Changelog - agtOS

Unreleased

OpenAI cloud provider — GPT-4o and GPT-4o Mini available as an alternative cloud tier via AGTOS_CLOUD_PROVIDER=openai. Full streaming, tool calling, session management, and health checks. (ADR-019)
Cloud provider selection — new AGTOS_CLOUD_PROVIDER env var to choose between claude (default) and openai for Tier 3 inference
CLI API key validation — agtos setup validates API keys against the actual provider API before saving
First-run detection — agtos start guides you to agtos setup when no configuration exists
Structured startup progress — agtos start shows step-by-step service initialization with status icons
Doctor credential validation — agtos doctor checks API key functionality, network connectivity, and reports feature degradation
Onboarding mic test — real-time audio level visualization during desktop app setup
Settings credential management — update API keys inline with validation from the Settings page

Auth overhaul — removed OAuth/setup token support. Authentication is now API key only for all providers. ANTHROPIC_AUTH_TOKEN and CLAUDE_CODE_OAUTH_TOKEN env vars are no longer recognized.
Setup wizard simplified — single API key prompt per provider (Anthropic, then optional OpenAI). The Max subscription token flow has been removed.
CLI transport restructured — opt-in via AGTOS_CLAUDE_TRANSPORT=cli. Passes ANTHROPIC_API_KEY to the subprocess instead of OAuth tokens.
Model router — RoutingDecision.provider now includes 'openai' as a valid value. Cloud routing uses the configured provider.
Default speech engine — changed from speaches to sherpa-onnx (backward-compatible env var fallback)

Onboarding wizard not shown in Tauri desktop app on first launch
Uptime display showing incorrect values (was using stale module-level timestamp)
503 error during first few minutes after launch (/api/health now bypasses initialization gate)
OpenAI tool calls silently dropped during streaming
OpenAI stream cancellation for voice barge-in
Various OAuth UI remnants removed from Settings page