* Clarify model-facing message when user rejects a tool call
* Include the rejected tool's name in denial reasons
* Move user-rejected tool reason into @cline/shared
* Route new user-rejection approval paths through shared reason builder
Since the original PR, several new approval surfaces landed on main with
their own terse denial strings (CLI connectors, ACP permissions, Cline Hub
webview, desktop webview, example VS Code extension). Route all of them
through buildUserRejectedToolReason so the model sees a consistent,
non-error rejection message.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Add buildUserRejectedToolReason to the @cline/shared integration-test stub
The VS Code integration tests run the tsc-built CJS tree and stub the
ESM-only @cline/shared package in test-setup.js; the stub was missing the
new export, so tool-approval-denial.js threw at module load in CI.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Trim scope back to the minimal rejection-copy fix
Restore the connector deniedReason plumbing, ACP permission strings,
desktop webview reason, example extension reason, and hub server fallback
to their main versions. Those surfaces already attribute the denial to a
user and are outside ENG-2329. Keep the Cline Hub webview change since
that path emits its own rejection string the model sees.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Move rejection guidance suffix into agent runtime per review
* Apply review suggestions: neutral fallback reason and -- separator before rejection suffix
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Flipping the <markdown> streaming prop from true to false when an
assistant text segment settles makes MarkdownRenderable call
updateBlocks(true), which skips every block-reuse path and destroys and
recreates all block renderables. Until tree-sitter re-highlights them
the whole message renders blank/unhighlighted, which users see as the
text flashing at the end of each response. Keep streaming={true} for
the transcript markdown (opencode's TUI does the same); entry.streaming
still drives the spinner glyph.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): stop an empty capability list from stripping image input
`modelHasCapability` documents a missing or empty capability list as
carrying no signal, so each gate declares its own default. Two readers
bypassed it and read `capabilities` directly, where an empty list is not
nullish but `[].includes(x)` is false:
- the session runtime's `modelSupportsImages` metadata used
`capabilities?.includes("images") ?? true`, so the intended fail-open
never fired for an empty list and the file-read tool silently dropped
every image from the request;
- `toProviderModel` projected an empty list onto `false`, telling pickers
a model definitively lacks vision, attachments, and reasoning when
nothing had been declared.
Both now route through the shared helpers, which state their unspecified
default explicitly: `modelSupportsImageInput` fails open for a capability
gate, and `declaredCapability` preserves `undefined` for `ProviderModel`'s
tri-state booleans. A populated list stays authoritative in both.
A thinking config now short-circuits `supportsReasoning` instead of being
OR-ed with the capability read, so its absence no longer collapses the
tri-state to `false`.
* fix(llms): translate gateway capabilities in one place
Three producers built gateway model definitions from catalog `ModelInfo`,
and each carried its own hand-written `switch` over the capability list.
Nothing tied them together, so they drifted:
- builtin providers always emitted a capability list, so a model whose
catalog entry declares no capabilities became `["text"]` where the other
producers emitted `undefined`. `modelSupportsToolCalling` fails open only
for an absent or empty list, so that list read as an authoritative denial
and stripped every tool definition from requests to the affected language
models (dify, sapaicore, opencode, and the Codex CLI);
- the OpenAI-compatible path mapped an `audio` capability that
`ModelCapabilitySchema` does not define, while the other two dropped it;
- the pass-through capabilities (`streaming`, `files`, `temperature`, ...)
were enumerated explicitly in one, folded into `default:` in another,
and ignored in the third.
One exported `toGatewayModelCapabilities` now serves every producer. It is
built on a `Record<ModelCapability, GatewayModelCapability | null>` rather
than a `switch`, so extending `ModelCapabilitySchema` without deciding the
new capability's mapping fails to compile instead of silently falling
through to a default.
The conformance tests walk the capability state space taken from
`ModelCapabilitySchema` itself and assert the real producers agree with the
translator, so a future producer that maps capabilities on its own fails
even when the translator's own unit tests still pass.
---------
Co-authored-by: Cline Agent <cline-agent@users.noreply.github.com>
Co-authored-by: Ara <arafat.da.khan@gmail.com>
`modelHasCapability` documents a missing or empty capability list as
carrying no signal, so each gate declares its own default. Two readers
bypassed it and read `capabilities` directly, where an empty list is not
nullish but `[].includes(x)` is false:
- the session runtime's `modelSupportsImages` metadata used
`capabilities?.includes("images") ?? true`, so the intended fail-open
never fired for an empty list and the file-read tool silently dropped
every image from the request;
- `toProviderModel` projected an empty list onto `false`, telling pickers
a model definitively lacks vision, attachments, and reasoning when
nothing had been declared.
Both now route through the shared helpers, which state their unspecified
default explicitly: `modelSupportsImageInput` fails open for a capability
gate, and `declaredCapability` preserves `undefined` for `ProviderModel`'s
tri-state booleans. A populated list stays authoritative in both.
A thinking config now short-circuits `supportsReasoning` instead of being
OR-ed with the capability read, so its absence no longer collapses the
tri-state to `false`.
Co-authored-by: Cline Agent <cline-agent@users.noreply.github.com>
* fix(vscode): sanitize pasted provider API keys at the settings write boundary
Clipboards smuggle control and invisible formatting characters (newlines,
zero-width spaces, BOM) into pasted API keys. The masked key field hides
the corruption and providers reject the key with a 401 indistinguishable
from a genuinely wrong key. Strip those characters and surrounding
whitespace once in the provider config store write path, so both backing
stores (legacy state secrets and providers.json) receive the clean value.
A whitespace-only value now clears the key.
* feat(llms,vscode): classify provider 401/403 as auth errors and surface actionable guidance
Add an "auth" ProviderErrorClass, assigned when the HTTP layer reports
401/403 — status-only on purpose, since provider bodies can quote words
like "unauthorized" without the request being an auth failure. The class
rides the existing errorClass plumbing (finish -> run-failed ->
AgentErrorEvent), so every host receives it with no new wiring.
In the VS Code chat surface, rewrite classified credential rejections
from BYOK providers into actionable text pointing at the API key
configuration, keeping the provider's raw body as a diagnostic tail.
Raw bodies alone are dead ends: Mistral, for example, answers an
identical {"detail":"Invalid API Key"} for a wrong, empty, or
wrong-scope key. Cline-account providers keep the JSON path so the
webview still renders their auth failures as a sign-in card.
The SDK hooks adapter created every hook runner without a task id, and
StdioHookRunner gates all captureHookExecution calls on one being set —
so the next variant emitted zero hooks.execution events while discovery
telemetry fired normally. Pass the task id (and tool name for the tool
hooks) at all five factory.create call sites, and pin the threading
with a regression test.
* fix(vscode): prevent hook spawn failures from crashing the core process
A hook child-process spawn failure emitted "error" on HookProcess with no
listener registered, which Node's EventEmitter turns into an uncaught
exception - killing the entire cline-core process instead of failing the
one hook open. Guard the emit behind listenerCount so the rejection (which
StdioHookRunner handles) is the only propagation path.
The trigger was a workspace root that no longer exists on disk passed as
the spawn cwd: Node reports a nonexistent cwd as a misleading ENOENT on
the launcher binary ("spawn /bin/sh ENOENT"). Validate cwd existence in
HookProcess right before spawning - falling back to no explicit cwd with
a warning that names the missing directory - and when a spawn still fails
ENOENT because the directory vanished in between, name it in the error
message instead of blaming the shell.
* fix(vscode): fail hooks with a missing working directory instead of relocating them
Running a hook whose assigned cwd no longer exists from the host
process's own working directory would let its relative paths read and
write an unrelated location (e.g. the IDE install directory). Reject
before spawning, with an error naming the missing directory; the runner
reports the hook as failed and the task continues. Also carry pre-spawn
failure messages into HookExecutionError details so the cause is not
reduced to a bare "exited with code 1".
* fix(llms): recognize direct tracer providers
* fix(llms): make Langfuse tracer detection survive minified release builds
Release binaries are compiled with minify enabled, which renames classes,
so initializeLangfuseTelemetry's constructor-name guard never matched
"ProxyTracerProvider" and silently returned readiness=false in every
production build (hub log: "creating span processor" followed by
"initialized readiness=false" with no branch message in between). Dev runs
execute unminified source, which is why the same env vars worked there.
Replace every constructor-name comparison with checks that survive
minification: detect the proxy structurally via getDelegate, distinguish a
recording provider from the no-op fallback by its lifecycle methods, and
confirm our NodeTracerProvider registration by object identity. When a
foreign provider already owns the global slot, attach the Langfuse span
processor to it when it accepts processors, and otherwise shut down the
orphaned provider and report the rejection instead of bailing silently.
Verified by bundling the module with Bun minify:true against the real
OpenTelemetry packages: the previous code reproduces readiness=false
(provider class name mangles to "H2"), the new code initializes with
readiness=true.
* feat: add searchable session history
Rebased onto main and updated to supersede the sidebar search dialog
from #13533: the sidebar search icon now opens the indexed command bar
(Cmd/Ctrl+P) instead of a sidebar-local cmdk dialog that eagerly loaded
the entire session history via loadAllSessions(). CommandDialog gains a
shouldFilter passthrough so server-ranked FTS hits are displayed as-is.
* fix: harden session history search
* fix: evict failed restoration sessions from search
* fix: preserve deletion when search eviction fails
* fix: address session search review feedback
* fix: preserve search suppression during reconciliation
* test: cover sidecar search fallback on hub timeout and rejection
The existing search_sessions tests only exercised the index-hit and
empty-index-fallback paths with an immediately-resolved hub reply.
Add coverage for the two other realistic Hub-connection failure
modes the fallback is meant to tolerate: the hub call rejecting, and
the hub call hanging past the 750ms withSearchDeadline race.
---------
Co-authored-by: abeatrix <beatrix@cline.bot>
Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>
* chore(llms): built-in model list update 1787907289186
Result of `bun run build:models`.
Includes updated model list and fixed formatting issues across codebase.
* test(llms): update GLM reasoning toggle expectation
* fix(desktop): render tool output images as attachments
Add support for displaying media returned by tool calls (e.g. screenshots)
as rendered images with expand-to-fullscreen capability instead of raw
base64 text. Introduces an `ImageCarousel` component for navigating
multiple images, propagates the expand handler to tool message blocks,
and extracts/validates output media in tool summaries.
* test: cover multi-image and canonical media extraction in tool output (#13645)
extractOutputMedia and the desktop tool-message rendering path were only
ever exercised with exactly one distinct valid image, and
canonicalInlineMedia (MCP-style type: "media" blocks for audio/video/file)
had zero coverage. Add tests for: multiple distinct images in one tool
result (parser + desktop carousel navigation), inline audio via the
mime_type key spelling, canonical video/file media blocks, and rejection
of an invalid canonical image block.
---------
Co-authored-by: Harrison <harrison@cline.bot>
* fix(e2e): stop VS Code e2e worker teardown from timing out
The ext-vscode-test-e2e job has been failing on main with 'Worker teardown
timeout of 60000ms exceeded' even though every test passes. Playwright only
reports an Electron app as closed once the process exits AND every holder of
its stdio pipes is gone (ChildProcess 'close' waits on the extra fd3/fd4
pipes Playwright creates for Electron). Any VS Code descendant that outlives
the main process (chrome_crashpad_handler, GLib's 'dconf watch' helper,
xdg-open browser handlers, VS Code 1.135's agent host CLI subprocess that
logs 'unable to kill the process') keeps those pipes open, so app.close()
never resolves and the worker teardown hangs on it until its 60s timeout
fails the job.
Harness fixes, each removing one source of that wedge:
- closeAppForTeardown now SIGKILLs the whole process group (taskkill /T on
Windows) when app.close() times out, instead of only the main pid — and
does so even when the main process already exited, which is exactly the
wedged state. Playwright launches Electron detached, so pid == pgid.
- Launch VS Code with --disable-crash-reporter so no crashpad handler
outlives the app holding the harness pipes.
- Seed the fresh user-data-dir with chat.disableAIFeatures: true so VS
Code's own AI features (rolled out via server-side experiments, so CI
breaks without any repo change) never start their agent host process.
- Drop the page.close() teardown: closing VS Code's last window quits the
whole app, and ElectronApplication.close() on an already-exited app
deadlocks; the app fixture's app.close() closes windows itself while the
app is alive.
- Codex sign-in no longer opens a real external browser under E2E_TEST; the
codex-oauth test drives the OAuth callback itself, and the browser was an
orphaned process holding the harness pipes on the runner.
* fix(core): deflake hub daemon e2e tests on Windows runners
sdk-test on windows-latest fails intermittently in the hub daemon e2e
files:
- shutdown.e2e.test.ts dies with a bare 'Error: socket hang up'. That
message is the ws handshake (http.ClientRequest) failing, not the
/shutdown fetch (an undici failure prints 'TypeError: fetch failed'):
a freshly spawned bun daemon on a loaded 2-core Windows runner
occasionally drops its first accepted connection before writing the
upgrade response. Real hub clients reconnect with backoff, and the test
asserts shutdown behavior rather than first-connection reliability, so
openAuthenticatedSocket now retries transient handshake failures within
a 15s budget.
- singleton.e2e.test.ts times out waiting for daemon discovery: it still
used the 10s hang guard that 0cfc90158 already raised to 30s in
shutdown.e2e.test.ts for the same reason. Use the same 30s guard.
- Raise the e2e testTimeout to 60s so a test that legitimately spawns two
daemons back to back can survive slow-runner startups instead of the
discovery hang guard being cut off by the test timeout.
* Add feature flags to the app
* React to account updates
* Address comments
* Add a GitHub integration step to the onboarding
* validate domain and fix errors on auth
* Hide the step behind a feature flag
* update version
---------
Co-authored-by: John Choi <john.choi@cline.bot>
Remote (SSE/streamable HTTP) MCP connects run on the session.create
critical path, which the hub caps at 30s. Without a connect budget an
unreachable server spent the full 60s default request timeout (with the
SSE transport stuck in a reconnect loop), stalling session.create past
the hub deadline and tearing the whole session down - the interactive
TUI exited and one-shot runs failed. Stdio servers already have a
bounded initialize budget for exactly this reason; give URL clients the
same treatment with a 10s default connect budget that an explicit
timeout overrides in either direction.
Fixes#13597
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat: add searchable session history
Rebased onto main and updated to supersede the sidebar search dialog
from #13533: the sidebar search icon now opens the indexed command bar
(Cmd/Ctrl+P) instead of a sidebar-local cmdk dialog that eagerly loaded
the entire session history via loadAllSessions(). CommandDialog gains a
shouldFilter passthrough so server-ranked FTS hits are displayed as-is.
* fix: harden session history search
* fix: evict failed restoration sessions from search
* fix: preserve deletion when search eviction fails
* fix: address session search review feedback
* fix: preserve search suppression during reconciliation
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
The VS Code Rules tab resolves the Documents folder via
'xdg-user-dir DOCUMENTS', which prints bare $HOME when no user-dirs
config exists (WSL/headless installs), so it reads and writes global
rules at ~/Cline/Rules. The SDK's rule search paths only covered
~/Documents/Cline/Rules, so those rules never reached the system prompt.
Add the missing path to the search list.
Fixes#13542
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): hide history cost estimates for subscription-billed tasks
The task-header fix for subscription providers cannot reach history:
history rows render the stored totalCost (an API-rate estimate) and do
not know which provider ran the task, so the history page printed
$X.XXXX on every row and the recent-task chips in an empty chat view
rendered a $ chip even for subscription-billed tasks.
The SDK session records already persist the provider — the CLI's
history view uses it for exactly this — but the VS Code mappers dropped
it. Map it through both transports (HistoryItem.apiProvider for the
state-pushed taskHistory, TaskItem.api_provider for getTaskHistory) and
suppress the dollar figure per row when that provider's
usageCostDisplay is not "show", via a new useUsageCostVisibility
predicate shared by both surfaces.
Rows without a recorded provider (tasks predating the field, legacy
imports) keep showing the stored value — there is nothing to key
suppression on.
* test(vscode): e2e-verify history cost suppression in real VS Code
Seeds SDK session records (one openai-codex subscription task, one
anthropic usage-billed task) into the isolated CLINE_DIR before the
webview loads, then asserts in a real VS Code instance that both the
recent-task chips and the full history page render the dollar figure
only for the usage-billed task. Covers the two boundaries the unit
tests stub: on-disk records reaching getTaskHistory with provider
populated, and the provider listings delivering the subscription mark
to the webview.
* fix(core): refuse checkpoint workspace restore when HEAD moved past the checkpoint
Restoring a checkpoint runs git reset --hard, which moves the current
branch pointer. If commits were made after the checkpoint (by the user
or by the agent), the reset silently knocked them off the branch,
leaving them reachable only through the reflog.
Guard the reset: if HEAD no longer matches the commit the checkpoint
was created on, throw a descriptive error (including how many commits
would be dropped) instead of destroying history. Chat-only restore is
unaffected, and users who really want to discard the commits can reset
the branch manually first.
Fixes#13550
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): close the guard-to-reset race with an atomic ref update
The moved-HEAD guard read HEAD, ran further git commands, then reset
unconditionally, so a commit landing in that window could still be
knocked off the branch. Replace the reset's branch move with git's
native compare-and-swap (git update-ref HEAD <new> <old>), which fails
if HEAD no longer points at the verified commit, and follow with a bare
reset --hard to sync the index and worktree to the already-moved HEAD.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): don't show providers as configured without real credentials
The desktop settings marked any provider with a persisted settings entry
as Configured, but legacy VS Code migration and empty saves can seed
entries (e.g. qwen-code, sapaicore) holding only a default model and no
credentials. Move the CLI's isProviderSettingsUsable readiness check into
@cline/core, expose it as a computed 'configured' flag on the provider
catalog, and use it in the desktop's isProviderConnected.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): resync catalog after saves so Configured badge updates live
Optimistic provider mutations can't know the sidecar-computed 'configured'
flag, so after connecting a keyless provider or saving cloud credentials
(e.g. a Vertex project id) the row stayed 'Not configured' until remount.
Silently refetch the catalog after each successful save, guarded by the
existing generation counter so newer edits discard stale responses.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): claim a generation in post-save resync so overlapping refreshes can't apply stale snapshots
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): bump catalog generation on OAuth login success
Every other optimistic provider mutation claims a new generation; the
OAuth success path didn't, so a catalog load or resync still in flight
could arrive late and overwrite the just-connected state.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): resync catalog after OAuth login instead of bare generation bump
The resync claims a new generation (discarding any stale in-flight
response) and its own fetch covers both the new OAuth connection and any
provider saved moments earlier, matching the post-save path.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(core): anchor agent-created schedules in the user's .cline schedules home
Agent-created schedules inherited whichever workspace folder the chat
session happened to run in, scattering user-level routines across chat
and project folders. They were invisible to workspace-scoped listings
elsewhere, tied to folders that may be cleaned up, and each chat's
tasks tool saw a different set when checking for duplicates.
Anchor them in ~/.cline/schedules instead: the hub's scheduled-task
session defaults now resolve to that home (created on demand), so
agent-created schedules live and run in one stable user-level scope.
The tasks tool guidance now tells agents that scheduled sessions run in
the schedules home, so prompts must carry absolute paths to any project
they operate on.
Schedules created explicitly with a workspace (CLI --workspace, desktop
routine wizard) are unchanged, and existing rows keep their current
workspaceRoot - they stay visible through the all-workspaces listing
paths (#13613, #13633).
* test(core): restore any pre-existing CLINE_DIR after the agenda hub test
The test's cleanup deleted CLINE_DIR outright, so an environment that
had it configured would leave later tests in the same worker on the
default storage directory. Save the previous value and restore it.
* test(core): restore CLINE_DIR even when hub test setup throws early
Restoring the override in the try/finally missed failures thrown during
transport construction or start(), before the try was entered. Register
the restore with onTestFinished instead, which runs regardless of where
the test fails.
* fix: make OpenAI Codex sign-in fail loudly instead of silently dead-ending
When callback port 1455 is already in use (e.g. by the Codex CLI or a
previous pending sign-in), startLocalOAuthServer returns a no-op server
and loginOpenAICodex would open the browser anyway, then dead-end:
the callback could never be received, and in the VS Code extension the
user just saw nothing happen after clicking 'Sign in to OpenAI Codex'.
- loginOpenAICodex now fails fast with an actionable 'port in use'
error before opening the browser, unless the host provides manual
code entry (the CLI's paste fallback keeps working)
- surface OAuth redirect errors (e.g. access_denied) instead of
collapsing them into 'Missing authorization code'
- the extension dedupes concurrent sign-in clicks: a re-click re-opens
the auth page of the pending flow instead of spawning a second flow
that would collide with our own callback server
- browser-open failures now show an error message with the URL to
open manually instead of only logging
- abandoned-flow timeouts no longer surface a confusing 'Missing
authorization code' toast
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor: drop host-side codex login dedupe, keep flow identical to CLI
The SDK owns the failure handling now (fail-fast on an unbindable
callback port), so the extension keeps the exact same simple
loginOpenAICodex call the CLI uses. A second click while a flow is
pending gets the SDK's clear port-in-use error, same as running
'cline auth openai-codex' twice would. Keep only the CLI-parallel
onOpenUrlError surfacing (the CLI prints 'open the URL above
manually'; the extension's equivalent is an error toast with the
URL).
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* test(e2e): cover Codex sign-in callback-port failure and redirect errors
Two driven-VS Code tests for the OpenAI Codex (ChatGPT subscription)
sign-in flow:
- with port 1455 occupied on both loopback families, clicking the
sign-in button surfaces the fail-fast port-in-use toast
- with the port free, the callback server binds and an OAuth redirect
error (access_denied) propagates to a visible error toast
The second test opens a real browser tab to the OpenAI auth page as a
side effect of the genuine sign-in click.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Co-authored-by: Mikołaj Kondratek <19799111+mkondratek@users.noreply.github.com>
* fix(sdk): don't log out Codex/OCA users when token refresh fails transiently
Port the cline-provider refresh semantics to openai-codex and oca:
a transient refresh failure (network error, timeout, server 5xx) with an
already-expired access token now rethrows instead of returning null.
A null return means the refresh token was REJECTED and re-auth is
required; treating an outage blip as a rejection is what turned it into
a forced 'openai-codex requires re-authentication.' task stop while the
settings UI still showed the user as signed in.
Both providers also emit user.auth_refresh_soft_failure telemetry on
transient failures (the 'prevented logout' counter the cline provider
already has) and attach status/errorCode details to the genuine
invalid_grant logout event.
* refactor: collapse duplicate soft-failure telemetry branches and test
Review feedback: compute tokenExpired once and emit the soft-failure
event once in both providers, then return current credentials or
rethrow. Fold the codex soft-failure telemetry assertions into the
existing still-usable-token test instead of a near-duplicate case.
* fix(core): stop watching agenda spec dirs while the todo tool is disabled
Since #13530 disabled the agent todo tool, the Agenda UI, and the
automation pump, the hub still created fs.watch watchers on the global
agenda specs dir and on every workspace root recorded in the task store
(at startup and on scope access). Nothing consumes the watcher-driven
task events while the feature is off, and the task.* hub commands
already reconcile spec files on demand, so the watchers are pure
overhead - one OS watch handle per known workspace.
Wire watchFiles to AGENDA_TODO_TOOL_ENABLED the same way
automationEnabled is, preserving a host's explicit watchFiles opt-out
for when the flag is turned back on. Schedules are unaffected: the
schedule list has no file watcher and updates through hub commands and
published schedule events.
* fix(core): reconcile external spec edits inside updateTask
With the spec watchers off there is no background reconciliation, so a
task spec edited directly on disk made every same-store task.update fail
the signature check with "task spec changed outside the manager" until
an unrelated task.get or task.list happened to reconcile the scope.
Reconcile the task's scope at the start of updateTask (mirroring what
refreshAndVerifyTaskIntent already does for approve/run), skipping it
when the file reconciler itself is the caller to avoid recursing from
reconcileFileStore. An external edit now surfaces as the store's normal
stale-revision conflict, and a re-read-and-retry succeeds. This also
closes the pre-existing watcher debounce race for updates.
- Defer updater installation to the user-initiated restart on Windows:
install() launches the NSIS installer and exits the process immediately,
so the background cycle now downloads only and stages the bytes, and
restart_to_apply_update installs them after stopping the sidecar.
- Spawn child processes (sidecar, git, cmd /C start) with CREATE_NO_WINDOW
so the GUI-subsystem app doesn't pop visible console windows.
- Fall back to USERPROFILE when HOME is unset resolving the MCP settings
path, matching the sidecar's homedir().
- Reap the sidecar after the Windows hard-kill so its exe file lock is
released before the NSIS installer replaces it.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): show agent-created schedules on the Schedules page
Schedule hub commands are scoped to the workspace registered by the
connection, but the desktop app's hub client registers the app launch
directory while agent-created schedules live under each chat's own
workspace folder - so they never appeared on the Schedules page.
Grant token-authenticated hub connections (which can already bind any
workspace at registration) explicit cross-workspace schedule access via
an allWorkspaces payload flag, and have the desktop sidecar request it
for routine schedule commands. Workspace-bound clients (local browser
origins) and default CLI behavior stay scoped.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(core): strip allWorkspaces flag from schedule inputs and pin it in the sidecar payload
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(core): tunnel ProtoBus over Host Bridge
* fix(core): harden Host Bridge stream lifecycle
* fix(core): serialize concurrent chunked responses per request
Streaming handlers deliver updates fire-and-forget, so two logical
responses for one request_id can be in flight at once. Chunked payloads
made forwarding non-atomic: each chunk write is an await, so concurrent
forwards could interleave their chunk sequences and the receiver --
which reassembles purely by arrival order -- would splice two payloads
into one. Route all forwards for a request through one promise chain; a
failed write rejects every later forward so a torn payload is never
followed by more chunks.
Rename the lock manager's instanceAddress to instanceOwner: it holds an
opaque per-spawn instance ID on the token path and a listener address
only on the CLI-harness path. Delete the caller-less getInstanceByPort
query that interpreted the owner as an address.
Also: document message_json as a legal wire encoding for small
payloads, close the gRPC client when startup fails, note the
intentional discard of the cancellation confirmation, and add the
proto's trailing newline.
---------
Co-authored-by: Cline Agent <cline-agent@users.noreply.github.com>
* fix(hub): stop shipping full transcripts inside broadcast hub events
Every session.updated (and session.created/detached/run.started) event
embedded the session's ENTIRE message transcript via readCoreSessionSnapshot,
even though no consumer reads snapshot.messages off an event — clients fetch
messages with the session.messages command. For a multi-megabyte transcript
this turns every status flip into megabytes per subscriber, floods the
durable event log, and (until the send-queue backpressure fix lands) lets a
slow subscriber balloon the hub process by one full transcript copy per
event — reported as a 25GB cline process on a 16GB Mac.
Strip snapshot.messages centrally in HubServerTransport.publish() so every
current and future event publisher is covered, the event log stores slim
envelopes, and cursor replay stays byte-identical with live fan-out. All
other snapshot fields (status, usage, model, workspace, checkpoint) are kept,
and command replies are untouched.
* fix(hub): never capture the transcript into event/reply snapshots
Replaces the publish-boundary strip with the real fix: don't build
message-bearing snapshots in the first place. emitSessionSnapshot no longer
re-reads the entire transcript from disk on every status flip, and
readCoreSessionSnapshot no longer reads it for any event or reply — a
snapshot is a state notification (status, usage, model, workspace,
checkpoint); the transcript is fetched via the session.messages command.
Checkpoint-restore snapshots (session-versioning-service) are untouched:
restore replies carry messages in their own dedicated field.
* fix: install marketplace plugins and MCP servers in-process instead of spawning a cline binary
The desktop app sidecar and cline-hub shelled out to 'cline plugin install'
and 'cline mcp install' for marketplace installs. Packaged GUI apps inherit
launchd's minimal PATH on macOS and most desktop users have no cline CLI
installed at all, so installs failed with a red
'Executable not found in $PATH: "cline"' error.
Install via @cline/core's installPlugin/installMcpServer in-process instead,
matching what the VS Code extension already does. Also fix
parseMcpInstallArgs in @cline/core to treat the marketplace catalog's '--'
separator as end-of-options; previously the separator itself became the
stdio command.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor: drop test-injection plumbing from marketplace installers
Call @cline/core's installPlugin directly instead of threading an
installer option through the marketplace entry points; tests stub the
core module instead.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* revert: keep cline-hub marketplace installs CLI-backed
The hub dashboard is launched via 'cline dashboard', so a CLI is always
present and CLINE_WRAPPER_PATH resolves it; the PATH bug only affects
the desktop app, which does not ship a CLI.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Each session row shows a trash icon on the right while hovered (or
when the button itself is focused), opening the same delete
confirmation dialog the row's context menu uses. The row is a button
and buttons cannot nest, so the trash is an absolutely positioned
sibling inside a group/row wrapper, overlaid where the timestamp sits:
row hover hides the timestamp, shows the trash, and moves the row's
hover background to the wrapper group so it holds while the pointer is
on the trash itself.
Quitting the mac app beach-balled for ~5-7s. The shutdown POST was
built from the ws transport URL (appending /shutdown lands inside the
query string), so the sidecar was never told to exit, and stop() then
polled the child for up to 7s on the main thread - on macOS inside
applicationWillTerminate - before SIGKILLing it.
stop() now sends SIGTERM and returns immediately. The sidecar handles
SIGTERM with the same bounded (5s) graceful shutdown as the /shutdown
endpoint and exits itself, finishing session persistence as an orphan.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(desktop): merge schedule details into one view and open run-now sessions
The schedule details dialog drops its Overview/Runs tabs: one scrollable
column with the meta grid, the configuration JSON (capped at max-h-64
with internal scroll so it cannot crowd out what follows), and a Runs
section beneath it showing the three most recent runs with a ghost
"Show all N runs" expander (collapsed again whenever a different
schedule's details open). The "Full configuration for this schedule"
subtext is gone; the dialog passes aria-describedby={undefined} so
Radix does not warn about the missing description.
Run now hands you into the session it starts. The trigger command
queues the run and returns before the runner attaches a session id, so
after the toast the handler polls the schedule overview once a second
for up to 15 seconds — which doubles as keeping the page's run status
fresh (refreshSchedules now returns the fetched overview to make that
single-stream) — until the triggered execution reports its session id,
then calls onOpenSession. Guarded so it never auto-navigates after the
user left the page.
* feat(desktop): hide runtime steering messages from transcripts
Scheduled/automation runs inject user-role steering messages each
iteration ("[SYSTEM] This run is not complete until you call
submit_and_exit...", plus a team-obligations variant). The chat view
rendered them as user bubbles, as if the person had typed them — in a
scheduled session the transcript was mostly [SYSTEM] noise.
They are machinery talking to the model, not something the person said
or needs to read, so the transcript now hides them entirely:
MessageBubble renders null for any [SYSTEM]-prefixed user message.
Grouping still treats them as working-row machinery via a single
isSystemSteeringMessage predicate — they collapse into the run's work
span, are never a turn boundary, can never be mistaken for a run's
answer, and never advance the run count even when metadata is missing —
so work-block folding and checkpoint/edit run numbering stay correct.
A finished scheduled session now reads as prompt, work summary, answer.
* fix(desktop): poll history while an attached session's event stream is dead
Opening a scheduled session while (or right after) it runs left the
view stuck on the thinking shimmer until the user switched away and
back. Root cause is in core: the hub daemon executes scheduled runs on
a private LocalRuntimeHost inside createLocalHubScheduleRuntimeHandlers,
while the hub server only projects live events from its own session
host — so session.attach succeeds but no assistant/tool/status events
ever flow. And since multiple hub daemons share cron.db, a run claimed
by a different daemon is invisible to this hub regardless. The proper
core rewiring is tracked as ENG-2474.
Client-side heal that covers every case: while an attached history
session reports a busy status and no chat_event chunk has arrived for
five seconds (and no assistant bubble is mid-stream), poll every three
seconds — re-read canonical history, merged through the same dedupe
path hydration uses, and the session record's status — so the
transcript and the thinking indicator settle in place. Locally driven
turns keep chunks flowing, so the quiet-window guard keeps the fallback
inert there.
* chore(desktop): format workspace selector components
Biome formatting drift that landed on main; picked up by a formatter
pass over components/views/chat.
* fix(desktop): keep stale-stream poll inert during locally driven turns
The fallback poll could fire between a local submit and the model's
first chunk (optimistic user bubble added, stream quiet past the
window, no assistant bubble yet). It then replaced the optimistic
bubble — raw prompt text — with its canonical history twin, which is
stored wrapped in a user_input envelope. The rekey handler that runs
when the stream starts looks for a trailing user bubble matching the
raw prompt, finds only the wrapped copy, and appends a second bubble:
duplicated messages in normal interactive chat.
The poll now stays inert while a local turn is in flight
(turnEpoch !== turnSettledEpoch, or outstanding optimistic user
messages), checked both before polling and again after the snapshot
returns. Hydration marks the turn settled — the mount defaults
(epoch 0, settled -1) otherwise read as an open turn and would keep
the fallback inert forever for the scheduled-session case it exists
for. Applying a polled snapshot also rebuilds the live tool routing
keys, same as hydration, so later tool events update canonical rows
in place instead of appending.
* fix(desktop): keep the working indicator alive for narrating scheduled runs
Watching a scheduled run live: the first tool row appeared, then the
thinking indicator vanished with nothing streaming, and the rest of
the run (final answer, submit_and_exit) only showed up seconds later
in one lump.
inferHydratedChatStatus treats a "running" session record whose
transcript ends on an assistant message as a session that died without
a status flip and reports "completed". That heuristic is right for
stale records, but scheduled/automation models narrate between tool
calls, so a polled snapshot can genuinely end on assistant text
mid-run — the completed flip hid the working indicator, folded the
run early, and disarmed the stale-stream poll (status left the busy
set), dead-ending live updates until an in-flight poll happened to
deliver the finished run.
The heuristic now only applies once the transcript has actually gone
quiet (newest message older than two minutes — comfortably past model
latency plus tool runs). A recently active transcript keeps the
record's "running" verdict, so the indicator stays up and polling
stays armed until the record itself settles.
* fix(desktop): stale-stream poll mirrors the session record instead of inferring
Replaces the previous fix for the vanishing working indicator (the
time-window guard added to inferHydratedChatStatus) with a version
that adds no inference at all: the heuristic is restored to exactly
its long-standing form, and the poll now maps the session record's
status verbatim (mapSessionRecordStatus).
The record is the right authority in the poll's context: the sessions
this fallback serves have a live host maintaining their record, and it
flips to a terminal status when the run ends. Transcript-shape
inference belongs only where it has always lived — hydrating sessions
whose records may be orphaned — and would misread a mid-run snapshot
ending on assistant narration as a finished session, hiding the
working indicator and disarming the poll.
* fix(desktop): address review findings on steering detection and run-now matching
Steering detection additionally requires the injected-message marker
(meta.userRunSpan === 0) beside the [SYSTEM] prefix, so a person's
genuine prompt that happens to start with "[SYSTEM]" stays visible
and turn-counted. The failure direction is deliberate: an unstamped
injected reminder would merely show as a user bubble, while the
content-only check could hide a real prompt.
Run-now only follows the execution id the trigger reply itself named;
the newest-execution-for-this-schedule fallback could open a previous
run's session when the trigger failed to enqueue one.
* fix(desktop): report a failed run-now instead of confirming a start
A trigger reply without an execution means no run was enqueued (the
schedule may have been disabled or deleted since the page loaded). The
handler previously toasted "Run started" regardless and then silently
skipped the session-open polling. It now shows a destructive
"Run not started" toast, refreshes the schedule list so the row
reflects reality, and skips the polling entirely.
* feat(desktop): split Customize into Installed and Marketplace pages
The Customize hub previously embedded a Browse section inside every tab
that had a catalog. That inlining made each tab long and buried the
catalog. Customize is now the installed inventory only (skills, MCP,
plugins, rules, hooks, tools tabs pass marketplaceVariant="installed"
to the embedded MarketplaceView; McpServersContent grew the same prop),
with an outline Marketplace button in the header.
Browsing moved to a dedicated Marketplace settings section that renders
the previously dead "directory" variant of MarketplaceView: one list
across all catalog types with type-filter chips, wrapping tag chips,
and light rules separating the filter tiers from each other and from
the results. The Clear control now renders inline at the end of the tag
row only while a tag is active, the Updated date is gone, and the
header hosts an Installed button mirroring the one on the Customize
page. Directory subheader copy: "A curated set of plugins, MCP
servers, and skills from the Cline community."
Tag and type chips wrap to new lines instead of scrolling
horizontally.
* feat(desktop): sidebar time view with sections, sort toggle, and scheduled detection
Restores the time-sorted session list as the default sidebar view, with
collapsible Pinned / Scheduled / Tasks sections (headers appear only
once something is pinned or scheduled) and the page-fill effect that
grows the fetched history window until a Show-more click makes visible
progress. Project grouping stays as the alternate mode behind a
one-click sort toggle whose icon reflects the active mode — the old
dropdown cost an extra click for a two-option choice.
Scheduled sessions are detected two ways: the hub-schedule origin
trigger in session metadata, plus a fallback that asks the hub which
session ids belong to schedule executions (list_routine_schedules,
fetched on mount and every two minutes, merged into a rolling set).
The fallback matters because locally executed scheduled runs do not
reliably stamp the trigger into session metadata — a real scheduled
session created today carried only {mode:"user"} provenance. The
scheduled clock icon now leads the row, left of the title; pin and
timestamp stay on the right.
The initial visible page grows from 10 to 30 rows so a tall sidebar
fills instead of stranding a stub of rows over empty space (history
fetches already start at 50).
The expanded sidebar's Customize row now hosts indented Installed and
Marketplace sub-tabs while a customize section is open; the active
sub-tab carries the full selected background while the parent keeps a
subtler one so the two simultaneous highlights read differently.
Also fixes the hover-card flash on click (logo card and session-row
cards): Radix HoverCardContent sits on a DismissableLayer, so a click
on the trigger registers as a pointer-down outside the card and
dismisses it, and the trigger's focus event immediately reopens it.
onPointerDownOutside preventDefault suppresses the dismissal; cards
still close on pointer leave.
* feat(desktop): schedule page row, dialog, and details UX polish
Schedule cards are now click targets: clicking anywhere on a card
outside its controls opens the details dialog (guarded via
closest("button,...") since every inline control, including the Radix
switch, renders a button element), with Enter/Space keyboard support.
The redundant eye button is gone. The remaining edit / run / pause /
delete buttons grow from the 12px icon-sm size to 28px targets with
16px icons, sized consistently with the adjacent enable toggle — the
icons use explicit size-4 classes so the Button base svg rule cannot
shrink them back.
The new/edit dialog gains breathing room between field labels and their
inputs (space-y-2 per field wrapper).
The details dialog no longer scrolls as a whole when the schedule JSON
is long: the dialog is a flex column capped at 85vh, the JSON pre
shrinks to the remaining space (min-h-0) and scrolls internally, and
the Runs tab list scrolls inside the tab the same way.
* feat(desktop): add Retina DMG background tooling
* feat(desktop): customize the macOS DMG layout
* ci(desktop): validate DMG background assets
* fix(desktop): adjust DMG Applications icon position
* ci(desktop): drop redundant DMG artwork validation from publish workflow
Tauri's beforeBuildCommand already runs dmg:background (with its own
validation) at the start of the build/sign/notarize step, and the
release/beta config overlays do not override the build section, so this
step duplicated work the publish job performs anyway. PR-time coverage
lives in desktop-test.yml.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): stop showing cost estimates for subscription-billed providers
Providers whose usage is covered by a flat-rate subscription (ChatGPT
Plus/Pro via openai-codex, ClinePass) are marked with
metadata.usageCostDisplay = "subscription" in the SDK, and the CLI
already suppresses dollar figures for them. The VS Code host collapsed
that value into "show" before it reached the webview, so the task
header and model pricing rows rendered API-rate cost estimates that
users read as real charges on top of their subscription.
Pass all three usageCostDisplay values ("show" | "hide" |
"subscription") through the catalog listing and render cost only when
the value is "show", matching the CLI's shouldShowCliUsageCost
policy.
* feat(llms): mark Claude Code as a subscription-billed provider
Claude Code is typically authenticated with a Claude Pro/Max
subscription, but its models reuse Anthropic API pricing metadata, so
Cline rendered per-token prices and API-rate cost estimates for usage
that is covered by the subscription. Set usageCostDisplay =
"subscription" on the provider (picked up by the CLI and the VS Code
webview) and suppress the price rows in the Claude Code settings card.
The Claude Code CLI can also run on API-key billing, where a real cost
exists; the provider cannot distinguish the two, so we prefer showing
no number over a misleading one.
* fix(vscode): suppress cost display until provider listings load
While the ListProviders request is in flight (or after it fails), the
usage-cost hook had no listing to consult and fell back to "show",
flashing the API-rate estimate at subscription users on every chat-view
mount — the exact display the previous commit removes. Return
"unknown" whenever listings are absent; consumers already render cost
only for "show", so they suppress it during that window with no
changes. Briefly hiding a real cost is harmless, briefly showing a fake
charge is not.
* capture richer workspace information for vs code extension
* fix(shared): redact credentials from workspace remotes
* fix(shared): avoid regex backtracking in remote redaction
---------
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
The model picker renders a radiogroup of styled buttons with role=radio
and aria-checked; biome's useSemanticElements flags the role as an
error, which fails the sdk-test Quality Checks lint for every PR
touching sdk/ or apps/ paths. Suppress with a justification — switching
to input type=radio needs a restyle and belongs to the desktop settings
work.
* feat(desktop): merge customization pages into a Customize hub with inline marketplace
Replaces the Plugins page and the dedicated Marketplace page with a single
Customize hub. Tabs: Skills, MCP, Plugins, Rules, Hooks, Tools, each with
live counts. Tabs backed by a marketplace catalog render the installed
items followed by an inline browsable Browse section (CLI-hub style), so
installing from the catalog immediately reflects in Installed above.
- Installed cards restyled to mirror the browse-card anatomy: bg-card p-4
containers, absolute top-right xs Uninstall matching Install, truncating
semibold titles, primary-tinted icons, real Badge components instead of
ad-hoc bordered spans, un-indented line-clamped descriptions
- Rules/Hooks/Tools rows brought into the same card language; redundant
intro paragraphs (duplicating the page description) removed; Tools group
headers match the Installed header style with counts
- Marketplace section header renamed to Browse; duplicate 'N results' row
removed (the header count is the single source)
- MCP embedded view now shows the full marketplace instead of
installed-only
* feat(desktop): overhaul sidebar sessions and navigation
Sessions list:
- Sort toggle removed; sessions are always grouped by project, with pinned
sessions leading each group (both subsets ordered by recency). The
Pinned/Scheduled/Tasks category sections and their time-mode paging
machinery (page-fill effect included) are deleted
- Scheduled sessions get an inline clock icon next to the pin position;
pin + clock render together when both apply, and the running/unread
status dot now coexists with them
- One font size (text-sm) across the list: titles, timestamps, project
headers, show-more buttons, empty states. sidebarText needed !text-sm
because the default button size's text-base wins the twMerge conflict
- Gradient fade under the Sessions header once the list scrolls, so rows
fade out instead of hard-clipping
- The session-detail hover card is controlled from the sidebar and closes
on scroll (Radix receives no pointer events while scrolling, so it used
to float over moving content)
- Sidebar min resize width raised 224->260px; the per-project show-more
label truncates so its nowrap text can't force rows to overflow and clip
timestamps at narrow widths
Navigation:
- Customize replaces the Plugins/Marketplace/Hooks/Rules/Tools sidebar
entries; Schedules and Customize are hidden from the expanded settings
nav (their top rows cover them) but stay reachable when collapsed
- The settings gear always opens General instead of resuming the last
section; the Account no-op hover special case is gone
- The New row highlights (aria-current) while the fresh not-yet-started
task page is showing and hands off to the session row once the task
starts; hitting New also focuses the prompt input via a window-event
signal (lib/prompt-input-focus.ts) since the sidebar and composer sit in
distant subtrees
- Fixed the xs button size collapsing any icon-bearing button to 12x12
(leftover has-[>svg]:size-3 from when xs was a micro button) — this was
why Uninstall buttons rendered broken next to Install
* feat(desktop): polish settings pages and chat composer
Models page:
- The provider detail panel is always open: no X button, no empty
no-selection state. It defaults to the first connected provider (falling
back to the first in the catalog), which also removes the layout shift
that happened when the page swapped between full-width and panel
variants on selection
- Fixed the list pane becoming unscrollable while the panel was open:
grid items default to min-size auto, so the pane grew past its track
inside the overflow-hidden grid and its ScrollArea had nothing to
scroll; wrapped it in a min-h-0 min-w-0 cell
- Add Provider opens a Dialog instead of swapping the page
(AddProviderContent gained a dialog variant that renders only the form)
- Embedded inputs (provider search, model search, detail fields) share one
EMBEDDED_INPUT_CLASS stripping the Input component's own border/dark bg
tint/shadow/ring, which rendered as a mismatched inner box; the model
search box uses the same h-9/px-3 frame as the provider search
- Model list flows with the page instead of a max-h capped inner scroller
Other pages:
- Account uses the shared PageFrame/PageHeader: left-aligned, text-3xl
title, Sign Out in the header actions slot
- Desktop notifications is one General section: header row plus the
Event/Notify/Sound matrix nested in a card, so its rows no longer read
as top-level peers of Dark mode; 'Available in the desktop app' label
removed
- Schedule page retitled from Schedules with a real description; Customize
description rewritten
Chat composer:
- The voice dictation button only renders once a voice model is
configured (Settings -> Voice); the unconfigured deep-link state is
gone (prop type kept for an easy restore)
* Redesign desktop Model Providers page and split voice input into its own settings page
- Group providers into Connected / Popular / All with auth-kind hints and
connection status instead of per-row enable toggles
- Show browser sign-in (not an API key field) for OAuth providers, with a
collapsed manual-key escape hatch where supported, plus explicit
Connect / Disconnect / Sign out actions
- Move voice input to a dedicated Settings > Voice page that only offers
connected transcription-capable providers, preselects a default model
(streaming preferred), and stays disabled in the sidebar until a
provider is connected
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Show native tooltip on the disabled Voice settings nav item
Disabled buttons drop pointer events, so the 'connect a model provider'
hint moves to a wrapping span for the browser tooltip to render.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Drop letter avatars and gray provider ids from provider rows and voice chips
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Drop model counts from provider list rows
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Rename provider Connected status to Configured and drop the green styling
A settings entry is configuration, not a live connection; neutral gray
text avoids implying an active link, since the user still picks which
configured provider to use per chat.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Resync provider catalog from disk when a settings save fails
Connect/disconnect/credential edits update the list optimistically; a
failed save now reloads the catalog instead of leaving the optimistic
state (and the view's module cache) claiming a configuration that was
never persisted.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Rename oauthProvider test fixture to dodge CodeQL name heuristic
CodeQL's clear-text-storage query flags any identifier matching 'oauth'
as a credential source and traced the fixture's provider id into the
favorite-models localStorage write, which stores only provider/model id
strings. Renaming the fixture removes the false-positive source.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Guard catalog reloads against races and resync detail drafts on failed saves
Optimistic provider mutations now bump a generation that discards any
in-flight catalog response, so a failed-save recovery reload can't
overwrite a newer edit with an older disk snapshot. The recovery also
remounts the provider detail panel via a reset token so its local field
drafts reflect the reloaded on-disk state instead of unpersisted edits
or an optimistically cleared disconnect.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix failed-save recovery ordering and retry superseded reloads
Remount the provider detail only after the authoritative catalog reload
lands, so its drafts re-seed from disk state rather than the optimistic
values that failed to persist. When a concurrent edit supersedes the
recovery's in-flight response, retry the reload (bounded) instead of
dropping it, since that edit performs no reload of its own.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Add Pinned/Scheduled/Tasks categories to desktop app sidebar
Replace the Schedules and Favorites filter-menu options with visible
collapsible category sections in the session sidebar, and rename the
Favorite action to Pin across the sidebar and sessions view.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Grow full history window when Tasks show-more outpaces loaded tasks
loadMoreSessions treats its argument as a limit on all sessions, but the
Tasks show-more count only tracks Task rows, so once pinned/scheduled
rows pushed the loaded total past the requested count the call no-oped
and clicks went dead. Grow the whole history window via
loadOlderSessions instead, and only when the loaded tasks cannot fill
the next page. Addresses Greptile review on #13528.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Auto-fill the Tasks page instead of fetching once per show-more click
A single 50-session window growth can consist entirely of pinned or
scheduled sessions, leaving a show-more click with no visible Tasks
progress. Replace the one-shot fetch with a page-fill effect that keeps
growing the history window until the requested Tasks page fills or
history runs out. Addresses the follow-up Greptile review on #13528.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Halt page-fill retries after a failed history fetch
A failed fetch leaves the task count and has-more state unchanged,
which are exactly the conditions the page-fill effect fires on, so one
failing request would retry and re-toast forever. Halt the effect after
a failure and let the next explicit show-more click retry. Addresses
the third Greptile review on #13528.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: clean up sidebar navigation chrome
- Give New Task its own full-width labeled row below the logo row
instead of an ambiguous icon next to the agenda toggle
- Wire the New Task row to the home action so starting a new task
clearly takes you home (the logo still works as a fallback)
- Swap back/forward chevrons for browser-style arrow icons and
bump their size
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: sidebar New/Schedule/Customize rows and always-visible search
- Stack New (plus icon), Schedule, and Customize as full-width labeled
rows below the logo; whole row highlights on hover via sidebarItem
- New starts a fresh task (home), Schedule opens Settings > Schedules,
Customize opens the Customizations sections (Plugins first)
- Show the session search bar permanently above the sessions list
instead of hiding it behind a search icon toggle
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: move session search into a dialog behind a logo-row icon
- Replace the inline sidebar search bar with a search icon in the
logo row that opens a cmdk command dialog listing sessions
- Selecting a result opens that session and closes the dialog
- Remove the agenda/tasks toggle the icon replaces, along with the
now-unreachable sidebar Agenda panel (the welcome screen still
surfaces agenda tasks)
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: load full session history when the search dialog opens
Addresses Greptile review on #13533: the dialog only searched the
currently loaded history batch, so older unloaded sessions could not
be found. Opening search now kicks off loadAllSessions() (the hook's
purpose-built global-search loader), and the empty state reads
'Searching older sessions...' while more history is streaming in.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(vscode): remove per-tool MCP auto-approve checkboxes from webview
MCP auto-approval is now governed solely by the global 'Use MCP servers'
toggle; the SDK approval path (shared with the CLI and desktop app) has no
per-tool granularity, so the per-tool and 'Auto-approve all tools'
checkboxes were no-ops that implied control that no longer exists. Remove
them from the MCP settings view and chat tool rows. The autoApprove arrays
in cline_mcp_settings.json and the toggleToolAutoApprove RPC are left
intact for the legacy extension.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(vscode): hide per-tool MCP auto-approve checkboxes behind a flag
Keep the checkbox components, handlers, and RPC plumbing intact but gate
rendering behind SHOW_MCP_PER_TOOL_AUTO_APPROVE=false: the SDK approval
path (shared with the CLI and desktop app) is all-or-nothing via the
global 'Use MCP servers' toggle, so the per-tool checkboxes were no-ops.
Flip the flag back on if the SDK gains per-tool approval granularity.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): prevent search_codebase from crashing the process on giant single-line files
searchWithRipgrep buffered all of rg's --json stdout into one string. Each
JSON event embeds the full text of the matched line (--max-columns is
ignored in JSON mode), so searching a directory of serialized trace dumps
(single-line multi-hundred-MB JSON files) accumulated gigabytes of stdout
until string concatenation threw RangeError: Out of memory inside the
stream data handler. That throw is outside the tool's try/catch, so it
escalated to an uncaughtException and killed the CLI/hub daemon.
Parse rg's JSON events incrementally line by line, drop events larger
than 256KB, truncate matched/context lines to MAX_LINE_CHARS, and stop
reading once maxResults is reached. The fallback regex scan now skips
files larger than 10MB (reporting the skip count) and truncates its
context lines the same way.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* simplify search_codebase crash fix to a minimal diff
Replace the incremental JSON-event parser with three small guards: stop
buffering rg stdout past 10MB, drop the trailing partial event before
parsing, and slice fallback context lines to MAX_LINE_CHARS. Drops the
fallback file-size skip and skip-count reporting.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The /shutdown handler queued teardown on a microtask, which runs before
the event loop's write phase, so the daemon could process.exit() before
the accepted 202 was handed to the socket. Unix masked it (uv_try_write
lands small loopback writes synchronously); Windows has no such fast
path and lost the race regularly — the recurring shutdown.e2e.test.ts
'socket hang up' failures on windows-latest. Start teardown from the
response's write callback instead, with an idempotent 1s fallback so a
client that vanishes mid-write cannot strand the daemon, and send
Connection: close so the client gets a FIN rather than an abort.
Since the flakiness this compensated for is fixed at the source, restore
maxWorkers: 2 for the Windows core suite (serializing it cost ~3 min of
CI per run), and raise the e2e daemon discovery hang guard 10s→30s —
it guards against hangs, not runner speed.
ci-node-smoke.ts installs the packed SDK tarballs with a plain npm
install in a fresh temp dir, where the repo root package.json overrides
do not apply. When @sap-cloud-sdk 4.9.0 shipped (2026-08-24) it broke
@sap-ai-sdk/ai-api 2.14.0 (via @jerome-benoit/sap-ai-provider in
@cline/llms) with ERR_PACKAGE_PATH_NOT_EXPORTED, failing the smoke step
on every PR even though the root already pins @sap-cloud-sdk/* to 4.6.0.
Copy the root overrides block into the generated sandbox package.json
so the smoke install resolves the same pinned versions as the repo and
future third-party releases cannot break it independently.
* fix(hub): cap hub-events db size so it can't fill the disk
Row/time retention alone didn't bound disk usage: envelopes carrying
full session snapshots reach hundreds of KB each, so retained rows
could total tens of GB, sweeps only ran hourly, and DELETE never
shrinks a SQLite file. Enforce a 64 MiB size budget in prune() (oldest
rows first, VACUUM to return the space), and also prune after every
16 MiB appended so bursts can't outrun the hourly timer.
Fixes#13505
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(hub): tolerate VACUUM failure on a full disk
VACUUM needs scratch space and can fail in exactly the state a
ballooned event log causes. The byte-budget deletes already bound live
data, so swallow the error and let the next sweep retry the reclaim
instead of aborting startup pruning and disabling the durable log.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(hub): count the size budget in UTF-8 bytes, not characters
envelopeJson.length (UTF-16 units) and SQLite LENGTH() (characters)
undercount multibyte text by up to 3x, which could leave a CJK-heavy
log settled above budget and re-running VACUUM every sweep. Use
Buffer.byteLength and LENGTH(CAST(... AS BLOB)) instead.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): resolve hook workspace identity from the window, not shared global state
Hook discovery, hook cwd selection, and the workspaceRoots metadata passed
to hook scripts all read the workspaceRoots/primaryRootIndex global state
keys. Global state lives in ~/.cline and is shared by every Cline instance
(all VS Code windows, the CLI, the JetBrains plugin), and nothing writes
these keys anymore, so hooks resolved against whatever project some other
or older instance last recorded. With a second window open on another
project, a workspace's .clinerules/hooks scripts were never discovered.
Resolve workspace roots via a single guarded helper backed by
HostProvider.workspace.getWorkspacePaths() (in-process, window-scoped,
same as refreshHooks): blank paths are filtered, a host-bridge failure
degrades to no workspace roots instead of silently disabling global hooks
or skipping blocking PreToolUse guards, and one resolution is threaded
through hooks-dir discovery, cache misses, cwd selection, and hook input
metadata so they can't disagree (previously up to four host lookups per
hook execution — real gRPC round trips in the standalone host). Roots and
hooks dirs are matched on whole path segments with the longest root
winning, so prefix-sharing or nested workspace roots resolve to the right
project. The adapter creates the runner once per event and skips no-op
runners, making creation the single resolution point; the separate
hasHook/getHookInfo checks are removed. The dead workspaceRoots and
primaryRootIndex state keys are dropped, and the four hand-rolled
HostProvider.workspace test stubs are consolidated into one shared
helper.
* test(vscode): add e2e coverage for workspace-scoped hook discovery
Boots real VS Code with the packaged extension against the workspace
fixture, sends a prompt, and asserts the fixture's UserPromptSubmit hook
was discovered from the open window's workspace, executed with that
workspace root as its cwd, and received the same root in its
workspaceRoots input — the end-to-end contract the hook workspace
identity fix establishes.
* test(vscode): isolate the e2e hook fixture from the shared workspace
The UserPromptSubmit fixture hook lived in the shared e2e workspace, so
every prompt-sending spec executed it (hooksEnabled defaults to true) —
and its cold PowerShell spawn on Windows pushed chat.test.ts past the
5s expect timeout. hooks.test.ts now overrides workspaceDir to a
dedicated workspace-hooks fixture, so only the hooks spec pays the hook
spawn.
The $4.99 first-month promo is ending, so the CLI's first-launch "Try ClinePass" dialog should no longer advertise it. Also drops the leftover CLI_PROMO_CODE plumbing, which has been an empty string since the promo-code flow was removed.
* fix(vscode): honor MCP auto-approve settings for SDK tool calls
The SDK extension required both the global 'Use MCP servers' auto-approve
toggle AND each tool's per-tool autoApprove flag before silently approving
an MCP call, while the legacy extension treated them as either/or. Restore
the legacy OR semantics so toggling MCP auto-approve works again.
Also key toolPolicies by the registered SDK tool name (via
defaultMcpToolNameTransform, now exported from @cline/core) instead of raw
server__tool. Servers whose names contain sanitized characters (e.g.
marketplace names like github.com/user/repo) or exceed 64 chars produced
policy keys that never matched the registered tool, so those MCP tools ran
without any approval gate; the live auto-approve lookup now re-applies the
transform instead of string-splitting the name.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Revert "fix(vscode): honor MCP auto-approve settings for SDK tool calls"
This reverts commit 86c568fbba.
* fix(vscode): auto-approve all MCP tool calls when the MCP toggle is on
The SDK extension only auto-approved an MCP call when the global 'Use MCP
servers' auto-approve toggle AND that tool's per-tool autoApprove flag were
both set, so toggling MCP auto-approve appeared to do nothing and users had
to opt in each tool individually. The toggle alone now governs all MCP
tools; the per-tool flag is no longer consulted.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The task.completed fallback lived only inside shutdownSession, but
stopSession/dispose route interactive sessions with a terminal reported
status through releaseSessionRuntime, which never emitted. Truthful
session-status reporting (shipped in 4.1.11) re-routed a large share of
interactive stops onto that branch and silently dropped the event.
Route the emission through a single choke point,
emitTaskCompletedOnTeardown, called from both shutdownSession and
releaseSessionRuntime. The completion criterion no longer reads
session.status: interactive sessions use the recorded final-turn
outcome (lastInteractiveTurnFinishReason), non-interactive sessions
keep the existing input.status === "completed" logic. A new
taskCompletedEmitted flag (also set by the submit_and_exit observer)
enforces exactly one task.completed per session. failSession now
records the errored final turn so a stale "completed" from an earlier
turn can never leak into the teardown emission. Telemetry only; no
user-facing behavior changes.
Four consecutive SDK publish runs failed on windows-latest, each on a
different test, all of them plain timeouts: two @cline/shared SQLite
tests at the 5s vitest default, core's bash executor at 10s, and the hub
singleton endpoint test at 10s. The 2-core Windows runner spawns forks
and takes SQLite locks slowly enough to blow those budgets under load.
These timeouts guard against hangs; they are not timing assertions (the
one suite that does assert elapsed time, shutdown.e2e, was fixed by
removing file-level parallelism instead). Raise core to 20s and give
@cline/shared an explicit 15s in place of the inherited 5s default.
singleton.e2e.test.ts (added in #13468) spawns real daemons and runs for
~15s. Vitest's default file parallelism let it run alongside
shutdown.e2e.test.ts, whose assertions are wall-clock bound: discovery
within 10s, exit within 5s, and a 2s shutdown watchdog. On the 2-core
windows-latest runner that contention alone broke those budgets, failing
the shutdown test two different ways across runs — once never observing
discovery, once with the daemon forced to exit before its HTTP 202
flushed (socket hang up). The test passed on Windows before #13468 and
has failed every SDK publish run since.
* fix(core): seed tools capability when custom model capabilities are synthesized from boolean flags
For a models.json entry with no explicit capabilities list, toStoredModelInfo
synthesized a capability array purely from boolean convenience flags (e.g.
supportsReasoning: true -> ["reasoning"]). modelSupportsToolCalling fails open
only for a missing or empty list, so the synthesized non-empty list read as an
authoritative denial and silently stripped every tool definition from requests
to custom OpenAI-compatible models (#13463).
Seed "tools" whenever the list was not explicitly authored and the boolean
projections made it non-empty, preserving the fail-open contract. Explicitly
authored capability lists remain authoritative and can still disable tools.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* test(core): cover stale catalog capability overrides
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix: treat stored capability lists as non-authoritative for tool calling
The hasExplicitCapabilities guard still let two producers of tool-less
lists through:
- The VS Code legacy-override migration (legacyModelInfoToOverrides)
persists explicit partial lists like ["prompt-cache"] into models.json
for custom OpenAI-compatible models, which then read as an authoritative
"cannot call tools" and drop every tool - same symptom as #13463.
- Any hand- or UI-authored partial list on a non-catalog model.
Stored entries and user-authored provider metadata have no way to declare
"cannot call tools" (there is no supportsTools field, and every writer
that authors a full list includes "tools"), so seed "tools" into any
non-empty list for a language model. Only generated catalog capabilities
remain authoritative - a genuine no-tools catalog model stays that way -
and non-language models (e.g. image generation) never gain a tools claim.
Also make legacyModelInfoToOverrides write "tools" into the arrays it
fabricates, matching the providers.json migration, so models.json stops
being poisoned for older readers.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(hub): add drain and upgrade commands with replay support
* handles disconnection
* feat(hub): wire bot profiles, drain, and durable event/run-queue into the live transport
Completes the wiring the previous commits' primitives needed:
HubServerTransport gains isDraining(), hub.drain/hub.status/profile.get
command handling, and replayEventsAfter() (backed by the durable event
log), plus the sequence/sinceSequence wire types they depend on in
shared/hub.ts. run-queue-handlers.ts reads the active bot profile's
plugin roots when executing durable runs.
Also adds hub/profiles/: profile.json (identity/rules/plugins) ->
system prompt composition, --profile / CLINE_HUB_BOT_PROFILE
resolution, and the bundled cline-dad profile with its
cline_hub_support read-only diagnostics tool.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Revert "feat(hub): wire bot profiles, drain, and durable event/run-queue into the live transport"
This reverts commit 6696d5d202.
* fix(hub): dedupe replayed events by eventId, not just sequence
HubEventLogStore.append() returns a new envelope stamped with a
sequence rather than mutating the input, so a pending approval
re-issued sequence-less by subscribe() (it predates any durable-log
append) and its later sequence-stamped copy from the durable log are
two different objects carrying the same eventId. The replay-then-live
buffer in browser-websocket.ts only deduped by sequence, so the
sequence-less copy's guard never tripped and it was delivered a second
time when the buffer flushed after replay.
Track delivered eventIds alongside the sequence cursor; eventId
survives the append/stamp round-trip unchanged, so this dedupes the
exact-same logical event regardless of which copy arrives first.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix(hub): wire drain, durable event log, and run queue into the live transport
CI on this branch failed bun run build:sdk: browser-websocket.ts,
client/index.ts, and hub-websocket-server.ts (already on this branch)
reference sequence/sinceSequence, HubServerTransport.isDraining(), and
the "hub.drain" command — but the commit that reverted bot profiles
out of this branch also reverted this wiring, since it shared a commit
with the profiles work. That wiring is a hub concern, not a
bot-profiles one; split it back out.
- shared/hub.ts: sequence/sinceSequence types, run.enqueue/run.list/
hub.drain/hub.status/stream.replay capability, command, and event
names. profile.get intentionally excluded — stays bot-profiles-only.
- context.ts: isDraining() on HubTransportContext. botProfile field
intentionally excluded.
- hub-server-transport.ts: eventLog/runQueue fields and start/stop
lifecycle, publish() appends to the durable log, handleCommand cases
for run.enqueue/run.list/hub.drain/hub.status, drain-refusal check,
replayEventsAfter()/lastEventSequence(). startBotProfile()/
startHubSupportTool() and the profile.get case intentionally
excluded.
- run-queue-handlers.ts: added without handleProfileGet (needs
ctx.botProfile, which doesn't exist here).
- hub-upgrades.test.ts: added without its two bot-profile-injection
tests (they need a resolved bot profile to assert against).
Verified bun run build:sdk exits 0 (the exact CI command) and
bunx vitest run src/hub passes (311/312; the one failure is the
same pre-existing environment-timing flake already present before
this change).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix(hub): export instance-lock, event-log, and run-queue from the hub barrel
These landed as internal modules only; hub-server-transport.ts and
hub-websocket-server.ts import them by direct path, but nothing
re-exported them from the public @cline/core/hub surface the way
sibling discovery/server modules already are.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix(hub): wire the instance lock into the daemon entry point
The singleton lock (discovery/instance-lock.ts) and its consumption in
startHubWebSocketServer/ensureHubWebSocketServer were already on this
branch, but the daemon entry point's own half was not: retrying a bind
when a retiring predecessor still holds the lock, and exiting with a
distinct code (3) instead of the generic fatal path when a live Hub
already owns the data directory. Without this, a daemon racing a
retiring predecessor could fail outright instead of waiting the lock
out, and losing the singleton race looked identical to a crash.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix(hub): address drain/upgrade review findings (#13478)
- cline hub upgrade: check idleness at least once (--wait 0 works), reject
non-numeric --wait, and un-drain on every abort path so an aborted
upgrade can never leave the hub refusing new work
- add cline hub drain --off and the off query param to requestHubDrain so
POST /drain?off is reachable from shipped code
- HubEventLogStore/HubRunQueue: WAL journal mode + busy_timeout, and stamp
sequences from lastInsertRowid instead of SELECT MAX(sequence)
- HubInstanceLock.acquire: degrade to an unheld lock when SQLite is
unavailable instead of refusing hub startup; only BUSY/LOCKED still
raises HubLockHeldError
- ensureHubWebSocketServer: retire an unusable discovered hub through the
shared retireDiscoveredHub (busy hubs are attached to, drain precedes
shutdown, discovery cleared only when the hub actually retired)
- replay adapter: advance the cursor past eventId-deduped events, cap
replay pages, stop when the cursor stalls, and drop the dedupe set after
the buffered flush so it cannot grow for the socket lifetime
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(hub): derive the singleton e2e challenger cwd portably
The challenger's working directory was derived by round-tripping the
discovery path through a file: URL and stripping the last pathname
segment. On Windows that yields a POSIX-style '/C:/...' path, which is
not a valid spawn cwd, so the spawn fails ENOENT before the singleton
lock is ever contested and the Windows SDK test job goes red.
The data dir is simply the discovery file's parent: use dirname().
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The PublishNightly environment gained required reviewers, so each cron
run parked on approval, held the workflow's concurrency group, and
silently cancelled every scheduled run queued behind it. 20 consecutive
scheduled nightlies died this way between 2026-07-31 and 2026-08-21;
the only nightlies that shipped in that window were manual dispatches.
Drop the cron rather than leave a trigger that cannot succeed unattended.
* fix telemetry session propagation
* feat telemetry client version metadata
* fix(core): address Langfuse review feedback — hub client identity + delegated agent session grouping (#13475)
* fix(core): rebuild hub session client identity from request headers
Hub-backed sessions do not transport extensionContext (it is local-only),
so the daemon's runtime built traces without the clientName/clientVersion
metadata even though the hub client bakes X-CLIENT-TYPE / X-CLIENT-VERSION
into the session's provider headers. Reconstruct extensionContext.client
from those headers during local runtime bootstrap so hub-backed Langfuse
traces carry the same client identity as local runtimes, and the daemon's
header re-resolution stops clobbering the original X-CLIENT-TYPE.
* fix(core): propagate parent distinctId/sessionId to delegated agents
Delegated agents (spawned sub-agents, configured agents, teammates) were
built without distinctId and sessionId, so their Langfuse traces had no
userId or sessionId and did not group with the parent user or session.
Thread the host-resolved distinctId through RuntimeBuilderInput and the
root sessionId through the delegated-agent config provider, and copy both
onto the delegated AgentConfig.
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* Treat an empty preserved capability list as unspecified when seeding tools
toSdkModelInfo guarded the tools seeding with a strict
preservedCapabilities === undefined check, but modelHasCapability —
the runtime's own reader — treats undefined AND length === 0 as
"unspecified". A custom OpenAI-Compatible model whose stored
capabilities field is a defined-but-empty array (a config carried over
from before the field existed, or one round-tripped through a boundary
that defaults it to []) skipped the seeding; the first boolean
projection to run afterwards (e.g. supportsReasoning) then populated
the array, the runtime gate read the non-empty, tool-less list as
authoritative, and every tool definition was silently dropped from the
session (#13463).
The guard now covers the empty array too, matching the reader's
unspecified semantics.
* test: satisfy the store's isModelInfo gate so the empty-capabilities case actually reaches knownModels
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: yzxcj797 <yzxcj797@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): enforce enterprise MCP controls on the Customize marketplace
The unified Customize marketplace replaced the old MCP marketplace
without carrying over enterprise remote-config enforcement: the catalog
RPC returned every MCP entry and installs were never policy-checked,
so orgs with mcpMarketplaceEnabled=false or an allowedMCPServers
allowlist saw (and could install) all marketplace MCP servers.
- Filter MCP entries out of getMarketplaceCatalog when the marketplace
is disabled, and restrict entries to the allowlist when configured
(matching entry id, display name, installed server name, or source
repo URL, mirroring legacy GitHub-URL allowlist ids)
- Reject installMarketplaceEntry requests that violate the policy
- Map the published catalog's repo/homepage fields onto
sourceUrl/homepageUrl so URL-based allowlists can match
- Update the enterprise MCP server controls docs
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor: simplify MCP marketplace policy enforcement
Fold the policy check into marketplace-helpers, drop the dedicated
test suite, and trim the docs edit to the strictly necessary line.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(deps): update Langfuse packages and bump app versions
Update @langfuse/otel to v5.10.1 and add @langfuse/vercel-ai-sdk v5.9.1 for improved observability with Vercel AI SDK.
Bump versions for @cline/code to 0.0.14 and @cline/ui to 0.2.0-next.6, updated via bun.lock.
Other Changes:
Added optional userId to AgentRuntimeConfig.
Propagated userId, sessionId, conversationId, runId, iteration, provider, and model context into AI SDK telemetry.
Added AI SDK 7 runtimeContext with explicit includeRuntimeContext.
Added stable OTEL_SERVICE_NAME=cline-sdk.
Added runtime metadata assertions in agent tests.
* add taskId
* Revert "add taskId"
This reverts commit f20d31d96d.
* fix(core): keep hub session status truthful across queue-drained turns
Queue-drained turns settle only through the event stream, but the hub
runtime host mistranslated their lifecycle in two ways:
- session.updated events carrying only a snapshot (persistence updates)
defaulted the projected status to "running". When one trailed the
final idle update after a turn, clients that track busy state from
status events (the desktop sidecar's workspace restore gate) stayed
busy forever. Use the snapshot's real status and emit nothing when
neither source reports one.
- the per-run agent.done dedup was only reset by run.started, which the
daemon-side queue drain never publishes, so a drained turn's done was
swallowed as a duplicate of the previous turn's. Reset the dedup on
session.pending_prompt_submitted, and suppress stale run.completed
events that land inside a drained turn's window so they can neither
emit a phantom done nor consume the drained turn's dedup slot.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* test(desktop): cover restore unlock after an event-settled queued turn
Exports the sidecar's core-session event handler so the queued-turn
lifecycle (busy via status events, cleared by the done agent event,
restore allowed afterwards) is testable end-to-end.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): start interactive sessions without a prompt as idle
The runtime host reported every new session as "running" until its
first turn ended. Interactive hosts (the desktop app) start sessions
with no prompt and dispatch turns through separate send calls, so a
created-but-never-prompted session stayed "running" forever — wedging
clients that gate workspace operations (checkpoint restore, message
edit) on active turns.
Interactive no-prompt starts now begin idle, start emits the session's
actual status (resumed sessions no longer masquerade as running), and
markTurn* transitions keep tracking in-memory status for lazily
persisted sessions so the first turn still reports running -> idle.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* style: format hub-runtime-host test filter
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor: drop the drained-turn done bookkeeping, keep the minimal fix
The stuck restore is fully explained by the two status defects (fabricated
"running" from snapshot-only session.updated events, and never-prompted
interactive sessions reporting "running"). The done-dedup machinery for
queue-drained turns addressed a separate cosmetic gap (queued turns emit no
chat_done, pre-existing) and required fragile run-window heuristics, so it
is removed to keep this change reviewable. Sidecar test now settles the
queued turn through the status event, matching the shipped mechanism.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* docs(sdk): document the truthful session-status contract
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The edit preview computed proposed content with an exact old_text match, but
the SDK executor normalizes old/new text to the file's own line endings before
matching (#12305) - reads strip CR, so models emit LF-only text even for CRLF
files. Any multi-line old_text in a CRLF file therefore failed the preview's
match: the diff edit view silently never opened while the executor applied the
edit. Single-line edits (no line break in old_text) were unaffected, which is
why the diff view appeared to trigger inconsistently.
Mirror the executor's EOL normalization (and its literal $-sequence insertion)
in the preview computation.
Fixes#13296
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Classic Cline truncated long conversations by omitting an index range of
api_conversation_history from every API request (keep the first
user-assistant pair, drop everything through the range end, strip
orphaned tool_results from the first kept message). The range was
persisted on the history item while the full history stayed on disk.
legacyApiHistoryToSdkMessages ignored conversationHistoryDeletedRange
and converted the entire file, so resuming a migrated long task handed
the SDK an untruncated working context that could exceed the model's
context window by millions of tokens - every request failed with
'prompt is too long' and every compaction restarted from the full
history (#12996, confirmed by the reporter: the task was migrated from
an older version and broke after a restart, with each compaction
starting from ~3M tokens).
The migration now replays exactly what the classic extension sent:
slice out the deleted range and drop orphaned tool_results, mirroring
ContextManager.getTruncatedMessages (see origin/main). Malformed ranges
fall back to the full history (previous behavior).
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): watch agenda task specs via the resolved long path
fs.watch on a path with 8.3 short components (e.g. C:\Users\RUNNER~1
temp dirs) trips a libuv assertion in fs-event.c on Windows and aborts
the whole process. Since the agenda task manager landed, every hub
server test spins up its spec watcher on such a path on hosted Windows
runners, killing the vitest worker and failing the sdk-test Windows job
on every branch. Resolve the specs dir with realpathSync.native before
watching so libuv only ever sees the long form.
* test(ui): stub ResizeObserver for @pierre/diffs in tool-diff tests
jsdom does not implement ResizeObserver, so every ToolFileDiff render
logged a ReferenceError from @pierre/diffs to stderr. Tests still
passed; this just silences the noise the same way the constructable
stylesheet shim does.
* fix(core): skip the agenda spec watcher when the dir does not resolve
Falling back to the raw path on realpath failure would reintroduce the
Windows short-path abort; log and go without the watcher instead.
* fix(hooks): collect PostToolUse hook output and honor its control
tool_result (PostToolUse) hooks ran fire-and-forget with stdout
ignored, so their entire JSON output — contextModification and cancel —
was discarded. Legacy awaited PostToolUse, injected its
contextModification into the conversation, and honored cancel.
- Run tool_result hook commands blocking (same 120s default timeout as
tool_call) in both the hook-config-file layer and the agent-hook
subprocess layer.
- Map their output: cancel stops the run with the hook's error message
as the reason; otherwise context is injected via afterTool
appendContext.
This restores legacy blocking semantics: tool results now wait for
tool_result hooks, but only in sessions that have one configured.
Ref: https://linear.app/cline-bot/issue/CLINE-2987
* fix(hooks): bound tool_result hook wait and isolate cancel reason
Address review findings:
- The agent-hook subprocess layer forwarded an unset timeoutMs
unchanged, so a tool hook command that never exits would block the
agent indefinitely. Default both tool_call and tool_result to the
120s bound the hook-config-file layer already used.
- A cancelling hook's error message was folded into the same context
field as other hooks' injectable context, so merging controls could
leak unrelated hook context into the cancellation reason. Carry it as
a separate cancelReason, and surface it as the stop reason for
beforeTool cancels too.
* fix(hooks): prefer errorMessage as a cancelling hook's stop reason
When a cancelling hook returns both contextModification and
errorMessage, the context-first parse precedence made the injectable
context the cancel reason and discarded the actual error. Parse the two
fields separately: errorMessage wins as the cancel reason (matching
legacy), and a lone errorMessage still folds into injectable context
for non-cancelling hooks as before.
* fix(vscode): honor PostToolUse hook cancel and contextModification
The adapter awaited PostToolUse hooks but discarded their output
entirely. Map cancel to a stop control (with errorMessage as the
reason) and contextModification into the runtime appendContext channel,
matching the PreToolUse mapping and legacy semantics.
* fix(hooks): whitespace-only errorMessage no longer suppresses the cancel reason
A cancelling hook returning meaningful context alongside a blank
errorMessage lost both: the parsers selected the whitespace as the
reason and the result mappers trimmed it away. Require a non-blank
errorMessage before it wins, so context serves as the fallback reason.
Apply the same fallback in the extension adapter's stop mapping.
* fix(hooks): deliver tool hook contextModification to the model
On the next engine, a tool_call (PreToolUse) hook's contextModification
was parsed into HookControl.context and then silently dropped: the
runtime beforeTool/afterTool result contract had no channel for
injecting conversation context. Legacy consumed it (ToolExecutor /
ToolHookUtils pushed <hook_context> blocks into the next user turn), so
this was a regression of documented behavior.
- Add appendContext to AgentBeforeToolResult/AgentAfterToolResult.
- AgentRuntime collects appendContext across hooks during an
iteration's tool executions and appends one <hook_context> user
message after the tool results, keeping tool-result parts contiguous.
- Map HookControl.context into appendContext in both subprocess hook
layers (skipped when the hook cancels, matching legacy, where the
message doubled as the error).
- Truncate injected context at 50KB per hook output, matching legacy.
- Concatenate appendContext across merged hook layers.
tool_result (PostToolUse) hooks still run detached with stdout ignored;
making them blocking so their context can be collected is a follow-up.
Ref: https://linear.app/cline-bot/issue/CLINE-2987
* fix(hooks): stamp tool identity on injected hook context blocks
Contexts are batched into one message after the tool results, and
parallel tool execution collects them in completion order, so position
alone cannot attribute a block to its tool call. Add tool_name and
tool_call_id attributes to each <hook_context> block.
* fix(hooks): sanitize hook context block markup
Attribute values (tool_name, tool_call_id) are stripped of quote/angle
characters and embedded </hook_context> closers in hook output are
neutralized, so neither provider-supplied ids nor hook text can corrupt
or spoof a block's stamped identity.
* fix(hooks): neutralize forged opening hook_context tags in hook output
The previous sanitization only neutralized closing tags, so hook output
could still open a forged <hook_context> block claiming another tool's
identity. Escape both opening and closing embedded tags with one rule.
* fix(hooks): hide injected hook context from user-facing transcripts
Stamp the injected hook-context user message with displayRole 'system'
(the compaction-summary convention) so it reaches the model but does
not render as a user bubble in live or replayed transcripts. Without
this, resuming a session showed the raw <hook_context> block as if the
user had typed it.
* fix(hooks): neutralize case-variant embedded hook_context tags
The tag-neutralization regex was case-sensitive, so hook output could
still smuggle a forged tag as <HOOK_CONTEXT>. Match case-insensitively.
* fix(vscode): map PreToolUse contextModification into runtime appendContext
The extension's hooks adapter bridged file hooks into the SDK runtime
but forwarded only cancel/errorMessage, so a PreToolUse hook's
contextModification never reached the model. Map it into the runtime's
appendContext channel; HookFactory already truncates it at 50KB.
* fix(vscode): hide hook-injected context from replayed transcripts
Live sessions never rendered the injected <hook_context> user message,
but session reload replayed it as a user bubble (and post-resume turns
kept doing so). Treat these messages as synthetic in the user-message
mapping: honor the displayRole 'system' stamp the runtime sets, with a
text-prefix guard for paths where metadata is unavailable. This also
keeps edit/regenerate ordinal mapping aligned with visible bubbles.
* fix(hooks): run file hooks through exactly one layer per host
The VS Code extension registered two independent hook execution layers:
its own hooks adapter (config.hooks) and the SDK core's file-hook
extension from the runtime bootstrap. When both discover the same hook
files, every hook executes twice per event — and with context injection
wired, each contextModification would be injected twice.
Add a 'hooks' runtime config extension kind (in the default set, so the
CLI keeps core file hooks unchanged) and gate the bootstrap's file-hook
extension on it. The extension excludes 'hooks' at session start, so
its adapter — which also provides the hook status UI and the
hooksEnabled setting — is its single execution path.
* fix(vscode): discover hooks from the session workspace, not only global state
Hook discovery read workspaceRoots from global state shared across
every Cline instance, so another window repointing it made workspace
hooks silently stop being discovered. With the extension's adapter now
the single hook execution layer, that meant no hooks at all.
HookFactory takes an optional sessionWorkspaceRoot and unions that
root's .clinerules/hooks into discovery (and into cwd resolution), fed
from the session config's cwd. Shared-state discovery still works, so
behavior in the single-window case is unchanged.
* fix(hooks): keep sanitized hook attribute values distinguishable
Replacing every markup delimiter with the same underscore could
collapse two tool call ids that differ only by such a character into
identical stamps. Escape each delimiter with a distinct token instead.
* fix(hooks): make hook attribute sanitization injective
Escaping the underscore itself turns the attribute escaping into a
uniquely decodable code, so no two distinct tool call ids can collapse
to the same sanitized stamp (previously an id containing a literal
escape token could collide with an id containing the delimiter).
* fix(vscode): reconstruct hook status rows when replaying transcripts
hook_status messages are emitted live but never persisted, so reloading
a session dropped every hook row. The injected <hook_context> blocks
carry the hook source and tool name, so the replay translator now
rebuilds a completed hook status row from each block. The injection is
also no longer treated as a user turn boundary, so the final turn's
completion retag is unaffected by it.
The job sets working-directory: apps/vscode, but that default applies to run
steps only, not to `uses:` steps. Since #10961 moved the extension under apps/
and added that default, the artifact path has resolved against the repo root,
matched nothing, and every failing run logged "No files were found with the
provided path: test-results/playwright/" instead of uploading recordings.
Widen to test-results/ so Playwright's error-context snapshots ship alongside
the videos.
The ui-publish smoke check pins a set of Tailwind candidates the packed
sources must emit; #13410 grew the SearchCombobox options list from
max-h-56 to max-h-64, so the publish run failed on the stale candidate.
All other pinned candidates verified against the current sources.
* feat(ui): sectioned model picker support in SearchCombobox
Adds option sections with headers, badges (NEW/Free pills), keyboard
navigation (arrows/Home/End/Enter with active-row tracking and
aria-activedescendant), substring match highlighting, a configurable
panel width, a trigger chevron, and a cleaner borderless search row.
All additions are backwards compatible; bumps @cline/ui to
0.2.0-next.6.
* feat(desktop): recommended and free model tiers in the composer picker
The composer's model selector showed raw provider/model ids and listed
the entire catalog alphabetized by id. It now labels providers and
models by display name and, for the cline provider, leads with the
Recommended and Free tiers from the recommended-models feed (NEW/Free
badges, descriptions) ahead of an All models section — matching the
CLI's featured picker and the kanban selector. cline-pass gets
Subscribed/Free tiers. A new list_cline_recommended_models sidecar
command exposes @cline/core's fetchClineRecommendedModels (display-ready
names, bundled offline fallback); feed ids resolve against the catalog
with a unique-slug fallback for Vercel/OpenRouter alias spellings, and
unresolvable entries are dropped rather than rendered unselectable.
* fix(desktop): widen the provider trigger for display names
Provider labels are now display names (e.g. "Cline Usage-Billing"),
which truncated badly at max-w-28.
* chore(desktop): drop unused featured-models test helper
* style(desktop): align workspace/branch picker search rows with the model picker
The composer's workspace/branch popover and the welcome screen's
workspace and branch pickers used a boxed inner search shell that now
clashed with the model picker's borderless search row sitting next to
them. Behavior unchanged.
* feat(ui): center the selected option when SearchCombobox opens
Opening a long list previously scrolled the selection just into view at
the panel edge; it now lands centered, and keyboard/hover navigation
falls back to minimal nearest-edge scrolling.
* style(desktop): picker row contrast, transparent search fields, centered open
The workspace/branch pickers' rows had a nearly invisible
surface-hover-lighter hover; rows now hover with surface-hover and mark
the current entry with the accent background plus check, matching the
model picker. The search inputs drop the Input base class's
dark:bg-input/30 tint that rendered a gray box inside the panel in dark
mode. Opening a picker now centers the current workspace/branch via a
shared scroll helper instead of starting at the top of the list.
* fix(ui): visible option hover/selected states and no scroll-jump on hover
The option row stacked bg-transparent with the conditional state
backgrounds; at equal specificity the later-sorted bg-transparent
utility won, so hover/selected rows rendered with no background at all.
The background classes are now mutually exclusive.
Mouse-driven active-row changes also reused the keyboard scroll-into-
view effect: hovering a row at the panel edge scrolled it into view,
which moved the list under the cursor and re-triggered hover — an
endless jump. Scroll mode is now per-source: center on open, nearest
for keyboard/typing, none for hover.
* fix(desktop): show only subscribed and free tiers in the cline-pass picker
The ClinePass offer is exactly the feed's subscribed + free tiers, but
stale bundled/cached catalog entries (e.g. a nemotron model) leaked
into an "All models" tier. Match the CLI's featured picker: hide
catalog leftovers, and only fall back to the full catalog when the
subscribed bucket is empty so a subscriber is never limited to free
models offline.
* fix(ui/desktop): strengthen the selected-row highlight in light mode
The selected row used the semantic accent surface (violet step 3),
which is nearly white in light mode. SearchCombobox and the desktop
workspace/branch pickers now highlight the selected/current row with
accent step 4 (with a fallback to --accent), which reads clearly in
both themes without touching the shared --accent token that shadcn
hover states depend on.
* fix(desktop): fit full provider display names in the composer trigger
"Cline Usage-Billing" — the default provider — truncated to
"Cline Usage-Bi…" at max-w-36; the trigger now allows up to max-w-56,
which fits the longest built-in provider names.
* style(ui/desktop): animate picker panels open like the shadcn dropdowns
The thinking-effort Select (shadcn/Radix) animates open while the
model/provider/workspace/branch pickers popped in instantly. All picker
panels now share the same open treatment — 150ms fade + slight zoom,
sliding from the trigger side. SearchCombobox uses a self-contained CSS
keyframe (consumers may not ship tw-animate-css); the desktop's custom
panels use the app's tw-animate utilities. Both respect
prefers-reduced-motion.
* chore(desktop): drop stale eslint-disable comments in picker search rows
This repo lints with biome; the jsx-a11y/no-autofocus disables were
inert leftovers. Flagged in review.
* refactor(core/desktop): stamp recommended-feed tiers onto ProviderModel in the SDK
Review feedback on the composer picker: tier joining should live where
the SDK serves model lists so each client doesn't fetch and join the
recommended-models feed itself (the CLI and now the desktop each did).
ProviderModel gains description and featured ({tier, rank, tags});
getLocalProviderModels overlays the feed's recommended/free tiers onto
cline models and subscribed/free onto cline-pass via
applyClineFeaturedModels, matching feed ids through the
Vercel/OpenRouter alias rules. The feed access is a new cached wrapper
(getCachedClineRecommendedModels, 5-minute TTL, in-flight dedupe) —
this path runs on every picker open, and the bundled offline fallback
is cached too so offline users don't re-pay the 5s timeout per list.
The desktop webview now reads tiers straight off the models: the
list_cline_recommended_models sidecar command, the webview feed fetch,
and its unique-slug alias matching are all deleted. toProviderModel
also carries ModelInfo.description generally.
* feat(desktop): recommended-feed badges and descriptions in provider settings
Review suggestion on #13410: the provider settings page has room for
more model detail than the composer's picker. The cline/cline-pass
provider cards now refresh their model list through
list_provider_models (the catalog snapshot deliberately skips the
recommended-feed overlay so the startup catalog fetch never blocks on
the feed) and render Recommended/Free tier badges plus feed tags (NEW)
next to the model name, with the model description underneath. The
refreshed list also surfaces the live entries instead of the bundled
snapshot.
* fix(ui): hand focus back to the combobox trigger on selection, close on Tab
Selecting an option (Enter or click) unmounted the focused search input
without a new focus target, dropping keyboard users' focus to <body> —
only Escape restored it. And since the search input is the panel's only
tabbable element, Tab always moved focus outside the component while
leaving the popup open behind the new focus target.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): keep the composer model selection inside the picker's visible offer
The active/remembered model was validated against the provider's full
catalog while the picker can intentionally hide models (the ClinePass
offer is exactly its subscribed/free tiers), so a stale remembered model
could become the selection while being absent from the dropdown.
Remembered and default selections (including on provider switch) now
resolve against the picker's visible options, and an explicitly
configured model that falls outside the offer stays active but is
surfaced under a 'Current model' section so the selection is always
visible and re-selectable.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): scope the settings featured model list to its provider and revision
The fetched featured list was unscoped component state: switching
between cline and cline-pass reused the component instance, so the
previous provider's models stayed visible while the new request was
pending (or forever, when it failed), and the retained copy shadowed
later provider.modelList updates — adding a second custom model
submitted the stale list as the complete configuration and dropped the
first addition.
The fetched list now only applies to the provider and modelList
revision it was fetched for (falling back to the catalog snapshot
otherwise and refetching on membership changes), and add-model submits
the union of the displayed and configured ids so an update can never
silently unconfigure existing entries.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(core): stamp featured tiers onto the provider catalog synchronously
listLocalProviders deliberately skipped the feed overlay so the catalog
never blocks on the network — but that left the composer's very first
picker open after a cold boot rendering an untiered flat list until the
per-provider fetch landed. Blocking was never required: stamp tiers from
a synchronous peek at data already in memory (the cached live feed when
fresh, else the bundled fallback, whose recommended ids resolve against
the bundled cline catalog). The per-provider model-list path still
refreshes with live feed data moments later.
* fix(core): harden featured-tier matching and the feed cache reset
Review findings on the tier overlay:
Vendor-prefix mismatches now match by unambiguous id slug (two-pass, so
a catalog carrying both spellings of a model stamps one row, and a slug
shared by two feed entries stamps nothing) — the bundled fallback feed's
vendor-prefixed ids can otherwise miss cline-free/-prefixed catalog
entries, leaving them untiered in degraded mode.
resetClineRecommendedModelsCacheForTests now bumps a generation so an
in-flight feed request resolving after a reset cannot repopulate the
cache it just cleared.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(ui): sectioned model picker support in SearchCombobox
Adds option sections with headers, badges (NEW/Free pills), keyboard
navigation (arrows/Home/End/Enter with active-row tracking and
aria-activedescendant), substring match highlighting, a configurable
panel width, a trigger chevron, and a cleaner borderless search row.
All additions are backwards compatible; bumps @cline/ui to
0.2.0-next.6.
* feat(desktop): recommended and free model tiers in the composer picker
The composer's model selector showed raw provider/model ids and listed
the entire catalog alphabetized by id. It now labels providers and
models by display name and, for the cline provider, leads with the
Recommended and Free tiers from the recommended-models feed (NEW/Free
badges, descriptions) ahead of an All models section — matching the
CLI's featured picker and the kanban selector. cline-pass gets
Subscribed/Free tiers. A new list_cline_recommended_models sidecar
command exposes @cline/core's fetchClineRecommendedModels (display-ready
names, bundled offline fallback); feed ids resolve against the catalog
with a unique-slug fallback for Vercel/OpenRouter alias spellings, and
unresolvable entries are dropped rather than rendered unselectable.
* fix(desktop): widen the provider trigger for display names
Provider labels are now display names (e.g. "Cline Usage-Billing"),
which truncated badly at max-w-28.
* chore(desktop): drop unused featured-models test helper
* style(desktop): align workspace/branch picker search rows with the model picker
The composer's workspace/branch popover and the welcome screen's
workspace and branch pickers used a boxed inner search shell that now
clashed with the model picker's borderless search row sitting next to
them. Behavior unchanged.
* feat(ui): center the selected option when SearchCombobox opens
Opening a long list previously scrolled the selection just into view at
the panel edge; it now lands centered, and keyboard/hover navigation
falls back to minimal nearest-edge scrolling.
* style(desktop): picker row contrast, transparent search fields, centered open
The workspace/branch pickers' rows had a nearly invisible
surface-hover-lighter hover; rows now hover with surface-hover and mark
the current entry with the accent background plus check, matching the
model picker. The search inputs drop the Input base class's
dark:bg-input/30 tint that rendered a gray box inside the panel in dark
mode. Opening a picker now centers the current workspace/branch via a
shared scroll helper instead of starting at the top of the list.
* fix(ui): visible option hover/selected states and no scroll-jump on hover
The option row stacked bg-transparent with the conditional state
backgrounds; at equal specificity the later-sorted bg-transparent
utility won, so hover/selected rows rendered with no background at all.
The background classes are now mutually exclusive.
Mouse-driven active-row changes also reused the keyboard scroll-into-
view effect: hovering a row at the panel edge scrolled it into view,
which moved the list under the cursor and re-triggered hover — an
endless jump. Scroll mode is now per-source: center on open, nearest
for keyboard/typing, none for hover.
* fix(desktop): show only subscribed and free tiers in the cline-pass picker
The ClinePass offer is exactly the feed's subscribed + free tiers, but
stale bundled/cached catalog entries (e.g. a nemotron model) leaked
into an "All models" tier. Match the CLI's featured picker: hide
catalog leftovers, and only fall back to the full catalog when the
subscribed bucket is empty so a subscriber is never limited to free
models offline.
* fix(ui/desktop): strengthen the selected-row highlight in light mode
The selected row used the semantic accent surface (violet step 3),
which is nearly white in light mode. SearchCombobox and the desktop
workspace/branch pickers now highlight the selected/current row with
accent step 4 (with a fallback to --accent), which reads clearly in
both themes without touching the shared --accent token that shadcn
hover states depend on.
* fix(desktop): fit full provider display names in the composer trigger
"Cline Usage-Billing" — the default provider — truncated to
"Cline Usage-Bi…" at max-w-36; the trigger now allows up to max-w-56,
which fits the longest built-in provider names.
* style(ui/desktop): animate picker panels open like the shadcn dropdowns
The thinking-effort Select (shadcn/Radix) animates open while the
model/provider/workspace/branch pickers popped in instantly. All picker
panels now share the same open treatment — 150ms fade + slight zoom,
sliding from the trigger side. SearchCombobox uses a self-contained CSS
keyframe (consumers may not ship tw-animate-css); the desktop's custom
panels use the app's tw-animate utilities. Both respect
prefers-reduced-motion.
* chore(desktop): drop stale eslint-disable comments in picker search rows
This repo lints with biome; the jsx-a11y/no-autofocus disables were
inert leftovers. Flagged in review.
* refactor(core/desktop): stamp recommended-feed tiers onto ProviderModel in the SDK
Review feedback on the composer picker: tier joining should live where
the SDK serves model lists so each client doesn't fetch and join the
recommended-models feed itself (the CLI and now the desktop each did).
ProviderModel gains description and featured ({tier, rank, tags});
getLocalProviderModels overlays the feed's recommended/free tiers onto
cline models and subscribed/free onto cline-pass via
applyClineFeaturedModels, matching feed ids through the
Vercel/OpenRouter alias rules. The feed access is a new cached wrapper
(getCachedClineRecommendedModels, 5-minute TTL, in-flight dedupe) —
this path runs on every picker open, and the bundled offline fallback
is cached too so offline users don't re-pay the 5s timeout per list.
The desktop webview now reads tiers straight off the models: the
list_cline_recommended_models sidecar command, the webview feed fetch,
and its unique-slug alias matching are all deleted. toProviderModel
also carries ModelInfo.description generally.
* fix(ui): hand focus back to the combobox trigger on selection, close on Tab
Selecting an option (Enter or click) unmounted the focused search input
without a new focus target, dropping keyboard users' focus to <body> —
only Escape restored it. And since the search input is the panel's only
tabbable element, Tab always moved focus outside the component while
leaving the popup open behind the new focus target.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): keep the composer model selection inside the picker's visible offer
The active/remembered model was validated against the provider's full
catalog while the picker can intentionally hide models (the ClinePass
offer is exactly its subscribed/free tiers), so a stale remembered model
could become the selection while being absent from the dropdown.
Remembered and default selections (including on provider switch) now
resolve against the picker's visible options, and an explicitly
configured model that falls outside the offer stays active but is
surfaced under a 'Current model' section so the selection is always
visible and re-selectable.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(core): stamp featured tiers onto the provider catalog synchronously
listLocalProviders deliberately skipped the feed overlay so the catalog
never blocks on the network — but that left the composer's very first
picker open after a cold boot rendering an untiered flat list until the
per-provider fetch landed. Blocking was never required: stamp tiers from
a synchronous peek at data already in memory (the cached live feed when
fresh, else the bundled fallback, whose recommended ids resolve against
the bundled cline catalog). The per-provider model-list path still
refreshes with live feed data moments later.
* fix(core): harden featured-tier matching and the feed cache reset
Review findings on the tier overlay:
Vendor-prefix mismatches now match by unambiguous id slug (two-pass, so
a catalog carrying both spellings of a model stamps one row, and a slug
shared by two feed entries stamps nothing) — the bundled fallback feed's
vendor-prefixed ids can otherwise miss cline-free/-prefixed catalog
entries, leaving them untiered in degraded mode.
resetClineRecommendedModelsCacheForTests now bumps a generation so an
in-flight feed request resolving after a reset cannot repopulate the
cache it just cleared.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(ui): sectioned model picker support in SearchCombobox
Adds option sections with headers, badges (NEW/Free pills), keyboard
navigation (arrows/Home/End/Enter with active-row tracking and
aria-activedescendant), substring match highlighting, a configurable
panel width, a trigger chevron, and a cleaner borderless search row.
All additions are backwards compatible; bumps @cline/ui to
0.2.0-next.6.
* feat(desktop): recommended and free model tiers in the composer picker
The composer's model selector showed raw provider/model ids and listed
the entire catalog alphabetized by id. It now labels providers and
models by display name and, for the cline provider, leads with the
Recommended and Free tiers from the recommended-models feed (NEW/Free
badges, descriptions) ahead of an All models section — matching the
CLI's featured picker and the kanban selector. cline-pass gets
Subscribed/Free tiers. A new list_cline_recommended_models sidecar
command exposes @cline/core's fetchClineRecommendedModels (display-ready
names, bundled offline fallback); feed ids resolve against the catalog
with a unique-slug fallback for Vercel/OpenRouter alias spellings, and
unresolvable entries are dropped rather than rendered unselectable.
* fix(desktop): widen the provider trigger for display names
Provider labels are now display names (e.g. "Cline Usage-Billing"),
which truncated badly at max-w-28.
* chore(desktop): drop unused featured-models test helper
* style(desktop): align workspace/branch picker search rows with the model picker
The composer's workspace/branch popover and the welcome screen's
workspace and branch pickers used a boxed inner search shell that now
clashed with the model picker's borderless search row sitting next to
them. Behavior unchanged.
* feat(ui): center the selected option when SearchCombobox opens
Opening a long list previously scrolled the selection just into view at
the panel edge; it now lands centered, and keyboard/hover navigation
falls back to minimal nearest-edge scrolling.
* style(desktop): picker row contrast, transparent search fields, centered open
The workspace/branch pickers' rows had a nearly invisible
surface-hover-lighter hover; rows now hover with surface-hover and mark
the current entry with the accent background plus check, matching the
model picker. The search inputs drop the Input base class's
dark:bg-input/30 tint that rendered a gray box inside the panel in dark
mode. Opening a picker now centers the current workspace/branch via a
shared scroll helper instead of starting at the top of the list.
* fix(ui): visible option hover/selected states and no scroll-jump on hover
The option row stacked bg-transparent with the conditional state
backgrounds; at equal specificity the later-sorted bg-transparent
utility won, so hover/selected rows rendered with no background at all.
The background classes are now mutually exclusive.
Mouse-driven active-row changes also reused the keyboard scroll-into-
view effect: hovering a row at the panel edge scrolled it into view,
which moved the list under the cursor and re-triggered hover — an
endless jump. Scroll mode is now per-source: center on open, nearest
for keyboard/typing, none for hover.
* fix(desktop): show only subscribed and free tiers in the cline-pass picker
The ClinePass offer is exactly the feed's subscribed + free tiers, but
stale bundled/cached catalog entries (e.g. a nemotron model) leaked
into an "All models" tier. Match the CLI's featured picker: hide
catalog leftovers, and only fall back to the full catalog when the
subscribed bucket is empty so a subscriber is never limited to free
models offline.
* fix(ui/desktop): strengthen the selected-row highlight in light mode
The selected row used the semantic accent surface (violet step 3),
which is nearly white in light mode. SearchCombobox and the desktop
workspace/branch pickers now highlight the selected/current row with
accent step 4 (with a fallback to --accent), which reads clearly in
both themes without touching the shared --accent token that shadcn
hover states depend on.
* fix(desktop): fit full provider display names in the composer trigger
"Cline Usage-Billing" — the default provider — truncated to
"Cline Usage-Bi…" at max-w-36; the trigger now allows up to max-w-56,
which fits the longest built-in provider names.
* style(ui/desktop): animate picker panels open like the shadcn dropdowns
The thinking-effort Select (shadcn/Radix) animates open while the
model/provider/workspace/branch pickers popped in instantly. All picker
panels now share the same open treatment — 150ms fade + slight zoom,
sliding from the trigger side. SearchCombobox uses a self-contained CSS
keyframe (consumers may not ship tw-animate-css); the desktop's custom
panels use the app's tw-animate utilities. Both respect
prefers-reduced-motion.
* chore(desktop): drop stale eslint-disable comments in picker search rows
This repo lints with biome; the jsx-a11y/no-autofocus disables were
inert leftovers. Flagged in review.
* fix(ui): hand focus back to the combobox trigger on selection, close on Tab
Selecting an option (Enter or click) unmounted the focused search input
without a new focus target, dropping keyboard users' focus to <body> —
only Escape restored it. And since the search input is the panel's only
tabbable element, Tab always moved focus outside the component while
leaving the popup open behind the new focus target.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): keep the composer model selection inside the picker's visible offer
The active/remembered model was validated against the provider's full
catalog while the picker can intentionally hide models (the ClinePass
offer is exactly its subscribed/free tiers), so a stale remembered model
could become the selection while being absent from the dropdown.
Remembered and default selections (including on provider switch) now
resolve against the picker's visible options, and an explicitly
configured model that falls outside the offer stays active but is
surfaced under a 'Current model' section so the selection is always
visible and re-selectable.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Unify desktop plugins, apps, MCP, and skills into one Plugins hub with a Browse directory mode
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Open the marketplace directory as a modal over the Plugins hub instead of swapping the page
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Rename directory to Marketplace: Browse Marketplace button, Marketplace modal title with icon, search placeholder
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix search input focus ring clipped by the Marketplace modal scroll container
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Address Greptile review: keep selected tag chip visible when its count drops to zero, and remount installed tab when a marketplace install completes after the modal closed
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Track marketplace modal mutation flag in a ref so a close click racing a queued render cannot skip the inventory remount
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Make Marketplace its own settings page under Customizations and restore Channels as a standalone page
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Remove icon from Marketplace page header for consistency with other settings pages
* Notify mounted inventory views when the marketplace invalidates the cache so late install completions refresh the Plugins hub
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix @ file mentions breaking on paths with spaces
Quote mentions generated by getFileMentionFromPath (Add to Cline /
Fix / Explain / Improve commands) when the relative path contains
spaces, so the mention regex no longer truncates the path at the
first space. Also quote the path part of workspace-prefixed mentions
(workspace:/path with spaces) inserted from the @ context menu, which
previously bypassed quoting because the value does not start with '/'.
Fixes#13338
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix import ordering in mentions test (biome organize imports)
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Reduce fix to minimal scope
Revert the webview quoting refactor and extra tests; keep only the
getFileMentionFromPath quoting fix with a single regression test.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Normalize mention paths to posix separators for Windows
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix code actions failing with 'command not found' on VS Code 1.134
Code action commands carried arguments (expandedRange, diagnostics),
which routes them through VS Code's CommandsConverter cache. VS Code
1.134 disposes the cached entries before the clicked action executes,
so every lightbulb action failed with 'Actual command not found,
wanted to execute cline.addToChat'.
Drop the arguments so the command id is passed through directly, and
recover the context in the handler instead: getContextForCommand now
expands an empty selection by 3 surrounding lines (matching the old
provider behavior) and gathers document diagnostics intersecting the
range when none are passed explicitly.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Scope gathered diagnostics to the selection/cursor
Match the old CodeActionContext.diagnostics behavior: only include
diagnostics intersecting the range the action was requested for, not
the surrounding lines the text gets expanded to.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix @ file mentions breaking on paths with spaces
Quote mentions generated by getFileMentionFromPath (Add to Cline /
Fix / Explain / Improve commands) when the relative path contains
spaces, so the mention regex no longer truncates the path at the
first space. Also quote the path part of workspace-prefixed mentions
(workspace:/path with spaces) inserted from the @ context menu, which
previously bypassed quoting because the value does not start with '/'.
Fixes#13338
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Fix import ordering in mentions test (biome organize imports)
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Reduce fix to minimal scope
Revert the webview quoting refactor and extra tests; keep only the
getFileMentionFromPath quoting fix with a single regression test.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Normalize mention paths to posix separators for Windows
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): don't show 'No sessions found' while session history is still loading
Replace the isLoadingHistory flag with hasLoadedHistory, set only once the
backend has actually answered a list_discovered_sessions request. The sidebar
and Sessions view now keep their loading state until that first definitive
response, so the empty-state copy can no longer appear while history is still
being fetched (or while a failed fetch is being retried).
Also retry a failed initial fetch on the 2s event cadence instead of stranding
the UI until the 12s periodic poll, which is what stretched the misleading
empty state to ~10 seconds after a webview reload when the websocket lost the
race with the page load.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): stop history fast-retry from re-arming after hook unmount
A failed initial fetch that settles after the hook unmounted could schedule a
new retry timer after cleanup had already cleared the refs, leaving the
abandoned hook polling the backend every 2s. Guard scheduleRefresh with a
disposed ref set by the mount effect's cleanup.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): anchor work summary duration on the answer row, not attached pre-tool reasoning
The collapsed 'Worked for Xs' row undercounted wall time whenever a turn's
assistant message contained thinking + tool_use with no narration text: the
canonical projection emitted the reasoning-only row after the tool row (both
stamped before the tool executed), the webview attached that row to the final
answer, and collapseCompletedWork used the answer's earliest attached
reasoning timestamp as the end anchor - excluding the entire tool execution
(e.g. 'Worked for 5s' for a turn with an 8s command).
- webview: end the work span at the answer row's own timestamp, clamped to
the last collapsed row so a fallback answer bubble with a synthetic early
timestamp cannot shrink the duration either
- sidecar: flush pending thinking before a tool_use row so rehydrated
transcripts keep the live-stream order (thinking before its tool call) and
pre-tool reasoning no longer rides on the next answer
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): keep interleaved thinking between the tool calls it separates
Address Greptile review: when one assistant message interleaves thinking
between multiple tool_use blocks, each reasoning segment now projects at its
own position (attached to a text row from its own segment when present,
otherwise as its own row) instead of merging into the first reasoning row,
which displayed later thinking before a tool call it actually followed.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
streamdown renders each Shiki token line as a bare inline span with no
newline text between non-empty lines, and only applies its block line
class when lineNumbers is on. With lineNumbers off (the desktop app's
config) every multi-line fenced block collapsed into one run-on line.
Make the direct line spans under code-block-body display: block in the
shared markdown.css; empty lines keep their height via their lone "\n"
child under white-space: pre.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): treat ClinePass as OAuth-managed in chat credential gate
ClinePass shares the Cline account OAuth credentials (its auth handler
stores under the "cline" provider), so the webview never sees a plain
API key for it. The chat pre-flight check only exempted cline/oca/
openai-codex, so switching to ClinePass while signed in via OAuth
blocked with "Missing API key" even though the sidecar resolves the
stored access token fine (which is why the CLI worked).
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* style: format helpers.test.ts with biome
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(llms): surface provider-executed tool activity as observational events
Provider-executed tool parts (e.g. every tool the Claude Code CLI runs
inside its own session) were dropped by the model-tool guard added for
web search: only declared model tools were re-emitted, everything else
hit continue with nothing yielded. Those sessions modified the workspace
with no tool activity in runtime events, transcripts, or the UI.
Route all providerExecuted parts onto the observational path instead:
emit execution-tagged tool-call-delta and tool-result events, matched by
tool-call ID for providers that omit the flag on the result half. They
stay out of AgentRuntime's execution/approval loop, and the runtime
already persists them as modelToolActivities and projects them for
display.
The AgentModelEvent tool-result variant widens toolName from
ModelToolName to string to carry the provider's own tool names.
* fix(agents): keep turns that are only provider-executed tool activity
A turn consisting solely of observational tool activity has an empty
assistant content array - the activity lives in message metadata, since
projecting it into content would replay tool_use blocks the model never
gets results for. The empty-content guard threw on such turns, erroring
the run and losing the activity from the transcript. Count model-tool
activity as content for the emptiness check (error finishes still
throw); replay stays safe through the codec's empty-content placeholder.
Also drop the trailing text delta from one gateway test so the tool-only
stream shape stays covered end to end.
Publish workflows now always do clean npm installs (no dependency
cache in their test gates), the e2e workflow's cache keys are
exact-match only, and the e2e job drops an id-token permission it
never used.
Slack section blocks reject text longer than 3000 characters. The Slack
action logs that rejection as ##[error] but does not fail the step, so an
over-long changelog drops the release announcement while the run stays
green — cline@3.0.50 (3272 chars) published to npm, tagged, and cut a
GitHub release with no Slack post and nothing red to notice.
Every publish workflow pasted the changelog section verbatim into one
section block, so all six were exposed; the SDK, desktop, and extension
sections were only 150-350 chars under the ceiling.
Add a slack_content output alongside content: unchanged when the section
fits, otherwise trimmed on a line boundary with a link to the full
release notes. Only the Slack payload uses it — GitHub release bodies and
the desktop updater manifest still get the whole section.
* fix(shared): run PowerShell commands with fail-fast error semantics
The run_commands PowerShell wrapper never set $ErrorActionPreference, so
the default 'Continue' applied: a pipeline erroring per item (e.g. a
malformed Where-Object over Get-ChildItem -Recurse) emitted one error
record per enumerated file - tens of thousands of stderr records on
large trees, looking like a hang - and could still resolve as SUCCESS
with exit 0.
Prepend $ErrorActionPreference='Stop'; to the script content executed
by the ScriptBlock so the first error terminates the command with a
non-zero exit and a single error message. Concatenated on the same line
as the user command so error line numbers stay unshifted.
Fixes#13285
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(shared): set the fail-fast preference in the bootstrap scope
Setting $ErrorActionPreference='Stop' by string-prepending it into the
scriptblock source displaced a leading param(...) from its mandatory
first-statement position, so scripts beginning with a param block failed
with CommandNotFoundException. Preference variables are dynamically
scoped, so setting Stop in the -Command bootstrap gives the invoked
scriptblock identical fail-fast semantics while keeping the user script
byte-identical (param works, error positions unshifted) and drops the
doubled-quote escaping.
* docs(shared): document the fail-fast tradeoffs in the PowerShell wrapper
Stop promotes every non-terminating error, not only per-item pipeline
floods: partial-result commands (recursive listings over access-denied
junctions) now stop at their first error, and Windows PowerShell 5.1
turns in-script stderr redirection of succeeding native commands fatal.
State this in the wrapper comment as a deliberate tradeoff, with the
GitHub Actions precedent and the per-command opt-outs.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Co-authored-by: Mikołaj Kondratek <19799111+mkondratek@users.noreply.github.com>
Turns that settle through the event stream (queued prompts, including the
first prompt of a fresh session) resolve their send() RPC early, so nothing
cleared the streaming shimmer or reconciled live-streamed content against
the persisted transcript at turn end. A turn whose deltas were incomplete
stayed visually streaming forever and only healed when a later non-queued
send rehydrated history.
chat_done (and chat_session_ended / the queue-drain double check) now clears
the active assistant streaming id and schedules a short-delayed
read_session_messages + applyCanonicalHistory, guarded by turn epoch,
session id, and in-flight send submissions so it never clobbers a newer
turn or duplicates the blocking send path's own finalization.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): show typed slash command instead of expanded skill markdown
The sidecar expands /skill and /workflow tokens into their instructions
before dispatching, so the runtime's persisted transcript only contains the
expanded text. After a turn (and when reopening a session) the webview
re-hydrates from that history and rendered the whole SKILL.md body as the
user's message; queue events echoing the expanded prompt could also add a
second user bubble, and fresh sessions were titled with the markdown's first
line. The CLI never shows this because its TUI keeps the typed text in its
own transcript and only sends the expanded prompt to the model.
Mirror that separation inside the desktop sidecar's display boundaries:
- history projection (readSessionMessages) inverts user text that starts
with a configured command's instructions back to '/name remainder',
which also repairs sessions recorded before this fix
- queue snapshots and chat_queued_prompt_start events echo the typed
prompt recorded at expansion time, so the webview's optimistic-bubble
re-key matches again
- an untitled session sent an expanded prompt gets titled from the typed
command instead of the instructions' first line
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): don't overwrite a mid-turn rename with the typed-command title
The untitled check ran before dispatch, so renaming a fresh slash-command
session while its first turn was running got clobbered by the post-turn
typed-command title. Re-check at write time and only replace a missing title
or the one the runtime auto-derived from the expanded prompt.
Also documents the inherent prefix-inversion ambiguity flagged in review:
text hand-typed with a command's exact instructions persists byte-identically
to that command's expansion, so stored history alone cannot distinguish them.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): stop expanding skill commands; let the skills tool load them
Pasting the skill body into the prompt is why the transcript could ever show
it: the desktop webview re-hydrates from the runtime's persisted history, so
whatever the sidecar splices into the user message renders as if the user
typed it. The runtime already registers the skills tool, whose description
requires the model to invoke it whenever the user references a slash command
— so send the typed /skill text through and let the tool deliver the
instructions as a tool result (previously they arrived twice: pasted and via
the tool). The persisted user message, session title, and queue entries are
then simply the typed command, which deletes the typed-prompt registry, the
queue event/snapshot rewriting, and the title machinery from the previous
approach.
Workflows are not served by the skills tool and keep textual expansion, so
the read-time display inverter stays: it collapses expanded workflow prompts
— and skill prompts persisted before this change — back to the typed
/command in the history projection.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(core): option to keep skill slash commands typed for the skills tool
resolveRuntimeSlashCommandFromWatcher (and the hub snapshot proxy) accept
expandSkillCommands: hosts whose sessions register the skills tool pass
false so the typed /skill goes through and the model loads the instructions
as a tool result, keeping the persisted transcript as what the user typed.
Workflows always expand — the tool does not serve them. isSkillsToolAvailable
exposes the catalog check hosts use to decide (yolo preset and the skills
tool toggle leave textual expansion as the only delivery path).
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(cli): skill slash commands load via the skills tool instead of expanding
The TUI user-command wrap and buildUserInputMessage now keep a typed /skill
as-is when the session's mode/toggles register the skills tool, matching the
desktop app; workflows keep expanding, and yolo (zen) keeps expanding skills
because its preset has no skills tool. This also fixes CLI resume/history
surfaces showing the skill body: the persisted user message is now the typed
command.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): keep configured skill slash commands typed for the skills tool
expandSlashCommands no longer splices a configured skill's instructions into
the model text; the SDK session's skills tool delivers them as a tool result
(previously they arrived twice). Builtin pseudo-skills like /deep-planning
are not served by that tool and keep expanding, as do workflows.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(desktop): use the shared skill-expansion option in the sidecar
Replaces the sidecar's workflow-detection dance with core's
expandSkillCommands option and gates on isSkillsToolAvailable, restoring
textual expansion where the tool is missing (yolo mode or the skills tool
toggle) — a gap in the previous desktop-only change.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(desktop): drop the display inverter for expanded transcripts
Accepted trade-off to keep the change minimal: sessions recorded before
skills switched to the skills tool, workflow sends (deprecated), and
yolo-mode skill sends persist expanded instructions and now render that text
as-is instead of being collapsed back to the typed /command at projection
time.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(cli): make TUI dialog colors follow theme changes live
Dialog content previously read the static palette constant, so open
dialogs (including the theme picker itself) kept the default dark-blue
accents while scrolling through theme previews. Add getDialogPalette /
useDialogPalette, which resolve dialog colors from the active theme's
dialog accents and re-render on every theme change, and migrate all
dialog-rendered components to it.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(cli): derive dialog panel background from the active theme
Dark themes now lift their own background one OKLAB step for the dialog
surface, so panels keep the theme's hue instead of the library's fixed
#262626. DialogThemeSync pushes the surface into the dialog container
for new dialogs and repaints open panels, so the surface also follows
live theme previews. Light themes keep the neutral dark panel to match
the dark accent fallback and the light-on-dark dialog text.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix: run_commands object form without args routes through the shell
The structured { command, args? } form of run_commands was always spawned
directly with shell: false. When a model emitted a full command line in
command with no args (e.g. { command: "echo hello" }), spawn failed with
ENOENT for any command containing a space, breaking command execution for
the whole session.
Direct exec now only applies when a non-empty args list is provided; the
object form without args is routed through getShellInvocation like the
string form. Schema descriptions are tightened so models put arguments in
args instead of embedding them in command.
Fixes#13279
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore: trim structured-command schema descriptions
The union schema is only used for lenient validation of input the model
already sent; its descriptions never reach a model prompt. Keep them
short instead of restating executor behavior.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore: simplify direct-exec comment in shell executor
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* revert: keep original structured-command schema description
The description never reaches a model prompt and the executor now handles
both shapes, so the wording change was cosmetic noise.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix: gate direct exec on args key presence, not array length
Review feedback: an explicit empty args array is intentionally structured
input and stays direct exec; only an object with no args key is treated
as a full shell command line. Matches the key-presence rule already used
by the VS Code host's formatCommandForTerminal. Also replaces the
empty-args shell test (which was PowerShell-incompatible) with a test
pinning the direct-exec contract.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
@cline/ui's generated-media imports @cline/shared/browser, which resolves to
shared's dist output. The build-shared step sat after typecheck/test/build,
so the first ui-publish dispatch since #13025 failed at Typecheck UI with
TS2307. Move the step to right after install.
* feat(ui): share the markdown pipeline, chat polish CSS, and ThinkingBlock
The desktop app and the cloud dashboard both consume @cline/ui yet rendered
assistant output differently, because Markdown policy and the thinking-trace
row lived app-side. This moves the shareable parts into the package:
- components/markdown (new export): the lazy Shiki code highlighter (GitHub
light/dark, pinned language set) and agentMarkdownControls — the standard
Streamdown configuration. streamdown/shiki/@shikijs/* become optional peer
dependencies, mirroring @pierre/diffs.
- components/markdown.css: the desktop's chat polish moves in — chat-scale
headings, outside list markers, single quiet code blocks with a
hover-revealed copy control, table cards. Kept unlayered so it beats
Streamdown's layered Tailwind utilities without !important.
- ThinkingBlock + formatThoughtLabel in agent-chat: the standard thinking
row (brain icon, Thinking/Thought-for-Ns label, streaming shimmer, rail
presentation, capped scrollable body). The shimmer and the
reasoning-hover-suppression rule move into agent-chat.css; triggers gain
the color transition the desktop applied locally.
Version bumps to 0.2.0-next.5 for the dashboard to pick up.
* refactor(desktop): consume shared markdown and thinking primitives from @cline/ui
The local Shiki highlighter, Streamdown controls, chat markdown polish CSS,
streaming-title shimmer, and reasoning hover-suppression rule are deleted in
favor of the @cline/ui versions (the highlighter test moves to the package's
suite). ReasoningBlock becomes a thin wrapper that hands MemoizedMarkdown to
the shared ThinkingBlock, and formatThoughtLabel re-exports from the package
so grouping code and tests keep their import path.
globals.css now imports @cline/ui/components/markdown.css (unlayered, so the
polish keeps beating Streamdown's layered utilities); the app keeps only what
is genuinely app-specific: link/image policy in markdown.tsx, selectability
rules, accent palettes, and the view-enter transition.
* style(ui/desktop): make thinking-trace prose legible
Thinking body text rendered too faint: plain muted-foreground plus the
desktop's font-thin weight. The shared thinking content now leans 75% of the
way back toward the body text color (still slightly de-emphasized), and the
desktop drops the thin font weight.
* feat(ui): add WorkActivity collapsed-run summary and float message actions as a pill
WorkActivity/WorkActivityTrigger/WorkActivityContent fold a finished agent
run's working rows (tool calls, thinking traces, narration) behind a single
"Worked for 4m 12s · 14 tool calls" disclosure built on the shared animated
disclosure primitives, with formatWorkActivityLabel/formatWorkDuration
exported for consumers.
Message hover actions no longer rely on the transcript reserving blank space
below each message: the action row is now a self-backed pill (border,
blurred background, shadow) that floats over whatever follows, so
conversations can pack rows tightly without hover chrome colliding with the
next message.
* feat(desktop): collapse finished runs into a work summary and tighten chat spacing
collapseCompletedWork post-processes the grouped transcript: once a run ends
on assistant text with no further tool calls, its working rows fold into one
expandable WorkActivity row while the final answer stays visible. Runs are
delimited by user messages; the trailing run only collapses when the session
has stopped running and actually produced an answer, so live streams and
cancelled/failed tails keep their rows. Assistant messages carrying images
or media are treated as deliverables and never collapse.
The conversation list gap drops from gap-8 to gap-4 now that hover actions
are self-backed pills that need no reserved space, and user messages add
their own top margin so turn boundaries stay visually distinct.
* refactor(ui/desktop): work summary label wording, flat expansion, stable in-run rhythm
Feedback round on #13315:
- Label reads "Worked for 4m 12s and made 14 tool calls" instead of joining
with a dot; without a duration it falls back to "Made N tool calls".
- Expanded work rows render at transcript level — no rail or extra indent —
since tool rows and thinking traces already carry their own nesting when
expanded. The work content keeps the tight working-row rhythm.
- Live working rows (thinking traces + tool calls) now group into a 'run'
render item with the same tight 0.25rem rhythm, so there is no oversized
gap under a "Thought for Ns" row and every row keeps its exact position
when the finished run folds into the work summary. A trailing
answer-in-progress stays outside the group at transcript level, and pure
prose spans keep normal spacing.
- The transient "Thinking..." indicator moves inside the transcript column
and mirrors a trigger row's geometry, so the first real row replaces it in
place with no jump.
* style(ui/desktop): hover-pill metrics, right-pointing work chevron, scroll and spacing fixes
Another feedback round on #13315:
- Hover action pill: +2px internal padding, a trailing inset after the
timestamp (it sat flush against the pill border), and more clearance
between the message content and the pill (2px -> 6px; the hover bridge
grows to match).
- The work summary chevron points right while collapsed and continues
counterclockwise to point up when expanded.
- Conversation bottom padding drops pb-20 -> pb-8: the composer sits below
the scroller, so the padding only needs to clear a pinned action pill.
- Sending a message scrolls back to the bottom even if the reader had
scrolled up (new AutoScrollOnSend on the user-message count, which ignores
optimistic-bubble re-keying; @cline/ui now exports useConversation for
this).
- An assistant answer directly under its run's working rows pulls itself
0.5rem closer than the full transcript gap.
* style(desktop): leave a visible gap between a pinned action pill and the composer
pb-8 exactly matched the pill's ~40px footprint, so the last row's hover
actions sat flush against the composer top; pb-12 restores ~8px of daylight.
* style(desktop): widen the gap between the pinned action pill and the composer to ~24px
pb-12 left only ~8px of daylight under the pill; pb-16 reads comfortable
without reverting to pb-20's dead space.
* fix(desktop): keep the thinking indicator at the working-row offset mid-run
The indicator matched a trigger row's geometry but sat a full transcript gap
(1rem) below the last working row, while the tool/thinking row replacing it
joins the tight run group at 0.25rem — a visible upward jump. When the last
transcript item is working rows (or streamed assistant output), the
indicator now pulls up to the same tight offset; only at the start of a run,
under the user message, does it keep the normal gap.
* style(ui): calm the hover actions surface per team feedback
Borderless rectangle instead of the bordered pill: radius drops to
var(--radius), the side padding goes entirely (the icon buttons carry their
own hit areas), and the vertical padding halves. Blurred background and
shadow stay so it remains legible over following content.
* feat(ui/desktop): full-band hover reveal and iOS-style disclosure easing
The hover actions only appeared while the pointer was inside the message
box itself. The invisible bridge under each message now spans the full
height of the band the floating actions occupy (full row width), so
hovering anywhere in that strip reveals them. Sibling row types
(.cline-chat-tool, .cline-chat-work, and the desktop's run/tool groups)
become position: relative so they paint above the bridge — their own
content keeps its hover and clicks, and the bridge only wins in the band's
genuinely empty space.
All expandable rows (work summary, tool panels, thinking) open and close on
a 240ms symmetric ease-in-out cubic-bezier instead of the 60ms snap, with
chevron rotation on the same curve. Reduced-motion still disables both.
* revert(ui/desktop): drop the full-band hover reveal; quicken disclosure easing to 180ms
The full-band hover bridge (and the position: relative changes that made it
safe) is reverted per feedback — back to the narrow bridge that only spans
the gap under the message. The iOS-style ease-in-out on disclosures stays
but speeds up from 240ms to 180ms.
* fix(ui): recover live tool diffs that mount as a blank pierre skeleton
Live-streamed edit rows could show an empty diff for the whole run, with the
diff only appearing after the collapsed work row was expanded (fresh mount).
Root cause, confirmed by driving a live session and inspecting the element:
React StrictMode double-invokes @pierre/diffs' ref callback; the first
instance's async highlight work aborts on its immediate cleanup, and the
second instance adopts the abandoned half-rendered shadow tree as if it were
complete prerendered output — zero height, no code, no theme stylesheet,
permanently. A rendered diff always carries style[data-theme-css] in its
shadow root, so ToolFileDiff now checks for it shortly after mount and
remounts FileDiff (bounded attempts) when missing; the fresh host element
takes the normal render path and recovers within ~400ms. Verified live: the
diff now renders during the run.
* fix(desktop): keep interrupted runs expanded even with partial trailing text
The trailing-run collapse gated on 'ended with assistant text', which
misread a Stop that landed mid-answer as a finished run and folded the tool
calls the user wants to inspect. The gate is now the terminal status itself:
only completed (or restored-idle) sessions collapse the trailing run;
cancelled/failed/error tails keep their rows regardless of partial text.
(Greptile P1 on #13315 — matches the PR's stated rule.)
* feat(desktop): show provider web-search support under the settings toggle
The global Web search toggle silently does nothing unless the session's
provider offers native web search, which made the setting read as if it
worked with any provider. The desktop General settings row now explains
that only providers with built-in web search honor it, and shows a live
status line: which connected providers are ready to use it (no extra
setup needed), or an amber warning with a link to the Models section
when none of them support it.
Support is resolved in the webview via a new providerOffersModelTool
helper in @cline/llms (browser export), sharing the same builtin-manifest
source of truth as the runtime's supportsModelTool attachment check.
* fix(desktop): address review — refetch web-search status on catalog invalidation, clarify per-model support
Greptile P2: the one-time catalog fetch could race an in-flight provider
save and show stale status; the row now refetches when the provider
catalog cache is invalidated (fired after saves complete).
Greptile P1: the ready line implied every model on the provider works;
Vertex excludes Claude routes, so the copy now scopes the promise to
models that support it.
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(vscode): clear task-scoped settings overlay when task view is cleared or switched
Toggling an auto-approve setting while a task is open writes
autoApprovalSettings into the StateManager's task-settings overlay
(updateAutoApprovalSettings -> setTaskSettings). The SDK controller never
cleared that overlay on clearTask/showTaskWithId (the legacy controller
did), so after New Task the stale overlay kept shadowing global settings
in getGlobalSettingsKey(): toggle RPCs were accepted into global state,
but every posted state still carried the overlay's old version, which the
webview rejects as not newer - the auto-approve checkboxes froze forever.
Restore legacy parity in SdkTaskControlCoordinator: drop the overlay
(persisting pending writes first) in clearTask() and before installing a
different task's proxy in showTaskWithId().
Fixes#13260
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* changeset
* test(vscode): add end-to-end regression test for auto-approve freeze after New Task
Wires the real StateManager, the real updateAutoApprovalSettings handler,
and the real SdkTaskControlCoordinator.clearTask() together with the
webview's version gate modeled on ExtensionStateContext, pinning the
end-to-end invariant behind #13260: checkbox toggles must keep reaching
the webview after a mid-task toggle followed by New Task. Verified the
test fails when the clearTaskSettings() call is removed from clearTask().
* fix implicit any in regression test
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The branch dispatch input was a free-form string with no validation. Both
jobs checked it out and ran full npm lifecycle scripts from it: the publish
job next to VSCE_PAT/OVSX_PAT (and npm run publish:marketplace executes a
script from that same ref with the PATs in env), and the test job with NO
environment approval at all while inheriting the workflow-level
contents/packages/checks/pull-requests write grants. A dispatch pointing at
e.g. refs/pull/N/head would run outside-contributor code with the
marketplace keys behind one approval, or with a repo-write token behind
none.
Remove the input and hardcode the protected legacy-extension branch, drop
the workflow-level permissions to contents: read, and elevate only the
publish job to contents: write (tag push + GitHub release). The branch
input's default was legacy-extension, so normal publishes are unchanged.
publish-extension skill dispatch command updated to match.
The combined-VSIX workflow took legacy-ref as a free-form dispatch input
with no publish-time validation (next-ref has one: publish requires main).
Any typed ref — a PR merge ref, an unprotected branch — would be built
into the published VSIX by the environment-less build job, and the publish
environment approver only ever sees an opaque prebuilt artifact, so the
approval protected the marketplace PAT but not the shipped bytes.
Remove the input entirely and hardcode the protected legacy-extension
branch, which makes that branch's protection rules load-bearing for
releases. The tested-sha pinning between test-legacy and build is
unchanged. publish-extension skill dispatch command updated to match.
* fix(vscode): point Mistral signup URL at the general API keys console
The Mistral provider's signup link led to the Codestral console, which
issues Codestral-scoped keys that fail with 401 on api.mistral.ai — the
endpoint the provider actually calls. Point it at the general API keys
page instead.
Fixes#13288
* fix(vscode): deep-link DeepSeek and Fireworks signup URLs to their API key pages
Both pointed at marketing homepages; link straight to the key-creation
pages instead, matching the rest of the registry and the desktop app's
provider-key-urls map.
* fix(vscode): stop resubmitting the original task text on bare resume (#12975)
A bare Resume after Stop rebuilt the session from task history and
injected historyItem.task into the resumption prompt as 'New
instructions from the user'. The model treated the already-completed
original request as fresh instructions and re-executed it (e.g. re-ran
all terminal commands after stopping a queued follow-up turn).
The preserved conversation history is the source of truth on resume, so
the fallback prompt now just asks the model to reassess the history and
continue, matching the legacy resume prompt which also never resent the
original task. User-typed text still takes precedence when provided.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): continue the surviving idle session on follow-ups instead of rebuilding
Stopping a turn keeps the session alive, but every idle follow-up (bare
Resume after Stop, and typed follow-ups after a completed turn) tore
that session down and rebuilt it from persisted task history before
sending. Continue the matching idle session in place instead, the same
way the CLI reuses the live session after an abort. Rebuilding from
history now only happens when no live session matches the displayed
task (task opened from history, extension host reload).
A bare resume still needs a prompt to start a turn, so it sends the
neutral [TASK RESUMPTION] prompt (shared with the rebuild fallback and
hidden from the transcript); user-typed content is echoed and sent
as-is. If the send lands while the abort is still settling, the runtime
auto-queues it and drains once the abort completes.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(vscode): consolidate follow-up send paths in SdkFollowupCoordinator
Now that idle follow-ups continue the live session in place, the
two-mode sendToActiveSession helper was redundant: its non-queued branch
duplicated continueIdleSession minus the bare-resume prompt. Split it
into a single-purpose queueToActiveSession and fold the idle no-task
send into continueIdleSession, flattening askResponse's decision tree
to: queue onto a running turn, continue a matching live idle session,
rebuild from history, or abandon.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(vscode): reuse the existing neutral resumption prompt for bare resumes
Drop the newly invented long resumption wording in favor of the phrase
that already existed as the no-history fallback and that the transcript
hiding logic and test fixtures recognize: '[TASK RESUMPTION] Please
continue where you left off.' The net change to resumeSessionFromTask
against main is now just deleting the branch that resubmitted
historyItem.task as new instructions.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): stop resubmitting the original task text on bare resume (#12975)
A bare Resume after Stop rebuilds the session from task history and
injected historyItem.task into the resumption prompt as 'New
instructions from the user'. The model treated the already-completed
original request as fresh instructions and re-executed it (e.g. re-ran
all terminal commands after stopping a queued follow-up turn).
Bare resumes now always use the neutral prompt that already existed as
the no-history fallback; user-typed text still takes precedence. This
matches the legacy resume prompt (responses.taskResumption), which only
ever included user-supplied text as new instructions.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): hide synthetic prompts from the queued-prompt echo
A send that races a settling abort is auto-queued by the runtime, so a
bare Resume can reach the pending_prompt_submitted echo carrying the
synthetic [TASK RESUMPTION] prompt. Echoing it leaked model-facing text
as a visible user bubble and shifted the visible-user-message ordinals
that edit/regenerate mapping relies on. Filter synthetic prompts with
isSyntheticUserPrompt, keeping user attachments visible (matching
isSyntheticSdkUserMessage semantics).
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
A restore that reuses the source session id rolled the workspace back but
left the persisted transcript describing the discarded turns, so the chat
kept showing turns whose file changes had just been reverted.
Before #13075 the restore reply carried the trimmed messages and the
webview rendered them directly. Now the webview always re-reads through
read_session_messages, which prefers the persisted file over the live
session, so the trimmed history the sidecar puts on the live session is
never read. Persist it as well.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Beta builds (prerelease versions from desktop-experimental, shipped as
'Cline Code Beta') now identify themselves everywhere users look: a Beta
pill in the sidebar footer, the product name in the sidebar hover card,
an About row in Settings > General with version + channel, the runtime
window title, and the tray menu/tooltip (via package_info, which carries
the overlay's productName).
Channel detection is a pure version-string check (-beta suffix) in the
new webview/lib/app-channel.ts — the version is baked into package.json
at build time and reported by the sidecar's get_process_context, so it
works in both the Tauri shell and web dev mode with no new plumbing.
Stable builds render no channel UI at all.
* feat(desktop): add beta release channel from desktop-experimental branch
Adds a 'channel' input (stable|beta) to desktop-publish.yml. Beta releases
are tagged desktop-vX.Y.Z-beta.N on the desktop-experimental branch, built
with the tauri.beta.conf.json overlay (Cline Code Beta / bot.cline.app.beta,
side-by-side install with stable), published as prerelease GitHub releases,
and served by a separate rolling desktop-beta update feed. Both channels
dispatch from main so the PublishDesktop signing gates are unchanged.
Guards: stable channel now rejects prerelease tags (previously a beta tag
could clobber desktop-latest and auto-update every stable install onto it),
feed selection is fail-closed and cross-checked in the release job, and the
build asserts the compiled binary embeds exactly its own channel's feed URL.
Changelog extraction is exact-version now that stable and beta sections
interleave across branch merges.
Process doc in apps/examples/desktop-app/EXPERIMENTAL.md; publish-desktop
skill now asks stable-or-beta.
* docs(desktop): warn against renaming the desktop-latest feed
* docs(desktop): document the code-trust model for publish approvals
The beta dispatch-from-main invariant protects the workflow definition, not
the checked-out tag's build scripts, which run with signing secrets in scope
for stable and beta alike. Make explicit that the PublishDesktop reviewer
approval is the trust gate for that code, and that desktop-experimental
therefore needs main-grade merge controls.
* feat: add image generation support
* fix(llms): preserve mixed image model behavior
* fix(llms): validate generated image models
* fix(llms): preserve mixed image response streaming
* fix(llms): preserve runtime tool ownership
* fix(llms): address image generation review feedback
* fix(desktop): relay images for attached hub sessions
* chore(llms): regenerate provider and model catalog
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(vscode): preserve SDK model capabilities across the catalog boundary
The new modelSupportsToolCalling gate treats a populated capability list
without "tools" as authoritative. But the VS Code host round-trips model
metadata through the legacy ModelInfo shape, and toSdkModelInfo
reconstructed capability arrays from the legacy booleans alone — which
have no "tools" projection. Every model with any capability flag set
came back as "cannot call tools", so sessions registered zero tools and
the file-edit e2e failed on all platforms (the editor tool call resolved
to "Unknown tool" and the edit never reached disk).
Fix, following the modalities-passthrough pattern so stacked capability
PRs can reuse it:
- Preserve the SDK capability list verbatim on legacy ModelInfo at the
catalog boundary (adaptSdkModelInfo); union user overrides into it
without ever fabricating a list from overrides alone.
- Seed toSdkModelInfo from the preserved list, and when none survived,
emit an explicit "tools" signal (honoring legacy supportsTools=false)
so reconstructed arrays can never silently disable tool calling.
- Add a shared modelHasCapability(model, capability,
{assumeWhenUnspecified}) helper: missing or empty capability lists
carry no signal and each check declares its own default. Future
capability gates should route through it instead of reading
model.capabilities directly.
Verified: file-edit e2e (Single Root + Multi-Roots) passes locally;
shared/core/llms/model-catalog/session-factory suites and typechecks
pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(llms): refresh generated model catalog
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The Vertex case asserted that a bare providerId resolves to a model
without web search, which only held because the generated catalog's
Vertex default happened to be a Claude route. models.dev has since moved
that default to gemini-3.7-flash, which does support native web search,
so the assertion failed on the next catalog regen while the behavior it
guarded was unchanged.
Drop the catalog-dependent case and cover the default-model fallback
against a synthetic manifest instead, where the excluded route is stated
by the test rather than inherited from upstream data.
The outdated_hub notice reports a state the user cannot act on: this CLI
is already the newer build, the Hub is behind only because retiring it
would kill the sessions it is serving, and the swap happens on its own at
the next launch. A toast that interrupts to say "no action needed" is
still an interruption, and the desktop surface already concluded the same
thing by rendering nothing for this reason.
It also could not deliver the message it existed for. Toast caps at
maxWidth = Math.min(44, width - 4), and the 61-character string did not
wrap, so what actually rendered was "Update finishes the next time Cline"
- a sentence cut off before the reassuring half. Identical at 120 and 200
columns, so widening the terminal did not help.
The classification stays in core and still earns its keep at this call
site: outdated_hub is what stops the update-and-restart prompt from
firing at someone who has nothing to update. Only the rendering goes.
The build_mismatch direction, where the user does have something to do,
is untouched.
Render assistant markdown with internalBlockMode="top-level" so each
top-level markdown block gets its own renderable. The default coalesced
mode merged the entire message into one block that was rebuilt and
re-highlighted on every streamed chunk, flashing settled headings and
links back to raw uncolored markdown (visible ###, unconcealed syntax)
until the async tree-sitter highlight landed, and re-wrapping rows so
the transcript jumped vertically.
Top-level blocks are reused by token identity, so settled content never
re-renders; only the trailing unstable block updates per chunk. Pass
tableOptions style=grid to keep the bordered table rendering coalesced
mode used by default.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): stop concurrent Hub installs from retiring each other
Two Cline installations on different builds would shut each other's Hub
daemon down in a loop, and every session died with an abnormal socket
close (code=1006) as its daemon was killed mid-handshake.
The retire decision was a one-sided predicate: each client independently
asked "may I reuse this Hub?", and two clients on differing builds both
answered no. #13177 added build-epoch ordering to break the tie, but left
every unordered case - missing epoch, missing build id - retiring as
before, so any pair involving a build from before epochs were embedded
still looped.
Derive the decision from a total order instead. compareHubBuilds orders
two builds by embedded epoch, then core release version, then build id,
and is antisymmetric by construction, so at most one side of a pair can
ever decide to retire. A Hub that is newer or cannot be ordered is
attached over the compatible wire protocol and left to the build-mismatch
watcher to prompt about. Genuine protocol incompatibility still replaces.
Identity is now read from the same fields on both sides. Filling in a
coreVersion locally that the wire record omits made a build's identity
depend on which role it was playing, and the two directions of a pair were
then decided by different tiers with both concluding they were newer -
a second, independent way to produce the loop.
Also:
- Scope the development Hub owner by build id, so differing dev builds run
their own daemon side by side instead of contending for one record.
Production keeps its singleton.
- Break the circuit after repeated retirements of the same URL, bounding
any future ordering bug to a stale-build prompt rather than an
unusable Hub.
- Report `cline doctor fix` honestly: separate processes that survived a
kill from ones that appeared while the fix ran, name the live parent
respawning a daemon, and mark a startup lock held by a running process
as held rather than leaked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(cli): only blame a live parent for processes seen during doctor fix
The advice printed under "started during fix" asserted that every such
process was respawned by a live parent, and told the user to go stop it. A
process can also start on its own mid-repair - someone opening a new
session - and then the instruction points at an unrelated process, or at
none at all.
Derive the wording from whether a live parent actually exists: name it
when every process has one, state the facts when none do, and split the
list when it is mixed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test(core): order the builds in the stale-discovery hub server case
The case stubbed two build ids and expected the second to replace the
first, but supplied nothing that says which came first: no epochs, and both
servers report the same core version. Ordering therefore fell to the
build-id tiebreak, where "new-build" sorts before "old-build" and the
replacement was judged the older of the two.
Give the case the epochs its name implies, and add the missing sibling for
an unorderable pair, which is attached to rather than retired - the
behavior that keeps two installations from shutting each other down.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(core): defer replacing a Hub that is serving live sessions
Retiring a Hub kills its established WebSockets, so replacing one under a
running session ends that turn with an abnormal close (code=1006). The
replacement is correct - the newer build should own the Hub - but the
timing is not the user's to absorb mid-turn.
Defer instead while the Hub reports live sessions: the newer client
attaches to the older Hub over the compatible wire protocol, and the swap
happens once those sessions end. Attaching rather than spawning matters -
a second daemon would race the busy one for the port.
Deferring silently would be worse than the interruption it avoids, because
a long-lived session pins the Hub to old code indefinitely with nothing to
show for it. The build-mismatch watcher only ever prompted in the
direction where updating the client resolves the mismatch; its own comment
notes that older Hubs "are retired and replaced automatically, so
prompting would only flash a stale dialog", which stops being true once
replacement can be deferred.
Add the missing direction as `outdated_hub`, reported only when a mismatch
survives consecutive checks - an idle older Hub is replaced within moments
of being seen, so a single sighting would flash exactly the stale dialog
the original comment warns about. The CLI and desktop dialogs render it as
information rather than an update prompt: nothing to install, the Hub
swaps itself when the sessions end.
The direction is decided by compareHubBuilds rather than reusability,
because a Hub that is newer and one that carries too little metadata to
order are both "reusable" but need opposite advice.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(core): key the outdated-Hub check by daemon instance, not build
The consecutive-sighting check that keeps a routine replacement from
flashing an informational dialog was keyed by build id. Two daemons from
the same build share one, so an outdated Hub replaced by another daemon of
the same older build satisfied the check and reported exactly the churn the
check exists to hide.
Carry a hubInstanceId on the mismatch event - the Hub's own id, falling
back to pid and start time - and key the pending sighting by it. A
replacement instance now restarts the count instead of confirming it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(core): source Hub instance identity from the discovery record
The instance id added in the previous commit was read from the probe
response, but the watcher probes without an auth token and `/health`
deliberately reports only build and address fields - no hubId, pid, or
startedAt. So the id was always undefined in production and the check it
guards still conflated two daemons of the same build. The test missed it by
injecting a hubId into a mocked probe, a shape `/health` never returns.
Take identity from the discovery record instead, which every daemon version
writes with all three fields and which a replacement daemon rewrites as its
own. The probe is still preferred when it does carry an id, since that is
the process just spoken to.
The tests now use the real `/health` payload shape and vary identity through
the discovery record, including the pid-and-start-time fallback for records
written before Hubs carried an id.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(core): confirm the Hub record still describes the daemon just probed
Instance identity is read from discovery before the probe and build data
comes back after it, so a daemon replaced between those two steps was
described with its predecessor's identity - the replacement then satisfied
the prior daemon's pending sighting and emitted the notification the
consecutive-instance check exists to suppress.
Re-read discovery after the probe and report nothing when the record no
longer describes the same daemon. A Hub mid-swap is churn; the next check
sees whatever it settles into.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* revert(core): drop the watcher instance-identity hardening
Reverts the three follow-up commits that keyed the outdated-hub
consecutive-sighting check by daemon instance (42a83beae, 931431371,
9d634f7b3). They guarded one scenario - a different daemon of the same
outdated build swapping in between two watcher ticks - where the only
consequence is an informational dialog showing one interval early or
late. The unauthenticated probe carries no instance fields in
production, which is why the first attempt needed two more patches; the
original reason+buildId consecutive-sighting suppression from this PR's
base commit already covers the case that matters (not flashing a dialog
for a hub that is mid-replacement).
* fix(core): only count sessions that stopping the hub would actually harm
hasActiveHubSessions treated every non-terminal status as busy. But a
session's hub-side runtime outlives its client: a TUI that is killed or
crashes never stops its session, which then sits in the hub with no
participants and a status that never reaches a terminal state. Under the
defer-while-busy rule that pinned the displaced hub as "serving
sessions" forever - it was never retired, every new CLI kept attaching
to the old build, and the outdated-hub dialog recurred with a promise
("replaced once those sessions end") that could never come true.
Verified empirically: a cleanly detached+disposed client leaves its
session status "running" indefinitely.
Busy now means: someone is attached (participants), or a turn may be
executing hub-side (running/pending, which covers headless and scheduled
runs). An idle session with a confirmed-empty participant list is
resumable persisted state, not live work. Hubs from core < 0.0.75 omit
the participants field entirely, so idle stays conservative (busy)
there - an attached client cannot be ruled out.
updatedAt-freshness was considered and rejected as the discriminator:
the sessions row only updates on status transitions, so a single long
agentic turn looks stale while genuinely executing.
* fix(core): gate hub busyness on attached participants only
Simplifies the busy-check to the one signal that cannot go stale:
participants are live socket subscriptions the hub drops the moment a
client's connection closes, so a crashed client can never leave a ghost
that counts as busy. Session status is deliberately not consulted - a
client killed mid-turn strands its session in a non-terminal status
forever, and QA reproduced that pinning an outdated hub as "serving
sessions" until reboot. This replaces the earlier status+participants
heuristic (and drops the aging bound it was growing) with the rule the
deferred-update design stated from the start: the hub is busy while a
client is connected to a session, and replaceable otherwise.
The accepted cost: a participant-less background run executing at the
exact moment of a hub swap dies with the old hub. Rare, and its next
scheduled tick runs normally on the replacement.
* fix(cli): tell the truth about when the outdated Hub is replaced
The outdated-hub dialog and toast said the Hub is replaced "once those
sessions end". It is not: nothing retires a hub except a fresh launch
running the ensure path, so a user who quits the busy session and
watches sees the old hub stay put and concludes something is stuck
(observed in hands-on QA). Say what actually happens - the newer build
takes over the next time Cline starts after those sessions end.
* fix(cli): speak to users, not architecture, in the pending-update notice
"Cline Hub is running an older build" assumes the reader knows what the
Hub is and why builds differ. The user-relevant facts are only: your
update is not fully active yet, your work is safe, and it finishes by
itself. Say exactly that, in both the TUI and desktop dialogs and the
toast, with the version tucked in parentheses for bug reports.
* fix(cli): drop the outdated-hub dialog for a single quiet toast
The dialog interrupted the user to say that nothing is wrong and no
action is needed - the ideal number of modals for that message is zero.
The TUI now shows one info toast ("Update finishes the next time Cline
starts. No action needed.") and the desktop app shows nothing for the
outdated_hub reason; both dialog components return to their shipped
update-and-restart form, which still appears for the build_mismatch
direction where the user genuinely has something to do. The watcher
keeps reporting outdated_hub - surfaces decide, core informs.
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* fix(core): bridge protections for updates landing under pre-3.0.55 clients
Three pieces, each proven against real released artifacts:
- postinstall shield: CLI versions <= 3.0.54 restart the hub daemon after a
background auto-update even while it serves live sessions, and their
fingerprint check then rejects every replacement hub, bricking the running
TUI. That code is on users' machines and cannot be patched — but it runs
only after the install completes, and it bails out harmlessly when no hub
discovery record exists. The newly installed package's postinstall sets
the record aside so the old updater never fires.
- superseded-record fallback: the set-aside record is also the only source
of the auth token and pid the next new-build launch needs to retire the
displaced hub (a port probe carries neither); ensure reads it back.
- bind retry: a hub retired on the fixed port can hold it ~2s after acking
shutdown (watchdog force-exit); the replacement daemon retries EADDRINUSE
for up to 5s instead of dying and leaving no hub at all.
* fix(cli): defer auto-update install until no CLI is attached to the hub
Installing while cline processes run swaps the npm package under them:
their respawn paths break on the new build fingerprint, and the updater
then restarted the hub daemon out from under live sessions (the 'Hub
connection closed (code=1006)' incident). Guarding the restart treats the
symptom; the fix is to never install under a running process.
The startup check now only records that an update is available. The
install runs at process exit, and only when the hub confirms no other
cli* client is attached — desktop sidecars and connectors ship their own
binaries, so only cli* clients make the swap unsafe. With nothing old
running at install time, no hub restart is needed at all: the next launch
retires the stale hub through the existing ensure path. Deletes
restartHubServerIfRunning, ensureCliHubServerAfterUpdate, and their
support code; manual 'cline update' still installs immediately and now
just notes that the update applies on next start.
* fix(cli): apply deferred update from the entrypoint exit sequence
The CLI entrypoint always terminates with an explicit process.exit(),
which never emits beforeExit — the hook the deferred installer waited on,
so it would never have run (caught by review). Invoke applyDeferredUpdate
directly from the entrypoint's exit sequence after disposeAll(), where
every normal termination passes; crash paths deliberately skip it. Also
clear the pending update once an install spawns so the apply is
idempotent.
* test(cli): isolate unit tests from the real ~/.cline
A full vitest run could leave a real hub daemon running against the
developer's actual ~/.cline discovery record (observed while validating
this PR: a daemon spawned from the globally installed cline binary,
attached to the real data dir). Point CLINE_DIR, CLINE_DATA_DIR, and
CLINE_HUB_DISCOVERY_PATH at a per-worker temp dir and disable auto-update
before any test file loads; subprocesses inherit the isolation via env.
* fix(core): discard the superseded discovery record once consumed
The set-aside record is one-shot recovery metadata, but nothing deleted
it, and it feeds a pid into retireDiscoveredHub's SIGTERM. Weeks later a
launch that finds no live record (routine after any retirement) could
read the stale file and signal whatever process the OS recycled that pid
onto (review finding by @abeatrix). Unlink it at every ensure resolution
that ends with a live, verified hub; failure paths keep it for the next
attempt.
* fix(cli): harden the exit-time update gate
Three review findings on the deferred-apply path:
- A wedged hub could stall an otherwise-finished CLI for tens of seconds
via the hub client's default timeouts; the whole exit-time query is now
bounded to 3s, with timeout counting as attached (never install unless
the hub positively confirms).
- Sub-second commands exited before the startup version check resolved
and silently dropped the update every time for one-shot-only usage;
exit now grants the in-flight check a 250ms grace.
- client.list can lose a TUI's registration during transport churn while
its session connection survives, so an empty client list is not proof
of safety; cross-check sessions with participants. Participants rather
than session status: finished sessions linger idle forever and must
not pin updates, and participant-less scheduled runs live in the hub
process, which the binary swap does not touch. Verified live: a
session-holding client invisible to client.list defers the install,
and the gate opens once it disconnects.
* docs(cli): fix stale beforeExit reference in the exit-gate comment
* style(cli): apply biome formatting to update deferral code
* fix(cli): let doctor see a hub whose record the update shield set aside
During the shielded update window the discovery record is renamed to
.superseded so pre-3.0.55 updaters cannot restart a busy hub. Doctor
read only the primary record, so in that window it reported the live
daemon - the one serving the user's still-open old session - as a stale
hub daemon and advised 'cline doctor fix', which kills it and reproduces
the exact 1006 incident the shield exists to prevent (found by QA).
Doctor now falls back to the set-aside record the same way the ensure
path does, and doctor fix clears the set-aside file along with the
primary record so a deliberate reset does not leave stale retirement
metadata pointing at a recyclable pid.
* fix(core): keep shielded sessions on one Hub authority (#13244)
* fix(core): recover shielded busy hub discovery
* chore(core): instrument shielded hub recovery
* fix(core): recover shielded hubs with attached clients
* fix(cli): recognize shielded hubs in doctor
* refactor(core): keep shield recovery minimal
* fix(core): retain shared Hub idle helper semantics
* chore(core): align busyness helper with the #13231 wording
The participants-only hasActiveHubSessions here duplicates the change on
bee/hub-lifecycle (this branch needs its semantics for the participant
gate). Matching that version byte for byte lets the two merges resolve
cleanly instead of conflicting. Also restores the module-registry reset
comment this branch dropped - it documents a real local-vs-CI gotcha.
* fix(core): stop concurrent Hub installs from retiring each other
Two Cline installations on different builds would shut each other's Hub
daemon down in a loop, and every session died with an abnormal socket
close (code=1006) as its daemon was killed mid-handshake.
The retire decision was a one-sided predicate: each client independently
asked "may I reuse this Hub?", and two clients on differing builds both
answered no. #13177 added build-epoch ordering to break the tie, but left
every unordered case - missing epoch, missing build id - retiring as
before, so any pair involving a build from before epochs were embedded
still looped.
Derive the decision from a total order instead. compareHubBuilds orders
two builds by embedded epoch, then core release version, then build id,
and is antisymmetric by construction, so at most one side of a pair can
ever decide to retire. A Hub that is newer or cannot be ordered is
attached over the compatible wire protocol and left to the build-mismatch
watcher to prompt about. Genuine protocol incompatibility still replaces.
Identity is now read from the same fields on both sides. Filling in a
coreVersion locally that the wire record omits made a build's identity
depend on which role it was playing, and the two directions of a pair were
then decided by different tiers with both concluding they were newer -
a second, independent way to produce the loop.
Also:
- Scope the development Hub owner by build id, so differing dev builds run
their own daemon side by side instead of contending for one record.
Production keeps its singleton.
- Break the circuit after repeated retirements of the same URL, bounding
any future ordering bug to a stale-build prompt rather than an
unusable Hub.
- Report `cline doctor fix` honestly: separate processes that survived a
kill from ones that appeared while the fix ran, name the live parent
respawning a daemon, and mark a startup lock held by a running process
as held rather than leaked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(cli): only blame a live parent for processes seen during doctor fix
The advice printed under "started during fix" asserted that every such
process was respawned by a live parent, and told the user to go stop it. A
process can also start on its own mid-repair - someone opening a new
session - and then the instruction points at an unrelated process, or at
none at all.
Derive the wording from whether a live parent actually exists: name it
when every process has one, state the facts when none do, and split the
list when it is mixed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test(core): order the builds in the stale-discovery hub server case
The case stubbed two build ids and expected the second to replace the
first, but supplied nothing that says which came first: no epochs, and both
servers report the same core version. Ordering therefore fell to the
build-id tiebreak, where "new-build" sorts before "old-build" and the
replacement was judged the older of the two.
Give the case the epochs its name implies, and add the missing sibling for
an unorderable pair, which is attached to rather than retired - the
behavior that keeps two installations from shutting each other down.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
* feat(core, llms): Cline custom provider & web search
* fix(llms): preserve reasoning model token parameter
* fix(llms): keep ClinePass provider options on the wire in the shared Cline provider
The shared Cline provider hardcoded the AI SDK provider name to "cline",
but the openai-compatible model reads request-body passthrough options from
providerOptions[<name>]. Option routing emits ClinePass options under the
"cline-pass"/"clinePass" buckets, so gateway reasoning (extended thinking
budgets) silently stopped reaching the wire for cline-pass after it moved
off the generic openai-compatible module.
Thread the gateway provider id through as the provider name, and restore
strictJsonSchema: false for the new "cline" provider-options target so the
wire format matches the previous openai-compatible behavior. Add cline-pass
coverage at both the option-routing and request-body levels.
* feat(sdk): persist provider-executed tool activity (#13077)
* feat(core, llms): Cline custom provider & web search
* fix(llms): preserve reasoning model token parameter
* feat(sdk): persist provider-executed tool activity
* fix(vscode): restore state proto and settings section reverted by merge
The merge of origin/bee/websearch into this branch resolved conflicts by
keeping this branch's pre-#13126 copies of apps/vscode files, which
deleted the auto_approve_all_toggled = 174 proto field (without reserving
the number) and dropped a formatting line in FeatureSettingsSection.tsx.
Neither file is in scope for this PR. Restore both to main's content so
the proto source matches the checked-in generated code again.
* chore(vscode): match main byte-for-byte in FeatureSettingsSection.tsx
The pre-commit biome hook strips a blank line that exists on main, which
kept this out-of-scope file in the PR diff. Commit the exact main content
with --no-verify so the PR no longer touches apps/vscode at all.
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* refactor(llms): key ClinePass provider options to the shared cline bucket
Both Cline gateway ids (cline and cline-pass) are served by the same
shared "cline" AI SDK provider and hit the same Cline API, so threading
the gateway provider id through as the AI SDK provider name (78dc6f3e7)
was unnecessary indirection. Revert the name threading and instead
normalize option-routing bucket keys: buildProviderAndAliasPatch now
keys both Cline gateway ids to the shared "cline" providerOptions
bucket, which is the only bucket the openai-compatible model reads for
request-body passthrough.
Also tighten the regression coverage that motivated the original fix:
the previous effort-based test rows were vacuously satisfied through the
portable-reasoning early return (effort reasoning never reaches provider
option buckets by design). The rows now use explicit reasoning budgets,
which do flow through the gateway bucket path, and the wire-level test
composes real provider options end to end instead of hand-feeding
buckets.
* revert(llms): drop the cline strictJsonSchema special case in generic-compatible
Restores buildCompatibleProviderOptions to its pre-78dc6f3e7 state. The
strictJsonSchema passthrough is verified inert for the gateway (nothing
in @cline/llms sets a response format), so keeping a hardcoded provider
target in the generic helper bought nothing. If structured outputs are
ever added, strictness for the cline target can be decided deliberately
then.
* fix(llms): claim native web search for openai-native, not the openai alias
supportsModelTool listed "openai", but that id aliases to
openai-compatible (PROVIDER_ID_ALIASES), whose module has no native web
search. The actual native OpenAI builtin id is "openai-native", which is
served by the OpenAI Responses module that does implement
buildModelTools with provider.tools.webSearch(). Without this, the
web_search tool was never offered to native OpenAI users, and was
wrongly offered for the compatible alias.
* refactor(llms): declare model tools in provider manifests
* feat(sdk): project provider tool activity in session history
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Picks up the shared button primitives (#13164), the one-row-per-tool-call
chat rendering (#13186), the refined session chat layout (#13205), and the
@pierre/diffs hunk renderer (#13201) that landed since 0.2.0-next.3.
* Render desktop diff view hunks with shared @pierre/diffs renderer
Replace DiffView's hand-rolled DiffHunk +/- line rows with ToolFileDiff
from @cline/ui (backed by @pierre/diffs), matching the chat tool rows.
Hunks carrying complete new contents (created files) render with real
line numbers; fragment hunks hide them, mirroring ToolCallRow. All of
DiffView's chrome (collapse, copy, open-in-editor, counts) is unchanged.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Make ToolFileDiff syntax palette follow the app theme, not browser preference
@pierre/diffs declares 'color-scheme: light dark' on its shadow :host, so
its light-dark() token colors resolve from the browser's preferred scheme.
Apps themed by the .dark class (desktop app) got the light palette's
near-black text on dark surfaces. Inline colorScheme: inherit on the host
wins over the :host rule and follows the app's color-scheme, which the
@cline/ui theme already flips with .dark. Skipped when a caller pins an
explicit themeType.
Also key diff-view hunks by index so repeated same-shaped hunks (a file
created twice with identical contents) don't collide.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The Claude Code provider was unusable for agentic work (#13146):
- The claude-code manifest lacked the provider-tools capability, so the
gateway sent Cline's tool definitions (which the provider drops as
unbridgeable) while the CLI's native tools stayed enabled with no
approval plumbing - every write was refused and no prompt appeared.
- ai-sdk-provider-claude-code defaults settingSources to [], so the
spawned session read neither ~/.claude/settings.json nor project
settings, silently ignoring user-configured permission rules.
- No cwd was passed, so the session inherited the extension host's
cwd (/ on macOS) and refused writes outside it.
Changes:
- Mark claude-code with provider-tools (same treatment as the Codex
CLI provider): stop sending unbridgeable external tools and let the
CLI execute its own, tagged executionMode=provider for the runtime.
- Forward the session workspace cwd from @cline/core into the
claude-code gateway provider options and lift it into the agent
session settings.
- Default settingSources to [user, project] and permissionMode to
acceptEdits (file edits under cwd auto-approved; command execution
stays gated by the user's own Claude settings), all overridable via
explicit defaultSettings.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): don't let a stale queued send response wedge the composer
A fresh session is still busy while its interactive loop starts, so the
sidecar coerces the first send onto the pending-prompt queue and replies
{queued:true} with a queue snapshot taken at enqueue time. The turn itself
runs via the runtime's queue drain and completes through stream events
(chat_queued_prompt_start -> deltas -> chat_done). On cold/slow sidecars the
RPC response lands only after those events; the webview then applied the
stale snapshot and unconditionally set status back to "running", leaving
the composer on "Agent is working..." forever and resurrecting a phantom
queue entry.
Webview: capture the turn epoch at send dispatch; chat_queued_prompt_start
bumps it, so a mismatch when the queued response arrives means the stream
already advanced the turn lifecycle and the response is ignored. Aborts now
resolve the queued branch to "cancelled" like the direct path.
Sidecar: the queued send response no longer routes its enqueue-time snapshot
through applyPendingPrompts, which overwrote the event-maintained
session.promptsInQueue and rebroadcast the stale list to every webview.
Includes deterministic regression tests for the stale-response orderings
plus temporary [P0DBG] debug instrumentation (region-marked, to be removed
after runtime verification).
* fix(desktop): ignore stale hub 'running' status after turn settles
The sidecar core is hub-attached, so chat_session_status events are
asynchronous projections of the hub's session record. A stale 'running'
can trail the stream's chat_done and flip a settled turn back to busy,
wedging the composer on 'Agent is working…' with nothing left to
reconcile. Track the epoch at which the turn settled and drop 'running'
status events until a new turn bumps the epoch.
* chore: remove stray QA screenshot artifacts from repo root
* chore(desktop): remove P0 debug instrumentation and fault injection
Strips all [P0DBG] logging, the /p0dbg sidecar route, the webview log
mirror + heartbeat, and the P0DBG_STARTUP_BUSY_MS /
P0DBG_DELAY_QUEUED_RESPONSE_MS fault-injection paths used to reproduce
the stuck-composer P0. The two real fixes (stale queued-response epoch
guard + stale-running-after-settle guard in the webview, and the
sidecar's non-clobbering queued-send snapshot) and the regression tests
remain.
* refactor(desktop): replace turn-epoch guards with an explicit turn lifecycle
The stuck-composer fixes left the hook with two hand-rolled epoch refs
(turnEpochRef / turnSettledEpochRef) mutated and compared inline across
eight call sites. Extract the rules into a pure TurnLifecycle module that
is now the only writer of the session status:
- a settled turn cannot be reopened: stale hub 'running' projections and
stale queued-send acknowledgements are dropped by the lifecycle instead
of by inline epoch comparisons
- async work (send RPC responses, queue reconciliation) captures an opaque
token and the lifecycle decides whether the world moved on, instead of
handlers comparing counters
- every status write goes through a named operation (begin, turnStarted,
settle, projectStatus, apply, reset), so the state machine is explicit
and unit-testable in isolation
No behavior change: the 5 wedge regression tests and the full hook suite
pass unchanged, plus 10 new unit tests for the lifecycle module itself.
* Revert "refactor(desktop): replace turn-epoch guards with an explicit turn lifecycle"
This reverts commit c480aaabe8.
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(vscode): stop legacy-migration backlog telemetry spam, emit real migration outcomes
* refactor(vscode): slim migration telemetry fix to minimal surface
* fix(vscode): emit legacy migration outcome only after seeded session start settles
The completed event fired at in-memory conversion time, before the
seeded session start persisted the migration, so a start/persistence
failure was misreported as a successful migration and never produced an
error outcome. Conversion now records a pending migration; the followup
and compaction coordinators settle it after the session start resolves
(completed) or rejects (error/session_start_failed).
* fix(vscode): surface seeded-persistence failures in migration outcomes
LocalRuntimeHost.startSession deliberately swallows seeded-message
persistence failures (the in-memory session still works), so a resolved
start was not proof the legacy conversion became durable. The start
result now reports seededMessagesPersistence, and the resume/compaction
coordinators settle the migration from that result: completed only when
the seed write succeeded, error/seed_persistence_failed when the start
resolved but the write failed, error/session_start_failed when the
start rejected. durationMs now spans conversion through settlement.
Adds the core boundary test forcing persistSessionMessages to fail and
asserting the start still resolves with the failure visible on the
result, plus coordinator tests for both failure modes.
* refactor(vscode): drop per-task migration outcome events, keep volume fixes only
Scope the PR down to the zero-behavioral-risk telemetry fixes, per
review: keep the backlog event transition gating and the one-line
migratedSdkTaskCount fix (counting resumed legacy sessions via their
legacyTask metadata), and revert the per-task terminal outcome
plumbing (pending-migration settlement, coordinator hooks, and the
core StartSessionResult.seededMessagesPersistence field) along with
the success->completed outcome rename on the now-uncalled
captureLegacyTaskMigration. The per-task outcome events can land
separately on the observable persistence boundary.
* fix(llms): reject truncated tool-call JSON with unterminated strings
* fix(llms): scope truncation guard to jsonrepair only and handle single quotes
* fix(shared): keep jsonrepair ahead of bare-object repair for typed literals
Restores main's precedence for inputs both strategies can handle:
{"flag": True} must repair to a typed true, not the string "True".
The truncation guard now gates only the jsonrepair step, which is the
only strategy that can invent a string terminator.
---------
Co-authored-by: Mikołaj Kondratek <19799111+mkondratek@users.noreply.github.com>
A message whose content array held only empty text parts slipped past the
existing empty-content guards in formatMessagesForAiSdk (which cover
content: "" and content: []). The AI SDK then strips empty text parts,
producing {"role":"user","content":[]} on the wire, which strict
providers reject — seen in prod as Vercel 400s for kimi-k3:
"user message must have content".
* fix(telemetry): emit disjoint per-request token buckets in task.tokens
SDK usage events follow the AI SDK convention where inputTokens is the
full request input including cache reads/writes. task.tokens forwarded
that value as tokensIn while also reporting cacheReadTokens and
cacheWriteTokens, so every event re-counted the whole (mostly cached)
conversation context and per-task token sums inflated ~5x on
cache-heavy sessions relative to the legacy contract (tokensIn =
uncached input only, disjoint buckets).
task.tokens now subtracts the cache buckets from tokensIn at the
capture site (mirroring the webview's normalizeUsageEvent), defaults
the cache buckets to 0 instead of undefined, and stamps the provider
attribute for parity with the legacy event schema. Event and attribute
names are unchanged.
* fix(core): normalize registered ApiHandler usage to cache-inclusive inputTokens
Review follow-up: two producer contracts shared AgentUsage.inputTokens.
Native AI SDK usage reports the full cache-inclusive prompt size, but the
ApiHandler adapter forwarded classic disjoint chunk.inputTokens unchanged,
so the task.tokens cache subtraction would zero out real uncached input
for a cache-reporting registered handler.
Normalize at the adapter boundary (inputTokens + cacheReadTokens +
cacheWriteTokens) so every producer entering AgentUsage satisfies the
same cache-inclusive invariant, document that invariant on
AgentTokenUsage.inputTokens, and reframe the telemetry clamp as a
defensive guard rather than a supported producer shape. Adds an adapter
normalization test and a boundary test from an ApiStreamUsageChunk
through task.tokens asserting the disjoint buckets round-trip.
* Revert "fix(core): normalize registered ApiHandler usage to cache-inclusive inputTokens"
This reverts commit 9a9aff374a.
* fix(telemetry): report involuntary Cline logouts from the SDK auth service
The SDK auth service cleared credentials silently when a refresh token was
rejected (invalid grant), both mid-session and during startup restore, so
user.auth_logged_out never captured involuntary logouts on the next bundle.
Emit token_invalid at both credential-clearing sites and restore_error when
startup restore throws, matching the reason vocabulary the legacy bundle now
uses so the same warehouse query measures involuntary logouts across rollout
variants. Startup with no stored session still emits nothing.
* refactor(telemetry): trim logout-reason parity change to the minimum
* fix(telemetry): report Cline invalid-grant logouts as token_invalid in the SDK resolver
getValidClineCredentials is the single owner of the involuntary-logout
event for the Cline provider; normalize its reason to the legacy
extension's LogoutReason vocabulary (token_invalid) so warehouse queries
cover both bundles. The raw OAuth code stays in errorCode. Codex/OCA
paths keep emitting invalid_grant and are unaffected.
* fix(telemetry): let the SDK resolver own token_invalid; keep restore_error for real restore failures
Address review on the SDK-adapter half of the logout-reason split:
- drop both adapter-side token_invalid emissions - the SDK resolver
already emits user.auth_logged_out on the same telemetry instance, so
the adapter was double-counting the exact signal being measured
- transient failures refreshing the stored session on startup (resolver
throws: network/timeout/5xx) no longer book as restore_error; stored
credentials are kept and the SDK books auth_refresh_soft_failure, so
an offline startup is not a logout
- single-source LogoutReason in services/auth/types.ts and re-export it
from the SDK auth service instead of maintaining two parallel enums
- boundary test runs the real getValidClineCredentials and asserts
exactly one auth_logged_out (reason=token_invalid) total, so a
reintroduced adapter emission fails the suite
* feat(hub): prompt update and restart when another install replaces the shared Hub
* feat(hub): make managed Hub build-watch interval configurable via CLINE_HUB_BUILD_WATCH_INTERVAL_MS
* feat(hub): reuse newer managed Hub builds instead of retiring them
Embed a build epoch alongside the deterministic runtime fingerprint so
managed-Hub compatibility can order builds in time. When fingerprints
differ, a Hub produced after the client's own build is attached over the
compatible wire protocol (and the build-mismatch watcher prompts the user
to update) instead of being retired, so concurrent installations converge
on the newest build rather than replacing each other's daemons. Older,
unordered, or metadata-less Hubs are retired and replaced as before.
* refactor(hub): simplify mismatch status derivation and dedupe sidecar event encoding
* fix(cli): only watch for managed Hub build mismatches in hub-attached sessions
Yolo and sandbox sessions force the local backend and never attach to the
shared managed Hub, so a newer Hub owned by another installation must not
interrupt them with the blocking update dialog.
* fix(desktop): stage an app update before hub-mismatch restart
'Update and restart' previously invoked restart_to_apply_update directly,
which only relaunches the current bundle. With no update staged by the
background 2h updater loop, the app came back on the same version, hit the
same newer Hub, and re-prompted immediately.
Add a check_for_update_now Tauri command that runs one updater
check/download/stage cycle on demand and reports the resulting status. The
dialog now stages the update first and restarts only when the updater
reports 'ready'; otherwise it stays open and explains that no update is
downloadable yet (or that the check failed) instead of restarting into the
same version. Addresses the outstanding Greptile P1 on the dialog.
* fix(desktop): reset the no-update hint when a new hub mismatch arrives
Without this, a dialog for a fresh mismatch reopened pre-set to 'Try again'
with the previous prompt's stale hint.
* fix(desktop): serialize updater cycles so overlapping checks cannot clobber a staged update
The periodic update loop and the on-demand check_for_update_now command
run the same check/download/stage cycle against shared state. Without
exclusion, two overlapping cycles could download the same bundle
concurrently, and the later one could overwrite a freshly staged "ready"
status with "idle" or "error" decided from its stale pre-await
ready_version snapshot - making the update dialog deny that a staged
update exists. A tokio::sync::Mutex now serializes whole cycles; the
ready_version snapshot is read under the lock, so it stays authoritative
for the cycle that took it.
* fix(core): harden Hub daemon lifecycle
* fix(core): wait for Hub listener before replacement
* fix(core): recover after Hub cleanup errors
* fix(core): assign the close memo handle before socket termination re-enters beginClose
On every shutdown with a connected client, the daemon logged
'unhandledRejection: AggregateError: hub server close failed' and exited
with code 1 instead of 0. Root cause: beginClose() terminated the
tracked WebSockets before assigning closeHandle. terminate() fires close
events whose microtask continuations advance the daemon coordinator's
deferred cleanup into server.beginClose() while the first invocation is
still mid-body, so the memo guard passes twice and a second set of
wss.close()/server.close() calls runs against the already-closing server,
rejecting with 'Server is not running' and spuriously failing the close
aggregate. The rejection then rode the daemon's unhandledRejection
fatal path and escalated the exit code.
Construct the close promises and assign the memo handle first, and only
then terminate sockets and run detach handlers; a re-entrant call now
hits the memo guard. Also observe the /shutdown handler's
fire-and-forget closeServer() so a genuine close failure is reported
solely by the owner's own await on the same memoized promise instead of
the unhandledRejection path.
Verified with a real daemon: shutdown with zero clients stays graceful
(exit 0, ~26ms); shutdown with a held-open authenticated WebSocket now
exits 0 with no unhandled rejection, still bounded by the 2s coordinator
deadline for the genuine Bun listener-close stall, with the discovery
record cleaned. Hub suites (228) and the shutdown e2e (5) pass.
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* fix(llms): update AI SDK deps to fix streamed tool calls with non-zero indexes
LiteLLM's Anthropic passthrough emits chat-completions tool_call deltas
whose index mirrors the Anthropic content-block index (1 when a text
block precedes the tool call; see BerriAI/litellm#11580).
@ai-sdk/provider-utils 5.0.18 stored streamed tool calls in a sparse
array keyed by that index and crashed at stream flush with
"Cannot read properties of undefined (reading 'hasFinished')",
aborting the agent turn. Upstream fixed this in provider-utils 5.0.21
("Fix streamed tool calls with non-zero, non-contiguous, reused, or
missing indexes.").
Update the ai / @ai-sdk packages so every chat-completions streaming
path resolves @ai-sdk/provider-utils 5.0.25, and drop the root
">=4.0.0" override on @ai-sdk/provider-utils: with intersect semantics
it pinned the workspace to the already-locked 5.0.18 even after parents
began requiring 5.0.25, and it force-upgraded dify-ai-provider two
majors past its declared ^3 range. Each package now resolves the
version line it declares.
Fixes#13119
* test(llms): pin non-zero streamed tool_call index regression (#13119)
Wire-level regression test: an openai-compatible SSE stream whose only
tool_call delta carries index 1 (Anthropic content-block numbering via
LiteLLM) must complete and emit the tool-call part instead of throwing
at flush.
* fix: address review findings from merge-conflict resolution
- Restore apps/vscode/proto/cline/state.proto to main's version: the
merge commit's pre-commit hook regenerated it with a stale generator,
deleting auto_approve_all_toggled = 174 and moving a reserved line,
creating drift against the checked-in descriptor. The deletion was
never intended.
- Restore FeatureSettingsSection.tsx to main's version (the same hook
reformatted main's file during the merge).
- Regenerate bun.lock narrowly from main's lockfile without --force so
the diff contains only the @ai-sdk family and its direct transitives;
drop the spurious webview-ui-scoped @radix-ui duplicate entries the
previous install introduced (hoisted resolutions still satisfy
webview-ui's unchanged ranges; verified with --frozen-lockfile).
- Align @ai-sdk/provider to ^4.0.7 in @cline/llms to match the rest of
the AI SDK family and avoid parallel provider resolutions.
Revalidated: wire repro streams to finishReason=tool-calls, @cline/llms
suite passes incl. the index-1 regression test, all workspaces
typecheck, SDK builds clean.
* fix: restore FeatureSettingsSection.tsx to main's formatting
The branch's pre-commit biome hook (--semicolons=as-needed, --write
--staged) strips a blank line from this file whenever it is staged,
which is how the unintended diff appeared in the merge commit. Commit
with --no-verify to keep the file byte-identical to main; this PR does
not touch the VS Code webview.
* refactor(desktop): extract chat transcript logic to messages/
Verbatim moves out of chat-messages.tsx (2,415 -> ~1,300 lines), with no behavior changes.
- Extract shared constants, grouping and reasoning helpers, tool summaries, and tool icons into messages/.
- Add unit tests for the extracted pure logic.
- Update test:chat-ui to include tests under messages/.
chat-messages.test.tsx remains unchanged and continues to pass.
* refactor(desktop): extract chat message components to messages/
Moves MessageBubble, ReasoningBlock, ToolMessageBlock, ToolApprovalPanel
(+ formatApprovalTimestamp and the ToolApprovalRequestItem type), and the
image lightbox out of chat-messages.tsx into their own modules under
messages/. Memo wrappers, comparators, and prop contracts are unchanged;
chat-messages.tsx keeps only the ChatMessages orchestration (~780 lines).
chat-messages.test.tsx is untouched and still passes.
* refactor(desktop): extract chat transcript logic to messages/
Verbatim moves out of chat-messages.tsx (2,415 -> ~1,300 lines), with no behavior changes.
- Extract shared constants, grouping and reasoning helpers, tool summaries, and tool icons into messages/.
- Add unit tests for the extracted pure logic.
- Update test:chat-ui to include tests under messages/.
chat-messages.test.tsx remains unchanged and continues to pass.
* refactor(desktop): extract chat message components to messages/
Moves MessageBubble, ReasoningBlock, ToolMessageBlock, ToolApprovalPanel
(+ formatApprovalTimestamp and the ToolApprovalRequestItem type), and the
image lightbox out of chat-messages.tsx into their own modules under
messages/. Memo wrappers, comparators, and prop contracts are unchanged;
chat-messages.tsx keeps only the ChatMessages orchestration (~780 lines).
chat-messages.test.tsx is untouched and still passes.
* refactor(desktop): extract chat message components to messages/
Moves MessageBubble, ReasoningBlock, ToolMessageBlock, ToolApprovalPanel
(+ formatApprovalTimestamp and the ToolApprovalRequestItem type), and the
image lightbox out of chat-messages.tsx into their own modules under
messages/. Memo wrappers, comparators, and prop contracts are unchanged;
chat-messages.tsx keeps only the ChatMessages orchestration (~780 lines).
chat-messages.test.tsx is untouched and still passes.
* fix(telemetry): stop mirroring per-token stream deltas into telemetry
Gate assistant-text-delta, assistant-reasoning-delta, and tool-updated
runtime events out of the unconditional telemetry.capture mirror in
AgentRuntime.emit. These fire once per streamed token or tool progress
chunk and accounted for ~97% of all agent.* telemetry volume in the
field with no analytical value. Listeners, hooks.onEvent, and the
run-failed sdk.error reporting are unchanged; the gate is a static
Set lookup so no per-event allocation is added.
* refactor(telemetry): inline stream-delta telemetry gate as a switch
Replace the module-level Set constant with case labels directly at the
capture site; same behavior, less indirection.
* feat(ui): styled label parts, terminal-style commands, and patch fidelity fixes
Label segments: ToolSummary gains labelParts ({text, code?}[]) so
consumers can render code-ish segments (file names, commands, queries,
URLs) in a monospace face. Single commands now read like a terminal
prompt — '$ bun test' — and an untruncated single command no longer
duplicates itself as a detail line.
Review fixes folded in:
- apply_patch preserves hunk boundaries: per-hunk oldText/newText on
ApplyPatchFile and file items (re-diffing concatenated hunks let a
deletion in one hunk pair with an addition in another), plus action
metadata — Delete File labels as 'Deleted x' with no phantom diff,
'*** Move to:' renames display as 'old → new'.
- run_commands accepts every RunCommandsInputUnionSchema shape (single
entry, bare arrays, top-level {command,args}, {cmd}).
- makeUnifiedDiff treats empty text as zero lines, so creating an empty
file or deleting all content no longer reports a phantom +1.
- parseWebFetchInput drops non-string urls instead of stringifying
objects into labels.
- hoisted a double normalizeValue in the unknown-tool fallback.
* refactor(desktop): render each tool call as its own chat row
Drops the consecutive-call grouping ('Read 3 files · Ran 2 commands')
in favor of one row per tool call — each with its own icon, status,
disclosure, and treatment per kind:
- commands read like a terminal: '$ bun run test' in monospace, with
the captured output in a capped scrollable mono block on expand and
'$ '-prefixed detail lines for multi-command calls
- edit rows carry mono filenames, the +/- badge, and their pierre
diffs pre-expanded (one diff per hunk for multi-hunk patches),
keeping the user-toggle override from the grouped implementation
- reads/searches/fetches keep inline specifics with mono code segments
via the shared labelParts
Also fixes the test:chat-ui exit-1 regression flagged in review:
@pierre/diffs' custom element calls CSSStyleSheet.replaceSync, which
jsdom lacks — a prototype polyfill in the suite keeps the real
component in the test tree (and the pre-expand assertions meaningful)
while letting the run exit 0. This suite gates ui-publish.yml.
* fix(desktop): keep the thinking indicator up during quiet turn stretches
The indicator only covered the gap right after a user message, so the
turn looked frozen while the model composed its next step — most
noticeably while streaming tool-call arguments, when neither text nor
a tool row is on screen. It now shows whenever the turn is running and
nothing else is visibly active (no streaming text, no in-progress tool
row, no pending approval/question).
* feat(ui): action-first tool labels
Every row leads with the plain action phrase — 'Ran command',
'Read file', 'Edited file', 'Created file', 'Deleted file' — with the
specifics (command, file name, line range) following as a monospace
segment. The mono segment renders at full size; the previous 0.92em
downscale made it look smaller than the surrounding prose.
* fix(desktop): chat polish — indicator alignment, action spacing, no expanded fade
- The Thinking indicator now mirrors the tool-row trigger metrics
(min-h-7, py-1, gap-2, 16px icon, font-medium, 8px rhythm) so the
text no longer shifts when the indicator swaps with an arriving
tool row.
- The copy/fork/timestamp action row sat 4px up into the message text
above it (-translate-y-1); it now rests 2px below the message block.
- Expanded reasoning/tool panels rendered at 70% opacity with
hover-to-unfade; expanded content is what the user is reading, so it
now renders at full opacity.
* feat(ui): violet active rows, gray finished rows, no green hover
Tool-row colors follow activity: running/pending rows (and the row
spinner) carry the brand violet, finished rows settle into
muted-foreground gray, and hover brightens toward the foreground
instead of hue-shifting to the success green. Errors stay red.
Also: maxInlineChars default raised 60 → 200 so real commands stop
getting truncated (the cap is now only a guard against pathological
payloads; layout handles overflow), and expanded editor rows lead with
the fuller file path above the diff, matching read rows.
* refactor(ui): let layout own label overflow instead of char caps
maxInlineChars now defaults to unlimited — labels carry the full
command/task/question text (whitespace collapsed to one line) and
.cline-chat-tool-label ellipsizes at the container edge via CSS
(nowrap + text-overflow) instead of wrapping. The cap remains as an
opt-in for width-constrained surfaces like TUIs. Since the label can
now be visually cut by layout, single-command rows always carry the
full command in their expanded details.
* fix(ui): drop stale green base color on tool triggers
The redesign moved finished tool rows to muted gray and running rows to
brand violet, but a leftover .cline-chat-tool-trigger { color:
var(--success-text) } rule later in the sheet overrode the gray base, so
every settled row still rendered green.
* fix(desktop): give message actions clear separation from message text
2px below the text read as touching; 6px (translate-y-1.5) gives the
copy/fork/timestamp row visible breathing room.
* feat(ui): spinner replaces the tool icon while a call is in flight
The progress ring used to append to the right of the label, so running
rows sprouted chrome instead of reading as one glyph + label. It now
takes the icon slot and fills the same 1rem box, so the label never
shifts when the icon swaps back in on completion.
* fix(desktop): align thinking indicator with the tool row that replaces it
The indicator sits outside the message column, so it already inherits the
conversation gap; its own mt-2 stacked on top and rendered it 8px lower
than the tool row that swaps in.
* style(desktop): message actions match chat text scale in a lighter gray
Copy/edit/restore/fork icons go from 12-14px to the 16px the rest of the
chat chrome uses, the timestamp moves from 11px to text-sm, and the whole
row renders at 70% muted-foreground so it reads as secondary chrome;
hover still brightens to full foreground.
* style(ui): running tool rows share the thinking indicator's gray
Violet-on-running read as a different system than the muted thinking
state it replaces; the spinner alone now signals activity. The progress
ring draws in currentColor so it stays gray on normal rows and red on
error rows without extra rules.
* style(desktop): nudge message actions down 2px and scale them down a step
Actions row moves from 6px to 8px below the message text; icons go
16px -> 14px and the timestamp text-sm -> text-xs after the previous
bump overshot.
* fix(ui): don't unstick conversation follow when content grows
Stick-to-bottom flipped off whenever a scroll event landed between a
content-height jump (tall diff rows mounting) and the resize observer's
re-pin: the handler read the new distance-from-bottom as the user having
left the bottom. Sticking is now released only by an actual upward
scroll and always restored on reaching the bottom, so the transcript
keeps following while rows stream in.
* feat(ui): user message bubbles on a filled brand-violet surface
The card-colored bubble sat too close to the app background to read at
a glance. New brand-violet-surface tokens (deep enough for near-white
text in both themes) fill the user bubble.
* style(desktop): give the conversation bottom padding above the composer
The last message (and its hover actions hanging below) butted against
the composer border.
* fix(desktop): composer keeps its two-line height when unfocused
Collapsing to one row on blur made the input and the conversation above
it jump on every focus change; the focus-tracking state existed only to
drive that resize.
* refactor(ui): simplify AgentAskQuestion and move it to the brand accent
The 'Follow-up question' heading, intro sentence, and box-in-box nesting
made a one-question prompt read like a form. The question now leads the
card directly (icon + text + option buttons) and the accent shifts from
blue to brand violet, with the section still labelled for assistive
tech.
* fix(desktop): pending questions and approvals render at the end of the transcript
They rendered above the whole conversation like a banner, so a follow-up
question appeared at the top of the chat instead of where the
conversation actually is.
* fix(desktop): keep message actions reachable and make hover/focus feedback instant
The 8px offset under a message was a translated gap — dead space that
dropped the parent's :hover midway to the buttons, hiding them before
they could be clicked. The offset is now padding on the actions element
so the hover chain stays unbroken. Also removes the opacity fade on the
actions row and the composer's focus border transition: both read as lag
rather than polish.
* feat(ui): add shared tool-summary presentation module
Pure, framework-free tool-call presentation logic under
@cline/ui/components/agent-chat/tool-summary: buildToolSummary and
buildGroupedToolLabel turn raw {toolName, input, result} payloads into
rich row labels (file names with line ranges, inline commands, search
queries, URLs), per-item details, +/- diff counts, per-file unified
diffs (editor old/new text and apply_patch envelopes), team_* labels,
and MCP-aware output text extraction. Merges the desktop app's
buildToolSummary layer with the CLI's tool-parsing/diff utilities so
every @cline/ui consumer renders tool rows consistently.
Exports the new subpath from package.json, extends the packed-tarball
smoke test to cover it, documents the boundary change in ADOPTION.md,
and bumps the package to 0.2.0-next.3.
* refactor(desktop): adopt shared tool-summary for chat tool rows
Replaces ~950 lines of app-local tool extraction (buildToolSummary,
teamSummary, parsers, grouped-label logic) in chat-messages.tsx with
the @cline/ui tool-summary module. Desktop tool rows gain single-call
specifics inline (Read app.tsx (10-80), Ran bun test, Edited util.ts
with +/- badge), line ranges on reads, shortened paths with directory
context in expanded details, per-file unified diffs in the expanded
panel, and grouped labels joined with a middot. Detail keys switch to
index-based to fix duplicate-line key collisions. Icons re-key on the
shared ToolKind classification.
* fix(ui): stop fabricating line positions in fragment tool diffs
Editor str_replace payloads carry old_text/new_text as fragments of the
file, but makeUnifiedDiff treated them as whole files and emitted hunk
headers anchored at line 1, mislocating the change in expanded edit
rows (Greptile P1 on #13151). Fragment diffs now use a neutral
'@@ … @@' separator; only whole-file content (editor create,
apply_patch Add File sections) keeps real hunk positions.
File items also expose the raw oldText/newText (reconstructed from
hunks for apply_patch) plus a fragment flag, so rich diff renderers
can consume the texts directly instead of re-parsing unified output.
* feat(ui): render tool-row edit diffs with @pierre/diffs
Adds @cline/ui/components/agent-chat/tool-diff exporting ToolFileDiff,
a thin wrapper over @pierre/diffs (optional peer dependency) that
renders a tool-summary file item as a syntax-highlighted, theme-aware
unified diff. Fragment diffs hide line numbers instead of showing
misleading ones. The desktop chat renders edit diffs through it, and
tool groups containing an edit diff now open pre-expanded so the diff
is immediately visible.
ADOPTION.md reframes the shared-module story: extracting presentation
logic products would otherwise duplicate is the direction @cline/ui is
headed, with tool-summary and tool-diff as the first two modules. The
packed-tarball smoke test covers the new subpath in both consumers.
* fix(ui): blend tool diffs into the app surface
Two polish fixes to ToolFileDiff from design review:
- Normalize trailing newlines on both sides before diffing so tool
payload fragments (which rarely end in a newline) don't litter every
diff with 'No newline at end of file' markers.
- Map @pierre/diffs' background hooks (--diffs-light-bg/--diffs-dark-bg)
to the host app's --background token (stock white/black fallback),
so the diff surface and all its color-mixed tints (context lines,
gutters, separators) derive from the app background instead of
pierre's pure white/black. Overridable via a new background prop.
Storybook's ToolSummaries story now renders file items through
ToolFileDiff pre-expanded (matching the apps) and adds a multi-file
apply_patch fixture.
* fix(desktop): pre-expand tool groups when edit diffs arrive mid-stream
defaultOpen only applies at mount, but a streaming tool group mounts
with its first (often read) call and gains the edit later, so live runs
never saw the promised pre-expanded diff. Drive the disclosure with
controlled state that opens when a file diff first appears, unless the
user has toggled the row themselves. Covers the streaming path with a
rerender test.
* chore(ui): replace font dependencies
* refactor(ui): migrate shared typography tokens
* refactor(ui): adopt Inter and Geist Mono in apps
* fix(hub): preserve variable font weight tokens
* feat(ui): tune font weights for dark mode
* docs(ui): add font migration screenshots
* (chore)ui: misc typography adjustments
* fix(hub): make dark-mode font-weight overrides take effect
Tailwind's @theme inline bakes literal values into utilities, so the
.dark --font-weight-* overrides were dead code and dark mode rendered
the heavier light-mode weights. Declare the weights in :root instead so
font-* utilities keep their var() references, matching the @cline/ui
tokens approach. Also rewrap --font-mono to satisfy biome format.
* fix(ui): restore light-mode semibold to 640 and pin weight scales in test
The PR intent is a 480/560/640/640 light scale with 400/500/600/600
dark overrides, and the Hub already uses 640; tokens.css had drifted to
600 for light semibold. Regenerate scoped-tokens.css and assert both
the light and dark weight scales in the theme contract test.
* chore(desktop): remove stray double space in provider header class
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Verbatim moves out of chat-messages.tsx (2,415 -> ~1,300 lines), with no behavior changes.
- Extract shared constants, grouping and reasoning helpers, tool summaries, and tool icons into messages/.
- Add unit tests for the extracted pure logic.
- Update test:chat-ui to include tests under messages/.
chat-messages.test.tsx remains unchanged and continues to pass.
getAuthToken captured expiresAt before refreshing, then validated the new
token against that stale value. When the old token was already past expiry
(not just inside the 5-minute buffer), a successful refresh was thrown
away and null returned, so the first call after long idle failed despite
valid credentials. Re-read the expiry from the refreshed auth info.
* fix(hub): don't forward recoverable agent errors to dashboard peers
Recoverable error events are in-run notices, not turn outcomes: the
MistakeTracker emits one for every recorded mistake (e.g. a plan-mode
guard-blocked run_commands call) while the run continues. The hub
dashboard forwarded every error event to peers, so the webview dropped
out of the sending state and appended an error row mid-turn — the same
host bug fixed for VS Code and the CLI in #12953.
Gate the forward on recoverable, matching those hosts: the tool failure
is already shown inline via the failed tool_event, and the turn's
outcome stays decided by how it actually ends (turn_done or a
non-recoverable error). Recoverable errors are logged server-side.
* fix(hub): forward recoverable flag to peers instead of filtering server-side
Per review: the server is a translation layer between agent events and
the webview protocol, so it should not embed display policy or console
logging. Forward every agent error with its recoverable flag on the
peer message and let each peer decide — the webview keeps recoverable
errors out of the transcript and keeps the turn state, matching how the
CLI gates display on the same flag while the information stays
available to any peer that wants it.
* add custom model selection to the vertex provider
* fix race conditions from PR review
* fix linter warnings
* fix test failures
* refactor(vscode): drop Vertex global-endpoint picker filtering
The SDK catalog is live (models.dev), so a static host allowlist of
global-endpoint-capable models lags every model launch and silently hides
new models from users on vertexRegion=global. Remove the allowlist, the
host override that injected supportsGlobalEndpoint, and the picker filter;
show the full catalog for every region.
An unsupported pick now fails loudly at request time: map Vertex's
'model not available in region: global' (and Google's Publisher Model
locations/global not-found body) to recovery guidance in the error row.
Also drop Anthropic's universal pricing from the Vertex Fable 5 overlay —
Vertex bills region-dependently, so the copied price understated recorded
cost; the record now carries no pricing instead of a wrong one.
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* fix: remove stale Double-Check Completion feature tip
The rotating feature tips still told users to enable "Double-Check
Completion" in settings, but that toggle was removed in the new UI —
the Features section now offers Auto Compact, Feature Tips, Background
Edit, Checkpoints, Worktrees and Hooks. Following the tip sent users
searching the settings panel for something that isn't there.
Drop the tip. The remaining ten were checked against the current UI and
all still hold, including the "Settings → Features → Feature Tips" path.
* chore: remove dead CLI settings e2e page object and orphaned test
`page-objects/settings.ts` asserted the CLI settings Features tab shows
"Double-check completion" — the same removed setting behind the stale
feature tip. Nothing in the live tui-test suite (apps/cli/src/tests)
imported it; only chat.ts and auth.ts page objects are in use.
Its one importer, apps/vscode/tests/e2e/cli/interactive.test.ts, is a
leftover from the pre-2026-06-02 SDK migration squash: all three of its
imports resolve to files that don't exist, there's no tui-test config in
that tree, and no npm script runs it. It cannot execute.
* fix: respect user max output tokens in compaction summarizer requests
The compaction summarizer hardcoded max_tokens to 1024 and the VSCode host
never mirrored the user's Max Output Tokens onto providerConfig, so summary
requests were always capped at 1024 tokens. Reasoning models can spend that
entire budget thinking; the reasoning stream is discarded, so no summary
text arrives and compaction is skipped on every attempt.
- Mirror maxTokensPerTurn onto providerConfig.maxOutputTokens in the VSCode
session factory so consumers that build handlers straight from it (the
compaction summarizer) honor the user's setting, matching the CLI.
- Resolve the summarizer output budget from explicit config, then model
info, then knownModels, before the default; raise the default to 4096.
- Log a diagnostic warning (reasoning chars, incompleteReason, likely
cause) when the summarizer returns no summary text instead of silently
skipping.
* fix: clamp summarizer default output budget by model metadata instead of adopting it
Model maxTokens is reported capability, not a product default: without an
explicit configuration the summarizer now requests the 4096 default, lowered
by model metadata when the model reports less, never raised by it. Explicit
values still win as-is.
* feat(vscode): remove YOLO mode setting, migrate old users to auto-approve all
The SDK extension's YOLO toggle was cosmetic: nothing in the approval
path read it, so runs were silently governed by the per-action
auto-approval settings underneath (cline/cline#13114). Instead of
keeping a parallel override system, remove the setting entirely and
make the auto-approve menu the single source of truth:
- drop yoloModeToggled (and the equally dead autoApproveAllToggled)
from state keys, settings handlers, state posts, telemetry, the
remote-config yoloModeAllowed transform, and the settings protos
(field numbers reserved)
- remove the Yolo Mode toggle from Settings -> Features (the whole
Experimental section, it was the only entry) and the
"Auto-approve: YOLO" AutoApproveBar takeover
- add a v3 storage migration that folds a previously-enabled YOLO /
auto-approve-all toggle into autoApprovalSettings by enabling every
action, so previously-unattended setups keep running unattended;
the dead keys are cleared from the file store
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(vscode): keep dead yolo keys in place instead of clearing them
Current builds never read the removed keys (the state loader only visits
known keys), so deleting them buys nothing - and the file store is shared
with older builds that still know them, so clearing would flip YOLO off
for a user who downgrades. Same downgrade-safety rule as the v1 export.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(vscode): rename wasUnattended to shouldEnableAllActions in yolo migration
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(vscode): drop dead toggleActModeForYoloMode and stale yoloModeAllowed comment
The method was a legacy-controller carryover nothing called, and it set
the mode without rebuilding the session, which is wrong for the SDK
architecture. The comment cited yoloModeAllowed as a live remote-config
example; it no longer maps to anything.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(vscode): refresh checked-in proto descriptor_set.pb
The tracked descriptor set had not been regenerated since the repo
move and still advertised long-changed schemas (including the removed
yolo_mode_toggled fields) to gRPC reflection clients. Sync it with the
output of bun run protos.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: paste clipboard images into the composer as attachments (CLIENTS-78)
Pasting a screenshot into the composer did nothing: only drag-and-drop
and the paperclip file picker fed the attachment pipeline. Add an
onPaste handler on the composer textarea that extracts image files from
the clipboard, renames them to timestamped pasted-image-*.png files, and
routes them through the existing onAttachFiles flow. Text pastes are
untouched.
* desktop: only extract clipboard images in formats message serialization supports
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: context-aware welcome suggestions for non-code folders (CLIENTS-98)
* desktop: treat pending branch discovery as its own state for welcome cards
The welcome-card classifier read the "no-git" sentinel as a confirmed
non-repo, but page.tsx also used that value for the initial state and
while a workspace switch was awaiting branch discovery, so a git repo
could briefly show the plain-folder cards. Branch state is now null
while discovery is pending: the welcome screen shows no cards until the
folder is classified, and chat-mode cards (which never depend on git
state) still show immediately. Other branch consumers keep the string
contract via a "no-git" fallback.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: carry nullable branch state to all consumers
Propagate the pending-discovery null through ChatInputBar,
WorkspaceSelector, and the welcome workspace controls instead of
coercing to "no-git" at the page boundary, so only display leaves
fall back and the welcome classifier is the single consumer that
distinguishes pending from confirmed non-repo.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: never let 'Add project…' fail silently; add manual folder path entry (CLIENTS-73)
- sidecar picker tries zenity then kdialog on Linux and throws a descriptive
error when neither exists, instead of returning null (indistinguishable
from user cancel); picked paths are trimmed of trailing separators
- picker failures now surface as visible error messages in both workspace
selectors, with a manual path-entry fallback (typed absolute or ~ paths
in the search box offer an 'Open folder' action)
- failed workspace switches (invalid/nonexistent paths) show an inline
error instead of silently doing nothing
- validate_workspace_directory expands ~ and returns the resolved path
* desktop: keep workspace menu search/error state through catalog refreshes
The welcome-screen workspace picker reset its search text and error
message whenever onRefreshWorkspaces changed identity, which happens on
every session-history poll. Typing a path or reading an inline error
raced against the timer: the menu would silently wipe mid-interaction.
Hold the refresh callback in a ref so the reset only runs when the menu
actually opens.
* desktop: format welcome-workspace-controls test
* desktop: distinguish picker launch failures from user cancellation
A zenity/kdialog rejection with a non-ENOENT spawn error (EACCES, EMFILE,
ENOMEM) or a crash signal was classified as a user cancel, which skipped
the kdialog fallback and suppressed the inline error - recreating the
silent no-op this branch is meant to eliminate. Only a clean exit code 1
from a dialog that actually opened now counts as cancellation; broken
backends fall through to the next candidate and surface a descriptive
error otherwise. Picker logic moved to sidecar/workspace-picker.ts with
an injectable exec so the classification is unit-tested.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Classify picker launch failures separately from user cancellation
zenity/kdialog failures like EACCES, EMFILE, or ENOMEM were treated as
user cancellation, suppressing the kdialog fallback and the inline
manual-entry error. Only a clean exit code 1 now counts as a cancel;
any other failure falls through to the next backend or throws the
picker-unavailable error. Picker logic moved to sidecar/folder-picker.ts
with an injectable exec so the classification is unit tested.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Revert "Classify picker launch failures separately from user cancellation"
This reverts commit 24d27a004d.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): preserve queued prompts across user-initiated aborts
Pressing stop while prompts were queued silently destroyed them:
abort() called clearAborted(), which emptied the pending prompt queue
with no way to recover the typed input. The prompts vanished from the
UI, were never sent, and left no trace in session artifacts.
Aborting now only stops the in-flight turn. Queued prompts stay in the
queue and drain once the abort settles, matching the drain behavior
that already existed for self-aborted turns (loop detector / mistake
limit). The thrown-abort path (completeAbortedInteractiveTurn) now
schedules the same drain that runTurn schedules for turns resolving
with an aborted finish.
* fix(core): full-stop semantics and abort-window queue edits for surviving queues
Follow-up to the queued-prompt survival change: aborting a user turn keeps
the queue and auto-runs it, but two gaps remained.
1. No full stop: aborting a queue-initiated turn also kept draining, so
every Escape consumed one queued prompt and started a fresh provider
call - a session with queued messages could never be brought to rest.
Aborting a drained turn now discards the remaining queue: the first
Escape skips to your queued follow-ups, a second Escape stops the
queued work too.
2. Queue operations were still rejected while an abort settled: a prompt
typed right after Escape was silently dropped, and queued prompts were
briefly uneditable and undeletable even though they were about to
auto-run. enqueue/update/delete now work during the abort window;
scheduleDrain/drain still wait for the abort to settle.
* test(core): cover abort + host restart + seeded recovery durability
Adds an e2e regression guard for the reported "cancel a turn, lose the
conversation" failure: a cancelled turn, a daemon restart, a
client-side recovery seeded from disk, and a second restart before that
replacement ever runs a turn. Reverting the eager seeded-history
persistence makes the final read come back empty.
Materializing a seeded session at start also left its history row with
no prompt and no title, since there is no first prompt to derive one
from. Seed the title from the inherited transcript using the same
inference listSessionHistory hydration applies, so forks and recoveries
stay identifiable in unhydrated surfaces too.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): retitle seeded sessions from their first user prompt
Eagerly-materialized seeded sessions kept the interim transcript-
inferred title forever, a behavior change from pre-eager persistence
where a fork's history row was titled by the first post-fork prompt.
The interim title now only covers the window where no turn has run
(previously those rows were simply absent), and the first user prompt
after the seed backfills the row's prompt and retitles it — unless the
user renamed the session in the meantime, in which case only the prompt
column is backfilled. The resident manifest and session metadata are
updated in step so the end-of-turn usage-metadata merge cannot clobber
the title back through a stale in-memory fallback.
The e2e mock's updateSession now mirrors the real persistence-service
contract (row + manifest file), and the durability e2e covers both the
retitle and the rename guard; removing the retitle call fails the
'now add tests' assertion.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(core): collapse seeded-session titling to the old mechanism
The interim transcript-derived title, retitle flags, rename comparison,
and resident-manifest syncing existed only to title forks that never
run a turn - a new nicety, not parity. Dropping it collapses the whole
design back to what rows did before eager persistence: the persistence
service derives the title from the prompt when a row gains one, so the
host only needs to backfill the promptless row with the first user
prompt via updateSession. Renames win automatically because the service
preserves an existing title when no explicit title is passed.
Net production change vs main is a single 20-line backfill block in
executeTurn. The e2e mock's updateSession now models the service's
title semantics (explicit title wins, existing title preserved,
untitled rows derive from prompt), and the durability e2e asserts the
raw row stays untitled until first prompt while history hydration
infers a display title from the transcript.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Pressing stop while prompts were queued silently destroyed them:
abort() called clearAborted(), which emptied the pending prompt queue
with no way to recover the typed input. The prompts vanished from the
UI, were never sent, and left no trace in session artifacts.
Aborting now only stops the in-flight turn. Queued prompts stay in the
queue and drain once the abort settles, matching the drain behavior
that already existed for self-aborted turns (loop detector / mistake
limit). The thrown-abort path (completeAbortedInteractiveTurn) now
schedules the same drain that runTurn schedules for turns resolving
with an aborted finish.
* fix(core): keep a hung MCP server from taking down session creation
A stdio MCP server that never finishes initializing used to hold its
connect open for the full DEFAULT_MCP_CONNECT_TIMEOUT_MS (doubled across
the newline/framed attempts). MCP tool discovery runs on the
session.create critical path, so that wait blew past the 30s hub command
timeout and the CLI tore the whole interactive session down instead of
just skipping the bad server.
- Bound MCP tool loading during session build with a startup budget that
is safely under the hub command timeout. Servers that connect in time
contribute their tools; slower/hung servers are skipped for the session
(their error still surfaces via the MCP manager) instead of failing
session creation. Budget is overridable via CLINE_MCP_STARTUP_BUDGET_MS
for tests.
- Add StdioMcpClient.close() (and optional McpServerClient.close) that
marks the client disposed so an in-flight connect() aborts its retry
loop instead of respawning the framed fallback.
- Dispose the manager by closing clients up front, outside the per-server
operation locks, so a server hung in initialize can no longer stall
teardown for the full connect budget.
Adds regression tests covering both the non-blocking build and prompt
disposal while a client is hung in connect().
* refactor(core): simplify hung-MCP-server fix to a startup budget
Replace the bespoke per-server race/tracking in loadConfiguredMcpTools
with a small withStartupBudget() wrapper around the existing
Promise.allSettled: a server that exceeds the budget becomes a normal
rejection that the existing loop already logs and skips. The connect
budget, MCP settings display (initialize timeout 30s), and the rest of
the loader are left untouched.
The client close()/manager.dispose() cleanup is kept minimal: it is what
lets teardown abort a still-in-flight connect instead of blocking on the
per-server lock (and clears the pending request timer).
* fix(mcp): cap the default initialize budget at 3s to protect session creation
Supersedes the startup-budget approach on this branch with the simple
constant fix.
MCP initialize runs on the session.create critical path, which the hub
caps at 30s, and connect() can spend the budget twice (newline then
Content-Length framing). The 30s default from #13067 meant a server that
never initializes held session.create for up to 60s, so the hub RPC
timed out and the CLI tore the whole session down and exited.
Return to the pre-#13067 shape with a bigger probe: 3s instead of 1.5s.
That still covers the ~2s starters the old probe killed (#13035) and
keeps the worst case at ~6s per server, far under the hub deadline.
Genuinely slow starters (JVM-based servers like Oracle SQLcl) now need
an explicit timeout in cline_mcp_settings.json, which continues to
override the default in either direction.
Tests: update the slow-start regression tests to the new policy (2s
connects by default, 4s connects with a configured timeout), refresh the
displayed initialize-timeout assertions, and add an invariant test that
keeps the doubled default well under HUB_DEFAULT_COMMAND_TIMEOUT_MS so
the budget cannot silently creep past the session deadline again.
* fix(desktop): stop opening a session from replacing the remembered model
The composer's ModelSelector mirrored every provider/model prop change
into the remembered last selection (localStorage), which seeds new
sessions via getInitialChatConfig(). Opening an existing session drives
those props to that session's config, so merely viewing an old session
silently replaced the user's explicitly picked default model.
The remembered selection is now written only from the explicit picker
handlers (provider select and model select). Passive prop changes, such
as opening a session, no longer touch it.
* fix(desktop): re-seed remembered provider/model on chat reset
reset() kept the previous config's provider/model and only cleared the
session ID, so a chat pane that had hydrated a historical session could
carry that session's model into the next chat. Re-seed provider/model
(and apiKey when the provider changes) from the remembered defaults --
the same source a freshly mounted thread uses -- so reset and remount
behave identically.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): stop treating leftover plugin install dirs as installed
isOfficialPluginInstalled() only checked that the marketplace install
directory existed. A failed or interrupted install can leave that
directory behind with no plugin inside, and the next install attempt
then short-circuited with a fake 'already installed' success: the
marketplace button flipped to Uninstall with no error while nothing
actually worked, and the installed-entries listing kept reporting the
broken entry as installed.
The check now requires a loadable plugin module inside the directory
(via discoverPluginModulePaths) before reporting the entry as
installed, so partial directories fall through to a real install
attempt whose outcome is surfaced to the UI.
* fix(desktop): reclaim leftover partial plugin install dirs with --force
* fix(desktop): canonicalize diff panel paths against the session cwd
Tool calls address the same file inconsistently across a session: one
edit uses a workspace-relative path (journal.txt), a later one the
absolute path (/tmp/ws/journal.txt). mergeToolDiffs keyed entries by the
raw string, so the same file was listed twice in the diff panel with
split +/- counts and inconsistent naming, most visibly after git was
initialized mid-session and the model switched to absolute paths.
Diff paths are now canonicalized against the session cwd before
merging: entries for the same file collapse into one, files inside the
cwd display as workspace-relative paths, and files outside it display
their resolved path. Without a cwd the previous raw-key behavior is
kept.
* style: collapse editorReplaceEvent signature per biome format
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): collapse dot segments and keep root cwd in diff path keys
* fix(desktop): compare Windows diff path keys case-insensitively
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): hide View Changes on completion rows until there are changes to show
The button previously always rendered on the latest completion row, faded
and disabled when the count check came back 0 - which covers both 'nothing
changed since your last message' and 'no checkpoint to compare against'
(non-git workspace, repo with no commits, comparison failure). A dead
button with a misleading tooltip in the non-git case is worse than no
button: now the row renders nothing until the host confirms there are
actual changes, and the button is always enabled when shown.
* fix(vscode): reset View Changes state when showViewChanges toggles
Greptile review: a stale positive hasChanges from a previous evaluation
could flash the button before the host confirms the new comparison when
showViewChanges flips false and back true on the same row. Reset to
'still checking' whenever the effect re-runs.
* fix(core): never run a foreign compiled plugin-sandbox bootstrap for a source host
When @cline/core runs from source (e.g. the desktop hub daemon in dev)
with CLINE_WRAPPER_PATH set, resolveBootstrap() picked the compiled
plugin-sandbox-bootstrap.js from a separately installed CLI platform
package (such as a published version sitting in the package-manager
cache) before falling back to the source bootstrap. That bootstrap
resolves modules against the other installation's layout, so every
plugin failed to load with "Cannot find module '@cline/core'" - and
the settings pipeline swallowed the failure, leaving Settings > Tools
showing "No plugin tools found" and plugins showing no contributions
even though the same plugins loaded fine in chat sessions.
Bootstrap selection now prefers, in order: a compiled bootstrap next to
this module (always matches the host build), the source bootstrap when
the host runs from source, and only then wrapper/executable-derived
bootstraps - which remain the path for compiled binaries where
import.meta points inside the bunfs bundle.
* chore(core): restore untouched settings-service formatting
* fix(core): keep session context durable across aborts and hub restarts
Users on slow self-hosted endpoints reported sessions losing their entire
conversation after cancelling a long-running request: the TUI still showed
the transcript, but the next turn greeted them like a brand-new session.
Root cause is a stack of two failures:
1. The hub daemon exits on any unhandled rejection that is not an
AgentRuntimeAbortError, so a floating abort-family rejection from a
cancelled provider stream kills every resident session.
2. When the CLI recovers the missing session it rebuilds from the persisted
messages file - but aborting a turn never flushed the transcript, and
lazy session persistence (SDK 0.0.70) kept seeded history (mode-switch
restarts, forks, previous recoveries) memory-only until the first
completed turn. Recovery then seeds an empty session: silent context wipe.
Fixes:
- completeAbortedInteractiveTurn now flushes the transcript to disk, so an
aborted exchange survives a hub restart.
- Sessions started with initialMessages persist them (and any compaction
sidecar) immediately; brand-new empty sessions stay lazy, so closing an
unused runtime still leaves no empty history entry.
- The hub daemon ignores abort-family unhandled rejections (DOMException
AbortError, Node ABORT_ERR) the same way it already ignores
AgentRuntimeAbortError, instead of exiting with every session resident.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): write seeded history atomically with session materialization
Greptile review flagged a residual crash window in the seeded-session
persistence: ensureSessionPersisted created the session row (with an empty
messages file) and only then called persistSessionMessages, so a crash
between the two left a discoverable session whose seeded history was gone.
Close the window by threading initialMessages/systemPrompt through
createRootSessionWithArtifacts: the messages artifact is now written with
the seeded transcript before the session row is committed, so every crash
point leaves either nothing discoverable or complete data. The follow-up
persistSessionMessages call at session start is gone; the seed travels
inside session materialization.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* Revert "fix(core): write seeded history atomically with session materialization"
This reverts commit 5a7e0b37f1.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
Turns drained from the pending-prompt queue resolve their errored
AgentResult inside PendingPromptsController.drain(), which discards it,
and the legacy 'error' agent event had no projection in the hub's
session-event projector — so a failed queued turn never produced any
terminal hub event. Interactive clients (e.g. the desktop app) hung on
'Thinking...' with no error shown.
The projector now publishes run.failed (with the error text and a core
session snapshot) for non-recoverable lead-agent error events, but only
when no RPC-driven turn is awaiting sessionHost.runTurn for that
session — the awaiting run.start handler already publishes the
authoritative terminal event, so this avoids double-reporting a turn
that resolves through both paths.
* fix(core/cli): drain queued prompts after self-aborted turns and surface the stop
When a run ends with finishReason "aborted" without a user abort request
(loop detector hard escalation or the consecutive-mistake safety stop),
runTurn skipped the pending-prompt drain, stranding user-queued messages
forever, and the CLI rendered nothing - the task appeared to silently
stop with queued messages never consumed (#13030).
- core: schedule the drain after every completed turn, including
aborted/error finishes. User-initiated aborts are unaffected because
abortSession() already clears the queue, and drain() stops after one
failed send so an erroring provider cannot spin the queue.
- cli: when a turn comes back aborted without the user having requested
an abort, append a "Task stopped before completion." status entry
instead of ending the turn silently.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): hold queued prompts on error finishes instead of consuming them
Addresses the Greptile P1 review on #13061: a drained prompt whose turn
resolved with finishReason "error" returned normally, so the
exception-only requeue path treated the send as successful - the failed
prompt was consumed and draining continued firing the remaining queue
into a failing provider.
- drain() now stops the chain when a drained send resolves with an
error finish. The errored entry itself is not requeued (its turn ran:
the prompt is in the conversation and the error is surfaced), but the
rest of the queue is held.
- runTurn() no longer schedules a drain after "error" finishes (the
skip is removed only for "aborted", which is the #13030 fix).
Held prompts still drain via the existing enqueue/update/delete
triggers or the next successful turn.
- Two new unit tests cover both layers.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* revert(cli): drop the 'Task stopped before completion' status line
Keep the change scoped to the queue-drain fix in @cline/core. The CLI
no longer prints a notice for non-user-initiated aborted finishes;
apps/cli is back to parity with main. When messages are queued, the
drain itself makes the stop visible (the queued message runs); richer
stop-reason surfacing can be a follow-up.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The litellm builtin spec pinned protocol: "openai-responses", so every
request went to POST {baseUrl}/responses. Self-hosted LiteLLM proxies
commonly implement only /chat/completions, so all prompts failed with
404 Not Found on the SDK path (CLI, and now the Next extension bundle).
Drop the override so litellm inherits the openai-compatible family
default (openai-chat -> /chat/completions), matching every sibling
openai-compatible builtin and the Legacy extension behavior.
Fixes#13003, fixes#10781
* fix(cli): render MCP tool result text instead of escaped JSON in TUI
MCP tools return {content: [{type: "text", text}]} which
extractFullOutputText JSON-stringified, escaping newlines into one giant
line that word-wrapped across the whole terminal and never triggered the
line-based collapse. Extract the text parts with real newlines so the
existing collapse works.
Fixes#13038
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(cli): keep placeholders for non-text blocks in mixed MCP results
Addresses Greptile review on #13066: text-only filtering silently
dropped image/resource/audio blocks from mixed MCP content. Render them
as [type] placeholders instead.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(cli): surface non-text MCP block metadata in TUI output
Extract embedded resource text, and include resource/resource_link URIs
and image/audio mime types in placeholders so expanded mixed MCP
results keep identifying metadata.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
The stdio MCP client gave servers without a configured `timeout` only
1.5 seconds to answer initialize before killing the process, so
slow-starting servers (e.g. Oracle SQLcl's JVM-based `sql -mcp`) could
never load and were silently skipped at session start.
Raise the default connect budget to 30s, in line with the startup
budget other MCP clients allow. A configured `timeout` still overrides
it in either direction, dead commands still fail fast through the spawn
error/exit path, and the newline -> Content-Length framing fallback is
unchanged.
Fixes#13035
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* feat(desktop): route /team prompts through core runtime
Rewrite desktop `/team` commands as structured user command blocks before sending them to the core runtime. Validate task input and respect the globally disabled Teams tool setting.
Remove legacy agent spawn and team enablement flags from session configuration, and add coverage for prompt rewriting and disabled-tool behavior.
* fix(desktop): preserve team tool defaults
* fix(desktop): display queued /team prompts as their slash form
Queued prompts are stored in their runtime form, so a queued /team
command showed its raw <user_command> envelope in the prompt queue chip
and edit textarea. Fold queue items through formatDisplayUserInput for
display; saving an edit re-resolves the slash form through the sidecar,
so the round trip is lossless.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(hub): align builtin tool catalog flags with the desktop sidecar
The desktop sidecar pins enableSpawnAgent/enableAgentTeams when listing
the builtin tool catalog; the hub's parallel listing did not, so the two
would drift if the preset defaults ever change. Pin the same flags in
the hub and cross-reference the two call sites.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(desktop): drop inert enableSpawn/enableTeams config leftovers
buildCoreSessionConfig no longer reads these keys, so remove the dead
schema fields, default-config initializers, and chat-test payload
entries. The chat-session regression test still sends them on purpose
to prove legacy flags cannot override the runtime's tool presets.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(desktop): reject /team when the mode's tool preset disables teams
The /team guard only checked the global disabled-tools setting, but the
runtime resolves tool availability from the mode's preset, so a preset
without team tools (yolo) would still send the model a spawn-a-team
instruction it cannot act on. Resolve the teams catalog entry for the
session's mode and reject /team when it is unavailable, mirroring the
runtime's own availability logic.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(core): surface OAuth authorization for SSE MCP servers on 401
A 401 from an SSE MCP server never persisted authorizationRequired: the
fetch-boundary UnauthorizedError was consumed by EventSource and re-thrown
as a status-less SseError, so the instanceof check routed it to
markConnectionError and hosts never offered the OAuth connect action.
Give the SSE stream request a raw fetch so a 401 fails the connection with
the SDK's typed SseError(401), and recognize 401s across transports with a
single isMcpUnauthorizedError predicate at every detection site.
* style(core): apply biome formatting to MCP oauth changes
Toggling Plan/Act while a turn was streaming or waiting on a tool approval
aborted the turn but left the TurnStateTracker on its last live phase: the
aborted session's done event is fenced off as stale once the rebuild
unsubscribes it, so nothing ever settled the phase. The webview then kept
rendering that phase forever - an eternal Thinking spinner with the input
disabled (aborted while streaming), or dead Approve/Run Command buttons wired
to an approval that clearPending had already denied (aborted while awaiting
approval). Users experienced this as 'switched to act mode and nothing
happened / it never wrote the files'.
Mirror cancelTask: after aborting the turn for the mode change, append a
resume_task ask row and set the phase to resumable, so the footer offers
Resume Task with the input enabled in the new mode.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(llms): retry mid-stream network interruptions before any model output
* fix(llms): scale network retry backoff by network retry count, not shared attempt number
* desktop: native-feel polish and render-path performance fixes
- Suppress the WebView browser context menu on app chrome (keep it for
editable fields and active text selections)
- Make UI chrome unselectable app-wide; opt chat messages, markdown,
code, diffs, and error banners back into text selection
- Contain overscroll so inner scrollers don't rubber-band the window
- Lazy-load Settings/Sessions/Onboarding/Diff views out of the entry chunk
- Memoize ChatInputBar and AgentHeader; stabilize their props in the chat
pane so stream flushes only re-render the affected message bubble
- Stop refocusing the composer textarea on every keystroke (caret flicker)
- Cache slash commands across menu opens (stale-while-revalidate)
- Avoid rebuilding reversed message arrays and ask-question JSX per render
- Drop core info/debug console logging on the streaming hot path behind a
cline:debug-logs opt-in; remove leftover [webview:delete] debug logs
- SearchCombobox (provider/model picker): Escape closes and restores focus
- Remove unused @vercel/analytics, recharts, embla-carousel deps and the
unused chart/carousel UI components
* desktop: surface failed-turn errors instead of leaving the chat blank
On a failed run the runtime reports its error string in result.text.
The webview rendered that as an assistant bubble, which the canonical
history rehydration then wiped (the failed turn is never persisted),
so provider errors like a retired model id left the user staring at a
silently empty chat. Route failed-turn text to a persistent error-role
message added after rehydration instead.
* desktop: fade the welcome/conversation swap instead of hard-cutting
Sending the first message replaced the hero layout with the message
grid in a single commit, which read as a white flash. A 180ms enter
animation now plays when either side becomes visible; disabled under
prefers-reduced-motion.
* desktop: render new-chat panes instantly from the last catalog load
Clicking + remounts ChatThreadPane, which refused to render until the
provider catalog (a large fetch) and workspace list resolved again —
about a second of blank pane plus boot spinner on every new chat.
Seed remounts from a module-level snapshot of the last successful
load; the mount effect still refreshes both in the background.
* desktop: invalidate the provider-catalog snapshot with the cache
Seeding remounted chat panes from the last catalog load left a window
where a pane created right after a credential change could act on the
old keys. The snapshot now lives in the catalog module and is dropped
by invalidateProviderCatalogCache(), so credential edits force the
next remount to wait for fresh data.
* fix(cli): harden tool input/output formatters against malformed payloads
Tool inputs cross the model/tool boundary and may not match their
TypeScript annotations (e.g. run_commands with { command: null }).
truncate() called str.replace() on such values, crashing the TUI with
'.replace is not a function' and making persisted sessions containing
the payload non-resumable, since hydration replays the same input
through formatToolInput().
Normalize untrusted values at the formatting boundary: truncate() now
accepts unknown and safely stringifies null/undefined/objects (including
circular structures and throwing toJSON), formatStructuredCommand no
longer returns non-string commands verbatim, and fetch_web_content
request summaries tolerate malformed entries.
Fixes#13036
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(cli): keep valid empty-string args in structured command summaries
Greptile review: filtering normalized args by truthiness also dropped
genuine empty-string argv entries, so summaries could show a different
argument list than the one executed. Filter only nullish entries before
normalization instead.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* fix(vscode): fall back to session cwd/Desktop for @-mention search in empty windows
* fix(vscode): use the shared chat workspace as the no-folder fallback root
ensureGitRepository cached a negative probe for the lifetime of the hook
instance, so a session started in a non-git folder never got checkpoints
even after the user ran git init. Cache only the positive answer and
re-probe otherwise; the probe runs at most once per user turn.
* fix(desktop): treat signed-out state as a typed result instead of a command error
* fix(desktop): sign out when the organization balance fetch reports the typed signed-out result
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore: retrigger checks after runner outage
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* refactor(ui): introduce Cline-owned semantic color system
* refactor(desktop): adopt shared semantic theme roles
* refactor(ui): set 15px root and recalibrate xs/sm type scale
Scale rem steps so xs/sm stay 12/13px visually, and slightly lift dark-mode neutral-4.
* refactor(ui): align SearchCombobox with package type and hover tokens
Use host-safe cline-ui utilities and keep option font inheritance from CSS.
* fix(ui): use standard stroke-2 utility on approval spinner
* refactor(desktop): modernize shared UI primitives for Tailwind v4
Replace legacy arbitrary/has selectors with current utility syntax.
* refactor(desktop): bump chat chrome typography to text-sm
Keep composer controls and pickers on the shared sm type step.
* refactor(desktop): use max-w-344 for page frame content width
* chore(desktop): disable Next.js dev indicators
* chore: ignore desktop-app Cursor settings
* docs(pr): add before/after screenshots for #12941
* chore: retrigger checks
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* desktop: fix silent turn failures, message duplication, and stuck composer; add first-run setup guidance
Findings from two full computer-use UX audits of the desktop app:
- Surface failed turns in the transcript: queued turns (incl. the first
prompt of a fresh session) only signal errors via chat_done, which the
UI previously ignored - sending a message with no credentials failed
in complete silence. Failed turns now show an error message enriched
with the latest core error log and a pointer to Settings -> Models.
- Fix duplicated user messages: a live send's optimistic user message
was materialized a second time by the runtime's queued-prompt-start
event.
- Fix composer stuck on 'Agent is working...': drop prompts from the
local queue snapshot when they start, emit a fresh queue snapshot from
the sidecar on pending_prompt_submitted, and double-check the server
queue on turn completion.
- Add a 'Connect a model' notice on the welcome screen when no provider
has credentials, with actions to reopen onboarding at the connect step
or jump to model settings; it reacts live to credential changes.
- Add 'Get an API key' links for popular providers in onboarding and
Settings -> Models (the catalog docUrl is never populated), and link
the Cline dashboard from the Cline API key form.
- Explain what Cline is on the onboarding welcome step.
- Make the stop button visible (was 8px with no padding) and support
Esc to stop; add Cmd/Ctrl+N (new session) and Cmd/Ctrl+, (settings).
- Remove leftover [webview:delete] console.error debug logging that
surfaced an error badge after deleting a session.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: remove remaining delete debug logging in session history hook
The sidebar right-click delete path had the same leftover [webview:delete]
console.error instrumentation, which made the Next dev-mode issues badge
appear after every deletion.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: fix Biome a11y error in WelcomeSetupNotice
biome's lint/a11y/useSemanticElements errors on role="status" divs;
use the semantic <output> element (implicit status role) instead. This
was failing the repo's 'bun run lint'.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: count structured-config and keyless providers as connected
The welcome setup notice previously only recognized apiKey/OAuth
credentials, so users running Bedrock/Vertex (structured configValues)
or a deliberately enabled keyless local endpoint (e.g. Ollama) were
nagged to connect a model they already use. isProviderConnected now
also counts an enabled provider whose required config fields are all
filled, or an enabled provider that has no API-key field at all.
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* desktop: keep re-key eligible when chat_done lands in the same batch as its prompt start
When a turn fails fast, chat_queued_prompt_start and chat_done can be
dispatched in one React batch. Clearing the outstanding-optimistic-
bubble registry synchronously in the chat_done handler ran before the
re-key updater enqueued by the prompt-start event, so the optimistic
bubble was appended a second time instead of re-keyed. Clear the
registry inside a state updater so it executes in event order after
the re-key. Caught by the queued-turn-failure regression test.
* desktop: make the queued-prompt re-key updater idempotent under StrictMode
React StrictMode double-invokes state updaters in dev. The
chat_queued_prompt_start re-key updater consumed the optimistic
bubble's id from outstandingOptimisticUserIdsRef on its first run, so
the second run against the same prev found no eligible candidate and
appended the same user message a second time (and, without a promptId,
makeId() minted a different id per invocation). Hoist the message id
out of the updater and remember which optimistic bubble each queued
message id re-keyed so a re-run reaches the identical result. The memo
resets alongside the outstanding set (error state, reset, hydration).
Root-caused with runtime instrumentation: the duplicate only appeared
on turns that exercised the queue-drain re-key path, and hydration
later collapsed it to one message because the duplicate never existed
in persisted state.
* desktop: preserve failure messages across post-send canonical hydration
Persisted history never contains UI-only error bubbles, so the two
post-send read_session_messages replacements in sendPrompt wiped the
failure explanation appended from chat_done ~40ms after it rendered
(confirmed with runtime instrumentation). Re-append the active
session's error messages after the canonical history. Includes a
regression test reproducing the chat_done-error-then-RPC-resolution
race.
* desktop: don't let an optional API-key field veto a connected provider
Greptile P1 follow-up: Bedrock's catalog entry carries an optional
apiKey field ('Optional Bedrock bearer token') alongside IAM/profile
authentication, and keyless local endpoints can also surface one — so
treating the mere presence of an apiKey field as proof of disconnection
kept nagging configured users. An enabled provider (the user
deliberately persisted settings for it) now counts as connected unless
a required config field is unmet; auth may legitimately live outside
the catalog (IAM, env vars, local endpoints). Brand-new users have no
enabled providers, so the first-run notice still shows for them.
* desktop: tighten credential-error guidance and stop re-pinning stale failure bubbles
* desktop: invalidate the shared provider catalog after settings OAuth login
Greptile P1 follow-up: runOAuthProviderLogin only updated the settings
view's local provider state, so the shared catalog cache and its
invalidation subscribers (the composer selector and the welcome
screen's 'Connect a model' notice) kept reporting the provider as
disconnected until an unrelated invalidation or a pane remount. Notify
the shared cache on successful OAuth login, like the account view and
the API-key save path already do.
* desktop: clear the remembered core error on turn end, reset, and hydration
Greptile flagged that turn-start events are the only thing clearing
lastCoreErrorBySessionRef, and websocket events are not replayed: a
transport interruption that drops a turn's start event lets a later
detail-less failure resurrect an earlier turn's error. The remembered
error belongs to exactly one turn, so clear it whenever a turn ends
(chat_done, any reason) as well as on reset() and history hydration.
Regression test covers the dropped-start-event sequence.
---------
Co-authored-by: Saoud Rizwan <saoudrizwan@users.noreply.github.com>
* chore(llms): regenerate model catalog from models.dev
* feat(llms): surface meta/muse-spark-1.2-contributor for the Cline provider
* test(llms): guard Vercel-only Cline model allowlist
* feat(vscode): explain when a free model promotion ends
Once a free promotion ends, the cline-free/ model is removed from the
catalog and the backend answers 'model not found' to requests against it.
The CLI has shown a dedicated 'Free model promotion ended' banner for this
since #12593; the extension instead rewrote the answer into generic
model-not-found guidance with no model-picker offramp.
Detect the case in the host where the active model id is known
(reshapeErrorForWebview, fed by a new MessageTranslatorState model-id
source), stamp the payload with a cline_free_promotion_ended code, and
render a dedicated card in the webview with a button into the model
picker. Classification is gated on the cline-free/ prefix so ordinary
model-not-found errors keep their generic path, and it runs before the
auth branch since the 404 status falls inside the generic auth range.
* fix(vscode): prefer the live task model over session-start metadata
A mid-task model-only switch updates the running session's model in place
(updateActiveSessionModel) and refreshes the task API shim, but never
touches the session's startConfig/manifest. Preferring the session-start
snapshot could therefore misclassify after such a switch: a genuine
retired-model 404 would miss the promotion-ended card, and the reverse
switch could show it for the wrong model. Provider switches restart the
session, so both sources agree there; the shim starts as "unknown"
(filtered out), so fresh sessions still resolve through start metadata.
* fix(desktop): dedupe chat_queued_prompt_start emitted for the same prompt
PendingPromptService.drain() emits a pending_prompts snapshot (head
removed) and a pending_prompt_submitted event back-to-back for the same
prompt. The sidecar translated both into chat_queued_prompt_start, so
the webview rendered the user's message twice until the chat was
re-hydrated from history. Track the last announced prompt id per live
session and emit the start chunk once.
* fix(desktop): re-key optimistic user bubble when the runtime queues the prompt
The send path renders an optimistic user bubble for prompts dispatched
while the session is idle, keyed by a random id. When the runtime
routes that prompt through its pending queue (e.g. during session
startup), the queued-prompt-start event appended a second bubble under
queued_user_<promptId> — the same message rendered twice until the
chat was re-hydrated from history. Re-key the trailing optimistic
bubble to the event's id instead of appending.
* fix(desktop): re-key only outstanding optimistic bubbles on queued prompt start
Review follow-up: matching by content alone could swallow a new queued
prompt that repeats the text of a message left at the transcript tail
by an earlier cancelled/failed turn. Track in-flight optimistic bubble
ids explicitly (registered on optimistic append; cleared on re-key,
turn end, error, and history hydration) and only re-key those.
Fix auto-approve checkboxes freezing after "New Task": clear the task-scoped settings overlay when the task view is cleared or switched, so stale task settings no longer shadow global settings
Hide the "View Changes" button on completion rows until there are actually changes to show, instead of rendering it faded and disabled. Turns that changed nothing, non-git workspaces, and repos without commits no longer show a dead button with a misleading tooltip.
@@ -7,7 +7,7 @@ description: Use when preparing, tagging, and publishing an apps/cli npm release
Use this skill when the user asks to release the CLI, publish `cline`, bump the CLI version, draft release notes, create a `cli-vX.Y.Z` tag, or trigger the CLI publish workflow.
The CLI is npm-only. Do not add alternate distribution or signing steps.
The CLI is npm-only. Do not add alternate distribution channels. Windows binaries are Authenticode-signed automatically by the publish workflow via Azure Trusted Signing (see the `.github/actions/sign-windows-cli` composite action and "Windows code signing" in `apps/cli/DISTRIBUTION.md`); if the signing secrets are not configured the workflow warns and publishes unsigned binaries. Local publishes (`bun release cli`) do not sign — prefer the GitHub Actions publish path for releases users run on Windows.
> Working directory: run every command below from the repository root. Paths and scripts (e.g. `apps/cli/package.json`, `sdk/packages/`, `bun release cli`, `bun run version`) are written relative to the repo root.
description: Use when preparing, tagging, and publishing a Cline Code desktop app (apps/examples/desktop-app) release. Guides changelog drafting, version bumps in package.json + tauri.conf.json, desktop-vX.Y.Z tags, and the desktop-publish GitHub workflow that builds, signs, notarizes, and updates the auto-update feed.
description: Use when preparing, tagging, and publishing a Cline desktop app (apps/examples/desktop-app) release — stable (desktop-vX.Y.Z from main) or beta (desktop-vX.Y.Z-beta.N from desktop-experimental, shipped as the side-by-side "Cline Beta" app). Guides changelog drafting, version bumps in package.json + tauri.conf.json, tagging, and the desktop-publish GitHub workflow that builds, signs, notarizes, and updates the per-channel auto-update feed.
---
# Desktop App Release
Use this skill when the user asks to release the desktop app, publish Cline Code, bump the desktop version, create a `desktop-vX.Y.Z` tag, or trigger the desktop publish workflow.
Use this skill when the user asks to release the desktop app, publish the Cline desktop app, cut a desktop beta, bump the desktop version, create a `desktop-vX.Y.Z` (or `desktop-vX.Y.Z-beta.N`) tag, or trigger the desktop publish workflow.
> Working directory: run every command below from the repository root.
Desktop releases are macOS-only today (a single signed + notarized universal DMG that runs natively on both Apple Silicon and Intel) and are built entirely in GitHub Actions — there is no local publish path. Installed apps discover new releases automatically through the Tauri updater, so publishing a release is what ships the update to every existing user.
Desktop releases ship two platforms, built entirely in GitHub Actions — there is no local publish path. macOS: a single signed + notarized universal DMG that runs natively on both Apple Silicon and Intel. Windows: an Authenticode-signed NSIS installer (`<Product>_<version>_x64-setup.exe`), signed via Azure Trusted Signing in the `build-windows` job (jsign through Tauri's `signCommand`, see `apps/examples/desktop-app/scripts/tauri-sign-windows.ps1`; requires the repo-level `AZURE_*` secrets including `AZURE_TRUSTED_SIGNING_CERTIFICATE_PROFILE_DESKTOP`, plus a `PublishDesktop`-environment federated credential on the `cline-cli-signing` Entra app). Installed apps discover new releases automatically through the Tauri updater, so publishing a release is what ships the update to every existing user**on that channel**.
## Release contract
- Two channels, one workflow (`channel` input on `desktop-publish.yml`):
- **stable** — tag `desktop-vX.Y.Z` (no suffix; the workflow rejects prerelease suffixes on this channel), cut from `main`, feeds the rolling `desktop-latest` release, ships as "Cline".
- **beta** — tag `desktop-vX.Y.Z-beta.N`, cut from `desktop-experimental`, feeds the rolling `desktop-beta` release, ships as "Cline Beta" (separate bundle identifier `bot.cline.app.beta`; installs side by side with stable). Built with the extra `src-tauri/tauri.beta.conf.json` overlay. Process background: `apps/examples/desktop-app/EXPERIMENTAL.md`.
- Version sources (must match each other and the tag): `apps/examples/desktop-app/package.json` and `apps/examples/desktop-app/src-tauri/tauri.conf.json`. (`src-tauri/Cargo.toml` has its own version but `tauri.conf.json` overrides it; no need to touch it.)
-Release tag: `desktop-vX.Y.Z`, where `X.Y.Z` matches both version files.
- Release prep includes approved release notes, the version bumps, and an `apps/examples/desktop-app/CHANGELOG.md` update.
- Publish path: `.github/workflows/desktop-publish.yml` (workflow_dispatch, requires the tag to exist, point at the checked-out commit, and be reachable from `origin/main`).
-The workflow creates the `desktop-vX.Y.Z` GitHub release (universal DMG + updater artifact + `latest.json`) and refreshes the rolling `desktop-latest` release, which is the static auto-update feed every installed app polls. Never delete the `desktop-latest` release or tag.
- The changelog's top `## X.Y.Z` section is extracted verbatim into the GitHub release body, the Slack announcement, and the updater manifest notes.
-Beta versions are prereleases of the **next** stable: stable `0.0.13` → betas `0.0.14-beta.1`, `-beta.2`, … Once a stable ≥ the beta base ships, the next beta bumps its base (`0.0.15-beta.1`).
- Release prep includes approved release notes, the version bumps, and an `apps/examples/desktop-app/CHANGELOG.md` update — committed on `main` for stable, on `desktop-experimental` for beta.
- Publish path: `.github/workflows/desktop-publish.yml` (workflow_dispatch, requires the tag to exist, point at the checked-out commit, and be reachable from the channel's branch — `origin/main` for stable, `origin/desktop-experimental` for beta).
-**Both channels dispatch from `main`.** This is a security invariant, not a convenience: the run executes `main`'s workflow copy and only the checkout points at the tag, so the signing-secret gates (the `github.ref == main` check and the PublishDesktop environment's main-only deployment-branch policy) hold for beta too. Never add `desktop-experimental` to the PublishDesktop deployment-branch policy.
- The workflow creates the tag's GitHub release (universal DMG + macOS updater artifact + Windows NSIS installer with its updater signature + `latest.json`; marked prerelease for beta) and refreshes the channel's rolling feed release, which is the static auto-update feed every installed app on that channel polls. Never delete the `desktop-latest` or `desktop-beta` release or tag.
- The changelog's `## <version>` section (exact-match, not "topmost") is extracted verbatim into the GitHub release body, the Slack announcement, and the updater manifest notes.
- Always ask before pushing commits or tags.
## Workflow
0. Ask which channel this release is for — **stable or beta** — if the user has not said. Everything below branches on it; never guess.
If there is no `desktop-v*` tag yet, this is the first release; use the desktop app's first commit as the baseline and say the baseline is inferred.
For a **beta** release, work on `desktop-experimental` (check out `origin/desktop-experimental`; merge `origin/main` into it first if it is behind — see EXPERIMENTAL.md for the conflict policy) and read the version files from that branch. The last-tag baseline is the newest `desktop-v*` tag of either channel that is an ancestor of the branch.
The sidecar bundles `@cline/core` and friends from the monorepo, so SDK changes ship inside the desktop app too. Fold user-visible SDK changes (providers, models, behavior fixes) into the notes; skip purely internal ones.
@@ -49,13 +60,15 @@ Flat bullet list, user-facing language. Present the draft and wait for approval
4. Decide the version bump.
Ask whether this is patch, minor, major, or an explicit version. Do not guess if the user has not made it clear.
Stable: ask whether this is patch, minor, major, or an explicit version. Do not guess if the user has not made it clear.
5. Update release files.
Beta: apply the versioning rule — base = next stable version, increment `N` (`0.0.14-beta.1` → `0.0.14-beta.2`; after stable `0.0.14` ships, next is `0.0.15-beta.1`). Confirm the computed version with the user.
5. Update release files (on `main` for stable, on `desktop-experimental` for beta).
-`apps/examples/desktop-app/package.json` → new version
-`apps/examples/desktop-app/src-tauri/tauri.conf.json` → same version
- Prepend `## X.Y.Z` (no date) to `apps/examples/desktop-app/CHANGELOG.md` with the approved notes.
- Prepend `## X.Y.Z` (no date; `## X.Y.Z-beta.N` for beta) to `apps/examples/desktop-app/CHANGELOG.md` with the approved notes.
6. Verify before committing.
@@ -77,16 +90,20 @@ Ask before pushing the release commit, then before creating and pushing the tag:
```sh
git push origin HEAD
git tag -a desktop-vX.Y.Z -m "Desktop vX.Y.Z"
git tag -a desktop-vX.Y.Z -m "Desktop vX.Y.Z"# beta: desktop-vX.Y.Z-beta.N / "Desktop vX.Y.Z-beta.N"
git push origin refs/tags/desktop-vX.Y.Z
```
8. Publish.
The release commit must be on `main` and the tag pushed first.
The release commit must be on the channel's branch (`main` for stable, `desktop-experimental` for beta) and the tag pushed first. Dispatch from `main` for **both** channels (see the release contract for why).
```sh
gh workflow run desktop-publish.yml -f git_tag=desktop-vX.Y.Z -f confirm_publish=publish
# stable:
gh workflow run desktop-publish.yml --ref main -f git_tag=desktop-vX.Y.Z -f channel=stable -f confirm_publish=publish
# beta:
gh workflow run desktop-publish.yml --ref main -f git_tag=desktop-vX.Y.Z-beta.N -f channel=beta -f confirm_publish=publish
gh run list --workflow=desktop-publish.yml --limit=1 --json url,status,conclusion,createdAt --jq '.[0]'
```
@@ -103,21 +120,24 @@ gh api repos/cline/cline/actions/runs/<run-id>/pending_deployments \
Nothing after `validate` runs — and no signing key is readable — until then.
The workflow builds one universal macOS bundle (`tauri build --target universal-apple-darwin` lipos the aarch64 + x86_64 Rust binaries; the Bun sidecar is lipo'd by `build-sidecar-bin.ts`), verifies every Mach-O in the bundle carries both slices, signs with the Developer ID certificate, notarizes with the App Store Connect API key, signs the updater artifact with the Tauri updater key, creates the GitHub release, refreshes `desktop-latest/latest.json`, and posts to Slack. Notarization typically adds 2–10 minutes.
The workflow builds one universal macOS bundle (`tauri build --target universal-apple-darwin` lipos the aarch64 + x86_64 Rust binaries; the Bun sidecar is lipo'd by `build-sidecar-bin.ts`; beta adds the `tauri.beta.conf.json` overlay), verifies every Mach-O in the bundle carries both slices and that the compiled binary embeds exactly its own channel's feed URL, signs with the Developer ID certificate, notarizes with the App Store Connect API key, and signs the updater artifact with the Tauri updater key. In parallel, `build-windows` builds the x64 NSIS installer on a Windows runner, Authenticode-signs every binary via Azure Trusted Signing (Tauri `signCommand` -> `scripts/tauri-sign-windows.ps1`), runs the same feed-endpoint and telemetry guardrails, and verifies the shipped installer with `Get-AuthenticodeSignature`. The release job then creates the GitHub release (prerelease for beta), refreshes the channel's feed (`desktop-latest/latest.json` or `desktop-beta/latest.json`), and posts to Slack. Notarization typically adds 2–10 minutes.
If the workflow fails on missing credentials, see "Publish secrets (one-time setup)" below.
9. Verify the update feed after the run succeeds.
```sh
curl -sL https://github.com/cline/cline/releases/download/desktop-latest/latest.json | head -30
curl -sL https://github.com/cline/cline/releases/download/desktop-latest/latest.json | head -30# stable
curl -sL https://github.com/cline/cline/releases/download/desktop-beta/latest.json | head -30 # beta
```
The `version` field must be the new release and both `darwin-aarch64` and `darwin-x86_64` entries must point at the same new`desktop-vX.Y.Z` universal `.app.tar.gz` asset (each slice of the fat binary requests its own arch key at runtime, so both keys serve the one artifact). Installed apps — including older per-arch installs — pick the update up on next launch or within 2 hours.
The `version` field must be the new release; both `darwin-aarch64` and `darwin-x86_64` entries must point at the same new universal `.app.tar.gz` asset under the release tag (each slice of the fat binary requests its own arch key at runtime, so both keys serve the one artifact), and the `windows-x86_64` entry must point at the new `*_x64-setup.exe` asset. Installed apps on that channel — including older per-arch installs — pick the update up on next launch or within 2 hours.
After a **beta** publish, also confirm the stable feed was not touched: `desktop-latest/latest.json` must still serve the previous stable version. (The workflow guards this fail-closed, but it is cheap to verify and catastrophic to miss — the updater comparator is a plain semver "newer than", so a beta manifest on `desktop-latest` would auto-update every stable install onto the beta.)
10. Final response.
Report: version, tag, changelog updated, commit hash, what was pushed, workflow URL, and the feed verification result.
Report: channel, version, tag, changelog updated, commit hash, what was pushed, workflow URL, and the feed verification result.
# (the branch is hardcoded to legacy-extension in the workflow; it is
# deliberately not an input)
```
npm test suite runs ungated; the publish job waits on the `Publish` environment. This workflow derives + pushes the `v<version>` tag itself and creates the GitHub release — no manual tagging. Publishes to Marketplace **and** Open VSX. The branch is the npm codebase: use `npm`, never `bun`, and expect the old monolith layout (`apps/vscode/src/core/...`).
Paste the "About" diagnostics for your Cline surface. This captures the IDE build, runtime, and host details we need.
Paste the diagnostics for your Cline surface. This captures the build, runtime, and host details we need.
- VSCode Extension: open `Help → About` (Windows/Linux) or `Code → About Visual Studio Code` (macOS), then copy the info.
- JetBrains Plugin: open `Help → About` (Windows/Linux) or `<IDE name> → About` (macOS), then click `Copy` to grab build, runtime, OS, memory, and cores.
- CLI: there is no About dialog. Run `cline --version` and paste the output.
placeholder:Paste the copied About info or `cline --version` output here.
- Desktop App: paste the app version from the Settings view.
- Cloud Platform: paste your browser name and version, plus the page URL where the issue occurred.
placeholder:Paste the copied About info, `cline --version` output, or browser/app details here.
for var in AZURE_CLIENT_ID AZURE_TENANT_ID AZURE_SUBSCRIPTION_ID SIGNING_ENDPOINT SIGNING_ACCOUNT SIGNING_PROFILE; do
if [ -z "${!var}" ]; then
missing+=("$var")
else
set_count=$((set_count + 1))
fi
done
if [ "${#missing[@]}" -eq 0 ]; then
echo "Azure Trusted Signing is configured; Windows binaries will be signed."
echo "enabled=true" >> "$GITHUB_OUTPUT"
elif [ "$set_count" -eq 0 ]; then
echo "::warning::Azure Trusted Signing is not configured; publishing UNSIGNED Windows binaries. Set the AZURE_* and AZURE_TRUSTED_SIGNING_* repository secrets to enable signing."
echo "enabled=false" >> "$GITHUB_OUTPUT"
else
# Partial configuration is almost certainly a typo'd or renamed
# secret. Fail loudly instead of silently publishing unsigned.
echo "::error::Azure Trusted Signing is PARTIALLY configured; refusing to publish. Missing: ${missing[*]}"
if ! gh release view "$FEED" >/dev/null 2>&1; then
if [ "$CHANNEL" = "beta" ]; then
gh release create "$FEED" \
--title "Cline desktop beta (auto-update feed)" \
--notes "Rolling release backing the beta desktop app auto-updater. The latest.json asset points at the newest desktop-vX.Y.Z-beta.N release. Only beta installs poll this feed; stable installs use desktop-latest. Do not delete." \
--latest=false \
--prerelease \
--target "$(git rev-parse HEAD)"
else
gh release create "$FEED" \
--title "Cline desktop (auto-update feed)" \
--notes "Rolling release backing the desktop app auto-updater. The latest.json asset points at the newest desktop-vX.Y.Z release. Do not delete." \
text: "<https://github.com/${{ github.repository }}/releases/tag/${{ needs.validate.outputs.tag }}|Download DMG> — installed apps auto-update on next launch${{ steps.prev_tag.outputs.prev_tag != '' && format(' | Full Changelog: https://github.com/{0}/compare/{1}...{2}', github.repository, steps.prev_tag.outputs.prev_tag, needs.validate.outputs.tag) || '' }}"
text: "<https://github.com/${{ github.repository }}/releases/tag/${{ needs.validate.outputs.tag }}|Download DMG> — ${{ needs.validate.outputs.channel == 'beta' && 'beta channel: installs side by side with the stable app and only beta installs auto-update; stable users are unaffected' || 'installed apps auto-update on next launch' }}${{ steps.prev_tag.outputs.prev_tag != '' && format(' | Full Changelog: https://github.com/{0}/compare/{1}...{2}', github.repository, steps.prev_tag.outputs.prev_tag, needs.validate.outputs.tag) || '' }}"
Everything here lands through the SDK bundle, so it applies to windows running that bundle.
### Fixed
- Cost estimates are no longer shown for providers billed by a flat-rate subscription (ClinePass, ChatGPT via Codex, and Claude Code). The task header and model pricing rows rendered API-rate dollar figures that read as real charges on top of the subscription, including a flash of them on every chat-view mount while provider listings were loading.
- Signing back in no longer moves your last-used provider off ClinePass on credential refresh.
- Hooks now resolve their workspace from the VS Code window instead of shared global state in `~/.cline`. With a second window open on another project, a workspace's `.clinerules/hooks` scripts were never discovered, and hook cwd and the workspace paths passed to hook scripts resolved against whatever project some other or older Cline instance last recorded.
- New files are now created with your platform's native line endings.
- Fixed the codebase search tool crashing on files containing a single enormous line.
- Credentials embedded in git remote URLs are now redacted from the workspace information sent to the model, which also now carries richer workspace metadata.
- Installing an MCP server from the marketplace no longer misreads the catalog's `--` separator as part of the server command.
- The hub's event log can no longer grow until it fills your disk.
### Changed
- The per-tool MCP auto-approve checkboxes are hidden. MCP auto-approval is governed solely by the global "Use MCP servers" toggle — the per-tool checkboxes were no-ops that implied granularity the approval path does not have.
## [4.1.15]
Everything here lands through the SDK bundle, so it applies to windows running that bundle.
### Fixed
- Auto-approve every MCP tool call while the "Use MCP servers" toggle is on. The toggle only took effect on tools that had also been opted in individually, so turning it on appeared to do nothing; it now governs all MCP tools on its own.
## [4.1.14]
Everything here lands through the SDK bundle, so it applies to windows running that bundle.
### Added
- Refresh the built-in model catalog. New entries include Claude Fable 5, Grok 4.6 on Vertex, several DeepSeek V4 Flash variants (including the vision preview), MiMo v2.5, Qwen3.8 27B, Gemma 4 26B, LongCat 2.0, Nemotron 3.5 Lightning, and Thinking Machines' Inkling models.
### Fixed
- Restore task completion telemetry for interactive sessions. A share of interactive stops routed through a teardown path that never reported completion after 4.1.11 changed how session status is tracked; every session now reports it exactly once.
## [4.1.13]
Everything here lands through the SDK bundle, so it applies to windows running that bundle.
### Fixed
- Restore tool calling for custom OpenAI-Compatible models whose capability list was inferred from convenience flags like `supportsReasoning`. The inferred list read as an authoritative denial and stripped every tool from the request; an explicitly authored capability list still decides.
- Keep Hub-backed sessions intact across a Hub restart or upgrade. Clients replay the events they missed while disconnected, and the same event is no longer delivered twice when the replay and live streams overlap.
- Carry session and client identity into Langfuse traces for Hub-backed and delegated-agent runs, which previously arrived without their session grouping or client version.
## [4.1.12]
Everything here lands through the SDK bundle, so it applies to windows running that bundle.
### Fixed
- Enforce enterprise MCP controls on the Customize marketplace. MCP entries are now hidden when remote config disables the marketplace, and limited to `allowedMCPServers` when an allowlist is configured.
- Restore tool calling for custom OpenAI-Compatible models whose stored capability list was empty.
## [4.1.11]
Everything here lands through the SDK bundle, so it applies to windows running that bundle — except the last section, which is a legacy-bundle fix.
### Added
- Let models that support it generate images during a task. Generated images render inline in the conversation.
### Fixed
- Fix code actions failing with "command not found" on VS Code 1.134.
- Fix `@` file mentions breaking on paths that contain spaces.
- Show the diff edit view for multi-line edits in files with CRLF line endings.
- Continue the surviving session when resuming a task, instead of rebuilding it from the original task text.
- Clear the task-scoped settings overlay when the task view is cleared or switched, so one task's overrides no longer leak into the next.
- Honor the classic truncation range when migrating legacy tasks.
- Preserve LiteLLM input token limits instead of overwriting them with catalog values.
- Restore custom base URLs for Gemini, and normalize legacy host-root values so they keep working.
- Point provider signup links at each provider's API key page instead of a generic landing page.
- Load skill slash commands through the skills tool instead of pasting their instructions into your message, which previously delivered them twice.
- Stop offering image, voice, and other non-chat models in chat model pickers.
- Deliver a `PreToolUse` hook's `contextModification` to the model again, and wait for `PostToolUse` hooks so their output and `cancel` control are honored.
- Show tool activity a provider runs itself — every tool the Claude Code provider executes inside its own session — instead of dropping it from the conversation.
- Fix `run_commands` failing with ENOENT when a structured command carried a full command line with no arguments.
- Run PowerShell commands fail-fast, so a pipeline erroring per item stops at the first error instead of flooding output and still reporting success.
- Keep remote configuration in step with the SDK: coordinated refreshes, session gating, and a fail-closed opt-out.
### Changed
- Show the billed cost for Cline gateway usage.
- Refresh the model catalog, which adds AMD, Arcee, Echo, Jalapeno, Kosmik, LLM Gateway, RunInfra, and SCNet as providers and updates model lists, pricing, and per-provider default models across the board.
### Fixed (legacy bundle)
- Only treat an Anthropic `invalid_request_error` as a context-overflow when its message says so. An unrelated invalid request (bad tool schema, oversized image, unknown model id) no longer triggers context-overflow recovery.
## [4.1.10]
Everything in this release lands through the SDK bundle, so it applies to windows running that bundle and not the legacy one. The legacy bundle is unchanged from 4.1.9.
### Added
- Let models that support it search the web during a task, with a toggle in Feature Settings to turn it on. Search calls and their results appear in the conversation and persist across reloads.
### Fixed
- Stop two Cline installations on different builds from shutting each other's Hub daemon down in a loop, which killed live sessions with an abnormal socket close. Build identity is now compared through a total order, so at most one side of a pair can decide to retire the other.
- Leave a Hub that is still serving sessions in place instead of replacing it mid-handshake; the swap happens once it goes idle.
- Reclaim idle plugin sandbox processes instead of leaving them running for the life of the session.
### Changed
- Refresh the model catalog, which adds Crusoe as a provider and updates model lists and per-provider default models across the board.
## [4.1.9]
### Changed
- Use the editor's foreground color for diff block text, so diffs stay legible in themes where the previous hardcoded color washed them out.
- Switch the interface to Inter and Geist Mono.
### Fixed
- Don't discard a successfully refreshed Cline token when the old one was already past expiry, which made the first request after a long idle period fail despite valid credentials.
- Stop the legacy-task migration backlog from spamming telemetry, and record a migration outcome only once the seeded session actually persists, so a failed migration is no longer reported as a success.
- Report involuntary Cline logouts (a rejected refresh token) instead of clearing credentials silently.
### Fixed (SDK bundle only)
These land through SDK v0.0.74 and therefore apply to windows running the SDK bundle, not the legacy one.
- Fix the Claude Code provider being unusable for agentic work: it now runs its own native tools instead of receiving tool definitions it cannot bridge, anchors the session on your workspace directory, and loads `~/.claude` plus project settings so your permission rules apply.
- Reject truncated tool-call JSON instead of silently "repairing" it into wrong arguments.
- Fix strict providers rejecting a turn with "user message must have content" when a message's content held only empty text parts.
- Fix a mid-turn crash on streamed tool calls with non-zero or non-contiguous indexes, hit through LiteLLM's Anthropic passthrough.
- Report disjoint per-request token buckets instead of re-counting the whole cached conversation on every request, which inflated per-task totals roughly 5x on cache-heavy sessions.
## [4.1.8]
### Added
- Enter any Vertex model ID by hand, including models the catalog doesn't list yet.
- Support Fable 5 on Vertex.
### Changed
- Show the full model catalog for every Vertex region instead of filtering the picker down to a hardcoded list of global-endpoint models, which lagged behind every model launch. Picking a model the region doesn't serve now fails at request time with recovery guidance in the error row.
- Report Fable 5 cost on Vertex as unknown rather than applying Anthropic's list price, which understated what Vertex actually bills — its rates are region-dependent.
- Make the auto-approve menu the single source of truth for unattended runs and remove the Yolo Mode toggle, which was cosmetic: nothing in the approval path read it. Setups that had Yolo Mode (or auto-approve-all) turned on are migrated to auto-approving every action, so they keep running unattended.
### Fixed
- Respect your configured max output tokens when the compaction summarizer requests a summary.
- Remove the stale "Double-Check Completion" feature tip.
## [4.1.7]
### Added
- Restore the "View Changes" button on completion rows, backed by SDK checkpoints, so you can review everything a task touched from the completion card.
- Bring back a copy button on turn-final response rows.
- Support pre-registered OAuth clients for remote MCP servers, for setups where dynamic client registration isn't available.
### Changed
- Fade the "View Changes" button until changes since the last message are confirmed, and hide it entirely when there is nothing to show.
- Centralize plugin settings and contributions, with host-aware snapshots and atomic plugin toggles.
- Carry execution context in scheduled run reports — readable headers, schedule metadata, durations, and lifecycle error details.
### Fixed
- Preserve prompts queued during a turn when that turn is interrupted: they survive aborts, are drained after a turn aborts itself, and the stop is surfaced instead of the queue being silently dropped.
- Keep session context durable across aborts and hub restarts, so an interrupted session resumes with the state it had.
- Settle the turn phase when a mode switch aborts a running turn.
- Report queued-turn failures as `run.failed` instead of letting them complete silently.
- Keep a hung MCP server from taking down session creation, and give stdio servers that were never configured a 30-second initialize budget instead of blocking indefinitely.
- Surface OAuth authorization for SSE MCP servers on a 401 instead of failing outright.
- Route LiteLLM through Chat Completions instead of the Responses API, fixing requests against LiteLLM proxies.
- Retry network interruptions that happen mid-stream but before any model output, instead of failing the turn.
- Use the configured fetch for Vertex ADC token refreshes, so they work behind proxies and custom transports.
- Include files that were untracked when a snapshot was taken in checkpoint diffs, and pick up checkpoints when git is initialized part-way through a session.
- Fall back to the session cwd or Desktop for @-mention file search in empty windows.
- Never run a foreign compiled plugin-sandbox bootstrap for a source host.
## [4.1.6]
### Added
- Offer `meta/muse-spark-1.2-contributor` on the Cline provider, alongside a refreshed model catalog.
### Fixed
- Attribute error telemetry to the model actually in use for a run, so failures are no longer reported against the wrong model.
## [4.1.5]
### Added
- Explain when a free model promotion ends. Requests to a retired free model now show a dedicated notice with a button to pick another model, instead of a generic error with nothing but a Retry prompt.
### Changed
- Map reasoning settings onto a shared path across AI SDK providers, so effort levels and enable/disable toggles behave consistently (including on Ollama) instead of relying on per-provider overrides.
## [4.1.4]
### Added
- Recognize Chutes as a provider.
- Show skills alongside workflows in the slash command menu, and disambiguate commands that share a name instead of letting one shadow the other.
### Changed
- Remove model-initiated plan-to-act switching. Switching out of plan mode is now driven by you, not by the model deciding mid-turn.
- Hard-block file-editing shell commands in plan mode instead of relying on prompting alone. Read-only investigation still works, but file manipulation, in-place editors, redirection to files, mutating git subcommands, and package installs are refused.
### Fixed
- Stop treating a turn that completes with a plan as a failed turn when a plan-blocked command was its only tool call. The turn no longer ends in the error state with a Retry footer, and toggling to Act correctly re-runs the presented plan instead of appearing to do nothing.
- Show tool paths relative to the workspace in the chat view instead of absolute paths.
- Reset pending attachments when starting a new task, so images from the previous task no longer carry over.
- Surface a clear error when the selected provider has no API key configured, instead of a generic failure.
- Refresh MCP tool and resource lists when a server sends a `list_changed` notification, instead of only showing a toast.
- Show installed plugins under their real package names instead of all appearing as "index".
- Correct the Linux keybinding label in the Plan/Act mode tooltip.
- Recover from running out of context instead of failing with a raw provider error — the run compacts and retries once, and the cases that genuinely cannot be recovered explain why.
- Retry empty model responses on every provider rather than only Ollama, fixing hard "Model returned empty response" failures on OpenRouter, Cline, and OpenAI-compatible endpoints.
- Stop Claude 4.6+ and 5.x models being rejected with "thinking.type.enabled is not supported" when they resolve from the offline catalog or from a hand-typed model id.
- Restore Bedrock prompt caching, which reported zero cache reads and writes because the provider sent a cache format Bedrock discards, and route Bedrock foundation models through geo inference profiles.
- Send `max_completion_tokens` for reasoning models on OpenAI-compatible endpoints, and substitute image content for models without image support instead of failing the request.
- Inherit the MiniMax default model from models.dev, and refresh the bundled catalog, which adds Infomaniak and SCX.ai.
- Report the same provider failure once instead of twice in error telemetry, and rate-limit repeated failures from unattended retry loops.
- Fixed the background hub process ballooning in memory during long sessions — session status updates were broadcasting a full copy of the conversation transcript to every connected client, which on a large task could grow the process to tens of gigabytes. Upgrading retires the running hub so the fix takes effect on the next command
- New files are now created with your platform's native line endings
- Fixed the codebase search tool crashing on files that contain a single enormous line
- Cost estimates are no longer shown for Claude Code. Its usage is typically covered by a Claude Pro/Max subscription, but its models reuse Anthropic API pricing, so Cline was showing charges you were not being billed
- Credentials embedded in git remote URLs are now redacted from the workspace information sent to the model
- Installing an MCP server no longer misreads a `--` separator in the install arguments as part of the server command
- Refreshed the model catalog. Adds seven providers (Agnes AI, Aixy, IteraCompute, LLM Tech, NeoSmith, Pendra, and Standard Compute) and updates model lists and pricing across providers. The resolved default model changes for ClinePass (now GLM 5.3), Z.ai, Hugging Face, evroc, LLM Gateway, NanoGPT, and Weights & Biases, so if you use one of those without pinning a model you will get a different default
## 3.0.58
- The first-launch "Try ClinePass" dialog no longer advertises the $4.99 first-month promo, which is ending
- The hub's event log is now capped at 64 MiB on disk. Events carrying full session snapshots could previously grow the log to tens of gigabytes on a long-running hub, since deleting rows never shrinks the file. Oldest events are dropped first and the space is returned, and pruning runs on volume as well as on a timer
- Refreshed the model catalog. Adds two providers (AgentRouter and Opper) and updates model lists and pricing across providers. The resolved default model changes for Aki.io and NanoGPT, so if you use one of those without pinning a model you will get a different default
## 3.0.57
- Added `cline hub drain`, which stops a hub from accepting new mutating work while it finishes what it is already running, and `cline hub drain --off` to lift it
- Added `cline hub upgrade`, which drains the hub, waits for it to go idle, stops it, and starts a fresh one on the current build. An aborted upgrade lifts the drain again, so the hub is never left refusing work
- Sessions now survive a hub restart. A reconnecting client replays the events it missed while disconnected, deduped by event id so nothing is delivered twice
- Fixed tool calling being silently disabled for custom OpenAI-Compatible models whose capability list was inferred from convenience flags like `supportsReasoning`. The inferred list read as an authoritative denial and stripped every tool from the request
- Langfuse traces now carry session and client identity for hub-backed and delegated-agent runs, instead of arriving without their session grouping or client version
- Refreshed the model catalog, which updates model lists and pricing across providers and changes the resolved default model for several of them (DeepSeek, Crof, CrossModel, Eden AI, Kilo, and NanoGPT)
## 3.0.56
- Models that support image generation can now produce media during a turn. The TUI saves each generated file to a temporary path and prints it so you can open it with your usual tools, HTML session exports embed images inline, and ACP clients receive generated images as image content
- Skill slash commands now load through the skills tool instead of expanding into your message. History and resume show the `/command` you typed instead of the whole skill body, and the instructions reach the model once instead of twice. Workflows still expand, as does zen mode, whose preset has no skills tool
- Image, voice, and other non-chat models are no longer offered in the onboarding and model pickers or ACP model listings, and are rejected for `--model`
- Fixed TUI dialog colors not following theme changes live
- Fixed the account dialog's selection chevron so it matches the other dialogs
- Fixed provider-executed tool activity — every tool the Claude Code provider runs inside its own session — being dropped instead of shown as a tool card
- Fixed `PreToolUse` hook `contextModification` never reaching the model, and `PostToolUse` hooks running fire-and-forget with their output and `cancel` control discarded
- Fixed `run_commands` failing with ENOENT when a structured command carried a full command line with no `args`
- PowerShell commands now fail fast on the first error instead of emitting an error record per enumerated item and still reporting success
- Fixed Gemini custom base URLs configured as a host root
- Fixed `cline schedule` commands against a remote hub, which now register a workspace client so they are authorized under the new workspace-scoped schedule rules
- Usage now displays the billed gateway cost
- Refreshed the model catalog, which adds AMD, Arcee, Echo, Jalapeno, Kosmik, LLM Gateway, RunInfra, and SCNet as providers and updates model lists, pricing, and per-provider default models across the board
## 3.0.55
- Auto-updates no longer install while a CLI is attached to the Hub. The update is recorded at startup and installed on exit, once the Hub confirms nothing else is attached, so a background update can no longer swap the package out from under a live session and kill it with `Hub connection closed (code=1006)`. `cline update` still installs immediately and now tells you the update applies on next start
- Added protections for an update landing under CLI 3.0.54 and earlier, whose updater restarts the Hub mid-session and then rejects every replacement, bricking a running session. The newly installed package defuses that path during install instead of leaving it to fire
- Fixed two Cline installations on different builds shutting each other's Hub daemon down in a loop, which killed every live session with an abnormal socket close. Build identity is now compared through a total order, so at most one side of a pair can ever decide to retire the other (from SDK v0.0.75)
- A newer build no longer replaces a Hub that is still serving sessions — it attaches to it and the swap happens on a later launch, instead of the sessions dying mid-handshake (from SDK v0.0.75)
- Removed the "outdated Hub" notice. It reported a state you cannot act on, and the toast was capped narrower than the message, so it rendered cut off before the reassuring half of the sentence at every terminal width. The prompt for a genuine build mismatch, where there is something to do, is unchanged
- Streaming assistant markdown no longer flashes back to raw text. Settled headings, links, and code stay rendered as new chunks arrive instead of the whole message being rebuilt and re-highlighted on every chunk, which also stops the transcript from jumping vertically mid-stream
- Web search calls and their results from models that run search natively now render in the transcript (from SDK v0.0.75)
- Idle plugin sandbox processes are now reclaimed instead of lingering for the life of the session (from SDK v0.0.75)
-`cline doctor fix` now reports honestly: processes that survived a kill are separated from ones that appeared while the fix ran, a live parent respawning a daemon is named, and a startup lock held by a running process is reported as held rather than leaked (from SDK v0.0.75)
- Refreshed the model catalog, which adds Crusoe as a provider and updates model lists and per-provider default models across the board (from SDK v0.0.75)
## 3.0.54
- Fixed the Claude Code provider being unusable for agentic work: the provider now runs its own native tools instead of receiving tool definitions it cannot bridge, the session is anchored on your workspace directory instead of inheriting the host's cwd, and `~/.claude` plus project settings are loaded so your permission rules apply. File edits under the workspace are auto-approved; command execution stays gated by your own Claude settings (from SDK v0.0.74)
- Fixed truncated tool-call JSON being silently "repaired" into wrong arguments — a payload with an unterminated string is now rejected rather than getting an invented terminator (from SDK v0.0.74)
- Fixed strict providers rejecting a turn with "user message must have content" when a message's content held only empty text parts (from SDK v0.0.74)
- Fixed a mid-turn crash on streamed tool calls with non-zero or non-contiguous indexes, hit through LiteLLM's Anthropic passthrough (from SDK v0.0.74)
- Managed Hub daemons now upgrade directionally: when another Cline install ships a newer Hub build, the CLI attaches to the newer daemon and prompts you to update and restart instead of the two installs repeatedly retiring each other's daemons. Yolo and sandbox sessions, which never attach to the shared Hub, are not interrupted by that prompt (from SDK v0.0.74)
- Fixed the Hub daemon logging an unhandled `hub server close failed` error and exiting non-zero whenever a client was still connected at shutdown (from SDK v0.0.74)
- Fixed per-task token totals being inflated roughly 5x on cache-heavy sessions — token telemetry now reports disjoint uncached-input, cache-read, and cache-write buckets instead of re-counting the whole cached conversation on every request (from SDK v0.0.74)
- Upgrading the CLI now retires an already-running Hub daemon and respawns it on the new code, instead of the upgraded CLI continuing to talk to a daemon executing the previous release
## 3.0.53
- Fixed the CLI reconnecting to a stale Hub daemon after an upgrade. Hub daemons now carry a runtime build fingerprint, so an upgraded CLI retires and respawns a daemon still running older code instead of attaching to it (from SDK v0.0.73)
- Fixed compaction being silently skipped on reasoning models. The summarizer no longer hardcodes a 1024-token output cap — it honors your max output tokens setting, defaults to 4096 (lowered when the model reports less), and logs a diagnostic when a summary comes back empty (from SDK v0.0.73)
- Added Fable 5 (`claude-fable-5`) to the Vertex model catalog. Pricing is intentionally omitted because Vertex bills region-dependently, so cost shows as unknown rather than wrong (from SDK v0.0.73)
- Custom Vertex model IDs are now passed through unchanged, routing Claude-style IDs to the Anthropic-on-Vertex path (from SDK v0.0.73)
## 3.0.52
- Added `cline mcp uninstall` for removing an installed MCP server
- Schedules now reuse your saved provider settings instead of needing provider configuration of their own
- Queued messages are legible on light-theme terminals — they were previously rendered in a color that washed out against a light background
- MCP tool results render as readable text in the TUI instead of escaped JSON, and binary payloads survive being expanded instead of being mangled
- Malformed tool input/output payloads no longer break rendering — the formatters degrade gracefully instead of throwing
- Prompts queued during a turn now survive being interrupted: they are preserved across aborts, drained after a turn aborts itself, and the stop is surfaced instead of leaving the queue silently dropped (from SDK v0.0.72)
- Session context stays durable across aborts and hub restarts, so an interrupted session resumes with the state it had (from SDK v0.0.72)
- A hung MCP server no longer takes down session creation, and stdio servers that were never configured get a 30-second initialize budget instead of blocking indefinitely (from SDK v0.0.72)
- Remote SSE MCP servers surface an OAuth authorization prompt on a 401 instead of failing outright, and pre-registered OAuth clients are supported for setups without dynamic client registration (from SDK v0.0.72)
- LiteLLM requests route through Chat Completions instead of the Responses API, fixing calls against LiteLLM proxies (from SDK v0.0.72)
- Network interruptions that happen mid-stream but before any model output are retried instead of failing the turn (from SDK v0.0.72)
- Vertex ADC token refreshes use the configured fetch, so they work behind proxies and custom transports (from SDK v0.0.72)
- Checkpoint diffs include files that were untracked when the snapshot was taken, and checkpoints are picked up when git is initialized part-way through a session (from SDK v0.0.72)
- Scheduled run reports carry execution context — readable headers, schedule metadata, durations, and lifecycle error details (from SDK v0.0.72)
## 3.0.51
- Reasoning effort now applies consistently across providers instead of going through per-provider thinking overrides, including Ollama, and asking for reasoning to be off is respected everywhere (from SDK v0.0.71)
-`meta/muse-spark-1.2-contributor` is now selectable on the Cline provider, alongside a refreshed model catalog (from SDK v0.0.71)
- Error telemetry now reports the model that was actually in use for the run (from SDK v0.0.71)
## 3.0.50
- Added user-selectable color themes to the interactive TUI. Pick one with `/theme`, the command palette, or the Theme row in `/settings` — the picker previews each theme live. Built-in themes are Auto (terminal-adaptive, the default), Cline Dark, Cline Light, Tokyo Night, Gruvbox Dark, Nord, Dracula, Catppuccin Mocha, One Dark, Solarized Dark, and Solarized Light. Named themes paint the background, foreground, accents, syntax highlighting, and diff colors, and `CLINE_THEME` overrides the persisted choice at startup
- The git branch shown below the prompt now updates when you switch branches from another terminal or your editor, instead of showing whatever was checked out when the TUI started
- Telegram slash commands such as `/clear` now reach the connector command host — the Telegram library was intercepting them and they were silently dropped
- Racing connector launches no longer collide: an instance is claimed before it opens socket mode, the hub supervises connector processes, and `doctor`/`connect` skip connectors that are already starting. Connector tools are also enabled by default, and the Slack greeting is no longer replayed on reconnect
- Auto-approval settings are now honored over ACP
- Plan mode now hard-blocks file-editing shell commands instead of relying on prompting alone — `run_commands` stays available for read-only investigation, but file-manipulation commands, in-place editors (`sed -i`, `perl -i`), redirection to files, mutating git subcommands, package installs, and nested command strings (`sh -c`, `eval`, `sudo`) are rejected, on Windows and PowerShell too (from SDK v0.0.70)
- A turn that ends with a completed plan is no longer rendered as a failed turn when a plan-blocked command was its only tool call
- Running out of context is now recovered from instead of failing with a raw provider error: the run force-compacts and retries once, and the cases that genuinely cannot be recovered report why (from SDK v0.0.70)
- Empty model responses are now retried on every provider, not just Ollama — OpenRouter, Cline, and OpenAI-compatible endpoints previously failed the task outright with "Model returned empty response" (from SDK v0.0.70)
- Claude 4.6+ and 5.x models are no longer rejected with "thinking.type.enabled is not supported" when they resolve from the offline catalog or from a hand-typed model id (from SDK v0.0.70)
- Bedrock prompt caching works again — the provider was sending a cache format Bedrock silently discards, so cache reads and writes were always 0 — and Bedrock foundation models are now routed through geo inference profiles (from SDK v0.0.70)
- Reasoning models on OpenAI-compatible endpoints now receive `max_completion_tokens` instead of the rejected `max_tokens`, and requests to models without image support substitute the image content instead of failing (from SDK v0.0.70)
- MiniMax now inherits its default model from models.dev, and the model catalog picked up two new providers, Infomaniak and SCX.ai (from SDK v0.0.70)
- Upgraded the model layer to AI SDK 7 and switched Ollama to the native AI SDK provider (from SDK v0.0.70)
- Error telemetry no longer reports the same provider failure twice, and repeated failures from unattended retry loops are rate-limited (from SDK v0.0.70)
## 3.0.49
-`/undo` works again once the agent has used tools — the checkpoint picker counted tool results as user turns, so restore aborted with "Could not find user message for run N"
@@ -270,6 +270,9 @@ The postinstall script runs in diverse environments (CI, Docker, restricted perm
### Windows
Windows binaries are `.exe` files. The build script appends `.exe` to the output filename on Windows targets. The resolver handles this. npm on Windows generates `.cmd` shims for bin entries automatically.
### Windows code signing
Windows application control (Smart App Control, WDAC, AppLocker) blocks unsigned executables at launch, regardless of how they were installed — npm distribution gets no exemption ([#12934](https://github.com/cline/cline/issues/12934)). The publish workflow Authenticode-signs `cli-windows-x64/bin/cline.exe` and `cli-windows-arm64/bin/cline.exe` with Azure Trusted Signing before publishing, via the `.github/actions/sign-windows-cli` composite action. Signing runs on the Linux publish runner using [jsign](https://ebourg.github.io/jsign/) (`--storetype TRUSTEDSIGNING`) with an OIDC-federated Entra app, then verifies the signature chain with `osslsigncode` against the Microsoft Identity Verification Root CA 2020. If all `AZURE_*` / `AZURE_TRUSTED_SIGNING_*` repository secrets are absent, the action logs a warning and the release ships unsigned rather than failing; if only some resolve (a typo'd or renamed secret), the release fails loudly instead. The certificate profile secret is suffixed `_CLI` because the desktop app will later get its own profile; the other five secrets are shared. Note that signing bun-compiled executables requires Bun >= 1.2.23 (earlier versions located the embedded bundle relative to the end of the file, which signing corrupts).
### File permissions
Compiled binaries need to be executable (`chmod 755`). The build script sets this after copying. The postinstall also sets permissions on the cached binary. Some npm packaging steps can strip permissions, so both handle this defensively.
"\nSome of these were respawned by a live parent (100); stop the parent process listed above, then re-run. The rest started after the fix began and were not targeted.",
return"\nThese processes started after the fix began, so they were not targeted. Re-run to see whether they persist.";
}
if(respawned.length===pids.length){
return"\nThese processes were respawned by a live parent. Stop the parent process listed above, then re-run.";
}
return`\nSome of these were respawned by a live parent (${respawned.join(", ")}); stop the parent process listed above, then re-run. The rest started after the fix began and were not targeted.`;
"Stdio MCP install requires a command after the server name, for example: cline mcp install fs -- npx -y @modelcontextprotocol/server-filesystem /tmp",
// biome-ignore lint/correctness/useExhaustiveDependencies: dialogCount re-runs the sync when a dialog opens, covering dialogs opened before the container-level option applied (see docblock).
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Saoud Rizwan