Agent Zero v2.2: In-Chat Model Setup, Streaming Fallbacks, & UI Polish
v2.2 smooths first-run model setup, makes provider choices more explicit, hardens streamed fallback behavior, and polishes everyday chat, memory, and WebUI workflows.
Model setup now happens in chat โ If a model is missing on first send, Agent Zero opens setup inside the current thread, keeps the pending prompt through refresh, and sends it automatically after configuration.
One provider selection step โ Cloud, Account, and Local choices now live in a single onboarding step instead of separate illustrated paths.
Utility Model selection is explicit โ Utility models no longer silently mirror the Main Model and now default to each provider's utility model when available.
OAuth model choices stay intentional โ Connecting an OAuth account no longer auto-fills Main and Utility models; users are sent to model configuration to choose them.
Stale OAuth provider selection fixed โ Stored model slots no longer show a disconnected OAuth provider as selected.
Claude Sonnet 5 defaults โ The bundled config, Balance preset, and onboarding defaults now use anthropic/claude-sonnet-5 as the default main model.
Codex OAuth defaults refreshed โ Stale Codex model metadata was removed so connected accounts use upstream /models responses, with fallback updated to gpt-5.5.
๐ LLM Transport & Streaming
Fallback before output starts โ Responses endpoint failures now fall back to Chat Completions before any output is emitted, including when the Responses mock sees real SSE streams.
Streamed tool-call deltas preserved โ Chat Completions tool-call deltas remain structured function-call items so fallback providers can still drive tools.
Parallel streamed tool parsing fixed โ Nested tool_calls objects no longer close the stream early before the parallel wrapper finishes.
๐ง Chat & Memory
Deleted chats leave the sidebar โ Removed saved chat files are pruned from sidebar state so stale in-memory contexts disappear.
Memory search inputs normalized โ memory_load threshold and limit values are normalized before vector search, preventing numeric strings from reaching FAISS unchanged.
Rename failures are visible โ Users are notified when automatic chat renaming cannot reach the Utility Model, while the rename task remains best-effort.
๐ฅ๏ธ Web UI
Markdown-backed code blocks โ Typing a triple-backtick fence and pressing Enter creates a visual code block that serializes back to fenced Markdown on send.
File browser menus no longer clip โ Action menus render outside the scroll container with fixed positioning.
Cleaner message copy/paste โ Message action button chrome is non-selectable, so copying message text no longer grabs toolbar labels.
Settings secrets avoid password managers โ Secret fields render as masked text inputs instead of browser password fields.
What's New waits for new content โ Cards are disabled until new content is added, while manual access still shows an empty state.
๐ Documentation
First-run docs refreshed โ Onboarding screenshots and first-run docs now match the new welcome screen, in-chat model gate, and provider paths.
Local model server guidance clarified โ Docker host-gateway addressing is documented for cases where container localhost cannot reach host loopback.
Memory plugin assumptions removed โ Non-plugin documentation now treats the memory plugin as optional.
Launcher links updated โ A0 Launcher download links now point to v1.2.
We use essential cookies for login and saving your preferences. With your consent, we also
use analytics cookies (Google Analytics) to improve the website.
Learn more