| Age | Commit message (Collapse) | Author |
|---|
|
- This changeset uses lowlight.js to parse the code in codeblocks to derive an AST, it then translates that into CSS themes that are widely known via highlight.js (things that GitHub use), finally I translate those css.color attributes into Ink colors and effectivel do <Text color={the color}>the text</Text>.
- To do this I needed to build color mappings from css -> Ink
- I introduced a new `Theme` type that will be used to represent many different color themes. It also enabled the color mappings to be seamless.
- Added a theme manager that only has one theme for now (VS2015). The theme works very well with our colorization.
- Some other bits was removal of borders around our codeblocks since they now have richer rendering.
- Most complex bits of code in this PR is in the `CodeColorizer.tsx`
Fixes https://b.corp.google.com/issues/412433479
|
|
- I plan to utilize these radio buttons for theme selection in the future. Refactoring them into their own component.
Part of https://b.corp.google.com/issues/412797985
|
|
|
|
|
|
Also address the open readability improvement comments from #104.
|
|
- 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
|
|
- This chaneset aligns our confirmation dialog with: https://screenshot.googleplex.com/9yZCX636LzpMrgc
- Primary changes include having custom indicators for confirmation options that align with our coloring / scheme
Fixes https://b.corp.google.com/issues/412607128
|
|
- 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
|
|
|
|
* 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.
|
|
|
|
sandbox name in footer (#96)
|
|
|
|
|
|
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.
|
|
This module is no longer needed and the types can be provided from types.
|
|
- 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.
|
|
and fix missing license headers while we're here) (#62)
|
|
|
|
|
|
* Wire through passthrough commands
* Add default passthrough commands
* Clean up config passing to useGeminiStream
|
|
* Adds debug mode config flag.
* Wire through debug lines
* Add debug mode logging example
* Run format
* Run format again
|
|
scripts/build_container.sh, then start with scripts/start_container.sh. Exit with ^C for now. (#61)
|
|
- This utilizes `ink-gradient` to render GEMINI CODE in amazing colors.
- Added a shared color configuration for UX (should this be in config?). It's very possible that we shouldn't be talking about the specific colors and instead be mentioning "foreground"/"background"/inlineCode etc. type colors.
- Updated existing color usages to utilize `Colors.*`
Fixes https://b.corp.google.com/issues/411385593
|
|
* 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.
|
|
|
|
|
|
Up and down arrows traverse the command history.
|
|
|
|
|
|
|
|
Also fix the bug where the API key is used accidentally as the model name.
|
|
|
|
* Bump the character limit to web fetch.
* Piped Input Hook. First step in bringing in STDIN piping.
* Fix linting errors.
* Remove incorrect comment.
|
|
|
|
- Also updated ci.yml to ensure that linting failures will break the build.
Fully fixes https://b.corp.google.com/issues/411384603
|
|
|
|
- This has the entirety of the changes.
Part of https://b.corp.google.com/issues/411720532
|
|
|
|
- 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
|
|
* Add a warning about the flickering in iTerm.
* Move the iterm warning out of App.tsx.
|
|
|
|
|
|
* Adding some wiring to allow the Ink app to warn if there are local development changes that haven't been captured in the recent build of the Gemini CLI.
* Adding a new useAppEffects.ts file that wores some useEffect handlers in.
* Updating package-lock.json to resolve `npm ci` issues.
* Updating package-lock.json and package.json to resolve `npm ci` issues.
|
|
* Adding a web fetch tool.
|
|
- 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
|
|
We don't have a use case for them yet.
|
|
* Introduce a config module to manage configuration
* Remove public modifier
|
