Separate clarification questions from action approvals while preserving Galaxy Decides and Read Only behavior. Respect question capabilities in explicit tool overrides, keep CLI monitors focused, and render approved asynchronous questions while they wait for answers.
Validation: cargo build passed on Linux. Added permission, request and question-state regressions; tests and GUI execution were not run under the build-only workflow.
Keep efficient context windows separate from expanded maxima throughout discovery, display and provider budgets. Expose correlated computer-use requests and actions with existing permissions, preserve screenshots as images, and retain them across checkpoints, compaction and explicit history recall.
Validation: cargo build on Linux passed. Added focused regression coverage; test execution and native GUI verification remain outside this CLI build-only workflow.
Run a conservative, read-only preflight off the UI thread before offering Full Disk Access setup. Successful or inconclusive checks stay silent; only a protected-access denial offers guidance. Honor the native reminder opt-out locally and expose manual settings access in the macOS app menu.
Improve tab-group search, rename focus, history navigation, shell prompt and
completion handling, emoji width promotion, and macOS clipboard support.
Guard unavailable settings/model-selector/undo-close views and forward the
MCP OAuth callback issuer through the existing authentication flow.
Adapt local changes from 14 upstream Warp commits through f571865ca3f2,
reviewed from the latest 200 commits. Preserve Galaxy provider lifecycle,
permissions, storage, and branding; exclude hosted/cloud infrastructure.
Fix existing boolean-assertion lints and use stronger optimization with four
code-generation units for the app test target to fit macOS unwind offsets.
Production and dependency compilation settings remain unchanged.
Validation: two clean builds and a final build; both prescribed Clippy
commands with -D warnings; formatting, shell syntax and completion cleanup;
167 focused regression tests. Galaxy was not launched.
Forward text and reasoning events as they arrive while retaining canonical history without replaying output. Tighten shared communication guidance and add streaming-order regression coverage. Include the staged dependency refresh.
Persist direct-provider tool calls, results, display details, and turn identities so saved conversations rebuild individual panes. Keep restored runs dormant until explicitly resumed and bind queued shell commands to their actual execution blocks.
Persist exact provider history and archived tool results independently of
terminal scrollback, and retain them when active run checkpoints are cleared.
Keep conversation and session saving independent of automatic reopening.
Deduplicate only committed session snapshots, retry transient SQLite write
contention, and enqueue conversation updates before writer shutdown. Recover
healthy startup data independently and protect unread records by disabling
writes with a persistent warning after an incomplete restore. Retain local
transcript pane conversation links across restarts.
Add regression coverage for SQLite failures, context round trips, legacy
fallbacks, and transcript snapshots.
Bring over selected Warp UI improvements: selectable Thought text, message
timestamps, animated theme backgrounds, editable New Window shortcuts,
safer tab renaming and restoration, and text/font/discard crash fixes.
Match upstream orchestration pill geometry and tooltips, and replace expanded
subagent previews with compact links that retain live status and conversation
navigation for launches and follow-up messages.
Include the pending Cargo.lock dependency refresh.
Adapted upstream PRs: #15948, #15884, #15691, #14618, #15772, #15705,
#15605, #14895, #15996, #15771, #14893, and #14603.
Allow new provider runs to continue without an arbitrary lifetime turn budget while preserving explicit limits, checkpoint compatibility, and bounded retries. Keep pending tool proposals visibly queued until execution status arrives, and show cancellation only when supported by actual state.
Validation: formatting, inline test-layout checks, both presubmit Clippy commands, 325 targeted regressions, and 54 core tests after final cleanup passed.
Preserve full terminal-grid width with horizontal scrolling in tool panes. Keep hidden command control changes from unpinning the viewport, and re-pin scrolling at the live edge in normal and inverted layouts.
Validation: formatting, test-layout checks, both presubmit Clippy commands, and 141 relevant tests passed. Ten other terminal-view tests failed identically on the untouched baseline (keyboard, cloud-agent, input status, and footer behavior).
Wait for shell bootstrap before dispatching child prompts, serialize provider preprocessing, and make permission callbacks idempotent. Restrict task lists to concrete multistep plans and stop inferring completion from tool activity.
Update regression fixtures and resolve existing lint and test-layout failures. Verified formatting, both presubmit Clippy commands, and 354 targeted nextest tests.
rkw6086
Ryan Ward