- 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