sdk/sdk/v0.0.91
mudler/LocalAIsdk/sdk/v0.0.91Oct 7, 2026by github-actions[bot]
Upgrading?
AI Summary
SDK v0.0.91 improves reasoning level handling, adds Langfuse tracing support, and fixes Anthropic provider options for custom endpoints.
Key Highlights
- Unknown finish reason handling
- Reasoning level snapping to model capabilities
- Langfuse tracing support
- Provider options fix for custom endpoints
New Features
- Finish reason handling (unknown)
- Reasoning level adjustment
- Langfuse tracing for BYOK providers
- Provider metadata and auth options
- Rule loading from records
Full Release Notes
- Responses that end with a missing or unrecognized finish reason are no longer treated as successful completions. `AgentModelFinishReason` gains `unknown` (the AI SDK adapter maps unified `other` and missing reasons to it instead of `stop`). Without tool activity, the agent keeps the partial response and continues once with a hidden user message; a second unknown finish fails the run. Queued user messages are now consumed at every request boundary, including the first iteration - Stdio MCP servers get a 10s default initialize budget (was 3s). `npx`/`uvx` launchers through cmd.exe on Windows routinely took 3-6s and were silently dropped from the session. An explicit `timeout` still overrides it - The Anthropic provider sends the server-side refusal `fallbacks` option only to `api.anthropic.com`. Custom endpoints such as Azure AI Foundry rejected it with a 400. New `isOfficialAnthropicEndpoint` helper - The portable reasoning level for the `cline` and `openai-compatible` adapters snaps to the model's advertised effort levels. Kimi K3 (low/high/max) was sent `medium` and `minimal`, which it rejects - OpenAI-compatible providers (generic, `vercel-ai-gateway`, user-defined ids) write `providerOptions` under the camelCase alias only, which stops the per-chunk `providerOptions key 'openai-compatible'` deprecation warning from `@ai-sdk/openai-compatible` - New `apiKeyOptional` provider fact (`GatewayProviderMetadata.apiKeyOptional`, `resolveProviderApiKeyOptional`, `ProviderListItem.auth.apiKeyOptional`), declared on openai-compatible, ollama, lmstudio, litellm, vertex, bedrock, and user-added endpoints from `providers.json`/`models.json` - Rules: new `listEnabledRulesFromRecords` / `loadRulesForSystemPromptFromRecords` exports. The combined user-instruction service now orders rules by name, matching the single-workspace path - Opt-in Langfuse tracing for BYOK providers (`CLINE_LANGFUSE_ALL_PROVIDERS`), plus operator tags, metadata and environment via `CLINE_LANGFUSE_TAGS`, `CLINE_LANGFUSE_METADATA`, `LANGFUSE_TRACING_ENVIRONMENT` - Hook discovery telemetry handles Windows path separators - Refreshed the model catalog. The Cline free list adds Solar Mini 4 and drops DeepSeek V4.1 Flash and space-bunny-alpha. Adds the Engy provider. Default models change for AKI.IO, Blue Claw, CoralBricks, CrossModel (GPT-6.1 Sol), DevPass, LLM Gateway, Mistral, NanoGPT, Requesty (Mistral Large 4), Neon (Claude Opus 5.5), Subconscious, and The Grid AI **Full Changelog**: https://github.com/cline/cline/compare/sdk/sdk/v0.0.90...sdk/sdk/v0.0.91
Related Repositories
ollama/ollama★ 184,205
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,051
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
asheshgoplani/agent-deck★ 102,148
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
infiniflow/ragflow★ 92,612
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.