v2.0.5

davidfowl/tallyv2.0.5May 13, 2026by enricoros

AI Summary

This release focuses on enhancing long-running AI sessions with persistent containers and resumable research capabilities. It introduces support for several advanced AI models and improves the user interface with new formatting and organizational tools.

Key Highlights

Introduction of Anthropic Containers for persistent files, bash sessions, and Skills across turns.
Support for new AI models including Opus 4.7, GPT-5.5, and DeepSeek V4.
Gemini Deep Research is now fully resumable with SSE migration and recovery modes.
UX improvements include inline message timestamps, single-dollar LaTeX support, and new chat startup options.
Addition of new vendors MiniMax and Arcee AI.

New Features

Persistent files and bash sessions in Anthropic Containers
Skills enabled by default with improved selector
Full SSE migration for Gemini Deep Research
Inline message timestamps with TimeAgo
Single-dollar inline LaTeX rendering
New Global AI Settings store

Full Release Notes

# Big-AGI 2.0.5 - Roberto

> Named after my father, on his birthday.

### Resilience, persistence, excellence.

Long-running AI sessions get a serious upgrade. Anthropic Containers give you persistent files, Skills, and bash sessions that span turns. Gemini Deep Research is now fully resumable - reconnect after pauses, recover from server cuts, cancel cleanly. Add to that Opus 4.7 with 1M tokens, GPT-5.5, DeepSeek V4, and two new vendors.


<img width="1536" height="1024" alt="205-b" src="https://github.com/user-attachments/assets/11e6052a-6dc9-4ca4-9a65-aa7f6846790a" />


### Models
- **Anthropic Opus 4.7** with 1M token context, X-High effort, auto-detect features and 0-day models
- **OpenAI GPT-5.5** family with 1M context, plus **gpt-image-2** for image generation
- **DeepSeek V4** Flash and Pro with native thinking/reasoning_effort
- **Gemini 3.1 Flash**, 3.1 Flash Lite, 3.1 Flash TTS, Robotics-ER 1.6, and Gemma 4
- **xAI Grok 4.3** with encrypted reasoning and reasoning summaries
- **Moonshot Kimi K2.6**
- New vendors: **MiniMax** and **Arcee AI**

### Anthropic
- **Containers** (1h): persistent files, bash sessions, Skills, dynamic filtering, temp files across turns
- **Skills**: enabled by default with improved selector
- **File API**: download, embed, delete - text and image inlining via Container -> File pipeline
- Server-side recovered errors ignored, refusal details surfaced, code execution failures traced

### Gemini Deep Research
- Full SSE migration (no more POST + GET-loop)
- Resumable across pauses with full recovery mode (#1088)
- Cancel and delete controls, multiple reattaches
- Audio + thoughts support, image-as-figure handling
- Option to disable visualizations (#1095)

### Beam
- Auto-title beam chats when done (#1078)
- No accidental wipe with Ctrl+Shift+B (#1079); no re-beam while open
- No ghost columns in 2-beam mode (#1073); title edit fix (#1085)

### UX
- Inline message timestamps with TimeAgo (#1065)
- New chat on startup option (#1002)
- Single-dollar inline LaTeX (#795)
- Model pub dates, "new" badges on models under 30 days
- Sort LLM categories by name, filter chat drawer by open beams

### Also New
- AIX Resume framework with stop/cancel/recovery across providers
- xAI: encrypted reasoning by default, reasoning summaries always (#1091)
- OpenAI Responses: encrypted reasoning, tool re-parsing fixes
- New Global AI Settings store
- Performance: throttled code highlighting, memoized reasoning chips, lazy per-chat stores

### Fixes
- Voice features hidden in browsers without Speech Recognition (#1061)
- OpenRouter models refresh (#804)
- Zod 4 type strictness (#1072)

## New Contributors
* @alexdenton123 made their first contribution in https://github.com/enricoros/big-AGI/pull/1062
* @tredondo made their first contribution in https://github.com/enricoros/big-AGI/pull/1074

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.4...v2.0.5

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.