Agent Zero v2.14

Highlights

Significantly faster startup and chat loading — Embedding warm-up now overlaps with chat restoration and startup watchdogs, reducing median boot-to-first-token by ~27% and chat-switch latency by running model/profile refreshes independently of snapshot rendering.
Upgraded LiteLLM (1.104.0) and OpenAI SDK (2.54.0) with an automatic startup migration for existing Docker instances, including installed-SDK HTTP test coverage.
Native LiteLLM routing for core providers — Nebius, Venice chat, Z.AI/Coding, and OpenRouter embeddings now use LiteLLM's built-in integrations, simplifying provider configuration while preserving existing overrides.
Responses prompt caching fix for long conversations — Completed Responses turns now retain masked extras at their original boundaries, preventing growing conversations from discarding cacheable prompt prefixes. A live test reached 99.3% cache hit rate at 131K input tokens.

Reduced browser startup and rendering overhead — avoids launching Chromium for empty tab listings, eliminates redundant load waits, and reuses native viewer display size. Local navigation medians improved from 474→83 ms, content reads from 82→19 ms.
Simplified Browser quick settings to focus on preset, Host/Container, zoom, and extensions; moved extension management and Chromium settings pages into Browser config. Added annotation screenshots as an opt-in setting.
Removed overlapping tooltips from Browser quick settings popover.

Fixed disappearing chats when Sidebar Folders was disabled and another plugin imported the folders store.
Fixed sidebar folder lag during activity and focus updates by replacing repeated full-context scans with a shared parent-child index. Median activity updates dropped from ~67 ms to 15 ms.
Persisted sidebar Project, Status, and Last Activity filters across reloads.
Fixed chat activity timestamps not updating when continuing a chat, by writing to the context timestamp in the shared history writer.
Revealed children of selected subagents at every delegation depth.
Fixed chat naming to preserve manual names under "always" mode and validate custom names before marking them manual.
Fixed pruning of just-saved chat contexts by re-checking disk before removal.

Reload model presets before the preset editor opens, preventing stale drafts from deleting presets created in other tabs or via the API. Fixes #1928.
Capped preset and agent profile selector menus to stay within the viewport.
Detect Claude models across all providers (OpenRouter, Vertex AI, Bedrock, etc.) for thoughts-prompt adaptation, not just those with "anthropic" in the provider name.
Restored full-response repeat checks for native tool calls, including commentary comparison.
Added context window display controls and price currency selection with Frankfurter exchange-rate conversion and 24-hour caching.
Enabled Venice and Agent Zero API cache routing; exposed a0_prompt_cache_mode for custom providers.

Improved Codex reconnection flow — handles rejected refresh tokens with actionable toasts, offers Reconnect without manual disconnect, and displays device challenge codes in a copyable box with accessible feedback.
Pinned Codex client version to 0.160.1.
Added success feedback when copying OAuth device codes.

Direct subordinate delegation now runs through the child's own context task, making child chats visible as Working/Paused and independently stoppable. Propagates caller cancellation while treating child-only Stop as recoverable.
Terminal I/O no longer blocks shared event loops — uses nonblocking POSIX PTY reads and cooperative writes.
Fixed native Windows TTY cleanup to avoid evaluating POSIX-only SIGKILL.
Fixed SSH command truncation — uses sendall through asyncio.to_thread to deliver complete commands including large heredocs.
Host Computer Use sessions now start automatically on the first action within the same tool call.

Fixed user plugin precedence — bundled values no longer overwrite community provider/profile definitions or subordinate profile settings during merges.
Scheduler prompt editing now uses full-width resizable fields with an expanded modal view; supports optional tasks.yaml files alongside JSON.
Added Paradee Heart as the default Local TTS voice alongside Kokoro, with lazy CPU ONNX synthesis and cached model assets.
Single-folder downloads are now named after the folder instead of using a generic timestamped archive name.

Raised security floors for aiohttp, anyio, urllib3, filelock, fsspec, and multidict.
Seeded APT indexes only when absent, skipping refresh on normal container boots.
Added Chat Completions reasoning fallback test coverage.
Updated Launcher README links to v1.9.