feat(tui): show running tools and LLM status in sidebar #9658
+431
−19
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
- Add 'Running' section to sidebar showing active tools with elapsed time - Display LLM inference states: Sending, Pondering, Streaming, Retry - Extract extractToolCommand utility to tui/util/running.ts - Reuse existing formatDuration from @/util/format - Add tests for extractToolCommand with 100% coverage
- Add 'Running' section showing active tools with elapsed time - Display LLM inference states: Sending, Pondering, Streaming, Retry - Show background agents as 'agent1:', 'agent2:', etc. with numbering - Always show LLM status on top, even while tools/agents are running - Extract createRunningState hook to tui/util/running.ts - Reuse existing formatDuration from @/util/format - Tick interval only runs when session is busy (perf optimization) - Add tests for extractToolCommand
Contributor
|
Hey! Your PR title Please update it to start with one of:
Where See CONTRIBUTING.md for details. |
Contributor
|
The following comment was made by an LLM, it may be inaccurate: No duplicate PRs found |
Becktor
changed the title
Adds a Running section to the sidebar showing LLM status (Pondering, Streaming, etc.) and active tools/agents with elapsed time. Closes anomalyco#9655 Related: anomalyco#8322, anomalyco#7093, anomalyco#5872
- Extract running-tools.tsx for tool tracking - Extract running-llm.tsx for LLM status - Make extractToolCommand generic with pattern-based fallback - Add tests for generic tool command extraction
Replace nested loops with functional flatMap/filter/map chain for cleaner code
Replace inferred LLM status with explicit server-side phases: - sending: waiting for LLM response - reasoning: receiving reasoning tokens - streaming: receiving text output This simplifies running-llm.tsx from inference logic to direct status lookup
Becktor
changed the title
- Add 'planning' status emitted on tool-input-start event - Add 'waiting' status emitted on tool-call event - Add TaskMetadata and str() helper for type-safe metadata access - Remove all 'as any' casts from running tools code
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Closes #9655
Related: #8322, #7093, #5872
What does this PR do?
Adds a "Running" section to the sidebar that displays:
agent1:,agent2:, etc.Implementation
SessionStatuswith explicit LLM phases (sending,planning,reasoning,streaming,waiting)tui/util/running*.tsxHow did you verify it works?
Screenshot