CLI v3.0.52
This release adds an MCP server uninstall command, improves provider settings reuse for schedules, fixes light-theme terminal readability for queued messages, and enhances tool result rendering. Multiple SDK improvements include better error handling for malformed payloads, session durability across interrupts, MCP server timeout handling, OAuth support for remote SSE servers, LiteLLM proxy routing fixes, network retry logic, and checkpoint tracking improvements.
- Added
cline mcp uninstallfor removing an installed MCP server - Schedules now reuse your saved provider settings instead of needing provider configuration of their own
- Queued messages are legible on light-theme terminals — they were previously rendered in a color that washed out against a light background
- MCP tool results render as readable text in the TUI instead of escaped JSON, and binary payloads survive being expanded instead of being mangled
- Malformed tool input/output payloads no longer break rendering — the formatters degrade gracefully instead of throwing
- Prompts queued during a turn now survive being interrupted: they are preserved across aborts, drained after a turn aborts itself, and the stop is surfaced instead of leaving the queue silently dropped (from SDK v0.0.72)
- Session context stays durable across aborts and hub restarts, so an interrupted session resumes with the state it had (from SDK v0.0.72)
- A hung MCP server no longer takes down session creation, and stdio servers that were never configured get a 30-second initialize budget instead of blocking indefinitely (from SDK v0.0.72)
- Remote SSE MCP servers surface an OAuth authorization prompt on a 401 instead of failing outright, and pre-registered OAuth clients are supported for setups without dynamic client registration (from SDK v0.0.72)
- LiteLLM requests route through Chat Completions instead of the Responses API, fixing calls against LiteLLM proxies (from SDK v0.0.72)
- Network interruptions that happen mid-stream but before any model output are retried instead of failing the turn (from SDK v0.0.72)
- Vertex ADC token refreshes use the configured fetch, so they work behind proxies and custom transports (from SDK v0.0.72)
- Checkpoint diffs include files that were untracked when the snapshot was taken, and checkpoints are picked up when git is initialized part-way through a session (from SDK v0.0.72)
- Scheduled run reports carry execution context — readable headers, schedule metadata, durations, and lifecycle error details (from SDK v0.0.72)
Full Changelog: cli-v3.0.51...cli-v3.0.52
Source: original entry ↗
More from Cline
Follow Cline to get its new changes in your feed and email digest.
Desktop v0.0.48
Added support for GPT-6 models on OpenAI and Azure OpenAI endpoints by fixing the max_tokens parameter issue. Updated default models across multiple providers and refreshed the model catalog with new CommandCode and Reflection providers.
CLI v3.0.73
GPT-6 models now work with OpenAI and Azure OpenAI endpoints after fixing a token parameter issue. Claude Sonnet 5.5 is restored as the default model when none is selected, and the model catalog has been refreshed with new providers and updated default models across multiple services.
SDK v0.0.95
OpenAI-compatible requests for GPT-6 and later models now use max_completion_tokens instead of max_tokens to prevent rejection by OpenAI and Azure. The hub daemon now tracks client launcher information as OTel resource attributes, the model catalog expanded from 6,952 to 7,041 models with new providers, and default models were updated across multiple providers with Claude Sonnet 5.5 restored as the primary recommended option.