new elements in browser state
Clarify system prompt description of `<new>` tags to specify new
clickable elements.
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Updated the system prompt to clarify that elements tagged with <new> are
clickable elements that appeared since the last step, if the URL has not
changed.
<!-- End of auto-generated description by cubic. -->
Auto-generated PR for: remove git function helpers
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Removed the git-functions.sh script, which included helper functions for
automating branch creation, commits, pushes, and pull requests. This
cleans up unused shell helpers from the codebase.
<!-- End of auto-generated description by cubic. -->
