[pull] main from Kilo-Org:main #333
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Fix race condition where getModel() was called before initialization completed - Add initializationPromise to properly await async initialization - Fix UI context window display to use user's ollamaNumCtx setting - User's explicit context window setting now always takes precedence - Provide fallback model info when Ollama models can't be fetched - Add improved error messages with troubleshooting steps
- Added gemini-3-flash-preview model configuration. - Updated the default model to gemini-3-flash-preview. - Updated maxThinkingTokens for gemini-3-pro-preview to 32,768. - Reordered model definitions to prioritize newer versions.
Updated Gemini CLI models and metadata, added new model configuration and adjusted settings for existing models.
- Add new slackbot.md documentation covering: - Overview and capabilities - Prerequisites (Kilo account, GitHub integration, Slack installation) - How to interact via DMs and channel mentions - Use cases (repo questions, implementing fixes, debugging, code reviews) - Cost information and tips for best results - Troubleshooting guide - Add slackbot entry to sidebars.ts in Advanced Usage section
fix(ollama): fix model not found error and context window display
chore: update Gemini Cli models and metadata
Removed section on AI-powered insights during code reviews from the Slackbot documentation.
…5c-82d5-09cc5d8ed826 docs: add Kilo Slackbot integration documentation
## Summary Adds telemetry tracking for the chat textarea autocomplete feature by reusing the existing `AutocompleteTelemetry` class with a new autocomplete type discriminator. ## Changes ### Extended AutocompleteTelemetry Class - Added `AutocompleteType` discriminator (`"inline"` | `"chat-textarea"`) to distinguish between editor autocomplete and chat textarea autocomplete - All telemetry events now include `autocompleteType` property for filtering in analytics - Made token/cost properties optional in `captureLlmRequestCompleted` (not available for chat completions) - Added optional `suggestionLength` parameter to `captureAcceptSuggestion` ### Chat Textarea Integration - Updated `ChatTextAreaAutocomplete.ts` to track: - Suggestion requests (`captureSuggestionRequested`) - LLM request completion with latency (`captureLlmRequestCompleted`) - LLM request failures with error details (`captureLlmRequestFailed`) - Suggestion filtering with reasons (`captureSuggestionFiltered`) - Successful suggestion returns (`captureLlmSuggestionReturned`) ### Acceptance Tracking - Added new `chatCompletionAccepted` webview message type - Created `handleChatCompletionAccepted.ts` handler for acceptance events - Updated `useChatGhostText.ts` to send telemetry when user accepts suggestions via Tab or ArrowRight - Tracks suggestion length for accepted completions ### Files Changed - `src/services/ghost/classic-auto-complete/AutocompleteTelemetry.ts` - Extended with type discriminator - `src/services/ghost/chat-autocomplete/ChatTextAreaAutocomplete.ts` - Added telemetry calls - `src/services/ghost/chat-autocomplete/handleChatCompletionAccepted.ts` - New handler - `src/core/webview/webviewMessageHandler.ts` - Added message handler - `src/shared/WebviewMessage.ts` - Added new message type - `webview-ui/src/components/chat/hooks/useChatGhostText.ts` - Send acceptance events ## Design Decisions - **Reused existing telemetry class** rather than creating a separate one, using a type discriminator for filtering - **Same event names** as inline autocomplete for consistent analytics, differentiated by `autocompleteType` - **Acceptance tracked from webview** since that's where user interaction happens - **Error handling** wraps LLM calls to capture failures with latency and error details ## Testing - ✅ All tests pass - ✅ Type checking passes - ✅ Linting passes
…e-telemetry feat: add telemetry for chat textarea autocomplete
…fa-a8ee-08c63697b069 feat: add .dist.* files to ManagedIndexing ignore list
…mplete-telemetry JetBrains IDEs - Add Autocomplete Acceptance Telemetry
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
7 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )