read_files results are no longer re-cut to the 8k tool-result cap on the way to the provider.Cline SDK 0.2.1
Released · Cline
BreakingSecurity fixChanges context and compaction settings
Models:Removes DeepSeek V4.1 Flash ·Adds Qwen 3.7 Plus ·Adds Qwen 3.7 Max ·Adds Kimi K3.1 ·Adds Gemini 4
What the release notes say
read_filesresults are no longer re-cut to the 8k tool-result cap on the way to the provider. They use the 50k file-content cap, so a read the tool reported in full arrives in full. Command, search, MCP and custom tool results keep the 8k cap, and an explicit tool-result cap still applies- Models that need interleaved reasoning get a placeholder
reasoning_contenton assistant messages that have none. This fixes Reflection Beam's400 Missing required parameter: 'messages[n].reasoning_content'after compaction or a model switch. The fact is carried asModelInfo.metadata.interleavedReasoningField - The summarizer now states a preference to go without reasoning instead of disabling it outright. The gateway disables it only for models whose catalog entry advertises an off option. Before, uncatalogued models got
reasoning_effort: "none", which some endpoints reject, and compaction fell back to basic - A custom model with saved overrides now has
reasoningseeded into its capability list unless it setssupportsReasoning: false, so an explicit reasoning disable reaches the provider. Before, gpt-5.6 and gpt-6 chat-completions endpoints rejected every tool call - The native OpenAI adapter fits the reasoning level to the model's advertised effort ladder, so
maxand Extra High are no longer sent verbatim to GPT-5.x and o-series models that reject them - LiteLLM: the legacy
max_tokensis no longer used as the input budget whenmax_output_tokensis set. Null limits are treated as missing - The
clineprovider's bundled default is now the first bundled free model.resolveClineDefaultModelId()in@cline/corereturns the first free model from the live recommended feed, then the bundled one, thenCLINE_DEFAULT_MODEL_ID CLINE_DEFAULT_MODEL_IDis nowanthropic/claude-sonnet-5.5, and the remaining hardcoded default-model literals use it.@cline/sharedaddsANTHROPIC_DEFAULT_MODEL_IDfor Anthropic's bare id format- A running compaction can be stopped, and cancellations are counted in telemetry
- Session config and the hub RPC schema accept the
maxreasoning effort - With tools and spawning enabled, core registers
ux_verifier, which delegates an ordered checklist to a subagent through the host'sspawn_agentexecutor. Disablingspawn_agentdisables it too createUxVerificationReportTool()creates the opt-inreport_ux_verificationtool for structured reports with captions, pass/fail/blocked results and screenshot referencescreatePublishArtifactsTool({ publish })creates the opt-inpublish_artifactstool.createArtifactPublisherfrom@cline/core/cloudpublishes to cloud sessions through signed upload policies. Artifact IDs default to the source filenameMcpToolDescriptor.annotationscarries a server's tool hints (readOnlyHintand friends) through the stdio and URL clients and the manager cache.task.tool_usedtelemetry gainsmodesession.resumestarts a runtime for a saved session ID and reads history on the hub, instead of requiringinitialMessages- Cloud task creation accepts
initialMessageto create and send in one call, andlocalGitto launch from a captured Git snapshot HubCloudSessionClient.getArtifactDownloadUrl(sessionId, artifactId)returns a signed URL without starting the sandbox- Provider, model, MCP and MCP OAuth management are available as hub commands, with token authentication required for provider management
- The hub can return session history in bounded chunks and archived cloud history
- The hub validates caller accounts for cloud commands, and no longer re-sends a rejected Cline refresh token on every cloud poll
- Hub cloud requests no longer duplicate the API prefix
- Hub session handlers are retained when a session deletion fails
- Confirmed cloud handoff publication is exported from
@cline/core/cloudfor direct hosts @cline/sharedaddsresolveClineAppUrl, and the account response carriesdataPrivacyPathfor the web app's privacy settings page@cline/uiaddsSectionHeading,Banner,ItemCard,DetailList, controlledDialogcomponents and a UX verification report carousel with screenshot downloads. Buttons, badges and switches are refreshed (loading and pending states, a small switch size), along with the colour tokens and a newtext-xxsstep- Removed the
CLINE_CAPTURE_*provider request capture, which wrote full request bodies to disk - Every SDK package now includes its license file
- Refreshed the model catalog (6,457 → 7,621 models). Adds 94 providers from models.dev and drops Lilac and Tempr. The Cline recommended list adds Muse Ember. The Cline free list drops Reflection Beam, Laguna S 2.1 and Solar Mini 4, so the
clineprovider's bundled default is Nemotron 3.5 Super VL. ClinePass drops DeepSeek V4.1 Flash, Mimo V2.6 Flash, Mimo V2.6 Pro, MiniMax M3, Qwen3.7 Plus and Qwen3.7 Max. Default models change for 67 other providers, mostly to Kimi K3.1 Pro, Gemini 4 Neon (including thegeminiandvertexproviders) or DeepSeek V4.1 Flash 1017. Qwen models now report tiered families such asqwen-plusandqwen-max
Full Changelog: https://github.com/cline/cline/compare/sdk/sdk/v0.2.0...sdk/sdk/v0.2.1