A diff is ordered by file path, which is almost never the order in which a
change makes sense. This adds a Walkthrough surface that reorders it: the model
groups related hunks into stops, explains what each group changes about
behavior, and orders the stops so each builds on the last. It explains and
orders; judging code stays with the existing Review action.
Reviews uncommitted work (all, staged, unstaged), a branch against its base, or
a pull request. Generation is always user-initiated — nothing runs on a timer,
on a file change, or as a side effect of opening a panel.
Invariants worth preserving:
- Hunk identity is derived on the server and only there. Ids are content
hashes, so an anchor that no longer resolves is proof the code it described
changed, and staleness needs no heuristics. The client matches ids to ids and
never recomputes them; two implementations would have to agree forever.
- The digest is never truncated. A diff that does not fit the model's context
is refused with an actionable reason, because a walkthrough written against
half a diff reads as confident and is wrong.
- Nothing disappears. Lockfiles and other generated output are excluded from
the model's input by name — never by size — and everything no stop covers is
listed at the end, so "have I seen all of it" stays answerable.
- Cost is explicit. Results are content-addressed, so returning the working
tree to an earlier state costs nothing; generation outlives its request, so a
refresh detaches the client rather than discarding paid-for work, and only an
explicit cancel stops it.
Supporting changes to shared modules:
- git: expose the existing getRangeDiff as GET /api/git
listUntrackedPaths and getUntrackedDiffs. The latter resolve the repository
once for a batch instead of per file, taking a panel
~340ms on an 80-file working tree.
- small-model: structured output across four wire forma
and abort signal, and an onOverflow policy so an oversized prompt fails
loudly instead of being silently clipped. A provider
remembered so the prompt-side fallback goes first next time.
- models.dev metadata: surface structured_output as tri
false blocks a model, a missing field does not, because the catalog omits it
for roughly half of all models.
Desktop and tablet only: VS Code serves Git through its
these routes, and the mobile shell does not consume the surface registry.
Docs: packages/docs walkthrough page in English and all eight locales.
Add an opt-in OpenCode plugin that replaces the built-in provider behavioral prompt with a minimal identity while preserving environment, project, MCP, skill, history, and tool context.
Track the active agent per session and apply the transform only to build and plan. Keep plan/build mode reminders and permission enforcement owned by OpenCode, leave all other agents untouched, and fail safely when the expected prompt boundary is absent.
Expose the feature in Behavior settings with localized guidance, explicit Save + Reload application, settings search integration, persisted boolean validation, and managed-runtime lifecycle composition that does not load the plugin while disabled or on external OpenCode servers.
Document the runtime contract and cover plugin materialization, config preservation, build/plan selection, agent switching, unknown prompt formats, and settings sanitization.
Left-side controls now use macOS traffic-light order (close, minimize,
maximize). Remove the unused auto option and default window controls to
the right for Windows and Linux frameless chrome.
Authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
Persists draft starter visibility across desktop and web settings
Adds a new OpenChamber visual setting with localization and search support
Hides the draft starter chips when the setting is off
Add a shared OpenChamber control service with two thin adapters — a native
`openchamber` tool injected into managed OpenCode, and new CLI commands — so
users can manage parallel sessions, worktrees, and scheduled tasks
conversationally through agents or from the terminal.
Control plane:
- New openchamber-control service owning a fixed action contract:
projects.list, models.list, session list/create/send/fork/status/messages,
and schedule list/create/run/delete/toggle. Session and worktree deletion
and project registration are deliberately not exposed.
- New openchamber-sessions module owning create/worktree/prompt orchestration,
Goal Mode dispatch, wait semantics (initial idle never counts as completion;
timeout and cancellation are failures), and explicit partial-failure results.
- Scheduled-task logic extracted into a service shared by routes, CLI, and the
agent tool.
Agent tool:
- Managed OpenCode gets a materialized plugin registering one typed tool with
a loopback-only callback, per-child ephemeral bearer (timing-safe, never
persisted or logged), and abort propagation into the service.
- The ~1.5k-token schema applies progressive disclosure: short descriptions,
server-side validation returning actionable usage errors, and intent
guardrails — created sessions/tasks are user-facing work (not age
self-delegation); worktree/goal/agent/variant/wait are omit-by-default;
dispatches produce no completion notification, and later result r
to session.messages, which now returns the authoritative sessionStatus.
- session.create without a user-named model picks from favorites/re
send/fork omit the selection and the service reuses the target session's
last user-message model, agent, and variant before falling back t
- An "Agent control tool" setting (default on, Save + Reload to apply)
disables plugin injection entirely.
CLI:
- New `openchamber session`, `schedule`, `projects`, and `models` commands
with automatic instance targeting, --wait/--timeout/--last-assist
worktree flags, and Goal Mode, preserving interactive, non-TTY, --quiet,
and --json contracts. The control HTTP timeout derives from the w
instead of the 4-second default.
UI:
- New built-in "Schedule a Task" starter (/schedule-task) running a
dialogue that defines a task and offers to create it via the tool after
explicit confirmation; Craft a Goal and Feature Planning gain the
handoff offer, and guided starters reserve the question tool for concrete
option choices. Localized in all 10 locales, migrated into custom
starter lists, hidden on VS Code.
- Sidebar shows CLI/agent-created sessions live via the control eve
- openchamber tool calls render with per-action titles and metadata.
Adds a General settings switch to show or hide the macOS menu bar item.
Persists the new desktopMacMenuBarEnabled setting and passes tray state into Electron.
Disables tray sync and native tray setup when the menu bar is turned off.
Improve OpenChamber responsiveness under large session workloads while fixing
cache, synchronization, and persistence correctness across runtimes, projects,
directories, and worktrees.
- prioritize selected and visible sessions during bootstrap and defer
non-critical enrichment work
- reduce redundant message loading, event processing, store publication, and
hidden sidebar work
- prevent stale session and message requests from overwriting newer
authoritative state
- preserve existing data when authoritative fetches fail instead of treating
failures as successful empty responses
- scope session materialization, messages, drafts, queues, todos, pins,
permissions, folders, tabs, Git state, and pull request data by runtime and
directory identity
- harden runtime switching, reconnect, cleanup, mutation reconciliation, and
persisted-state ordering
- preserve live subagent Task linkage when metadata arrives after an older
message request or while streaming parts are suspended
- coalesce overlapping tail refreshes without losing newer refresh demand
- improve cold-session loading by moving deferrable work out of the critical
bootstrap path
- isolate URL authentication, mobile credentials, native secrets, and other
runtime-owned state across endpoint changes
- bound long-lived caches and remove avoidable allocations from event and
rendering hot paths
- limit virtualization to archive collections where it improves rendering
without disrupting active sidebar layout
- stabilize session folders, pin ordering, expanded state, and persisted
sidebar behavior
- open skill files through the same secure editor and outside-workspace grant
flow used by file navigation, including worktree sessions
- expand regression coverage for stale completions, runtime collisions,
reconnect behavior, persistence races, authoritative empty results, and
subagent refresh ordering
- document the updated synchronization, cache ownership, performance, and
runtime-isolation invariants
Replace the legacy terminal flow with a shared authenticated WebSocket
runtime used across web, desktop, relay, and mobile surfaces.
- introduce the v3 terminal protocol with scoped attachments, snapshots,
ordered output, bounded replay history, reconnects, and explicit lifecycle
- harden PTY creation, restart, resize, close, force-kill, idle cleanup,
shell selection, login mode, environment sanitization, and appearance sync
- add runtime-aware terminal APIs with relay authentication and Electron parity
- add a fullscreen mobile terminal workspace with touch scrolling,
long-press selection, safe-area controls, quick keys, and Ctrl/Alt input
- add terminal selection attachments, preview detection, project actions,
shell settings, and localized UI
- harden Ghostty rendering, resize recovery, Unicode handling, block
characters, line height, and stale-row behavior
- remove the obsolete terminal SSE path and update reverse-proxy guidance
- expand terminal runtime, transport, input, selection, and store coverage
- avoid duplicate web builds when preparing mobile assets in root CI builds
* feat(chat): add desktop prompt navigator rail
Add a ChatGPT-style right-center prompt marker rail for web/desktop chat
with hover/keyboard preview panel, load-more for partial history (panel only),
Chat setting, and mod+alt+p shortcut. Disabled in VS Code across rail,
shortcut, settings, help, and search surfaces.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
* fix(ui): read promptNavigatorEnabled from getState in shortcut handler
Match the file convention used by other shortcut handlers so the toggle
does not rely on a hook-level selector closure.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
* fix(ui): drop use-no-memo and default prompt navigator off
Remove the project-unprecedented React Compiler opt-out, and ship the
prompt navigator as opt-in to match other recent chat UI toggles.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
* feat(electron): add Linux AppImage releases
* ci: cache Linux OpenCode CLI artifacts
* fix(ci): await Linux release inventory check
* fix(electron): add frameless window controls on Linux desktop
Linux AppImages were created without native WM decorations and without
in-app controls, leaving users unable to close the window with a mouse.
Treat Linux like Windows: frameless BrowserWindow plus the existing
WindowsWindowControls header buttons and app-menu entry. macOS keeps
hidden title bar with traffic lights unchanged.
Shared usesFramelessElectronChrome() helper drives main window, mini
chat, header insets, and titlebar controls.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
* feat(desktop): add configurable window controls position by OS
Add desktopWindowControlsPosition setting (auto/left/right) with OS-aware
defaults: Linux left, Windows right. Wire frameless chrome controls in
Header, TitlebarLeftControls, and MiniChatLayout, plus a Sessions settings
control for Windows and Linux desktop shells.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
* fix(desktop): address Linux AppImage release review findings
Propagate updater capability errors to the UI, treat missing
latest-linux.yml feeds as no-update, stop installed-apps IPC spam on
Linux, document FUSE/AppImage limits, add CHANGELOG entry, migrate
remaining btriapitsyn URLs, and run Electron Linux unit tests on PRs.
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
---------
Co-authored-by: jibanez-staticduo <staticduo@gmail.com>
Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>
Move per-session permission auto-accept policy ownership from the UI to the
OpenChamber server so enabled sessions continue running when clients disconnect
or the server restarts.
- persist explicit per-session policies in OpenChamber settings
- inherit the nearest explicit policy across subagent session hierarchies
- allow child sessions to opt out of an inherited parent policy
- immediately accept matching global and directory-scoped pending requests
- process future requests without requiring a connected UI client
- reconcile pending permissions after startup and event-stream reconnects
- deduplicate concurrent requests and retry transient reply failures
- synchronize policy updates across connected clients
- migrate existing browser-persisted policies to server storage
- suppress auto-accepted permission cards before they enter UI state
- show deduplicated permission toasts for inactive sessions
- preserve foreground-only permission handling in VS Code
- integrate directory-aware notification routing from main
- add coverage for persistence, inheritance, retries, reconciliation, pending
requests, client hydration, and inactive-session toasts
Arm the target button in the composer and the next prompt becomes a goal:
the server keeps the session working toward it (idle tick -> small-model
audit -> continuation) until the objective is verifiably complete, blocked,
or out of budget — even with the UI closed.
Server (packages/web/server/lib/session-goal):
- event-driven loop on the global SSE hub; goal state lives in
session.metadata.openchamber.goal (merge-safe patches, stale-write guard
by goal id), so it survives restarts and syncs to every client for free
- the small-model audit (objective + last assistant turn only, language
pinned to the objective) is the sole termination authority; blocked needs
3 consecutive verdicts, audit outages tolerate one unaudited continuation
then stop the goal as resumable-blocked
- hard stops: optional token budget, auto-continuation cap (Resume grants a
fresh allowance), turn errors; user abort pauses the goal instead of
blocking it, and resuming over an aborted tail nudges immediately
- token accounting as a snapshot of the latest turn (input + cache.read +
output), goal-relative via a creation baseline and segmented across
compactions; a compaction summary skips the audit and continues
- continuations reuse the session's own provider/model/agent/variant
UI:
- three-mode target button (arm / disarm / manage dialog), informational
goal strip with inline pause/resume and an Evaluating indicator, sidebar
state glyph, objective length counter (2000-char server clamp),
read-only completed goals
- goal entry points: composer (sessions and drafts), start-new-session-
from-answer dialog, plan implement dialog (plan content becomes the
objective), scheduled tasks (Run as goal + budget)
- Settings -> Chat -> Goal: feature toggle + default token budget with
three-layer parity (web server, client persistence, VS Code bridge);
VS Code renders goal state but hides the entry points (the loop runs in
the web server only)
Notifications: per-turn "ready" notifications are suppressed while a goal
is active; settling sends one final notification (desktop, web-push, APNs
generic titles with the session name as body) honoring the completion
toggle. Error/question/permission notifications are untouched.
Docs: user guide (session-goals) in all 9 locales + sidebar entry,
scheduled-tasks cross-reference, server module DOCUMENTATION.md.
Add Windows launch-at-login with background startup support and extend the
native tray integration to Windows.
Add a Windows-only setting to minimize or close the main window to the
system tray, persist it through desktop settings, and expose it in Settings
search and all locale dictionaries.
Keep tray state synchronized with live sessions on both macOS and Windows,
while preserving the existing macOS behavior.
Adds a server-side "small model" capability: direct, cheap LLM calls that
reuse the user's existing OpenCode provider logins — the mechanism OpenCode
uses internally for titles and summaries but does not expose through the
SDK or plugins. Zero new dependencies; plain fetch with per-provider wire
formats, credentials never leave the server.
Core (packages/web/server/lib/small-model):
- Resolution mirrors OpenCode's session scoping: explicit settings override
→ small_model from the OpenCode config → family scan within the session's
provider → the session's own model. The global provider scan only serves
callers without a session context, and background callers forbid it
entirely (restrictToPreferredProvider), so conversation content never
reaches a provider the user didn't pick — explicit choices excepted.
- Per-provider auth replicating OpenCode's plugin loaders: GitHub Copilot
(device token as bearer, no exchange), ChatGPT plan via the codex
Responses API (single-flight OAuth refresh written back to auth.json),
Anthropic messages, Google generateContent, generic OpenAI-compatible.
- OpenCode's free models (opencode/big-pickle, *-free) are never called
directly; unauthenticated providers are skipped by design.
- Prompt clamping to the model's catalog context limit; thinking disabled
where a wire switch exists (Z.AI/GLM, MiniMax-M3, Gemini Flash); robust
content parsing with a clear error when a thinking model spends its whol
budget on reasoning.
- Settings → Sessions gains a Small Model group: use-default checkbox plus
an override picker limited to authenticated providers, persisted with
web/desktop/VS Code sanitization parity.
Consumers:
- Session assist: a server-side watcher on the global SSE hub generates a
short recap and one suggested follow-up after a session idles quietly fo
a minute, stored on session metadata (openchamber.assist). Freshness is
keyed to the last assistant message id, so new activity invalidates the
payload everywhere with no extra writes. The chat shows the recap under
the last message after five quiet minutes and the suggestion as a
dismissible chip above the composer (tap fills the input, never sends).
Gated by a new Chat setting (default on) that is a hard generation
switch. Language is anchored to the conversation itself, with a
script-mismatch guard against model/backend language hallucination.
- TTS: a third input mode, summarized — long replies are condensed to
spoken prose before playback on any TTS engine.
- Git: commit-message and PR generation moved off the active chat session
onto the small model fed with real diffs and the commit list (bodies
included), with a session-transport fallback for free-model-only setups.
- Notes: Add to notes distills long selections into 1-3 dense sentences
preserving exact identifiers, with verbatim fallback on failure.
Fixes along the way:
- The global event watcher now starts unconditionally; it was gated behind
the desktop-notify env, leaving the server-side event hub dead in
packaged apps.
- OpenCode re-emits message.updated for old user messages after idle; the
watcher no longer mistakes those for new activity.
- Session metadata merges from a fresh read right before the PATCH, so
writes made during the generation window (suggestion dismissals, review
links) are preserved; the assist runtime stops during graceful shutdown.
Complete rebuild of voice input on a server-authoritative streaming
architecture, replacing the legacy Web Speech / whole-blob / WASM engines
and the dead voice-agent layer (~4k lines removed).
Speech-to-text (dictation):
- Client streams 16 kHz mono PCM16 chunks over /api/dictation/ws with
seq/ack ordering; buffered audio is retained and replayed on reconnect
- Server transcribes and streams live partial transcripts back;
segments auto-commit every ~15s with silence suppression and adaptive
finalization timeouts
- Local provider (default, zero config): sherpa-onnx models in a forked
worker process — auto-download with progress, staged extraction with
verification, corrupt-model auto-recovery, idle shutdown after 5 min
- Model catalog with settings picker (accuracy/speed ratings, sizes,
download/delete): Parakeet TDT v2 (English) and v3 (25 European
languages, auto-detected), Whisper base and tiny (multilingual, light)
- OpenAI-compatible provider for any Whisper endpoint
- Composer overlay with live transcript, volume meter, timer, and
cancel / insert / insert-and-send actions; failed transcriptions keep
their audio for retry or accepting the partial text as-is
- Configurable keyboard shortcut (default mod+alt+v) toggles dictation;
Enter confirms and Escape cancels while recording
- Overlay is pixel-aligned with the composer (measured footer height,
matching paddings/typography/gaps) — no layout shift when toggling
Text-to-speech:
- Local Kokoro provider (English, 11 voices) synthesized in the same
worker via /api/dictation/tts/speak, managed by the shared model
pipeline; sentence-pipelined playback keeps time-to-first-audio at
~1 sentence regardless of message length, and stop cancels in-flight
synthesis
- Sanitizer keeps inline-code content (strips backticks only), reads
interword slashes aloud, and removes only absolute file paths
Settings:
- Voice page unified: a single read-aloud toggle owns all playback
options (the confusing "Enable Voice Mode" is gone); a new "Enable
voice input" toggle (default on, persisted to settings.json) hides
the composer mic entirely when disabled
Mobile and transport:
- iOS/Android microphone permissions added (dictation was previously
impossible on mobile)
- Fixed Android WebSocket upgrades: the Capacitor WebView origin
(https://localhost) was missing from the packaged-client allowlist,
403-ing every WS connection — root cause of the old mobile SSE lock,
which is now removed for all transports
Security and conventions:
- All HTTP routes sit behind the global /api auth gate; the WS upgrade
explicitly validates the UI session and origin, with oc_url_token
narrowly allowlisted and covered by tests; the dictation socket mints
a fresh URL token before connecting
- Routes register before the generic OpenCode proxy; the client goes
through runtimeFetch/getRuntimeUrlResolver, and runtime switches
reset the dictation socket
- VS Code deliberately reports dictation as unavailable (no server
process in that runtime)
CI: workflow Node bumped 20 -> 22 to match the repo engines and fix
better-sqlite3 installs broken by node-gyp@latest on Node 20.
New dependency: sherpa-onnx-node (prebuilt N-API; macOS/Linux x64+arm64,
Windows x64 — Windows-on-ARM falls back to the OpenAI-compatible provider)
* feat: support OpenCode steer delivery / follow-up behavior settings
Implements issue #1766 — steer delivery mode for mid-turn message
insertion, replacing the old boolean queue-mode toggle with a tri-state
follow-up behavior setting (Steer / Queue / Send immediately).
- Plumbing: threaded optional delivery: 'steer' through sendMessage
-> routeMessage -> opencodeClient.sendMessage -> promptAsync
- Store: messageQueueStore stores followUpBehavior; migration from
legacy queueModeEnabled persisted state
- Settings: Chat -> Follow-up behavior shows three radio options
using existing settings UI patterns
- Composer: when session is busy, a floating queue button remains;
force-sending a queued message (via chip click) uses delivery: 'steer'
during a busy session; Steer button intentionally omitted — steer is
available via the two-gesture path (Enter to queue -> chip to steer)
- Keyboard: queue mode = Enter queues, Ctrl+Enter sends; otherwise
Enter sends, Ctrl+Enter queues
- Persistence: DesktopSettings, web settings payload, and server-side
sanitizer handle the new key with legacy fallback
- i18n: follow-up behavior section and option labels in all 9 locales
plus new chat.chatInput.actions.queue label
- Search: settings registry updated from chat.queue-mode to
chat.follow-up-behavior
Validation: type-check passes (no new errors), lint clean.
* fix(#1766): make steer mode actually steer
The followUpBehavior === 'steer' branch in handlePrimaryAction and the
keyboard handler was a no-op — both fell into the else branch and sent
without the delivery: 'steer' flag, so selecting 'Steer (insert into
the running turn)' in settings produced identical behavior to 'Send
immediately'.
- handlePrimaryAction: when steer mode is selected and the session is
busy, call handleSubmit({ delivery: 'steer' }) directly
- Keyboard handler: in steer mode, Enter steers and Ctrl+Enter sends
immediately (consistent with queue mode where Ctrl+Enter bypasses
the special handling)
Also removes the unused chat.chatInput.actions.queue i18n key from all
9 locales (it was a dead key after the Steer button was removed from
the composer).
Validation: type-check clean, lint clean.
* refactor(#1766): flatten nested ternary in followUpBehavior resolution
Replace nested ternary with explicit if/else chain per project code style
(CONTRIBUTING.md). Import FollowUpBehavior type explicitly for the new
let declaration.
* feat(chat): drop redundant 'immediate' follow-up mode, keep Queue + Steer
'Immediate' was wire-identical to 'Steer' on a busy session: OpenCode only
supports delivery 'steer' | 'queue' and defaults to 'steer', so an immediate
send (no delivery flag) already steered into the running turn. The three-mode
UI therefore exposed two settings that did the same thing.
Collapse to two modes — Queue (unchanged: client-side queue with edit/reorder)
and Steer. Any persisted/legacy 'immediate' (and legacy queueModeEnabled=false)
now maps to 'steer', preserving prior behavior. Removes the immediate option,
its keyboard branch, the i18n label across all locales, and narrows the
followUpBehavior union to 'steer' | 'queue'.
---------
Co-authored-by: Leonid Skorobogatyy <bash@opencode.itc.local>
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
* fix(settings): persist per-model visibility and sibling selector state
The server-side settings sanitizer only allowlisted favoriteModels and
recentModels, so hiddenModels, collapsedModelProviders, recentAgents, and
recentEfforts were stripped on every write to settings.json — per-model
visibility and collapsed-provider state silently reset on every container
redeploy or settings reload.
Add the four missing fields to sanitizeSettingsUpdate:
- hiddenModels: sanitizeModelRefs(..., 1024) — same shape as favoriteModels;
1024 covers dense multi-provider setups while bounding persistence/memory.
- collapsedModelProviders: normalizeStringArray with Array.isArray gate
(matches usageDropdownProviders).
- recentAgents: normalizeStringArray (Array<string> per ui-store).
- recentEfforts: new sanitizeRecentEfforts validating Record<string, string[]>
(shape confirmed in ui-store + addRecentEffort action); trims/dedupes keys
and variants, caps at 128 keys x 5 variants/key (5 matches client slice).
No ui-store version bump or migration: zustand's default merge spreads
persisted state over defaults, so missing fields fall back to [] / {} until
the next toggle. favoriteModels and recentModels are untouched.
Tests: 8 new cases in settings-helpers.test.js using the real
sanitizeModelRefs / normalizeStringArray — round-trips, empty-[] parity with
favoriteModels, garbage rejection, and a full-payload regression test.
* fix: sync model selector settings
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
Packaged desktop showed no sessions in 1.12.4. Root cause: the sanitized
session-list proxy path added in #1538 forwarded the renderer's
"authorization" header (the OpenChamber UI client token) to the managed
OpenCode upstream alongside the managed "Authorization" credential.
OpenCode does not recognize UI client tokens, so every session-list
request answered 401 — only in the packaged app, because only its
renderer (openchamber-ui:// origin) attaches a bearer token; dev web and
dev Electron run same-origin without one. The legacy http-proxy path
overwrote the header correctly, which is why everything except session
lists kept working.
Proxy fix:
- proxy-headers: filter the client "authorization" header out of
forwarded request headers; the OpenCode upstream must only ever see
its own managed credentials. Covered by tests.
Desktop cwd:
- electron: launch the managed OpenCode CLI from the user home instead
of app userData, matching upstream desktop behavior. userData-as-cwd
made OpenCode treat the app-data folder as a separate empty workspace.
Home directory poisoning loop:
- directoryPersistence: stop replaying localStorage homeDirectory
through synchronizeHomeDirectory on boot/auth resync. The persisted
value is only a boot-time cache; replaying it re-wrote stale values
(e.g. a project path) into desktop settings on every start, overriding
the authoritative /api/fs/home resolution.
- persistence: never overwrite an injected window.__OPENCHAMBER_HOME__
with a persisted value.
- useDirectoryStore: host switches happen in place (no reload), so
re-resolve home from the new runtime's /api/fs/home on endpoint
change instead of keeping the previous host's value.
- opencode client: only short-circuit to the injected desktop home when
the active runtime is local; remote runtimes ask /api/fs/home.
Settings hygiene:
- persistSettings: log field names only — change payloads can carry
credentials (UI password, client tokens, tunnel tokens) that must not
reach the log file; drop step-by-step log chatter.
- validateProjectEntries: only stat project paths when the incoming
update actually touches the projects list, not on every settings save.
- remove the write-only approvedDirectories setting everywhere and add
a migration that strips the stale key from persisted settings.
Tests:
- usePluginsStore.test: register an own runtime-fetch module mock so the
suite is independent of process-global mock.module leakage from other
files, and restore globalThis.fetch after the suite.
- persistence.test: clean up the window global created for the suite.
Let users curate the draft welcome chips: pin existing commands and skills
as starters, remove them, and drag to reorder — all inline on the draft
screen via a '+' picker dialog and per-chip remove, with no separate
settings UI.
A starter references a command or skill; its scope is inherited from the
item (user-scope -> global, project-scope -> per-project). Global starters
persist to settings.json (useUIStore + client/server sanitizers); project
starters persist to the project config alongside worktree setup commands.
The two scopes form ordered namespaces shown global-first then project,
reorderable only within each group.
The six built-in Session magic-prompt commands are the default global set
and stay available in the picker for re-pinning if removed; they keep their
bespoke icons, while user commands/skills fall back to the Commands/Skills
section icons. Chip labels are normalized (/simplify-code -> 'Simplify
code'). Missing commands/skills are skipped rather than shown broken.
Drag-to-reorder works on desktop and mobile: rectSortingStrategy for the
wrapping multi-row layout, CSS.Translate (no scale) so the lifted chip
doesn't stretch, and MouseSensor + long-press TouchSensor so taps still
submit and swipes still scroll. The '+' picker is a searchable dialog on
every surface.
* feat: add collapsible reasoning traces with animated labels
* feat(ui): redesign reasoning blocks with merged collapsible Thought view
- Replace per-part reasoning blocks with a single merged block per turn
(VSCode Copilot pattern), controlled by new `groupReasoningBlocks` store flag
- `ReasoningTimelineBlock` redesigned: chevron toggle, summary preview on
collapsed header, 'Thinking'/'Justification' label when expanded, BusyDots
while streaming, auto-scroll to bottom during live streaming
- Short texts (< 120 chars) render inline without a toggle
- Summary now strips markdown and truncates at a word boundary with ellipsis
- New `MergedReasoningPart` component merges all reasoning parts for a message
into one block at the position of the first reasoning part
- `defaultExpanded` prop lets callers override initial expand state
- Remove `.thinking-dot` CSS animation (replaced by BusyDots component)
- Fix reasoning markdown font-size: use `--text-markdown` instead of `--text-meta`
* refactor(ui): scope working phrases inside useAssistantStatus and simplify reasoning status
- Move WORKING_PHRASES array and getRandomWorkingPhrase() inside the hook
so they are no longer exported (were only consumed by ReasoningPart which
no longer needs them)
- Change the 'reasoning' activity status text from a random working phrase
to the deterministic string 'thinking' — matches the new UI label
* test(ui): expand ReasoningPart tests for new collapsible and summary behavior
- Update baseline test to use text long enough to trigger the collapsible
path (short texts now render inline) and assert on the correct aria markup
- Add test for 'Justification' label when pre-expanded via defaultExpanded
- Add test for 'Thinking' label for the thinking variant when expanded
- Add test verifying summary is a word-boundary-truncated excerpt ending with
an ellipsis character
* i18n: rename 'Reasoning Traces' to 'Thinking Blocks' and add thought key
- Rename settings label from 'Show Reasoning Traces' → 'Show Thinking Blocks'
across all supported locales (en, es, ko, pl, pt-BR, uk, zh-CN)
- Add `chat.reasoningTrace.thought` key to all locales (used by merged
reasoning block header in completed state)
* feat(ui): add collapsibleThinkingBlocks setting with full persistence wiring
- New boolean store field `collapsibleThinkingBlocks` (default true) with
`setCollapsibleThinkingBlocks` action; persisted to localStorage
- Threaded through DesktopSettings, SettingsPayload (API types), desktop
persistence (sanitize + apply), web appearance persistence, appearance
auto-save watcher, and server-side settings-helpers sanitize/format
- Server defaults to true when the field is absent in formatSettingsResponse
- MessageBody reads the flag: false → render reasoning as plain AssistantTextPart;
true → existing collapsible/merged block path
* feat(settings): expose Collapsible Reasoning Blocks toggle in visual settings
Add a checkbox under the 'Show Thinking Blocks' row (visible only when
showReasoningTraces is enabled) that toggles the collapsibleThinkingBlocks
preference. Follows the existing toggle pattern: div role=button, keyboard
handler for Enter/Space, Checkbox primitive, aria-pressed attribute.
* i18n: revert showReasoningTraces label rename and add collapsibleThinkingBlocks strings
- Revert 'Show Reasoning Traces' → 'Show Thinking Blocks' rename (the
collapsibleThinkingBlocks toggle is now a separate control, so the parent
label stays as 'Reasoning Traces' for clarity)
- Add `collapsibleThinkingBlocks` / `collapsibleThinkingBlocksAria` strings
across all seven supported locales (en, es, ko, pl, pt-BR, uk, zh-CN)
* test(server): add settings-helpers coverage for collapsibleThinkingBlocks
- Verify sanitizeSettingsUpdate accepts boolean true/false and rejects
non-boolean values (string, number)
- Verify formatSettingsResponse forwards the value correctly for both true
and false, and defaults to true when the field is absent
* fix(ui): respect defaultExpanded prop and remove dead alwaysShowActions from ReasoningTimelineBlock
The useEffect on [isStreaming] was firing on mount and immediately calling
setIsExpanded(false) (since isStreaming is false for completed blocks),
overriding any defaultExpanded={true} passed by callers. The fix uses a
prevIsStreamingRef so the effect only collapses the block on a true→false
transition and is a no-op on initial mount.
Also removes alwaysShowActions from ReasoningTimelineBlockProps — the new
header design always shows the chevron, making the prop obsolete. The prop
was already absent from the component destructuring (a dead type entry) and
was silently ignored at runtime. Removed it from ReasoningPartProps,
MergedReasoningPartProps, and the two call-sites in MessageBody as well.
* chore: remove unused reasoningpresentation module and test
* fix(ui): polish collapsible reasoning block UI
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
- Add local Whisper STT via Transformers.js with Web Worker (no UI freeze)
- Default sttProvider to 'local' in Electron (browser STT unavailable)
- Fix infinite toast loop: stop auto-restart on network errors
- Add retry limit with exponential backoff for transient STT errors
- Append voice transcript to input field (append-inline), not replace
- Add model catalog with download/load button in Voice Settings
* feat: add 'Open files in preview mode' setting
- Add defaultFileViewerPreview setting to persist user preference for file viewer default mode
- Add checkbox in Settings → Sessions → Session Defaults to toggle the setting
- Files now open in preview mode by default when setting is enabled
- Respects per-file-type localStorage persistence for markdown/HTML/JSON files
- Setting persists across sessions via /api/config/settings endpoint
* fix: address PR review feedback
- FilesView: respect HTML localStorage preference in file-change effect,
falling back to global setting only when nothing stored
- DefaultsSettings: read defaultFileViewerPreview directly from config store
instead of redundant local state + separate fetch
- DefaultsSettings: extract duplicated toggle logic into
handleToggleFileViewerPreview callback
* fix: honor default preview setting for markdown files
Previously mdViewMode only read localStorage on mount (deps: []), so
when settingsDefaultFileViewerPreview was enabled and no MD_VIEWER_MODE_KEY
was stored, markdown files silently opened in edit mode — ignoring the
setting for the very file type users most want to preview.
Fold md init into the per-file-change effect, mirroring the html handling:
localStorage preference wins, falling back to the setting-derived default.
The saveMdViewMode callback stays untouched so user-initiated toggles
still persist.
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
* feat: keep desktop app running in background when closing last window
Closing last window hides it instead of quitting — sidecar keeps running
Cmd+Q now shows confirmation dialog warning about stopping background processes
Clicking dock icon reopens hidden window or creates a new one
* docs: add scheduled tasks impl plan
* feat: add scheduled tasks runtime, api, and ui
* feat: conditionally confirm desktop quit on risks
* chore: remove scheduled tasks plan doc
* feat: add scheduled tasks runtime and management UI
Add server-side scheduled task runtime with project-backed config persistence
Add task scheduling UI and API integration for creating and editing schedules
Add tests for runtime scheduling behavior and project config validation
* feat: add locale display preferences for scheduled tasks
Add Appearance settings for time format and week start with settings.json persistence
Apply preferences in scheduled task editor for time display and weekday ordering
Rename Thinking level control and disable it when model variants are unavailable
* feat: improve scheduled tasks editor and sidebar action order
Reorder session sidebar header actions to separate creation and management tools
Polish scheduled tasks dialog layout and controls for clearer editing flow
* feat: polish scheduled task editor usability
Improve scheduled task dialog layout for clearer scheduling controls
Refine time and weekday inputs for more intuitive task configuration
Update editor labels and control states for better model variant guidance
* feat: add prompt autocomplete and command-aware scheduled runs
Add @ and / autocomplete support to task, multi-run, and agent manager prompt fields
Fix agent mention selection so subagents can be inserted from @ suggestions
Run scheduled prompts as commands when they match slash commands, with message fallback
* fix: added desktop app background throttling
* perf: add streaming debug metrics panel
- Show streaming performance metrics in the debug panel
- Auto-enable stream profiling while the panel is open
- Add JSON export for sharing UI and VS Code metrics
* perf: batch streaming updates more aggressively
- Buffer message deltas and metadata updates to cut render churn
- Skip no-op part updates before they touch the message store
- Fix the desktop debug panel shortcut binding
* perf: split streaming event handling and coalesce deltas
- Move streaming content events onto a dedicated fast path
- Defer non-critical stream side effects off the hot path
- Merge repeated message delta events before they reach the UI
* perf: isolate streaming rows from chat rerenders
- Memoize chat rows against render-relevant message changes only
- Read live assistant text directly from store to narrow streaming updates
- Split the active streaming entry from the stable message list path
* perf: streamline chat streaming and SSE proxying
- Reduce chat rerenders around the active streaming path
- Simplify server SSE forwarding to avoid duplicate proxy work
* fix: preserve the first streaming text chunk
- Show the initial text chunk immediately before batched deltas arrive
- Bypass batching for the first text or reasoning part update
- Keep later streaming updates buffered for performance
* perf: align streaming/render hot paths with opencode parity
* perf: harden turn/cache stability and stale delta suppression
* fix: stabilize chat rendering and disable timeline interactions
- Disabled timeline dialog access from shortcuts, commands, and chat input
- Reduced chat render churn by simplifying message list and turn staging behavior
- Improved session-switch stability to prevent update-depth crashes
* perf: track static message rerenders during streaming
* perf: reduce sorted-mode activity rerender fanout
* perf: reduce chat rerender fanout and add active-turn metrics
- Reduced sorted-mode rerender coupling by tightening turn context propagation
- Added a metric for static rerenders outside the active turn during streaming
- Exposed new chat render counters in the debug panel for parity tracking
* fix: keep sorted activity mounted while stream grows
* fix: stabilize session and history scroll rendering
* refactor: decouple server routes from index
* refactor: extract fs module from server index
* refactor: move opencode route ownership into module
* refactor: extract notification route registration
* refactor: extract opencode and notification runtimes from index
* refactor: extract settings runtime and complete server modularization pass
* refactor: modularize server config, skills, icons, and tunnel routes
* refactor: extract server modules from monolithic index.js
Split proxy, routes, runtime helpers, and notification emitter
into dedicated modules under packages/web/server/lib/.
* refactor: replace session/message stores with SSE-driven sync layer
Delete ~9200 lines of old architecture (useEventStream, messageStore,
sessionStore, useSessionStore, questionStore, useTodoStore, client SSE).
New sync layer: event pipeline with coalescing + 16ms flush, pure event
reducer, per-directory child stores with LRU eviction, cursor pagination,
optimistic updates, deferred timeline staging, text throttle.
Migrate all UI consumers to sync hooks (useSessionMessages,
useSessionMessageRecords, useSessionStatus, useSessionPermissions, etc).
Strip session-ui-store to UI-only state, delegate SDK ops to
session-actions with abort-if-busy, optimistic store updates, and
response merging for revert/fork/archive/delete.
Add notification-store for SSE-driven session attention tracking,
cross-directory GlobalSessionStatusStore for sidebar indicators,
client-side diff snapshot sanitization to prevent memory bloat,
and revert message filtering via useVisibleSessionMessages.
* feat: notification store, session actions, activity detection
Add notification-store.ts for SSE-driven attention tracking.
Add sanitize.ts to strip diff snapshot memory bloat.
Add session-actions.ts with optimistic revert/fork/archive/delete.
Improve useSessionActivity with incomplete-message fallback.
Delete useServerSessionStatus polling hook.
* fix: add directory param to all SDK calls, fix command/shell/abort routing
All SDK calls in session-actions.ts now pass directory parameter —
required by OpenCode server to scope session operations. Without it,
abort, commands, revert, fork, and other operations returned 500.
Add routeMessage() in session-ui-store for shell mode (session.shell),
slash commands (session.command), and normal prompts. Command lookup
checks both sync child store and useCommandsStore. Handle /compact
locally via session.summarize().
Implement getContextUsage() to restore header context usage display —
reads token counts from last assistant message in sync store.
* refactor: replace custom API proxy with http-proxy-middleware
Remove ~280 lines of custom proxy code: forwardSseRequest,
forwardGenericApiRequest, collectRequestBodyBuffer, header
manipulation, hop-by-hop filtering, SSE block buffering.
Replace with single createProxyMiddleware() call that handles
SSE streaming, large bodies, and timeouts out of the box.
Dynamic router for OpenCode port changes after restarts.
Auth headers injected via proxyReq hook.
Keep: readiness gate, Windows session merge, API prefix detection.
* perf: targeted event draft cloning to fix streaming render cascade
Event handler was eagerly cloning all state slices on every event,
breaking Zustand selector referential equality. During streaming
(~60 events/sec), this caused every subscriber to re-render regardless
of which slice actually changed.
Now only clones fields the specific event type mutates. Also extracts
StatusRowContainer to isolate high-frequency useAssistantStatus
subscription, removes dead messageStreamStatesMap subscription from
ChatContainer, and narrows useAssistantStatus to only track last
assistant message parts.
MessageList renders: 1972 → 296 per streaming session (-85%).
* fix: null safety for sync state slices
Add defensive ?? {} guards on permission, question, session_status,
and message record access. Prevents crashes when child store state
is partially initialized during bootstrap.
* perf: dedup inflight SDK calls, extract concurrency util, delay PR tracking
Extract mapWithConcurrency to shared lib/concurrency.ts. Add in-flight
dedup for loadProviders/loadAgents to prevent concurrent duplicate SDK
calls. Delay initial PR background tracking by 5s to reduce startup
CPU burst.
* fix: header session lookup across all child stores
Session title and context panel click failed when session belonged to
a different directory than the current child store. Fall back to
getAllSyncSessions() to search all initialized stores.
* chore: bump @opencode-ai/sdk to 1.3.5
* docs: add sync event handling guide
* Optimize session prefetch and improve delete/archive UX
- Add settlement delay to session prefetch to avoid race conditions on
rapid session switches
- Reduce git diff prefetch and session cache limits for better performance
- Implement optimistic UI updates for session delete/archive operations
with proper rollback on failure
- Wire session prefetch hook into SessionSidebar with sync integration
* Add file content cache and sync optimizations
- Wrap FilesAPI with in-memory LRU cache for file content with dual
constraints (entry count and byte size)
- Optimize chat timeline scroll restoration using useLayoutEffect
- Preserve React references in message and part arrays to prevent
unnecessary re-renders when prepending history
- Add session prefetch TTL cache to prevent redundant fetches
- Integrate session prefetch cache clearing with eviction flow
* Improve session sidebar error handling and add diff prefetch filtering
Load active and archived sessions independently using Promise.allSettled
to prevent one failure from blocking the other. Add retry logic to session
API calls and skip large files during diff prefetch to improve performance.
* Replace sendMessage with optimisticSend wrapper
Introduces optimistic UI updates for normal chat messages to provide
instant feedback. Messages appear immediately in the UI while the API
call executes in the background, with automatic rollback on errors.
* perf: split stores, proper optimistic send, fix revert/directory bugs
- split session-ui-store into voice/input/selection/viewport stores
to reduce subscriber re-evaluation during streaming
- wire optimisticSend through useSync shadow Map infrastructure
matching OpenCode's pattern (no heuristic part detection)
- port OpenCode Identifier.ascending ID format for correct sorting
- pass messageID to promptAsync to prevent duplicate messages
- fix worktree directory not propagating to session actions
(dynamic dir() via opencodeClient.getDirectory)
- fix setCurrentSession accepting directoryHint for new sessions
- fix revert not hiding messages (session limit was 5, bumped to match loaded count)
- fix revert optimistic message removal from store
- fix load-more flicker (useLayoutEffect scroll compensation)
- add prefetch TTL cache, file content LRU cache
- add session prefetch for adjacent sessions
- add instant archive/delete (optimistic before SDK call)
- migrate legacy window.__zustand_session_store__ to session-ui-store
- add retry + independent error handling for archived sessions
- add AGENTS.md performance rules
* perf: startup optimization — dedup, caching, light git status, diff rendering gates
- defer diff prefetch to git tab open, reduce concurrency 4→2, skip >500 changed lines
- cap project git checks concurrency (2), directory status probe (3)
- dedup provider/agent loading, github auth, worktree list (in-flight + TTL caches)
- delay PR tracking 5s, cache 403 search failures per-repo
- coalesce settings PUT (200ms debounce), cache settings GET (2s TTL)
- cache canonical directory resolution (60s TTL)
- persist missing directory status to localStorage (10min TTL)
- light/heavy git status: polling skips numstat+line counting+rev-list
- large diff rendering gate (>500 lines → "render anyway" button)
- tokenization degradation for >500KB files in Pierre
- parallelize main.tsx pre-render awaits
- batch sidebar file tree expanded paths restoration (3 at a time)
- remove bare useConfigStore() subscription in AgentsPage
- sync worktree sandboxes to OpenCode SQLite DB
- fix RightSidebarTabs ternary → explicit tab matching
- defensive guards on sync state (session_status, permission, question, message)
* fix: add defensive guards on remaining sync state field accesses
guard session_status, permission, message, todo, part, config with ?? {}
in useDirectorySync selectors, session-cache, and bootstrap
* fix: add missing directory dep to useCallback in use-sync.ts
* fix: preserve diffStats when light-mode polling overwrites status
* perf: optimize startup git status polling and diff rendering
Preserves diff stats when lightweight polling updates repository status
Reduces startup overhead with smarter git polling and store updates
Adds detailed optimization and migration docs for next performance steps
* fix: keep chat diff stats stable during git status updates
Prevents lightweight git polling from dropping diff statistics
Keeps MessageList diff indicators consistent while status refreshes
Improves reliability of git-aware chat rendering
* fix: user animation replay, queued message variant, startup provider loading
- consume animation ID after first play to prevent re-animation
on neighbor assistant message completion
- capture send config (model/agent/variant) at queue time matching
OpenCode's FollowupDraft pattern instead of re-resolving at send time
- replace one-shot startup recovery effect with polling interval
that retries every 2s until providers and agents load
- fix optimistic bridge to avoid re-render loop (stable ref wrappers)
* chore: update tauri to 2.10.3 and all plugins to latest
- tauri 2.9.4 → 2.10.3
- tauri-build 2.5.3 → 2.5.6
- tauri-plugin-dialog 2.4.2 → 2.6.0
- tauri-plugin-log 2.7.1 → 2.8.0
- tauri-plugin-shell 2.3.3 → 2.3.5
- tauri-plugin-updater 2 (floating) → 2.10.0 (pinned)
- @tauri-apps/api ^2.9.0 → ^2.10.1
- wry 0.53.5 → 0.54.4 (transitive)
* refactor: decouple web server index orchestration runtimes
* fix: align VS Code runtime behavior with web and reduce draft view CPU load
- Queue VS Code bridge and SSE startup requests until API readiness to avoid false bootstrap failures
- Make agent manager actions directory-aware and remove real worktrees with safer partial-failure handling
- Replace heavy logo animation path with a lightweight pulse to cut draft-session CPU usage
* fix: restore auto-selected file sending in chat input
- Send server-selected files as proper file URLs in the message payload
- Include server-backed attachments in submit flow instead of dropping them
- Restore queued-message attachments through the refactored input store
* fix: restore session model selection consistently on session switch
- Restore agent, model, and variant from the latest loaded user message for each session
- Wait for session messages before applying restored selections to avoid stale or missing state
- Remove legacy session-choice inference paths that caused overlap and instability
* fix: restore permission replies and auto-accept across sessions
- Scope permission and question replies to the target session directory so answers take effect reliably
- Make permission auto-accept immediately handle pending requests and react to new permission prompts
- Keep parent-session handling working for child-session requests through the shared response path
* feat: add reusable fuzzy branch fuzzy-search helper and dialog integration (#798)
* feat: add reusable fuzzy branch search for worktrees
* chore: drop planning docs from feature branch
* feat: make worktree branch refresh manual
* feat: add configurable session retention action
* refactor: centralize global session state in ui store
* fix: cancel debounced permission push after reply
* docs: clarify global and directory session store architecture
* docs: refine agent development rules and session activity guidance
- Clarify agent code of conduct and durable development patterns
- Add explicit shared-store rerender and live-state guidance
- Narrow session activity fallback to avoid stale working state
* chore: updated .gitignore
---------
Co-authored-by: Iuliia Ivashko <yulia.ivashko@gmail.com>
Serhii Dziupin