* fix(agent): don't release an idle native agent while background tasks are running
A turn's background tasks (Claude Code's run_in_background commands) outlive
the turn: release_when_idle only checked for a running turn and open
permission requests, so five minutes after the turn ended it stopped the
agent process and orphaned whatever still ran, its result never reaching
the conversation.
Claude Code reports its live background tasks in stream-json mode: a
system/background_tasks_changed event carries the full list on every
change. The driver now translates it into an openidea_background_tasks
session update (like openidea_retry), the task keeps the list, and the
idle release waits while it isn't empty: it checks again after the usual
delay, and when the last task is done its report voids the pending
schedule and starts the delay over from then. A (re)started process
starts with no tasks, so a stale list can never hold the agent up.
Signed-off-by: Inf1mum <[email protected]>
* feat(agents): show the agent's background tasks above the composer
A grey bar above the composer lists what the agent runs in the
background (shells, monitors), with how long each has been running and
a Stop button per task. The task now carries the background tasks the
agent reports, with when each was first seen, and clears them when the
process ends. Stop asks Claude Code to end that one task through a new
_openidea/stop_task request; the composer's Stop keeps ending only the
turn (perTaskStopAffordance).
Closes#1788
---------
Signed-off-by: Inf1mum <[email protected]>
Co-authored-by: Inf1mum <[email protected]>
Co-authored-by: NealimeKenna <[email protected]>
Agent task tabs now stay mounted while another tab is active (the five most
recently used per pane). A hidden one skips rendering with
content-visibility: hidden, which keeps its layout and scroll offset, so
showing it again costs a few milliseconds instead of building and laying out
the whole conversation. Hidden tabs don't mark their task read and close Find.
Thinking blocks and tool output now sit in a wrapper that skips off-screen
layout like other entries; on <details> itself WebKit wouldn't expand them,
so they were laid out in full on every resize and reopen.
A permission request line kept the title, "Waiting for your answer" and the answers on one row, so in a narrow agent conversation a long command title squeezed the answers until they were cut off. Title, state and answers now wrap next to the icon: a long title takes its own line and the state and answers go below it, in line with the title.
The meters were fixed-width and the header didn't clip, so in a narrow
conversation the stop, terminal and changes buttons spilled over the
Changes pane. The title now shrinks first, meters that don't fit drop
out whole, and the buttons keep their size.
- One composer button shows the model and its effort; its popup has the searchable model list and a stepped effort slider over the levels the agent advertises.
- With an on/off permissions option (Allow All), the mode menu carries it as a switch, and new tasks start with it on like the other bypass settings.
- Recognise ACP session-mode URIs when picking mode icons.
- The Stop action in a running session is an icon button.
Agent conversations: an editor tab mounts only while it is active, so switching back to a
task rebuilt the whole conversation, parsed and sanitized every message again, and fetched
all entries again, which replaced them and rendered everything a second time. Loaded entries
are already kept current by the task's events, so they are no longer fetched again; rendered
Markdown is cached by text; and a conversation opened at its end renders its last 40 entries
first and the earlier ones in batches behind it (all at once when a scroll position or Find
needs them).
Git log: with branch-aware layout (#1076) a commit's lane was its branch's global layout
index, so a repository with many branches drew lanes dozens of columns apart, joined by
diagonals across the row. Each row boundary and node level is now packed side by side in
layout order; adjacent rows share their boundary, so lines stay joined. The column header row
is hidden by default and can be shown from View Options › Columns › Column Headers, where
columns are resized and reordered.
Closing Settings while an ACP Registry agent was installing cancelled the install, and Install was offered again while a previous attempt could still hold the agent's folder. Installs now outlive the page as a background task of the project windows (stoppable from the status bar); the backend refuses a second install of the same agent and marks it installing in the list, which a reopened page follows until it ends.
Fixes#1430
The read-only previews beside Problems, Show Usages and TODO results are syntax-coloured from one whole-file parse (capped for very large files), so a line inside a block comment or a multi-line string is coloured as such; the pane renders plain first and recolours when the parse lands. SourcePreview takes the colouring as a colorize prop (the editor's previewColors), keeping src/ui free of editor imports, and the tok-* colours live once in global.css instead of a copy per view, with the theme's comment style.
Co-authored-by: qtvbwfn <[email protected]>
Agent replies only styled paragraphs, lists and code, so tables, headings, quotes, rules, images and task lists fell back to browser defaults: a 26px h1, a quote indented 40px, table columns squeezed to a few letters by overflow-wrap. They now get chat-sized styles from tokens; wide tables scroll sideways.
Closes#1273
Co-authored-by: ntbang0901 <[email protected]>
Markdown from comments, hovers, agent replies and files renders into the IDE's own document, so a raw <style> restyled the whole IDE and <form> / style= reached the page. Every Markdown sanitizer (LSP hovers and comments, agent messages, Markdown preview) now forbids <style>, <form> and the style attribute; agent messages also drop data-* written in a reply, since their click handlers trust data-copy / data-path. align, width and <details> stay.
Closes#1319
Co-authored-by: ntbang0901 <[email protected]>
For a folder that isn't a repository, the current-branch query answers with a repository found below it, so the New Agent Task page read "<folder> on <branch>" although the agent runs in the folder itself and the branch couldn't be changed. The branch is now shown only when the project is a repository.
Folders now appear in the composer's `@` completion next to files, from a new
`find_dirs` index query over the folders that hold indexed files (kept
incrementally in the index, ~0.5 ms on 100k files). Enter or a click
references the folder as `@dir/` and sends it as a resource link; Tab keeps
completing inside it.
Closes#1202
Icon themes could only map files by exact name or extension and folders by name. Themes can now match by regular expression or path (patterns that could backtrack badly, lookaround, inline flags and named groups are refused at install), ship dark variants, replace built-in UI and symbol (PSI) icons, and offer packs (groups) and variants (choices). A theme describes its own options page in Settings › Plugins as sections of items naming options the IDE implements (hide file/folder/UI/PSI icons, hollow folders, accent, monochrome, saturation, opacity, icon size, row height); values are stored per theme in appearance.fileIconThemeOptions. Existing themes are unchanged.
Closes#1096
Co-authored-by: pdasilem <[email protected]>
A pending agent question / permission request could only be answered from the banner at the top of the session; the conversation line said "Waiting for your answer" with nothing to click. The line now offers the same answers, and a request without options gets Cancel in both places so the agent isn't left waiting.
Fixes#1148
Settings › Tools › Agents › Built-in has an Environment variables field under the executable. They are saved in the agent's file like a command override, and the agent starts with them on top of the shell environment, replacing variables of the same name. Changing the command or the environment keeps the other; a file left with only the built-in's values is removed.
Closes#1133
CI / Rust (ubuntu-22.04) (push) Failing after 1h0m11s
CI / Remote server (linux musl) (push) Failing after 34m34s
CI / Plugins (SDK, official, fixtures) (push) Successful in 6m55s
CI / Cargo deny (push) Successful in 1m32s
CI / Frontend (push) Successful in 26m39s
CI / E2E (push) Failing after 19m40s
CI / Rust (macos-latest) (push) Canceled after 0s
CI / Rust (windows-latest) (push) Canceled after 0s
The permission banner kept its text on one line, so an agent's question (Claude Code's AskUserQuestion arrives as a permission request) was cut off and its answers crowded into the rest of the line. The question now wraps and scrolls past a third of the editor's height, and the answers wrap after it; permission lines in the conversation show up to three lines with the full text as tooltip.
A task's agent process lived until the task was archived or the project closed, and stopping it killed only the direct child, so wrappers (npx, codex.cmd, claude shims) left the real agent running. Agents that support session/load are now stopped after 5 minutes idle and restarted with the session reloaded on the next message; agent connections, language servers and the native Claude CLI start in their own process group and are stopped with their whole tree.
New tasks run in the local checkout unless the user picks a worktree, and worktrees go next to the project (<parent>/<project>.worktrees/<task>), on the project's drive and outside its tree.
Fixes#1011Fixes#1003
Claude Code reports the account's 5-hour and weekly usage limits (rate_limit_event) and the session cost (result.total_cost_usd); only the limit status was used. The limits now show as meters next to the context meter in the task header, with the reset time in the tooltip, and Settings › Tools › Agents › Chat turns each meter (context, work time, limits, cost) on or off. Limits are per provider and kept in memory; cost is off by default.
Closes#1057
Co-authored-by: matthiasdemauroy <[email protected]>
- List rows are no longer text-selectable. Settings pages enable text selection
for their content, and the shared List inherited it, so dragging or ⌘A
highlighted every row.
- An agent missing from PATH is shown as a muted row with a small "Not found"
label instead of an orange warning badge; a custom executable gets an accent
"Custom" label.
- The details header puts the status (with a status dot) and the launch command
on one line.
- Reset only appears when a custom executable is set.
- The sign-in hint gets its own "Sign in" heading.
- The list/details frame sizes to its content instead of filling the page.
Settings › Tools › Agents is split into Built-in and ACP Registry tabs. The Built-in tab lists every built-in agent with its status (custom executable or not found on PATH) and, for the selected agent, its default launch line, an Executable field (empty = auto-detect on PATH) with Browse and Reset, and its sign-in hint. Edits are staged with the Settings dialog and written on Apply / OK; Cancel discards them.
The override is written to <config>/agents/<id>.toml, keeping hand-written name, driver, args and env; resetting a command-only override removes the file. AgentProvider now exposes the program, args, built-in defaults, login hint and whether the command is editable: built-ins started through a package runner (npx) and registry installs are read-only, with the reason shown.
Fixes#596
Co-authored-by: a-rookie-of-C-language <[email protected]>
GitHub Copilot, Qwen Code and Mistral Vibe were listed in the ACP Registry under their registry ids (github-copilot-cli, qwen-code, mistral-vibe), so they showed as unrelated third-party agents and could not be installed over the built-in providers. Registry ids now map to the built-in ids: the rows use the built-in name and icon, install and update into <config>/agents/<id>.toml, show "x.y.z available" when the registry has a newer version, and fall back to the built-in command on PATH after Remove. Installing never overwrites a hand-written agent config, and Remove only deletes a registry install. Changing installed providers reloads them and drops stale probes, so New Task sees the installed version right away.
Co-authored-by: dengliu <[email protected]>
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
Vadim Lazuk
l0ng-ai
Deng Liu
Qingтаqtvbwfn
ntbang0901
Sergei Melnikov
matthiasdemauroyтаmatthiasdemauroy
arookieofcтаa-rookie-of-C-language
DIMAS FEBRIYANTO
arookieofcтаa-rookie-of-C-language
Dimas Victorтаdvictor357