- When larger confirmations were shown and then declined you'd typicaly get large chunks of content flickering upon typing or sending a subsequent request. This was primarily due to us leaving the latest confirmation as "updateable" / pending. This changeset addresses that by flushing any pending confirmation to the static container.
Part of https://b.corp.google.com/issues/414196943
Implements robust error handling for Gemini API calls, integrating with the centralized error reporting system.
- API errors are now caught and reported to dedicated log files, providing detailed diagnostics without cluttering the user interface.
- A concise error message is surfaced to the user in the UI, indicating an API issue.
- Ensures any pending UI updates are processed before an API error is displayed.
This change improves our ability to diagnose API-related problems by capturing rich error context centrally, while maintaining a clean user experience.
Signed-off-by: Gemini <YourFriendlyNeighborhoodAI@example.com>
- Upon decline / cancellation we weren't showing the model the cancellation status or states. Therefore it didn't know why things would or wouldn't happen
Fixes https://b.corp.google.com/issues/416797704
- Plumbed abort signals through to tools
- Updated the shell tool to properly cancel active requests by killing the entire child process tree of the underlying shell process and then report that the shell itself was canceled.
Fixes https://b.corp.google.com/issues/416829935
- We were console.erroring, throwing and early aborting. Instead we now treat cancels like a normal user message and show an indicator in the UI
Fixes https://b.corp.google.com/issues/416515841
Problem:
When a tool confirmation dialog appeared for a potentially long-running
operation (e.g., `npm install`), accepting the confirmation would cause
the UI to appear to hang. The confirmation dialog would remain visible,
and no further UI updates would occur until the long-running task
completed. This provided a poor user experience as the application
seemed unresponsive.
Fix:
This change addresses the issue by ensuring the UI is updated to remove
the confirmation dialog *before* the long-running operation begins.
It also marks the tool as executing so a spinner can be shown.
Fixes https://b.corp.google.com/issues/415844994
Signed, sealed, delivered, it's yours!
- Gemini, your friendly neighborhood code-slinger
* First integration of at commands into useGeminiStream.ts
* feat: Integrate @ command for file/directory reading
- Adds support for `@<path>` commands in the CLI UI to read file or directory contents using the `read_many_files` tool.
- Refactors `useGeminiStream` hook to handle slash, passthrough, and @ commands before sending queries to the Gemini API.
- Improves history item ID generation to prevent React duplicate key warnings.
* fix: Handle additional text after @ command path
- Modifies the `@` command processor to parse text following the file/directory path (e.g., `@README.md explain this`).
- Includes both the fetched file content and the subsequent text in the query sent to the Gemini API.
- Resolves the TODO item in `atCommandProcessor.ts`.
* feat: Allow @ command anywhere in query and fix build
- Update `atCommandProcessor` to correctly parse `@<path>` commands regardless of their position in the input string using regex. This enables queries like "Explain @README.md to me".
- Fix build error in `useGeminiStream` by importing the missing `findSafeSplitPoint` function.
* rename isPotentiallyAtCommand to isAtCommand
* respond to review comments.
* Refactor useGeminiStream to pull slash commands and passthrough commands into their own processors.
* whitespace lint errors.
* Add sugestions from code review.
- Refactors history display using Ink's <Static> component to prevent flickering and improve performance by rendering completed items statically.
- Introduces ConsolePatcher component to capture and display console.log, console.warn, and console.error output within the Ink UI, addressing native handling issues.
- Introduce a new content splitting mechanism to work better for static items. Basically when content gets too long we will now split content into multiple blocks for Gemini messages to ensure that we can statically cache larger pieces of history.
Fixes:
- https://b.corp.google.com/issues/411450097
- https://b.corp.google.com/issues/412716309
- We weren't reseting the tool group inbetween content which meant we'd start a new group on the first tool call, and if regular textual content followed it'd effectively close that group; however, we weren't updating our state to really close that group. Meaning, any subsequent tool calls or confirmations would get grouped with the original grouping.
- When we see textual content from Gemini we now reset the tool call group.
Fixes https://b.corp.google.com/issues/412605330
- Bring tool messages in line with original envisioned UI of: https://screenshot.googleplex.com/9yZCX636LzpMrgc
- In particular this represents more descriptive names. FWIW we already had this tech we just weren't passing around information correctly (`displayName` vs. `name`)
- Add gray to our list of color pallete's and removed Background (unused)
- Re-enabled representing canceled messages
- Migrated back towards a cleaner tool message design of status symbols & border colors vs. overly verbose text.
- Removed border from confirmation diffs.
Fixes https://b.corp.google.com/issues/412598909
- This fixes what it means to get confirmations in GC. Prior to this they had just been accidentally unwired as part of all of the refactorings to turns + to server/core.
- The key piece of this is that we wrap the onConfirm in the gemini stream hook in order to resubmit function responses. This isn't 100% ideal but gets the job done for now.
- Fixed history not updating properly with confirmations.
Fixes https://b.corp.google.com/issues/412323656
- 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
- There were a few hiccups here. Somehow 2.5-flash wasn't actually abiding by our tool schema. Instead it was inferring `path`. To semi-combat this I've renamed `file_path` -> `path`.
- We weren't elevating errors that were created via schema validation. Instead both the `glob` and `read-file.ts` now surface this.
- In error scenarios (like failing schema) we were improperly surfacing these as success cases because we were overriding tool status.
* 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.
