ClineProduct update
Cline · v0.0.95
Cline SDK v0.0.95 sends max_completion_tokens in OpenAI-compatible requests for GPT-6 and similar models, so OpenAI and Azure stop rejecting them, while Azure's gpt-35-turbo still uses max_tokens. The hub daemon records the client that launched it and publishes it as OTel resource attributes, and the telemetry self-check report now includes traces_exporter. The model catalog grows from 6,952 to 7,041 models with two new providers, CommandCode and Reflection, the cline provider's bundled default returns to Claude Sonnet 5.5 from Gemini 4 Argon, and several other providers get new default models.
SSH remote hubs report the local client with transport ssh.
Saved . A shortened excerpt from GitHub Releases; the original publisher retains authorship.