* SANDBOX_SET_UID_GID option for systems where this is necessary (should be only rootful docker on linux w/o userns-remap configured)
* Merge remote-tracking branch 'origin/main' into sandbox_uid_gid
* enable servers in sandbox to listen on localhost (127.0.0.1) instead of 0.0.0.0, ensuring servers can be container/host-agnostic
* Merge remote-tracking branch 'origin/main' into sandbox_localhost_works
* env flags SANDBOX_{MOUNTS,ENV}, improved debugging through sandbox that should now work in all scenarios
* Merge remote-tracking branch 'origin/main' into sandbox_flags_improved_debugging
* New method for handling stdin. Bypass Ink, and output to stdout. Makes the CLI work like a typical Unix application when called with piped input.
* Fixing a few post-merge errors.
* Format code.
* Clean up lint and format errors.
Else branches are an anti pattern especially if you can easily return from the previous branch. Over time, else branches cause deep nesting and make code unreadable and unmaintainable. Remove elses where possible.
- 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.
Introduces a process.on('unhandledRejection') handler in src/gemini.ts
as a workaround for an issue where 429 ClientErrors originating from
the @google/genai library's sendMessageStream during iteration can
cause an unhandled rejection, even when caught within local try/catch
blocks in the application code (e.g., in processGeminiStream).
The handler specifically identifies this known 429 ClientError based on
its type and message content. If matched, it logs a warning indicating
the known issue is being suppressed and prevents process.exit(1).
Any other genuinely unhandled promise rejections will still be logged
as critical errors and will terminate the application, maintaining
default behavior for unexpected issues. This workaround mitigates a
suspected library-internal problem related to error propagation during
asynchronous stream iteration.
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__
Jacob Richman
Brandon Keiji
Olcan
Allen Hutchison
Jaana Dogan
Taylor Mullen
Evan Senter
Tyler
Allen Hutchison