Repository navigation
Live thought line on the working row (#1531) - #1535
Conversation
The status strip showed a bare "Thinking…" while reasoning streamed. It now shows the last non-empty line of the latest thought, with markdown emphasis stripped and clamped to 120 chars, falling back to "Thinking…" when there is no text. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b92baa30b4
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| const liveThought = latestThinkingId | ||
| ? (detail?.messages.find((m) => m.id === latestThinkingId)?.text ?? null) |
There was a problem hiding this comment.
When a Claude, Kimi, Cursor, OpenCode, or Codex reasoning block grows beyond 8,000 characters, the provider adapters store only its prefix in ChatMessage.text (THINKING_TRUNCATE in electron/runner.js, with truncate implemented as slice(0, max) in electron/claude.js). Reading the last line from that stored value therefore makes the new working-row text freeze at the 8,000-character boundary even while further thoughts are streaming; preserve or transmit the current tail separately so the row continues showing the latest thought.
Useful? React with 👍 / 👎.
Part of #1531.
While the agent is thinking, the working row now shows the last line of its latest thought instead of just "Thinking…". Markdown emphasis such as Claude's
**Planning the fix**headers is stripped, and the line is cut off at 120 characters. When there is no thought text yet, the row still says "Thinking…". A hung warning, workflow fan-out or a running tool still take priority over the thought.Tests are in
test/workingLabel.test.ts, plus updated call-site expectations intest/threadView.test.tsx.🤖 Generated with Claude Code