Conductor 0.39 adds instant chat summaries, PR actions in the command palette, in-file search, and a faster experimental sidebar. Teams running multi-session coding workflows can use it to cut UI friction and reduce context switching during review and triage.

Conductor positioned 0.39 as a workflow release. The headline change is that summarizing chats is now "instant," which removes a wait state from session handoffs and review passes in long-running agent conversations, according to Conductor's release thread. The same release expands the command palette so users can "create, merge, and manage PRs," jump to the next session needing attention, search sessions by message content, open settings tabs, and check for updates without leaving the keyboard, per the command palette post.
A smaller but practical addition is in-file search during edit mode. Conductor's search update says users can "finally search within files" with ⌘F, which closes an obvious gap for people reviewing or editing generated code inside the app rather than bouncing out to another editor.
Yes. Conductor says it fixed "a bug in our virtualization library," and that switching between workspaces should now be faster with less "scroll jank," according to the performance post. That matters most for teams running many parallel sessions, where list rendering and workspace hops can become the bottleneck even when the underlying model is fast enough.
The experimental sidebar also got a more operational view of session state. In Conductor's sidebar update, workspaces now show human-readable branch names, distinct icons for plan-approval and user-input states, running indicators, and workspace counts next to collapsed status groups. The company says the redesigned sidebar is still behind Settings → Experimental → New sidebar, so these navigation improvements are available as an opt-in rather than the default UI.
Claude can now drive macOS apps, browser tabs, the keyboard, and the mouse from Claude Cowork and Claude Code, with permission prompts when it needs direct screen access. That makes legacy desktop workflows automatable, and Anthropic is pairing the push with more background-task support for longer agent loops.
releaseOpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.
releaseCursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
breakingChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
breakingEpoch AI says GPT-5.4 Pro elicited a publishable solution to one 2019 conjecture in its FrontierMath Open Problems set, with a formal writeup planned. Treat it as an early milestone worth reproducing, not blanket evidence that frontier models can already automate math research.
Conductor 0.39 is out! So many good things in this release. First up: summarizing chats is now instant!
You can finally search within files (in edit mode) with ⌘F
We’ve fixed a bug in our virtualization library. Switching between workspaces should now be faster, and there should be less scroll jank. (this one's for you, @garrytan 🫡)