Agent sessions can be opened in the Agents tool window beside the editor (Open in Tool Window / Open in Editor in the task menus, or by dragging between the editor and the tool window); opening in an editor tab stays the default.
Fixes in review:
- A docked conversation kept the previous task's subagent view after switching tasks: the session's local state is now keyed by task.
- Moving a conversation between the editor and the tool window lost its scroll position: position and follow-output are kept per conversation (task or subagent).
- In a short bottom tool window the message area shrank to a few pixels: wide windows place the task list beside the conversation, narrow ones cap the list height.
- Drag and drop and list selection now go through the agents.dockTask / undockTask / openTask actions.
Co-authored-by: a-rookie-of-C-language <[email protected]>
The composers' primary actions were text buttons. Start, Send and Queue, plus Send in edit-and-resend, now share an icon-only submit button that keeps the translated name as its accessible label and tooltip, and shows a spinner while the action is pending. Stop is unchanged.
Pasting or dropping OS files into a remote project tree sent a client-local source path to the server, so nothing was copied. Local-source imports are now carried separately from project copies and uploaded over the session SFTP channel: streamed in bounded chunks, created exclusively, cancellable across all selected paths under one task, with partial files removed on failure. Symlinks and Unix file modes are preserved, and special files are skipped and reported. Project-internal paste keeps working when the OS clipboard is briefly unavailable.
Native drop positions were assumed to be physical pixels, which shifted the target far from the pointer on Retina displays and with IDE zoom. A shared helper converts them to CSS coordinates for the project tree, the editor and Markdown drop handling, and the agent composer. Composer image drops are now read on the client in remote windows.
Verified on macOS against a live SSH host. Windows and Linux were not run: the Windows conversion is unchanged, the Linux one changed. Copy out from a remote tree to the local machine still needs a download workflow.
Projects now open with a user-owned trust decision. The prompt offers Preview in Restricted Mode, Don't Open and Trust Project, with an optional trusted parent folder; preview is the default focus so Enter never grants trust.
Restricted projects keep browsing, editing, saving, search and highlighting. Project-controlled execution is denied by default in the backend: run, debug, build, tools, language servers, plugins and Git commands that could honour repository configuration. Trusting a project enables those paths without reopening it, and decisions can be revoked in Settings.
Terminals stay available when the user opens one, without project shell settings, environment or virtualenv activation. A shell prompt that runs git in the folder can still honour the repository's core.fsmonitor.
Fixes#462
Agents can report model ids with nested provider paths, which made long rows that lost their provider context. The model picker now shows the short name under a provider heading with the remaining path as detail. Searchable Select matches several tokens across label, detail and hidden keywords, with fuzzy matching, and keeps a heading while one of its items matches.
Select now has an explicit section option, separate from disabled, so a heading can never be selected and a disabled option is not rendered as a heading. Existing section rows in provider options and Find in Files scopes use it. Keyboard navigation skips headings in filtered lists.
Co-authored-by: dimassfeb-09 <[email protected]>
Workspaces open several local project folders in one IDE session (File › New / Open / Manage Workspace…, or Attach when opening a project, which creates a workspace automatically for a plain project window). Member folders are the Project view roots and take part in indexing, Find in Files, Git, language servers, run configurations and builds; agent tasks choose which member they work in. Window › Merge All Project Windows groups project windows into one window with project tabs (switch, reorder, close, move to a new window), restored on reopen.
Closes#241Closes#198Closes#286
The Changes pane took a fixed column next to every agent conversation, including tasks that changed nothing. It is now shown while the task has changes (so it appears when the agent first edits a file) and toggled from a Changes button with the file count in the task header; once toggled, the choice is kept per task.
Co-authored-by: a-rookie-of-C-language <[email protected]>
Images sent to an agent were dropped from the conversation: the user message kept only text and file chips. User entries now record their images and show them as thumbnails that open full size; composer thumbnails open the same preview. Editing a sent message keeps its images (removable) and rerunning from it sends them again.
New agent tasks start in the agent's mode that approves everything without asking (bypassPermissions, yolo, full-access…) or with approvals bypassed, unless the New Task page sets something else.
Agent tasks failed in projects without git because change tracking assumed a repository. Outside a repository there are no changes to compare; worktree isolation is hidden and the task runs in the local checkout, and asking for a worktree there returns a clear error.
Co-authored-by: a-rookie-of-C-language <[email protected]>
content-visibility: auto on <details> kept collapsed Thinking blocks from expanding in WebKit; details elements are now excluded from the off-screen layout skip.
Co-authored-by: dimassfeb-09 <[email protected]>
Archived agent tasks could be opened but never returned to the active list, so their message composer stayed disabled. Unarchive is now available in the task header, in the archived-task notice above the composer, and in the task context menu (including mixed bulk selections). Restoring a task moves it back to the active list, keeps its conversation and worktree, and reconnects the existing agent session on the next message; the backend persists and broadcasts the restored status and refuses restoration while a stopped turn is still settling.
Select gains an optional search box that filters its options; the agent model pickers use it, so long model lists can be filtered instead of scrolled. Keyboard navigation and type-ahead work on the filtered list, and the popup keeps its width while filtering.
Co-authored-by: dimassfeb-09 <[email protected]>
In the agent composer, an @ query starting with ../, ./ or / lists the contents of the directory typed so far (through path_completions) instead of searching the project file index, so files outside the project can be referenced. Picking a folder inserts @dir/ and keeps completing inside it; picking a file inserts @rel, resolved to an absolute path when sending. Typed paths resolve against Windows project roots as well, keeping the drive.
Opens .ipynb files in a native notebook editor, in a project or LightEdit.
- crates/ide-notebook: lossless nbformat documents (unchanged notebooks save byte-for-byte, unknown fields kept, external changes detected) and owned local kernels over ZMQ via kernelspec — the selected Python environment only needs ipykernel, no Jupyter server.
- ide-host owns notebook documents per project incarnation and admits one execution batch at a time; outputs stream over IPC channels and kernel status is an IdeEvent.
- src/features/notebook: virtualized Python/Markdown cells, insert/delete/move/change type, Run Cell / Run All (Shift+Enter), interrupt, restart, interpreter selection from ide-sdk discovery, shared split views. Raw/unknown cells stay read-only.
- Custom editor kinds take part in dirty state, save/save all, undo/redo and Save/Don't Save/Cancel; closing editors from other features awaits that decision.
- Outputs: text, tracebacks, PNG/JPEG and sanitized SVG inline; HTML sanitized in a sandboxed iframe without allow-same-origin; JavaScript output is shown as inert source.
- Explicit launches (opening a notebook from the OS) win over session restoration.
Closes#131
Co-authored-by: dvictor357 <[email protected]>
When Claude Code loses its API connection or is refused, it retries on its own
for up to several minutes. The session showed only "Working…" meanwhile. It
now shows "API request failed, retrying in Ns (attempt 3/10)" with the error
in the tooltip, cleared by the agent's next output or the end of the turn.
Agents can run through native drivers or any ACP agent, speak ACP v1 or v2, and be installed from the ACP Registry. Tasks gain fork, in-place edit-and-rerun, steering and usage-limit handling where the agent supports them.
- Native Claude Code (`claude` stream-json) and Codex (`codex app-server`) drivers, each served to the task machinery as an in-process ACP shim, using the newest install on PATH.
- ACP v2 with v1 fallback, negotiated on initialize; per-agent capabilities (fork, rollback, steer) so the UI only shows supported actions; usage-limit errors put the task in a `limited` status with the reset time.
- Settings › Tools › Agents lists Registry agents (featured first) to install, update and remove; installed agents update when a project opens. "More agents…" in the provider picker opens it. Registry index and downloads are HTTPS-only, release archives are checked against their sha256, and entries without one show "No checksum provided" and ask for confirmation before installing. Package names from the registry can't be passed as options to npm/uv.
Claude-Session: https://claude.ai/code/session_01Dq6jQQn8ZhRfkkyj3PRutA
Root cause: once a project was open, nothing outside the Project view handled files dropped from the OS, so drops onto the editor, tabs or other tool windows were ignored.
A window-wide handler now opens dropped files in the editor (one tab each, last one focused, files outside the project included) and opens a dropped folder as a project through the open-project policy. Regions that handle drops themselves (Project view, agent prompt box) are marked with OWNS_FILE_DROP and hit-tested, so each drop has a single handler; the Welcome screen and remote windows are left alone.
Switching between agent session tabs in the editor now moves the Agents
tool window's selection to that task, expanding its group (e.g. Archived)
when it is collapsed. The list also opens with the active session selected.
Tabs of other kinds leave the selection as it is.
The editor service gains activeInput() and onActiveInputChange() so
features can follow the active tab of any kind.
Run oxfmt once over the whole repository (formatting only, no logic changes) and add `pnpm format:check` to the frontend CI job so unformatted code no longer builds up. `.oxfmtrc.json` now skips the generated theme docs, test fixtures and code blocks inside Markdown.
Co-authored-by: jaw52 <[email protected]>
Dragging the bottom tool window edge over a terminal refit xterm on every
pointer move and sent each intermediate size to the shell, which redrew its
prompt every time. Terminals now refit at most every 100 ms while their host
keeps resizing, plus once when it stops, and the process only learns the size
once it has held for 150 ms. This covers the Terminal tool window and terminals
embedded in Run consoles.
Resizing the width of an agent conversation reflowed every entry, including the
off-screen ones (14-16 ms per move in a long session). Entries now use
content-visibility: auto, so only the visible ones are laid out.
When a list item's text was followed by a nested list and a selection ended at
the end of that text, WebKit painted a thin strip of selection from there to the
right edge. The text of such items now gets its own block.
* feat(agents): Show subagents as their own conversations
Agents that support ACP subagent sessions (Claude Code, Codex) now run each
subagent as a child session. Its tool calls and messages no longer mix into
the task's conversation: the parent shows a card per subagent with its state,
tool call count, latest step, task and result, and the card opens the
subagent's own conversation.
- Route session/update by session id; subagent settings and usage stay out
of the task.
- Subagent permission requests are answered in the task's conversation,
named after the subagent.
- Subagent conversations are saved with the task; a running subagent is
marked stopped after a restart.
- A running subagent can be stopped on its own.
* fix(agents): Save a subagent's state when it changes after the turn
* fix(agents): Leave changes made before a local checkout task out of its changes
A task in the project's own checkout listed every uncommitted and untracked
file as its own. The files already changed when the task starts are now
recorded with their size and modification time, and drop out of the task's
changes until they are edited again.
* feat(agents): Show the current branch for a local checkout task
Hard-coded UI text, titles and aria-labels in about 110 components (Git panels, hierarchy, pull requests, dialogs, settings, welcome) now go through tx; spliced fragments became whole sentences (fileCount, noneFoundLabel, hierarchyTitle) and pull request states use keyed messages. 225 zh entries added, stale fragment entries removed.
Also: tx used as a tag without interpolations (tx`No checks`) now looks the text up exactly instead of as a template, so it is translated like tx("No checks"); the text-catalog test checks such tags as plain literals. Check and test counts reuse the existing "{count} passed" / "{failed} failing" entries.
Claude-Session: https://claude.ai/code/session_01VUYsdXA2nkF5v6zsC93dpn
Co-authored-by: jaw52 <[email protected]>
A local-checkout task shows the repository's current branch in its header, and
Changes compares against it; both follow branch switches. The header also shows
the time the agent has spent on the task's turns.
A usage update without a cost (Claude sends one for its rate limits) no longer
clears the session cost.
- Agents sits right after Project on the left stripe.
- The separator between a stripe's primary and split windows only shows
while a button is dragged, as a drop target.
- "Show tool window names" is off by default: stripes start at their
narrowest width with icons only.
* feat(agents): Select, copy, quote and search the conversation
- Conversation text can be selected and copied.
- Selected text gets a Quote button that replies to it in the composer.
- Messages have Copy on hover; your own messages also have Edit and
Resend and Send Again.
- Code blocks are highlighted and have a Copy button.
- File paths in replies (`src/lib.rs:12`) open in the editor when the
file exists.
- Find in Conversation (⌘F / Ctrl+F) highlights every match and steps
through them, opening collapsed tool output.
- Jump to Bottom appears after scrolling up.
- Your messages show when they were sent and how long the agent took;
a running turn shows its elapsed time.
* feat(agents): Quote a selection from the context menu
* feat(agents): Drop Jump to Bottom from the conversation
* feat(agents): Drop the hover Copy button from agent messages
* fix(agents): Highlight only the find matches on screen
WebKit paints a highlight range inside a collapsed tool output over the
text next to it. Matches in collapsed output still count, and stepping
to one expands it.
* fix(agents): Repaint find highlights as the search changes
WebKit doesn't repaint where a replaced highlight object was, so matches
of an earlier search stayed painted; each highlight is now one object
changed in place.
The new-task composer only offered the slash commands the agent sent in its last session, stored once globally, so a project that hadn't run a session (or whose last session ran elsewhere) showed none of its skills; matching was substring-only, so `/trig` didn't find `/triage` either.
Offered commands are now remembered per project root. For Claude Code, skills (`.claude/skills/*/SKILL.md`) and commands (`.claude/commands/**/*.md`) are also discovered on disk, from the working directory up to home plus `~/.claude`, and merged with the agent's list (agent entries win). New `agent_commands` IPC serves the home composer (project root) and session composer (the task's cwd). Matching ranks prefix (also after `plugin:`), then substring, then subsequence. Picking a completion inserts `/name ` and the prompt is sent unchanged.
Not covered: a new worktree of a project that gitignores `.claude/` doesn't contain the project's skills.
Claude-Session: https://claude.ai/code/session_01VUYsdXA2nkF5v6zsC93dpn
About 270 UI strings were JS template literals with interpolation passed to exact catalog lookup, so they could never be translated; about 25 more spliced lowercase English fragments into sentences.
`tx` now also works as a template tag (`` tx`Remove data source '${name}'?` ``): it looks up the entry by the literal parts (`{name}` placeholders), translates interpolated values that have entries, and remembers generated text so it re-translates after a language switch or when the catalog loads later. Call sites use the tag; spliced fragments are written as whole sentences per variant. Adds 280 Chinese translations and removes stale ones.
The catalog guard now also fails on untagged template literals reaching exact lookup (unless allowlisted with a reason), tagged text missing from the catalog, case-changed or ternary-suffix interpolations, and duplicate template patterns.
Claude-Session: https://claude.ai/code/session_01VUYsdXA2nkF5v6zsC93dpn
- Enter that commits an input-method candidate no longer sends the message.
- The composer turns off autocorrect, autocapitalisation and spellcheck, which
popped up correction bubbles over prompts.
- The provider icon in the task header sits inline with the details instead of
on its own line above them.
## What
An Agents feature: hand a task to a coding agent and follow it from the IDE. Agents speak the [Agent Client Protocol](https://agentclientprotocol.com). Built in: Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, OpenCode, Qwen Code, Kimi CLI, Goose, Auggie, Kiro, Mistral Vibe. You can add your own in `<config>/agents/<id>.toml` (`name`, `command`, `args`, `[env]`). An agent whose command isn't on `PATH` is listed under "Not installed".
- **New Task page.** An editor page with a prompt box. You pick the agent, model, mode and thinking effort, and whether it runs in a new worktree (from a chosen branch) or in the checkout.
- **Agents tool window.** Tasks are grouped by what they need: Needs Input, Failed, Running, Ready to Review, Archived. It also shows a stripe badge, a status bar item and notifications.
- **Session tab.**
- The conversation: Markdown, thinking, tool calls with diff stats, the plan.
- Permission requests appear as an editor banner.
- The changed files are compared against the task's base commit and open in the diff viewer.
- A context-usage meter.
- **Composer.**
- `@` references files from the project index. A referenced file's text is sent when the agent accepts embedded context, otherwise a `resource_link`.
- `/` lists the agent's commands; ↑/↓ recall earlier messages.
- Images can be pasted, dropped or picked; Shift+Tab cycles the mode.
- While the agent works, Enter queues the message and ⌘↵ interrupts the turn and sends it now. Queued messages can be sent now, edited or removed.
- **Send to Agent.** In the editor and Project view context menus. It adds `@file:10-20` references to the message you typed last.
- Landing the work is left to the existing Git features: the worktree is a normal branch.
## How
- **`crates/ide-agent`**: one ACP agent process per task, running in the task's directory.
- It folds `session/update` into a timeline and answers `session/request_permission`.
- It tracks the session's settings: `configOptions`, falling back to the older `modes` / `models` fields. The user's choices are applied again on every new or reloaded session.
- Tasks are saved as JSON per task. Sessions resume with `session/load` without duplicating history, and old task files are upgraded when read.
- **`ide-jsonrpc`**: adds newline-delimited framing (ACP) next to Content-Length (LSP).
- **`ide-vcs`**: adds `numstat_with_worktree` for the changes list.
- **Editor**:
- The Switcher (⌃⇥) lists every open editor, as IDEA does, not just files.
- `EditorKindContribution.restorable` lets a kind's tabs be saved with the editor session, so agent tabs survive reloads.
- **UI**: `Select` popups now size to fit short option details (they used to cut them off).
## Testing
- `cargo test -p ide-agent` (14 tests). They use an in-memory ACP agent and cover permissions, restart with `session/load`, settings, the queue with send-now and stop, and prompt blocks.
- There is also an ignored end-to-end test against the real Claude Code adapter: `OPENIDEA_AGENT_E2E=1 cargo test -p ide-agent real_claude -- --ignored`.
- `pnpm vitest run`: 2052 tests.
- `cargo clippy -p ide-agent -p openidea --all-targets -- -D warnings` and typecheck are clean.
- Driven in the running app with Claude Code:
- A task in a worktree, with permission answers, changes listed and the diff opened.
- A follow-up after restarting the IDE.
- `@` reference with embedded content, `/` commands, Shift+Tab mode changes.
- A queued message and send-now, an image prompt, Send to Agent from a selection.
- The Switcher and restored tabs after a reload.
Not covered yet: only Claude Code was driven end to end. The other agents go through the same ACP path but weren't run here.
Merged on the maintainer's go-ahead. Merge with main: kept both sides in Cargo.toml (ide-agent + ide-clipboard), the feature registry (agents + vim) and zh.json (no duplicate keys). After the merge: typecheck clean, full vitest 268 files / 2247 tests passed, ide-agent/ide-jsonrpc/ide-vcs 144 passed, bindings unchanged after regeneration.
l0ng-ai
arookieofcтаa-rookie-of-C-language
DIMAS FEBRIYANTO
arookieofcтаa-rookie-of-C-language
Dimas Victorтаdvictor357
Jaw