- The tl;dr; is that GC couldn't see what the user was saying when tool call events happened in response. The rason why this was happening was because we were instantly invoking tools that the model told us to invoke and then instantly re-requesting. This resulted in the bug because the genai APIs can't update the chat history before a full response has been completed (doesn't know how to update if it's incomplete).
- To address the above issue I had to do quite the large refactor. The gist is that now turns truly drive everything on the server (vs. a server client split). This ensured that when we got tool invocations we could control when/how re-requesting would happen and then also ensure that history was updated. This change also meant that the server would act as an event publisher to enable the client to react to events rather than try and weave in complex logic between the events.
- A BIG change that this changeset incudes is the removal of all of the CLI tools in favor of the server tools.
- Removed some dead code as part of this
- **NOTE: Confirmations are still broken (they were broken prior to this); however, I've set them up to be able to work in the future, I'll dot hat in a follow up to be less breaking to others.**
Fixes https://b.corp.google.com/issues/412320087
* Starting to move a lot of code into packages/server
* More of the massive refactor, builds and runs, some issues though.
* Fixing outstanding issue with double messages.
* Fixing a minor UI issue.
* Fixing the build post-merge.
* Running formatting.
* Addressing comments.
- As part of this work I also started building out errors.ts which will be a cumulation of error helpers to better handle the challenging `catch (error: unknown)` requirement.
- More changes are to come, this is truly a partial change in order to not disrupt as many people as possible.
Part of https://b.corp.google.com/issues/411384603
This is only the first change of many changes.
* Remove redundant autogenerated comments
* Use the recommended file name style
* Use camelCase for variable names
* Don't introduce submodules for relevant types
* Don't introduce constants like modules, these are implementation details
* Remove empty files
This commit introduces the initial codebase for the Gemini Code CLI, a command-line interface designed to facilitate interaction with the Gemini API for software engineering tasks.
The code was migrated from a previous git repository as a single squashed commit.
Core Features & Components:
* **Gemini Integration:** Leverages the `@google/genai` SDK to interact with the Gemini models, supporting chat history, streaming responses, and function calling (tools).
* **Terminal UI:** Built with Ink (React for CLIs) providing an interactive chat interface within the terminal, including input prompts, message display, loading indicators, and tool interaction elements.
* **Tooling Framework:** Implements a robust tool system allowing Gemini to interact with the local environment. Includes tools for:
* File system listing (`ls`)
* File reading (`read-file`)
* Content searching (`grep`)
* File globbing (`glob`)
* File editing (`edit`)
* File writing (`write-file`)
* Executing bash commands (`terminal`)
* **State Management:** Handles the streaming state of Gemini responses and manages the conversation history.
* **Configuration:** Parses command-line arguments (`yargs`) and loads environment variables (`dotenv`) for setup.
* **Project Structure:** Organized into `core`, `ui`, `tools`, `config`, and `utils` directories using TypeScript. Includes basic build (`tsc`) and start scripts.
This initial version establishes the foundation for a powerful CLI tool enabling developers to use Gemini for coding assistance directly in their terminal environment.
---
Created by yours truly: __Gemini Code__
