SDK v0.0.90 — Performance and storage optimization
Agent teams now persist only changed entities instead of the entire state on every stream chunk or heartbeat, significantly reducing database writes and preventing storage bloat. Additionally, standalone provider requests can now resolve Cline surface headers and default models have been updated across multiple providers.
- Agent teams no longer slow down as a session runs or while a teammate is streaming. Every streamed chunk and 2-second heartbeat used to re-save the whole team state, including every finished teammate's full transcript (one local
teams.dbreached 1.66 GB, with a single run row rewritten ~339k times). Stream chunks and heartbeats now go to live UIs only and are never persisted, only changed entities are written (batched into one transaction every ~300 ms), run records keep a summary instead of the transcript, andteam_eventsis capped per team (2000 rows, 30 days). SQLite team storage moves to schema v2 with a one-time migration that compacts existing data;SqliteTeamStore.vacuum()returns the freed space when called explicitly. Failed team writes are retried instead of dropped - Standalone provider requests made outside a session (such as commit message generation) can now resolve Cline surface headers.
sessionIdis optional inresolveProviderRequestHeaders, andX-Task-IDis omitted rather than sent empty - Refreshed the model catalog. Default models change for DigitalOcean (GPT-6.1 Sol), GMI Cloud (Qwen 3.8 Flash), NanoGPT (Pareto 26.10 Preview), Nvidia (DeepSeek V4.1 Flash), and Ofox (GPT-6.1 Sol)
Full Changelog: sdk/sdk/v0.0.89...sdk/sdk/v0.0.90
Source: original entry ↗
More from Cline
Follow Cline to get its new changes in your feed and email digest.
Desktop v0.0.45
SSH remotes and environment connections now work correctly, with improved branch checking performance. Long model names display fully when space allows, reasoning mode works on additional models, and the model catalog has been refreshed with new defaults including Claude Haiku 5.5.
CLI v3.0.70
Multiple bug fixes and improvements including fixes for GPT-6 Astra and Claude Fable 5 error handling, MCP server input reading, settings migration, and CLI command validation. Enhanced header preservation for MCP add command, improved error messaging for invalid options, and refreshed model catalog with Claude Haiku 5.5 support.
SDK v0.0.92
Unified AI SDK to single release line (ai 7.0.120 with @ai-sdk/* packages on provider-utils 5.0.50), improved reasoning/thinking handling for GPT and Claude models that don't support these features, fixed EPIPE handling in stdio MCP clients and removed Winston's uncaught exception handler from SAP AI Core provider, added parseMcpHeaders export to @cline/core, and refreshed model catalog including new Claude Haiku 5.5.