Cline tools

All TOOLS Bug Fixes

• Fixed background Hub process memory ballooning during long sessions by changing session status updates to carry only state snapshots.(v4.1.17)
• Prevented hook scripts that fail to spawn from crashing the extension's core process and taking down the running task.(v4.1.17)
• Fixed a chat render crash caused by malformed `api_req` payloads.(v4.1.17)
• Ensured cost estimates do not appear in task history for subscription-billed tasks.(v4.1.17)
• Fixed an issue where pasted provider API keys were not stripped of invisible characters, preventing them from being corrupted and rejected.(v4.1.17)
• Improved error handling for OpenAI Codex sign-in when the callback port is occupied, now displaying a clear 'port in use' error.(v4.1.17)
• Fixed OAuth redirect errors during sign-in to be surfaced correctly instead of being reported as a missing authorization code.(v4.1.17)
• Prevented users from being signed out due to transient network failures while refreshing OpenAI Codex or OpenAI-compatible-account tokens.(v4.1.17)
• Fixed tool calling being silently disabled for Dify, SAP AI Core, opencode, and Codex CLI models.(v4.1.17)
• Fixed images being dropped from file reads on models with an empty capability list.(v4.1.17)
• Prevented restoring a checkpoint from silently removing commits made after it.(v4.1.17)
• Ensured `apply_patch` now preserves a file's existing CRLF line endings.(v4.1.17)
• Prevented an enabled but unreachable remote MCP server from stalling session startup by implementing a 10-second budget for remote connections.(v4.1.17)
• Ensured aborting a task now also cancels delegated subagents and teammates.(v4.1.17)
• Fixed Langfuse tracing to work in released builds by addressing issues with OpenTelemetry provider detection after minification.(v4.1.17)
• Ensured hook execution telemetry events are fired by correctly threading the task ID into hook runner creation.(v4.1.17)
• Fixed tool calling being silently disabled for Dify, SAP AI Core, opencode, and Codex CLI models.(desktop-v0.0.22)
• Fixed images being dropped from file reads on models with empty capability lists.(desktop-v0.0.22)
• Resolved an issue where editing and resending messages failed on sessions without checkpoint history.(desktop-v0.0.22)
• Fixed voice input on macOS by adding the necessary microphone usage description and entitlement.(desktop-v0.0.22)
• Fixed the CLI crashing when an enabled remote MCP server is unreachable by implementing a 10-second connection budget, preventing stalled session startups and session teardowns.(cli-v3.0.61)
• Resolved silent disabling of tool calling for Dify, SAP AI Core, opencode, and Codex CLI models by correcting how model capabilities are read.(cli-v3.0.61)
• Fixed images being dropped from file reads on models with empty capability lists.(cli-v3.0.61)
• Ensured Langfuse tracing now functions correctly in released builds by addressing issues caused by code minification renaming OpenTelemetry provider class names.(cli-v3.0.61)
• Prevented restoring a checkpoint from silently removing subsequent commits; it now refuses to run and informs the user.(cli-v3.0.61)
• Fixed `apply_patch` incorrectly altering line endings by preserving existing CRLF line endings.(cli-v3.0.61)
• Resolved OpenAI Codex (ChatGPT subscription) sign-in failures when port 1455 is occupied, now providing a clear 'port in use' error instead of an uncompletable browser flow.(cli-v3.0.61)
• Prevented users from being logged out due to transient network failures during token refreshes for Codex or OpenAI-compatible accounts.(cli-v3.0.61)
• Ensured aborting a session now correctly cancels delegated subagents and teammates, preventing their work from continuing.(cli-v3.0.61)
• Fixed scheduled tasks disappearing after a hub restart.(cli-v3.0.61)
• Corrected markdown flashing at the end of streamed responses.(cli-v3.0.61)
• Updated the message shown to the model when a tool call is rejected to clearly name the tool and indicate it's a user decision, not an error.(cli-v3.0.61)
• Fixed tool calling being silently disabled for gateway models that declared no capabilities, ensuring tool definitions are correctly included for Dify, SAP AI Core, opencode, and the Codex CLI.(sdk/sdk/v0.0.82)
• Fixed an empty capability list from incorrectly stripping image input, ensuring the file-read tool and model pickers correctly handle models with and without vision capabilities.(sdk/sdk/v0.0.82)
• Fixed Langfuse tracing to work in minified release builds by changing how the OpenTelemetry provider is identified.(sdk/sdk/v0.0.82)
• Fixed the hub being retired out from under running work by establishing a drain barrier before checking for activity, preventing sessions from being killed by hub replacements.(sdk/sdk/v0.0.82)
• Fixed restoring a checkpoint from running when HEAD has moved past the checkpoint's commit, preventing later commits from being lost.(sdk/sdk/v0.0.82)
• Fixed `apply_patch` to preserve a file's own CRLF line endings across updates.(sdk/sdk/v0.0.82)
• Fixed global rules not being discovered at ~/Cline/Rules on WSL and headless installs, ensuring rules written in the Documents folder are now correctly recognized.(sdk/sdk/v0.0.82)
• Fixed OpenAI Codex sign-in to fail fast with an actionable error when the callback port is in use, instead of leading to a broken sign-in flow.(sdk/sdk/v0.0.82)
• Fixed transient token-refresh failures from logging out Codex and OpenAI-compatible-account users, ensuring only rejected refresh tokens force re-authentication.(sdk/sdk/v0.0.82)
• Fixed aborting a session not propagating to spawned work, ensuring delegated subagents and teammates are now cancelled with the session.(sdk/sdk/v0.0.82)
• Fixed hub-managed schedules being wiped by cron reconciliation on hub restart.(sdk/sdk/v0.0.82)
• Fixed the hub creating filesystem watchers on agenda spec directories while the todo tool was disabled, preventing signature mismatch errors after editing specs on disk.(sdk/sdk/v0.0.82)
• Fixed the ask-a-question tool's option text overflowing by enabling wrapping.(desktop-v0.0.21)
• Resolved an issue where Langfuse tracing was not initializing in release builds due to a minified bundle breaking tracer detection.(desktop-v0.0.21)
• Ensured that stopping a session now correctly stops all initiated processes, including propagating aborts to delegated subagents and teammates, and persisting cancelled teammate tasks.(desktop-v0.0.21)
• Fixed scheduled tasks disappearing after app updates by ensuring hub-managed schedules are not wiped by cron reconciliation.(desktop-v0.0.20)
• Fixed OpenAI Codex (ChatGPT subscription) sign-in silently dead-ending when a specific callback port was in use, now providing an actionable error.(desktop-v0.0.20)
• Fixed Codex and OCA sign-ins from being dropped during token refresh when encountering transient network failures or server errors.(desktop-v0.0.20)
• Fixed checkpoint restore from silently removing commits made after the checkpoint, now refusing to reset the workspace in such cases.(desktop-v0.0.20)
• Fixed an enabled but offline remote MCP server from stalling session startup.(desktop-v0.0.20)
• Fixed an issue where the window title bar was not draggable across all views.(desktop-v0.0.20)
• Fixed the hub from watching agenda spec directories when the todo tool is disabled, preventing unnecessary OS watch handle usage.(desktop-v0.0.20)
• Fixed a crash in the codebase search tool that occurred on files with a single, very long line.(cli-v3.0.60)
• Resolved an issue where installing an MCP server would misinterpret '--' separators in install arguments as part of the server command.(cli-v3.0.60)
• Fixed the background hub process from ballooning in memory during long sessions by correcting how session status updates broadcast conversation transcripts.(cli-v3.0.60)
• Fixed `search_codebase` crashing when processing files with a single, extremely long line.(sdk/sdk/v0.0.80)
• Resolved an issue where `installMcpServer` incorrectly interpreted a `--` separator in install arguments as part of the stdio command.(sdk/sdk/v0.0.80)
• Fixed cost estimates incorrectly showing for flat-rate subscription providers, preventing confusion about actual charges.(v4.1.16)
• Resolved an issue where signing back in would incorrectly change the last-used provider.(v4.1.16)
• Ensured hooks correctly resolve their workspace from the VS Code window, fixing issues with discovering `.clinerules/hooks` scripts and incorrect path resolution in multi-window scenarios.(v4.1.16)
• Fixed new files being created with incorrect line endings by ensuring native platform line endings are used.(v4.1.16)
• Prevented the codebase search tool from crashing when encountering files with a single, extremely long line.(v4.1.16)
• Ensured credentials embedded in git remote URLs are now redacted from workspace information sent to the model.(v4.1.16)
• Fixed an issue where installing an MCP server from the marketplace could misinterpret command separators.(v4.1.16)
• Prevented the hub's event log from growing indefinitely and filling the disk.(v4.1.16)
• Fixed scheduled sessions getting stuck on a thinking shimmer when opened during execution.(desktop-v0.0.18)
• Resolved an issue where installing plugins and MCP servers from the Marketplace failed due to missing executables in $PATH.(desktop-v0.0.18)
• Fixed the application beach-balling for several seconds upon quitting.(desktop-v0.0.18)
• Corrected hover cards that were flashing closed and reopening when clicked.(desktop-v0.0.18)
• Fixed an issue where internal `[SYSTEM]` steering messages were incorrectly displayed in scheduled and automation runs.(desktop-v0.0.18)
• Fixed the provider list being unscrollable when a provider detail panel was open.(desktop-v0.0.17)
• Resolved an issue where a failed settings save incorrectly indicated a provider was configured.(desktop-v0.0.17)
• Fixed Uninstall buttons that were collapsing into a broken square.(desktop-v0.0.17)
• Fixed unreadable selected text within input fields.(desktop-v0.0.17)
• Fixed the codebase search tool crashing the app on files with a single extremely long line.(desktop-v0.0.17)
• Prevented the hub's event log from growing indefinitely and filling the disk.(desktop-v0.0.17)
• Fixed an issue where the first-launch "Try ClinePass" dialog incorrectly advertised an expiring $4.99 first-month promotion.(cli-v3.0.58)
• Fixed task.completed telemetry being dropped for most interactive sessions; the event is now emitted correctly once per session teardown.(sdk/sdk/v0.0.79)
• Prevented the hub's durable event log from accumulating to tens of gigabytes by capping it at 64 MiB on disk and implementing more frequent vacuuming.(sdk/sdk/v0.0.79)
• Fixed an issue where the "Use MCP servers" toggle did not auto-approve all MCP tool calls. Previously, the toggle only applied to individually opted-in tools, making it seem ineffective. Now, it correctly governs all MCP tools automatically.(v4.1.15)
• Fixed tool calling being silently disabled for custom OpenAI-Compatible models when their capabilities were inferred from convenience flags, which previously caused all tools to be stripped from requests.(cli-v3.0.57)
• Fixed tool calling being silently disabled for custom OpenAI-Compatible models when capability lists were synthesized from convenience flags, ensuring that inferred lists no longer override explicitly authored capability lists.(sdk/sdk/v0.0.78)
• Fixed tool calling being silently disabled for custom OpenAI-Compatible models when capabilities were inferred from convenience flags.(desktop-v0.0.16)
• Fixed tool calling for custom OpenAI-Compatible models where capability lists were incorrectly inferred from convenience flags, preventing tools from being used.(v4.1.13)
• Ensured Hub-backed sessions remain intact after a Hub restart or upgrade, preventing duplicate event delivery during stream overlaps.(v4.1.13)
• Restored session and client identity in Langfuse traces for Hub-backed and delegated-agent runs, which were previously missing grouping and version information.(v4.1.13)
• Fixed enterprise MCP controls enforcement on the Customize marketplace, ensuring MCP entries are hidden when remote config disables the marketplace and limited to `allowedMCPServers` when an allowlist is configured.(v4.1.12)
• Restored tool calling for custom OpenAI-Compatible models that had an empty stored capability list.(v4.1.12)
• Fixed a bug where typed prompts were lost during cloud handoffs; prompts now carry over to the live draft and are restored if the handoff fails.(desktop-v0.0.16-beta.1)
• Resolved an issue where a closed model popover was blocking clicks in the composer.(desktop-v0.0.16-beta.1)
• Corrected a problem with checkpoint restore staying locked after queued turns.(desktop-v0.0.16-beta.1)
• Fixed hook issues, ensuring PostToolUse output and context changes now reach the model.(desktop-v0.0.16-beta.1)
• Fixed checkpoint restore from getting stuck permanently by ensuring sessions that were never prompted or only had persistence updates correctly report their status.(desktop-v0.0.15)
• Resolved an issue where the "No sessions found" message would flash briefly while session history was still loading.(desktop-v0.0.15)
• Corrected the work summary to accurately count elapsed time when a tool call was attached to the answer instead of the run.(desktop-v0.0.15)
• Fixed the settings gear to no longer maintain its hover state when the Account screen is open.(desktop-v0.0.15)
• Prevented ClinePass from being incorrectly identified as not OAuth-managed in the chat credential gate, which was causing it to request credentials it already possessed.(desktop-v0.0.15)
• Fixed an issue where copying a user message would include its internal envelope data.(desktop-v0.0.15)
• Resolved the problem of multi-line code blocks collapsing into a single line.(desktop-v0.0.15)
• Ensured that provider-executed tool activity is now shown, rather than being dropped.(desktop-v0.0.15)
• Fixed the `PreToolUse` hook `contextModification` to correctly reach the model and ensured `PostToolUse` hook output and `cancel` control are no longer discarded.(desktop-v0.0.15)
• Improved PowerShell command execution to fail fast on the first error, preventing excessive output and incorrect success reporting.(desktop-v0.0.15)
• Fixed code actions failing with "command not found" on VS Code 1.134.(v4.1.11)
• Fixed `@` file mentions breaking when paths contain spaces.(v4.1.11)
• Ensured the diff edit view is shown for multi-line edits in files with CRLF line endings.(v4.1.11)
• Fixed tasks resuming by continuing the surviving session instead of rebuilding from original text.(v4.1.11)
• Fixed task-scoped settings overlays not clearing when the task view is cleared or switched, preventing overrides from leaking.(v4.1.11)
• Fixed LiteLLM input token limits being overwritten by catalog values.(v4.1.11)
• Restored custom base URLs for Gemini and normalized legacy host-root values.(v4.1.11)
• Fixed provider signup links pointing to a generic landing page instead of the provider's API key page.(v4.1.11)
• Fixed skill slash commands being loaded by pasting instructions into messages, which caused them to be delivered twice.(v4.1.11)
• Stopped offering non-chat models (image, voice) in chat model pickers.(v4.1.11)
• Ensured `PreToolUse` hook's `contextModification` is delivered to the model again and that `PostToolUse` hooks are waited for.(v4.1.11)
• Fixed tool activity run by a provider within its own session from being dropped from the conversation.(v4.1.11)
• Fixed `run_commands` failing with ENOENT when a structured command had a full command line without arguments.(v4.1.11)
• Fixed PowerShell commands to fail-fast, stopping at the first error instead of flooding output.(v4.1.11)
• Fixed an issue where an Anthropic `invalid_request_error` was incorrectly treated as a context-overflow.(v4.1.11)
• Fixed TUI dialog colors to correctly update live with theme changes.(cli-v3.0.56)
• Corrected the account dialog's selection chevron to align with other dialog styles.(cli-v3.0.56)
• Resolved an issue where provider-executed tool activity was dropped instead of being displayed as a tool card.(cli-v3.0.56)
• Ensured that `PreToolUse` hook `contextModification` is now correctly sent to the model.(cli-v3.0.56)
• Fixed `PostToolUse` hooks to properly handle output and `cancel` control.(cli-v3.0.56)
• Resolved `run_commands` failures with ENOENT when a structured command had a full command line without arguments.(cli-v3.0.56)
• Corrected PowerShell command behavior to fail fast on the first error instead of reporting partial success.(cli-v3.0.56)
• Fixed Gemini custom base URLs configured as a host root.(cli-v3.0.56)
• Ensured `cline schedule` commands against a remote hub now correctly register a workspace client for authorization under new workspace-scoped rules.(cli-v3.0.56)
• Fixed provider-executed tool activity from being dropped, ensuring it now surfaces as observational tool events.(sdk/sdk/v0.0.76)
• Fixed the `PreToolUse` hook `contextModification` not reaching the model by delivering it as a `<hook_context>` block.(sdk/sdk/v0.0.76)
• Fixed `PostToolUse` hooks running fire-and-forget by awaiting them and honoring their `contextModification` and `cancel` controls.(sdk/sdk/v0.0.76)
• Fixed `run_commands` failing with ENOENT for structured commands containing spaces by routing them through the shell.(sdk/sdk/v0.0.76)
• Fixed PowerShell commands to fail-fast, preventing excessive stderr records and false success reports on pipeline errors.(sdk/sdk/v0.0.76)
• Fixed Gemini custom base URLs configured as a host root.(sdk/sdk/v0.0.76)
• Fixed sessions reporting a bogus "running" status for interactive sessions never prompted and snapshot-only session updates, preventing clients from getting stuck.(sdk/sdk/v0.0.76)
• Fixed Windows crashes caused by the agenda spec watcher when the specs directory resolved through an 8.3 short path.(sdk/sdk/v0.0.76)
• Fixed an issue where turns would get stuck on a streaming shimmer without final output, only healing after sending another message.(desktop-v0.0.14)
• Corrected sessions being assigned the Yolo-mode system prompt when auto-approve was on, ensuring auto-approval is an independent tool policy.(desktop-v0.0.14)
• Resolved an issue where `/skill` and `/workflow` commands would dump the entire skill body into the chat.(desktop-v0.0.14)
• Fixed command execution breaking for entire sessions when a model emitted a full command line without separate arguments.(desktop-v0.0.14)
• Ensured restoring a checkpoint now trims the saved transcript to prevent showing reverted file changes.(desktop-v0.0.14)
• Fixed Gemini custom base URLs, including host-root and proxy values, which were previously failing.(desktop-v0.0.14)
• Restored correct LiteLLM input token limits reported by the server, preventing a 128K default override.(desktop-v0.0.14)
• Fixed misaligned columns in the Usage table.(desktop-v0.0.14)
• Fixed routine dialog dropdowns not responding to mouse clicks.(desktop-v0.0.14)
• Fixed an issue where extended thinking budgets were not being applied to Cline Pass when the gateway moved off the OpenAI-compatible path.(desktop-v0.0.13)
• Resolved a bug where two Cline installs on different builds would shut each other's Hub down in a loop, causing live sessions to disconnect abnormally.(desktop-v0.0.13)
• Fixed the application from replacing a Hub that was still serving sessions; it now attaches to the Hub and swaps once it becomes idle.(desktop-v0.0.13)
• Corrected the 'update required' dialog to no longer interrupt when the Hub is finishing its own update, as the app was already on a newer build and the Hub would replace itself after sessions ended.(desktop-v0.0.13)
• Fixed an issue where two Cline installations on different builds could cause a loop of daemon shutdowns, resulting in abnormal socket closes and killed live sessions. Build identity comparison has been improved to prevent this.(v4.1.10)
• Resolved an issue where a Hub serving sessions was incorrectly replaced mid-handshake; it will now only be swapped once it becomes idle.(v4.1.10)
• Fixed an issue where idle plugin sandbox processes were not reclaimed and remained running for the entire session duration.(v4.1.10)
• Fixed an issue where auto-updates could install while a CLI was attached, causing the Hub connection to close and kill live sessions.(cli-v3.0.55)
• Resolved a bug where older CLI versions (3.0.54 and earlier) could brick a running session during an update.(cli-v3.0.55)
• Corrected a loop where two Cline installations on different builds would shut down each other's Hub daemon, leading to abnormal socket closes and session termination.(cli-v3.0.55)
• Prevented newer builds from replacing a Hub that was still serving sessions, avoiding mid-handshake session deaths.(cli-v3.0.55)
• Fixed streaming assistant markdown from flashing back to raw text by ensuring settled content remains rendered as new chunks arrive.(cli-v3.0.55)
• Resolved an issue where idle plugin sandbox processes would linger for the life of the session.(cli-v3.0.55)
• Fixed an issue where Cline installations on different builds would cause Hub daemons to shut each other down, resulting in abnormal socket closes for live sessions.(sdk/sdk/v0.0.75)
• Resolved a problem where newer builds would prematurely replace active Hubs, causing sessions to die mid-handshake.(sdk/sdk/v0.0.75)
• Fixed an issue where idle plugin sandbox processes would linger unnecessarily for the life of the session.(sdk/sdk/v0.0.75)
• Corrected `cline doctor fix` to accurately report process statuses, including surviving processes, newly appeared processes, respawned daemons, and held startup locks.(sdk/sdk/v0.0.75)
• Fixed issue where a successfully refreshed Cline token was discarded if the old one had expired, preventing the first request after idle periods from failing.(v4.1.9)
• Prevented legacy-task migration backlog from spamming telemetry by recording migration outcomes only after session persistence.(v4.1.9)
• Ensured involuntary Cline logouts (rejected refresh tokens) are reported instead of silently clearing credentials.(v4.1.9)
• Fixed a mid-turn crash on streamed tool calls with non-zero or non-contiguous indexes.(v4.1.9)
• Corrected token bucket reporting to show disjoint per-request buckets instead of recounting the entire cached conversation, reducing inflated per-task totals.(v4.1.9)
• Fixed the Claude Code provider to correctly run native tools and anchor sessions on the workspace directory, resolving issues with tool definitions and permission rules.(cli-v3.0.54)
• Fixed truncated tool-call JSON from being silently repaired into incorrect arguments, now rejecting payloads with unterminated strings.(cli-v3.0.54)
• Fixed strict providers rejecting turns with only empty text parts in user messages.(cli-v3.0.54)
• Fixed a mid-turn crash occurring during streamed tool calls with non-zero or non-contiguous indexes when using LiteLLM's Anthropic passthrough.(cli-v3.0.54)
• Fixed the Hub daemon from logging an unhandled error and exiting non-zero when a client was still connected at shutdown.(cli-v3.0.54)
• Fixed per-task token totals from being inflated due to cache-heavy sessions by reporting token telemetry in disjoint buckets.(cli-v3.0.54)
• Resolved an issue where upgrading the CLI would cause it to communicate with a daemon running the previous release; the CLI now correctly retires and respawns the Hub daemon on the new code.(cli-v3.0.54)
• Fixed the Claude Code provider from being unusable for agentic work by correctly handling tool definitions and session anchoring.(sdk/sdk/v0.0.74)
• Fixed truncated tool-call JSON from being silently repaired into incorrect arguments; payloads with unterminated strings are now rejected.(sdk/sdk/v0.0.74)
• Fixed strict providers from rejecting turns with empty text parts in messages.(sdk/sdk/v0.0.74)
• Fixed a mid-turn crash on streamed tool calls with non-zero or non-contiguous indexes by updating AI SDK packages.(sdk/sdk/v0.0.74)
• Fixed the Hub daemon from logging an unhandled rejection and exiting non-zero on client disconnect during shutdown; shutdown is now clean.(sdk/sdk/v0.0.74)
• Fixed involuntary Cline logouts from being reported instead of silent credential clearing, and prevented transient network failures from being logged as logouts.(sdk/sdk/v0.0.74)
• Fixed an issue where reconnecting to a stale managed Cline Hub daemon would cause problems; the app now prompts to update and restart correctly.(desktop-v0.0.12)
• Resolved an issue where the Hub daemon would shut down uncleanly when a client was still connected.(desktop-v0.0.12)
• Fixed strict providers rejecting turns with an "user message must have content" error when the message contained only empty text.(desktop-v0.0.12)
• Fixed a mid-turn crash that occurred with streamed tool calls having non-zero indexes, particularly when using LiteLLM's Anthropic passthrough.(desktop-v0.0.12)
• Fixed the first turn of a fresh session from getting stuck on "Agent is working…" indefinitely.(desktop-v0.0.12)
• Resolved an issue where truncated tool-call JSON was being silently repaired instead of being rejected.(desktop-v0.0.12)
• Fixed git jargon display when opening non-git repos.(desktop-v0.0.11)
• Fixed folder picker to report failures instead of doing nothing.(desktop-v0.0.11)
• Fixed diff panel to resolve file paths against the session's working directory for correct diff opening.(desktop-v0.0.11)
• Fixed failed turns to surface errors in the transcript instead of leaving the chat blank.(desktop-v0.0.11)
• Fixed a startup script-load error.(desktop-v0.0.11)
• Fixed webview errors to be attributed to the source URL that caused them.(desktop-v0.0.11)
• Fixed signing out to be handled as a normal state instead of a command error.(desktop-v0.0.11)
• Fixed tool output to no longer nest its own scrollbar.(desktop-v0.0.11)
• Fixed hung MCP servers to no longer prevent session creation.(desktop-v0.0.11)
• Fixed stdio servers that were never configured from blocking indefinitely.(desktop-v0.0.11)
• Fixed LiteLLM requests to route through Chat Completions instead of the Responses API.(desktop-v0.0.11)
• Ensured checkpoints are picked up when git is initialized part-way through a session.(desktop-v0.0.11)
• Fixed an issue where prompts queued during an interrupted turn were silently dropped; they are now preserved and drained after the turn aborts, with the stop surfaced.(v4.1.7)
• Resolved an issue where session context was not durable across aborts and hub restarts, ensuring interrupted sessions now resume with their previous state.(v4.1.7)
• Fixed a bug where a mode switch aborting a running turn would not settle the turn phase.(v4.1.7)
• Corrected the reporting of queued-turn failures, which now appear as `run.failed` instead of completing silently.(v4.1.7)
• Prevented hung MCP servers from causing session creation to fail and provided stdio servers a 30-second initialization budget instead of blocking indefinitely.(v4.1.7)
• Ensured OAuth authorization for SSE MCP servers is now surfaced on a 401 error instead of causing an outright failure.(v4.1.7)
• Fixed requests against LiteLLM proxies by routing LiteLLM through Chat Completions instead of the Responses API.(v4.1.7)
• Resolved an issue where network interruptions mid-stream but before any model output caused turns to fail; these are now retried.(v4.1.7)
• Fixed Vertex ADC token refreshes to use the configured fetch, enabling them to work behind proxies and custom transports.(v4.1.7)
• Included untracked files in checkpoint diffs when a snapshot was taken and ensured checkpoints are picked up even when git is initialized part-way through a session.(v4.1.7)
• Fixed @-mention file search in empty windows to fall back to the session cwd or Desktop.(v4.1.7)
• Prevented foreign compiled plugin-sandbox bootstraps from running for a source host.(v4.1.7)
• Fixed issue where queued messages were unreadable on light-theme terminals due to poor color contrast.(cli-v3.0.52)
• Fixed rendering of MCP tool results to display as readable text instead of escaped (cli-v3.0.52)
• Fixed mangling of binary payloads when expanded in MCP tool results.(cli-v3.0.52)
• Fixed rendering issues caused by malformed tool input/output payloads, which now degrade gracefully instead of throwing errors.(cli-v3.0.52)
• Fixed issue where a hung MCP server would prevent session creation.(cli-v3.0.52)
• Fixed indefinitely blocking stdio servers that were never configured by providing a 30-second initialization budget.(cli-v3.0.52)
• Fixed LiteLLM requests to route through Chat Completions instead of the Responses API, resolving issues with calls against LiteLLM proxies.(cli-v3.0.52)
• Fixed network interruptions mid-stream (before model output) to retry instead of failing the turn.(cli-v3.0.52)
• Fixed Vertex ADC token refreshes to use the configured fetch, ensuring they work behind proxies and custom transports.(cli-v3.0.52)
• Fixed an issue where turns completing with a plan were incorrectly treated as failed when a plan-blocked command was the only tool call, ensuring the turn correctly re-runs the presented plan instead of appearing to do nothing.(v4.1.4)
• Fixed tool paths to display relative to the workspace in the chat view instead of absolute paths.(v4.1.4)
• Fixed pending attachments to reset when starting a new task, preventing images from previous tasks from carrying over.(v4.1.4)
• Fixed a generic failure to surface a clear error when the selected provider has no API key configured.(v4.1.4)
• Fixed MCP tool and resource lists to refresh when a server sends a `list_changed` notification, instead of only showing a toast.(v4.1.4)
• Fixed installed plugins to display under their real package names instead of all appearing as "index".(v4.1.4)
• Corrected the Linux keybinding label in the Plan/Act mode tooltip.(v4.1.4)
• Fixed recovery from running out of context by compacting and retrying once, and providing explanations for genuinely unrecoverable cases.(v4.1.4)
• Fixed empty model responses to retry on every provider, not just Ollama, resolving hard "Model returned empty response" failures on OpenRouter, Cline, and OpenAI-compatible endpoints.(v4.1.4)
• Fixed Claude 4.6+ and 5.x models from being rejected with "thinking.type.enabled is not supported" when resolving from the offline catalog or a hand-typed model ID.(v4.1.4)
• Restored Bedrock prompt caching by ensuring the correct cache format is used and routing Bedrock foundation models through geo inference profiles.(v4.1.4)
• Fixed requests for reasoning models on OpenAI-compatible endpoints by sending `max_completion_tokens` and substituting image content for models without image support.(v4.1.4)
• Fixed MiniMax default model inheritance from models.dev and refreshed the bundled catalog to include Infomaniak and SCX.ai.(v4.1.4)
• Fixed error telemetry to report provider failures only once and rate-limit repeated failures from unattended retry loops.(v4.1.4)
• Fixed chat message actions (copy, fork, edit, restore) colliding with message descenders.(desktop-v0.0.9)
• Resolved application errors not being reported in diagnostics due to telemetry configuration issues.(desktop-v0.0.9)
• Fixed plan mode relying solely on prompting for file-editing shell commands; it now hard-blocks them.(desktop-v0.0.9)
• Enabled automatic recovery from running out of context by compacting and retrying runs.(desktop-v0.0.9)
• Fixed 'Model returned empty response' failures on OpenRouter, Cline, and OpenAI-compatible endpoints by retrying empty model responses on all providers.(desktop-v0.0.9)
• Restored Bedrock prompt caching functionality, which was previously not working.(desktop-v0.0.9)
• Ensured reasoning models on OpenAI-compatible endpoints receive the correct token parameter.(desktop-v0.0.9)
• Fixed models without image support failing when encountering image content; they now substitute content instead.(desktop-v0.0.9)
• Fixed an issue where the git branch shown below the prompt would not update when switching branches from another terminal or editor.(cli-v3.0.50)
• Resolved an issue where Telegram slash commands like `/clear` were silently dropped due to interception by the Telegram library.(cli-v3.0.50)
• Corrected a problem where racing connector launches could collide, ensuring instances are claimed before socket mode is opened.(cli-v3.0.50)
• Fixed a bug where a turn ending with a completed plan was incorrectly rendered as failed if a plan-blocked command was its only tool call.(cli-v3.0.50)
• Resolved an issue where running out of context would cause a failure with a raw provider error, now recovering by force-compacting and retrying.(cli-v3.0.50)
• Fixed an issue where empty model responses were only retried on Ollama, now retrying on every provider including OpenRouter, Cline, and OpenAI-compatible endpoints.(cli-v3.0.50)
• Restored Bedrock prompt caching functionality, which was previously not working due to an incorrect cache format.(cli-v3.0.50)
• Fixed an issue where reasoning models on OpenAI-compatible endpoints were sent `max_tokens` instead of the supported `max_completion_tokens`.(cli-v3.0.50)
• Resolved an issue where requests to models without image support would fail, now substituting image content instead.(cli-v3.0.50)
• Fixed context-window overflow errors that previously surfaced as raw unclassified provider errors.(sdk/sdk/v0.0.70)
• Fixed Bedrock prompt caching to correctly emit `cachePoint` markers, resolving issues with cache reads and writes.(sdk/sdk/v0.0.70)
• Fixed Ollama to use the native AI SDK provider with wire-contract fixes for empty `think` settings, mid-stream errors, and attachment-only turns.(sdk/sdk/v0.0.70)
• Fixed image-bearing requests to no longer log deprecation warnings by emitting canonical AI SDK 7 file parts.(sdk/sdk/v0.0.70)
• Fixed `sdk.error` telemetry to no longer be emitted twice for the same provider failure.(sdk/sdk/v0.0.70)
• Fixed issue where `read_files` would reject input from weaker models if line-range entries were sent as separate array items by coalescing them back onto the preceding file path.(cli-v3.0.38)
• Fixed dropped plan/act mode notices from prompts sent to the model.(cli-v3.0.37)
• Fixed an unexpected restart triggered by switching modes in an empty session.(cli-v3.0.37)
• Fixed issue where switching from plan mode to act mode did not take effect until the end of the turn, preventing the use of file editors.(cli-v3.0.36)
• Prevented auto-starting plan execution when a Tab mode toggle races a completing turn, ensuring users only run approved plans.(cli-v3.0.36)
• Fixed issue where MCP tool names exceeding 64 characters caused errors with OpenAI-compatible providers(cli-v3.0.31)
• Fixed marketplace edge cases related to refreshing MCP servers after installs, remote configuration disabling of the MCP Marketplace tab, hiding workflows, surfacing plugin-bundled skills, and uninstalling shared marketplace entries.(v4.0.0)
• Fixed chat submission during active turns by queuing new messages instead of dropping or racing them, ensuring pending/queued states display promptly, and removing delayed send behavior.(v4.0.0)
• Fixed editing previous user messages, ensuring Escape cancels editing locally and clarifying reset action labels.(v4.0.0)
• Fixed terminal reliability issues, including standalone Windows output capture, hardened PowerShell command handling, correct running-state display, and preservation of raw structured commands.(v4.0.0)
• Fixed SDK tool-result and provider-message budgeting by implementing default truncation for large tool outputs, capping assistant text, limiting ingestion of bash/file-read/search output, and bounding media budgets.(v4.0.0)
• Fixed login and feature-flag resolution by ensuring the correct user/account identity is used on startup and simplifying the login user experience.(v4.0.0)
• Fixed an "ERROR: EMPTY CONTENT" message that could appear during errors.(cli-v3.0.30)
• Resolved a packaging issue (createRequire) that could cause the CLI to break at runtime.(cli-v3.0.30)
• Fixed Cline model display names so they resolve correctly by model name(cli-v3.0.28)
• Fixed apply_patch to fail correctly when a hunk is skipped(cli-v3.0.25)
• Fixed run_commands to return captured stdout on failure and correctly handle split heredocs(cli-v3.0.25)
• Fixed search tools to treat zero results as a successful operation(cli-v3.0.25)
• Fixed disabled-reasoning handling specifically for StepFun flash operations(cli-v3.0.25)
• Fixed history resume rendering isolation issues(cli-v3.0.25)
• Fixed incorrect Cline OAuth token formatting within the provider configuration(cli-v3.0.25)
• Fixed truncation of structured tool operation result strings, ensuring oversized tool output is properly contained(cli-v3.0.24)
• Stopped echoing the full command text within run_commands tool results for cleaner output(cli-v3.0.24)
• Fixed scrolling issues for inline ask-question responses(cli-v3.0.21)
• Fixed connector thread session routing and stale hub session handling(cli-v3.0.21)
• Fixed empty message content replay for Bedrock(cli-v3.0.21)
• Fixed an issue where settings writes during MCP server delete/add flows caused the MCP server list to be emptied by the file watcher.(v3.88.0)
• Corrected Fireworks model metadata and cache pricing, and removed stale Fireworks AI models.(v3.88.0)
• Fixed an issue related to OAuth token migration for users who were previously signed in via the old extension.(cli-v3.0.16)
• Fixed issues with @ file mentions and workspace file search on VS Code 1.122+ by correctly resolving the new bundled @vscode/ripgrep-universal binary layout.(v3.86.2)
• Fixed failing file mentions using the @ symbol in environments like VS Code Remote SSH or after certain VS Code updates by ensuring the file-search fallback remains active when the workspace index or bundled ripgrep binary is missing.(v3.86.1)
• Fixed incorrect global endpoint handling for Claude models when using Vertex AI.(v3.85.0)
• Ensured Poolside Laguna models are correctly routed through next-gen prompts and native tool calling.(v3.85.0)
• Fixed a regression in the ChatGPT OAuth provider that caused requests to fail with an output token limit error by restoring the full output token budget.(cli-v3.0.11)
• Fixed issue where tool result content blocks did not include tool names, ensuring message logs and session history accurately track which tool generated the result.(cli-v3.0.11)
• Fixed an issue where interactive sessions were prematurely ended when idle or awaiting user approval, ensuring they remain alive.(cli-v3.0.10)
• Restored correct AWS Bedrock profile-based authentication during legacy configuration migration, preserving settings made with `awsAuthentication: "profile"`.(cli-v3.0.10)
• Fixed an issue where the system prompt incorrectly showed the skills tool even when skills were disabled, and ensured slash commands refresh after toggling a skill.(cli-v3.0.10)
• Fixed runtime host crash that occurred after a cancel operation hit an error during hub abort cleanup.(cli-v3.0.9)
• Fixed GLM thinking not behaving correctly through the gateway by routing it through provider metadata.(cli-v3.0.9)
• Fixed plugin tools failing in the production npm build by ensuring SDK dependencies are imported correctly at runtime.(cli-v3.0.4)
• Fixed dropped macOS screenshots when pasting or reading them by correctly resolving paths containing Unicode variants like U+202F (narrow no-break space).(cli-v3.0.3)
• Resolved a crash that occurred when encountering detached hub event errors during a session.(cli-v3.0.3)
• Ensured that Ollama models with reasoning enabled by default now correctly honor the --thinking none flag.(cli-v3.0.3)
• Fixed validation failures occurring for MCP servers that require an object.(v3.83.0)
• Resolved issue where `write_to_file` could not create or overwrite files containing empty content.(v3.83.0)
• Fixed incorrect JSON escaping within hook templates.(v3.82.0)
• Improved error handling when using ripgrep for file searching.(v3.82.0)
• Fixed an issue where cache reflection failed for Cline and Vercel API handlers.(v3.79.0)
• Resolved a problem where the command output would get stuck when a terminal command ended unexpectedly.(v3.79.0)
• Patched a security vulnerability related to action injection.(v3.79.0)
• Fixed an issue where the `new_task` tool was incorrectly included in the system prompt when running in yolo/headless mode.(v3.77.0)
• Corrected formatting issues in the Kanban demo video.(v3.77.0)
• Fixed an issue preventing CLI Kanban from spawning correctly on Windows by enabling shell mode for 'npx.cmd'.(v3.76.0)
• Replaced the generic error message shown when a user is not logged into Cline with a more specific message(v3.74.0)
• Fixed alignment issue in ClineRulesToggleModal padding to match ServersToggleModal(v3.74.0)
• Skipped WebP format processing for GLM and Devstral models running via llama.cpp(v3.74.0)
• Ensured user-configured context window is respected in LiteLLM getModel() calls(v3.74.0)
• Ensured explicit model IDs outside the static catalog are honored in the W&B provider(v3.74.0)
• Added missing Fireworks serverless models and their associated pricing information(v3.74.0)
• Fixed crashes in the Claude Code Provider when encountering rate limit events, empty content arrays, error results, or unknown content types(v3.73.0)
• Ensured tool handlers (read_file, list_files, list_code_definition_names, search_files) return graceful errors instead of crashing(v3.73.0)
• Resolved native tool placeholder interpolation issues within prompts(v3.72.0)
• Fixed Gemini Flash output token limit to 8192 across all providers(v3.72.0)
• Fixed unit test path normalization issues specifically on Windows(v3.72.0)
• Resolved flaky hooks tests occurring on Windows environments(v3.72.0)
• Fixed Bedrock to correctly handle thinking and redacted_thinking blocks during message conversion and streaming(v3.72.0)
• Prevented crashes when the list_files or list_code_definition_names functions receive an invalid file path(v3.72.0)
• Fixed a crash related to reasoning delta when processing usage-only stream chunks(v3.67.0)
• Corrected an issue where OpenAI tool ID transformation was incorrectly restricted to the native provider only(v3.67.0)
• Fixed authentication check failure when operating in ACP mode(v3.67.0)
• Resolved an issue where the CLI yolo setting was being incorrectly persisted to disk(v3.67.0)
• Fixed the inline focus-chain slider to correctly operate within its feature row(v3.67.0)
• Ensured compatibility with Gemini 3.1 Pro(v3.67.0)
• Corrected authentication issues when using the Cline CLI with the ACP flag(v3.67.0)
• Fixed CLI to correctly handle stdin redirection in CI/headless environments.(v3.58.0)
• Fixed CLI to preserve OAuth callback paths during auth redirects.(v3.58.0)
• Fixed OAuth callback reliability in VS Code Web by generating callback URLs via `vscode.env.asExternalUri`.(v3.58.0)
• Fixed Terminal to surface command exit codes in results and improved long-running `execute_command` timeout behavior.(v3.58.0)
• Fixed UI rendering by adding a loading indicator and fixing `api_req_started` rendering.(v3.58.0)
• Prevented duplicate streamed text rows after task completion during task streaming.(v3.58.0)
• Fixed API to preserve the selected Vercel model when model metadata is missing.(v3.58.0)
• Ensured telemetry flushes on shutdown and routed PostHog networking through proxy-aware shared fetch.(v3.58.0)
• Increased Windows E2E test timeout to reduce flakiness in CI.(v3.58.0)
• Fixed issue where the read file tool failed to support reading large files(v3.57.0)
• Resolved crash occurring when entering decimal input in OpenAI Compatible price fields (#8129)(v3.57.0)
• Corrected build complete handlers when updating the API configuration(v3.57.0)
• Fixed missing provider from the model list(v3.57.0)
• Fixed issue where the Favorite Icon/Star was getting clipped in the task history view(v3.57.0)
• Fixed an issue where remotely configured providers were not being selected correctly.(v3.50.0)
• Resolved a bug where act_mode_respond could result in consecutive, unnecessary calls.(v3.50.0)
• Fixed incorrect tool call IDs when switching between different model formats.(v3.50.0)
• Fixed workflow slash command search to be case-insensitive.(v3.49.1)
• Fixed incorrect model display in ModelPickerModal when using LiteLLM.(v3.49.1)
• Fixed LiteLLM model fetching when using the default base URL.(v3.49.1)
• Fixed crash that occurred when OpenAI-compatible APIs sent usage chunks with empty or null choices arrays at the end of streaming.(v3.49.1)
• Fixed incorrect model ID for the Kat Coder Pro Free model.(v3.49.1)
• Fixed issue where expired tokens were being used in authenticated requests(v3.47.0)
• Fixed diff view to correctly exclude binary files that lack file extensions(v3.47.0)
• Fixed issue where file endings and trailing newlines were not being preserved(v3.47.0)
• Fixed rate limiting issues specific to the Cerebras provider(v3.47.0)
• Fixed Auto Compact functionality for the Claude Code provider(v3.47.0)
• Made Workspace and Favorites history filters operate independently(v3.47.0)
• Fixed remote MCP server connection failures, specifically handling 404 responses(v3.47.0)
• Disabled native tool calling for the Deepseek 3.2 speciale model(v3.47.0)
• Fixed the Baseten model selector interface(v3.47.0)
• Fixed duplicate error messages that occurred during streaming for the Diff Edit tool when Parallel Tool Calling was disabled.(v3.46.0)
• Corrected typos found in Gemini system prompt overrides.(v3.46.0)
• Resolved issues with the model picker favorites ordering, star toggle functionality, and keyboard navigation for OpenRouter and Vercel AI Gateway providers.(v3.46.0)
• Fixed an issue where remote configuration values were not being fetched from the cache.(v3.46.0)