Commit Graph

709 Commits

Author SHA1 Message Date
Daniel Riccio
3d901929c2 test: add comprehensive tests for NewUnifiedDiffStrategy error handling and edge cases 2025-01-14 16:44:15 -05:00
Daniel Riccio
534888af97 refactor: improve NewUnifiedDiffStrategy with enhanced formatting and error handling
- Cleaned up formatting in the parseUnifiedDiff method to ensure consistent indentation and spacing.
- Updated documentation to clarify format requirements for generating unified diffs.
- Added error handling for cases where no hunks are found in the provided diff, improving robustness.
- Enhanced overall readability of the code by standardizing comments and structure.
2025-01-14 12:20:52 -05:00
Daniel Riccio
d25f370013 refactor: enhance NewUnifiedDiffStrategy for improved diff parsing and context handling
- Refactored the parseUnifiedDiff method to streamline the processing of diff lines and improve context line management.
- Added handling for empty context lines to ensure accurate representation in hunks.
- Updated the tool description to clarify requirements for generating unified diffs, emphasizing the importance of preserving indentation and grouping related changes.
- Improved overall readability and consistency of the code by standardizing formatting and indentation practices.
2025-01-14 12:01:09 -05:00
Daniel Riccio
258024aa5a refactor: enhance search strategies with adaptive thresholds and overlapping windows
- Introduced adaptive confidence thresholds based on file size to improve search accuracy.
- Implemented overlapping window functionality in search strategies to capture matches more effectively.
- Added helper functions for evaluating content uniqueness and creating overlapping windows.
- Enhanced existing search functions (exact, similarity, and Levenshtein) to utilize new strategies for better match validation.
- Improved logging for search results to facilitate debugging and analysis of search performance.
2025-01-14 12:00:29 -05:00
Daniel Riccio
f007f64344 refactor: increase minimum confidence threshold in search strategies
- Updated the minimum confidence level from 0.95 to 0.97 to enhance the accuracy of search results.
- Adjusted confidence calculation in the findLevenshteinMatch function to ensure more reliable matching.
2025-01-10 17:36:43 -05:00
Daniel Riccio
0d004b5c77 refactor: increase context lines in NewUnifiedDiffStrategy
- Updated the maximum context lines from 3 to 6 in the parseUnifiedDiff method to provide more context around changes.
2025-01-10 17:35:22 -05:00
Daniel Riccio
6d68edef3e refactor: implement Git fallback strategy in edit processing
- Introduced a new Git fallback strategy for handling edits when confidence levels are low.
- Replaced the previous Git edit strategy with a more robust approach that utilizes temporary directories and commits for original, search, and replace states.
- Enhanced error handling and logging for better debugging during the edit process.
- Updated the main edit function to incorporate the Git fallback strategy, ensuring it is attempted when other strategies fail.
- Improved overall structure and readability of the applyGitFallback function, streamlining the process of applying changes using Git.
2025-01-10 17:34:44 -05:00
Daniel Riccio
ab31aea551 refactor: enhance context handling and confidence validation in edit strategies
- Improved the applyContextMatching function to better track context lines and handle changes more accurately.
- Updated the applyEdit function to enforce a stricter confidence check, now requiring a confidence level of 1 for successful edits.
- Refined the processing logic for addition and removal changes, ensuring more reliable diff application.
- Enhanced debugging capabilities with clearer logging and validation checks for edit results.
2025-01-09 16:38:32 -05:00
Daniel Riccio
5351b3d981 refactor: improve the prompt to prevent absurd amounts of context being generated 2025-01-09 12:05:36 -05:00
Daniel Riccio
44dc489e49 revert: lower the confidence levels 2025-01-08 17:18:09 -05:00
Daniel Riccio
9591ae062a Refactor edit strategies and confidence validation in unified diff processing
- Enhanced the applyContextMatching and applyDMP functions to improve handling of context and edit changes.
- Updated confidence validation logic to ensure stricter checks, now requiring a minimum confidence of 1 for successful edits.
- Refined the way changes are processed, including better tracking of removal and addition changes.
- Improved the validation of edit results by incorporating strategy-specific checks and logging for better debugging.
- Adjusted the applyEdit function to ensure strategies are applied in a more robust manner, with clearer handling of debug mode.
2025-01-08 17:13:46 -05:00
Daniel Riccio
995692c48e Improve strategies and confidence system 2025-01-08 12:28:31 -05:00
Daniel Riccio
594481643b Add New Unified Diff Strategy Implementation
- Introduced a new unified diff strategy with support for context matching, DMP, and Git-based edits.
- Implemented helper functions for parsing unified diffs and evaluating similarity.
- Added types for changes, hunks, and diffs to enhance type safety.
- Created a main edit function that applies strategies sequentially based on confidence levels.
- Included detailed descriptions and usage examples for the new strategy.
2025-01-07 19:01:12 -05:00
Daniel Riccio
2857dd4996 Refactor test cases in search-replace and unified strategies to use async/await for applyDiff method, ensuring consistent handling of asynchronous operations across all tests. 2025-01-07 19:00:29 -05:00
Daniel Riccio
70cf27071b Refactor applyDiff methods in search-replace and unified strategies to return Promises for asynchronous handling 2025-01-07 18:59:55 -05:00
Daniel Riccio
420c6c72dd Replace SearchReplaceDiffStrategy with NewUnifiedDiffStrategy in getDiffStrategy function 2025-01-07 18:59:16 -05:00
Daniel Riccio
612d7020f3 Add unit tests for NewUnifiedDiffStrategy 2025-01-07 18:58:23 -05:00
Daniel Riccio
4356cffb0d Refactor applyDiff method to return a Promise and add logging for diff results 2025-01-07 18:57:40 -05:00
Matt Rubens
bd888d8f5c Merge pull request #189 from RooVetGit/o1_model
Add the o1 model
2025-01-07 15:12:36 -05:00
Matt Rubens
00ac5b48bf Better API error messages 2025-01-07 13:58:53 -05:00
Matt Rubens
0aa5f1fb85 Add the o1 model 2025-01-07 13:33:47 -05:00
Matt Rubens
0ff8fe45d4 UI tweaks 2025-01-07 10:38:51 -05:00
Matt Rubens
c9de9cda66 Revert some whitespace changes 2025-01-07 10:31:42 -05:00
RaySinner
fe22d1ff2d feat: add retry request control with delay settings
- Add requestDelaySeconds setting for configuring delay between retry attempts
- Add alwaysApproveResubmit option for automatic retry approval
- Add api_req_retry_delayed message type for delayed retries
- Update UI components to support new retry control settings
2025-01-07 10:21:51 -05:00
Matt Rubens
87ba95b288 Allow deleting single messages 2025-01-06 23:27:32 -05:00
Mike C
ae2e429fc3 Merge pull request #270 from RooVetGit/feat/full_Integration_Tests
Set up vscode integration test
2025-01-06 22:00:08 -06:00
Matt Rubens
7e9ea7ac28 Add a Git section to the context mentions 2025-01-06 12:17:26 -05:00
Matt Rubens
7383a0514a Merge pull request #282 from RooVetGit/open_ai_streaming_toggle
Streaming checkbox for OpenAI-compatible providers
2025-01-05 22:46:50 -05:00
Matt Rubens
5e8d804d2b Add test 2025-01-05 20:52:06 -05:00
Matt Rubens
2cdfff02c0 Streaming checkbox for OpenAI-compatible providers 2025-01-05 20:34:54 -05:00
Frank
ac776cc8bf fix: adjust log wording 2025-01-05 19:25:52 -05:00
Frank
f813d65b5a fix: parse text to float 2025-01-05 19:25:44 -05:00
Frank
8b0e9bbf32 fix: remove unnecessary comment 2025-01-05 19:25:35 -05:00
Frank
e632998026 feat: add cache information 2025-01-05 19:25:29 -05:00
Frank
8284efc64b fix: use x-completion-request-id header 2025-01-05 16:42:34 -05:00
Frank
6b048923c6 fix: remove unnecessary delay 2025-01-05 16:42:20 -05:00
Frank
eb78332d4e fix: dynamically set computer use value 2025-01-05 00:18:33 -05:00
Frank
e5e700ffcb feat: add Glama gateway 2025-01-04 22:50:12 -05:00
ColemanRoo
8e54360a86 Switch to using dotenv to get test environment variables 2025-01-03 21:35:25 -06:00
ColemanRoo
66c5485534 Set up vscode integration test 2025-01-03 14:26:26 -06:00
Matt Rubens
d32c5f805e Cleanup 2025-01-02 21:36:05 -08:00
Matt Rubens
70f3c041e6 Put more logic behind mcpEnabled flag 2025-01-02 21:11:52 -08:00
Daniel Riccio
ed358b4e07 Add toggle to enable or disable MCP servers on the system prompt 2025-01-02 21:02:59 -08:00
Matt Rubens
621655aacb Try a better enhanced prompt prompt 2025-01-01 00:13:29 -08:00
Matt Rubens
92c2303416 Fix 'allow stream options' checkbox 2024-12-31 22:01:11 -08:00
Matt Rubens
cec623ada4 Fix fuzzy match slider 2024-12-31 10:06:30 -08:00
Matt Rubens
7dba94c0d6 Merge pull request #253 from RooVetGit/cat_pager
Improvements to terminal output when executing commands
2024-12-31 08:06:51 -08:00
Matt Rubens
169f11c78b Add a test ensuring that we're sending a clean conversation history 2024-12-31 03:29:51 -08:00
Matt Rubens
26f7ba07c2 Pass clean conversation history to API for Anthropic 2024-12-31 03:16:42 -08:00
Matt Rubens
c8b8eff147 Setting for number of terminal lines to return from commands 2024-12-30 23:15:01 -08:00