dev/gemini-cli/packages/server/src/utils, branch main[no description]http://cgit.wit.com/dev/gemini-cli/atom?h=main2025-05-31T01:25:47ZRename server->core (#638)2025-05-31T01:25:47ZTommaso Sciortinosciortino@gmail.com2025-05-31T01:25:47Zurn:sha1:21fba832d1b4ea7af43fb887d9b2b38fcf8210d0feat: Implement retry with backoff for API calls (#613)2025-05-30T17:57:00ZN. Taylor Mullenntaylormullen@google.com2025-05-30T17:57:00Zurn:sha1:8c46108a852128d1d0792c149746631d83fc58cfChange ReadFile to not have a result display.2025-05-30T17:48:10ZTaylor Mullenntaylormullen@google.com2025-05-30T04:57:25Zurn:sha1:c5608869c00c433a468fe5e88bcbafd83f6599a1
- It's verbose on its own; however, if file content is truncated we'll indicate that in the result display.
Refactor read-file and support images. (#480)2025-05-29T22:30:18ZJacob Richmanjacob314@gmail.com2025-05-29T22:30:18Zurn:sha1:dab7517622527a70bf2f36a9d7a9fa5e1a3b56e0feat: Allow cancellation of in-progress Gemini requests and pre-execution checks2025-05-28T06:46:37ZTaylor Mullenntaylormullen@google.com2025-05-28T06:40:25Zurn:sha1:f2f2ecf9d83224778e5fc38cfcc4a1edddf9f7d4
- Implements cancellation for Gemini requests while they are actively being processed by the model.
- Extends cancellation support to the logic within tools. This allows users to cancel operations during the phase where the system is determining if a tool execution requires user confirmation, which can include potentially long-running pre-flight checks or LLM-based corrections.
- Underlying LLM calls for edit corrections (within and ) and next speaker checks can now also be cancelled.
- Previously, cancellation of the main request was not possible until text started streaming, and pre-execution checks were not cancellable.
- This change leverages the updated SDK's ability to accept an abort token and threads s throughout the request, tool execution, and pre-execution check lifecycle.
Fixes https://github.com/google-gemini/gemini-cli/issues/531
Fix(chat): Finalize next speaker detection logic2025-05-26T22:21:45ZTaylor Mullenntaylormullen@google.com2025-05-26T21:39:29Zurn:sha1:9e1cfca53f4e71697f883c17d71bfcae86f01408
- Enhance `checkNextSpeaker` to handle cases where the last message is a function response or an empty model message.
- If the last message is a function response, the model should speak next.
- If the last message is an empty model message, the model should speak next.
- This ensures more robust and accurate determination of the next speaker in the conversation, completing the fix for the issue.
- Updated tests.
Fixes https://github.com/google-gemini/gemini-cli/issues/551
Fix(chat): Prevent empty model response after function call2025-05-26T21:29:24ZTaylor Mullenntaylormullen@google.com2025-05-26T21:25:31Zurn:sha1:597dc86a9c7011b7f3288445b14abb11817424da
- Addresses a Gemini model bug where it may return an empty content object after a function response.
- Previously, the SDK attempted to inject an empty model message, which could disrupt curated history.
- This change modifies our custom class to detect this scenario using an utility and avoid pushing an unnecessary empty model message, thus preserving history integrity.
Workaround for https://b.corp.google.com/issues/420354090
Part of https://github.com/google-gemini/gemini-cli/issues/551
Refactor(chat): Introduce custom Chat class for future modifications2025-05-26T21:20:28ZTaylor Mullenntaylormullen@google.com2025-05-26T21:17:56Zurn:sha1:480549e02ed4ae01c7df2abbd98bb0eb5b23bdd5
- Copied the `Chat` class from `@google/genai` into `packages/server/src/core/geminiChat.ts`.
- This change is in preparation for future modifications to the chat handling logic.
- Updated relevant files to use the new `GeminiChat` class.
Part of https://github.com/google-gemini/gemini-cli/issues/551
Fix(test): Improve write-file and editCorrector test suites2025-05-25T22:02:08ZTaylor Mullenntaylormullen@google.com2025-05-25T21:59:45Zurn:sha1:3281cbc835ae77d0c33662485505651d01a984cc
- Enhanced by:
- Mocking and utilities (, ) to allow for more focused unit testing of .
- Adding comprehensive tests for the private method, covering new and existing file scenarios, as well as error handling.
- Expanding tests for and to verify behavior with the new content correction logic, including diff generation and directory creation.
- Refined by:
- Introducing robust mocking for and its methods (, , ) to simulate LLM interactions accurately.
- Adding extensive test scenarios for , categorized by how matches and how is processed, including direct matches, unescaping, and LLM-based corrections.
- Including tests for edge cases like no matches or multiple matches.
- Adding a utility for better test isolation.
Final fix for https://github.com/google-gemini/gemini-cli/issues/484
Fix(write-file): Correct over-escaping and improve content generation2025-05-25T21:45:47ZTaylor Mullenntaylormullen@google.com2025-05-25T21:41:37Zurn:sha1:5097b5a6563a4d514242580495c5974b7e665c3f
- Leveraged existing edit correction technology from `edit.ts` to address over-escaping issues in `write-file.ts`.
- Introduced `ensureCorrectFileContent` for correcting content in new files, where a simple "replace" isnt applicable. This uses a new LLM prompt tailored for correcting potentially problematic string escaping.
- Added caching for `ensureCorrectFileContent` to optimize performance.
- Refactored `write-file.ts` to integrate these corrections, improving the reliability of file content generation and modification.
Part of https://github.com/google-gemini/gemini-cli/issues/484