- Moves MCP tool discovery logic from ToolRegistry into a new, dedicated MCP client (mcp-client.ts and mcp-tool.ts).
- Updates ToolRegistry to utilize the new MCP client.
- Adds comprehensive tests for the new MCP client and its integration with ToolRegistry.
Part of https://github.com/google-gemini/gemini-cli/issues/577
- 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
- Removes the sqlite3 dependency and refactors the logging mechanism to use a JSON file (logs.json) instead of a database.
- This change is a temporary workaround to address issues with macOS sandboxing that were caused by the SQLite native module.
- Storing all logs in a single JSON file may introduce scalability concerns in the future.
Fixes https://github.com/google-gemini/gemini-cli/issues/522
- 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
- Corrects an issue where the `nextSpeakerCheck` would determine the model should speak next, but the models response was not properly propagated due to a missing `yield*` in a recursive call within `sendMessageStream`.
- This change ensures that when the model is designated as the next speaker, its generated content is correctly unwoven and returned, allowing the conversation to proceed as expected.
Part of https://github.com/google-gemini/gemini-cli/issues/551
- 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
- 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
- Upgraded the @google/genai SDK from ^0.13.0 to ^1.0.1.
- Addressed a related type error in `packages/server/src/tools/edit.test.ts` by updating a type assertion.
Part of https://github.com/google-gemini/gemini-cli/issues/551
- Updated the diff generation in `edit.ts` and `write-file.ts` to include the `ignoreWhitespace: true` option.
- This ensures that whitespace-only changes are not highlighted in the diff output when there are other content modifications, making the diffs cleaner and easier to review.
- Extract default diffing options into single source of truth.
Fixes https://github.com/google-gemini/gemini-cli/issues/548
- 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
- 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
- Edit corretion leans on LLM-isms to ensure we properly fix poorly escaped content. Beacues of this we need to ensure that we don't re-run edit correction in many cases.
- To ensure this an `LruCache` has been added to capture intermediate steps of edit correction to avoid re-computations.
- Max cache size is 50 currently. This means a user can have a muti-confirmation flow of 25 items without recomputing anything (assuming they all break edit correction).
- Laid some groundwork for future testing.
Part of https://github.com/google-gemini/gemini-cli/issues/484
- Prior to this when a user would turn on auto-accept for edits we'd stop ensuring correct edits. This would result in a lot of back and forth by the model. This change also incoporates ensure correct edit into the normal execution flow.
- Added edit tests for this.
Part of https://github.com/google-gemini/gemini-cli/issues/484
- Since we're now LLM correcting a lot of problematic edits we need to also potentially trim bad edits (llms have a bad habbit of adding whitespace places).
Part of https://github.com/google-gemini/gemini-cli/issues/484
- When correcting edits prior to this if we found more than one occurrence we would try to auto-correct the old/new strings. There's no need in this situation because the tool has already provided too vague of an old_string to act upon. Instantly return.
Part of https://github.com/google-gemini/gemini-cli/issues/484
- Previously, `new_string` was assumed to be over-escaped if `old_string` was.
- This change introduces an explicit check (`newStringPotentiallyEscaped`) to determine if `new_string` itself needs correction.
- If `new_string` is potentially escaped, its corrected using an LLM call; otherwise, the original `new_string` is used.
- This avoids unnecessary corrections to `new_string` when only `old_string` was problematic.
Part of https://github.com/google-gemini/gemini-cli/issues/484
- Implement a heuristic to detect and unescape `new_string` if it appears Gemini has over-escaped it, while `old_string` is correctly formatted.
- This improves the reliability of the replace tool when the model generates an incorrectly escaped replacement string.
Part of https://github.com/google-gemini/gemini-cli/issues/484
- Refactor `ensureCorrectEdit` to clarify the correction flow for `old_string` and `new_string`.
- Only correct `new_string` if it was potentially escaped; otherwise, use the original.
- Introduce `CorrectedEditParams` and `CorrectedEditResult` interfaces for better type definition.
- Relocate `countOccurrences` for better logical grouping.
Part of https://github.com/google-gemini/gemini-cli/issues/484
