Maintenance task commands now fill .github/PULL_REQUEST_TEMPLATE.md section by
section instead of inventing their own headings, and follow-up tasks keep the
description true for the final HEAD while preserving hand-added content.
Raise the anti-slop batch window to 60-120 findings and require each selected
file to be finished: remaining findings need an individual specific reason,
shared root causes count once, and difficulty alone no longer justifies a skip.
A half-fixed file otherwise returns as a second pull request over the same code.
Add the maintenance-review command, which reviews every open anti-slop and
react-doctor pull request and fixes the findings directly rather than
commenting, without merging or approving.
Vendor the anti-slop Oxlint plugin at tools/oxlint/anti-slop and register it
in oxlint.config.ts, with Oxlint's own rule categories disabled so ESLint
stays the general-purpose linter.
Add scripts/anti-slop.mjs (bun run deslop) mirroring the React Doctor batch
interface: next-batch, check-batch, active, release, top, file. Batch handoff
directories now double as file claims shared across clones via
~/.openchamber/maintenance-claims, so concurrent maintenance batches from
either pipeline never select the same file.
Harden both scheduled maintenance flows: stop on a dirty worktree, stop on
NO BATCH AVAILABLE, validate per package instead of workspace-wide, and pin
react-doctor to 0.9.12. The anti-slop task command documents concrete
good and bad fixes and forbids laundering types to satisfy a rule.
Branch status resolves an open PR across the whole fork network first, so a
merged fork PR can never hide an open upstream PR for the same head. Only when
no target has an open PR does the branch's newest closed/merged PR come back,
as history.
The panel shows that history as a compact note and offers creating the next PR
below it, instead of either sticking on a terminal PR or going blank after a
merge. Terminal associations stay persisted for reload continuity but are never
treated as authority: they revalidate on the discovery cadence and on focus.
History is looked up only for the branch's own remote and name, and remembered
per repo+branch, so the extra lookup cannot exhaust the route's resolve budget.
The checks summary and merge-permission lookup are skipped for a closed or
merged PR, where neither is actionable.
Auto-derived project labels were title-cased, turning .ssh into .Ssh and
opencode-claude into Opencode Claude. Show the folder name verbatim in the
sidebar, window title, settings selector and notification templates, and
migrate persisted legacy labels back to the folder name (manual renames
are preserved).
The opencode-claude integration registers its provider as `claude-code`, which
never matched the `claude` quota provider, so the collapsed Usage section in
the work status panel showed no limit for a model from that integration.
Claude windows also reported no duration, leaving the headline to fall back to
whichever row came first instead of the limit that runs out soonest. The
session and weekly windows now carry their length; extra usage stays without
one because it is a monthly spend cap.
Claude quota only worked when the user had signed into Anthropic through
OpenCode. Credentials are now discovered from Claude Code itself first: the
macOS Keychain entry, then the Linux/WSL credentials file (honouring
CLAUDE_CONFIG_DIR), then OpenCode auth.json, then CLAUDE_CODE_OAUTH_TOKEN.
All sources stay read-only and the OAuth token is never refreshed: Anthropic
allows one live refresh token per client_id, so refreshing here would sign the
user out of Claude Code. Credentials are re-read per request instead, and an
expired token reports that Claude Code needs a sign-in rather than a bare 401.
Usage is now read from the limits[] array, so model-scoped weekly limits work
again after Anthropic stopped populating seven_day_sonnet/seven_day_opus, and
new limit kinds no longer need a code change. Adds extra-usage spend and the
plan name, and holds the last good values through Anthropic's 429s with a
cooldown and an account-keyed cache.
Adds a keydown handler on the comment input that stops propagation
Keeps Enter-to-submit behavior working in the annotation overlay
Cleans up the new event listener when the overlay is removed
A server running with authentication disabled pairs and connects fine, but
the saved connection has no bearer token. Auto-connect silently bailed on
the missing token and the resume reprobe reported it as 'unreachable',
so every return to the app kicked the user to the connect screen.
Treat a saved tokenless connection as valid: probe it without a bearer and
let the probe decide — auth disabled connects, auth enabled later reports
needs-login. Bail out only when an expected token cannot be read.
A single uncaught exception (e.g. a Node-internal socket error) no longer
shuts the local server down; only a sustained storm does. The dev-tunnel
client now rejects non-http(s) base URLs cleanly instead of throwing an
uncaught exception in the connection handler.
Opens the chat view before focusing the input
Routes a new webview command to focus the composer
Refocuses the input after adding a VS Code selection attachment
The preview panel worked by proxying a dev server through OpenChamber's own
origin and rewriting the HTML that came back. Anything the rewriter did not
anticipate broke, and pages that refuse to be embedded never loaded at all.
This deletes the proxy (-1604 lines and its tests) and merges the preview and
browser panels into one surface backed by a real Chromium view.
What the panel is now
- A `<webview>` in its own session partition: logins and cookies persist, hot
reload works because nothing is rewritten, DevTools are one click away.
- Annotation: pick one element, drag a region, or draw freehand, write a note,
and it reaches chat with a screenshot of the visible page with the marks on it.
- Toolbar: hard reload, page zoom, device sizes, a light/dark switch that
applies to the page rather than the app, and cookie/cache clearing scoped to
the panel alone.
- Several pages at once, each tab showing the page's own favicon, and an address
bar that suggests pages already visited in this project.
- Dev servers are listed from what is actually listening on the machine, checked
against what a project announced, so a server is offered no matter how it was
started. One that is still starting is waited for instead of failing.
Remote dev servers
The desktop app binds a local port and pipes raw bytes to the OpenChamber host
over the existing authenticated connection, so the page keeps its own origin at
the root of its own host. The reachable set is exactly what discovery reports
and is re-checked per connection, so an authenticated client cannot dial
arbitrary local services on the host. Links and redirects to another loopback
port stay on the machine that served the page. A tunnel that cannot be opened is
reported; it is never replaced by the plain loopback URL, which would answer
from the user's own machine under a remote address.
Agent control
Browser actions are a separate `openchamber_web` tool: open, snapshot, click,
type, scroll, inspect computed styles, resize between mobile/tablet/desktop, and
capture a screenshot into `.openchamber/screenshots/` in the project. The
existing `openchamber` tool keeps sessions, worktrees and scheduled tasks. Each
has its own setting in the new Settings -> General -> OpenChamber Tools section,
and the plugin is not injected at all when both are off.
Capability belongs to the connected client, not to configuration: a client
declares on its event stream that it can drive a page, which only a Chromium
host does. Exactly one client performs each request — it claims the request
before acting, and the first claim wins — because deciding by whose result
arrives first would be too late for a click that already happened. No client
listening is answered immediately with an explanation rather than a timeout.
Runtime boundaries
Web tabs get a plain iframe that can display a page but not inspect one. The
VS Code extension no longer offers the surface at all, since nothing that makes
the panel worth having works there. Mobile is unaffected.
Native boundary
Camera, microphone, location and device-picker requests from panel pages are
denied — Electron grants them by default when no handler is set, and the panel
loads whatever address the user types. Page capture, appearance emulation and
storage clearing verify that their target belongs to the panel's own session
instead of trusting a web-contents id from the renderer.
Persisted state
Stored `preview` tabs migrate to `browser` (v13 -> v14). Context panel tab
limits are now per surface, so filling one surface no longer evicts another's
tabs. Address history is stored per project and per runtime.
Documentation
`preview.mdx` and `desktop-browser.mdx` rewritten across all locales, the agent
tool settings path corrected, new `DOCUMENTATION.md` for the browser-control
broker and the dev tunnel, and the `ui-api-decoupling` skill updated where it
still described the deleted proxy.
Pass initial subagent prompting settings into embedded chat URLs and views
Prevent inactive embedded chats from stealing focus on load
Treat review sessions as independent conversations when resolving prompt read-only state
A single fast probe (2.5s per transport) used to be the only chance a
connection got on cold launch and resume, so a just-woken network, a
WireGuard re-handshake, or a relay cold start (TLS + WS + E2EE) regularly
produced false "unreachable" verdicts that kicked the user to the connect
screen. Now:
- cold launch releases the splash on the fast verdict and retries once in
the background with the full connect budget — a reachable instance
reconnects on its own, and a manual connect started meanwhile wins;
- resume retries on a 4s/10s ladder, the last attempt with the full budget,
before tearing the connection down; needs-login still disconnects
immediately on every path;
- full-budget relay probes are capped at the shared 8s connect budget
instead of inheriting the 15s relay session default, so a genuinely dead
server does not pin the retry for 15 extra seconds.
Probe steps, budgets, and retry decisions all land in the connection log.
Connection lifecycle events (probes, transport failures, resume decisions)
are mirrored into an in-memory trail that resets on every launch. A long
press on the connect-screen logo or the instances list opens a panel that
renders the trail with one-tap copy, so release builds can report the exact
probe sequence without a tethered debugger. Details reuse the already-masked
log payloads — no tokens or secrets are captured.
A request body stream that yields no chunks still declares hasBody in
the request head; send one empty HttpBody frame so the host can tell an
intentionally empty body apart from body frames lost in transit.
Settle the buffered-body wait when the delivery deadline fires so the
stream's buffered chunks are freed immediately, and make the deadline
injectable for tests. Covers the stalled-mid-body path with a test.
Creating a device key while the UI is open through a public https domain
(reverse proxy) dropped that domain from the QR payload whenever the
dialog passed a preferred LAN URL, leaving only the local IP and relay
as transports. Carry the non-loopback request origin as an additional
direct candidate (priority 20, between LAN and relay) so paired devices
can keep using the same domain on any network.
OpenCode Go now reads quota usage with a bearer API key from OpenCode auth.json
Removes the old workspace ID and browser cookie credential flow
Deletes legacy OpenCode Go credential files during upgrade
Adds a dedicated skill for drafting user-facing unreleased changelog entries.
Covers both the main app changelog and the VS Code extension changelog.
Updates agent guidance to route changelog work to the new skill.
Keeps the work status panel aligned to the draft's target directory
Resolves project labels for sibling worktrees using shared session-directory logic
Adds coverage for resolving a worktree back to its registered project
MCP authorization was broken in several stacked ways. The browser return
leg landed on the SPA behind the auth gate, so the system browser saw a
login page instead of finishing; the pending-context store silently
saved nothing because its route had no JSON body parser; and the
callback-URL config write started deferring behind Apply & Restart, so
authorization ran against a runtime without the URL and dead-ended on
OpenCode's loopback listener.
The return leg is now completed entirely server-side by an
unauthenticated GET /mcp/oauth/callback that only forwards a code whose
state matches a parked context. Desktop with the local server and VS
Code switch to OpenCode's native flow over its fixed loopback port —
no config writes or restarts at all, with a one-time cleanup of the
previously written callback URL — and its completion signal drives the
page instead of blind status polling. Remote, hosted-web, and mobile
keep the server-callback flow, applying a queued callback-URL write
immediately since authorization cannot wait for a manual restart.
Also: a server queued behind Apply & Restart now shows an Awaiting
restart badge and explanation instead of connect/reauthorize buttons
that can only fail, and Reauthorize is offered only while the server is
actually connected.
Dialogs and settings window now use the standard background color
Removed dialog from the glass utility styles
Preserves existing glass effects for other surfaces
Relay demand now counts the authoritative transport signal: a request
arriving through the tunnel permanently marks the client usesRelay, and
hasActiveRelayClients also accepts lastTransport === 'relay'. Store read
failures no longer masquerade as no demand, so reconcile can't persist
enabled=false and sever paired devices on a transient error.
Drops the macOS vibrancy toggle, IPC, and related settings copy
Updates dialogs, popovers, tooltips, and dropdowns to use shared glass styles
Adds sticky header fade behavior to model picker and sidebar lists
Adds a work-status panel beside the transcript. Context fill, model and
cost, todos, running subagents and the permission requests blocking
them, branch and working-tree state, MCP servers, pinned messages and
context sources were scattered across the header, the composer and the
context panel — a blocked subagent was reported nowhere at all. The
panel reads them from live channels rather than persisted history, and
becomes an overlay where the chat is too narrow to seat a column.
It is on by default, including for existing installs. Because it now
carries these readouts, the desktop header and composer drop the ones it
duplicates: todo and changed-files chips, usage and MCP tabs. VS Code
and mobile keep theirs — neither hosts the panel.
Fixes MCP authorization, which was broken from the panel, invalidated by
a directory switch through a redirect URI that encoded the working
directory, and left the desktop app in the background because browsers
will not follow a custom-protocol link without a user gesture. The
settings page no longer asks the user to understand the MCP spec before
adding a server: one field takes the command or the link, with the kind
inferred and a visible override, and client-registration fields appear
only when a server actually asks for its own credentials.
Also: skills load from the panel instead of only when the composer's
slash autocomplete opens; the header button names the current instance
rather than falling through to the word "Instance" for relay hosts.
Three new optional UI settings keys, all migrated. No change to stored
MCP server configuration.
The ping has no pong-timeout on either side — it exists only to keep
intermediaries from idling out the socket. 45s stays safely under the
relay host-data idle reaper (90s) and common proxy read timeouts (60s),
while halving the events that wake the relay Durable Object during an
open session.
The suite mocks `session-actions` by listing its exports one by one, and had
fallen behind `unarchiveSession`/`unarchiveSessions`. `session-ui-store` imports
both, so the file threw on import and ran zero tests — the draft auto-accept and
canonical-worktree-directory guarantees it covers were unprotected, and the
report looked almost like silence rather than a failure.
The spinner ran a CSS animation on every active row for the whole turn,
repainting a composited layer at frame rate. Rows now carry a static dot —
primary while running, info while unread — and the metadata slot on the right
shows how long the turn has been going, updating once per second in the dot's
colour. The counter is the motion the spinner used to provide, at 1 fps.
Collapsed groups, folders and projects take the dot only, since one counter
cannot speak for several running turns.
Elapsed time is measured client-side because SessionStatus carries no
timestamps, and starts are persisted so a reload resumes the same count. Two
rules keep that honest. Only a liveness stamp — refreshed while a session is
observed active, stamped as the page hides, and compared against the page's
navigation start so a slow bootstrap is not charged to the absence — and a 90s
adoption window may expire a record; a snapshot that cannot yet see a session
is not evidence its turn ended. And a busy event is never read as a turn
boundary, because OpenCode republishes busy at every step of the agent loop, so
after a reload one of those repeats normally beats the first status snapshot.
Idle and error events do end a turn, and retire the record with it.
Snapshot reconciliation walks the running turns and asks whether the snapshot
covers each one, rather than being handed everything it covers: only a live
start can settle, so the pass scales with timing work instead of with the
directory's session list, and allocates nothing per poll.
Also applied to the mobile sessions sheet and session switcher. The shared
duration ticker moves to hooks/ now that it has a second consumer.
Follow-up to #2629, which stopped the walkthrough from comparing against a
branch that does not exist. The same guessing, and the same near-misses in how
the answer was applied, were left elsewhere:
- The default branch travelled as `rootBranchHint`, whose documented meaning is
"the branch the project root worktree is on". It gets its own option, because
a parameter that means two things is one the next caller gets wrong.
- A candidate equal to the branch being compared is skipped. In a plain checkout
the root hint *is* the current branch, so it won every time and produced a
comparison with itself; the repository default now wins there.
- The Changes and pull-request surfaces read the default branch too. A pull
request opened against a branch that does not exist is a worse failure than a
walkthrough that will not generate.
- `hasResolvableBaseBranch` matched `origin/feature/main` for a base of `main`,
passing the check and then failing the comparison it exists to prevent.
- `getRangeDiff` promoted only `origin/<base>`. A base carried by any other
remote stayed a bare name, which git resolves against refs/heads and nowhere
else, so it failed exactly as before.
- `getBranches` dropped every branch of a remote that did not answer, turning
"we could not ask" into "these branches are gone" — offline, that silently
removed comparisons that work fine against local remote-tracking refs.
- A remote with no `remote/HEAD` is asked once with `ls-remote --symref` rather
than falling back to the guess this data exists to replace.
The `defaultBranches` contract was documented under the status response; it
belongs to the branches response, which now has a section of its own.
- Add switch_context_surface shortcut (default Cmd/Ctrl + 1..9, 0 for the 10th
surface) that opens/closes/switches context panel rail surfaces by their
visible order, configurable and persisted in Settings -> Shortcuts.
- Show order-number badges on rail icons while the modifier is held >500ms;
dismiss on release, blur, or a number press until the next press-and-hold.
- Remove the legacy mod+2/3/4 (diff/terminal/git) and switch_tab_1..9 bindings
so numbered surface switching goes only through the new mechanism.
- Replace the help-dialog 'Switch Project' row with the surface-switch row and
update the shortcuts footer/header icons to the command icon.
OpenCode's authorize response reports how the client must finish: `code`
expects a pasted code, while `auto` requires the client to call
oauth/callback immediately and hold it open — upstream blocks in there
polling for the device code or waiting on its loopback redirect, and only
that call persists the credential. Every auth plugin OpenCode ships uses
`auto`; none use `code`.
The page implemented only `code`. It opened the browser, showed a paste
field no provider can fill, and never called back, so a successful sign-in
stored nothing and the app sat unchanged. Authorization now drives the UI:
`auto` chains straight into the callback behind a waiting state with a
cancel, and the paste field appears only when a provider actually asks
for a code.
Two smaller failures shared that surface. Prompts were never collected,
which put GitHub Copilot Enterprise out of reach entirely, so a method
that declares them now asks first and passes the answers to authorize.
Device codes are also recovered from the instructions text, where they
actually live — the old code read fields the API does not return, so the
copy button never appeared.
The callback is exempt from the ordinary proxy deadline and gets a
15-minute budget, bounded by the shortest upstream expiry we know of.
A human sign-in with 2FA does not fit in four minutes, and expiring it
turned a completed login into a 504.
A server without these routes does not answer 404 with JSON. The unmatched
/api path reaches the OpenCode proxy, and OpenCode serves its embedded web UI
for anything it does not recognise — HTML, status 200 — so a client newer than
its server parsed a web page as JSON and put "Unexpected token '<', "<!doctype"
in the panel, naming neither the cause nor the remedy.
The client now checks the content type before parsing. A non-JSON answer on 2xx
or 404 blocks with "this server is older than the app, update it and refresh".
A non-JSON 5xx keeps its own failure: a server that answered badly is not a
server missing the feature, and sending that user to upgrade chases the wrong
thing.
The "Critical" pill was painted in the status-error colour, so a stop marked
because it drives the change read as a severity reported against the code —
the one thing this feature never does. It is now "Key change", carries its
emphasis with weight and an outline rather than a status colour, and both tags
state their meaning in a tooltip. The panel links the guide from its header,
and the guide gained a section on what the tags mean and what they do not.
Also corrects two German strings that translated the noun "stop" as the verb.
`prompt_async` answers 204 as soon as OpenCode forks the run and reports
every later failure only on the session event stream, so an unusable
model, agent, or variant produced a session with no message while the
result still claimed `promptDispatched: true`.
Validate an explicitly requested model, agent, and variant against the
directory's own agent and provider lists before any session, worktree, or
goal is created, and confirm a new user message actually reached the
session before reporting the dispatch. A failed or empty lookup never
turns a valid selection into a rejection.
Adds a new info-styled button variant for consistent secondary actions.
Updates mobile sessions sheet actions to use the shared Button component.
Cleans up the mobile footer buttons with the shared sizing and styling system.
Review found the owning documentation still describing the behaviour this
branch replaced, in one case stacked directly above the new docstring saying
the opposite. Holding a session proves containment, not ownership, so every
text that called store membership the authoritative mapping was actively
misleading for the module whose wrong answer misroutes every send.
Corrected in the module docstring, the resolution module's precedence
description, the sync-refs helper it points at, and the sync DOCUMENTATION.md
table and rules.
The debug report built its authoritative value membership-first, so for exactly
the scenario this branch fixes it reported the parent directory and could raise
a source-disagreement alert while routing was in fact correct. It now uses the
same record-first order as the resolver.
The CLI timeout comment claimed the wait and provisioning windows were additive
while the code took the larger of the two. The server provisions the worktree
inside session creation, before it waits for the session to go idle, so they do
run in sequence: the windows are now summed and the tests pin both cases.
Softens the dark surface and syntax background tones
Updates foreground, selection, and cursor contrast
Keeps markdown, chat, and tool text aligned with the new palette
Creating a session with a worktree reported "Request to /api/openchamber/control
timed out after 4000ms" while the worktree was in fact created, leaving the user
with a failure message, a real worktree, and no session id. Reported alongside
worktree creation appearing to take forever.
The client HTTP timeout was extended only when the caller asked to wait for the
session. Provisioning a worktree is slow on its own: it runs git against the
repository and prepares a new directory. Measured on a cold path immediately
after a restart it takes about four seconds, which lands exactly on the four
second default and explains why this failed intermittently rather than always.
A warm run finishes in well under two.
The timeout now follows the work being requested rather than only the wait
flag, and covers whichever of the two windows is longer. The server always
completed the operation, so nothing about the outcome changes: only the client
stops abandoning it.
Verified by creating a worktree on the cold path immediately after a restart,
which previously failed here: 4004 ms and 1376 ms, both reported ok.
A session created in a git worktree while the client was already running did
not render: the message list stayed empty while the prompt and the assistant
reply were both present in the session, visible on any fresh load. Reported as
prompting in a worktree sometimes not working.
Ownership was read from which child store holds the session. That is
containment, not ownership. A project's session list includes the sessions of
its worktrees so the sidebar can group them, so the parent repository holds
worktree sessions too, and whichever store bootstrapped first won. Captured
mid-failure, the two signals disagreed outright:
owningDirectory /repo <- parent, merely holds it
recordDirectory /repo/.worktrees/feature <- the session's own directory
The parent won, so every fetch was addressed to a directory that does not own
the session, the session id resolved to undefined there, and the requests
failed as /api/session/undefined in a retry loop. The session's own record is
now believed; store membership remains the fallback for a record that carries
no directory.
This also explains why the previous commit alone was not enough: settling the
guessed directory adopted this same wrong value and then cleared the guess,
which prevented any later correction.
Verified against the reproduction rather than by reasoning. Before: three of
four runs never rendered. After, on a clean build with the instrumentation
removed: three of three rendered the reply live, each routed to its own
worktree. Tests cover ownership disagreeing with containment, plus both
directions of the guess promotion.
Adds an Electron install check that repairs incomplete or wrong-architecture binaries
Runs the check during root postinstall and before electron dev startup
Adds tests and docs for the new ensure:electron workflow
Selecting a session whose directory this client has not indexed yet routes it
through the active directory. That is a deliberate, documented guess: it keeps
routing usable while the owning store bootstraps, and it is excluded from both
the resolver and persistence.
Nothing settled the guess afterwards. `setSessionDirectory` performs exactly
that promotion, but only confirmed destinations call it — a completed move or a
worktree this client created. A session whose directory the client learned about
later, such as one in a worktree created outside this client, kept the guess
forever: every message fetch was addressed to the parent repository, which does
not own the session.
Captured for such a session before this change, with the session already
indexed and its owning store known:
routedDirectory .../worktree/feature
currentSessionDirectory /repo <- guess, never settled
opencodeClientDirectory /repo
conflict selected -> /repo
and after:
routedDirectory .../worktree/feature
currentSessionDirectory .../worktree/feature
opencodeClientDirectory .../worktree/feature
conflict null
Directory bootstrap completion is the moment the authoritative directory first
becomes readable, so the promotion runs there. It only ever promotes a guess:
a confirmed selection and a selection that has since moved on are both left
alone, and tests cover both directions.
This removes a real routing split-brain. It does not by itself fix the reported
symptom of a session created mid-session never rendering; that remains open.
Bohdan Triapitsyn