* feat(cli): bundle and serve Cline Hub dashboard with cline dashboard
Add the @cline/cline-hub workspace dependency to the CLI and build the
Hub webview as part of CLI packaging. Copy the generated dashboard assets
into platform-specific CLI distributions so the dashboard is available in
built artifacts.
Refactor the Cline Hub server startup into an exported function so the CLI
can start and stop the dashboard server programmatically.
* fix(cli): resolve dashboard webview in wrapper installs
Detect the platform-specific CLI package from the published wrapper layout
and use its bundled cline-hub webview assets when no explicit dist path is
set. Add test coverage for resolving assets via CLINE_WRAPPER_PATH.
* patches
* patch
* fix server detachHub on stop
Imported detachHub.
Changed ClineHubDashboardServer.stop to () => Promise<void>.
Made stop() idempotent with a stopped guard.
Clears the health interval.
Calls server.stop(true).
Always calls await detachHub(ctx) in a finally, so hub client teardown still happens if the HTTP server stop throws.
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* fix(plugin-sandbox): expose CLINE_PLUGIN_IMPORT_TIMEOUT_MS env override
The hardcoded 4000 ms importTimeoutMs default is too tight on Windows
cold-start; the plugin-sandbox tests already use 30_000 ms for the same
reason. This patch lets hosts raise the ceiling via env var without
touching code or adding a CLI flag, with explicit options.importTimeoutMs
still taking precedence.
Precedence: options.importTimeoutMs > env var > 4000.
Refs: #11065
* fix(plugin-sandbox): tighten env parsing + use vi.stubEnv (PR feedback)
- Number.parseInt accepts trailing garbage ("4000ms" -> 4000); switch
to Number() + Number.isInteger() so malformed env values fall back
to the default instead of silently consuming the numeric prefix.
- Replace manual process.env save/restore in the regression test with
the idiomatic vi.stubEnv() / vi.unstubAllEnvs() pattern.
Per Greptile review on #11084.
* docs(sdk): add env-blocker plugin example
Adds a beforeTool hook plugin that deterministically blocks the agent
from reading .env secret files via read_files, editor, or run_commands
(e.g. cat .env), while leaving .env.example/.sample/.template readable.
Demonstrates moving a security policy out of an AGENTS.md rule (a
suggestion the model can ignore) and into the execution path.
* docs(sdk): install env-blocker globally in usage examples
A secret-protection guard is most useful applied to every project, so
drop the --cwd . project-scoped install in favor of the global default.
* docs(sdk): trim env-blocker usage docs
* docs(sdk): limit env-blocker to read paths only
It is a read blocker, so only guard read_files and run_commands.
Drop the editor case (and with it the symmetric apply_patch concern),
keeping the example focused and simple.
* docs(sdk): rename env-blocker helpers for readability
collectPaths -> extractFilePaths, collectCommands -> extractShellCommands
so the beforeTool call sites read clearly at a glance.
* docs(sdk): rename commandTouchesEnv to commandReadsEnv
* docs(sdk): drop console.error from env-blocker hook
VS Code 1.122.0 migrated its bundled ripgrep from `@vscode/ripgrep` to
`@vscode/ripgrep-universal`, which ships per-platform/arch subdirectories
(`node_modules/@vscode/ripgrep-universal/bin/<platform>-<arch>/{rg|rg.exe}`)
instead of the previous flat `node_modules/@vscode/ripgrep/bin/{rg|rg.exe}`.
The migration commit (microsoft/vscode@bf19e5ca / @c4471e24) landed on
`release/1.122` and ships in stable 1.122.0+. Microsoft hit the identical
bug in their own sandbox engines and patched it in microsoft/vscode#317978;
our `getBinaryLocation` was still on the retired layout.
Symptom: on VS Code 1.122.x, all four `checkPath` probes in extension.ts
miss, `getBinaryLocation("rg")` throws `Could not find ripgrep binary`,
and `searchFiles` returns `{results: [], errorReason: "unknown"}`. The
@-mention picker shows "No results found" immediately, regardless of
workspace or query.
Telemetry confirmed the regression bisects cleanly to the VS Code
version boundary, not any Cline release — `mention_failed` events with
`errorType=unknown` jumped from ~300/week on 1.121.0 to ~100k/week on
1.122.0/1, while JetBrains versions (which don't use this code path)
stayed flat. Every historical Cline version is affected when the user
is on 1.122+.
Fix: probe the new `@vscode/ripgrep-universal/bin/<platform>-<arch>/`
layout first (both regular and `.asar.unpacked` variants), then fall
through to the four legacy probes so users on ≤1.121.x keep working.
`<platform>-<arch>` is `${process.platform}-${process.arch}`, matching
the directory naming Microsoft documented in #317978
(darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-arm,
linux-ia32, win32-x64, win32-arm64, win32-ia32, etc.).
This also closes the residual #11105 reports that survived #11166:
Yufeng's PR moved the failure mode from `unknown` to
`ripgrep_spawn_failed` (bare `rg`/`rg.exe` on PATH fallback) but didn't
restore actual functionality for users on 1.122.x — they got
spawn-ENOENT instead of file-not-found. With this patch the bundled
binary resolves correctly and ripgrep runs as before.
Refs: https://github.com/cline/cline/issues/11105
Refs: https://github.com/cline/cline/issues/11142
Refs: https://github.com/microsoft/vscode/pull/317978
* feat(plugin): support rule contributions in sandbox
Add plugin rule registration to the sandbox descriptor and handler state so
plugins can contribute static or dynamic rule content.
Update plugin installation to omit peer dependencies and use
legacy-peer-deps to avoid peer resolution failures during isolated installs.
* feat(cli): support participant mute targets in Discord
Resolve /mute and /unmute targets from Discord user mentions and raw
user IDs so a specific participant can be muted within a thread.
Update Discord system rules to guide agents toward thread-level and
participant-level mute commands, and add tests for target parsing.
* Update sdk/apps/cli/src/utils/chat-commands.ts
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(cli): normalize addressed bot command suffixes
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* fix(cli): clear connector sessions on hub shutdown
* fix: stop Discord connector after repeated errors
Added error tracking to Discord connector to prevent spam:
- Tracks errors by message within a 1-minute window
- After 3 identical errors, shuts down connector instead of posting
- Prevents repeated error messages flooding Discord channels
- Logs shutdown reason for debugging
* fix: address Greptile feedback
1. Error tracker now per-thread (includes thread.id in key)
- Prevents cross-thread error aggregation
- One thread having errors will not kill the whole connector
2. Use fixed time window instead of sliding window
- Track firstSeen timestamp, not just lastSeen
- Prevents indefinite spam from errors every 61s
- Window properly resets after ERROR_WINDOW_MS from first error
3. Remove redundant delete in clearBindingSessionIds
- binding.state.sessionId already deleted in earlier block
- Cleanup was misleading/unnecessary
* feat: Cline Hub web app
Add a Cline Hub app for monitoring connected clients, viewing and driving sessions, streaming assistant output, and restarting the local hub. Document local, LAN, and tunnel usage with room-secret gating, ignore generated Cline cache/config data, and update lockfile entries.
* feat: Cline Hub UI
* feat: provider config schema
* run command update
* Use Workspace versions
* fix: rename routines to schedules
* feat(schedule): add routine summary and update support
Include last execution data in routine schedule overviews and cache the
summary state in the UI to reduce unnecessary reloads.
Add support for updating routine schedules from the hub server, validate
required fields, and trigger schedules asynchronously after confirming they
exist.
* UI for Connectors
* Fix UI switch for telemetryOptOut
* Expands Recent Sessions UI - allow title update
* feat: Cline Hub routes
* Add "health" and "version" routes
* Refactor server.ts nto 17 focused modules
* Provider Model list search box
* Extensions -> Customizations
* fix: restore discord connector catalog
* fix
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* feat(cli): support participant mute targets in Discord
Resolve /mute and /unmute targets from Discord user mentions and raw
user IDs so a specific participant can be muted within a thread.
Update Discord system rules to guide agents toward thread-level and
participant-level mute commands, and add tests for target parsing.
* patches
* update prompt
* fix(cli): stabilize core tests on Windows
Avoid several Windows-specific failure modes in the core CLI test suite.
Vitest already runs test files inside worker pools. The workspace file indexer was lazily spawning a nested worker from a transformed TypeScript module via import.meta.url, which is fragile on Windows and can cause Vitest to report only a generic worker fork crash. Disable that worker path under VITEST and use the deterministic fallback indexer for tests.
Quote process.execPath in bash executor shell-string tests. Windows Node/Bun paths commonly contain spaces, so unquoted command strings can fail under PowerShell or cmd even though they work on Unix paths.
Make detached hub probing defensive by routing probeHubServer calls through a safe wrapper, so rejected or malformed probe results are treated as unreachable instead of destabilizing startup/prewarm flows.
Also clear CLINE_RUN_AS_HUB_DAEMON in daemon test setup so tests do not inherit daemon-mode state from the surrounding CLI environment except where explicitly set.
Validation: bunx vitest run --config vitest.config.ts src/hub/daemon/index.test.ts src/services/workspace/file-indexer.test.ts src/services/workspace/mention-enricher.test.ts src/extensions/tools/executors/bash.test.ts --reporter=dot
Validation: bun run typecheck
Validation: bun run test:unit
* patch
* fix(cli): bind discord sessions to individual message authors
Resolve Discord participants from normalized message author data and persist
participant-specific thread state in bindings. Restore or create sessions per
participant so different Discord users do not accidentally share chat state.
Also add coverage for bot author handling and owner user configuration.
* patches
* fix(cli): steer active connector sessions across turn keys
Detect active connector turns by session ID when the current turn key
does not match, so replies steer the existing runtime session instead of
starting a duplicate session.
Also treat queued runtime turns as a non-error completion and log the
queued state for connector transports.
* fix(cli): steer active connector sessions across turn keys
Detect active connector turns by session ID when the current turn key
does not match, so replies steer the existing runtime session instead of
starting a duplicate session.
Also treat queued runtime turns as a non-error completion and log the
queued state for connector transports.
* add /idel
* fix(cli): bind discord sessions to individual message authors
Resolve Discord participants from normalized message author data and persist
participant-specific thread state in bindings. Restore or create sessions per
participant so different Discord users do not accidentally share chat state.
Also add coverage for bot author handling and owner user configuration.
* patches
Eve Killaby (@candieduniverse) has left Cline; transfer her /.github/ codeowner slot to @dominiccooney so .github changes still have four code owners able to approve.
Add claude-opus-4-8 (200k) and claude-opus-4-8:1m model variants across the
Anthropic, Claude Code, Bedrock, and Vertex catalogs, mirroring the Opus 4.7
setup (same pricing, 1M tiers, global endpoint, adaptive thinking).
- Wire the OpenRouter/Vercel AI Gateway 1m suffix handling and Cline/OpenRouter
model refresh derivation for anthropic/claude-opus-4.8
- Register 4.8 in adaptive thinking detection so it uses the reasoning-effort
selector path
- Bump the Claude Code "opus" alias to 4.8
- Add context window switchers in the Cline and OpenRouter model pickers
- Add provider tests for the new model ids
* ci: gate ext-jb-test-integration auto-trigger on PR author association
Extend the existing MEMBER/OWNER/COLLABORATOR allow-list (already used
for the /test-jetbrains comment path) to pull_request_target [opened,
reopened] as well, so the same trust model applies regardless of how
the workflow is triggered. PRs from non-trusted authors no longer
auto-trigger; a maintainer can still opt them in via /test-jetbrains.
* ci: replace hardcoded app-id with CLINE_JETBRAINS_WORKFLOW_ID var
Matches the convention already in use in cline/intellij-plugin and lets us change the App ID without touching workflow code.
* Update .github/workflows/ext-jb-test-integration.yml
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* ci: rename CLINE_JETBRAINS_WORKFLOW_KEY to CLINE_JETBRAINS_APP_KEY
The secret holds a GitHub App private key. Matches the rename of the matching app-id var in the previous commit.
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Single-file plugins can only import Node builtins and @cline/*. As soon
as a plugin needs an npm dep it has to ship as a package. Adds one
sentence each to the writing-plugins guide (with dependencies in the
example package.json) and plugin-install (noting pluginPaths accepts a
package directory for fast iteration).
TheRealSpencer