Run Cline inference through the VS Code Language Model API (vscode.lm), enabling
models contributed by any extension that registers a language model chat
provider with VS Code. GitHub Copilot is the most common such vendor, but the
implementation is vendor-agnostic — it selects models via
vscode.lm.selectChatModels and has no Copilot-specific logic.
- VsCodeLmHandler implements the Cline SDK ApiHandler and is registered with the
SDK handler registry; the model selector travels as a vendor/family[/version/id]
string in modelId and is parsed back here. Selector segments are
percent-encoded so values containing slashes round-trip intact.
- Native tool calling: tool definitions are passed to sendRequest and tool calls
are surfaced as tool-call chunks; tool results round-trip as
LanguageModelToolResultPart, with structured tool output serialized to text and
a trailing user message appended when a turn ends on tool results so models can
read the output.
- Gated to VS Code: registration is conditioned on the vscode.lm API being
present, and the provider is hidden in the UI on hosts without it (JetBrains).
Depends on @cline/{shared,llms,agents,core} 0.0.42-nightly.1780514867, the first
published SDK build with the custom-registered-handler routing this provider
needs.
Both packages are imported directly from source but were never declared in
apps/vscode/package.json, so they only resolved transitively. On a clean
install this broke:
- @grpc/proto-loader — imported by scripts/proto-utils.mjs,
src/standalone/utils.ts and src/standalone/hostbridge-client.ts; its absence
made `npm run protos` (and therefore the whole build) fail on a fresh checkout.
- @opentelemetry/api-logs — imported by the OpenTelemetry telemetry providers;
its absence produced TS2307 "Cannot find module" errors under tsc.
Versions are pinned to align with the existing dependency families already
declared in this package (@grpc/grpc-js ^1.9.x → proto-loader ^0.7.13;
the @opentelemetry/* 0.56.x line → api-logs ^0.56.0). The npm and bun
lockfiles are updated accordingly (the api-logs change also dedupes several
previously-nested copies to a single hoisted entry).
* fix(vscode): wire auto compact into SDK sessions
* test(sdk): cover both directions of useAutoCondense task override
The previous test left the global mock at `true` for both calls, so the
`taskSettings: true` branch would have passed even if task settings were
ignored entirely. Make the mock read a mutable flag and flip it to `false`
before the second call so both override directions — task `false` over
global `true`, and task `true` over global `false` — are genuinely
exercised.
* Fix mock return type in cline-session-factory test
The getGlobalSettingsKey mock inferred a literal 'false | undefined' return type, so later mockImplementation overrides returning 'true' failed type checking (TS2345). Annotate the implementation as 'boolean | undefined' to widen the inferred mock signature.
---------
Co-authored-by: Mikołaj Kondratek <19799111+mkondratek@users.noreply.github.com>
The MCP SDK calls redirectToAuthorization() on every connection attempt,
and a single server can be reconnected repeatedly (settings watcher,
reconnect handler, restart). Regenerating the OAuth `state` on each call
replaced the state stored for a flow whose authorization URL the user may
already have open, so the completed callback failed validation with
"Invalid OAuth state".
redirectToAuthorization() now keeps an in-progress, still-fresh flow
instead of starting a new one (freshness measured from when the flow
started, never extended, so a stale flow always expires). The PKCE
verifier is pinned to the kept flow so token exchange still validates.
Also add local dev/test tooling:
- src/dev/mcp-oauth-test-server: a zero-dependency OAuth AS + MCP
StreamableHTTP server for exercising the flow locally, with
fault-injection flags (--auto-deny, --slow-authorize, --code-ttl).
- src/extension.ts: a debug-only globalThis.__clineHandleUri hook (gated
on CLINE_CAPTURE_BROWSER) so the debug harness can deliver simulated
vscode:// OAuth callbacks; documented in the harness README.
Bedrock requests built by the SDK adapter dropped the AWS region and
authentication mode, so a pasted Bedrock API key (awsBedrockApiKey +
awsAuthentication "apikey") was silently ignored and requests fell
through to the SigV4 credential chain with no region.
Two bugs, both verified end-to-end against a live Bedrock endpoint via
the debug harness:
1. The SDK ProviderConfig was built with only providerId/modelId/apiKey/
baseUrl. New bedrock-config.ts maps the legacy ApiConfiguration onto
the SDK's structured region + aws block (including the webview's
"credentials" radio -> SDK "iam"), wired into both inference paths
(buildSdkProviderConfig for utility calls, buildSessionConfig for the
main task loop).
2. The main chat path's gateway config is built by core from the
providers.json `stored` entry, which the session's providerConfig does
not override. A stale Bedrock entry (e.g. a legacy migration with
region us-east-1 + SigV4 keys) silently won, sending requests to the
wrong region (403). buildSessionConfig now persists the
StateManager-derived Bedrock settings to providers.json so `stored` is
authoritative. The bearer apiKey is only persisted for api-key auth to
keep stored clean for profile/iam.
Also documents the ELECTRON_RUN_AS_NODE debug-harness gotcha in
.clinerules/general.md.
The nightly 'vscode test' job (npm run ci:build -> build:webview -> tsc -b) failed on both Linux and windows-latest:
ZAiProvider.tsx: Argument of type 'Event | FormEvent<HTMLElement>' is not assignable to parameter of type 'Event'
VSCodeDropdown's onChange supplies 'Event | React.FormEvent<HTMLElement>', but the getEventValue helper (added when the zai provider was moved to providers.json) was typed to accept only Event. The helper only reads target.value, which exists on both, so widen the parameter to the same union the dropdown provides.
Note: this only surfaces under 'tsc -b' / 'tsc --noEmit -p tsconfig.app.json'; the webview's root tsconfig.json is a solution file with files:[] so a bare 'tsc --noEmit' checks nothing.
The separate 'test / test' job failure is an aggregate gate that fails because vscode-test failed; fixing this resolves it too.
The nightly CI 'Unit Tests with coverage - Linux' step (npm run test:unit) failed in ts-node compilation:
state-keys.ts: Module 'vscode' has no exported member 'LanguageModelChatSelector'
This surfaced as a misleading 'Cannot find package @shared/...' ERR_MODULE_NOT_FOUND: Mocha tried require() first (which threw the ts-node TSError), then fell back to import(), whose ESM resolver cannot resolve the @shared/* path alias.
tsconfig.unit-test.json is driven by ts-node, which defaults to files:false and compiles modules on demand from their imports. The loose ambient augmentation in src/types/vscode-language-model.d.ts was therefore never loaded, so state-keys.ts failed to compile.
Set ts-node.files=true and add src/types/**/*.d.ts to include so the augmentation is part of the unit-test program. Mirrors the earlier tsconfig.test.json fix for the separate build toolchain.
The nightly CI "Build Tests and Extension" step (npm run ci:build) failed
in compile-tests (tsc -p tsconfig.test.json) with:
getVsCodeLmModels.ts: Property 'lm' does not exist on type 'typeof import("vscode")'
state-keys.ts: Module '"vscode"' has no exported member 'LanguageModelChatSelector'
@types/vscode is pinned to 1.84.0, which predates the Language Model API.
The repo compensates with an ambient augmentation in
src/types/vscode-language-model.d.ts, which the main tsconfig picks up via
its 'src/**/*' include. tsconfig.test.json overrides include to only
'src/**/*.test.ts'; listing src/types under typeRoots does not load a loose
.d.ts (typeRoots only auto-loads @types-style package folders), so the
augmentation was missing from the test program.
Add 'src/types/**/*.d.ts' to tsconfig.test.json include so the augmentation
is part of the test compilation.
The completion signal (attemptCompletionSeen) was scoped to the message
translator's per-iteration reset(), so a turn that called the completion tool
and then ran another iteration before 'done' lost the signal — the turn ended
as awaiting_followup instead of completed and the footer showed no
'Start New Task' button despite the green Task Completed box.
Make the completion signal turn-scoped: reset() only clears streaming pointers;
a new clearTurnOutcome() clears it at genuine turn/task boundaries (initTask,
reinitExistingTaskFromId, askResponse). Also recognize the SDK's built-in
submit_and_exit completion tool (summary field) alongside the VSCode
attempt_completion tool (result field).
Removes the webview-message-state design/findings docs and rewrites the
related comments to describe the system as-is.
Webview now gates turnState by seq (a stale snapshot can no longer revert
streaming->idle), never empties a live transcript on a lone newer-epoch partial,
and routes a follow-up after completed/awaiting_followup to askResponse instead
of starting a new task.
Backend phase emission fixes surfaced by live testing:
- post state on turn end even when the done event carries no messages
- askResponse sets phase=streaming (resume/continue shows Cancel, unblocks send)
- a post-cancel turn-complete straggler no longer clobbers resumable
Adds reducer, send-routing, and session-event-coordinator unit tests. See
src/sdk/docs/webview-message-state-design.md §11 for the full debugging log.
S7 (a + c) of the message-state redesign — removes two order-dependent hacks now that
TurnState is authoritative.
(a) ask_question / ask_followup_question are suppressed from the generic say:"tool"
renderer (both content_start and content_end). The SdkInteractionCoordinator services
these and emits the proper ask:"followup"; the generic tool row was an orphan partial
that never finalized and defeated the tail heuristics. The CLI already does this.
(c) The `done` handler no longer synthesizes a trailing ask:"completion_result" — that
was the "must be last message" hack (ENG-1887) that existed only because the webview
inferred UI mode from the array tail. `done` now emits no transcript message and only
signals turnComplete; the webview reads phase from TurnState (completed when
attempt_completion was used, else awaiting_followup). The green "Task Completed" box
still comes from the say:"completion_result" emitted at attempt_completion content_end.
Translator unit tests updated to the new contract (done → 0 messages, turnComplete=true).
Deferred to a follow-up (lower risk if left): (b) collapsing the approval ask onto the
streaming tool's id (needs cross-coordinator id threading), and (d) the mistake_limit
forced abort (now harmless since phase is authoritative). The persisted-history renderer
still appends its own trailing ask so reopened tasks show the resume affordance —
intentional.
428 SDK unit tests pass; tsc + biome clean.
S6 of the message-state redesign. sdkHost.abort() is cooperative — the SDK can emit a
few more events after it. Previously cancelTask aborted first and only the (post-abort)
!isRunning filter stripped two trailing ask types, letting say:* stragglers land after
the resume_task ask and wedge the UI.
Now cancel raises the fence SYNCHRONOUSLY before the abort:
- SdkController.cancelTask sets turnState.phase = "resumable" (already in S4), then
- SdkTaskControlCoordinator.cancelTask calls raiseCancelFence() (epoch bump) BEFORE
awaiting sdkHost.abort().
Any event the SDK emits after the abort request therefore carries the OLD epoch and is
dropped by the webview's convergent reducer; the authoritative phase is "resumable"
(Resume Task), independent of the message tail. Order matters and is covered by a unit
test (fence before abort).
Usage accounting is exempt from the fence — it was never gated by the message filter, so
a post-cancel usage event still bills the tokens the provider actually generated.
The legacy !isRunning ask-only filter is now redundant but kept as defense-in-depth.
428 SDK unit tests pass; tsc + biome clean.
S5 of the message-state redesign. The webview decided "thinking vs approving vs done"
and which buttons to show by inspecting the TAIL of clineMessages. Because the backend
appends bookkeeping (api_req_started usage) after content and even after approval asks,
the tail routinely meant the wrong thing — producing stuck "Thinking", vanishing
Approve/Reject, and the footer disagreeing with the buttons (RC1, reproduced on camera).
Now the webview reads the authoritative backend-owned TurnState (added in S4):
- buttonConfig: add buttonsForPhase(turnState, anchoredMessage) and the dispatcher
getButtonConfigFromState(messages, turnState, mode). The button SET is chosen by phase;
approval labels (Approve vs Save, Run Command, MCP, subagents) come from the anchored
message (turnState.anchorTs). When turnState is absent (classic/older state) it falls
back to the legacy tail-walking getButtonConfigForMessages.
- ActionButtons reads turnState from useExtensionState and uses getButtonConfigFromState.
- MessagesArea.isWaitingForResponse short-circuits to `phase === "streaming"` when
turnState is present (and only shows the footer loader until a content row is actually
streaming); the legacy tail inference is kept as the fallback.
Button actions (approve/reject/proceed/new_task) already send a fixed responseType
independent of clineAsk, and the SDK backend resolves the pending approval/followup
promise — so routing is correct under TurnState. Classic fallback paths are untouched.
New unit tests cover buttonsForPhase (every phase + anchored-label selection +
mistake_limit-vs-api_req_failed) and getButtonConfigFromState (prefers TurnState over a
trailing bookkeeping tail; legacy fallback). 68 webview chat tests pass; tsc + biome clean.
S4 of the message-state redesign. Introduces the single source of truth for the
webview's UI mode so it no longer has to be inferred from the tail of clineMessages
(the root of RC1: missing/stuck "Thinking", vanishing approval buttons, footer and
buttons disagreeing).
- Add TurnPhase / TurnState to shared types and ExtensionState.turnState (rides inside
state_json; no proto change).
- Add TurnStateTracker, owned by SdkController, sharing the one id/seq/epoch authority.
Each transition stamps a fresh seq so the webview keeps only the newest TurnState.
- Set the phase at the exact lifecycle points where the backend knows it:
streaming — initTask / reinit / user responded (resolvePending*)
awaiting_approval — handleRequestToolApproval (anchored on the ask)
awaiting_followup — handleAskQuestion; and a turn that ends WITHOUT attempt_completion
completed — turn ends and attempt_completion was used
error — onSendError; mistake_limit
resumable — cancelTask (set before abort)
idle — clearTask
The completed-vs-awaiting_followup decision uses
MessageTranslatorState.wasAttemptCompletionSeen().
- getStateToPostToWebview now ships turnState in every snapshot.
This is ADDITIVE: the webview does not read turnState yet (S5 wires footer/buttons to
it and deletes the tail heuristics). Classic/legacy paths leave turnState undefined and
keep the legacy behavior. 427 SDK unit tests pass (incl. new turn-state-tracker tests);
tsc and biome clean.
S3 of the message-state redesign. The webview received the same conversation over
two unordered, fire-and-forget channels — incremental partial messages and full
state snapshots — and the state handler REPLACED clineMessages wholesale ("// HACK:
Preserve clineMessages if currentTaskItem is the same"). A stale snapshot captured
before the last message landed could clobber the transcript, dropping the final
message and leaving the UI stuck on "Thinking…" (reproduced earlier on camera).
Introduce a pure convergent-replica reducer (messageReducer.ts) keyed on the three
extension-stamped quantities from S2:
- ts : identity / merge key
- seq : freshness (higher seq wins for the same ts)
- epoch : conversation/replica fence (newer replaces, older is dropped, equal merges)
applyMessage / applyStateSnapshot are total and side-effect free:
- older epoch -> drop (straggler from a previous task/render)
- newer epoch -> replace the transcript wholesale (new task / history load)
- same epoch -> merge by ts keeping the higher seq; a snapshot may ADD/UPDATE
rows but NEVER truncate, so it can't drop a message the partial
stream already delivered. Stale (older stateVersion) snapshots are
ignored wholesale.
ExtensionStateContext now feeds both subscription callbacks through the reducer via a
replicaRef, replacing the wholesale-replace HACK and the findLastIndex append. Classic/
legacy state is unstamped (epoch 0 / version 0) and merges by ts exactly as before.
Tests (messageReducer.test.ts): deterministic cases mapping 1:1 to the bugs (stale
snapshot must not shrink the transcript; lower-seq ignored; partial->final in place;
older-epoch straggler dropped; older-version snapshot ignored), PLUS an
order-independence proof — all 120 permutations of a causal log, with duplication and
with non-final drops, converge to the same canonical state. This is the high-confidence
guarantee that the webview cannot get stuck regardless of delivery timing.
62 webview chat tests pass; tsc and biome clean.
S2 of the message-state redesign. Lays the groundwork for the convergent-replica
webview reducer (S3) so the webview can never get stuck on stale/out-of-order
delivery.
Stamping (extension-owned, synchronous, from the single MessageIdMinter):
- Every ClineMessage flowing to the webview is stamped in SdkMessageCoordinator with
a fresh `seq` (freshness) and the current `epoch` (conversation/replica fence),
before it is stored or emitted. The same object references go to both the message
state handler and the partial-message stream, so both channels carry identical
stamps. An updated message (partial -> final, same ts) passes through again and
gets a higher seq, so the freshest copy always wins regardless of arrival order.
- Every state snapshot is stamped in SdkController.getStateToPostToWebview with a
fresh `stateVersion` (sampled from the same counter) and the current `epoch`.
- `epoch` is bumped at every conversation boundary via a new
resetMessageTranslatorAndFence() wired into the existing resetMessageTranslator
sites (task start/clear, history open, reinit, mode rebuild, new-session
follow-up). iteration_start streaming resets do NOT bump it.
Transport:
- ClineMessage proto gains seq/epoch (fields 24/25) and the conversions carry them.
- ExtensionState gains stateVersion/epoch (ride inside state_json, no proto change).
Fire-and-forget delivery:
- sendPartialMessageEvent and sendStateUpdate no longer await postMessage to the
webview. A hidden/reloaded/closed webview can make postMessage hang or resolve
false; awaiting it could stall the backend turn loop. Correctness no longer
depends on any single delivery — the webview will be a convergent replica (S3).
All new fields are optional/default-0 so the classic/legacy path is unaffected.
Cancel's epoch bump + fence-before-abort and the remaining one-off Date.now() mint
sites are handled in later steps (S6/S2-tail). 423 unit tests pass; tsc clean.
Message ids (ClineMessage.ts) were minted from Date.now() in two independent
generators: the live message translator (pure ++counter seeded once) and the
interaction coordinator (Math.max(Date.now(), last+1)). Because the translator
counter drifts behind wall-clock, it can later catch up to a clock-based id
minted by the interaction coordinator, producing colliding ids for different
messages. That breaks any merge-by-id scheme on the webview side.
Introduce a single process-wide MessageIdMinter (pure monotonic id/seq/epoch
counters, never reads the clock) owned by MessageTranslatorState and shared by:
- live SDK event translation,
- the interaction coordinator (tool approval / ask_question / user_feedback),
- history rendering (sdkMessagesToClineMessages).
This makes every id globally unique within the process, so regenerated history
ids never overlap live-session ids. Behavior is otherwise unchanged.
Also adds the message-state pipeline design + investigation docs under
src/sdk/docs.
S1 of the message-state redesign; seq/epoch stamping and the remaining one-off
Date.now() mint sites follow in S2.
After inspecting the SDK's generic models-URL fetcher
(sdk/packages/core/src/services/providers/model-source.ts
`fetchModelIdsFromSource` + `resolveModelsSourceUrl`), update the TODOs on the
bespoke refresh*Models handlers to capture the real constraint discovered:
- The SDK fetcher exists and is provider-agnostic, but returns model *ids only*
(unknown ids get placeholder ModelInfo with no real pricing/capabilities).
- `mergeKnownModels` treats a registered `modelsSourceUrl` as the authoritative
"installed" list (Ollama/LM Studio semantics) and DISCARDS the curated catalog
when the live fetch returns results.
So simply registering `modelsSourceUrl` for Groq/Baseten/Hicap/HuggingFace/
Vercel/OpenRouter would regress rich model metadata. Proper consolidation needs
an SDK enhancement first (merge-mode or richer per-provider parsing), then the
extension handlers + RPCs can be deleted. refreshGroqModels.ts carries the
detailed note; the others reference it.
refreshClineRecommendedModels now delegates the HTTP fetch + response
normalization + offline fallback to the SDK's fetchClineRecommendedModels
(@cline/core), removing ~80 lines of duplicated logic. The extension wrapper
keeps its distinct behavior: the CLINE_RECOMMENDED_MODELS_UPSTREAM feature-flag
gate, the in-memory TTL cache, and in-flight dedup. The proxy-aware fetch
(@/shared/net) and the configured apiBaseUrl are passed through to preserve
network/proxy behavior. The SDK's offline fallback list is identical to
CLINE_RECOMMENDED_MODELS_FALLBACK, so offline behavior is unchanged.
Because the module now imports the ESM-only @cline/core, its unit test moves
from mocha to vitest (joining the other SDK-touching models tests): added to
vitest include + mocha ignore, and fetchClineRecommendedModels added to the
vitest @cline/core stub (and the mocha/integration @cline/core mocks for
completeness). Rewrote the test vitest-native, asserting flag-gate, delegation,
and flag re-check.
Also:
- Add TODO(sdk-consolidation) notes to the remaining bespoke live-model-refresh
handlers (Groq, Baseten, Hicap, HuggingFace, Vercel AI Gateway, OpenRouter)
documenting the path to share them with the CLI via the SDK (register
modelsSourceUrl) and then delete the extension-only handlers + RPCs. These
are NOT migrated yet because the SDK does not currently live-fetch those
providers (only ollama/lmstudio register modelsSourceUrl), so deleting them
today would regress to the curated catalog.
- Remove an unused local type (RuleLoadPart) found while reviewing biome
noUnusedVariables output.
tsc --noEmit clean; vitest 439 passing.
- services/telemetry/events/EventHandlerBase.ts: abstract base for telemetry
event handlers whose concrete subclasses were removed with the classic task
code; no remaining references (it was the only file left in events/).
- services/auth/AuthServiceMock.ts: test mock with no importers after the
associated test was deleted.
Note: the rest of services/* (TelemetryService, McpHub, FeatureFlagsService,
ErrorService and their IFoo interfaces) IS live — the interfaces only looked
unreachable to the esbuild oracle because they're consumed via type-only
imports (erased at emit). Verified via importer cross-check; tsc + vitest green.
- Delete src/utils/cost.ts (+ test): calculateApiCostAnthropic/OpenAI/Qwen had
no consumers left after the provider handlers were removed (only the test
referenced them).
- Remove createOpenAIClient from src/shared/net.ts (no remaining callers) and
its now-unused openai + EnvUtils imports. The proxy-aware fetch and
getAxiosSettings exports remain.
tsc --noEmit clean, vitest 436 passing.
Remove dependencies that became unused after the legacy API provider handlers
and tree-sitter service were deleted (no remaining imports in src, webview, or
build config):
@anthropic-ai/vertex-sdk, @aws-sdk/client-bedrock-runtime,
@aws-sdk/credential-providers, @azure/identity,
@cerebras/cerebras_cloud_sdk, @google-cloud/vertexai, @mistralai/mistralai,
@sap-ai-sdk/ai-api, @sap-ai-sdk/orchestration, @sap-cloud-sdk/connectivity,
ollama, tree-sitter-wasms, web-tree-sitter
Also remove the now-dead copyWasmFiles esbuild plugin (it only copied
tree-sitter WASM files for the deleted code-definition service). Kept openai,
@anthropic-ai/sdk, @google/genai, and aws4fetch — still imported by live code.
Verified: extension + standalone esbuild builds succeed, tsc --noEmit clean,
vitest 436 passing.
The previous deletion commit (2c9bd62) removed
core/assistant-message/parse-assistant-message.ts and
core/permissions/CommandPermissionController.ts, but the corresponding barrel
edits (removing their re-exports from index.ts) were dropped by lint-staged's
stash and never committed, leaving HEAD referencing deleted modules. Remove the
dead re-exports so the barrels only export live members.
Computes src files unreachable from the shipped entry points (extension host + standalone host used by JetBrains/CLI) plus webview shared refs, using esbuild metafile reachability. Used to drive the post-SDK-migration dead-code deletions; keep for future pruning. Note: results still need a tsc-gated importer cross-check because esbuild drops import-type-only edges.
Removes additional source files unreachable from any shipped entry point
(extension host, standalone host, webview) after the SDK migration, verified
via esbuild reachability + a per-file importer cross-check that excludes any
file still referenced by a live non-test survivor or generated/test glue, then
gated on tsc --noEmit + vitest (436 passing):
- services/ripgrep, integrations/notifications, utils/string, utils/tabFiltering
- core/assistant-message/parse-assistant-message
- core/hooks: hook-model-context, notification-hook, precompact-executor,
PreToolUseHookCancellationError
- core/permissions/CommandPermissionController
- core/workspace/detection
- integrations/claude-code: run, message-filter
- integrations/editor: FileEditProvider, detect-omission
- integrations/misc: extract-file-content, extract-images
Dropped the now-dead re-exports from core/assistant-message/index.ts and
core/permissions/index.ts (those barrels stay; they still export live types
used by generated host glue).
src/services/tree-sitter/** (language parsers + queries for the classic
list_code_definition_names path) is unreachable from any shipped entry point
after the SDK migration. Verified via scripts/find-dead-src.mjs (esbuild
reachability from extension + standalone entries, plus webview shared refs) and
an importer cross-check (no live value or type importers), gated on
tsc --noEmit + vitest (436 passing).
The classic system-prompt builder (core/prompts/system-prompt/**), the
deep-planning prompt variants, core/prompts/commands.ts, and the
core/slash-commands handler are no longer reachable from any shipped entry
point (extension host, standalone host, or webview) after the SDK migration:
the SDK provides prompt construction (buildClineSystemPrompt) and slash-command
handling. Removed them and their orphaned tests.
Kept core/prompts/responses.ts (still live) and its tests.
Dead-code reachability was computed with scripts/find-dead-src.mjs (esbuild
metafile reachability from src/extension.ts + src/standalone/cline-core.ts,
plus webview src/shared references), then gated on tsc --noEmit + vitest.
Now that buildApiHandler routes through the @cline/llms SDK, the legacy
per-provider handler classes and their supporting code are unused. Remove them:
- apps/vscode/src/core/api/providers/** (all 40+ handler classes, types, tests)
- apps/vscode/src/core/api/transform/** except stream.ts (format/stream/
tool-call helpers only the handlers used)
- apps/vscode/src/core/api/utils/** (messages/responses API support)
- apps/vscode/src/core/api/retry.ts (+ test)
- apps/vscode/src/shared/sdk-handler-models.ts (getProviderModelFromSdk;
only the deleted handlers' getModel() used it)
core/api now contains just index.ts (types + SDK re-exports), transform/stream.ts
(ApiStream types still referenced by the local ApiHandler interface), and
adapters/.
Supporting changes to keep everything compiling/working:
- context-window-utils: drop the dead `api instanceof OpenAiHandler` DeepSeek
branch (handlers are SDK GatewayApiHandlers now); the 64k switch case already
handles DeepSeek context sizing.
- Relocate fetchLiteLlmModelsInfo from the deleted litellm handler into
core/controller/models/fetchLiteLlmModels.ts (used by refreshLiteLlmModels).
- Move the `declare module "vscode"` Language Model API augmentation (previously
carried by the vscode-lm handler) into src/types/vscode-language-model.d.ts so
live consumers (getVsCodeLmModels, vsCodeSelectorUtils) keep their types.
- Move the @google/genai test mock out of the deleted providers dir to
src/test/fixtures/google-genai-mock.ts and repoint test-setup.js.
Replace the legacy per-provider buildApiHandler factory with an SDK-backed
handler (apps/vscode/src/sdk/sdk-api-handler.ts) built via @cline/llms
createHandler(). The two standalone callers (commit-message generation and
explain-changes) now import buildApiHandler directly from the SDK module;
@core/api stays types-only (re-exporting SDK types) so it can keep being
imported widely without pulling the SDK runtime graph into activation.
Also:
- Delete the now-dead OpenRouterHandler and its test (createOpenRouterStream
stays; it is still used by ClineHandler).
- buildSdkProviderConfig never sends both reasoning.effort and
reasoning.max_tokens (some providers reject it), and supports
disableReasoning for fast one-shot utility calls; commit-message and
explain-changes opt in.
- commit-message generation surfaces the real SDK stream error instead of a
generic "empty API response".
- getGitDiff: run git diff --staged even before the first commit; only gate
the git diff HEAD fallback on having commits (fixes "no changes" for the
initial commit of a new repo).
- Delete refreshClineModels.ts, refreshClineModelsRpc.ts, and test
- Remove refreshClineModelsRpc proto RPC
- Remove clineModels state from ExtensionStateContext, StateManager cache, disk
- ClineModelPicker and useOnboardingModels use SDK catalog directly
- Replace ThinkingBudgetSlider with ReasoningEffortSelector for Cline provider
- Use supportsReasoning from SDK catalog instead of hardcoded model names
- Add ProviderReasoningPatch to proto and ProviderConfigPatch contract
- Wire reasoning effort changes through writeProviderConfig to SDK ProviderSettingsManager
- Remove hardcoded Claude switch in openrouter-stream.ts
- Add supportsReasoning to supportsReasoningEffort check in openrouter-stream
The mocha unit-test harness stubbed @cline/llms with an empty catalog, so the SDK-migrated provider handlers (which read the real catalog) failed ~51 tests under the nightly suite.
- src/test/requires.ts now loads the real @cline/llms by resolving its package directory and requiring the ESM entry by absolute path (Node 22 require(esm)), bypassing the package's import-only exports map. This restores real catalog data to provider unit tests.
- vertexModelSupportsGlobalEndpoint: also match legacy ':' context-window/speed suffixes (e.g. claude-opus-4-7:1m), not just '@' snapshot variants.
- refreshClineModels: derive prompt-cache support from reported input_cache_read pricing for any provider, not just openai/google prefixes.
- Delete the failing tests for the classic provider handlers (bedrock cross-region/native-tool-calling, gemini metadata, cline/openrouter qwen cache, wandb unknown-model). These handlers are only reached via buildApiHandler (explain-changes + commit-message generation) and the provider/catalog domain is owned and tested by the SDK; they will be removed when buildApiHandler is retired.
The nightly publish runs the full webview-ui suite and the Windows extension suite, which surfaced failures the extension-only run does not.
- Harden useProviderModels against a missing providerModelsByProvider map so a partially-mocked ExtensionStateContext no longer crashes the hook.
- Update the SapAiCoreModelPicker and APIOptions specs to provide the provider model-list context the components now read from the SDK catalog, and seed the model ids each test asserts. Removes the now-dead @shared/api sapAiCoreModels mock.
- Compare resolveDataDir() against path.join() instead of a hardcoded POSIX path so the CLINE_DIR fallback test passes on Windows.
Selecting the OpenAI Compatible provider failed with 'Unknown provider "openai"', and manually entered model ids were displayed as the catalog default (gpt-4o).
- Map the extension's 'openai' provider id to the SDK's 'openai-compatible' built-in at the SDK boundary (toSdkProviderId), and convert before handing the provider id to core when building a session config.
- Treat openai-compatible as a custom-model-id provider so model resolution honors a user-entered model id instead of coercing it to the catalog default. Adds providerAllowsCustomModelIds() as the shared signal.
- Bump @cline/core, @cline/llms, @cline/shared, @cline/agents to ^0.0.42 (which registers the openai-compatible built-in) and dedupe the dependency tree.
- Carry the tool name on reconstructed Anthropic-format tool_result blocks to satisfy the SDK's ToolResultContent contract.
- Update tests for the refreshed SDK model catalog (Gemini default).
- Remove porting scree: docs/sdk-model-catalog/* planning docs, TODO-resume-session.md, and stale doc references in code/comments.
- Rewrite before/after narrative comments in the 'eternal now' style; drop transient 'Step N'/'Phase N' labels.
- Remove leftover [HistoryPerf] diagnostic logging and a dead try/catch rethrow; minor readability/naming.
- Restore .clinerules/network.md (still relevant) and update sdk-migration.md to drop dangling references.
- Fix latent circular-init TDZ in openai-codex-models (lazy catalog build).
- toggleRemoteConfigSetting no longer returns a never-resolving promise.
- Move vitest config into apps/vscode and rename script test:sdk -> test:vitest; wire it into CI.
- Repair/reimplement the SDK-adapter vitest suites (auth-service, provider-migration, sdk-task-history) to match current behavior; all 432 tests pass.
Migrates the vscode extension off its hand-curated static model catalogs
in apps/vscode/src/shared/api.ts and on to the @cline/llms SDK as the
single source of truth for provider/model metadata, end-to-end across
the extension host and the webview.
Net impact on the static catalog file:
apps/vscode/src/shared/api.ts: 5092 -> 468 lines (~90% gone).
What changed at each layer
--------------------------
SDK / catalog plumbing (apps/vscode/src/sdk/model-catalog/):
- New `ProviderCatalog.peekModels(providerId)` synchronous cache read.
- `resolveModelInfo` rewritten: committed selection -> catalog peek
-> await catalog.resolveModels on cache miss. No race with a
background warmer; if the catalog truly has nothing, returns
source: "unknown" and the webview renders a neutral loading state.
- `applyHostModelInfoOverrides` is the canonical seam for the few
fields the SDK does not yet carry. Today it carries only the Vertex
`supportsGlobalEndpoint` allowlist (vertex-global-endpoint.ts, with
a TODO to upstream into the SDK).
- `ProviderListing` extended with SDK metadata (`is_popular`,
`popular_rank`, `usage_cost_display`, `capabilities[]`) and plumbed
through proto + conversion.
Extension-host handlers (apps/vscode/src/core/api/providers/):
- New shared helper `apps/vscode/src/shared/sdk-handler-models.ts`:
`getProviderModelFromSdk(providerId, requestedModelId, committedInfo?)`
returns `{ id, info }` from `getProviderCollectionSync` with
Vertex global-endpoint overrides applied.
- 27 handlers converted to a one-liner `getModel()` through that
helper. Per-handler nuances preserved:
* Anthropic: strips `:fast` and `:1m` host-side suffixes before
SDK lookup; carries them back on the returned id so the
per-request betas still flip.
* Bedrock: keeps the custom Application Inference Profile ARN
branch; base-model info from the SDK.
* Cerebras: keeps the `qwen-3-coder-480b-free` -> `qwen-3-coder-480b`
paid alias.
* Qwen / ZAi: SDK has a single catalog each; handlers keep the
regional base-URL switch but no longer fork the catalog.
* Wandb: keeps the "unknown id falls through to safe defaults"
escape hatch via `MODEL_COLLECTIONS_BY_PROVIDER_ID`.
Refresh-models background tasks:
- `refreshBasetenModels`, `refreshGroqModels`, `refreshHuggingFaceModels`
source their offline-fallback catalog from the SDK via
`getProviderCollectionSync` + `adaptSdkModelInfo`. Live fetch path
unchanged; only the seeding/fallback data changed.
Webview (apps/vscode/webview-ui/):
- `useNormalizedApiConfiguration` always routes through gRPC
`resolveModelInfo`. Removed the `isMigratedSdkProvider` /
`MIGRATED_SDK_PROVIDER_IDS` feature flag and the legacy
`normalizeApiConfiguration` switch entirely.
- New `useStaticProviderSelection` hook for the 22 settings
components whose catalog is now SDK-driven, and
`useDynamicProviderSelection` for the 12 dynamic-list pickers
(openrouter, cline, openai-compatible, ollama, lmstudio, requesty,
litellm, hicap, groq, baseten, huggingface, vercel-ai-gateway,
aihubmix, oca, huawei-cloud-maas, dify, fireworks, together,
vscode-lm) so all of them stop calling the legacy switch.
- `ModelInfoView` reads its `isGemini` check via
`useProviderModels("gemini")` instead of importing `geminiModels`.
- `App.stories.tsx` ships a small inline fixture instead of
importing `bedrockModels`.
- `ExtensionStateContext` no longer seeds `groqModelsState` /
`basetenModelsState` from the deleted catalog; the slices start
empty and the SDK-curated catalog is layered in by the pickers at
render time.
Misc:
- `src/utils/model-utils.ts`: `isAnthropicModelId` consults
`MODEL_COLLECTIONS_BY_PROVIDER_ID["anthropic"]` instead of the
deleted `anthropicModels` map.
- `src/shared/storage/provider-keys.ts`: `getProviderDefaultModelId`
no longer hard-codes 24 per-provider defaults. The function now
consults the SDK catalog and only keeps an override map for
providers whose default is intentionally not the SDK default
(openrouter-shared dynamic providers and local-only providers).
- `src/shared/openai-codex-models.ts`: relative path for
`shape-adapter` import so both the extension and webview build
contexts resolve it identically.
Tests retargeted to assert SDK behavior, not static-map shapes
--------------------------------------------------------------
- claude-code, anthropic, bedrock, vertex, wandb, provider-keys
test suites had assertions tied to deleted shapes. Rewrote them
to either assert through the SDK catalog
(anthropic compares against `adaptSdkModelInfo(sdkCollection.models[id])`,
wandb uses the SDK-declared default, etc.) or focus on the
host-side semantics (bedrock's "global endpoint" block now tests
`vertexModelSupportsGlobalEndpoint` directly).
- claude-code test trimmed its 8 `[1m]`/version-pin variants down
to three SDK-shaped cases. The 8 deleted assertions exercised
extension-only model-id derivations that the SDK does not carry;
matching the CLI's behavior was the explicit goal.
- resolveModelInfo test rewritten around the new peek -> await
-> unknown contract.
- proto-lint: added missing `go_package` option to
`proto/cline/remote_config.proto`.
Verification (npm scripts under apps/vscode/):
- npm run protos OK
- npm run check-types OK (apps/vscode + apps/vscode/webview-ui)
- npm run lint OK (biome + proto-lint)
- npm run build:webview OK (tsc -b && vite build)
- node esbuild.mjs OK (dist/extension.js produced)
- Runtime smoke test: 27/27 provider collections resolve from the
SDK with correct model counts, defaults, and usage-cost-display
flags. openai-codex returns cost=hide as expected; every other
provider returns cost=show.
* feat(llms,core): route custom registered handlers through the agent runtime
Expose the handler-registry helpers (hasRegisteredHandler, getRegisteredHandler,
getRegisteredHandlerAsync, isRegisteredHandlerAsync) from @cline/llms, and have
core's createAgentModelFromConfig consult the registry: when a handler is
registered for a provider, build it via createHandler and adapt its ApiHandler
surface onto the AgentModel contract (the inverse of the gateway's
toApiStreamChunk).
This lets hosts register provider handlers that need host-only dependencies
(e.g. a vscode.lm-backed handler) and have them used by the main agent loop,
not just standalone createHandler callers.
* fix(core): resolve registered handlers lazily and avoid double finish
Address review feedback:
- createAgentModelFromConfig built the handler eagerly with the sync
createHandler, which throws for providers registered via registerAsyncHandler.
The adapter now accepts a handler factory and resolves it on the first stream
via createHandlerAsync, supporting both sync- and async-registered handlers.
- Guard the adapter's catch-block finish with sawFinish so a handler that emits
an explicit done chunk and then throws does not produce two finish events.
* fix(core): preserve thought signatures and finish-reason semantics in adapter
Further review feedback on the ApiHandler -> AgentModel adapter:
- Reasoning and tool-call thought signatures are now surfaced under
metadata.thoughtSignature (the key downstream adapters read), instead of being
stored as metadata.signature / dropped.
- A done chunk whose incompleteReason indicates max output tokens now maps to
finish{reason:"max-tokens"} rather than "stop".
- A turn that ends with tool calls (no explicit done) now terminates as
finish{reason:"tool-calls"}, matching the gateway/AI-SDK adapters.
* Apply remaining changes
* fix(core): report lazy handler-factory rejection as a finish(error) event
The lazy handler resolution (await source()) ran outside the adapter's
try/catch, so a rejecting factory (e.g. when the host API is unavailable at
stream time) escaped as a raw generator exception instead of a terminal
finish{reason:"error"} event. Move the resolution inside the try block so all
failure paths converge on the same terminal finish.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
- user's who are signed in with oauth in old extension were not properly
migrating their token. this commit handles that
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
* docs(sdk): add custom model provider plugin example
Add an OpenRouter-backed example plugin demonstrating the providers
capability and registerProvider. It registers an OpenAI-compatible
provider plus its model catalog with the gateway so the agent can run
inference against an endpoint Cline does not bundle.
Registers under a distinct id (openrouter-plugin) to avoid colliding
with the built-in openrouter provider.
* docs(sdk): drop redundant provider section from plugin examples readme
* docs(sdk): drop provider demo line from plugin examples readme
* fix: support plugin model providers
* docs: remove provider plugin demo
* docs: address provider example review
* Move the apps to the root dir
* Update all references from sdk/apps/ to apps/
* Update dependencies
* Install bun types
* Fix types
* Fix types
* Fix linter
* Ingore apps from vscode
* Fix security warning
* Fix windows install
* Enable windows dev mode
* Revert "Enable windows dev mode"
This reverts commit a46c99282e.
* Revert "Ingore apps from vscode"
This reverts commit 47f7b265d2.
* Revert "Fix windows install"
This reverts commit 1dabba1556.
* update the repo root
* fix root dir
* fix path
* fix other path
* Fix unrelated changes
* fix: address apps move follow-up blockers (#11228)
* fix: update root app command paths
* fix: include moved apps in root checks
* fix: clean up moved app path references
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
- Fold provider/model setup into a single `cline` run; drop the auth command
- Remove the /yolo on step from the Telegram setup
- Present scheduling as two clear options (Telegram chat vs terminal with
delivery flags)
- Clarify how to find the schedule id before triggering a test run
* docs(cli): add supply-chain scan alerts sample
Walkthrough for scheduling the Cline CLI to run Perplexity's Bumblebee
scanner and deliver compromise alerts to Telegram. Covers installing the
CLI, cloning/building Bumblebee and how it stays read-only, the Telegram
connector, and creating a scheduled scan that texts a clean/alert verdict.
* docs(cli): drop unsupported --delivery-thread from supply-chain sample
* 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).
* fix: use correct base URL for Vertex AI global endpoint with Claude models
The AnthropicVertex SDK constructs the API hostname as
`${region}-aiplatform.googleapis.com`, which produces
`global-aiplatform.googleapis.com` when region is "global".
This hostname does not exist and returns 404.
Per Google Cloud docs, the correct global endpoint hostname is
`aiplatform.googleapis.com` (no region prefix). This fix overrides
the baseURL when region is "global" to use the correct hostname.
Fixes#10287
* chore: add changeset for vertex global endpoint fix
* fix: rebase on main and re-apply global endpoint baseURL override
* fix(llms): Use Google auth for Vertex Gemini
- Pass `providerConfig.gcp.projectId` through to Vertex Gemini as `googleAuthOptions.projectId`
- Disable Vertex API-key express mode when GCP project config is present so `google-auth-library` handles auth
- Add coverage for `AgentConfig.providerConfig.gcp` forwarding and Vertex Gemini provider creation
- Fix vertex model list only contains Claude models issue
* feat(core): includes tool names in tool results across messages
Updated `tool_result` content blocks to consistently include the `name` of the tool being executed. This change propagates through provider helpers and applies the new schema across all associated unit and live tests, ensuring proper tracking and logging of tool interactions within messages.
- Pass `providerConfig.gcp.projectId` through to Vertex Gemini as `googleAuthOptions.projectId`
- Disable Vertex API-key express mode when GCP project config is present so `google-auth-library` handles auth
- Add coverage for `AgentConfig.providerConfig.gcp` forwarding and Vertex Gemini provider creation
- Fix vertex model list only contains Claude models issue
* feat(runtime): track idle and pending session states
Propagate idle and pending as non-terminal session statuses across the CLI, hub records, and active-session checks. Update runtime handling so interactive sessions remain active while idle or awaiting approval instead of being treated as ended.
Removed `status` from showing up in `cline history` for now.
* hydrate: false no longer reads message files for every session.
* feat(uri): add LG task deeplink webhook integration
* feat(uri): include prompt-file path in LG task prompt
* refactor(uri): move LG webhook setup into integration service
* fix(cron): publish failed schedule execution events
Add cron runner execution event publishing for completed and failed runs.
Update connector adapters to react to failed schedule executions so clients are notified when scheduled work does not complete successfully.
* add unit tests
The new Bedrock path is not failing because credential_process is unsupported. Both old and new code use AWS SDK v3’s fromNodeProviderChain, which can load credential_process.
The practical difference is that the migrated config does not include the AWS profile name:
```
"aws": {
"region": "us-east-1",
"authentication": "profile"
}
```
There is no `"profile": "bedrock"` So the new llms provider never targets [profile bedrock]. It calls fromNodeProviderChain({ ignoreCache: true, clientConfig: { region } }), which means AWS SDK will use AWS_PROFILE if present, otherwise default.
## Cause
The migration code only migrates awsProfile when legacy awsUseProfile is true. But the old extension treats profile auth as active when awsAuthentication === "profile" too:
```
profile:
legacyGlobalState.awsAuthentication === "profile" || legacyGlobalState.awsUseProfile
? trimNonEmpty(legacyGlobalState.awsProfile)
: undefined
```
## Fixes
The migration now preserves awsProfile when awsAuthentication === "profile", even if the old awsUseProfile flag is missing. It also treats profile-based Bedrock settings as enough to migrate Bedrock without static AWS keys.
* refactor: cache global settings reads by file metadata
Avoid repeated global settings file reads by caching parsed settings and
validating the cache with path, mtime, and size. Invalidate the cache after
writes so updates remain visible, and clarify the legacy skills config name.
* refactor for performance
mtime-keyed cache of the parsed GlobalSettings — repeated reads do statSync + 4 comparisons instead of readFile + JSON.parse + zod (~30-100× speedup on hot path).
statSync(filePath, { throwIfNoEntry: false }) — avoids exception construction on missing-file path.
Cache invalidated on write — doesn't rely on filesystem mtime resolution.
loadSettingsFromDisk helper — pulls the read/parse/validate flow into one place, eliminates the previous three duplicated settingsCache = {...} assignments.
toggleDisabledTool cleaned up — single set construction + single write call, no branched copy of writeGlobalSettings.
* add unit tests for caching logic
* object freeze
All files automatically changed and formatted by `cd sdk && bun run build:models`
Generated model catalog version updated to 1779251127504
This includes the new X AI build
* fix: Speed up CLI plugin loading and config toggles
Load sandboxed plugins concurrently during initialization while preserving
existing duplicate override ordering. Update plugin tool discovery to use a
single sandbox per listing and cache descriptor results by plugin path stats,
provider, and model.
Make CLI plugin/tool config toggles persistence-only from the data loader and
update the TUI optimistically, avoiding full config reloads and repeated plugin
imports when users disable tools or plugins.
* patches
* fix: refresh plugin tools when config update lacks data
Reload config data with plugin tools included when a plugin action does not return updated data. This keeps the config view in sync and clears stale plugin tool errors after refresh.
* fix(cli): preserve config item state on missing toggle data
Only update the dialog item when toggle responses include a matching item. This avoids applying fallback enabled-state changes that can desync the UI when returned config data is missing or incomplete.
---------
Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>
All via `POST localhost:19229/api` with `{"method":"...", "params":{...}}`:
- **`launch`** / **`shutdown`** — lifecycle
- **`ui.screenshot`** — screenshot to `/tmp/cline-debug/`; returns `{path}` — **use `read_file` on the path to examine, do NOT `open` the file** (Preview.app covers the VSCode window)
- **`web.evaluate`** `{expression}` — eval in webview
- **`web.post_message`** `{message}` — send postMessage to extension host via exposed vsCodeApi
- **`wait_for_pause`** `{timeout?}` — block until breakpoint hit
- **`ui.locator`** `{role?, testId?, text?, frame?}` — Playwright locator (auto-retries on stale sidebar frame)
- **`ui.react_input`** `{text, selector?, clear?, submit?}` — set React textarea value via `execCommand('insertText')`; works reliably across multiple tasks
- **⚠️ Dismiss promotional overlays FIRST**: On fresh launches, full-screen promo overlays block the sidebar. **Dismiss immediately after `ui.open_sidebar`**, before any other interaction or screenshot. May need to run twice:
- **Screenshots — don't open the file**: `ui.screenshot` and `ui.sidebar_screenshot` save PNGs to `/tmp/cline-debug/` and return the `{path}`. Use `read_file` on that path to examine screenshots. Running `open <path>` launches Preview.app on macOS which covers the VSCode window.
- **Scripts count = 0 after launch**: CDP connects after extension host starts, so scripts parsed during startup aren't tracked. Breakpoints still work via sourcemap resolution.
- **Port 9230**: Extension host inspector. If another VSCode instance uses this port, the harness will fail to connect. Kill other debug instances first.
- **macOS only** for now (Playwright Electron launch behavior).
- **Webview CDP**: `connect_webview` may fail depending on Electron version. `web.evaluate` still works via Playwright's `frame.evaluate()` fallback.
- **Sourcemap paths**: esbuild outputs relative paths like `../src/extension.ts` in the sourcemap. The resolver handles this, but if a file isn't found, use `ext.source_files` to see exact paths.
- **OAuth with fake codes**: Browser capture intercepts the URL but doesn't provide a valid auth code. For real OAuth testing, open the captured URL in a browser. For unit testing, mock the token exchange.
See `src/dev/debug-harness/README.md` for full API reference.
@@ -13,11 +13,55 @@ This file is the secret sauce for working effectively in this codebase. It captu
**What NOT to add:** Stuff you can figure out from reading a few files, obvious patterns, or standard practices. This file should be high-signal, not comprehensive.
## Miscellaneous
- Avoid provider-specific string matching / hardcoded provider branches when fixing provider/config plumbing. Prefer provider metadata, shared catalog/defaults, explicit protocol/client capabilities, or centralized normalization utilities that apply by data shape rather than `providerId === "..."`. If a provider exception seems necessary, stop and explain why instead of adding ad-hoc string matching.
- This is a VS Code extension—check `package.json` for available scripts before trying to verify builds (e.g., `npm run compile`, not `npm run build`).
- When creating PRs, contributors should not create changelog-entry files. Maintainers handle release versioning and changelog curation during the release process.
- When adding new feature flags, see this PR as a reference https://github.com/cline/cline/pull/7566
- Additional instructions about making requests: @.clinerules/network.md
## Searching the Codebase — Avoiding Build Output
Several directories contain build output or generated code that produces
noisy or unusable results with `search_files` / `grep`:
| Directory | What it is | Why it's a problem |
|-----------|-----------|-------------------|
| `out/` | esbuild bundle output | Mirrors `src/` structure as minified JS — every search gets duplicate hits on single-line files |
| `dist/` | Packaged extension | Entire extension bundled into one minified `extension.js` (~1 long line) |
When adding a new provider (e.g., "openai-codex"), you must update the proto conversion layer in THREE places or the provider will silently reset to Anthropic:
1.`proto/cline/models.proto` - Add to the `ApiProvider` enum (e.g., `OPENAI_CODEX = 40;`)
2.`convertApiProviderToProto()` in `src/shared/proto-conversions/models/api-configuration-conversion.ts` - Add case mapping string to proto enum
3.`convertProtoToApiProvider()` in the same file - Add case mapping proto enum back to string
**Why this matters:** Without these, the provider string hits the `default` case and returns `ANTHROPIC`. The webview, provider list, and handler all work fine, but the state silently resets when it round-trips through proto serialization. No error is thrown.
**Other files to update when adding a provider:**
-`src/shared/api.ts` - Add to `ApiProvider` union type, define models
-`src/shared/providers/providers.json` - Add to provider list for dropdown
-`src/core/api/index.ts` - Register handler in `createHandlerForProvider()`
-`webview-ui/src/components/settings/utils/providerUtils.ts` - Add cases in `getModelsForProvider()` and `normalizeApiConfiguration()`
-`webview-ui/src/utils/validate.ts` - Add validation case
## Responses API Providers (OpenAI Codex, OpenAI Native)
Providers using OpenAI's Responses API require native tool calling. XML tools don't work with the Responses API.
**Symptoms of broken native tool calling:**
- Tools get called multiple times (e.g., `ask_followup_question` asks the same question twice)
- Tool arguments get duplicated or malformed
- The model responds but tools aren't recognized
**Root causes to check:**
1.**Provider missing from `isNextGenModelProvider()`** in `src/utils/model-utils.ts`. The native variant matchers (e.g., `native-gpt-5/config.ts`) call this function. If your provider isn't in the list, the matcher returns false and falls back to XML tools.
2.**Model missing `apiFormat: ApiFormat.OPENAI_RESPONSES`** in its model info (`src/shared/api.ts`). This property signals that the model requires native tool calling. The task runner in `src/core/task/index.ts` checks this and forces `enableNativeToolCalls: true` regardless of user settings.
**When adding a new Responses API provider:**
1. Add provider to `isNextGenModelProvider()` list in `src/utils/model-utils.ts`
2. Set `apiFormat: ApiFormat.OPENAI_RESPONSES` on all models that use the Responses API
3. The variant matcher and task runner will handle the rest automatically
## Adding Tools to System Prompt
This is tricky—multiple prompt variants and configs. **Always search for existing similar tools first and follow their pattern.** Look at the full chain from prompt definition → variant configs → handler → UI before implementing.
1.**Add to `ClineDefaultTool` enum** in `src/shared/tools.ts`
2.**Tool definition** in `src/core/prompts/system-prompt/tools/` (create file like `generate_explanation.ts`)
- Define variants for each `ModelFamily` (generic, next-gen, xs, etc.)
- **Fallback behavior**: If a variant isn't defined for a model family, `ClineToolSet.getToolByNameWithFallback()` automatically falls back to GENERIC. So you only need to export `[GENERIC]` unless the tool needs model-specific behavior.
3.**Register in `src/core/prompts/system-prompt/tools/init.ts`** - Import and spread into `allToolVariants`
4.**Add to variant configs** - Each model family has its own config in `src/core/prompts/system-prompt/variants/*/config.ts`. Add your tool's enum to the `.tools()` list:
**How overrides work:** Variants can override components via `componentOverrides` in their `config.ts`, or provide a custom template in `template.ts` (e.g., `next-gen/template.ts` exports `rules_template`). If no override, the shared component from `components/` is used.
**Example: Adding a rule to RULES section**
1. Check if variant overrides rules: look for `rules_template` in `variants/*/template.ts` or `componentOverrides.RULES` in `config.ts`
2. If shared: modify `components/rules.ts`
3. If overridden: modify that variant's template
4. XS variant is special—has heavily condensed inline content in `template.ts`
**After any changes, regenerate snapshots:**
```bash
UPDATE_SNAPSHOTS=true npm run test:unit
```
Snapshots live in `__tests__/__snapshots__/`. Tests validate across model families and context variations (browser, MCP, focus chain).
**See also:** `BrowserSessionRow.tsx` uses similar pattern with `isLastApiReqInterrupted` and `isLastMessageResume`.
**Backend side:** When streaming is cancelled, clean up properly (close tabs, clear comments, etc.) by checking `taskState.abort` after the streaming function returns.
## Debug Harness: clear inherited VSCode/Electron env vars before launching
The debug harness (`apps/vscode/src/dev/debug-harness/server.ts`) launches a child
VSCode via Playwright's `_electron.launch({ env: { ...process.env, ... } })`. If you
run the harness from a process that was itself spawned by VSCode (e.g. the Cline
extension host, an integrated terminal, or an agent running inside VSCode), the
parent's VSCode/Electron env vars leak into the child and break the launch.
The fatal one is **`ELECTRON_RUN_AS_NODE=1`**: it makes the child VSCode binary run
as plain Node, so it rejects every VSCode CLI flag. Symptom:
```
.../Visual Studio Code.app/Contents/MacOS/Code: bad option: --extensionDevelopmentPath=...
Error: Process failed to launch! (Playwright _electron.launch)
```
This is NOT the macOS Playwright flakiness mentioned in the harness README — it's
env inheritance. Fix: strip the inherited vars before starting the harness:
"rule":"Any new tool handler added to packages/agents/src or packages/core/src that performs a user-visible action (writes files, executes commands, modifies state, calls external APIs) must include a call to captureToolUsage() from packages/core/src/services/telemetry/core-events.ts, or emit a task.tool_used event via telemetry.capture(). Pure read-only helpers and getters are exempt. When in doubt, prefer instrumentation.",
"rule":"New session start, end, or state-transition code paths in packages/core/src must call the appropriate typed helper from packages/core/src/services/telemetry/core-events.ts (captureTaskCreated, captureTaskCompleted, captureConversationTurnEvent, captureTokenUsage, etc.). Do not inline raw telemetry.capture() calls for session lifecycle events — always use the typed helper, which guarantees a consistent payload shape.",
"scope":[
"packages/core/src/cline-core/**",
"packages/core/src/runtime/**"
"sdk/packages/core/src/cline-core/**",
"sdk/packages/core/src/runtime/**"
],
"severity":"high"
},
@@ -22,8 +25,8 @@
"id":"sdk-no-raw-event-strings",
"rule":"All telemetry event name strings must be sourced from CORE_TELEMETRY_EVENTS in packages/core/src/services/telemetry/core-events.ts. If a PR introduces a string literal in a telemetry.capture(), telemetry.captureRequired(), or recordCounter()/recordHistogram()/recordGauge() call that does not reference CORE_TELEMETRY_EVENTS, flag it. New events must be added to CORE_TELEMETRY_EVENTS first, with a typed capture helper created alongside them.",
"scope":[
"packages/core/src/**",
"packages/agents/src/**",
"sdk/packages/core/src/**",
"sdk/packages/agents/src/**",
"apps/cli/src/**",
"apps/vscode/src/**"
],
@@ -32,13 +35,17 @@
{
"id":"sdk-auth-telemetry-completeness",
"rule":"Any new OAuth or authentication provider added under packages/core/src/auth must emit all four lifecycle events using the typed helpers from core-events.ts: captureAuthStarted (at flow entry), captureAuthSucceeded + identifyAccount (on token success), captureAuthFailed (on error), and captureAuthLoggedOut (on token invalidation or explicit logout). Flag PRs that introduce a new auth flow file without all four. Cross-reference packages/core/src/auth/cline.ts and packages/core/src/auth/codex.ts as canonical examples.",
"scope":["packages/core/src/auth/**"],
"scope":[
"sdk/packages/core/src/auth/**"
],
"severity":"high"
},
{
"id":"sdk-telemetry-doc-update",
"rule":"Any PR that adds new event constants to CORE_TELEMETRY_EVENTS in packages/core/src/services/telemetry/core-events.ts, adds new capture* helper functions, or changes the payload shape of an existing event must update the Event Catalog section in DOC.md. Flag PRs that modify core-events.ts without a corresponding change to DOC.md.",
"description":"Single source of truth for all telemetry event names (CORE_TELEMETRY_EVENTS) and their typed capture helper functions. Every PR touching telemetry must be evaluated against this catalog. New events must be defined here first."
"description":"OpenTelemetry-backed provider that wires logs/metrics/traces exporters. Contains createConfiguredTelemetryService and createConfiguredTelemetryHandle, the canonical factories every host should use."
},
{
@@ -21,11 +21,11 @@
"description":"Public API and event documentation. The Event Catalog and 'Activation funnel' sections must be kept in sync with core-events.ts. Host integration rules (CLI dir ordering, hub daemon metadata forwarding) are documented here."
},
{
"path":"ARCHITECTURE.md",
"path":"sdk/ARCHITECTURE.md",
"description":"Architecture reference. Telemetry design decisions, completion semantics (submit_and_exit anchoring), and hub-daemon telemetry forwarding are documented here. Use as ground truth for design intent."
},
{
"path":"AGENTS.md",
"path":"sdk/AGENTS.md",
"description":"Package boundary rules. Telemetry runtime services live in @cline/core; @cline/agents must not own stateful telemetry. Use to evaluate whether a telemetry change is being made in the correct package."
- Update VS Code extension dependencies to resolve security issues in `@xmldom/xmldom`, `basic-ftp`, `axios`, `undici`, and other direct/transitive packages.
## [3.86.2]
### Fixed
- Fix `@` file mentions and workspace file search on VS Code 1.122+ by resolving the new bundled `@vscode/ripgrep-universal` per-platform binary layout before falling back to legacy ripgrep paths.
## [3.86.1]
### Fixed
- Fix `@` file mentions failing to find files in some environments (notably VS Code Remote SSH, and after certain VS Code updates) by keeping the file-search fallback alive when the workspace index or bundled ripgrep binary is unavailable.
## [3.86.0]
### Added
- Add Claude Opus 4.8 provider support, including 1M-context variants where available.
- Add Moonshot Kimi K2.6 model support.
### Fixed
- Show prompt-cache support for Qwen 3.7 Max in the Cline provider.
- Fix the VS Code nightly publish workflow startup permissions.
### Changed
- Move the VS Code extension project into `apps/vscode`.
## [3.85.0]
### Added
- Add GPT-5.5 support to SAP AI Core.
- Add DeepSeek V4 Flash and Pro models.
- Add Gemini 3.5 Flash to Gemini and Vertex providers.
- Add `/lg-task` URI webhook integration for LG dashboard flows.
### Fixed
- Fix Vertex AI global endpoint handling for Claude models.
- Route Poolside Laguna models through next-gen prompts and native tool calling.
Chat with your agent from any messaging platform: Telegram, Slack, Discord, Google Chat, WhatsApp, and Linear. Each conversation thread maps to an agent session with full context. Set up access control to restrict who can interact with your agent.
Known local-only test failure: `src/commands/distribution-package.test.ts > rejects direct source package packing by default` will fail on machines that have `ignore-scripts=true` in `~/.npmrc` (set by the npm supply-chain hardening guide). Bun reads npm's `ignore-scripts` from `~/.npmrc`, so `bun pm pack --dry-run` skips the source-publish `prepack` guard and exits 0, which the test reads as a failure. CI does not set `ignore-scripts`, so the test passes there. Confirm by running `bun pm pack --dry-run` directly: with `~/.npmrc` in place it exits 0 with no guard output; with `~/.npmrc` moved aside it exits 1 and prints the guard message. This is not a release blocker by itself, but it does mean the local-publish path (`bun release cli`) will also bypass the source-publish guard on this machine; prefer the GitHub Actions publish path on machines with `ignore-scripts=true` set globally, or temporarily unset it (`npm config delete ignore-scripts` or `mv ~/.npmrc ~/.npmrc.bak`) for the duration of a local publish.
7. Commit release changes.
Only after the user approves the notes and version:
- Add Cline Hub, a web app for monitoring connected clients, viewing and driving sessions, streaming assistant output, and restarting the local hub, with local, LAN, and tunnel usage gated by a room secret.
- Support global AGENTS rules so agent rules can be applied across all sessions, not just per-project.
- Let plugins contribute static or dynamic rule content when installed in the sandbox.
- Bind Discord sessions to individual message authors so different Discord users no longer share chat state in a thread.
- Support participant mute targets in Discord: resolve `/mute` and `/unmute` from user mentions or raw user IDs to mute a specific participant in a thread.
- Make OAuth URLs clickable in the TUI.
- Refresh the bundled model catalog, adding Claude Opus 4.8, Moonshot Kimi K2.6, and Qwen3.7 Max (with cache support).
- Discover SDK skill directories that are symlinked, including handling circular symlinks.
- Steer active connector sessions across turn keys by matching on session ID, so replies continue the existing session instead of starting a duplicate.
- Stop the Discord connector after repeated identical errors (per thread, within a time window) to prevent error messages from flooding a channel.
- Fix Discord connector registration and reply fallback handling.
- Fix SAP AI Core to use the AI SDK community provider.
- Log ACP output as diagnostics instead of errors so normal output no longer appears as errors.
## 3.0.14
- Fix OTEL telemetry variable bundling so telemetry is correctly enabled in compiled CLI builds: guard against environments where `process.env` is undefined and remove optional chaining so bundlers can inline the values at build time.
## 3.0.13
- Show a loading dialog while resuming a session from history so the TUI no longer appears frozen during the load.
- Speed up the `/clear` command by deferring new session creation until you send the next prompt, so clearing no longer blocks on spinning up an empty session.
## 3.0.12
- Show a loading dialog while the config screen switches provider or model so the transition no longer looks frozen.
- Render the ask question tool prompt inline with the conversation so the question and suggested answers stay attached to the assistant turn that asked them, instead of appearing in a separate modal.
- Allow manual `cline update` runs to install the latest published version immediately, bypassing the release age gate that delays automatic updates.
- Refresh the bundled SDK to 0.0.42, updating the model catalog.
## 3.0.11
- Fix a regression in the ChatGPT OAuth provider where requests failed with `max_output_tokens not supported`, by restoring the full output token budget instead of applying an implicit cap.
- Hide the `Space toggle` hint in the config footer when the highlighted row is not toggleable (rules, agents, hooks).
- Authenticate Vertex Gemini through Google auth when `gcp.projectId` is configured, and surface the full Vertex model list instead of only Claude models.
- Include tool names in tool result content blocks so message logs and session history consistently track which tool produced each result.
## 3.0.10
- Install plugins from `file://` URLs in addition to npm and git sources.
- Show Ollama API key note in TUI settings so users know when to provide an API key.
- Keep interactive sessions alive when idle or awaiting approval instead of treating them as ended, and stop reading message files for every session when `hydrate: false`.
- Add Poolside as a provider.
- Add Gemini 3.5 Flash to the Gemini provider model list.
- Auto-detect Telegram bot username from the bot token so the Telegram connector no longer requires it to be configured separately.
- Notify connectors when a scheduled execution fails, not just when it succeeds.
- Bake OTEL telemetry variables into the CLI at build time so telemetry works in nightly and production builds.
- Preserve model output token limits from the SDK model catalog so context window math matches the upstream provider.
- Soften the visual treatment of rejected tool calls in the TUI.
- Hide the skills tool from the system prompt when skills are disabled, and refresh slash commands after toggling a skill.
- Restore AWS Bedrock profile-based auth during legacy config migration so profiles set via `awsAuthentication: "profile"` are preserved without `awsUseProfile`.
- Cache global settings reads keyed by file mtime so repeated reads skip the JSON parse and zod validation on the hot path.
## 3.0.9
- Speed up CLI startup with plugins by loading sandboxed plugins concurrently and caching plugin tool descriptors per plugin, provider, and model.
- Speed up plugin and tool config toggles by updating the TUI optimistically and persisting changes without reloading the full config or reimporting plugins.
- Restore fuzzy ranking for the @-mention file picker so the most relevant files appear first.
- Keep the interactive CLI session alive after cancelling a task instead of tearing the session down.
- Accept dash-prefixed prompts when passed after `--`, so prompts starting with `-` are no longer parsed as flags.
- Recover from hub abort cleanup failures so a cancel that hits an error no longer crashes the runtime host.
- Route GLM thinking through provider metadata so thinking-enabled GLM models behave correctly through the gateway.
## 3.0.8
- Use Telegram numeric participant ids so renamed users stay linked to the same participant in the Telegram connector.
- Keep failed plugins visible in the config UI with their load/setup phase and error details so broken plugin definitions are easier to diagnose.
- Move the Create Session Fork shortcut from Opt+F to Opt+R so terminal word-right navigation works again.
- Fix AWS Bedrock region and profile detection in the CLI onboarding, and surface bearer-token and additional Bedrock config fields in the provider config screens.
- Fix inflated token usage counts caused by AgentRuntime.execute() not resetting usage between calls, which the local runtime host was then double-counting on top of the session baseline.
## 3.0.7
- Skip the ChatGPT OAuth model refresh on session startup so the CLI launches without the extra network round-trip.
@@ -416,7 +416,7 @@ Then attach VS Code or Chrome DevTools to `ws://127.0.0.1:6499`.
## Publishing
The CLI is published as the `cline` wrapper package on npm with platform-specific binaries under `@cline/cli-*`. The release flow lives in the `publish-cli` skill (`sdk/apps/cli/.cline/skills/publish-cli/SKILL.md`).
The CLI is published as the `cline` wrapper package on npm with platform-specific binaries under `@cline/cli-*`. The release flow lives in the `publish-cli` skill (`apps/cli/.cline/skills/publish-cli/SKILL.md`).
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.