Auth: Clerk provider

2026-05-10 21:50:14 -07:00 · 2024-05-13 12:11:26 -07:00
89 changed files with 1091 additions and 2009 deletions
@@ -11,8 +11,11 @@ name: Create and publish Docker images

 on:
  push:
+    branches:
+      - main
+      #- main-stable  # Disabled as the v* tag is used for stable releases
    tags:
-      - 'v1.1*'       # V1 legacy tags only (v1.10.x - v1.19.x range)
+      - 'v*'  # Trigger on version tags (e.g., v1.7.0)

 env:
  REGISTRY: ghcr.io
@@ -48,13 +51,11 @@ jobs:
        with:
          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
          tags: |
-            # V1 legacy pointers
-            type=raw,value=v1
-            type=raw,value=v1-stable
-
-            # Exact version tags (v1.16.11 and 1.16.11)
-            type=ref,event=tag
-            type=semver,pattern={{version}}
+            type=raw,value=development,enable=${{ github.ref == 'refs/heads/main' }}
+            type=raw,value=stable,enable=${{ github.ref == 'refs/heads/main-stable' }}
+            type=ref,event=tag  # Use the tag name as a tag for tag builds
+            type=semver,pattern={{version}}  # Generate semantic versioning tags for tag builds
+            type=sha # Just in case none of the above applies

      - name: Build and push Docker image
        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
@@ -64,10 +65,5 @@ jobs:
          platforms: linux/amd64,linux/arm64
          push: true
          tags: ${{ steps.meta.outputs.tags }}
-          labels: |
-            org.opencontainers.image.title=Big-AGI v1 (Legacy)
-            org.opencontainers.image.description=Big-AGI v1 - Legacy version. For the latest version, see GitHub and big-agi.com
-            org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
-            org.opencontainers.image.documentation=https://big-agi.com
-          build-args: |
-            NEXT_PUBLIC_GA4_MEASUREMENT_ID=${{ secrets.GA4_MEASUREMENT_ID }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: NEXT_PUBLIC_GA4_MEASUREMENT_ID=${{ secrets.GA4_MEASUREMENT_ID }}
@@ -1,6 +1,6 @@
 # Base
-FROM node:22-alpine AS base
-ENV NEXT_TELEMETRY_DISABLED=1
+FROM node:18-alpine AS base
+ENV NEXT_TELEMETRY_DISABLED 1


 # Dependencies
@@ -11,11 +11,8 @@ WORKDIR /app
 COPY package*.json ./
 COPY src/server/prisma ./src/server/prisma

-# link ssl3 for latest Alpine
-RUN sh -c '[ ! -e /lib/libssl.so.3 ] && ln -s /usr/lib/libssl.so.3 /lib/libssl.so.3 || echo "Link already exists"'
-
 # Install dependencies, including dev (release builds should use npm ci)
-ENV NODE_ENV=development
+ENV NODE_ENV development
 RUN npm ci


@@ -31,11 +28,8 @@ ENV NEXT_PUBLIC_GA4_MEASUREMENT_ID=${NEXT_PUBLIC_GA4_MEASUREMENT_ID}
 COPY --from=deps /app/node_modules ./node_modules
 COPY . .

-# link ssl3 for latest Alpine
-RUN sh -c '[ ! -e /lib/libssl.so.3 ] && ln -s /usr/lib/libssl.so.3 /lib/libssl.so.3 || echo "Link already exists"'
-
 # Build the application
-ENV NODE_ENV=production
+ENV NODE_ENV production
 RUN npm run build

 # Reduce installed packages to production-only
@@ -57,8 +51,8 @@ COPY --from=builder --chown=nextjs:nodejs /app/node_modules ./node_modules
 COPY --from=builder --chown=nextjs:nodejs /app/src/server/prisma ./src/server/prisma

 # Minimal ENV for production
-ENV NODE_ENV=production
-ENV PATH=$PATH:/app/node_modules/.bin
+ENV NODE_ENV production
+ENV PATH $PATH:/app/node_modules/.bin

 # Run as non-root user
 USER nextjs
@@ -1,41 +1,214 @@
-# BIG-AGI Legacy  ✨
+# BIG-AGI 🧠✨

-> **⚠️ IMPORTANT: `v1` Branch - End of Life**
->
-> This is the **v1** (formerly **v1-stable**) branch, which reached end-of-life in October 2025.
-> - **For the latest Big-AGI**, see the [**main** branch](https://github.com/enricoros/big-AGI/tree/main) and [**big-agi.com**](https://big-agi.com)
-> - **v1.16.11 is the final legacy release** - No further updates will be provided
-> - Docker users: `:stable`, `:development` and `:latest` point to the `main` branch
+Welcome to big-AGI, the AI suite for professionals that need function, form,
+simplicity, and speed. Powered by the latest models from 12 vendors and
+open-source servers, `big-AGI` offers best-in-class Chats,
+[Beams](https://github.com/enricoros/big-AGI/issues/470),
+and [Calls](https://github.com/enricoros/big-AGI/issues/354) with AI personas,
+visualizations, coding, drawing, side-by-side chatting, and more -- all wrapped in a polished UX.
+
+Stay ahead of the curve with big-AGI. 🚀 Pros & Devs love big-AGI. 🤖
+
+[![Official Website](https://img.shields.io/badge/BIG--AGI.com-%23096bde?style=for-the-badge&logo=vercel&label=launch)](https://big-agi.com)
+
+Or fork & run on Vercel
+
+[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI&env=OPENAI_API_KEY&envDescription=Backend%20API%20keys%2C%20optional%20and%20may%20be%20overridden%20by%20the%20UI.&envLink=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI%2Fblob%2Fmain%2Fdocs%2Fenvironment-variables.md&project-name=big-AGI)
+
+## 👉 [roadmap](https://github.com/users/enricoros/projects/4/views/2) 👉 [installation](docs/installation.md) 👉 [documentation](docs/README.md)
+
+> Note: bigger better features (incl. Beam-2) are being cooked outside of `main`.
+
+[//]: # (big-AGI is an open book; see the **[ready-to-ship and future ideas]&#40;https://github.com/users/enricoros/projects/4/views/2&#41;** in our open roadmap)
+
+### What's New in 1.16.1 · May 13, 2024 (minor release, models support)
+
+- Support for the new OpenAI GPT-4o 2024-05-13 model
+
+### What's New in 1.16.0 · May 9, 2024 · Crystal Clear
+
+- [Beam](https://big-agi.com/blog/beam-multi-model-ai-reasoning) core and UX improvements based on user feedback
+- Chat cost estimation 💰 (enable it in Labs / hover the token counter)
+- Save/load chat files with Ctrl+S / Ctrl+O on desktop
+- Major enhancements to the Auto-Diagrams tool
+- YouTube Transcriber Persona for chatting with video content, [#500](https://github.com/enricoros/big-AGI/pull/500)
+- Improved formula rendering (LaTeX), and dark-mode diagrams, [#508](https://github.com/enricoros/big-AGI/issues/508), [#520](https://github.com/enricoros/big-AGI/issues/520)
+- Models update: **Anthropic**, **Groq**, **Ollama**, **OpenAI**, **OpenRouter**, **Perplexity**
+- Code soft-wrap, chat text selection toolbar, 3x faster on Apple silicon, and more [#517](https://github.com/enricoros/big-AGI/issues/517), [507](https://github.com/enricoros/big-AGI/pull/507)
+
+#### 3,000 Commits Milestone · April 7, 2024
+
+![big-AGI Milestone](https://github.com/enricoros/big-AGI/assets/32999/47fddbb1-9bd6-4b58-ace4-781dfcb80923)
+
+- 🥇 Today we <b>celebrate commit 3000</b> in just over one year, and going stronger 🚀
+- 📢️ Thanks everyone for your support and words of love for Big-AGI, we are committed to creating the best AI experiences for everyone.
+
+### What's New in 1.15.0 · April 1, 2024 · Beam
+
+- ⚠️ [**Beam**: the multi-model AI chat](https://big-agi.com/blog/beam-multi-model-ai-reasoning). find better answers, faster - a game-changer for brainstorming, decision-making, and creativity. [#443](https://github.com/enricoros/big-AGI/issues/443)
+- Managed Deployments **Auto-Configuration**: simplify the UI models setup with backend-set models. [#436](https://github.com/enricoros/big-AGI/issues/436)
+- Message **Starring ⭐**: star important messages within chats, to attach them later. [#476](https://github.com/enricoros/big-AGI/issues/476)
+- Enhanced the default Persona
+- Fixes to Gemini models and SVGs, improvements to UI and icons
+- 1.15.1: Support for Gemini Pro 1.5 and OpenAI Turbo models
+- Beast release, over 430 commits, 10,000+ lines changed: [release notes](https://github.com/enricoros/big-AGI/releases/tag/v1.15.0), and changes [v1.14.1...v1.15.0](https://github.com/enricoros/big-AGI/compare/v1.14.1...v1.15.0)
+
+<details>
+<summary>What's New in 1.14.1 · March 7, 2024 · Modelmorphic</summary>
+
+- **Anthropic** [Claude-3](https://www.anthropic.com/news/claude-3-family) model family support. [#443](https://github.com/enricoros/big-AGI/issues/443)
+- New **[Perplexity](https://www.perplexity.ai/)** and **[Groq](https://groq.com/)** integration (thanks @Penagwin). [#407](https://github.com/enricoros/big-AGI/issues/407), [#427](https://github.com/enricoros/big-AGI/issues/427)
+- **[LocalAI](https://localai.io/models/)** deep integration, including support for [model galleries](https://github.com/enricoros/big-AGI/issues/411)
+- **Mistral** Large and Google **Gemini 1.5** support
+- Performance optimizations: runs [much faster](https://twitter.com/enricoros/status/1756553038293303434?utm_source=localhost:3000&utm_medium=big-agi), saves lots of power, reduces memory usage
+- Enhanced UX with auto-sizing charts, refined search and folder functionalities, perfected scaling
+- And with more UI improvements, documentation, bug fixes (20 tickets), and developer enhancements
+
+</details>
+
+<details>
+<summary>What's New in 1.13.0 · Feb 8, 2024 · Multi + Mind</summary>
+
+https://github.com/enricoros/big-AGI/assets/32999/01732528-730e-41dc-adc7-511385686b13
+
+- **Side-by-Side Split Windows**: multitask with parallel conversations. [#208](https://github.com/enricoros/big-AGI/issues/208)
+- **Multi-Chat Mode**: message everyone, all at once. [#388](https://github.com/enricoros/big-AGI/issues/388)
+- **Export tables as CSV**: big thanks to @aj47. [#392](https://github.com/enricoros/big-AGI/pull/392)
+- Adjustable text size: customize density. [#399](https://github.com/enricoros/big-AGI/issues/399)
+- Dev2 Persona Technology Preview
+- Better looking chats with improved spacing, fonts, and menus
+- More: new video player, [LM Studio tutorial](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-lmstudio.md) (thanks @aj47), [MongoDB support](https://github.com/enricoros/big-AGI/blob/main/docs/deploy-database.md) (thanks @ranfysvalle02), and speedups
+
+</details>
+
+<details>
+<summary>What's New in 1.12.0 · Jan 26, 2024 · AGI Hotline</summary>
+
+https://github.com/enricoros/big-AGI/assets/32999/95ceb03c-945d-4fdd-9a9f-3317beb54f3f
+
+- **Voice Calls**: real-time voice call your personas out of the blue or in relation to a chat [#354](https://github.com/enricoros/big-AGI/issues/354)
+- Support **OpenAI 0125** Models. [#364](https://github.com/enricoros/big-AGI/issues/364)
+- Rename or Auto-Rename chats.  [#222](https://github.com/enricoros/big-AGI/issues/222), [#360](https://github.com/enricoros/big-AGI/issues/360)
+- More control over **Link Sharing** [#356](https://github.com/enricoros/big-AGI/issues/356)
+- **Accessibility** to screen readers [#358](https://github.com/enricoros/big-AGI/issues/358)
+- Export chats to Markdown [#337](https://github.com/enricoros/big-AGI/issues/337)
+- Paste tables from Excel [#286](https://github.com/enricoros/big-AGI/issues/286)
+- Ollama model updates and context window detection fixes [#309](https://github.com/enricoros/big-AGI/issues/309)
+
+</details>
+
+<details>
+<summary>What's New in 1.11.0 · Jan 16, 2024 · Singularity</summary>
+
+https://github.com/enricoros/big-AGI/assets/1590910/a6b8e172-0726-4b03-a5e5-10cfcb110c68
+
+- **Find chats**: search in titles and content, with frequency ranking. [#329](https://github.com/enricoros/big-AGI/issues/329)
+- **Commands**: command auto-completion (type '/'). [#327](https://github.com/enricoros/big-AGI/issues/327)
+- **[Together AI](https://www.together.ai/products#inference)** inference platform support (good speed and newer models). [#346](https://github.com/enricoros/big-AGI/issues/346)
+- Persona Creator history, deletion, custom creation, fix llm API timeouts
+- Enable adding up to five custom OpenAI-compatible endpoints
+- Developer enhancements: new 'Actiles' framework
+
+</details>
+
+<details>
+<summary>What's New in 1.10.0 · Jan 6, 2024 · The Year of AGI</summary>
+
+- **New UI**: for both desktop and mobile, sets the stage for future scale. [#201](https://github.com/enricoros/big-AGI/issues/201)
+- **Conversation Folders**: enhanced conversation organization. [#321](https://github.com/enricoros/big-AGI/issues/321)
+- **[LM Studio](https://lmstudio.ai/)** support and improved token management
+- Resizable panes in split-screen conversations.
+- Large performance optimizations
+- Developer enhancements: new UI framework, updated documentation for proxy settings on browserless/docker
+
+</details>
+
+For full details and former releases, check out the [changelog](docs/changelog.md).
+
+## 👉 Key Features ✨
+
+| ![Advanced AI](https://img.shields.io/badge/Advanced%20AI-32383e?style=for-the-badge&logo=ai&logoColor=white) | ![100+ AI Models](https://img.shields.io/badge/100%2B%20AI%20Models-32383e?style=for-the-badge&logo=ai&logoColor=white) | ![Flow-state UX](https://img.shields.io/badge/Flow--state%20UX-32383e?style=for-the-badge&logo=flow&logoColor=white) | ![Privacy First](https://img.shields.io/badge/Privacy%20First-32383e?style=for-the-badge&logo=privacy&logoColor=white) | ![Advanced Tools](https://img.shields.io/badge/Fun%20To%20Use-f22a85?style=for-the-badge&logo=tools&logoColor=white) |  
+|---------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------| 
+| **Chat**<br/>**Call**<br/>**Beam**<br/>**Draw**, ...                                                          | Local & Cloud<br/>Open & Closed<br/>Cheap & Heavy<br/>Google, Mistral, ...                                              | Attachments<br/>Diagrams<br/>Multi-Chat<br/>Mobile-first UI                                                          | Stored Locally<br/>Easy self-Host<br/>Local actions<br/>Data = Gold                                                    | AI Personas<br/>Voice Modes<br/>Screen Capture<br/>Camera + OCR                                                      |
+
+![big-AGI screenshot](docs/pixels/big-AGI-compo-20240201_small.png)
+
+You can easily configure 100s of AI models in big-AGI:
+
+| **AI models**       | _supported vendors_                                                                                                                                                                                                             |
+|:--------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| Opensource Servers  | [LocalAI](https://localai.com) (multimodal) · [Ollama](https://ollama.com/) · [Oobabooga](https://github.com/oobabooga/text-generation-webui)                                                                                   |
+| Local Servers       | [LM Studio](https://lmstudio.ai/)                                                                                                                                                                                               |
+| Multimodal services | [Azure](https://azure.microsoft.com/en-us/products/ai-services/openai-service) · [Google Gemini](https://ai.google.dev/) · [OpenAI](https://platform.openai.com/docs/overview)                                                  |
+| Language services   | [Anthropic](https://anthropic.com) · [Groq](https://wow.groq.com/) · [Mistral](https://mistral.ai/) · [OpenRouter](https://openrouter.ai/) · [Perplexity](https://www.perplexity.ai/) · [Together AI](https://www.together.ai/) | 
+| Image services      | [Prodia](https://prodia.com/) (SDXL)                                                                                                                                                                                            | 
+| Speech services     | [ElevenLabs](https://elevenlabs.io) (Voice synthesis / cloning)                                                                                                                                                                 | 
+
+Add extra functionality with these integrations:
+
+| **More**     | _integrations_                                                                                                 |
+|:-------------|:---------------------------------------------------------------------------------------------------------------| 
+| Web Browse   | [Browserless](https://www.browserless.io/) · [Puppeteer](https://pptr.dev/)-based                              |
+| Web Search   | [Google CSE](https://programmablesearchengine.google.com/)                                                     |
+| Code Editors | [CodePen](https://codepen.io/pen/) · [StackBlitz](https://stackblitz.com/) · [JSFiddle](https://jsfiddle.net/) |
+| Sharing      | [Paste.gg](https://paste.gg/) (Paste chats)                                                                    | 
+| Tracking     | [Helicone](https://www.helicone.ai) (LLM Observability)                                                        | 
+
+[//]: # (- [x] **Flow-state UX** for uncompromised productivity)
+
+[//]: # (- [x] **AI Personas**: Tailor your AI interactions with customizable personas)
+
+[//]: # (- [x] **Sleek UI/UX**: A smooth, intuitive, and mobile-responsive interface)
+
+[//]: # (- [x] **Efficient Interaction**: Voice commands, OCR, and drag-and-drop file uploads)
+
+[//]: # (- [x] **Privacy First**: Self-host and use your own API keys for full control)
+
+[//]: # (- [x] **Advanced Tools**: Execute code, import PDFs, and summarize documents)
+
+[//]: # (- [x] **Seamless Integrations**: Enhance functionality with various third-party services)
+
+[//]: # (- [x] **Open Roadmap**: Contribute to the progress of big-AGI)
+
+<br/>
+
+## 🚀 Installation
+
+To get started with big-AGI, follow our comprehensive [Installation Guide](docs/installation.md).
+The guide covers various installation options, whether you're spinning it up on
+your local computer, deploying on Vercel, on Cloudflare, or rolling it out
+through Docker.
+
+Whether you're a developer, system integrator, or enterprise user, you'll find step-by-step instructions
+to set up big-AGI quickly and easily.
+
+[![Installation Guide](https://img.shields.io/badge/Installation%20Guide-blue?style=for-the-badge&logo=read-the-docs&logoColor=white)](docs/installation.md)
+
+Or bring your API keys and jump straight into our free instance on [big-AGI.com](https://big-agi.com).
+
+<br/>
+
+# 🌟 Get Involved!
+
+[//]: # ([![Official Discord]&#40;https://img.shields.io/discord/1098796266906980422?label=discord&logo=discord&logoColor=%23fff&style=for-the-badge&#41;]&#40;https://discord.gg/MkH4qj2Jp9&#41;)
+[![Official Discord](https://discordapp.com/api/guilds/1098796266906980422/widget.png?style=banner2)](https://discord.gg/MkH4qj2Jp9)
+
+- [ ] 📢️ [**Chat with us** on Discord](https://discord.gg/MkH4qj2Jp9)
+- [ ] ⭐ **Give us a star** on GitHub 👆
+- [ ] 🚀 **Do you like code**? You'll love this gem of a project! [_Pick up a task!_](https://github.com/users/enricoros/projects/4/views/4) - _easy_ to _pro_
+- [ ] 💡 Got a feature suggestion? [_Add your roadmap ideas_](https://github.com/enricoros/big-agi/issues/new?&template=roadmap-request.md)
+- [ ] ✨ [Deploy](docs/installation.md) your [fork](docs/customizations.md) for your friends and family, or [customize it for work](docs/customizations.md)
+
+<br/>
+
+[//]: # ([![GitHub stars]&#40;https://img.shields.io/github/stars/enricoros/big-agi&#41;]&#40;https://github.com/enricoros/big-agi/stargazers&#41;)
+
+[//]: # ([![GitHub forks]&#40;https://img.shields.io/github/forks/enricoros/big-agi&#41;]&#40;https://github.com/enricoros/big-agi/network&#41;)
+
+[//]: # ([![GitHub pull requests]&#40;https://img.shields.io/github/issues-pr/enricoros/big-agi&#41;]&#40;https://github.com/enricoros/big-agi/pulls&#41;)
+
+[//]: # ([![License]&#40;https://img.shields.io/github/license/enricoros/big-agi&#41;]&#40;https://github.com/enricoros/big-agi/LICENSE&#41;)

 ---

-**For the latest Big-AGI:**
- [**Big-AGI Open**](https://github.com/enricoros/big-AGI/tree/main) - Open Source, for self-hosting, with bleeding edge models support
- [**Big-AGI Pro**](https://big-agi.com) - Hosted for Professionals with extra services and Cloud Sync
-
---
-
-### What's New in 1.16.11 · October 2025
-
- Final v1 legacy release. Branch reaches end-of-life.
-
-### What's New in 1.16.1...1.16.10 · 2024-2025 (patch releases)
-
- 1.16.10: Openrouter models fixes
- 1.16.9: Docker Gemini fix (R1 models are supported in latest Big-AGI)
- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models are supported in latest Big-AGI)
- 1.16.7: OpenAI support for GPT-4o 2024-08-06
- 1.16.6: Groq support for Llama 3.1 models
- 1.16.5: GPT-4o Mini support
- 1.16.4: 8192 tokens support for Claude 3.5 Sonnet
- 1.16.3: Anthropic Claude 3.5 Sonnet model support
- 1.16.2: Improve web downloads, as text, markdwon, or HTML
- 1.16.2: Proper support for Gemini models
- 1.16.2: Added the latest Mistral model
- 1.16.2: Tokenizer support for gpt-4o
- 1.16.2: Updates to Beam
- 1.16.1: Support for the new OpenAI GPT-4o 2024-05-13 model
-
---
-
-2023-2025 · Enrico Ros x [Big-AGI](https://big-agi.com) · License: [MIT](LICENSE) · Made with 💙
+2023-2024 · Enrico Ros x [big-AGI](https://big-agi.com) · License: [MIT](LICENSE) · Made with 💙
@@ -1,8 +1,6 @@
-# big-AGI v1 Documentation (Legacy)
+# big-AGI Documentation

-> **Note:** This is documentation for the **v1 legacy branch**. For the latest Big-AGI, see the [main branch](https://github.com/enricoros/big-AGI/tree/main) or visit [big-agi.com](https://big-agi.com).
-
-Find all the information you need to get started, configure, and effectively use big-AGI v1.
+Find all the information you need to get started, configure, and effectively use big-AGI.

 [//]: # (## Quick Start)

@@ -35,7 +33,7 @@ Detailed guides to configure your big-AGI interface and models.

 ## Deployment

-System integrators, administrators, whitelabelers: instead of using the public big-AGI instance on app.big-agi.com, you can deploy your own instance.
+System integrators, administrators, whitelabelers: instead of using the public big-AGI instance on get.big-agi.com, you can deploy your own instance.

 Step-by-step deployment and system configuration instructions.

@@ -55,7 +53,7 @@ Step-by-step deployment and system configuration instructions.
 Join our community or get support:

 - Visit our [GitHub repository](https://github.com/enricoros/big-AGI) for source code and issue tracking
- Check the latest updates and features on [Changelog](changelog.md) or the in-app [News](https://big-agi.com/news)
+- Check the latest updates and features on [Changelog](changelog.md) or the in-app [News](https://get.big-agi.com/news)
 - Connect with us and other users on [Discord](https://discord.gg/MkH4qj2Jp9) for discussions, help, and sharing your experiences with big-AGI

 Thank you for choosing big-AGI. We're excited to see what you'll build.
@@ -1,26 +1,18 @@
-## Changelog (v1 Legacy Branch)
+## Changelog

-This is a high-level changelog for the v1 legacy branch. For the latest Big-AGI, see the [main branch](https://github.com/enricoros/big-AGI).
+This is a high-level changelog. Calls out some of the high level features batched
+by release.

-### 1.16.11 · October 2025 (Final Release)
+- For the live roadmap, please see [the GitHub project](https://github.com/users/enricoros/projects/4/views/2)

-Final v1 legacy release. Branch reaches end-of-life.
+### 1.17.0 - Jun 2024

-### What's New in 1.16.1...1.16.10 · 2024-2025 (patch releases)
+- milestone: [1.17.0](https://github.com/enricoros/big-agi/milestone/17)
+- work in progress: [big-AGI open roadmap](https://github.com/users/enricoros/projects/4/views/2), [help here](https://github.com/users/enricoros/projects/4/views/4)

- 1.16.9: Docker Gemini fix (R1 models are supported in Big-AGI 2)
- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models are supported in Big-AGI 2)
- 1.16.7: OpenAI support for GPT-4o 2024-08-06
- 1.16.6: Groq support for Llama 3.1 models
- 1.16.5: GPT-4o Mini support
- 1.16.4: 8192 tokens support for Claude 3.5 Sonnet
- 1.16.3: Anthropic Claude 3.5 Sonnet model support
- 1.16.2: Improve web downloads, as text, markdwon, or HTML
- 1.16.2: Proper support for Gemini models
- 1.16.2: Added the latest Mistral model
- 1.16.2: Tokenizer support for gpt-4o
- 1.16.2: Updates to Beam
- 1.16.1: Support for the new OpenAI GPT-4o 2024-05-13 model
+### What's New in 1.16.1 · May 13, 2024 (minor release, models support)
+
+- Support for the new OpenAI GPT-4o 2024-05-13 model

 ### What's New in 1.16.0 · May 9, 2024 · Crystal Clear

@@ -1,8 +1,4 @@
-# Deploying `big-AGI` with Docker (v1 Legacy)
-
-> **Note:** This documentation is for the **v1 legacy branch**. For the latest Big-AGI, use Docker tags `:latest`, `:stable`, or `:development` which point to the [main branch](https://github.com/enricoros/big-AGI/tree/main).
->
-> To use v1 legacy specifically, use Docker tags `:v1` or `:v1-stable`.
+# Deploying `big-AGI` with Docker

 Utilize Docker containers to deploy the big-AGI application for an efficient and automated deployment process.
 Docker ensures faster development cycles, easier collaboration, and seamless environment management.
@@ -0,0 +1,7 @@
+import { clerkMiddleware } from '@clerk/nextjs/server';
+
+export default clerkMiddleware();
+
+export const config = {
+  matcher: ['/((?!.+.[w]+$|_next).*)', '/', '/(api|trpc)(.*)'],
+};
@@ -9,6 +9,7 @@
      "version": "1.16.0",
      "hasInstallScript": true,
      "dependencies": {
+        "@clerk/nextjs": "^5.0.8",
        "@emotion/cache": "^11.11.0",
        "@emotion/react": "^11.11.4",
        "@emotion/server": "^11.11.0",
@@ -29,7 +30,6 @@
        "@vercel/analytics": "^1.2.2",
        "@vercel/speed-insights": "^1.0.10",
        "browser-fs-access": "^0.35.0",
-        "cheerio": "^1.0.0-rc.12",
        "eventsource-parser": "^1.1.2",
        "idb-keyval": "^6.2.1",
        "next": "~14.1.4",
@@ -52,8 +52,7 @@
        "sharp": "^0.33.3",
        "superjson": "^2.2.1",
        "tesseract.js": "^5.1.0",
-        "tiktoken": "^1.0.15",
-        "turndown": "^7.2.0",
+        "tiktoken": "^1.0.14",
        "uuid": "^9.0.1",
        "zod": "^3.23.8",
        "zustand": "^4.5.2"
@@ -70,7 +69,6 @@
        "@types/react-dom": "^18.3.0",
        "@types/react-katex": "^3.0.4",
        "@types/react-timeago": "^4.1.7",
-        "@types/turndown": "^5.0.4",
        "@types/uuid": "^9.0.8",
        "eslint": "^8.57.0",
        "eslint-config-next": "^14.2.3",
@@ -79,7 +77,7 @@
        "typescript": "^5.4.5"
      },
      "engines": {
-        "node": "^24.0.0 || ^22.0.0 || ^20.0.0 || ^18.0.0"
+        "node": "^20.0.0 || ^18.0.0"
      }
    },
    "node_modules/@babel/code-frame": {
@@ -223,6 +221,116 @@
        "node": ">=6.9.0"
      }
    },
+    "node_modules/@clerk/backend": {
+      "version": "1.1.3",
+      "resolved": "https://registry.npmjs.org/@clerk/backend/-/backend-1.1.3.tgz",
+      "integrity": "sha512-PCGolPkTff7aQjAoS+oDhUldviBYM376klclxJO8SK7eyNkxhwfU95T5McEVpEgz5nITKjKk03Zr7a7v82X6Iw==",
+      "dependencies": {
+        "@clerk/shared": "2.0.2",
+        "cookie": "0.5.0",
+        "snakecase-keys": "5.4.4",
+        "tslib": "2.4.1"
+      },
+      "engines": {
+        "node": ">=18.17.0"
+      }
+    },
+    "node_modules/@clerk/backend/node_modules/tslib": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.4.1.tgz",
+      "integrity": "sha512-tGyy4dAjRIEwI7BzsB0lynWgOpfqjUdq91XXAlIWD2OwKBH7oCl/GZG/HT4BOHrTlPMOASlMQ7veyTqpmRcrNA=="
+    },
+    "node_modules/@clerk/clerk-react": {
+      "version": "5.0.4",
+      "resolved": "https://registry.npmjs.org/@clerk/clerk-react/-/clerk-react-5.0.4.tgz",
+      "integrity": "sha512-sVpzLgz/2Muj7W2M3j1g4l296ld+XlEKIQ32sUhFeIM4XiOpBaO8bFu1c4YcdKaetreI6f6dB/K9lYJLGZTtFw==",
+      "dependencies": {
+        "@clerk/shared": "2.0.2",
+        "@clerk/types": "4.2.1",
+        "tslib": "2.4.1"
+      },
+      "engines": {
+        "node": ">=18.17.0"
+      },
+      "peerDependencies": {
+        "react": ">=18",
+        "react-dom": ">=18"
+      }
+    },
+    "node_modules/@clerk/clerk-react/node_modules/tslib": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.4.1.tgz",
+      "integrity": "sha512-tGyy4dAjRIEwI7BzsB0lynWgOpfqjUdq91XXAlIWD2OwKBH7oCl/GZG/HT4BOHrTlPMOASlMQ7veyTqpmRcrNA=="
+    },
+    "node_modules/@clerk/nextjs": {
+      "version": "5.0.8",
+      "resolved": "https://registry.npmjs.org/@clerk/nextjs/-/nextjs-5.0.8.tgz",
+      "integrity": "sha512-ZwTA+nd0EbeFbsrGYriv8t2oaiANTKQGvvPji9TWTwLR+gP9V5XcVsw4xuZ8w3+MjhnKCrc8BE+oCg5wUCn+Bw==",
+      "dependencies": {
+        "@clerk/backend": "1.1.3",
+        "@clerk/clerk-react": "5.0.4",
+        "@clerk/shared": "2.0.2",
+        "crypto-js": "4.2.0",
+        "path-to-regexp": "6.2.1",
+        "tslib": "2.4.1"
+      },
+      "engines": {
+        "node": ">=18.17.0"
+      },
+      "peerDependencies": {
+        "next": "^13.5.4 || ^14.0.3",
+        "react": ">=18",
+        "react-dom": ">=18"
+      }
+    },
+    "node_modules/@clerk/nextjs/node_modules/tslib": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.4.1.tgz",
+      "integrity": "sha512-tGyy4dAjRIEwI7BzsB0lynWgOpfqjUdq91XXAlIWD2OwKBH7oCl/GZG/HT4BOHrTlPMOASlMQ7veyTqpmRcrNA=="
+    },
+    "node_modules/@clerk/shared": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/@clerk/shared/-/shared-2.0.2.tgz",
+      "integrity": "sha512-uQXbBJyUV6B4y/cKIgKypVmCdCh7pHeQYbASCKI3RzlsC3FPyopy0hTlAIvXJqjulPYBfRUI1w2FDRJzpEk3sw==",
+      "hasInstallScript": true,
+      "dependencies": {
+        "glob-to-regexp": "0.4.1",
+        "js-cookie": "3.0.1",
+        "std-env": "^3.7.0",
+        "swr": "2.2.0"
+      },
+      "engines": {
+        "node": ">=18.17.0"
+      },
+      "peerDependencies": {
+        "react": ">=18",
+        "react-dom": ">=18"
+      },
+      "peerDependenciesMeta": {
+        "react": {
+          "optional": true
+        },
+        "react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@clerk/types": {
+      "version": "4.2.1",
+      "resolved": "https://registry.npmjs.org/@clerk/types/-/types-4.2.1.tgz",
+      "integrity": "sha512-tR7Qd1P5Fa4n81ZxKA0tFPJd1OgrL7chU/+moq/LSnK8ZRN/DUzh5K7730sdw5F26CKtT6pzmW+irtgpYLYdDQ==",
+      "dependencies": {
+        "csstype": "3.1.1"
+      },
+      "engines": {
+        "node": ">=18.17.0"
+      }
+    },
+    "node_modules/@clerk/types/node_modules/csstype": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.1.tgz",
+      "integrity": "sha512-DJR/VvkAvSZW9bTouZue2sSxDwdTN92uHjqeKVm+0dAqdfNykRzQ95tay8aXMBAAPpUiq4Qcug2L7neoRh2Egw=="
+    },
    "node_modules/@cloudflare/puppeteer": {
      "version": "0.0.5",
      "resolved": "https://registry.npmjs.org/@cloudflare/puppeteer/-/puppeteer-0.0.5.tgz",
@@ -1027,11 +1135,6 @@
        "node-pre-gyp": "bin/node-pre-gyp"
      }
    },
-    "node_modules/@mixmark-io/domino": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
-      "integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw=="
-    },
    "node_modules/@mui/base": {
      "version": "5.0.0-beta.42",
      "resolved": "https://registry.npmjs.org/@mui/base/-/base-5.0.0-beta.42.tgz",
@@ -2090,12 +2193,6 @@
        "@types/react": "*"
      }
    },
-    "node_modules/@types/turndown": {
-      "version": "5.0.4",
-      "resolved": "https://registry.npmjs.org/@types/turndown/-/turndown-5.0.4.tgz",
-      "integrity": "sha512-28GI33lCCkU4SGH1GvjDhFgOVr+Tym4PXGBIU1buJUa6xQolniPArtUT+kv42RR2N9MsMLInkr904Aq+ESHBJg==",
-      "dev": true
-    },
    "node_modules/@types/unist": {
      "version": "3.0.2",
      "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.2.tgz",
@@ -2677,11 +2774,6 @@
      "resolved": "https://registry.npmjs.org/bmp-js/-/bmp-js-0.1.0.tgz",
      "integrity": "sha512-vHdS19CnY3hwiNdkaqk93DvjVLfbEcI8mys4UjuWrlX1haDmroo8o4xCzh4wD6DGV6HxRCyauwhHRqMTfERtjw=="
    },
-    "node_modules/boolbase": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz",
-      "integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww=="
-    },
    "node_modules/brace-expansion": {
      "version": "1.1.11",
      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
@@ -2847,42 +2939,6 @@
        "url": "https://github.com/sponsors/wooorm"
      }
    },
-    "node_modules/cheerio": {
-      "version": "1.0.0-rc.12",
-      "resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.0.0-rc.12.tgz",
-      "integrity": "sha512-VqR8m68vM46BNnuZ5NtnGBKIE/DfN0cRIzg9n40EIq9NOv90ayxLBXA8fXC5gquFRGJSTRqBq25Jt2ECLR431Q==",
-      "dependencies": {
-        "cheerio-select": "^2.1.0",
-        "dom-serializer": "^2.0.0",
-        "domhandler": "^5.0.3",
-        "domutils": "^3.0.1",
-        "htmlparser2": "^8.0.1",
-        "parse5": "^7.0.0",
-        "parse5-htmlparser2-tree-adapter": "^7.0.0"
-      },
-      "engines": {
-        "node": ">= 6"
-      },
-      "funding": {
-        "url": "https://github.com/cheeriojs/cheerio?sponsor=1"
-      }
-    },
-    "node_modules/cheerio-select": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/cheerio-select/-/cheerio-select-2.1.0.tgz",
-      "integrity": "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==",
-      "dependencies": {
-        "boolbase": "^1.0.0",
-        "css-select": "^5.1.0",
-        "css-what": "^6.1.0",
-        "domelementtype": "^2.3.0",
-        "domhandler": "^5.0.3",
-        "domutils": "^3.0.1"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/fb55"
-      }
-    },
    "node_modules/chownr": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/chownr/-/chownr-2.0.0.tgz",
@@ -2985,6 +3041,14 @@
      "resolved": "https://registry.npmjs.org/convert-source-map/-/convert-source-map-1.9.0.tgz",
      "integrity": "sha512-ASFBup0Mz1uyiIjANan1jzLQami9z1PoYSZCiiYW2FczPbenXc45FZdBZLzOT+r6+iciuEModtmCti+hjaAk0A=="
    },
+    "node_modules/cookie": {
+      "version": "0.5.0",
+      "resolved": "https://registry.npmjs.org/cookie/-/cookie-0.5.0.tgz",
+      "integrity": "sha512-YZ3GUyn/o8gfKJlnlX7g7xq4gyO6OSuhGPKaaGssGB2qgDUS0gPgtTvoyZLTt9Ab6dC4hfc9dV5arkvc/OCmrw==",
+      "engines": {
+        "node": ">= 0.6"
+      }
+    },
    "node_modules/copy-anything": {
      "version": "3.0.5",
      "resolved": "https://registry.npmjs.org/copy-anything/-/copy-anything-3.0.5.tgz",
@@ -3033,6 +3097,11 @@
        "node": ">= 8"
      }
    },
+    "node_modules/crypto-js": {
+      "version": "4.2.0",
+      "resolved": "https://registry.npmjs.org/crypto-js/-/crypto-js-4.2.0.tgz",
+      "integrity": "sha512-KALDyEYgpY+Rlob/iriUtjV6d5Eq+Y191A5g4UqLAi8CyGP9N1+FdVbkc1SxKc2r4YAYqG8JzO2KGL+AizD70Q=="
+    },
    "node_modules/css-box-model": {
      "version": "1.2.1",
      "resolved": "https://registry.npmjs.org/css-box-model/-/css-box-model-1.2.1.tgz",
@@ -3041,32 +3110,6 @@
        "tiny-invariant": "^1.0.6"
      }
    },
-    "node_modules/css-select": {
-      "version": "5.1.0",
-      "resolved": "https://registry.npmjs.org/css-select/-/css-select-5.1.0.tgz",
-      "integrity": "sha512-nwoRF1rvRRnnCqqY7updORDsuqKzqYJ28+oSMaJMMgOauh3fvwHqMS7EZpIPqK8GL+g9mKxF1vP/ZjSeNjEVHg==",
-      "dependencies": {
-        "boolbase": "^1.0.0",
-        "css-what": "^6.1.0",
-        "domhandler": "^5.0.2",
-        "domutils": "^3.0.1",
-        "nth-check": "^2.0.1"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/fb55"
-      }
-    },
-    "node_modules/css-what": {
-      "version": "6.1.0",
-      "resolved": "https://registry.npmjs.org/css-what/-/css-what-6.1.0.tgz",
-      "integrity": "sha512-HTUrgRJ7r4dsZKU6GjmpfRK1O76h97Z8MfS1G0FozR+oF2kG6Vfe8JE6zwrkbxigziPHinCJ+gCPjA9EaBDtRw==",
-      "engines": {
-        "node": ">= 6"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/fb55"
-      }
-    },
    "node_modules/csstype": {
      "version": "3.1.3",
      "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz",
@@ -3295,55 +3338,13 @@
        "csstype": "^3.0.2"
      }
    },
-    "node_modules/dom-serializer": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz",
-      "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==",
+    "node_modules/dot-case": {
+      "version": "3.0.4",
+      "resolved": "https://registry.npmjs.org/dot-case/-/dot-case-3.0.4.tgz",
+      "integrity": "sha512-Kv5nKlh6yRrdrGvxeJ2e5y2eRUpkUosIW4A2AS38zwSz27zu7ufDwQPi5Jhs3XAlGNetl3bmnGhQsMtkKJnj3w==",
      "dependencies": {
-        "domelementtype": "^2.3.0",
-        "domhandler": "^5.0.2",
-        "entities": "^4.2.0"
-      },
-      "funding": {
-        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
-      }
-    },
-    "node_modules/domelementtype": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz",
-      "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==",
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/fb55"
-        }
-      ]
-    },
-    "node_modules/domhandler": {
-      "version": "5.0.3",
-      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz",
-      "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==",
-      "dependencies": {
-        "domelementtype": "^2.3.0"
-      },
-      "engines": {
-        "node": ">= 4"
-      },
-      "funding": {
-        "url": "https://github.com/fb55/domhandler?sponsor=1"
-      }
-    },
-    "node_modules/domutils": {
-      "version": "3.1.0",
-      "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.1.0.tgz",
-      "integrity": "sha512-H78uMmQtI2AhgDJjWeQmHwJJ2bLPD3GMmO7Zja/ZZh84wkm+4ut+IUnUdRa8uCGX88DiVx1j6FRe1XfxEgjEZA==",
-      "dependencies": {
-        "dom-serializer": "^2.0.0",
-        "domelementtype": "^2.3.0",
-        "domhandler": "^5.0.3"
-      },
-      "funding": {
-        "url": "https://github.com/fb55/domutils?sponsor=1"
+        "no-case": "^3.0.4",
+        "tslib": "^2.0.3"
      }
    },
    "node_modules/duplexer": {
@@ -4394,6 +4395,11 @@
        "node": ">=10.13.0"
      }
    },
+    "node_modules/glob-to-regexp": {
+      "version": "0.4.1",
+      "resolved": "https://registry.npmjs.org/glob-to-regexp/-/glob-to-regexp-0.4.1.tgz",
+      "integrity": "sha512-lkX1HJXwyMcprw/5YUZc2s7DrpAiHB21/V+E1rHUrVNokkvB6bqMzT0VfV6/86ZNabt1k14YOIaT7nDvOX3Iiw=="
+    },
    "node_modules/glob/node_modules/brace-expansion": {
      "version": "2.0.1",
      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
@@ -4792,24 +4798,6 @@
        "url": "https://opencollective.com/unified"
      }
    },
-    "node_modules/htmlparser2": {
-      "version": "8.0.2",
-      "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-8.0.2.tgz",
-      "integrity": "sha512-GYdjWKDkbRLkZ5geuHs5NY1puJ+PXwP7+fHPRz06Eirsb9ugf6d8kkXav6ADhcODhFFPMIXyxkxSuMf3D6NCFA==",
-      "funding": [
-        "https://github.com/fb55/htmlparser2?sponsor=1",
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/fb55"
-        }
-      ],
-      "dependencies": {
-        "domelementtype": "^2.3.0",
-        "domhandler": "^5.0.3",
-        "domutils": "^3.0.1",
-        "entities": "^4.4.0"
-      }
-    },
    "node_modules/https-proxy-agent": {
      "version": "5.0.1",
      "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz",
@@ -5392,6 +5380,14 @@
        "@pkgjs/parseargs": "^0.11.0"
      }
    },
+    "node_modules/js-cookie": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/js-cookie/-/js-cookie-3.0.1.tgz",
+      "integrity": "sha512-+0rgsUXZu4ncpPxRL+lNEptWMOWl9etvPHc/koSRp6MPwpRYAhmk0dUG00J4bxVV3r9uUzfo24wW0knS07SKSw==",
+      "engines": {
+        "node": ">=12"
+      }
+    },
    "node_modules/js-tokens": {
      "version": "4.0.0",
      "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz",
@@ -5565,6 +5561,14 @@
        "loose-envify": "cli.js"
      }
    },
+    "node_modules/lower-case": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/lower-case/-/lower-case-2.0.2.tgz",
+      "integrity": "sha512-7fm3l3NAF9WfN6W3JOmf5drwpVqX78JtoGJ3A6W0a6ZnldM41w2fV5D490psKFTpMds8TJse/eHLFFsNHHjHgg==",
+      "dependencies": {
+        "tslib": "^2.0.3"
+      }
+    },
    "node_modules/lru-cache": {
      "version": "10.2.2",
      "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.2.2.tgz",
@@ -5598,6 +5602,17 @@
        "semver": "bin/semver.js"
      }
    },
+    "node_modules/map-obj": {
+      "version": "4.3.0",
+      "resolved": "https://registry.npmjs.org/map-obj/-/map-obj-4.3.0.tgz",
+      "integrity": "sha512-hdN1wVrZbb29eBGiGjJbeP8JbKjq1urkHJ/LIP/NY48MZ1QVXUsQBV1G1zvYFHn1XE06cwjBsOI2K3Ulnj1YXQ==",
+      "engines": {
+        "node": ">=8"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
    "node_modules/markdown-table": {
      "version": "3.0.3",
      "resolved": "https://registry.npmjs.org/markdown-table/-/markdown-table-3.0.3.tgz",
@@ -6645,6 +6660,15 @@
        }
      }
    },
+    "node_modules/no-case": {
+      "version": "3.0.4",
+      "resolved": "https://registry.npmjs.org/no-case/-/no-case-3.0.4.tgz",
+      "integrity": "sha512-fgAN3jGAh+RoxUGZHTSOLJIqUc2wmoBwGR4tbpNAKmmovFoWq0OdRkb0VkldReO2a2iBT/OEulG9XSUc10r3zg==",
+      "dependencies": {
+        "lower-case": "^2.0.2",
+        "tslib": "^2.0.3"
+      }
+    },
    "node_modules/node-fetch": {
      "version": "2.7.0",
      "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
@@ -6696,17 +6720,6 @@
      "resolved": "https://registry.npmjs.org/nprogress/-/nprogress-0.2.0.tgz",
      "integrity": "sha512-I19aIingLgR1fmhftnbWWO3dXc0hSxqHQHQb3H8m+K3TnEn/iSeTZZOyvKXWqQESMwuUVnatlCnZdLBZZt2VSA=="
    },
-    "node_modules/nth-check": {
-      "version": "2.1.1",
-      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.1.1.tgz",
-      "integrity": "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==",
-      "dependencies": {
-        "boolbase": "^1.0.0"
-      },
-      "funding": {
-        "url": "https://github.com/fb55/nth-check?sponsor=1"
-      }
-    },
    "node_modules/object-assign": {
      "version": "4.1.1",
      "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz",
@@ -6966,18 +6979,6 @@
        "url": "https://github.com/inikulin/parse5?sponsor=1"
      }
    },
-    "node_modules/parse5-htmlparser2-tree-adapter": {
-      "version": "7.0.0",
-      "resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.0.0.tgz",
-      "integrity": "sha512-B77tOZrqqfUfnVcOrUvfdLbz4pu4RopLD/4vmu3HUPswwTA8OH0EMW9BlWR2B0RCoiZRAHEUu7IxeP1Pd1UU+g==",
-      "dependencies": {
-        "domhandler": "^5.0.2",
-        "parse5": "^7.0.0"
-      },
-      "funding": {
-        "url": "https://github.com/inikulin/parse5?sponsor=1"
-      }
-    },
    "node_modules/path-exists": {
      "version": "4.0.0",
      "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz",
@@ -7026,6 +7027,11 @@
        "url": "https://github.com/sponsors/isaacs"
      }
    },
+    "node_modules/path-to-regexp": {
+      "version": "6.2.1",
+      "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-6.2.1.tgz",
+      "integrity": "sha512-JLyh7xT1kizaEvcaXOQwOc2/Yhw6KZOvPf1S8401UyLk86CU79LN3vl7ztXGm/pZ+YjoyAJ4rxmHwbkBXJX+yw=="
+    },
    "node_modules/path-type": {
      "version": "4.0.0",
      "resolved": "https://registry.npmjs.org/path-type/-/path-type-4.0.0.tgz",
@@ -7949,6 +7955,39 @@
        "node": ">=8"
      }
    },
+    "node_modules/snake-case": {
+      "version": "3.0.4",
+      "resolved": "https://registry.npmjs.org/snake-case/-/snake-case-3.0.4.tgz",
+      "integrity": "sha512-LAOh4z89bGQvl9pFfNF8V146i7o7/CqFPbqzYgP+yYzDIDeS9HaNFtXABamRW+AQzEVODcvE79ljJ+8a9YSdMg==",
+      "dependencies": {
+        "dot-case": "^3.0.4",
+        "tslib": "^2.0.3"
+      }
+    },
+    "node_modules/snakecase-keys": {
+      "version": "5.4.4",
+      "resolved": "https://registry.npmjs.org/snakecase-keys/-/snakecase-keys-5.4.4.tgz",
+      "integrity": "sha512-YTywJG93yxwHLgrYLZjlC75moVEX04LZM4FHfihjHe1FCXm+QaLOFfSf535aXOAd0ArVQMWUAe8ZPm4VtWyXaA==",
+      "dependencies": {
+        "map-obj": "^4.1.0",
+        "snake-case": "^3.0.4",
+        "type-fest": "^2.5.2"
+      },
+      "engines": {
+        "node": ">=12"
+      }
+    },
+    "node_modules/snakecase-keys/node_modules/type-fest": {
+      "version": "2.19.0",
+      "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-2.19.0.tgz",
+      "integrity": "sha512-RAH822pAdBgcNMAfWnCBU3CFZcfZ/i1eZjwFU/dsLKumyuuP3niueg2UAukXYF0E2AAoc82ZSSf9J0WQBinzHA==",
+      "engines": {
+        "node": ">=12.20"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
    "node_modules/source-map": {
      "version": "0.5.7",
      "resolved": "https://registry.npmjs.org/source-map/-/source-map-0.5.7.tgz",
@@ -7974,6 +8013,11 @@
        "url": "https://github.com/sponsors/wooorm"
      }
    },
+    "node_modules/std-env": {
+      "version": "3.7.0",
+      "resolved": "https://registry.npmjs.org/std-env/-/std-env-3.7.0.tgz",
+      "integrity": "sha512-JPbdCEQLj1w5GilpiHAx3qJvFndqybBysA3qUOnznweH4QbNYUsW/ea8QzSrnh0vNsezMMw5bcVool8lM0gwzg=="
+    },
    "node_modules/stream": {
      "version": "0.0.2",
      "resolved": "https://registry.npmjs.org/stream/-/stream-0.0.2.tgz",
@@ -8264,6 +8308,17 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/swr": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/swr/-/swr-2.2.0.tgz",
+      "integrity": "sha512-AjqHOv2lAhkuUdIiBu9xbuettzAzWXmCEcLONNKJRba87WAefz8Ca9d6ds/SzrPc235n1IxWYdhJ2zF3MNUaoQ==",
+      "dependencies": {
+        "use-sync-external-store": "^1.2.0"
+      },
+      "peerDependencies": {
+        "react": "^16.11.0 || ^17.0.0 || ^18.0.0"
+      }
+    },
    "node_modules/tapable": {
      "version": "2.2.1",
      "resolved": "https://registry.npmjs.org/tapable/-/tapable-2.2.1.tgz",
@@ -8353,9 +8408,9 @@
      }
    },
    "node_modules/tiktoken": {
-      "version": "1.0.15",
-      "resolved": "https://registry.npmjs.org/tiktoken/-/tiktoken-1.0.15.tgz",
-      "integrity": "sha512-sCsrq/vMWUSEW29CJLNmPvWxlVp7yh2tlkAjpJltIKqp5CKf98ZNpdeHRmAlPVFlGEbswDc6SmI8vz64W/qErw=="
+      "version": "1.0.14",
+      "resolved": "https://registry.npmjs.org/tiktoken/-/tiktoken-1.0.14.tgz",
+      "integrity": "sha512-g5zd5r/DoH8Kw0fiYbYpVhb6WO8BHO1unXqmBBWKwoT17HwSounnDtMDFUKm2Pko8U47sjQarOe+9aUrnqmmTg=="
    },
    "node_modules/tiny-invariant": {
      "version": "1.3.3",
@@ -8442,14 +8497,6 @@
      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
      "integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
    },
-    "node_modules/turndown": {
-      "version": "7.2.0",
-      "resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.0.tgz",
-      "integrity": "sha512-eCZGBN4nNNqM9Owkv9HAtWRYfLA4h909E/WGAWWBpmB275ehNhZyk87/Tpvjbp0jjNl9XwCsbe6bm6CqFsgD+A==",
-      "dependencies": {
-        "@mixmark-io/domino": "^2.2.0"
-      }
-    },
    "node_modules/type-check": {
      "version": "0.4.0",
      "resolved": "https://registry.npmjs.org/type-check/-/type-check-0.4.0.tgz",
@@ -18,6 +18,7 @@
    "schema": "src/server/prisma/schema.prisma"
  },
  "dependencies": {
+    "@clerk/nextjs": "^5.0.8",
    "@emotion/cache": "^11.11.0",
    "@emotion/react": "^11.11.4",
    "@emotion/server": "^11.11.0",
@@ -38,7 +39,6 @@
    "@vercel/analytics": "^1.2.2",
    "@vercel/speed-insights": "^1.0.10",
    "browser-fs-access": "^0.35.0",
-    "cheerio": "^1.0.0-rc.12",
    "eventsource-parser": "^1.1.2",
    "idb-keyval": "^6.2.1",
    "next": "~14.1.4",
@@ -61,8 +61,7 @@
    "sharp": "^0.33.3",
    "superjson": "^2.2.1",
    "tesseract.js": "^5.1.0",
-    "tiktoken": "^1.0.15",
-    "turndown": "^7.2.0",
+    "tiktoken": "^1.0.14",
    "uuid": "^9.0.1",
    "zod": "^3.23.8",
    "zustand": "^4.5.2"
@@ -79,7 +78,6 @@
    "@types/react-dom": "^18.3.0",
    "@types/react-katex": "^3.0.4",
    "@types/react-timeago": "^4.1.7",
-    "@types/turndown": "^5.0.4",
    "@types/uuid": "^9.0.8",
    "eslint": "^8.57.0",
    "eslint-config-next": "^14.2.3",
@@ -88,6 +86,6 @@
    "typescript": "^5.4.5"
  },
  "engines": {
-    "node": "^24.0.0 || ^22.0.0 || ^20.0.0 || ^18.0.0"
+    "node": "^20.0.0 || ^18.0.0"
  }
 }
@@ -13,6 +13,7 @@ import '~/common/styles/GithubMarkdown.css';
 import '~/common/styles/NProgress.css';
 import '~/common/styles/app.styles.css';

+import { ProviderAuth } from '~/common/providers/ProviderAuth';
 import { ProviderBackendCapabilities } from '~/common/providers/ProviderBackendCapabilities';
 import { ProviderBootstrapLogic } from '~/common/providers/ProviderBootstrapLogic';
 import { ProviderSingleTab } from '~/common/providers/ProviderSingleTab';
@@ -32,18 +33,20 @@ const MyApp = ({ Component, emotionCache, pageProps }: MyAppProps) =>
    </Head>

    <ProviderTheming emotionCache={emotionCache}>
-      <ProviderSingleTab>
-        <ProviderTRPCQuerySettings>
-          <ProviderBackendCapabilities>
-            {/* ^ SSR boundary */}
-            <ProviderBootstrapLogic>
-              <ProviderSnacks>
-                <Component {...pageProps} />
-              </ProviderSnacks>
-            </ProviderBootstrapLogic>
-          </ProviderBackendCapabilities>
-        </ProviderTRPCQuerySettings>
-      </ProviderSingleTab>
+      <ProviderAuth>
+        <ProviderSingleTab>
+          <ProviderTRPCQuerySettings>
+            <ProviderBackendCapabilities>
+              {/* ^ SSR boundary */}
+              <ProviderBootstrapLogic>
+                <ProviderSnacks>
+                  <Component {...pageProps} />
+                </ProviderSnacks>
+              </ProviderBootstrapLogic>
+            </ProviderBackendCapabilities>
+          </ProviderTRPCQuerySettings>
+        </ProviderSingleTab>
+      </ProviderAuth>
    </ProviderTheming>

    {isVercelFromFrontend && <VercelAnalytics debug={false} />}
@@ -77,12 +77,9 @@ function AppShareTarget() {
      setIsDownloading(true);
      callBrowseFetchPage(intentURL)
        .then(page => {
-          if (page.stopReason !== 'error') {
-            let pageContent = page.content.markdown || page.content.text || page.content.html || '';
-            if (pageContent)
-              pageContent = '\n\n```' + intentURL + '\n' + pageContent + '\n```\n';
-            queueComposerTextAndLaunchApp(pageContent);
-          } else
+          if (page.stopReason !== 'error')
+            queueComposerTextAndLaunchApp('\n\n```' + intentURL + '\n' + page.content + '\n```\n');
+          else
            setErrorMessage('Could not read any data' + page.error ? ': ' + page.error : '');
        })
        .catch(error => setErrorMessage(error?.message || error || 'Unknown error'))
@@ -1,5 +1,5 @@
 import * as React from 'react';
-import { useShallow } from 'zustand/react/shallow';
+import { shallow } from 'zustand/shallow';

 import { Box, Card, ListDivider, ListItemDecorator, MenuItem, Switch, Typography } from '@mui/joy';
 import ArrowBackIcon from '@mui/icons-material/ArrowBack';
@@ -99,7 +99,7 @@ export function Telephone(props: {

  // external state
  const { chatLLMId, chatLLMDropdown } = useChatLLMDropdown();
-  const { chatTitle, reMessages } = useChatStore(useShallow(state => {
+  const { chatTitle, reMessages } = useChatStore(state => {
    const conversation = props.callIntent.conversationId
      ? state.conversations.find(conversation => conversation.id === props.callIntent.conversationId) ?? null
      : null;
@@ -107,7 +107,7 @@ export function Telephone(props: {
      chatTitle: conversation ? conversationTitle(conversation) : null,
      reMessages: conversation ? conversation.messages : null,
    };
-  }));
+  }, shallow);
  const persona = SystemPurposes[props.callIntent.personaId as SystemPurposeId] ?? undefined;
  const personaCallStarters = persona?.call?.starters ?? undefined;
  const personaVoiceId = overridePersonaVoice ? undefined : (persona?.voices?.elevenLabs?.voiceId ?? undefined);
@@ -225,7 +225,7 @@ export function Telephone(props: {
    let finalText = '';
    let error: any | null = null;
    setPersonaTextInterim('💭...');
-    llmStreamingChatGenerate(chatLLMId, callPrompt, 'call', callMessages[0].id, null, null, responseAbortController.current.signal, ({ textSoFar }) => {
+    llmStreamingChatGenerate(chatLLMId, callPrompt, null, null, responseAbortController.current.signal, ({ textSoFar }) => {
      const text = textSoFar?.trim();
      if (text) {
        finalText = text;
@@ -277,7 +277,7 @@ export function AppChat() {
    const conversation = getConversation(conversationId);
    if (!conversation)
      return;
-    const imaginedPrompt = await imaginePromptFromText(messageText, conversationId) || 'An error sign.';
+    const imaginedPrompt = await imaginePromptFromText(messageText) || 'An error sign.';
    await handleExecuteAndOutcome('generate-image', conversationId, [
      ...conversation.messages,
      createDMessage('user', imaginedPrompt),
@@ -1,7 +1,7 @@
 import * as React from 'react';
 import { useShallow } from 'zustand/react/shallow';

-import { Box, Button, Card, CardContent, Dropdown, IconButton, ListDivider, ListItem, ListItemButton, ListItemDecorator, Menu, MenuButton, MenuItem, Tooltip, Typography } from '@mui/joy';
+import { Box, Button, Dropdown, IconButton, ListDivider, ListItem, ListItemButton, ListItemDecorator, Menu, MenuButton, MenuItem, Tooltip, Typography } from '@mui/joy';
 import AddIcon from '@mui/icons-material/Add';
 import CheckRoundedIcon from '@mui/icons-material/CheckRounded';
 import ClearIcon from '@mui/icons-material/Clear';
@@ -10,7 +10,6 @@ import FileDownloadOutlinedIcon from '@mui/icons-material/FileDownloadOutlined';
 import FileUploadOutlinedIcon from '@mui/icons-material/FileUploadOutlined';
 import FolderIcon from '@mui/icons-material/Folder';
 import MoreVertIcon from '@mui/icons-material/MoreVert';
-import RocketLaunchRoundedIcon from '@mui/icons-material/RocketLaunchRounded';
 import StarOutlineRoundedIcon from '@mui/icons-material/StarOutlineRounded';

 import type { DConversationId } from '~/common/state/store-chats';
@@ -19,10 +18,8 @@ import { DFolder, useFolderStore } from '~/common/state/store-folders';
 import { DebounceInputMemo } from '~/common/components/DebounceInput';
 import { FoldersToggleOff } from '~/common/components/icons/FoldersToggleOff';
 import { FoldersToggleOn } from '~/common/components/icons/FoldersToggleOn';
-import { Link } from '~/common/components/Link';
 import { PageDrawerHeader } from '~/common/layout/optima/components/PageDrawerHeader';
 import { PageDrawerList } from '~/common/layout/optima/components/PageDrawerList';
-import { ROUTE_APP_NEWS } from '~/common/app.routes';
 import { capitalizeFirstLetter } from '~/common/util/textUtils';
 import { themeScalingMap, themeZIndexOverMobileDrawer } from '~/common/app.theme';
 import { useOptimaDrawers } from '~/common/layout/optima/useOptimaDrawers';
@@ -81,13 +78,6 @@ function ChatDrawer(props: {
  const [searchSorting, setSearchSorting] = React.useState<ChatSearchSorting>('frequency');
  const [debouncedSearchQuery, setDebouncedSearchQuery] = React.useState('');
  const [folderChangeRequest, setFolderChangeRequest] = React.useState<FolderChangeRequest | null>(null);
-  const [bigAgi2CalloutDismissed, setBigAgi2CalloutDismissed] = React.useState(() => {
-    try {
-      return localStorage.getItem('dismissedBA2ChatDrawerNotice') === 'true';
-    } catch {
-      return false;
-    }
-  });

  // external state
  const { closeDrawer, closeDrawerOnMobile } = useOptimaDrawers();
@@ -135,15 +125,6 @@ function ChatDrawer(props: {
    props.activeConversationId && onConversationsExportDialog(props.activeConversationId, true);
  }, [onConversationsExportDialog, props.activeConversationId]);

-  const handleDismissBigAgi2Callout = React.useCallback(() => {
-    setBigAgi2CalloutDismissed(true);
-    try {
-      localStorage.setItem('dismissedBA2ChatDrawerNotice', 'true');
-    } catch {
-      // ignore
-    }
-  }, []);
-

  // Folder change request

@@ -329,7 +310,7 @@ function ChatDrawer(props: {
              bottomBarBasis={filteredChatsBarBasis}
              onConversationActivate={handleConversationActivate}
              onConversationBranch={onConversationBranch}
-              onConversationDeleteNoConfirmation={handleConversationDeleteNoConfirmation}
+              onConversationDelete={handleConversationDeleteNoConfirmation}
              onConversationExport={onConversationsExportDialog}
              onConversationFolderChange={handleConversationFolderChange}
            />
@@ -359,45 +340,6 @@ function ChatDrawer(props: {
        )}
      </Box>

-      {/* Big-AGI 2.0 Callout */}
-      {!bigAgi2CalloutDismissed && (
-        <Box sx={{ p: 2 }}>
-          <Card variant='solid' color='primary' invertedColors>
-            <CardContent sx={{ gap: 1, position: 'relative' }}>
-              <IconButton
-                size='sm'
-                onClick={handleDismissBigAgi2Callout}
-                sx={{
-                  position: 'absolute',
-                  top: -4,
-                  right: -8,
-                }}
-              >
-                <ClearIcon />
-              </IconButton>
-              <Typography level='title-sm'>
-                Big-AGI 2.0 ✨ is Live!
-              </Typography>
-              <Typography level='body-xs' sx={{ mb: 1 }}>
-                Experience Beam 2, Personas, and Cloud Sync.
-              </Typography>
-              <Button
-                fullWidth
-                size='sm'
-                variant='solid'
-                color='neutral'
-                endDecorator={<RocketLaunchRoundedIcon />}
-                component={Link}
-                href={ROUTE_APP_NEWS}
-                noLinkStyle
-              >
-                Learn More
-              </Button>
-            </CardContent>
-          </Card>
-        </Box>
-      )}
-
      <ListDivider sx={{ my: 0 }} />

      {/* Bottom commands */}
@@ -42,7 +42,7 @@ export const ChatDrawerItemMemo = React.memo(ChatDrawerItem, (prev, next) =>
  prev.bottomBarBasis === next.bottomBarBasis &&
  prev.onConversationActivate === next.onConversationActivate &&
  prev.onConversationBranch === next.onConversationBranch &&
-  prev.onConversationDeleteNoConfirmation === next.onConversationDeleteNoConfirmation &&
+  prev.onConversationDelete === next.onConversationDelete &&
  prev.onConversationExport === next.onConversationExport &&
  prev.onConversationFolderChange === next.onConversationFolderChange,
 );
@@ -76,7 +76,7 @@ function ChatDrawerItem(props: {
  bottomBarBasis: number,
  onConversationActivate: (conversationId: DConversationId, closeMenu: boolean) => void,
  onConversationBranch: (conversationId: DConversationId, messageId: string | null) => void,
-  onConversationDeleteNoConfirmation: (conversationId: DConversationId) => void,
+  onConversationDelete: (conversationId: DConversationId) => void,
  onConversationExport: (conversationId: DConversationId, exportAll: boolean) => void,
  onConversationFolderChange: (folderChangeRequest: FolderChangeRequest) => void,
 }) {
@@ -155,16 +155,7 @@ function ChatDrawerItem(props: {

  // Delete

-  const { onConversationDeleteNoConfirmation } = props;
-  const handleDeleteButtonShow = React.useCallback((event: React.MouseEvent) => {
-    // special case: if 'Shift' is pressed, delete immediately
-    if (event.shiftKey) {
-      event.stopPropagation();
-      onConversationDeleteNoConfirmation(conversationId);
-      return;
-    }
-    setDeleteArmed(true);
-  }, [conversationId, onConversationDeleteNoConfirmation]);
+  const handleDeleteButtonShow = React.useCallback(() => setDeleteArmed(true), []);

  const handleDeleteButtonHide = React.useCallback(() => setDeleteArmed(false), []);

@@ -172,9 +163,9 @@ function ChatDrawerItem(props: {
    if (deleteArmed) {
      setDeleteArmed(false);
      event.stopPropagation();
-      onConversationDeleteNoConfirmation(conversationId);
+      props.onConversationDelete(conversationId);
    }
-  }, [conversationId, deleteArmed, onConversationDeleteNoConfirmation]);
+  }, [conversationId, deleteArmed, props]);


  const textSymbol = SystemPurposes[systemPurposeId]?.symbol || '❓';
@@ -58,12 +58,16 @@ export async function attachmentLoadInputAsync(source: Readonly<AttachmentSource
      edit({ label: source.refUrl, ref: source.refUrl });
      try {
        const page = await callBrowseFetchPage(source.url);
-        edit(
-          page.content.markdown ? { input: { mimeType: 'text/markdown', data: page.content.markdown, dataSize: page.content.markdown.length } }
-            : page.content.text ? { input: { mimeType: 'text/plain', data: page.content.text, dataSize: page.content.text.length } }
-              : page.content.html ? { input: { mimeType: 'text/html', data: page.content.html, dataSize: page.content.html.length } }
-                : { inputError: 'No content found at this link' },
-        );
+        if (page.content) {
+          edit({
+            input: {
+              mimeType: 'text/plain',
+              data: page.content,
+              dataSize: page.content.length,
+            },
+          });
+        } else
+          edit({ inputError: 'No content found at this link' });
      } catch (error: any) {
        edit({ inputError: `Issue downloading page: ${error?.message || (typeof error === 'string' ? error : JSON.stringify(error))}` });
      }
@@ -261,6 +261,7 @@ export function ChatMessage(props: {
  // derived state
  const {
    id: messageId,
+    text: messageText,
    sender: messageSender,
    avatar: messageAvatar,
    typing: messageTyping,
@@ -278,28 +279,7 @@ export function ChatMessage(props: {
  const fromSystem = messageRole === 'system';
  const wasEdited = !!messageUpdated;

-  // #840 - downgrade of V2 to V1
-  let messageText = props.message.text;
-  const isDowngradeV2toV1 = (!!(props.message as any)?.fragments) && messageText === undefined;
-  if (isDowngradeV2toV1) {
-    // try to salvage something: manual reduce the fragments to text
-    const fragments: unknown = (props.message as any)?.fragments;
-    if (fragments && Array.isArray(fragments) && fragments.length) {
-      messageText = '';
-      for (const frag of fragments) {
-        if (frag && typeof frag === 'object' && 'ft' in frag && frag.ft === 'content' && 'part' in frag && typeof frag.part === 'object' && 'pt' in frag.part && frag.part.pt === 'text' && 'text' in frag.part && typeof frag.part.text === 'string') {
-          if (messageText)
-            messageText += '\n\n';
-          messageText += frag.part.text;
-        }
-      }
-    }
-    if (!messageText)
-      messageText = '[Cannot downgrade to Big-AGI 1.x]';
-  }
-
  const textSel = selText ? selText : messageText;
-  // WARNING: if you get an issue here, you're downgrading from the new Big-AGI 2 data format to 1.x.
  const isSpecialT2I = textSel.startsWith('https://images.prodia.xyz/') || textSel.startsWith('/draw ') || textSel.startsWith('/imagine ') || textSel.startsWith('/img ');
  const couldDiagram = textSel.length >= 100 && !isSpecialT2I;
  const couldImagine = textSel.length >= 3 && !isSpecialT2I;
@@ -15,8 +15,7 @@ export const runBrowseGetPageUpdatingState = async (cHandler: ConversationHandle

  try {
    const page = await callBrowseFetchPage(url);
-    const pageContent = page.content.markdown || page.content.text || page.content.html || 'Issue: page load did not produce an answer: no text found';
-    cHandler.messageEdit(assistantMessageId, { text: pageContent, typing: false }, true);
+    cHandler.messageEdit(assistantMessageId, { text: page.content || 'Issue: page load did not produce an answer: no text found', typing: false }, true);
    return true;
  } catch (error: any) {
    console.error(error);
@@ -2,7 +2,7 @@ import type { DLLMId } from '~/modules/llms/store-llms';
 import type { StreamingClientUpdate } from '~/modules/llms/vendors/unifiedStreamingClient';
 import { autoSuggestions } from '~/modules/aifn/autosuggestions/autoSuggestions';
 import { conversationAutoTitle } from '~/modules/aifn/autotitle/autoTitle';
-import { llmStreamingChatGenerate, VChatContextRef, VChatMessageIn, VChatStreamContextName } from '~/modules/llms/llm.client';
+import { llmStreamingChatGenerate, VChatMessageIn } from '~/modules/llms/llm.client';
 import { speakText } from '~/modules/elevenlabs/elevenlabs.client';

 import type { DMessage } from '~/common/state/store-chats';
@@ -34,8 +34,6 @@ export async function runAssistantUpdatingState(conversationId: string, history:
  const messageStatus = await streamAssistantMessage(
    assistantLlmId,
    history.map((m): VChatMessageIn => ({ role: m.role, content: m.text })),
-    'conversation',
-    conversationId,
    parallelViewCount,
    autoSpeak,
    (update) => cHandler.messageEdit(assistantMessageId, update, false),
@@ -63,8 +61,6 @@ type StreamMessageStatus = { outcome: StreamMessageOutcome, errorMessage?: strin
 export async function streamAssistantMessage(
  llmId: DLLMId,
  messagesHistory: VChatMessageIn[],
-  contextName: VChatStreamContextName,
-  contextRef: VChatContextRef,
  throttleUnits: number, // 0: disable, 1: default throttle (12Hz), 2+ reduce the message frequency with the square root
  autoSpeak: ChatAutoSpeakType,
  editMessage: (update: Partial<DMessage>) => void,
@@ -96,7 +92,7 @@ export async function streamAssistantMessage(
  const incrementalAnswer: Partial<DMessage> = { text: '' };

  try {
-    await llmStreamingChatGenerate(llmId, messagesHistory, contextName, contextRef, null, null, abortSignal, (update: StreamingClientUpdate) => {
+    await llmStreamingChatGenerate(llmId, messagesHistory, null, null, abortSignal, (update: StreamingClientUpdate) => {
      const textSoFar = update.textSoFar;

      // grow the incremental message
@@ -5,8 +5,6 @@ import TimeAgo from 'react-timeago';
 import { AspectRatio, Box, Button, Card, CardContent, CardOverflow, Container, Grid, Typography } from '@mui/joy';
 import ExpandMoreIcon from '@mui/icons-material/ExpandMore';
 import LaunchIcon from '@mui/icons-material/Launch';
-import ArrowForwardRoundedIcon from '@mui/icons-material/ArrowForwardRounded';
-import ArrowOutwardRoundedIcon from '@mui/icons-material/ArrowOutwardRounded';

 import { Brand } from '~/common/app.config';
 import { Link } from '~/common/components/Link';
@@ -16,9 +14,6 @@ import { capitalizeFirstLetter } from '~/common/util/textUtils';

 import { NewsItems } from './news.data';
 import { beamNewsCallout } from './beam.data';
-import { bigAgi2NewsCallout, bigAgi2Url } from './bigAgi2.data';
-
-import { downloadAllConversationsJson } from '~/modules/trade/trade.client';


 // number of news items to show by default, before the expander
@@ -69,8 +64,6 @@ export function AppNews() {
  // show expander
  const canExpand = news.length < NewsItems.length;

-  const currentVer = '1.6.9'; // firstNews?.versionCode;
-
  return (

    <Box sx={{
@@ -85,41 +78,26 @@ export function AppNews() {
        display: 'flex', flexDirection: 'column', alignItems: 'center',
      }}>

-        <Typography level='h1' sx={{ fontSize: '2.7rem', mb: 4 }}>
-          Welcome to {Brand.Title.Base} <Box component='span' sx={{ animation: `${animationColorBlues} 10s infinite`, zIndex: 1 /* perf-opt */ }}>{currentVer}</Box>!
+        <Typography level='h1' sx={{ fontSize: '2.9rem', mb: 4 }}>
+          Welcome to {Brand.Title.Base} <Box component='span' sx={{ animation: `${animationColorBlues} 10s infinite`, zIndex: 1 /* perf-opt */ }}>{firstNews?.versionCode}</Box>!
        </Typography>

-        <Typography level='title-sm' sx={{ mb: 2, textAlign: 'center', lineHeight: 'lg' }} >
-          {capitalizeFirstLetter(Brand.Title.Base)} has been updated to version {currentVer}.<br/>
-          <b>And a whole-new 2.0 is waiting!</b>
+        <Typography sx={{ mb: 2 }} level='title-sm'>
+          {capitalizeFirstLetter(Brand.Title.Base)} has been updated to version {firstNews?.versionCode}
        </Typography>

-        <Box sx={{ mb: 5, display: 'flex', gap: 2, flexWrap: 'wrap', justifyContent: 'center' }}>
+        <Box sx={{ mb: 5 }}>
          <Button
-            variant='solid' color='neutral' size='lg'
+            variant='solid' color='primary' size='lg'
            component={Link} href={ROUTE_INDEX} noLinkStyle
-            endDecorator={<ArrowForwardRoundedIcon />}
-            // endDecorator='✨'
+            endDecorator='✨'
            sx={{
-              // boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
+              boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
              minWidth: 180,
            }}
          >
            Continue
          </Button>
-          <Button
-            variant='solid' color='primary' size='lg'
-            component={Link} href={bigAgi2Url} noLinkStyle
-            endDecorator={<><ArrowOutwardRoundedIcon /></>}
-            // endDecorator='✨'
-            sx={{
-              boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
-              minWidth: 180,
-              transform: 'translateY(-1px)',
-            }}
-          >
-            Big-AGI 2 ✨
-          </Button>
        </Box>

        {/*<Typography level='title-sm' sx={{ mb: 1, placeSelf: 'start', ml: 1 }}>*/}
@@ -128,17 +106,10 @@ export function AppNews() {

        <Container disableGutters maxWidth='sm'>
          {news?.map((ni, idx) => {
-            const firstCard = idx === 0;
+            // const firstCard = idx === 0;
            const addPadding = false; //!firstCard; // || showExpander;
            return <React.Fragment key={idx}>

-              {/* Inject the Big-AGI 2.0 item here*/}
-              {idx === 0 && (
-                <Box sx={{ mb: 3 }}>
-                  {bigAgi2NewsCallout}
-                </Box>
-              )}
-
              {/* Inject the Beam item here*/}
              {idx === 2 && (
                <Box sx={{ mb: 3 }}>
@@ -147,7 +118,7 @@ export function AppNews() {
              )}

              {/* News Item */}
-              <Card color={firstCard ? 'primary' : undefined} key={'news-' + idx} sx={{ mb: 3, minHeight: 32, gap: 1 }}>
+              <Card key={'news-' + idx} sx={{ mb: 3, minHeight: 32, gap: 1 }}>
                <CardContent sx={{ position: 'relative', pr: addPadding ? 4 : 0 }}>
                  <Box sx={{ display: 'flex', alignItems: 'center', justifyContent: 'space-between' }}>
                    <Typography level='title-sm' component='div'>
@@ -181,27 +152,6 @@ export function AppNews() {
                    </ul>
                  )}

-                  {firstCard && <Box sx={{ mt: 2 }}>
-                    <Card variant='soft' color='primary' invertedColors>
-                      <CardContent>
-                        <Typography level='title-sm' sx={{ lineHeight: 'lg' }}>
-                          <b>Migrate your chats:</b> you can download all your conversations at any time by clicking
-                          on &quot;Export&quot; &gt; &quot;Download All&quot; or the button below. Then open Big-AGI 2 and
-                          import the conversation by clicking &quot;Organize&quot; &gt; &quot;Import&quot;.
-                        </Typography>
-                        <Button
-                          size='sm'
-                          variant='soft'
-                          color='primary'
-                          sx={{ mt: 1 }}
-                          onClick={downloadAllConversationsJson}
-                        >
-                          Download All Conversations
-                        </Button>
-                      </CardContent>
-                    </Card>
-                  </Box>}
-
                </CardContent>

                {!!ni.versionCoverImage && (
@@ -2,6 +2,7 @@ import * as React from 'react';

 import { Button, Card, CardContent, Grid, Typography } from '@mui/joy';
 import LaunchIcon from '@mui/icons-material/Launch';
+import ThumbUpRoundedIcon from '@mui/icons-material/ThumbUpRounded';

 import { Link } from '~/common/components/Link';

@@ -1,52 +0,0 @@
-import * as React from 'react';
-
-import { Button, Card, CardContent, Grid, Typography } from '@mui/joy';
-import AccessTimeIcon from '@mui/icons-material/AccessTime';
-import LaunchIcon from '@mui/icons-material/Launch';
-import RocketLaunchRounded from '@mui/icons-material/RocketLaunchRounded';
-import SupportAgentIcon from '@mui/icons-material/SupportAgent';
-
-import { Link } from '~/common/components/Link';
-import { clientUtmSource } from '~/common/util/pwaUtils';
-
-
-export const bigAgi2Url = 'https://app.big-agi.com' + clientUtmSource('upgrade');
-const bigAgiSupport = 'https://form.typeform.com/to/nLf8gFmx?utm_source=big-agi-1&utm_medium=app&utm_campaign=support';
-
-
-export const bigAgi2NewsCallout =
-  <Card variant='solid' color='primary' invertedColors>
-    <CardContent sx={{ gap: 2 }}>
-
-      <Typography level='title-lg'>
-        Big-AGI 2.0 ✨ - Now Live
-      </Typography>
-
-      <Typography level='title-sm' sx={{ lineHeight: 'xl' }}>
-        Experience the <b>next generation of Big-AGI</b> with <b>Beam 2</b>, <b>Personas</b>, and <b>Cloud Sync</b> to never lose data.
-      </Typography>
-
-      <Grid container spacing={1}>
-        <Grid xs={12} sm={7}>
-          <Button
-            size='lg'
-            fullWidth variant='solid' color='neutral' endDecorator={<RocketLaunchRounded />}
-            component={Link} href={bigAgi2Url} noLinkStyle target='_blank'
-          >
-            Big-AGI 2.0
-          </Button>
-        </Grid>
-
-        <Grid xs={12} sm={5} sx={{ display: 'flex', flexAlign: 'center', justifyContent: 'center' }}>
-          <Button
-            fullWidth variant='soft' color='primary' endDecorator={<SupportAgentIcon />}
-            component={Link} href={bigAgiSupport} noLinkStyle target='_blank'
-            // disabled
-          >
-            Support
-          </Button>
-        </Grid>
-
-      </Grid>
-    </CardContent>
-  </Card>;
@@ -51,33 +51,18 @@ interface NewsItem {

 // news and feature surfaces
 export const NewsItems: NewsItem[] = [
-  {
-    versionCode: '2.0',
-    versionName: 'Big-AGI',
-    versionDate: new Date('2025-10-06T00:00:00Z'),
-    // text: <>Big-AGI 2.0 is now available at <B href='https://app.big-agi.com'>app.big-agi.com</B></>,
-    items: [
-      { text: <>Big-AGI 2.0 is ready with top-notch AI models support and more productive and faster than ever, including:</> },
-      { text: <><B href='https://app.big-agi.com' wow>Beam 2</B>: multi-modal, program-based, follow-ups, save presets</>, icon: ChatBeamIcon },
-      { text: <><B wow>Personas</B>: craft your perfect AI assistants with data support</> },
-      { text: <><B wow>Cloud Sync</B>: never lose your data</> },
-      { text: <>Built for the future, madly optimized</> },
-    ],
-  },
  /*{
-    versionCode: '1.17.0',
+    versionCode: '1.16.0',
    items: [
-      Screen Capture (when removed from labs)
-      Auto-Merge
      Draw
      ...
+      Screen Capture (when removed from labs)
    ]
  }*/
  {
-    versionCode: '1.16.9',
+    versionCode: '1.16.1',
    versionName: 'Crystal Clear',
-    versionDate: new Date('2024-06-07T05:00:00Z'),
-    // versionDate: new Date('2024-05-13T19:00:00Z'),
+    versionDate: new Date('2024-05-13T19:00:00Z'),
    // versionDate: new Date('2024-05-09T00:00:00Z'),
    versionCoverImage: coverV116,
    items: [
@@ -90,16 +75,7 @@ export const NewsItems: NewsItem[] = [
      { text: <>More: <B issue={517}>code soft-wrap</B>, selection toolbar, <B issue={507}>3x faster</B> on Apple silicon</>, issue: 507 },
      { text: <>Updated <B>Anthropic</B>*, <B>Groq</B>, <B>Ollama</B>, <B>OpenAI</B>*, <B>OpenRouter</B>*, and <B>Perplexity</B></> },
      { text: <>Developers: update LLMs data structures</>, dev: true },
-      { text: <>1.16.1: Support for <B>OpenAI</B> <B href='https://openai.com/index/hello-gpt-4o/'>GPT-4o</B></> },
-      { text: <>1.16.2: Proper <B>Gemini</B> support, <B>HTML/Markdown</B> downloads, and latest <B>Mistral</B></> },
-      { text: <>1.16.3: Support for <B href='https://www.anthropic.com/news/claude-3-5-sonnet'>Claude 3.5 Sonnet</B> (refresh your <B>Anthropic</B> models)</> },
-      { text: <>1.16.4: <B>8192 tokens</B> support for Claude 3.5 Sonnet</> },
-      { text: <>1.16.5: OpenAI <B>GPT-4o Mini</B> support</> },
-      { text: <>1.16.6: Groq <B>Llama 3.1</B> support</> },
-      { text: <>1.16.7: Gpt-4o <B>2024-08-06</B></> },
-      { text: <>1.16.8: <B>ChatGPT-4o</B> latest</> },
-      { text: <>1.16.9: <B>Gemini</B> fixes</> },
-      { text: <>OpenAI <B>o1</B>, DeepSeek R1, and newer models require Big-AGI 2. <B href='https://form.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2'>Sign up here</B></> },
+      { text: <>1.16.1: Support for <B>OpenAI</B> <B href='https://openai.com/index/hello-gpt-4o/'>GPT-4o</B> (refresh your OpenAI models)</> },
    ],
  },
  {
@@ -7,7 +7,7 @@ import { useAppStateStore } from '~/common/state/store-appstate';


 // update this variable every time you want to broadcast a new version to clients
-export const incrementalNewsVersion: number = 16.9; // not notifying for 1.16.9
+export const incrementalNewsVersion: number = 16.1;


 interface NewsState {
@@ -1,5 +1,4 @@
 import * as React from 'react';
-import { v4 as uuidv4 } from 'uuid';

 import { Alert, Box, Button, Card, CardContent, CircularProgress, Divider, FormLabel, Grid, IconButton, LinearProgress, Tab, tabClasses, TabList, TabPanel, Tabs, Typography } from '@mui/joy';
 import AddIcon from '@mui/icons-material/Add';
@@ -103,11 +102,8 @@ export function Creator(props: { display: boolean }) {
    strings: editedInstructions, stringEditors: instructionEditors,
  } = useFormEditTextArray(Prompts, PromptTitles);

-  const { steps: creationChainSteps, id: chainId } = React.useMemo(() => {
-    return {
-      steps: createChain(editedInstructions, PromptTitles),
-      id: uuidv4(),
-    };
+  const creationChainSteps = React.useMemo(() => {
+    return createChain(editedInstructions, PromptTitles);
  }, [editedInstructions]);

  const llmLabel = personaLlm?.label || undefined;
@@ -126,7 +122,7 @@ export function Creator(props: { display: boolean }) {
    chainError,
    userCancelChain,
    restartChain,
-  } = useLLMChain(creationChainSteps, personaLlm?.id, chainInputText ?? undefined, savePersona, 'persona-extract', chainId);
+  } = useLLMChain(creationChainSteps, personaLlm?.id, chainInputText ?? undefined, savePersona);


  // Reset the relevant state when the selected tab changes
@@ -200,7 +200,7 @@ export function SettingsModal(props: {

        <TabPanel value={PreferencesTab.Tools} variant='outlined' sx={{ p: 'var(--Tabs-gap)', borderRadius: 'md' }}>
          <Topics>
-            <Topic icon={<SearchIcon />} title='Browsing'>
+            <Topic icon={<SearchIcon />} title='Browsing' startCollapsed>
              <BrowseSettings />
            </Topic>
            <Topic icon={<SearchIcon />} title='Google Search API' startCollapsed>
@@ -1,15 +0,0 @@
-import * as React from 'react';
-
-import { Typography } from '@mui/joy';
-
-import CheckRoundedIcon from '@mui/icons-material/CheckRounded';
-
-
-export function AlreadySet(props: { required?: boolean }) {
-  return (
-    <Typography level='body-sm' startDecorator={props.required ? undefined : <CheckRoundedIcon color='success' />}>
-      {/*Installed Already*/}
-      {props.required ? 'required' : 'Already set on server'}
-    </Typography>
-  );
-}
@@ -9,6 +9,7 @@ import MoreHorizIcon from '@mui/icons-material/MoreHoriz';
 import { useModelsStore } from '~/modules/llms/store-llms';

 import { AgiSquircleIcon } from '~/common/components/icons/AgiSquircleIcon';
+import { authUserButton } from '~/common/providers/ProviderAuth';
 import { checkDivider, checkVisibileIcon, NavItemApp, navItems } from '~/common/app.nav';
 import { themeZIndexDesktopNav } from '~/common/app.theme';

@@ -184,6 +185,7 @@ export function DesktopNav(props: { component: React.ElementType, currentApp?: N
      <DesktopNavGroupBox sx={{ mb: 'calc(2 * var(--GroupMarginY))' }}>
        {navExtLinkItems}
        {navModalItems}
+        {authUserButton}
      </DesktopNavGroupBox>

    </InvertedBar>
@@ -0,0 +1,36 @@
+import * as React from 'react';
+import dynamic from 'next/dynamic';
+import { RedirectToSignIn, SignedIn, SignedOut, UserButton } from '@clerk/nextjs';
+
+
+const enableClerk = !!process.env.NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY;
+
+// Dynamically import ClerkProvider only if ENABLE_CLERK is true
+const ClerkProviderDynamic = !enableClerk ? null : dynamic(() =>
+  import('@clerk/nextjs')
+    .then(({ ClerkProvider }) => ClerkProvider)
+    .catch(err => {
+      console.error('Failed to load ClerkProvider:', err);
+      const AuthLoadIssue = () => <>Issue Loading Auth</>;
+      AuthLoadIssue.displayName = 'AuthLoadIssue';
+      return AuthLoadIssue;
+    }),
+);
+
+export const ProviderAuth = (props: { children: React.ReactNode }) => (enableClerk && ClerkProviderDynamic)
+  ? (
+    <ClerkProviderDynamic>
+      <SignedIn>
+        {props.children}
+      </SignedIn>
+      <SignedOut>
+        <RedirectToSignIn />
+      </SignedOut>
+    </ClerkProviderDynamic>
+  ) : props.children;
+
+export const authUserButton = (enableClerk && ClerkProviderDynamic)
+  ? <>
+    <UserButton />
+  </>
+  : null;
@@ -5,7 +5,7 @@ import { v4 as uuidv4 } from 'uuid';

 import { DLLMId, getChatLLMId } from '~/modules/llms/store-llms';

-import { idbStateStorage } from '../util/idbUtils';
+import { IDB_MIGRATION_INITIAL, idbStateStorage } from '../util/idbUtils';
 import { countModelTokens } from '../util/token-counter';
 import { defaultSystemPurposeId, SystemPurposeId } from '../../data';

@@ -407,7 +407,10 @@ export const useChatStore = create<ConversationsStore>()(devtools(
      storage: createJSONStorage(() => idbStateStorage),

      // Migrations
-      migrate: (persistedState: unknown, _fromVersion: number): ConversationsStore => {
+      migrate: (persistedState: unknown, fromVersion: number): ConversationsStore => {
+        // -1 -> 3: migration loading from localStorage to IndexedDB
+        if (fromVersion === IDB_MIGRATION_INITIAL)
+          return _migrateLocalStorageData() as any;

        // other: just proceed
        return persistedState as any;
@@ -462,6 +465,32 @@ function getNextBranchTitle(currentTitle: string): string {
    return `(1) ${currentTitle}`;
 }

+/**
+ * Returns the chats stored in the localStorage, and rename the key for
+ * backup/data loss prevention purposes
+ */
+function _migrateLocalStorageData(): ChatState | {} {
+  const key = 'app-chats';
+  const value = localStorage.getItem(key);
+  if (!value) return {};
+  try {
+    // parse the localStorage state
+    const localStorageState = JSON.parse(value)?.state;
+
+    // backup and delete the localStorage key
+    const backupKey = `${key}-v2`;
+    localStorage.setItem(backupKey, value);
+    localStorage.removeItem(key);
+
+    // match the state from localstorage
+    return {
+      conversations: localStorageState?.conversations ?? [],
+    };
+  } catch (error) {
+    console.error('LocalStorage migration error', error);
+    return {};
+  }
+}

 /**
 * Convenience function to count the tokens in a DMessage object
@@ -1,6 +1,10 @@
 import type { StateStorage } from 'zustand/middleware';
 import { del as idbDel, get as idbGet, set as idbSet } from 'idb-keyval';

+// used by the state storage middleware to detect data migration from the old state storage (localStorage)
+// NOTE: remove past 2024-03-19 (6 months past release of this utility conversion)
+export const IDB_MIGRATION_INITIAL = -1;
+

 // set to true to enable debugging
 const DEBUG_SCHEDULER = false;
@@ -126,6 +130,17 @@ export const idbStateStorage: StateStorage = {
    if (DEBUG_SCHEDULER)
      console.warn('   (read bytes:', value?.length?.toLocaleString(), ')');

+    /* IMPORTANT!
+     * We modify the default behavior of `getItem` to return a {version: -1} object if a key is not found.
+     * This is to trigger the migration across state storage implementations, as Zustand would not call the
+     * 'migrate' function otherwise.
+     * See 'https://github.com/enricoros/big-agi/pull/158' for more details
+     */
+    if (value === undefined) {
+      return JSON.stringify({
+        version: IDB_MIGRATION_INITIAL,
+      });
+    }
    return value || null;
  },
  setItem: (name: string, value: string): void => {
@@ -8,11 +8,8 @@ export function prettyBaseModel(model: string | undefined): string {
  if (!model) return '';
  if (model.includes('gpt-4-vision-preview')) return 'GPT-4 Vision';
  if (model.includes('gpt-4-1106-preview')) return 'GPT-4 Turbo';
-  if (model.includes('gpt-4-32k')) return 'GPT-4-32k';
-  if (model.includes('gpt-4o-mini')) return 'GPT-4o Mini';
-  if (model.includes('gpt-4o')) return 'GPT-4o';
-  if (model.includes('gpt-4-turbo')) return 'GPT-4 Turbo';
-  if (model.includes('gpt-4')) return 'GPT-4';
+  if (model.includes('gpt-4-32k')) return 'gpt-4-32k';
+  if (model.includes('gpt-4')) return 'gpt-4';
  if (model.includes('gpt-3.5-turbo-instruct')) return '3.5 Turbo Instruct';
  if (model.includes('gpt-3.5-turbo-1106')) return '3.5 Turbo 16k';
  if (model.includes('gpt-3.5-turbo-16k')) return '3.5 Turbo 16k';
@@ -6,20 +6,14 @@ import { DLLMId, findLLMOrThrow } from '~/modules/llms/store-llms';
 // Do not set this to true in production, it's very verbose
 const DEBUG_TOKEN_COUNT = false;

-// Globals
-// const tokenEncodings: string[] = ['gpt2', 'r50k_base', 'p50k_base', 'p50k_edit', 'cl100k_base', 'o200k_base'] satisfies TiktokenEncoding[];

-// Global symbols to dynamically load the Tiktoken library
+// global symbols to dynamically load the Tiktoken library
 let get_encoding: ((encoding: TiktokenEncoding) => Tiktoken) | null = null;
 let encoding_for_model: ((model: TiktokenModel) => Tiktoken) | null = null;
 let preloadPromise: Promise<void> | null = null;
 let informTheUser = false;

-/**
- * Preloads the Tiktoken library if not already loaded.
- * @returns {Promise<void>} A promise that resolves when the library is loaded.
- */
-export function preloadTiktokenLibrary(): Promise<void> {
+export function preloadTiktokenLibrary() {
  if (!preloadPromise) {
    preloadPromise = import('tiktoken')
      .then(tiktoken => {
@@ -39,21 +33,16 @@ export function preloadTiktokenLibrary(): Promise<void> {


 /**
- * Wrapper around the Tiktoken library to keep tokenizers for all models in a cache.
- * Also, preloads the tokenizer for the default model to avoid initial stall.
+ * Wrapper around the Tiktoken library, to keep tokenizers for all models in a cache
+ *
+ * We also preload the tokenizer for the default model, so that the first time a user types
+ * a message, it doesn't stall loading the tokenizer.
 */
 export const countModelTokens: (text: string, llmId: DLLMId, debugFrom: string) => number | null = (() => {
  // return () => 0;
  const tokenEncoders: { [modelId: string]: Tiktoken } = {};
-  let encodingDefault: Tiktoken | null = null;
+  let encodingCL100K: Tiktoken | null = null;

-  /**
-   * Counts the tokens in the given text for the specified model.
-   * @param {string} text - The text to tokenize.
-   * @param {DLLMId} llmId - The ID of the LLM.
-   * @param {string} debugFrom - Debug information.
-   * @returns {number | null} The token count or null if not ready.
-   */
  function _tokenCount(text: string, llmId: DLLMId, debugFrom: string): number | null {

    // The library shall have been preloaded - if not, attempt to start its loading and return null to indicate we're not ready to count
@@ -66,23 +55,21 @@ export const countModelTokens: (text: string, llmId: DLLMId, debugFrom: string)
      return null;
    }

-    const openaiModel = findLLMOrThrow(llmId)?.options?.llmRef;
+    const { options: { llmRef: openaiModel } } = findLLMOrThrow(llmId);
    if (!openaiModel) throw new Error(`LLM ${llmId} has no LLM reference id`);
-
    if (!(openaiModel in tokenEncoders)) {
      try {
        tokenEncoders[openaiModel] = encoding_for_model(openaiModel as TiktokenModel);
      } catch (e) {
-        // fallback to the default encoding across all models (not just OpenAI - this will be used everywhere..)
-        if (!encodingDefault)
-          encodingDefault = get_encoding('cl100k_base');
-        tokenEncoders[openaiModel] = encodingDefault;
+        // make sure we recycle the default encoding across all models
+        if (!encodingCL100K)
+          encodingCL100K = get_encoding('cl100k_base');
+        tokenEncoders[openaiModel] = encodingCL100K;
      }
    }
-
+    let count: number = 0;
    // Note: the try/catch shouldn't be necessary, but there could be corner cases where the tiktoken library throws
    // https://github.com/enricoros/big-agi/issues/182
-    let count = 0;
    try {
      count = tokenEncoders[openaiModel]?.encode(text, 'all', [])?.length || 0;
    } catch (e) {
@@ -1,4 +1,4 @@
-import { llmChatGenerateOrThrow, VChatFunctionIn, VChatMessageIn } from '~/modules/llms/llm.client';
+import { llmChatGenerateOrThrow, VChatFunctionIn } from '~/modules/llms/llm.client';
 import { useModelsStore } from '~/modules/llms/store-llms';

 import { useChatStore } from '~/common/state/store-chats';
@@ -83,18 +83,13 @@ export function autoSuggestions(conversationId: string, assistantMessageId: stri

  // Follow-up: Auto-Diagrams
  if (suggestDiagrams) {
-    const instructions: VChatMessageIn[] = [
-      { role: 'system', content: systemMessage.text },
-      { role: 'user', content: userMessage.text },
-      { role: 'assistant', content: assistantMessageText },
-    ];
-    llmChatGenerateOrThrow(
-      funcLLMId,
-      instructions,
-      'chat-followup-diagram', conversationId,
-      [suggestPlantUMLFn], 'draw_plantuml_diagram',
+    void llmChatGenerateOrThrow(funcLLMId, [
+        { role: 'system', content: systemMessage.text },
+        { role: 'user', content: userMessage.text },
+        { role: 'assistant', content: assistantMessageText },
+      ], [suggestPlantUMLFn], 'draw_plantuml_diagram',
    ).then(chatResponse => {
-      // cheap way to check if the function was supported
+
      if (!('function_arguments' in chatResponse))
        return;

@@ -115,8 +110,7 @@ export function autoSuggestions(conversationId: string, assistantMessageId: stri
        }
      }
    }).catch(err => {
-      // Likely the model did not support function calling
-      // console.log('autoSuggestions: diagram error:', err);
+      console.error('autoSuggestions::diagram:', err);
    });
  }

@@ -1,5 +1,5 @@
 import { getFastLLMId } from '~/modules/llms/store-llms';
-import { llmChatGenerateOrThrow, VChatMessageIn } from '~/modules/llms/llm.client';
+import { llmChatGenerateOrThrow } from '~/modules/llms/llm.client';

 import { useChatStore } from '~/common/state/store-chats';

@@ -34,23 +34,21 @@ export async function conversationAutoTitle(conversationId: string, forceReplace

  try {
    // LLM chat-generate call
-    const instructions: VChatMessageIn[] = [
-      { role: 'system', content: `You are an AI conversation titles assistant who specializes in creating expressive yet few-words chat titles.` },
-      {
-        role: 'user', content:
-          'Analyze the given short conversation (every line is truncated) and extract a concise chat title that ' +
-          'summarizes the conversation in as little as a couple of words.\n' +
-          'Only respond with the lowercase short title and nothing else.\n' +
-          '\n' +
-          '```\n' +
-          historyLines.join('\n') +
-          '```\n',
-      },
-    ];
    const chatResponse = await llmChatGenerateOrThrow(
      fastLLMId,
-      instructions,
-      'chat-ai-title', conversationId,
+      [
+        { role: 'system', content: `You are an AI conversation titles assistant who specializes in creating expressive yet few-words chat titles.` },
+        {
+          role: 'user', content:
+            'Analyze the given short conversation (every line is truncated) and extract a concise chat title that ' +
+            'summarizes the conversation in as little as a couple of words.\n' +
+            'Only respond with the lowercase short title and nothing else.\n' +
+            '\n' +
+            '```\n' +
+            historyLines.join('\n') +
+            '```\n',
+        },
+      ],
      null, null,
    );

@@ -68,7 +68,7 @@ export function DiagramsModal(props: { config: DiagramConfig, onClose: () => voi
  const [diagramLlm, llmComponent] = useFormRadioLlmType('Generator', 'chat');

  // derived state
-  const { conversationId, messageId, text: subject } = props.config;
+  const { conversationId, text: subject } = props.config;
  const diagramLlmId = diagramLlm?.id;


@@ -98,7 +98,7 @@ export function DiagramsModal(props: { config: DiagramConfig, onClose: () => voi
    const diagramPrompt = bigDiagramPrompt(diagramType, diagramLanguage, systemMessage.text, subject, customInstruction);

    try {
-      await llmStreamingChatGenerate(diagramLlm.id, diagramPrompt, 'ai-diagram', messageId, null, null, stepAbortController.signal,
+      await llmStreamingChatGenerate(diagramLlm.id, diagramPrompt, null, null, stepAbortController.signal,
        ({ textSoFar }) => textSoFar && setDiagramCode(diagramCode = textSoFar),
      );
    } catch (error: any) {
@@ -109,7 +109,7 @@ export function DiagramsModal(props: { config: DiagramConfig, onClose: () => voi
      setAbortController(null);
    }

-  }, [abortController, conversationId, customInstruction, diagramLanguage, diagramLlm, diagramType, messageId, subject]);
+  }, [abortController, conversationId, diagramLanguage, diagramLlm, diagramType, subject, customInstruction]);


  // [Effect] Auto-abort on unmount
@@ -117,7 +117,7 @@ export function FlattenerModal(props: {
    await startStreaming(llm.id, [
      { role: 'system', content: flattenProfile.systemPrompt },
      { role: 'user', content: encodeConversationAsUserMessage(flattenProfile.userPrompt, messages) },
-    ], 'ai-flattener', messages[0].id);
+    ]);

  }, [llm, props.conversationId, startStreaming]);

@@ -1,5 +1,5 @@
 import { getFastLLMId } from '~/modules/llms/store-llms';
-import { llmChatGenerateOrThrow, VChatMessageIn } from '~/modules/llms/llm.client';
+import { llmChatGenerateOrThrow } from '~/modules/llms/llm.client';


 const simpleImagineSystemPrompt =
@@ -10,15 +10,14 @@ Provide output as a lowercase prompt and nothing else.`;
 /**
 * Creates a caption for a drawing or photo given some description - used to elevate the quality of the imaging
 */
-export async function imaginePromptFromText(messageText: string, contextRef: string): Promise<string | null> {
+export async function imaginePromptFromText(messageText: string): Promise<string | null> {
  const fastLLMId = getFastLLMId();
  if (!fastLLMId) return null;
  try {
-    const instructions: VChatMessageIn[] = [
+    const chatResponse = await llmChatGenerateOrThrow(fastLLMId, [
      { role: 'system', content: simpleImagineSystemPrompt },
      { role: 'user', content: 'Write a prompt, based on the following input.\n\n```\n' + messageText.slice(0, 1000) + '\n```\n' },
-    ];
-    const chatResponse = await llmChatGenerateOrThrow(fastLLMId, instructions, 'draw-expand-prompt', contextRef, null, null);
+    ], null, null);
    return chatResponse.content?.trim() ?? null;
  } catch (error: any) {
    console.error('imaginePromptFromText: fetch request error:', error);
@@ -132,7 +132,7 @@ export class Agent {
    S.messages.push({ role: 'user', content: prompt });
    let content: string;
    try {
-      content = (await llmChatGenerateOrThrow(llmId, S.messages, 'chat-react-turn', null, null, null, 500)).content;
+      content = (await llmChatGenerateOrThrow(llmId, S.messages, null, null, 500)).content;
    } catch (error: any) {
      content = `Error in llmChatGenerateOrThrow: ${error}`;
    }
@@ -194,8 +194,7 @@ async function search(query: string): Promise<string> {
 async function browse(url: string): Promise<string> {
  try {
    const page = await callBrowseFetchPage(url);
-    const pageContent = page.content.markdown || page.content.text || page.content.html || '';
-    return JSON.stringify(pageContent ? { text: pageContent } : { error: 'Issue reading the page' });
+    return JSON.stringify(page.content ? { text: page.content } : { error: 'Issue reading the page' });
  } catch (error) {
    console.error('Error browsing:', (error as Error).message);
    return 'An error occurred while browsing to the URL. Missing WSS Key?';
@@ -1,5 +1,5 @@
 import { DLLMId, findLLMOrThrow } from '~/modules/llms/store-llms';
-import { llmChatGenerateOrThrow, VChatMessageIn } from '~/modules/llms/llm.client';
+import { llmChatGenerateOrThrow } from '~/modules/llms/llm.client';


 // prompt to be tried when doing recursive summerization.
@@ -80,11 +80,10 @@ async function cleanUpContent(chunk: string, llmId: DLLMId, _ignored_was_targetW
  const autoResponseTokensSize = contextTokens ? Math.floor(contextTokens * outputTokenShare) : null;

  try {
-    const instructions: VChatMessageIn[] = [
+    const chatResponse = await llmChatGenerateOrThrow(llmId, [
      { role: 'system', content: cleanupPrompt },
      { role: 'user', content: chunk },
-    ];
-    const chatResponse = await llmChatGenerateOrThrow(llmId, instructions, 'chat-ai-summarize', null, null, null, autoResponseTokensSize ?? undefined);
+    ], null, null, autoResponseTokensSize ?? undefined);
    return chatResponse?.content ?? '';
  } catch (error: any) {
    return '';
@@ -1,7 +1,7 @@
 import * as React from 'react';

 import { DLLMId, findLLMOrThrow } from '~/modules/llms/store-llms';
-import { llmStreamingChatGenerate, VChatContextRef, VChatMessageIn, VChatStreamContextName } from '~/modules/llms/llm.client';
+import { llmStreamingChatGenerate, VChatMessageIn } from '~/modules/llms/llm.client';


 // set to true to log to the console
@@ -20,7 +20,7 @@ export interface LLMChainStep {
 /**
 * React hook to manage a chain of LLM transformations.
 */
-export function useLLMChain(steps: LLMChainStep[], llmId: DLLMId | undefined, chainInput: string | undefined, onSuccess: (output: string, input: string) => void, contextName: VChatStreamContextName, contextRef: VChatContextRef) {
+export function useLLMChain(steps: LLMChainStep[], llmId: DLLMId | undefined, chainInput: string | undefined, onSuccess?: (output: string, input: string) => void) {

  // state
  const [chain, setChain] = React.useState<ChainState | null>(null);
@@ -114,7 +114,7 @@ export function useLLMChain(steps: LLMChainStep[], llmId: DLLMId | undefined, ch
    setChainStepInterimText(null);

    // LLM call (streaming, cancelable)
-    llmStreamingChatGenerate(llmId, llmChatInput, contextName, contextRef, null, null, stepAbortController.signal,
+    llmStreamingChatGenerate(llmId, llmChatInput, null, null, stepAbortController.signal,
      ({ textSoFar }) => {
        textSoFar && setChainStepInterimText(interimText = textSoFar);
      })
@@ -141,7 +141,7 @@ export function useLLMChain(steps: LLMChainStep[], llmId: DLLMId | undefined, ch
        stepAbortController.abort('step aborted');
      _chainAbortController.signal.removeEventListener('abort', globalToStepListener);
    };
-  }, [chain, contextRef, contextName, llmId, onSuccess]);
+  }, [chain, llmId, onSuccess]);


  return {
@@ -1,7 +1,7 @@
 import * as React from 'react';

 import type { DLLMId } from '~/modules/llms/store-llms';
-import { llmStreamingChatGenerate, VChatContextRef, VChatMessageIn, VChatStreamContextName } from '~/modules/llms/llm.client';
+import { llmStreamingChatGenerate, VChatMessageIn } from '~/modules/llms/llm.client';


 export function useStreamChatText() {
@@ -13,7 +13,7 @@ export function useStreamChatText() {
  const abortControllerRef = React.useRef<AbortController | null>(null);


-  const startStreaming = React.useCallback(async (llmId: DLLMId, prompt: VChatMessageIn[], contextName: VChatStreamContextName, contextRef: VChatContextRef) => {
+  const startStreaming = React.useCallback(async (llmId: DLLMId, prompt: VChatMessageIn[]) => {
    setStreamError(null);
    setPartialText(null);
    setText(null);
@@ -24,7 +24,7 @@ export function useStreamChatText() {

    try {
      let lastText = '';
-      await llmStreamingChatGenerate(llmId, prompt, contextName, contextRef, null, null, abortControllerRef.current.signal, ({ textSoFar }) => {
+      await llmStreamingChatGenerate(llmId, prompt, null, null, abortControllerRef.current.signal, ({ textSoFar }) => {
        if (textSoFar) {
          lastText = textSoFar;
          setPartialText(lastText);
@@ -30,30 +30,32 @@ export function BeamView(props: {

  // external state
  const { novel: explainerUnseen, touch: explainerCompleted, forget: explainerShow } = useUICounter('beam-wizard');
-  const gatherAutoStartAfterScatter = useModuleBeamStore(state => state.gatherAutoStartAfterScatter);
  const {
    /* root */ editInputHistoryMessage,
    /* scatter */ setRayCount, startScatteringAll, stopScatteringAll,
  } = props.beamStore.getState();
  const {
    /* root */ inputHistory, inputIssues, inputReady,
-    /* scatter */ hadImportedRays, isScattering, raysReady,
+    /* scatter */ isScattering, raysReady,
    /* gather (composite) */ canGather,
+    /* IDs */ rayIds, fusionIds,
  } = useBeamStore(props.beamStore, useShallow(state => ({
    // input
    inputHistory: state.inputHistory,
    inputIssues: state.inputIssues,
    inputReady: state.inputReady,
    // scatter
-    hadImportedRays: state.hadImportedRays,
    isScattering: state.isScattering,
    raysReady: state.raysReady,
    // gather (composite)
    canGather: state.raysReady >= 2 && state.currentFactoryId !== null && state.currentGatherLlmId !== null,
+    // IDs
+    rayIds: state.rays.map(ray => ray.rayId),
+    fusionIds: state.fusions.map(fusion => fusion.fusionId),
+  })));
+  const { gatherAutoStartAfterScatter } = useModuleBeamStore(useShallow(state => ({
+    gatherAutoStartAfterScatter: state.gatherAutoStartAfterScatter,
  })));
-  // the following are independent because of useShallow, which would break in the above call
-  const rayIds = useBeamStore(props.beamStore, useShallow(state => state.rays.map(ray => ray.rayId)));
-  const fusionIds = useBeamStore(props.beamStore, useShallow(state => state.fusions.map(fusion => fusion.fusionId)));

  // derived state
  const raysCount = rayIds.length;
@@ -171,7 +173,6 @@ export function BeamView(props: {
        beamStore={props.beamStore}
        isMobile={props.isMobile}
        rayIds={rayIds}
-        hadImportedRays={hadImportedRays}
        onIncreaseRayCount={handleRayIncreaseCount}
        // linkedLlmId={currentGatherLlmId}
      />
@@ -13,7 +13,6 @@ import { BeamStoreApi, useBeamStore } from '../store-beam.hooks';
 import { FFactoryId, FUSION_FACTORIES } from './instructions/beam.gather.factories';
 import { GATHER_COLOR } from '../beam.config';
 import { beamPaneSx } from '../BeamCard';
-import { useModuleBeamStore } from '../store-module-beam';


 const gatherPaneClasses = {
@@ -80,9 +79,8 @@ export function BeamGatherPane(props: {
    setCurrentFactoryId: state.setCurrentFactoryId,
    setCurrentGatherLlmId: state.setCurrentGatherLlmId,
  })));
-  const gatherAutoStartAfterScatter = useModuleBeamStore(state => state.gatherAutoStartAfterScatter);
  const [_, gatherLlmComponent/*, gatherLlmIcon*/] = useLLMSelect(
-    currentGatherLlmId, setCurrentGatherLlmId, props.isMobile ? '' : 'Merge Model', true, !props.canGather && !gatherAutoStartAfterScatter,
+    currentGatherLlmId, setCurrentGatherLlmId, props.isMobile ? '' : 'Merge Model', true, !props.canGather,
  );

  // derived state
@@ -170,24 +170,23 @@ export function Fusion(props: {
          <GoodTooltip title='Use this message'>
            <IconButton
              size='sm'
-              // variant='plain'
+              // variant='solid'
              color={GATHER_COLOR}
              disabled={isFusing}
              onClick={handleFusionUse}
              // endDecorator={<TelegramIcon />}
              sx={{
                // ...BEAM_BTN_SX,
-                fontSize: 'xs',
-                // '--Icon-fontSize': 'var(--joy-fontSize-xl)',
+                // fontSize: 'xs',
                // backgroundColor: 'background.popup',
                // border: '1px solid',
                // borderColor: `${GATHER_COLOR}.outlinedBorder`,
                // boxShadow: `0 4px 16px -4px rgb(var(--joy-palette-${GATHER_COLOR}-mainChannel) / 20%)`,
                animation: `${animationEnterBelow} 0.1s ease-out`,
-                whiteSpace: 'nowrap',
+                // whiteSpace: 'nowrap',
              }}
            >
-              {/*Use*/}
+              {/*Ok*/}
              <TelegramIcon />
            </IconButton>
          </GoodTooltip>
@@ -96,7 +96,7 @@ export async function executeChatGenerate(_i: ChatGenerateInstruction, inputs: E
  };

  // LLM Streaming generation
-  return streamAssistantMessage(inputs.llmId, history, 'beam-gather', inputs.contextRef, getUXLabsHighPerformance() ? 0 : 1, 'off', onMessageUpdate, inputs.chainAbortController.signal)
+  return streamAssistantMessage(inputs.llmId, history, getUXLabsHighPerformance() ? 0 : 1, 'off', onMessageUpdate, inputs.chainAbortController.signal)
    .then((status) => {
      // re-throw errors, as streamAssistantMessage catches internally
      if (status.outcome === 'aborted') {
@@ -23,7 +23,6 @@ export interface ExecutionInputState {
  readonly chatMessages: DMessage[];
  readonly rayMessages: DMessage[];
  readonly llmId: DLLMId;
-  readonly contextRef: string; // not useful
  // interaction
  readonly chainAbortController: AbortController;
  readonly updateProgressComponent: (component: React.ReactNode) => void;
@@ -68,7 +67,6 @@ export function gatherStartFusion(
    chatMessages: chatMessages,
    rayMessages: rayMessages,
    llmId: initialFusion.llmId,
-    contextRef: initialFusion.fusionId,
    // interaction
    chainAbortController: new AbortController(),
    updateProgressComponent: (component: React.ReactNode) => onUpdateBFusion({ fusingProgressComponent: component }),
@@ -16,7 +16,6 @@ import type { DLLMId } from '~/modules/llms/store-llms';

 import { GoodTooltip } from '~/common/components/GoodTooltip';
 import { InlineError } from '~/common/components/InlineError';
-import { animationEnterBelow } from '~/common/util/animUtils';
 import { copyToClipboard } from '~/common/util/clipboardUtils';
 import { useLLMSelect } from '~/common/components/forms/useLLMSelect';

@@ -110,8 +109,7 @@ function RayControls(props: {

 export function BeamRay(props: {
  beamStore: BeamStoreApi,
-  hadImportedRays: boolean
-  isRemovable: boolean,
+  isRemovable: boolean
  rayId: string,
  rayIndexWeak: number,
  // linkedLlmId: DLLMId | null,
@@ -242,20 +240,16 @@ export function BeamRay(props: {
            <GoodTooltip title='Choose this message'>
              <IconButton
                size='sm'
-                // variant='plain'
                color={GATHER_COLOR}
                disabled={isImported || isScattering}
                onClick={handleRayUse}
-                // endDecorator={!isImported ? <TelegramIcon /> : null}
                sx={{
                  fontSize: 'xs',
-                  // '--Icon-fontSize': 'var(--joy-fontSize-xl)',
                  px: isImported ? 1 : undefined,
-                  animation: `${animationEnterBelow} 0.1s ease-out`,
                  whiteSpace: 'nowrap',
                }}
              >
-                {isImported ? 'From Chat' : /*props.hadImportedRays ? 'Replace' : 'Use'*/ <TelegramIcon />}
+                {isImported ? 'From Chat' : /*'Use'*/ <TelegramIcon />}
              </IconButton>
            </GoodTooltip>

@@ -27,7 +27,6 @@ const rayGridMobileSx: SxProps = {

 export function BeamRayGrid(props: {
  beamStore: BeamStoreApi,
-  hadImportedRays: boolean
  isMobile: boolean,
  onIncreaseRayCount: () => void,
  rayIds: string[],
@@ -45,7 +44,6 @@ export function BeamRayGrid(props: {
          key={'ray-' + rayId}
          rayIndexWeak={index}
          beamStore={props.beamStore}
-          hadImportedRays={props.hadImportedRays}
          isRemovable={raysCount > SCATTER_RAY_MIN}
          rayId={rayId}
          // linkedLlmId={props.linkedLlmId}
@@ -67,7 +67,7 @@ function rayScatterStart(ray: BRay, llmId: DLLMId | null, inputHistory: DMessage

  // stream the assistant's messages
  const messagesHistory: VChatMessageIn[] = inputHistory.map(({ role, text }) => ({ role, content: text }));
-  streamAssistantMessage(llmId, messagesHistory, 'beam-scatter', ray.rayId, getUXLabsHighPerformance() ? 0 : rays.length, 'off', updateMessage, abortController.signal)
+  streamAssistantMessage(llmId, messagesHistory, getUXLabsHighPerformance() ? 0 : rays.length, 'off', updateMessage, abortController.signal)
    .then((status) => {
      _rayUpdate(ray.rayId, {
        status: (status.outcome === 'success') ? 'success'
@@ -134,7 +134,6 @@ export function rayIsImported(ray: BRay | null): boolean {
 interface ScatterStateSlice {

  rays: BRay[];
-  hadImportedRays: boolean;

  // derived state
  isScattering: boolean; // true if any ray is scattering at the moment
@@ -149,7 +148,6 @@ export const reInitScatterStateSlice = (prevRays: BRay[]): ScatterStateSlice =>
  return {
    // (remember) keep the same quantity of rays and same llms
    rays: prevRays.map(prevRay => createBRay(prevRay.rayLlmId)),
-    hadImportedRays: false,

    isScattering: false,
    raysReady: 0,
@@ -240,7 +238,6 @@ export const createScatterSlice: StateCreator<RootStoreSlice & ScatterStoreSlice
        // append the other rays (excluding the ones to remove)
        ...rays.filter((ray) => !raysToRemove.includes(ray)),
      ],
-      hadImportedRays: messages.length > 0,
    });
    _storeLastScatterConfig();
    _syncRaysStateToScatter();
@@ -70,7 +70,7 @@ const createRootSlice: StateCreator<BeamStore, [], [], RootStoreSlice> = (_set,


  open: (chatHistory: Readonly<DMessage[]>, initialChatLlmId: DLLMId | null, callback: BeamSuccessCallback) => {
-    const { isOpen: wasAlreadyOpen, terminateKeepingSettings, loadBeamConfig, hadImportedRays, setRayLlmIds, setCurrentGatherLlmId } = _get();
+    const { isOpen: wasAlreadyOpen, terminateKeepingSettings, loadBeamConfig, setRayLlmIds, setCurrentGatherLlmId } = _get();

    // reset pending operations
    terminateKeepingSettings();
@@ -89,7 +89,6 @@ const createRootSlice: StateCreator<BeamStore, [], [], RootStoreSlice> = (_set,
      onSuccessCallback: callback,

      // rays already reset
-      hadImportedRays,

      // update the model only if the dialog was not already open
      ...(!wasAlreadyOpen && initialChatLlmId && {
@@ -1,12 +1,10 @@
 import * as React from 'react';
-import { useShallow } from 'zustand/react/shallow';
+import { shallow } from 'zustand/shallow';

-import { Checkbox, FormControl, FormHelperText, Option, Select, Typography } from '@mui/joy';
+import { Checkbox, FormControl, FormHelperText } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
-import { ExternalLink } from '~/common/components/ExternalLink';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
-import { FormLabelStart } from '~/common/components/forms/FormLabelStart';
+import { Link } from '~/common/components/Link';
 import { platformAwareKeystrokes } from '~/common/components/KeyStroke';

 import { useBrowseCapability, useBrowseStore } from './store-module-browsing';
@@ -15,82 +13,50 @@ import { useBrowseCapability, useBrowseStore } from './store-module-browsing';
 export function BrowseSettings() {

  // external state
-  const { mayWork, isServerConfig, isClientValid, inCommand, inComposer, inReact, inPersonas } = useBrowseCapability();
-  const {
-    wssEndpoint, setWssEndpoint,
-    pageTransform, setPageTransform,
-    setEnableCommandBrowse, setEnableComposerAttach, setEnableReactTool, setEnablePersonaTool,
-  } = useBrowseStore(useShallow(state => ({
+  const { mayWork, isServerConfig, isClientValid, inCommand, inComposer, inReact } = useBrowseCapability();
+  const { wssEndpoint, setWssEndpoint, setEnableCommandBrowse, setEnableComposerAttach, setEnableReactTool } = useBrowseStore(state => ({
    wssEndpoint: state.wssEndpoint,
-    pageTransform: state.pageTransform,
-    setPageTransform: state.setPageTransform,
    setWssEndpoint: state.setWssEndpoint,
    setEnableCommandBrowse: state.setEnableCommandBrowse,
    setEnableComposerAttach: state.setEnableComposerAttach,
    setEnableReactTool: state.setEnableReactTool,
-    setEnablePersonaTool: state.setEnablePersonaTool,
-  })));
-
-  const handlePageTransformChange = (_event: any, value: typeof pageTransform | null) => value && setPageTransform(value);
-
+  }), shallow);

  return <>

-    <Typography level='body-sm'>
-      Configure Browsing to enable loading links and web pages. <ExternalLink
-      href='https://github.com/enricoros/big-agi/blob/main/docs/config-feature-browse.md'>
-      Learn more</ExternalLink>.
-    </Typography>
+    <FormHelperText sx={{ display: 'block' }}>
+      Configure a browsing service to enable loading links and pages. See the <Link
+      href='https://github.com/enricoros/big-agi/blob/main/docs/config-feature-browse.md' target='_blank' noLinkStyle>
+      browse configuration guide</Link> for more information.
+    </FormHelperText>

    <FormInputKey
-      autoCompleteId='browse-wss' label='Puppeteer Wss' noKey
+      autoCompleteId='browse-wss' label='Puppeteer Endpoint' noKey
      value={wssEndpoint} onChange={setWssEndpoint}
-      rightLabel={<AlreadySet required={!isServerConfig} />}
+      rightLabel={!isServerConfig ? 'required' : '✔️ already set in server'}
      required={!isServerConfig} isError={!isClientValid && !isServerConfig}
      placeholder='wss://...'
    />

-
-    <FormControl orientation='horizontal' sx={{ justifyContent: 'space-between', alignItems: 'center' }}>
-      <FormLabelStart title='Load pages as:' />
-      <Select
-        variant='outlined'
-        value={pageTransform} onChange={handlePageTransformChange}
-        slotProps={{
-          root: { sx: { minWidth: '140px' } },
-          indicator: { sx: { opacity: 0.5 } },
-          button: { sx: { whiteSpace: 'inherit' } },
-        }}
-      >
-        <Option value='text'>Text (default)</Option>
-        <Option value='markdown'>Markdown</Option>
-        <Option value='html'>HTML</Option>
-      </Select>
-    </FormControl>
-
-
-    <Typography level='body-sm' sx={{ mt: 2 }}>Browsing enablement:</Typography>
-
    <FormControl disabled={!mayWork}>
-      <Checkbox size='sm' label='Paste URLs' checked={inComposer} onChange={(event) => setEnableComposerAttach(event.target.checked)} />
-      <FormHelperText>{platformAwareKeystrokes('Load and attach when pasting a URL')}</FormHelperText>
+      <Checkbox variant='outlined' label='Attach URLs' checked={inComposer} onChange={(event) => setEnableComposerAttach(event.target.checked)} />
+      <FormHelperText>{platformAwareKeystrokes('Load and attach a page when pasting a URL')}</FormHelperText>
    </FormControl>

    <FormControl disabled={!mayWork}>
-      <Checkbox size='sm' label='/browse' checked={inCommand} onChange={(event) => setEnableCommandBrowse(event.target.checked)} />
+      <Checkbox variant='outlined' label='/browse' checked={inCommand} onChange={(event) => setEnableCommandBrowse(event.target.checked)} />
      <FormHelperText>{platformAwareKeystrokes('Use /browse to load a web page')}</FormHelperText>
    </FormControl>

    <FormControl disabled={!mayWork}>
-      <Checkbox size='sm' label='ReAct' checked={inReact} onChange={(event) => setEnableReactTool(event.target.checked)} />
+      <Checkbox variant='outlined' label='ReAct' checked={inReact} onChange={(event) => setEnableReactTool(event.target.checked)} />
      <FormHelperText>Enables loadURL() in ReAct</FormHelperText>
    </FormControl>

-    <FormControl disabled>
-      <Checkbox size='sm' label='Chat with Personas' checked={false} onChange={(event) => setEnablePersonaTool(event.target.checked)} />
-      <FormHelperText>Not yet available</FormHelperText>
-      {/*<FormHelperText>Enable loading URLs by Personas</FormHelperText>*/}
-    </FormControl>
+    {/*<FormControl disabled>*/}
+    {/*  <Checkbox variant='outlined' label='Personas' checked={inPersonas} onChange={(event) => setEnablePersonaTool(event.target.checked)} />*/}
+    {/*  <FormHelperText>Enable loading URLs by Personas</FormHelperText>*/}
+    {/*</FormControl>*/}

  </>;
 }
@@ -7,39 +7,31 @@ import { apiAsyncNode } from '~/common/util/trpc.client';
 const DEBUG_SHOW_SCREENSHOT = false;


-// export function
+export async function callBrowseFetchPage(url: string) {

-export async function callBrowseFetchPage(
-  url: string,
-  // transforms?: BrowsePageTransform[],
-  // screenshotOptions?: { width: number, height: number, quality?: number },
-) {
-
-  // validate url
+  // thow if no URL is provided
  url = url?.trim() || '';
  if (!url)
    throw new Error('Browsing error: Invalid URL');

-  // noinspection HttpUrlsUsage: assume https if no protocol is provided
+  // assume https if no protocol is provided
+  // noinspection HttpUrlsUsage
  if (!url.startsWith('http://') && !url.startsWith('https://'))
    url = 'https://' + url;

-  const { wssEndpoint, pageTransform } = useBrowseStore.getState();
+  const clientWssEndpoint = useBrowseStore.getState().wssEndpoint;

  const { pages } = await apiAsyncNode.browse.fetchPages.mutate({
    access: {
      dialect: 'browse-wss',
-      ...(!!wssEndpoint && { wssEndpoint }),
+      ...(!!clientWssEndpoint && { wssEndpoint: clientWssEndpoint }),
    },
-    requests: [{
-      url,
-      transforms: /*transforms ? transforms :*/ [pageTransform],
-      screenshot: /*screenshotOptions ? screenshotOptions :*/ !DEBUG_SHOW_SCREENSHOT ? undefined : {
-        width: 512,
-        height: 512,
-        // quality: 100,
-      },
-    }],
+    subjects: [{ url }],
+    screenshot: DEBUG_SHOW_SCREENSHOT ? {
+      width: 512,
+      height: 512,
+      // quality: 100,
+    } : undefined,
  });

  if (pages.length !== 1)
@@ -50,7 +42,7 @@ export async function callBrowseFetchPage(
  // DEBUG: if there's a screenshot, append it to the dom
  if (DEBUG_SHOW_SCREENSHOT && page.screenshot) {
    const img = document.createElement('img');
-    img.src = page.screenshot.webpDataUrl;
+    img.src = page.screenshot.imageDataUrl;
    img.style.width = `${page.screenshot.width}px`;
    img.style.height = `${page.screenshot.height}px`;
    document.body.appendChild(img);
@@ -59,7 +51,7 @@ export async function callBrowseFetchPage(
  // throw if there's an error
  if (page.error) {
    console.warn('Browsing service error:', page.error);
-    if (!Object.keys(page.content).length)
+    if (!page.content)
      throw new Error(page.error);
  }

@@ -1,9 +1,6 @@
 import { z } from 'zod';
 import { TRPCError } from '@trpc/server';
-
-import { BrowserContext, connect, ScreenshotOptions } from '@cloudflare/puppeteer';
-import { default as TurndownService } from 'turndown';
-import { load as cheerioLoad } from 'cheerio';
+import { BrowserContext, connect, ScreenshotOptions, TimeoutError } from '@cloudflare/puppeteer';

 import { createTRPCRouter, publicProcedure } from '~/server/api/trpc.server';
 import { env } from '~/server/env.mjs';
@@ -19,22 +16,17 @@ const browseAccessSchema = z.object({
  dialect: z.enum(['browse-wss']),
  wssEndpoint: z.string().trim().optional(),
 });
-type BrowseAccessSchema = z.infer<typeof browseAccessSchema>;
-
-const pageTransformSchema = z.enum(['html', 'text', 'markdown']);
-type PageTransformSchema = z.infer<typeof pageTransformSchema>;

 const fetchPageInputSchema = z.object({
  access: browseAccessSchema,
-  requests: z.array(z.object({
+  subjects: z.array(z.object({
    url: z.string().url(),
-    transforms: z.array(pageTransformSchema),
-    screenshot: z.object({
-      width: z.number(),
-      height: z.number(),
-      quality: z.number().optional(),
-    }).optional(),
  })),
+  screenshot: z.object({
+    width: z.number(),
+    height: z.number(),
+    quality: z.number().optional(),
+  }).optional(),
 });


@@ -42,18 +34,16 @@ const fetchPageInputSchema = z.object({

 const fetchPageWorkerOutputSchema = z.object({
  url: z.string(),
-  content: z.record(pageTransformSchema, z.string()),
+  content: z.string(),
  error: z.string().optional(),
  stopReason: z.enum(['end', 'timeout', 'error']),
  screenshot: z.object({
-    webpDataUrl: z.string().startsWith('data:image/webp'),
+    imageDataUrl: z.string().startsWith('data:image/'),
    mimeType: z.string().startsWith('image/'),
    width: z.number(),
    height: z.number(),
  }).optional(),
 });
-type FetchPageWorkerOutputSchema = z.infer<typeof fetchPageWorkerOutputSchema>;
-

 const fetchPagesOutputSchema = z.object({
  pages: z.array(fetchPageWorkerOutputSchema),
@@ -65,23 +55,21 @@ export const browseRouter = createTRPCRouter({
  fetchPages: publicProcedure
    .input(fetchPageInputSchema)
    .output(fetchPagesOutputSchema)
-    .mutation(async ({ input: { access, requests } }) => {
+    .mutation(async ({ input: { access, subjects, screenshot } }) => {
+      const pages: FetchPageWorkerOutputSchema[] = [];

-      const pagePromises = requests.map(request =>
-        workerPuppeteer(access, request.url, request.transforms, request.screenshot));
-
-      const results = await Promise.allSettled(pagePromises);
-
-      const pages: FetchPageWorkerOutputSchema[] = results.map((result, index) =>
-        result.status === 'fulfilled'
-          ? result.value
-          : {
-            url: requests[index].url,
-            content: {},
-            error: result.reason?.message || 'Unknown fetch error',
+      for (const subject of subjects) {
+        try {
+          pages.push(await workerPuppeteer(access, subject.url, screenshot?.width, screenshot?.height, screenshot?.quality));
+        } catch (error: any) {
+          pages.push({
+            url: subject.url,
+            content: '',
+            error: error?.message || JSON.stringify(error) || 'Unknown fetch error',
            stopReason: 'error',
-          },
-      );
+          });
+        }
+      }

      return { pages };
    }),
@@ -89,13 +77,12 @@ export const browseRouter = createTRPCRouter({
 });


-async function workerPuppeteer(
-  access: BrowseAccessSchema,
-  targetUrl: string,
-  transforms: PageTransformSchema[],
-  screenshotOptions?: { width: number, height: number, quality?: number },
-): Promise<FetchPageWorkerOutputSchema> {
+type BrowseAccessSchema = z.infer<typeof browseAccessSchema>;
+type FetchPageWorkerOutputSchema = z.infer<typeof fetchPageWorkerOutputSchema>;

+async function workerPuppeteer(access: BrowseAccessSchema, targetUrl: string, ssWidth: number | undefined, ssHeight: number | undefined, ssQuality: number | undefined): Promise<FetchPageWorkerOutputSchema> {
+
+  // access
  const browserWSEndpoint = (access.wssEndpoint || env.PUPPETEER_WSS_ENDPOINT || '').trim();
  const isLocalBrowser = browserWSEndpoint.startsWith('ws://');
  if (!browserWSEndpoint || (!browserWSEndpoint.startsWith('wss://') && !isLocalBrowser))
@@ -106,7 +93,7 @@ async function workerPuppeteer(

  const result: FetchPageWorkerOutputSchema = {
    url: targetUrl,
-    content: {},
+    content: '',
    error: undefined,
    stopReason: 'error',
    screenshot: undefined,
@@ -130,49 +117,35 @@ async function workerPuppeteer(
    if (!isWebPage) {
      // noinspection ExceptionCaughtLocallyJS
      throw new Error(`Invalid content-type: ${contentType}`);
-    } else {
+    } else
      result.stopReason = 'end';
-    }
  } catch (error: any) {
-    // This was "error instanceof TimeoutError;" but threw some type error - trying the below instead
-    const isTimeout = error?.message?.includes('Navigation timeout') || false;
+    const isTimeout: boolean = error instanceof TimeoutError;
    result.stopReason = isTimeout ? 'timeout' : 'error';
-    if (!isTimeout) {
-      result.error = '[Puppeteer] ' + (error?.message || error?.toString() || 'Unknown goto error');
-    }
+    if (!isTimeout)
+      result.error = '[Puppeteer] ' + error?.message || error?.toString() || 'Unknown goto error';
  }

  // transform the content of the page as text
  try {
    if (result.stopReason !== 'error') {
-      for (const transform of transforms) {
-        switch (transform) {
-          case 'html':
-            result.content.html = cleanHtml(await page.content());
-            break;
-          case 'text':
-            result.content.text = await page.evaluate(() => document.body.innerText || document.textContent || '');
-            break;
-          case 'markdown':
-            const html = await page.content();
-            const cleanedHtml = cleanHtml(html);
-            const turndownService = new TurndownService({ headingStyle: 'atx' });
-            result.content.markdown = turndownService.turndown(cleanedHtml);
-            break;
-        }
-      }
-      if (!Object.keys(result.content).length)
-        result.error = '[Puppeteer] Empty content';
+      result.content = await page.evaluate(() => {
+        const content = document.body.innerText || document.textContent;
+        if (!content)
+          throw new Error('No content');
+        return content;
+      });
    }
  } catch (error: any) {
-    result.error = '[Puppeteer] ' + (error?.message || error?.toString() || 'Unknown content error');
+    result.error = '[Puppeteer] ' + error?.message || error?.toString() || 'Unknown evaluate error';
  }

  // get a screenshot of the page
  try {
-    if (screenshotOptions?.width && screenshotOptions?.height) {
-      const { width, height, quality } = screenshotOptions;
-      const scale = Math.round(100 * width / 1024) / 100;
+    if (ssWidth && ssHeight) {
+      const width = ssWidth;
+      const height = ssHeight;
+      const scale = Math.round(100 * ssWidth / 1024) / 100;

      await page.setViewport({ width: width / scale, height: height / scale, deviceScaleFactor: scale });

@@ -183,10 +156,10 @@ async function workerPuppeteer(
        type: imageType,
        encoding: 'base64',
        clip: { x: 0, y: 0, width: width / scale, height: height / scale },
-        ...(quality && { quality }),
+        ...(ssQuality && { quality: ssQuality }),
      }) as string;

-      result.screenshot = { webpDataUrl: `data:${mimeType};base64,${dataString}`, mimeType, width, height };
+      result.screenshot = { imageDataUrl: `data:${mimeType};base64,${dataString}`, mimeType, width, height };
    }
  } catch (error: any) {
    console.error('workerPuppeteer: page.screenshot', error);
@@ -219,35 +192,3 @@ async function workerPuppeteer(

  return result;
 }
-
-
-function cleanHtml(html: string) {
-  const $ = cheerioLoad(html);
-
-  // Remove standard unwanted elements
-  $('script, style, nav, aside, noscript, iframe, svg, canvas, .ads, .comments, link[rel="stylesheet"]').remove();
-
-  // Remove elements that might be specific to proxy services or injected by them
-  $('[id^="brightdata-"], [class^="brightdata-"]').remove();
-
-  // Remove comments
-  $('*').contents().filter(function() {
-    return this.type === 'comment';
-  }).remove();
-
-  // Remove empty elements
-  $('p, div, span').each(function() {
-    if ($(this).text().trim() === '' && $(this).children().length === 0) {
-      $(this).remove();
-    }
-  });
-
-  // Merge consecutive paragraphs
-  $('p + p').each(function() {
-    $(this).prev().append(' ' + $(this).text());
-    $(this).remove();
-  });
-
-  // Return the cleaned HTML
-  return $.html();
-}
@@ -5,16 +5,11 @@ import { CapabilityBrowsing } from '~/common/components/useCapabilities';
 import { getBackendCapabilities } from '~/modules/backend/store-backend-capabilities';


-export type BrowsePageTransform = 'html' | 'text' | 'markdown';
-
 interface BrowseState {

  wssEndpoint: string;
  setWssEndpoint: (url: string) => void;

-  pageTransform: BrowsePageTransform;
-  setPageTransform: (transform: BrowsePageTransform) => void;
-
  enableCommandBrowse: boolean;
  setEnableCommandBrowse: (value: boolean) => void;

@@ -36,9 +31,6 @@ export const useBrowseStore = create<BrowseState>()(
      wssEndpoint: '', // default WSS endpoint
      setWssEndpoint: (wssEndpoint: string) => set(() => ({ wssEndpoint })),

-      pageTransform: 'text',
-      setPageTransform: (pageTransform: BrowsePageTransform) => set(() => ({ pageTransform })),
-
      enableCommandBrowse: true,
      setEnableCommandBrowse: (enableCommandBrowse: boolean) => set(() => ({ enableCommandBrowse })),

@@ -2,7 +2,6 @@ import * as React from 'react';

 import { FormControl } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormLabelStart } from '~/common/components/forms/FormLabelStart';
 import { useCapabilityElevenLabs } from '~/common/components/useCapabilities';
@@ -32,7 +31,7 @@ export function ElevenlabsSettings() {

    {!isConfiguredServerSide && <FormInputKey
      autoCompleteId='elevenlabs-key' label='ElevenLabs API Key'
-      rightLabel={<AlreadySet required={!isConfiguredServerSide} />}
+      rightLabel={isConfiguredServerSide ? '✔️ already set in server' : 'required'}
      value={apiKey} onChange={setApiKey}
      required={!isConfiguredServerSide} isError={!isValidKey}
    />}
@@ -2,10 +2,10 @@ import { sendGAEvent } from '@next/third-parties/google';

 import { hasGoogleAnalytics } from '~/common/components/GoogleAnalytics';

-import type { GenerateContextNameSchema, ModelDescriptionSchema, StreamingContextNameSchema } from './server/llm.server.types';
+import type { ModelDescriptionSchema } from './server/llm.server.types';
 import type { OpenAIWire } from './server/openai/openai.wiretypes';
 import type { StreamingClientUpdate } from './vendors/unifiedStreamingClient';
-import { DLLM, DLLMId, DModelSource, DModelSourceId, LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, useModelsStore } from './store-llms';
+import { DLLM, DLLMId, DModelSource, DModelSourceId, LLM_IF_OAI_Chat, useModelsStore } from './store-llms';
 import { FALLBACK_LLM_TEMPERATURE } from './vendors/openai/openai.vendor';
 import { findAccessForSourceOrThrow, findVendorForLlmOrThrow } from './vendors/vendors.registry';

@@ -21,10 +21,6 @@ export interface VChatMessageIn {

 export type VChatFunctionIn = OpenAIWire.ChatCompletion.RequestFunctionDef;

-export type VChatStreamContextName = StreamingContextNameSchema;
-export type VChatGenerateContextName = GenerateContextNameSchema;
-export type VChatContextRef = string;
-
 export interface VChatMessageOut {
  role: 'assistant' | 'system' | 'user';
  content: string;
@@ -73,7 +69,7 @@ function modelDescriptionToDLLMOpenAIOptions<TSourceSetup, TLLMOptions>(model: M
  // null means unknown contenxt/output tokens
  const contextTokens = model.contextWindow || null;
  const maxOutputTokens = model.maxCompletionTokens || (contextTokens ? Math.round(contextTokens / 2) : null);
-  const llmResponseTokensRatio = model.maxCompletionTokens ? 1 : 1 / 4;
+  const llmResponseTokensRatio = model.maxCompletionTokens ? 1 / 2 : 1 / 4;
  const llmResponseTokens = maxOutputTokens ? Math.round(maxOutputTokens * llmResponseTokensRatio) : null;

  return {
@@ -116,20 +112,13 @@ function modelDescriptionToDLLMOpenAIOptions<TSourceSetup, TLLMOptions>(model: M
 export async function llmChatGenerateOrThrow<TSourceSetup = unknown, TAccess = unknown, TLLMOptions = unknown>(
  llmId: DLLMId,
  messages: VChatMessageIn[],
-  contextName: VChatGenerateContextName,
-  contextRef: VChatContextRef | null,
-  functions: VChatFunctionIn[] | null,
-  forceFunctionName: string | null,
+  functions: VChatFunctionIn[] | null, forceFunctionName: string | null,
  maxTokens?: number,
 ): Promise<VChatMessageOut | VChatMessageOrFunctionCallOut> {

  // id to DLLM and vendor
  const { llm, vendor } = findVendorForLlmOrThrow<TSourceSetup, TAccess, TLLMOptions>(llmId);

-  // if the model does not support function calling and we're trying to force a function, throw
-  if (forceFunctionName && !llm.interfaces.includes(LLM_IF_OAI_Fn))
-    throw new Error(`Model ${llmId} does not support function calling`);
-
  // FIXME: relax the forced cast
  const options = llm.options as TLLMOptions;

@@ -143,15 +132,13 @@ export async function llmChatGenerateOrThrow<TSourceSetup = unknown, TAccess = u
    await new Promise(resolve => setTimeout(resolve, delay));

  // execute via the vendor
-  return await vendor.rpcChatGenerateOrThrow(access, options, messages, contextName, contextRef, functions, forceFunctionName, maxTokens);
+  return await vendor.rpcChatGenerateOrThrow(access, options, messages, functions, forceFunctionName, maxTokens);
 }


 export async function llmStreamingChatGenerate<TSourceSetup = unknown, TAccess = unknown, TLLMOptions = unknown>(
  llmId: DLLMId,
  messages: VChatMessageIn[],
-  contextName: VChatStreamContextName,
-  contextRef: VChatContextRef,
  functions: VChatFunctionIn[] | null,
  forceFunctionName: string | null,
  abortSignal: AbortSignal,
@@ -174,5 +161,5 @@ export async function llmStreamingChatGenerate<TSourceSetup = unknown, TAccess =
    await new Promise(resolve => setTimeout(resolve, delay));

  // execute via the vendor
-  return await vendor.streamingChatGenerateOrThrow(access, llmId, llmOptions, messages, contextName, contextRef, functions, forceFunctionName, abortSignal, onUpdate);
+  return await vendor.streamingChatGenerateOrThrow(access, llmId, llmOptions, messages, functions, forceFunctionName, abortSignal, onUpdate);
 }
@@ -1,5 +1,4 @@
 import * as React from 'react';
-import TimeAgo from 'react-timeago';
 import { shallow } from 'zustand/shallow';

 import { Box, Button, ButtonGroup, Divider, FormControl, Input, Switch, Tooltip, Typography } from '@mui/joy';
@@ -133,10 +132,10 @@ export function LLMOptionsModal(props: { id: DLLMId, onClose: () => void }) {
            llm id: {llm.id}<br />
            context tokens: <b>{llm.contextTokens ? llm.contextTokens.toLocaleString() : 'not provided'}</b>{` · `}
            max output tokens: <b>{llm.maxOutputTokens ? llm.maxOutputTokens.toLocaleString() : 'not provided'}</b><br />
-            {!!llm.created && <>created: <TimeAgo date={new Date(llm.created * 1000)} /><br /></>}
+            {!!llm.created && <>created: {(new Date(llm.created * 1000)).toLocaleString()}<br /></>}
            {/*· tags: {llm.tags.join(', ')}*/}
            {!!llm.pricing && <>pricing: $<b>{llm.pricing.chatIn || '(unk) '}</b>/M in, $<b>{llm.pricing.chatOut || '(unk) '}</b>/M out<br /></>}
-            {/*{!!llm.benchmark && <>benchmark: <b>{llm.benchmark.cbaElo?.toLocaleString() || '(unk) '}</b> CBA Elo<br /></>}*/}
+            {!!llm.benchmark && <>benchmark: <b>{llm.benchmark.cbaElo?.toLocaleString() || '(unk) '}</b> CBA Elo<br /></>}
            config: {JSON.stringify(llm.options)}
          </Typography>
        </Box>}
@@ -4,71 +4,14 @@ import { LLM_IF_OAI_Chat, LLM_IF_OAI_Vision } from '../../store-llms';

 const roundTime = (date: string) => Math.round(new Date(date).getTime() / 1000);

-export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: boolean })[] = [
-  // Claude 3.5 models - https://docs.anthropic.com/en/docs/about-claude/models
-  // {
-  //   id: 'claude-3.5-opus', // ...
-  //   label: 'Claude 3.5 Opus',
-  //   created: roundTime(?),
-  //   description: ?,
-  //   contextWindow: 200000 ?, // Characters
-  //   maxCompletionTokens: 4096 ?,
-  //   trainingDataCutoff: ?,
-  //   interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-  //   pricing: { chatIn: 15, chatOut: 75 },
-  //   benchmark: {
-  //     cbaElo: 1256, // Placeholder
-  //     cbaMmlu: 86.8, // Placeholder
-  //   },
-  // },
-  {
-    id: 'claude-3-5-sonnet-20241022',
-    label: 'Claude 3.5 Sonnet',
-    created: roundTime('2024-10-22 06:00'),
-    description: 'Most intelligent Claude model to date',
-    contextWindow: 200000, // Characters
-    maxCompletionTokens: 8192,
-    trainingDataCutoff: 'Apr 2024',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 3, chatOut: 15 },
-    benchmark: { cbaElo: 1269, cbaMmlu: 88.7 }, // moved from 3.5 Sonnet (Previous Version), TO UPDATE!!
-  },
-  {
-    id: 'claude-3-5-sonnet-20240620',
-    label: 'Claude 3.5 Sonnet (Previous)',
-    created: roundTime('2024-06-20 06:00'),
-    description: 'The most intelligent Claude model',
-    contextWindow: 200000, // Characters
-    maxCompletionTokens: 8192,
-    trainingDataCutoff: 'Apr 2024',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 3, chatOut: 15 },
-    benchmark: { cbaElo: 1269 - 0.1, cbaMmlu: 88.7 - 0.1 },
-    hidden: true,
-  },
-  // {
-  //   id: 'claude-3.5-haiku', // ...
-  //   label: 'Claude 3.5 Haiku',
-  //   created: roundTime(?),
-  //   description: ?,
-  //   contextWindow: 200000 ?, // Characters
-  //   maxCompletionTokens: 4096 ?,
-  //   trainingDataCutoff: ?,
-  //   interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-  //   pricing: { chatIn: 0.25, chatOut: 1.25 },
-  //   benchmark: {
-  //     cbaElo: 1181, // Placeholder
-  //     cbaMmlu: 75.2, // Placeholder
-  //   },
-  // },
+export const hardcodedAnthropicModels: ModelDescriptionSchema[] = [

-
-  // Claude 3 models
+  // Claude-3 models - https://docs.anthropic.com/claude/docs/models-overview#model-comparison
  {
    id: 'claude-3-opus-20240229',
    label: 'Claude 3 Opus',
    created: roundTime('2024-02-29'),
-    description: 'Powerful model for complex tasks',
+    description: 'Most powerful model for highly complex tasks',
    contextWindow: 200000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Aug 2023',
@@ -80,21 +23,19 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
    id: 'claude-3-sonnet-20240229',
    label: 'Claude 3 Sonnet',
    created: roundTime('2024-02-29'),
-    description: 'Balance of speed, cost, and performance',
+    description: 'Ideal balance of intelligence and speed for enterprise workloads',
    contextWindow: 200000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Aug 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
    pricing: { chatIn: 3, chatOut: 15 },
    benchmark: { cbaElo: 1203, cbaMmlu: 79 },
-    hidden: true,
-    isLegacy: true,
  },
  {
    id: 'claude-3-haiku-20240307',
    label: 'Claude 3 Haiku',
    created: roundTime('2024-03-07'),
-    description: 'Fastest, most cost-effective model',
+    description: 'Fastest and most compact model for near-instant responsiveness',
    contextWindow: 200000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Aug 2023',
@@ -114,7 +55,6 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
    interfaces: [LLM_IF_OAI_Chat],
    pricing: { chatIn: 8, chatOut: 24 },
    benchmark: { cbaElo: 1119 },
-    hidden: true,
  },
  {
    id: 'claude-2.0',
@@ -137,6 +77,25 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
    maxCompletionTokens: 4096,
    interfaces: [LLM_IF_OAI_Chat],
    pricing: { chatIn: 0.8, chatOut: 2.4 },
+  },
+  {
+    id: 'claude-instant-1.1',
+    label: 'Claude Instant 1.1',
+    created: roundTime('2023-03-14'),
+    description: 'Precise and fast',
+    contextWindow: 100000,
+    maxCompletionTokens: 2048,
+    interfaces: [LLM_IF_OAI_Chat],
+    hidden: true,
+  },
+  {
+    id: 'claude-1.3',
+    label: 'Claude 1.3',
+    created: roundTime('2023-03-14'),
+    description: 'Claude 1.3 is the latest version of Claude v1',
+    contextWindow: 100000,
+    maxCompletionTokens: 4096,
+    interfaces: [LLM_IF_OAI_Chat],
    hidden: true,
  },
 ];
@@ -8,7 +8,7 @@ import { fetchJsonOrTRPCError } from '~/server/api/trpc.router.fetchers';
 import { fixupHost } from '~/common/util/urlUtils';

 import { OpenAIHistorySchema, openAIHistorySchema, OpenAIModelSchema, openAIModelSchema } from '../openai/openai.router';
-import { llmsChatGenerateOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema } from '../llm.server.types';
+import { llmsChatGenerateOutputSchema, llmsListModelsOutputSchema } from '../llm.server.types';

 import { AnthropicWireMessagesRequest, anthropicWireMessagesRequestSchema, AnthropicWireMessagesResponse, anthropicWireMessagesResponseSchema } from './anthropic.wiretypes';
 import { hardcodedAnthropicModels } from './anthropic.models';
@@ -17,9 +17,7 @@ import { hardcodedAnthropicModels } from './anthropic.models';
 // Default hosts
 const DEFAULT_API_VERSION_HEADERS = {
  'anthropic-version': '2023-06-01',
-  // Former Betas:
-  // - messages-2023-12-15: to use the Messages API
-  'anthropic-beta': 'max-tokens-3-5-sonnet-2024-07-15',
+  'anthropic-beta': 'messages-2023-12-15',
 };
 const DEFAULT_MAX_TOKENS = 2048;
 const DEFAULT_ANTHROPIC_HOST = 'api.anthropic.com';
@@ -160,11 +158,7 @@ const listModelsInputSchema = z.object({

 const chatGenerateInputSchema = z.object({
  access: anthropicAccessSchema,
-  model: openAIModelSchema,
-  history: openAIHistorySchema,
-  // functions: openAIFunctionsSchema.optional(),
-  // forceFunctionName: z.string().optional(),
-  context: llmsGenerateContextSchema.optional(),
+  model: openAIModelSchema, history: openAIHistorySchema,
 });


@@ -1,442 +1,42 @@
 import type { GeminiModelSchema } from './gemini.wiretypes';
 import type { ModelDescriptionSchema } from '../llm.server.types';
-import { LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json, LLM_IF_OAI_Vision } from '../../store-llms';
+import { LLM_IF_OAI_Chat, LLM_IF_OAI_Vision } from '../../store-llms';


-// dev options
-const DEV_DEBUG_GEMINI_MODELS = false;
-
-
-// supported interfaces
-const geminiChatInterfaces: GeminiModelSchema['supportedGenerationMethods'] = ['generateContent'];
-
-// unsupported interfaces
 const filterUnallowedNames = ['Legacy'];
-const filterUnallowedInterfaces: GeminiModelSchema['supportedGenerationMethods'] = [
-  'generateAnswer',   // e.g. removes "models/aqa"
-  'embedContent',     // e.g. removes "models/embedding-001"
-  'embedText',        // e.g. removes "models/text-embedding-004"
-  'predict',          // e.g. removes "models/imagen-3.0-generate-002" (appeared on 2025-02-09)
-];
-const filterLyingModelNames: GeminiModelSchema['name'][] = [
-  // 2025-02-27: verified, old model is no more
-  'models/gemini-2.0-flash-exp', // verified, replaced by gemini-2.0-flash, which is non-free anymore
+const filterUnallowedInterfaces: GeminiModelSchema['supportedGenerationMethods'] = ['generateAnswer', 'embedContent', 'embedText'];

-  // 2025-02-09 update: as of now they cleared the list, so we restart
-  // 2024-12-10: name of models that are not what they say they are (e.g. 1114 is actually 1121 as of )
-  'models/gemini-1.5-flash-8b-exp-0924', // replaced by non-free
-  'models/gemini-1.5-flash-8b-exp-0827', // replaced by non-free
-];
+const geminiLinkModels = ['models/gemini-pro', 'models/gemini-pro-vision'];

-
-/* Manual models details
-   Gemini Name Mapping example:
-   - Latest version    gemini-1.0-pro-latest    <model>-<generation>-<variation>-latest
-   - Latest stable     version  gemini-1.0-pro  <model>-<generation>-<variation>
-   - Stable versions   gemini-1.0-pro-001       <model>-<generation>-<variation>-<version>
-
-   Gemini capabilities chart (updated 2024-10-01):
-   - [table stakes] System instructions
-   - JSON Mode, with optional JSON Schema [NOTE: JSON Schema is poorly supported?]
-   - Adjustable Safety Settings
-   - Caching
-   - Tuning
-   - [good] Function calling, with configuration
-   - [great] Code execution
-*/
-
-// Experimental Gemini models are Free of charge
-const geminiExpPricingFree: ModelDescriptionSchema['pricing'] = {
-  // input: 'free', output: 'free',
-};
-
-const gemini20FlashPricing: ModelDescriptionSchema['pricing'] = {
-  chatIn: 0.10, // inputAudio: 0.70,
-  chatOut: 0.40,
-};
-
-const gemini20FlashLitePricing: ModelDescriptionSchema['pricing'] = {
-  chatIn: 0.075,
-  chatOut: 0.30,
-};
-
-const gemini15FlashPricing: ModelDescriptionSchema['pricing'] = {
-  chatIn: 0.075,
-  chatOut: 0.30,
-};
-
-const gemini15Flash8BPricing: ModelDescriptionSchema['pricing'] = {
-  chatIn: 0.0375,
-  chatOut: 0.15,
-};
-
-const gemini15ProPricing: ModelDescriptionSchema['pricing'] = {
-  chatIn: 1.25,
-  chatOut: 5.00,
-};
-
-
-const _knownGeminiModels: ({
-  id: string,
-  labelOverride?: string,
-  isNewest?: boolean,
-  isPreview?: boolean,
-  symLink?: string,
-  deprecated?: string, // Gemini may provide deprecation dates
-  _delete?: boolean, // some gemini models are not acknowledged by Google Docs anymore, and leaving them in the list will confuse users
-} & Pick<ModelDescriptionSchema, 'interfaces' | 'pricing' | 'hidden' | 'benchmark'>)[] = [
-
-  /// Generation 2.5
-
-  // 2.5 Pro Experimental
-  {
-    id: 'models/gemini-2.5-pro-exp-03-25',
-    isPreview: true,
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1443 },
-  },
-
-  /// Generation 2.0
-
-  // 2.0 Experimental - Pro
-  {
-    hidden: true, // showing the 2.5 instead
-    id: 'models/gemini-2.0-pro-exp-02-05', // Base model: Gemini 2.0 Pro
-    isPreview: true,
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1380 },
-  },
-  {
-    hidden: true, // only keeping the latest
-    id: 'models/gemini-2.0-pro-exp',
-    symLink: 'models/gemini-2.0-pro-exp-02-05',
-    // copied from symlink
-    isPreview: true,
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1380 },
-  },
-  {
-    _delete: true, // replaced by gemini-2.0-pro-exp-02-05, 2025-02-27: verified, old model is no more
-    id: 'models/gemini-exp-1206',
-    labelOverride: 'Gemini 2.0 Pro Experimental 1206',
-    isPreview: true,
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1373 },
-  },
-
-  // 2.0 Experimental - Flash Thinking
-  {
-    hidden: true, // only keeping the latest
-    id: 'models/gemini-2.0-flash-thinking-exp', // alias to the latest Flash Thinking model
-    labelOverride: 'Gemini 2.0 Flash Thinking Experimental',
-    symLink: 'models/gemini-2.0-flash-thinking-exp-01-21',
-    // copied from symlink
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    benchmark: { cbaElo: 1385 },
-    isPreview: true,
-  },
-  {
-    id: 'models/gemini-2.0-flash-thinking-exp-01-21',
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    benchmark: { cbaElo: 1385 },
-    isPreview: true,
-  },
-  {
-    hidden: true, // replaced by gemini-2.0-flash-thinking-exp-01-21 - 2025-02-27: seems still different on the API, hence no deletion yet
-    id: 'models/gemini-2.0-flash-thinking-exp-1219',
-    labelOverride: 'Gemini 2.0 Flash Thinking Experimental 12-19',
-    pricing: geminiExpPricingFree,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    benchmark: { cbaElo: 1363 },
-    isPreview: true,
-  },
-
-  // 2.0 Experimental - Flash Image Generation
-  {
-    id: 'models/gemini-2.0-flash-exp-image-generation',
-    // labelOverride: 'Gemini 2.0 Flash Native Image Generation',
-    pricing: geminiExpPricingFree,
-    interfaces: [
-      LLM_IF_OAI_Chat, LLM_IF_OAI_Vision,
-      // LLM_IF_HOTFIX_StripSys0, // This first Gemini Image Generation model does not support the developer instruction
-    ],
-    isPreview: true,
-  },
-
-  // 2.0 Flash
-  {
-    id: 'models/gemini-2.0-flash-001',
-    pricing: gemini20FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1358 },
-  },
-  {
-    id: 'models/gemini-2.0-flash',
-    symLink: 'models/gemini-2.0-flash-001',
-    // copied from symlink
-    pricing: gemini20FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1358 },
-  },
-
-  // 2.0 Flash Lite
-  {
-    id: 'models/gemini-2.0-flash-lite',
-    pricing: gemini20FlashLitePricing,
-    symLink: 'models/gemini-2.0-flash-lite-001',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1309 },
-  },
-  {
-    id: 'models/gemini-2.0-flash-lite-001',
-    pricing: gemini20FlashLitePricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1309 },
-  },
-  {
-    hidden: true, // discouraged, as the official is out
-    id: 'models/gemini-2.0-flash-lite-preview-02-05',
-    isPreview: true,
-    pricing: gemini20FlashLitePricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1309 },
-  },
-  {
-    id: 'models/gemini-2.0-flash-lite-preview',
-    symLink: 'models/gemini-2.0-flash-lite-preview-02-05',
-    // coped from symlink
-    isPreview: true,
-    pricing: gemini20FlashLitePricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1309 },
-  },
-
-
-  /// Generation 1.5
-
-  // Gemini 1.5 Flash Models
-  {
-    id: 'models/gemini-1.5-flash-latest', // updated regularly and might be a preview version
-    isPreview: true,
-    pricing: gemini15FlashPricing,
-    // symLink: '-002 or newer',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-  },
-  {
-    id: 'models/gemini-1.5-flash',
-    // Defaults to version 002 on Oct 8, 2024
-    symLink: 'models/gemini-1.5-flash-002',
-    pricing: gemini15FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1271 },
-  },
-  {
-    id: 'models/gemini-1.5-flash-002', // new stable version
-    pricing: gemini15FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1271 },
-    hidden: true,
-  },
-  {
-    id: 'models/gemini-1.5-flash-001', // previous stable version
-    pricing: gemini15FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1227 },
-    hidden: true,
-  },
-  {
-    id: 'models/gemini-1.5-flash-001-tuning', // supports model tuning
-    pricing: gemini15FlashPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn /* Tuning ... */],
-    hidden: true,
-  },
-
-  // Gemini 1.5 Flash-8B Models
-  {
-    id: 'models/gemini-1.5-flash-8b-latest',
-    isPreview: false,
-    pricing: gemini15Flash8BPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-  },
-  {
-    id: 'models/gemini-1.5-flash-8b',
-    symLink: 'models/gemini-1.5-flash-8b-001',
-    pricing: gemini15Flash8BPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1213 },
-  },
-  {
-    id: 'models/gemini-1.5-flash-8b-001',
-    pricing: gemini15Flash8BPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1213 },
-    hidden: true,
-  },
-
-  // Gemini 1.5 Pro Models
-  {
-    id: 'models/gemini-1.5-pro-latest', // updated to latest stable version
-    pricing: gemini15ProPricing,
-    // symLink: '-002 or newer',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-  },
-  {
-    id: 'models/gemini-1.5-pro',
-    symLink: 'models/gemini-1.5-pro-002',
-    pricing: gemini15ProPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1302 },
-  },
-  {
-    id: 'models/gemini-1.5-pro-002',
-    pricing: gemini15ProPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1302 },
-    hidden: true,
-  },
-  {
-    id: 'models/gemini-1.5-pro-001',
-    pricing: gemini15ProPricing,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
-    benchmark: { cbaElo: 1260 },
-    hidden: true,
-  },
-
-
-  /// Generation 1.0
-
-  // Gemini 1.0 Pro Vision Model
-  {
-    id: 'models/gemini-1.0-pro-vision-latest',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    hidden: true,
-    _delete: true, // confusing
-  },
-  {
-    id: 'models/gemini-pro-vision',
-    symLink: 'models/gemini-1.0-pro-vision',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision], // Text and Images
-    _delete: true, // confusing
-  },
-
-
-  /// Experimental
-
-  // LearnLM Experimental Model
-  {
-    id: 'models/learnlm-1.5-pro-experimental',
-    isPreview: true,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: geminiExpPricingFree,
-    // hidden: true,
-    // _delete: true,
-  },
-
-  {
-    id: 'models/gemma-3-27b-it',
-    isPreview: true,
-    interfaces: [
-      LLM_IF_OAI_Chat,
-      // LLM_IF_HOTFIX_StripImages, /* "Image input modality is not enabled for models/gemma-3-27b-it" */
-      // LLM_IF_HOTFIX_Sys0ToUsr0, /* "Developer instruction is not enabled for models/gemma-3-27b-it" */
-    ],
-    // pricing: geminiExpPricingFree,
-    // hidden: true,
-    // _delete: true,
-  },
-
-];
+// interfaces mapping
+const geminiChatInterfaces: GeminiModelSchema['supportedGenerationMethods'] = ['generateContent'];
+const geminiVisionNames = ['-vision'];


 export function geminiFilterModels(geminiModel: GeminiModelSchema): boolean {
  const isAllowed = !filterUnallowedNames.some(name => geminiModel.displayName.includes(name));
  const isSupported = !filterUnallowedInterfaces.some(iface => geminiModel.supportedGenerationMethods.includes(iface));
-  const isWhatItSaysItIs = !filterLyingModelNames.includes(geminiModel.name);
-  return isAllowed && isSupported && isWhatItSaysItIs;
+  return isAllowed && isSupported;
 }

-
-const _sortOderIdPrefix: string[] = [
-  'models/gemini-exp',
-  'models/gemini-2.5-pro',
-  'models/gemini-2.0-pro',
-  'models/gemini-2.0-flash-exp-image-generation',
-  'models/gemini-2.0-flash-thinking',
-  'models/gemini-2.0-flash-0',
-  'models/gemini-2.0-flash',
-  'models/gemini-2.0-flash-lite',
-  'models/gemini-1.5-pro',
-  'models/gemini-1.5-flash',
-  'models/gemini-1.5-flash-8b',
-  'models/gemini-1.0-pro',
-  'models/gemini-pro',
-  'models/gemma',
-  'models/learnlm',
-] as const;
-
 export function geminiSortModels(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
-  // links to the bottom
-  const aIsLink = a.label.startsWith('🔗');
-  const bIsLink = b.label.startsWith('🔗');
-  if (aIsLink && !bIsLink) return 1;
-  if (!aIsLink && bIsLink) return -1;
-
  // hidden to the bottom, then names descending
-  // if (a.hidden && !b.hidden) return 1;
-  // if (!a.hidden && b.hidden) return -1;
-
-  // models beginning with 'gemini-' to the top
-  // const aGemini = a.label.startsWith('Gemini');
-  // const bGemini = b.label.startsWith('Gemini');
-  // if (aGemini && !bGemini) return -1;
-  // if (!aGemini && bGemini) return 1;
-
-  // sort by sortOrderIdPrefix
-  const aSortIdx = _sortOderIdPrefix.findIndex(p => a.id.startsWith(p));
-  const bSortIdx = _sortOderIdPrefix.findIndex(p => b.id.startsWith(p));
-  if (aSortIdx !== -1 && bSortIdx !== -1) {
-    if (aSortIdx < bSortIdx) return -1;
-    if (aSortIdx > bSortIdx) return 1;
-  }
-
-  // sort by label descending
+  if (a.hidden && !b.hidden) return 1;
+  if (!a.hidden && b.hidden) return -1;
  return b.label.localeCompare(a.label);
 }

-
-export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): ModelDescriptionSchema | null {
+export function geminiModelToModelDescription(geminiModel: GeminiModelSchema, allModels: GeminiModelSchema[]): ModelDescriptionSchema {
  const { description, displayName, name: modelId, supportedGenerationMethods } = geminiModel;

-  // if (DEV_DEBUG_GEMINI_MODELS)
-  //   console.log('geminiModelToModelDescription', geminiModel);
-
-  // find known manual mapping
-  const knownModel = _knownGeminiModels.find(m => m.id === modelId);
-  if (!knownModel && DEV_DEBUG_GEMINI_MODELS)
-    console.warn('geminiModelToModelDescription: unknown model', modelId, geminiModel);
-
-  // handle _delete
-  if (knownModel?._delete)
-    return null;
-
  // handle symlinks
-  let label = knownModel?.symLink
-    ? `🔗 ${knownModel?.labelOverride || displayName} → ${knownModel.symLink}`
-    : knownModel?.labelOverride || displayName;
-
-  // FIX: the Gemini 1114 model now returns 1121 as the version.. highlight the issue
-  // if (geminiModel.name.endsWith('1114') && label.endsWith('1121'))
-  //   label += ' (really: 1114)';
+  const isSymlink = geminiLinkModels.includes(modelId);
+  const symlinked = isSymlink ? allModels.find(m => m.displayName === displayName && m.name !== modelId) : null;
+  const label = isSymlink ? `🔗 ${displayName.replace('1.0', '')} → ${symlinked ? symlinked.name : '?'}` : displayName;

  // handle hidden models
  const hasChatInterfaces = supportedGenerationMethods.some(iface => geminiChatInterfaces.includes(iface));
-  const hidden = knownModel?.hidden || !!knownModel?.symLink || !hasChatInterfaces;
+  const hidden = isSymlink || !hasChatInterfaces;

  // context window
  const { inputTokenLimit, outputTokenLimit } = geminiModel;
@@ -444,30 +44,28 @@ export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): M

  // description
  const { version, topK, topP, temperature } = geminiModel;
-  const descriptionLong = (description || 'No description.') + ` (Version: ${version}, Defaults: temperature=${temperature}, topP=${topP}, topK=${topK}, interfaces=[${supportedGenerationMethods.join(',')}])`;
+  const descriptionLong = description + ` (Version: ${version}, Defaults: temperature=${temperature}, topP=${topP}, topK=${topK}, interfaces=[${supportedGenerationMethods.join(',')}])`;

-  // use known interfaces, or add chat if this is a generateContent model
-  const interfaces: ModelDescriptionSchema['interfaces'] = knownModel?.interfaces || [];
-  if (!interfaces.length && hasChatInterfaces) {
-    // newer models get good capabilities by default
-    interfaces.push(LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Vision, LLM_IF_OAI_Json);
+  const interfaces: ModelDescriptionSchema['interfaces'] = [];
+  if (hasChatInterfaces) {
+    interfaces.push(LLM_IF_OAI_Chat);
+    if (geminiVisionNames.some(name => modelId.includes(name)))
+      interfaces.push(LLM_IF_OAI_Vision);
  }

  return {
    id: modelId,
-    label: label, // + (knownModel?.isNewest ? ' 🌟' : ''),
+    label,
    // created: ...
    // updated: ...
    description: descriptionLong,
    contextWindow: contextWindow,
    maxCompletionTokens: outputTokenLimit,
-    // trainingDataCutoff: knownModel?.trainingDataCutoff, // disabled as we don't get this from Gemini
+    // trainingDataCutoff: '...',
    interfaces,
-    // parameterSpecs: knownModel?.parameterSpecs,
    // rateLimits: isGeminiPro ? { reqPerMinute: 60 } : undefined,
-    benchmark: knownModel?.benchmark,
-    pricing: knownModel?.pricing,
+    // benchmarks: ...
+    // pricing: isGeminiPro ? { needs per-character and per-image pricing } : undefined,
    hidden,
-    // deprecated: knownModel?.deprecated,
  };
 }
@@ -8,7 +8,7 @@ import { createTRPCRouter, publicProcedure } from '~/server/api/trpc.server';
 import { fetchJsonOrTRPCError } from '~/server/api/trpc.router.fetchers';

 import { fixupHost } from '~/common/util/urlUtils';
-import { llmsChatGenerateOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema, type ModelDescriptionSchema } from '../llm.server.types';
+import { llmsChatGenerateOutputSchema, llmsListModelsOutputSchema } from '../llm.server.types';

 import { OpenAIHistorySchema, openAIHistorySchema, OpenAIModelSchema, openAIModelSchema } from '../openai/openai.router';

@@ -120,11 +120,8 @@ const accessOnlySchema = z.object({

 const chatGenerateInputSchema = z.object({
  access: geminiAccessSchema,
-  model: openAIModelSchema,
-  history: openAIHistorySchema,
-  // functions: openAIFunctionsSchema.optional(),
-  // forceFunctionName: z.string().optional(),
-  context: llmsGenerateContextSchema.optional(),
+  model: openAIModelSchema, history: openAIHistorySchema,
+  // functions: openAIFunctionsSchema.optional(), forceFunctionName: z.string().optional(),
 });


@@ -148,10 +145,9 @@ export const llmGeminiRouter = createTRPCRouter({
      //       as the List API already all the info on all the models

      // map to our output schema
-      const models = (detailedModels
+      const models = detailedModels
        .filter(geminiFilterModels)
-        .map(geminiModel => geminiModelToModelDescription(geminiModel))
-        .filter(model => !!model) as ModelDescriptionSchema[])
+        .map(geminiModel => geminiModelToModelDescription(geminiModel, detailedModels))
        .sort(geminiSortModels);

      return {
@@ -9,30 +9,27 @@ export const geminiModelsStreamGenerateContentPath = '/v1beta/{model=models/*}:s


 // models.list = /v1beta/models
-const Methods_enum = z.enum([
-  'bidiGenerateContent', // appeared on 2024-12, see https://github.com/enricoros/big-AGI/issues/700
-  'createCachedContent', // appeared on 2024-06-10, see https://github.com/enricoros/big-AGI/issues/565
-  'countMessageTokens',
-  'countTextTokens',
-  'countTokens',
-  'createTunedModel',
-  'createTunedTextModel',
-  'embedContent',
-  'embedText',
-  'generateAnswer',
-  'generateContent',
-  'generateMessage',
-  'generateText',
-]);

 const geminiModelSchema = z.object({
  name: z.string(),
  version: z.string(),
  displayName: z.string(),
-  description: z.string().optional(),
+  description: z.string(),
  inputTokenLimit: z.number().int().min(1),
  outputTokenLimit: z.number().int().min(1),
-  supportedGenerationMethods: z.array(z.union([Methods_enum, z.string()])), // relaxed with z.union to not break on expansion
+  supportedGenerationMethods: z.array(z.enum([
+    'countMessageTokens',
+    'countTextTokens',
+    'countTokens',
+    'createTunedModel',
+    'createTunedTextModel',
+    'embedContent',
+    'embedText',
+    'generateAnswer',
+    'generateContent',
+    'generateMessage',
+    'generateText',
+  ])),
  temperature: z.number().optional(),
  topP: z.number().optional(),
  topK: z.number().optional(),
@@ -174,7 +171,7 @@ export const geminiGeneratedContentResponseSchema = z.object({
  // either all requested candidates are returned or no candidates at all
  // no candidates are returned only if there was something wrong with the prompt (see promptFeedback)
  candidates: z.array(z.object({
-    index: z.number().optional(),
+    index: z.number(),
    content: geminiContentSchema.optional(), // this can be missing if the finishReason is not 'MAX_TOKENS'
    finishReason: geminiFinishReasonSchema.optional(),
    safetyRatings: z.array(geminiSafetyRatingSchema).optional(), // undefined when finishReason is 'RECITATION'
@@ -19,10 +19,7 @@ import { OLLAMA_PATH_CHAT, ollamaAccess, ollamaAccessSchema, ollamaChatCompletio

 // OpenAI server imports
 import type { OpenAIWire } from './openai/openai.wiretypes';
-import { openAIAccess, openAIAccessSchema, openAIChatCompletionPayload, openAIHistorySchema, openAIModelSchema } from './openai/openai.router';
-
-
-import { llmsStreamingContextSchema } from './llm.server.types';
+import { openAIAccess, openAIAccessSchema, openAIChatCompletionPayload, OpenAIHistorySchema, openAIHistorySchema, OpenAIModelSchema, openAIModelSchema } from './openai/openai.router';


 // configuration
@@ -54,9 +51,6 @@ const chatStreamingInputSchema = z.object({
  access: z.union([anthropicAccessSchema, geminiAccessSchema, ollamaAccessSchema, openAIAccessSchema]),
  model: openAIModelSchema,
  history: openAIHistorySchema,
-  // NOTE: made it optional for now as we have some old requests without it
-  // 2024-07-07: remove .optional()
-  context: llmsStreamingContextSchema.optional(),
 });
 export type ChatStreamingInputSchema = z.infer<typeof chatStreamingInputSchema>;

@@ -78,15 +72,14 @@ export async function llmStreamingRelayHandler(req: NextRequest): Promise<Respon

  // Parse the request
  const body = await req.json();
-  const _chatStreamingInput: ChatStreamingInputSchema = chatStreamingInputSchema.parse(body);
-  const { dialect: accessDialect } = _chatStreamingInput.access;
-  const prettyDialect = serverCapitalizeFirstLetter(accessDialect);
+  const { access, model, history } = chatStreamingInputSchema.parse(body);
+  const prettyDialect = serverCapitalizeFirstLetter(access.dialect);


  // Prepare the upstream API request and demuxer/parser
  let requestData: ReturnType<typeof _prepareRequestData>;
  try {
-    requestData = _prepareRequestData(_chatStreamingInput);
+    requestData = _prepareRequestData(access, model, history);
  } catch (error: any) {
    console.error(`[POST] /api/llms/stream: ${prettyDialect}: prepareRequestData issue:`, safeErrorString(error));
    return new NextResponse(`**[Service Issue] ${prettyDialect}**: ${safeErrorString(error) || 'Unknown streaming error'}`, {
@@ -110,7 +103,7 @@ export async function llmStreamingRelayHandler(req: NextRequest): Promise<Respon
  } catch (error: any) {

    // server-side admins message
-    const capDialect = serverCapitalizeFirstLetter(accessDialect);
+    const capDialect = serverCapitalizeFirstLetter(access.dialect);
    const fetchOrVendorError = safeErrorString(error) + (error?.cause ? ' · ' + JSON.stringify(error.cause) : '');
    console.error(`[POST] /api/llms/stream: ${capDialect}: fetch issue:`, fetchOrVendorError, requestData?.url);

@@ -132,7 +125,7 @@ export async function llmStreamingRelayHandler(req: NextRequest): Promise<Respon
   * a 'healthy' level of inventory (i.e., pre-buffering) on the pipe to the client.
   */
  const transformUpstreamToBigAgiClient = createUpstreamTransformer(
-    requestData.vendorMuxingFormat, requestData.vendorStreamParser, accessDialect,
+    requestData.vendorMuxingFormat, requestData.vendorStreamParser, access.dialect,
  );

  const chatResponseStream =
@@ -493,7 +486,7 @@ function createStreamParserOpenAI(): AIStreamParser {
 }


-function _prepareRequestData({ access, model, history, context: _context }: ChatStreamingInputSchema): {
+function _prepareRequestData(access: ChatStreamingInputSchema['access'], model: OpenAIModelSchema, history: OpenAIHistorySchema): {
  headers: HeadersInit;
  url: string;
  body: object;
@@ -12,8 +12,6 @@ const pricingSchema = z.object({
 const benchmarkSchema = z.object({
  cbaElo: z.number().optional(),
  cbaMmlu: z.number().optional(),
-  heCode: z.number().optional(), // HumanEval, code, 0-shot
-  vqaMmmu: z.number().optional(), // Visual Question Answering, MMMU, 0-shot
 });

 // const rateLimitsSchema = z.object({
@@ -48,25 +46,6 @@ export const llmsListModelsOutputSchema = z.object({
 });


-// Chat Generation Input (some parts of)
-
-const generateContextNameSchema = z.enum(['chat-ai-title', 'chat-ai-summarize', 'chat-followup-diagram', 'chat-react-turn', 'draw-expand-prompt']);
-export type GenerateContextNameSchema = z.infer<typeof generateContextNameSchema>;
-export const llmsGenerateContextSchema = z.object({
-  method: z.literal('chat-generate'),
-  name: generateContextNameSchema,
-  ref: z.string(),
-});
-
-const streamingContextNameSchema = z.enum(['conversation', 'ai-diagram', 'ai-flattener', 'call', 'beam-scatter', 'beam-gather', 'persona-extract']);
-export type StreamingContextNameSchema = z.infer<typeof streamingContextNameSchema>;
-export const llmsStreamingContextSchema = z.object({
-  method: z.literal('chat-stream'),
-  name: streamingContextNameSchema,
-  ref: z.string(),
-});
-
-
 // (non-streaming) Chat Generation Output

 export const llmsChatGenerateOutputSchema = z.object({
@@ -11,7 +11,7 @@ import { capitalizeFirstLetter } from '~/common/util/textUtils';
 import { fixupHost } from '~/common/util/urlUtils';

 import { OpenAIHistorySchema, openAIHistorySchema, OpenAIModelSchema, openAIModelSchema } from '../openai/openai.router';
-import { llmsChatGenerateOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema, ModelDescriptionSchema } from '../llm.server.types';
+import { llmsChatGenerateOutputSchema, llmsListModelsOutputSchema, ModelDescriptionSchema } from '../llm.server.types';

 import { OLLAMA_BASE_MODELS, OLLAMA_PREV_UPDATE } from './ollama.models';
 import { WireOllamaChatCompletionInput, wireOllamaChunkedOutputSchema, wireOllamaListModelsSchema, wireOllamaModelInfoSchema } from './ollama.wiretypes';
@@ -117,11 +117,8 @@ const adminPullModelSchema = z.object({

 const chatGenerateInputSchema = z.object({
  access: ollamaAccessSchema,
-  model: openAIModelSchema,
-  history: openAIHistorySchema,
-  // functions: openAIFunctionsSchema.optional(),
-  // forceFunctionName: z.string().optional(),
-  context: llmsGenerateContextSchema.optional(),
+  model: openAIModelSchema, history: openAIHistorySchema,
+  // functions: openAIFunctionsSchema.optional(), forceFunctionName: z.string().optional(),
 });

 const listPullableOutputSchema = z.object({
@@ -1,84 +0,0 @@
-// here for reference only - for future mapping of CBA scores to the model IDs
-// const modelIdToPrefixMap: { [key: string]: string } = {
-//   // Anthropic models
-//   'Claude 3.5 Sonnet': 'claude-3-5-sonnet-20240620',
-//   'Claude 3 Opus': 'claude-3-opus-20240229',
-//   'Claude 3 Sonnet': 'claude-3-sonnet-20240229',
-//   'Claude 3 Haiku': 'claude-3-haiku-20240307',
-//   'Claude-2.1': 'claude-2.1',
-//   'Claude-2.0': 'claude-2.0',
-//   'Claude-1': '', // No exact match
-//   'Claude-Instant-1': 'claude-instant-1.2', // Closest match
-//
-//   // Gemini models
-//   'Gemini-1.5-Pro-Exp-0801': 'models/gemini-1.5-pro-latest', // Closest match
-//   'Gemini Advanced App (2024-05-14)': '', // No exact match
-//   'Gemini-1.5-Pro-001': 'models/gemini-1.5-pro-001',
-//   'Gemini-1.5-Pro-Preview-0409': 'models/gemini-1.5-pro-latest', // Closest match
-//   'Gemini-1.5-Flash-001': 'models/gemini-1.5-flash-001',
-//   'Gemini App (2024-01-24)': '', // No exact match
-//   'Gemini-1.0-Pro-001': 'models/gemini-1.0-pro-001',
-//   'Gemini Pro': 'models/gemini-pro',
-//
-//   // OpenAI models (from the previous file)
-//   'GPT-4o-2024-05-13': 'gpt-4o-2024-05-13',
-//   'GPT-4o-mini-2024-07-18': 'gpt-4o-mini-2024-07-18',
-//   'GPT-4-Turbo-2024-04-09': 'gpt-4-turbo-2024-04-09',
-//   'GPT-4-1106-preview': 'gpt-4-1106-preview',
-//   'GPT-4-0125-preview': 'gpt-4-0125-preview',
-//   'GPT-4-0314': 'gpt-4-0314',
-//   'GPT-4-0613': 'gpt-4-0613',
-//   'GPT-3.5-Turbo-0613': 'gpt-3.5-turbo-0613',
-//   'GPT-3.5-Turbo-0314': 'gpt-3.5-turbo-0314',
-//   'GPT-3.5-Turbo-0125': 'gpt-3.5-turbo-0125',
-//
-//   // Mistral models (from the previous file)
-//   'Mistral-Large-2402': 'mistral-large-2402',
-//   'Mixtral-8x7b-Instruct-v0.1': 'mistralai/Mixtral-8x7B-Instruct-v0.1',
-//
-//   // Other models without matches
-//   'Gemini-1.5-Pro-Exp-0801': '',
-//   'Meta-Llama-3.1-405b-Instruct': '',
-//   'Gemini-1.5-Pro-001': '',
-//   'Meta-Llama-3.1-70b-Instruct': '',
-//   'Yi-Large-preview': '',
-//   'Deepseek-v2-API-0628': '',
-//   'Gemma-2-27b-it': '',
-//   'Yi-Large': '',
-//   'Nemotron-4-340B-Instruct': '',
-//   'GLM-4-0520': '',
-//   'Llama-3-70b-Instruct': '',
-//   'Reka-Core-20240501': '',
-//   'Command R+': '',
-//   'Gemma-2-9b-it': '',
-//   'Qwen2-72B-Instruct': '',
-//   'GLM-4-0116': '',
-//   'Qwen-Max-0428': '',
-//   'DeepSeek-Coder-V2-Instruct': '',
-//   'Reka-Flash-Preview-20240611': '',
-//   'Meta-Llama-3.1-8b-Instruct': '',
-//   'Qwen1.5-110B-Chat': '',
-//   'Yi-1.5-34B-Chat': '',
-//   'Reka-Flash-21B-online': '',
-//   'Llama-3-8b-Instruct': '',
-//   'Command R': '',
-//   'Reka-Flash-21B': '',
-//   'Qwen1.5-72B-Chat': '',
-//   'Mixtral-8x22b-Instruct-v0.1': '',
-//   'Zephyr-ORPO-141b-A35b-v0.1': '',
-//   'Qwen1.5-32B-Chat': '',
-//   'Mistral-Next': '',
-//   'Phi-3-Medium-4k-Instruct': '',
-//   'Starling-LM-7B-beta': '',
-//   'Yi-34B-Chat': '',
-//   'Qwen1.5-14B-Chat': '',
-//   'WizardLM-70B-v1.0': '',
-//   'Tulu-2-DPO-70B': '',
-//   'DBRX-Instruct-Preview': '',
-//   'Phi-3-Small-8k-Instruct': '',
-//   'Llama-2-70b-chat': '',
-//   'OpenChat-3.5-0106': '',
-//   'Vicuna-33B': '',
-//   'Snowflake Arctic Instruct': '',
-//   'Starling-LM-7B-alpha': '',
-// };
@@ -9,139 +9,34 @@ import { wireTogetherAIListOutputSchema } from './togetherai.wiretypes';


 // [Azure] / [OpenAI]
-// https://platform.openai.com/docs/models
 const _knownOpenAIChatModels: ManualMappings = [

-  // GPT-4o -> 2024-05-13 (Starting October 2nd, 2024, gpt-4o will point to the gpt-4o-2024-08-06 snapshot)
+  // GPT-4o -> 2024-05-13
  {
    idPrefix: 'gpt-4o',
    label: 'GPT-4o',
-    description: 'Points to gpt-4o-2024-08-06 starting on Oct 2, 2024.',
-    symLink: 'gpt-4o-2024-08-06',
+    description: 'Currently points to gpt-4o-2024-05-13.',
+    symLink: 'gpt-4o-2024-05-13',
    hidden: true,
    // copied from symlinked
    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
-    pricing: { chatIn: 2.5, chatOut: 10 },
-    benchmark: { cbaElo: 1286 + 1 },
-  },
-  {
-    isLatest: true,
-    idPrefix: 'gpt-4o-2024-08-06',
-    label: 'GPT-4o (2024-08-06)',
-    description: 'Latest snapshot that supports Structured Outputs',
-    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json], // + Structured Outputs?
-    pricing: { chatIn: 2.5, chatOut: 10 },
-    benchmark: { cbaElo: 1286 + 1 },
-  },
-  {
-    idPrefix: 'gpt-4o-2024-05-13',
-    label: 'GPT-4o (2024-05-13)',
-    description: 'Advanced, multimodal flagship model that\'s cheaper and faster than GPT-4 Turbo.',
-    contextWindow: 128000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Oct 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 5, chatOut: 15 },
-    benchmark: { cbaElo: 1286 },
-    hidden: true,
+    benchmark: { cbaElo: 1310 },
  },
  {
-    idPrefix: 'chatgpt-4o-latest',
-    label: 'ChatGPT-4o Latest',
-    description: 'Intended for research and evaluation. Dynamic model continuously updated to the current version of GPT-4o in ChatGPT.',
+    isLatest: true,
+    idPrefix: 'gpt-4o-2024-05-13',
+    label: 'GPT-4o (2024-05-13)',
+    description: 'Advanced, multimodal flagship model that’s cheaper and faster than GPT-4 Turbo.',
    contextWindow: 128000,
-    maxCompletionTokens: 16384,
+    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Oct 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 5, chatOut: 15 },
-  },
-
-  // GPT-4o mini
-  {
-    idPrefix: 'gpt-4o-mini',
-    label: 'GPT-4o mini',
-    description: 'Currently points to gpt-4o-mini-2024-07-18.',
-    symLink: 'gpt-4o-mini-2024-07-18',
-    hidden: true,
-    // copied from symlinked
-    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
-    pricing: { chatIn: 0.15, chatOut: 0.60 },
-    benchmark: { cbaElo: 1277, cbaMmlu: 82.0 },
-  },
-  {
-    idPrefix: 'gpt-4o-mini-2024-07-18',
-    label: 'GPT-4o Mini (2024-07-18)',
-    description: 'Affordable model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo.',
-    contextWindow: 128000,
-    maxCompletionTokens: 16384,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
-    pricing: { chatIn: 0.15, chatOut: 0.60 },
-  },
-
-  // o1-preview
-  {
-    idPrefix: 'o1-preview',
-    label: 'o1 Preview',
-    description: 'Supported in Big-AGI 2. Points to the most recent snapshot of the o1 model: o1-preview-2024-09-12',
-    symLink: 'o1-preview-2024-09-12',
-    hidden: true,
-    // copied from symlinked
-    contextWindow: 128000,
-    maxCompletionTokens: 32768,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 15, chatOut: 60 },
-    isPreview: true,
-  },
-  {
-    hidden: true, // we can't support it in Big-AGI 1
-    idPrefix: 'o1-preview-2024-09-12',
-    label: 'o1 Preview (2024-09-12)',
-    description: 'Supported in Big-AGI 2. New reasoning model for complex tasks that require broad general knowledge.',
-    contextWindow: 128000,
-    maxCompletionTokens: 32768,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 15, chatOut: 60 },
-    isPreview: true,
-  },
-
-  // o1-mini
-  {
-    idPrefix: 'o1-mini',
-    label: 'o1 Mini',
-    description: 'Supported in Big-AGI 2. Points to the most recent o1-mini snapshot: o1-mini-2024-09-12',
-    symLink: 'o1-mini-2024-09-12',
-    hidden: true,
-    // copied from symlinked
-    contextWindow: 128000,
-    maxCompletionTokens: 65536,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 3, chatOut: 12 },
-    isPreview: true,
-  },
-  {
-    hidden: true, // we can't support it in Big-AGI 1
-    idPrefix: 'o1-mini-2024-09-12',
-    label: 'o1 Mini (2024-09-12)',
-    description: 'Supported in Big-AGI 2. Fast, cost-efficient reasoning model tailored to coding, math, and science use cases.',
-    contextWindow: 128000,
-    maxCompletionTokens: 65536,
-    trainingDataCutoff: 'Oct 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
-    pricing: { chatIn: 3, chatOut: 12 },
-    isPreview: true,
+    benchmark: { cbaElo: 1310 },
  },

  // GPT4 Turbo with Vision -> 2024-04-09
@@ -157,7 +52,7 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Dec 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1257 },
+    benchmark: { cbaElo: 1261 },
  },
  {
    idPrefix: 'gpt-4-turbo-2024-04-09',
@@ -168,12 +63,12 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Dec 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1257 },
+    benchmark: { cbaElo: 1261 },
  },

  // GPT4 Turbo Previews
  {
-    idPrefix: 'gpt-4-turbo-preview',
+    idPrefix: 'gpt-4-turbo-preview', // GPT-4 Turbo preview model -> 0125
    label: 'GPT-4 Preview Turbo',
    description: 'GPT-4 Turbo preview model. Currently points to gpt-4-0125-preview.',
    symLink: 'gpt-4-0125-preview',
@@ -185,33 +80,63 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Dec 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1245 },
+    benchmark: { cbaElo: 1251 },
  },
  {
-    idPrefix: 'gpt-4-0125-preview',
+    idPrefix: 'gpt-4-0125-preview', // GPT-4 Turbo preview model
    label: 'GPT-4 Turbo (0125)',
-    description: 'GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn\'t complete a task.',
+    description: 'GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn\'t complete a task. Returns a maximum of 4,096 output tokens.',
+    isPreview: true,
    contextWindow: 128000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Dec 2023',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
    pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1245 },
+    benchmark: { cbaElo: 1251 },
    hidden: true,
  },
  {
    idPrefix: 'gpt-4-1106-preview', // GPT-4 Turbo preview model
    label: 'GPT-4 Turbo (1106)',
-    description: 'GPT-4 Turbo preview model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
+    description: 'GPT-4 Turbo preview model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens.',
+    isPreview: true,
    contextWindow: 128000,
    maxCompletionTokens: 4096,
    trainingDataCutoff: 'Apr 2023',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
    pricing: { chatIn: 10, chatOut: 30 },
-    benchmark: { cbaElo: 1251 },
+    benchmark: { cbaElo: 1255 },
    hidden: true,
  },

+  // GPT4 Vision Previews
+  {
+    idPrefix: 'gpt-4-vision-preview', // GPT-4 Turbo vision preview
+    label: 'GPT-4 Preview Vision',
+    description: 'GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities. Currently points to gpt-4-1106-vision-preview.',
+    symLink: 'gpt-4-1106-vision-preview',
+    // copied from symlinked
+    isPreview: true,
+    contextWindow: 128000,
+    maxCompletionTokens: 4096,
+    trainingDataCutoff: 'Apr 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
+    pricing: { chatIn: 10, chatOut: 30 },
+    hidden: true, // Deprecated in favor of gpt-4-turbo
+  },
+  {
+    idPrefix: 'gpt-4-1106-vision-preview',
+    label: 'GPT-4 Preview Vision (1106)',
+    description: 'GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities. Returns a maximum of 4,096 output tokens.',
+    isPreview: true,
+    contextWindow: 128000,
+    maxCompletionTokens: 4096,
+    trainingDataCutoff: 'Apr 2023',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
+    pricing: { chatIn: 10, chatOut: 30 },
+    hidden: true, // Deprecated in favor of gpt-4-turbo
+  },
+

  // GPT4-32k's
  {
@@ -257,7 +182,7 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Sep 2021',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
    pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1161 },
+    benchmark: { cbaElo: 1164 },
  },
  {
    idPrefix: 'gpt-4-0314',
@@ -267,7 +192,7 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Sep 2021',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
    pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1186 },
+    benchmark: { cbaElo: 1189 },
    hidden: true,
  },
  {
@@ -281,49 +206,9 @@ const _knownOpenAIChatModels: ManualMappings = [
    trainingDataCutoff: 'Sep 2021',
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
    pricing: { chatIn: 30, chatOut: 60 },
-    benchmark: { cbaElo: 1161 },
-    isLegacy: true,
+    benchmark: { cbaElo: 1164 },
  },

-  // 3.5-Turbo
-  // As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast.
-  {
-    idPrefix: 'gpt-3.5-turbo-0125',
-    label: '3.5-Turbo (0125)',
-    description: 'The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.',
-    contextWindow: 16385,
-    maxCompletionTokens: 4096,
-    trainingDataCutoff: 'Sep 2021',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 0.5, chatOut: 1.5 },
-    benchmark: { cbaElo: 1105 },
-  },
-  {
-    idPrefix: 'gpt-3.5-turbo-1106',
-    label: '3.5-Turbo (1106)',
-    description: 'GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
-    contextWindow: 16385,
-    maxCompletionTokens: 4096,
-    trainingDataCutoff: 'Sep 2021',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 1, chatOut: 2 },
-    benchmark: { cbaElo: 1072 },
-    hidden: true,
-  },
-  {
-    idPrefix: 'gpt-3.5-turbo',
-    label: '3.5-Turbo',
-    description: 'Currently points to gpt-3.5-turbo-0125. As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast.',
-    symLink: 'gpt-3.5-turbo-0125',
-    hidden: true,
-    // copied
-    contextWindow: 16385,
-    maxCompletionTokens: 4096,
-    trainingDataCutoff: 'Sep 2021',
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 0.5, chatOut: 1.5 },
-    benchmark: { cbaElo: 1105 },
-  },

  // 3.5-Turbo-Instruct (Not for Chat)
  {
@@ -338,6 +223,46 @@ const _knownOpenAIChatModels: ManualMappings = [
  },


+  // 3.5-Turbo-16k's
+  {
+    idPrefix: 'gpt-3.5-turbo-0125',
+    label: '3.5-Turbo (0125)',
+    description: 'The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls. Returns a maximum of 4,096 output tokens.',
+    contextWindow: 16385,
+    maxCompletionTokens: 4096,
+    trainingDataCutoff: 'Sep 2021',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    pricing: { chatIn: 0.5, chatOut: 1.5 },
+    benchmark: { cbaElo: 1104 },
+  },
+  {
+    idPrefix: 'gpt-3.5-turbo-1106',
+    label: '3.5-Turbo (1106)',
+    description: 'The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.',
+    contextWindow: 16385,
+    maxCompletionTokens: 4096,
+    trainingDataCutoff: 'Sep 2021',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    pricing: { chatIn: 1, chatOut: 2 },
+    benchmark: { cbaElo: 1072 },
+    hidden: true,
+  },
+  {
+    idPrefix: 'gpt-3.5-turbo',
+    label: '3.5-Turbo',
+    description: 'Currently points to gpt-3.5-turbo-0125.',
+    symLink: 'gpt-3.5-turbo-0125',
+    hidden: true,
+    // copied
+    contextWindow: 16385,
+    maxCompletionTokens: 4096,
+    trainingDataCutoff: 'Sep 2021',
+    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    pricing: { chatIn: 0.5, chatOut: 1.5 },
+    benchmark: { cbaElo: 1104 },
+  },
+
+
  // Azure variants - because someone forgot the dot
  {
    idPrefix: 'gpt-35-turbo-16k',
@@ -451,31 +376,8 @@ export function localAIModelToModelDescription(modelId: string): ModelDescriptio


 // [Mistral]
-// updated from the models on: https://docs.mistral.ai/getting-started/models/
-// and the pricing available on: https://mistral.ai/technology/#pricing

 const _knownMistralChatModels: ManualMappings = [
-  // Codestral
-  {
-    idPrefix: 'codestral-2405',
-    label: 'Codestral (2405)',
-    description: 'Designed and optimized for code generation tasks.',
-    contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 1, chatOut: 3 },
-  },
-  {
-    idPrefix: 'codestral-latest',
-    label: 'Mistral Large (latest)',
-    symLink: 'mistral-codestral-2405',
-    hidden: true,
-    // copied
-    description: 'Designed and optimized for code generation tasks.',
-    contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 1, chatOut: 3 },
-  },
-
  // Large
  {
    idPrefix: 'mistral-large-2402',
@@ -483,7 +385,7 @@ const _knownMistralChatModels: ManualMappings = [
    description: 'Top-tier reasoning for high-complexity tasks.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 4, chatOut: 12 },
+    pricing: { chatIn: 8, chatOut: 24 },
    benchmark: { cbaElo: 1159 },
  },
  {
@@ -495,135 +397,103 @@ const _knownMistralChatModels: ManualMappings = [
    description: 'Top-tier reasoning for high-complexity tasks.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 4, chatOut: 12 },
+    pricing: { chatIn: 8, chatOut: 24 },
    benchmark: { cbaElo: 1159 },
  },
-
-  // Open Mixtral (8x22B)
  {
-    idPrefix: 'open-mixtral-8x22b-2404',
-    label: 'Open Mixtral 8x22B (2404)',
-    description: 'Mixtral 8x22B model',
-    contextWindow: 65536,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 2, chatOut: 6 },
-  },
-  {
-    idPrefix: 'open-mixtral-8x22b',
-    label: 'Open Mixtral 8x22B',
-    symLink: 'open-mixtral-8x22b-2404',
+    idPrefix: 'mistral-large',
+    label: 'Mistral Large (?)',
+    description: 'Flagship model, with top-tier reasoning capabilities and language support (English, French, German, Italian, Spanish, and Code)',
+    contextWindow: 32768,
+    interfaces: [LLM_IF_OAI_Chat],
    hidden: true,
-    // copied
-    description: 'Mixtral 8x22B model',
-    contextWindow: 65536,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 2, chatOut: 6 },
  },
-  // Medium (Deprecated)
+
+  // Medium - not updated on 2024-02-26
  {
    idPrefix: 'mistral-medium-2312',
    label: 'Mistral Medium (2312)',
-    description: 'Ideal for intermediate tasks that require moderate reasoning (Data extraction, Summarizing a Document, Writing emails, Writing a Job Description, or Writing Product Descriptions)',
+    description: 'Mistral internal prototype model.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
    pricing: { chatIn: 2.7, chatOut: 8.1 },
    benchmark: { cbaElo: 1148 },
-    isLegacy: true,
-    hidden: true,
  },
  {
    idPrefix: 'mistral-medium-latest',
    label: 'Mistral Medium (latest)',
    symLink: 'mistral-medium-2312',
+    hidden: true,
    // copied
-    description: 'Ideal for intermediate tasks that require moderate reasoning (Data extraction, Summarizing a Document, Writing emails, Writing a Job Description, or Writing Product Descriptions)',
+    description: 'Mistral internal prototype model.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
    pricing: { chatIn: 2.7, chatOut: 8.1 },
    benchmark: { cbaElo: 1148 },
-    isLegacy: true,
-    hidden: true,
  },
  {
    idPrefix: 'mistral-medium',
    label: 'Mistral Medium',
-    symLink: 'mistral-medium-2312',
-    // copied
-    description: 'Ideal for intermediate tasks that require moderate reasoning (Data extraction, Summarizing a Document, Writing emails, Writing a Job Description, or Writing Product Descriptions)',
+    description: 'Mistral internal prototype model.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
    pricing: { chatIn: 2.7, chatOut: 8.1 },
    benchmark: { cbaElo: 1148 },
-    isLegacy: true,
    hidden: true,
  },

-  // Open Mixtral (8x7B) -> currently points to `mistral-small-2312` (as per the docs)
-  {
-    idPrefix: 'open-mixtral-8x7b',
-    label: 'Open Mixtral (8x7B)',
-    description: 'A sparse mixture of experts model. As such, it leverages up to 45B parameters but only uses about 12B during inference, leading to better inference throughput at the cost of more vRAM.',
-    contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 0.7, chatOut: 0.7 },
-  },
-  // Small (deprecated)
+  // Small (8x7B)
  {
    idPrefix: 'mistral-small-2402',
    label: 'Mistral Small (2402)',
-    description: 'Suitable for simple tasks that one can do in bulk (Classification, Customer Support, or Text Generation)',
+    description: 'Optimized endpoint. Cost-efficient reasoning for low-latency workloads. Mistral Small outperforms Mixtral 8x7B and has lower latency',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 1, chatOut: 3 },
+    pricing: { chatIn: 2, chatOut: 6 },
+  },
+  {
+    idPrefix: 'mistral-small-2312',
+    label: 'Mistral Small (2312)',
+    description: 'Aka open-mixtral-8x7b. Cost-efficient reasoning for low-latency workloads. Mistral Small outperforms Mixtral 8x7B and has lower latency',
+    contextWindow: 32768,
+    interfaces: [LLM_IF_OAI_Chat],
+    pricing: { chatIn: 2, chatOut: 6 },
    hidden: true,
-    isLegacy: true,
  },
  {
    idPrefix: 'mistral-small-latest',
    label: 'Mistral Small (latest)',
    symLink: 'mistral-small-2402',
+    hidden: true,
    // copied
-    description: 'Suitable for simple tasks that one can do in bulk (Classification, Customer Support, or Text Generation)',
+    description: 'Cost-efficient reasoning for low-latency workloads. Mistral Small outperforms Mixtral 8x7B and has lower latency',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    pricing: { chatIn: 1, chatOut: 3 },
-    hidden: true,
-    isLegacy: true,
-  },
-  {
-    idPrefix: 'mistral-small-2312',
-    label: 'Mistral Small (2312)',
-    description: 'Aka open-mixtral-8x7b. Suitable for simple tasks that one can do in bulk (Classification, Customer Support, or Text Generation)',
-    contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 1, chatOut: 3 },
-    hidden: true,
-    isLegacy: true,
+    pricing: { chatIn: 2, chatOut: 6 },
  },
  {
    idPrefix: 'mistral-small',
    label: 'Mistral Small',
-    symLink: 'mistral-small-2312',
-    // copied
-    description: 'Aka open-mixtral-8x7b. Suitable for simple tasks that one can do in bulk (Classification, Customer Support, or Text Generation)',
+    description: 'Cost-efficient reasoning for low-latency workloads.',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 1, chatOut: 3 },
+    pricing: { chatIn: 2, chatOut: 6 },
    hidden: true,
-    isLegacy: true,
  },

-
-  // Open Mistral (7B) -> currently points to mistral-tiny-2312 (as per the docs)
+  // Open Mixtral (8x7B)
  {
-    idPrefix: 'open-mistral-7b',
-    label: 'Open Mistral (7B)',
-    description: 'The first dense model released by Mistral AI, perfect for experimentation, customization, and quick iteration. At the time of the release, it matched the capabilities of models up to 30B parameters.',
+    idPrefix: 'open-mixtral-8x7b',
+    label: 'Open Mixtral (8x7B)',
+    description: 'Mixtral 8x7B model, aka mistral-small-2312',
+    // symLink: 'mistral-small-2312',
+    // copied
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
-    pricing: { chatIn: 0.25, chatOut: 0.25 },
+    pricing: { chatIn: 0.7, chatOut: 0.7 },
  },
-  // Tiny (deprecated)
+
+  // Tiny (7B)
  {
    idPrefix: 'mistral-tiny-2312',
    label: 'Mistral Tiny (2312)',
@@ -631,34 +501,43 @@ const _knownMistralChatModels: ManualMappings = [
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
    hidden: true,
-    isLegacy: true,
  },
  {
    idPrefix: 'mistral-tiny',
    label: 'Mistral Tiny',
-    symLink: 'mistral-tiny-2312',
-    // copied
-    description: 'Aka open-mistral-7b. Used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial',
+    description: 'Used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial',
    contextWindow: 32768,
    interfaces: [LLM_IF_OAI_Chat],
    hidden: true,
-    isLegacy: true,
  },
+  // Open Mistral (7B)
+  {
+    idPrefix: 'open-mistral-7b',
+    label: 'Open Mistral (7B)',
+    description: 'Mistral 7B model, aka mistral-tiny-2312',
+    // symLink: 'mistral-tiny-2312',
+    // copied
+    contextWindow: 32768,
+    interfaces: [LLM_IF_OAI_Chat],
+    pricing: { chatIn: 0.25, chatOut: 0.25 },
+  },
+

  {
    idPrefix: 'mistral-embed',
    label: 'Mistral Embed',
-    description: 'A model that converts text into numerical vectors of embeddings in 1024 dimensions. Embedding models enable retrieval and retrieval-augmented generation applications.',
+    description: 'State-of-the-art semantic for extracting representation of text extracts.',
+    // output: 1024 dimensions
    maxCompletionTokens: 1024, // HACK - it's 1024 dimensions, but those are not 'completion tokens'
-    contextWindow: 8192, // Updated context window
+    contextWindow: 32768, // actually unknown, assumed from the other models
    interfaces: [],
-    pricing: { chatIn: 0.1, chatOut: 0.1 },
    hidden: true,
  },
 ];

+
 const mistralModelFamilyOrder = [
-  'codestral', 'mistral-large', 'open-mixtral-8x22b', 'mistral-medium', 'open-mixtral-8x7b', 'mistral-small', 'open-mistral-7b', 'mistral-tiny', 'mistral-embed', '🔗',
+  'mistral-large', 'mistral-medium', 'mistral-small', 'open-mixtral-8x7b', 'mistral-tiny', 'open-mistral-7b', 'mistral-embed', '🔗',
 ];

 export function mistralModelToModelDescription(_model: unknown): ModelDescriptionSchema {
@@ -674,13 +553,13 @@ export function mistralModelToModelDescription(_model: unknown): ModelDescriptio
 }

 export function mistralModelsSort(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
-  if (a.label.startsWith('🔗') && !b.label.startsWith('🔗')) return 1;
-  if (!a.label.startsWith('🔗') && b.label.startsWith('🔗')) return -1;
  const aPrefixIndex = mistralModelFamilyOrder.findIndex(prefix => a.id.startsWith(prefix));
  const bPrefixIndex = mistralModelFamilyOrder.findIndex(prefix => b.id.startsWith(prefix));
  if (aPrefixIndex !== -1 && bPrefixIndex !== -1) {
    if (aPrefixIndex !== bPrefixIndex)
      return aPrefixIndex - bPrefixIndex;
+    if (a.label.startsWith('🔗') && !b.label.startsWith('🔗')) return 1;
+    if (!a.label.startsWith('🔗') && b.label.startsWith('🔗')) return -1;
    return b.label.localeCompare(a.label);
  }
  return aPrefixIndex !== -1 ? 1 : -1;
@@ -742,14 +621,10 @@ export function openRouterModelFamilySortFn(a: { id: string }, b: { id: string }
  return aPrefixIndex !== -1 ? -1 : 1;
 }

-export function openRouterModelToModelDescription(wireModel: object): ModelDescriptionSchema | null {
+export function openRouterModelToModelDescription(wireModel: object): ModelDescriptionSchema {

  // parse the model
-  const { data: model, error } = wireOpenrouterModelsListOutputSchema.safeParse(wireModel);
-  if (error) {
-    console.warn(`openrouterModelToModelDescription: Failed to parse model: ${error}`);
-    return null;
-  }
+  const model = wireOpenrouterModelsListOutputSchema.parse(wireModel);

  // parse pricing
  const pricing: ModelDescriptionSchema['pricing'] = {
@@ -938,84 +813,41 @@ export function perplexityAIModelSort(a: ModelDescriptionSchema, b: ModelDescrip
 const _knownGroqModels: ManualMappings = [
  {
    isLatest: true,
-    idPrefix: 'llama-3.1-405b-reasoning',
-    label: 'Llama 3.1 · 405B',
-    description: 'LLaMA 3.1 405B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
-    contextWindow: 131072,
-    maxCompletionTokens: 8000,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
-    isLatest: true,
-    idPrefix: 'llama-3.1-70b-versatile',
-    label: 'Llama 3.1 · 70B',
-    description: 'LLaMA 3.1 70B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
-    contextWindow: 131072,
-    maxCompletionTokens: 8000,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
-    isLatest: true,
-    idPrefix: 'llama-3.1-8b-instant',
-    label: 'Llama 3.1 · 8B',
-    description: 'LLaMA 3.1 8B developed by Meta with a context window of 131,072 tokens. Supports tool use.',
-    contextWindow: 131072,
-    maxCompletionTokens: 8000,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
-    idPrefix: 'llama3-groq-70b-8192-tool-use-preview',
-    label: 'Llama 3 Groq · 70B Tool Use',
-    description: 'LLaMA 3 70B Tool Use developed by Groq with a context window of 8,192 tokens. Optimized for tool use.',
-    contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
-    idPrefix: 'llama3-groq-8b-8192-tool-use-preview',
-    label: 'Llama 3 Groq · 8B Tool Use',
-    description: 'LLaMA 3 8B Tool Use developed by Groq with a context window of 8,192 tokens. Optimized for tool use.',
-    contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
    idPrefix: 'llama3-70b-8192',
    label: 'Llama 3 · 70B',
-    description: 'LLaMA3 70B developed by Meta with a context window of 8,192 tokens. Supports tool use.',
+    description: 'LLaMA3 70b developed by Meta with a context window of 8,192 tokens.',
    contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    // isLegacy: true,
-    hidden: true,
+    interfaces: [LLM_IF_OAI_Chat],
  },
  {
+    // isLatest: true,
    idPrefix: 'llama3-8b-8192',
    label: 'Llama 3 · 8B',
-    description: 'LLaMA3 8B developed by Meta with a context window of 8,192 tokens. Supports tool use.',
+    description: 'LLaMA3 8b developed by Meta with a context window of 8,192 tokens.',
    contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-    // isLegacy: true,
+    interfaces: [LLM_IF_OAI_Chat],
+  },
+  {
+    idPrefix: 'llama2-70b-4096',
+    label: 'Llama 2 · 70B',
+    description: 'LLaMA2 70b developed by Meta with a context window of 4,096 tokens.',
+    contextWindow: 4096,
+    interfaces: [LLM_IF_OAI_Chat],
    hidden: true,
  },
  {
    idPrefix: 'mixtral-8x7b-32768',
    label: 'Mixtral 8x7B',
-    description: 'Mixtral 8x7B developed by Mistral with a context window of 32,768 tokens. Supports tool use.',
+    description: 'Mixtral 8x7b developed by Mistral with a context window of 32,768 tokens.',
    contextWindow: 32768,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
-  },
-  {
-    idPrefix: 'gemma2-9b-it',
-    label: 'Gemma 2 · 9B Instruct',
-    description: 'Gemma 2 9B developed by Google with a context window of 8,192 tokens. Supports tool use.',
-    contextWindow: 8192,
-    interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn],
+    interfaces: [LLM_IF_OAI_Chat],
  },
  {
    idPrefix: 'gemma-7b-it',
    label: 'Gemma 1.1 · 7B Instruct',
-    description: 'Gemma 7B developed by Google with a context window of 8,192 tokens. Supports tool use.',
+    description: 'Gemma 7b developed by Google with a context window of 8,192 tokens.',
    contextWindow: 8192,
    interfaces: [LLM_IF_OAI_Chat],
-    hidden: true,
  },
 ];

@@ -1032,11 +864,6 @@ export function groqModelToModelDescription(_model: unknown): ModelDescriptionSc
 }

 export function groqModelSortFn(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
-  // sort hidden at the end
-  if (a.hidden && !b.hidden)
-    return 1;
-  if (!a.hidden && b.hidden)
-    return -1;
  // sort as per their order in the known models
  const aIndex = _knownGroqModels.findIndex(base => a.id.startsWith(base.idPrefix));
  const bIndex = _knownGroqModels.findIndex(base => b.id.startsWith(base.idPrefix));
@@ -1048,13 +875,7 @@ export function groqModelSortFn(a: ModelDescriptionSchema, b: ModelDescriptionSc

 // Helpers

-type ManualMapping = ({
-  idPrefix: string,
-  isLatest?: boolean,
-  isPreview?: boolean,
-  isLegacy?: boolean,
-  symLink?: string
-} & Omit<ModelDescriptionSchema, 'id' | 'created' | 'updated'>);
+type ManualMapping = ({ idPrefix: string, isLatest?: boolean, isPreview?: boolean, isLegacy?: boolean, symLink?: string } & Omit<ModelDescriptionSchema, 'id' | 'created' | 'updated'>);
 type ManualMappings = ManualMapping[];

 function fromManualMapping(mappings: ManualMappings, id: string, created?: number, updated?: number, fallback?: ManualMapping): ModelDescriptionSchema {
@@ -12,7 +12,7 @@ import { fixupHost } from '~/common/util/urlUtils';

 import { OpenAIWire, WireOpenAICreateImageOutput, wireOpenAICreateImageOutputSchema, WireOpenAICreateImageRequest } from './openai.wiretypes';
 import { azureModelToModelDescription, groqModelSortFn, groqModelToModelDescription, lmStudioModelToModelDescription, localAIModelToModelDescription, mistralModelsSort, mistralModelToModelDescription, oobaboogaModelToModelDescription, openAIModelFilter, openAIModelToModelDescription, openRouterModelFamilySortFn, openRouterModelToModelDescription, perplexityAIModelDescriptions, perplexityAIModelSort, togetherAIModelsToModelDescriptions } from './models.data';
-import { llmsChatGenerateWithFunctionsOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema, ModelDescriptionSchema } from '../llm.server.types';
+import { llmsChatGenerateWithFunctionsOutputSchema, llmsListModelsOutputSchema, ModelDescriptionSchema } from '../llm.server.types';
 import { wilreLocalAIModelsApplyOutputSchema, wireLocalAIModelsAvailableOutputSchema, wireLocalAIModelsListOutputSchema } from './localai.wiretypes';


@@ -72,11 +72,8 @@ const listModelsInputSchema = z.object({

 const chatGenerateWithFunctionsInputSchema = z.object({
  access: openAIAccessSchema,
-  model: openAIModelSchema,
-  history: openAIHistorySchema,
-  functions: openAIFunctionsSchema.optional(),
-  forceFunctionName: z.string().optional(),
-  context: llmsGenerateContextSchema.optional(),
+  model: openAIModelSchema, history: openAIHistorySchema,
+  functions: openAIFunctionsSchema.optional(), forceFunctionName: z.string().optional(),
 });

 const createImagesInputSchema = z.object({
@@ -111,7 +108,7 @@ export const llmOpenAIRouter = createTRPCRouter({

      // [Azure]: use an older 'deployments' API to enumerate the models, and a modified OpenAI id to description mapping
      if (access.dialect === 'azure') {
-        const azureModels = await openaiGETOrThrow(access, `/openai/deployments?api-version=2023-03-15-preview`);
+        const azureModels = await openaiGET(access, `/openai/deployments?api-version=2023-03-15-preview`);

        const wireAzureListDeploymentsSchema = z.object({
          data: z.array(z.object({
@@ -149,7 +146,7 @@ export const llmOpenAIRouter = createTRPCRouter({


      // [non-Azure]: fetch openAI-style for all but Azure (will be then used in each dialect)
-      const openAIWireModelsResponse = await openaiGETOrThrow<OpenAIWire.Models.Response>(access, '/v1/models');
+      const openAIWireModelsResponse = await openaiGET<OpenAIWire.Models.Response>(access, '/v1/models');

      // [Together] missing the .data property
      if (access.dialect === 'togetherai')
@@ -256,8 +253,7 @@ export const llmOpenAIRouter = createTRPCRouter({
        case 'openrouter':
          models = openAIModels
            .sort(openRouterModelFamilySortFn)
-            .map(openRouterModelToModelDescription)
-            .filter(desc => !!desc) as ModelDescriptionSchema[];
+            .map(openRouterModelToModelDescription);
          break;

      }
@@ -271,22 +267,17 @@ export const llmOpenAIRouter = createTRPCRouter({
    .output(llmsChatGenerateWithFunctionsOutputSchema)
    .mutation(async ({ input }) => {

-      const { access, model, history, functions, forceFunctionName, context } = input;
+      const { access, model, history, functions, forceFunctionName } = input;
      const isFunctionsCall = !!functions && functions.length > 0;

      const completionsBody = openAIChatCompletionPayload(access.dialect, model, history, isFunctionsCall ? functions : null, forceFunctionName ?? null, 1, false);
-      const wireCompletions = await openaiPOSTOrThrow<OpenAIWire.ChatCompletion.Response, OpenAIWire.ChatCompletion.Request>(
+      const wireCompletions = await openaiPOST<OpenAIWire.ChatCompletion.Response, OpenAIWire.ChatCompletion.Request>(
        access, model.id, completionsBody, '/v1/chat/completions',
      );

      // expect a single output
-      if (wireCompletions?.choices?.length !== 1) {
-        console.error(`[POST] llmOpenAI.chatGenerateWithFunctions: ${access.dialect}: ${context?.name || 'no context'}: unexpected output${forceFunctionName ? ` (fn: ${forceFunctionName})` : ''}:`, model.id, wireCompletions?.choices);
-        throw new TRPCError({
-          code: 'UNPROCESSABLE_CONTENT',
-          message: `[OpenAI Issue] Expected 1 completion, got ${wireCompletions?.choices?.length}`,
-        });
-      }
+      if (wireCompletions?.choices?.length !== 1)
+        throw new TRPCError({ code: 'INTERNAL_SERVER_ERROR', message: `[OpenAI Issue] Expected 1 completion, got ${wireCompletions?.choices?.length}` });
      let { message, finish_reason } = wireCompletions.choices[0];

      // LocalAI hack/workaround, until https://github.com/go-skynet/LocalAI/issues/788 is fixed
@@ -327,7 +318,7 @@ export const llmOpenAIRouter = createTRPCRouter({
        delete requestBody.response_format;

      // create 1 image (dall-e-3 won't support more than 1, so better transfer the burden to the client)
-      const wireOpenAICreateImageOutput = await openaiPOSTOrThrow<WireOpenAICreateImageOutput, WireOpenAICreateImageRequest>(
+      const wireOpenAICreateImageOutput = await openaiPOST<WireOpenAICreateImageOutput, WireOpenAICreateImageRequest>(
        access, null, requestBody, '/v1/images/generations',
      );

@@ -349,7 +340,7 @@ export const llmOpenAIRouter = createTRPCRouter({
    .mutation(async ({ input: { access, text } }): Promise<OpenAIWire.Moderation.Response> => {
      try {

-        return await openaiPOSTOrThrow<OpenAIWire.Moderation.Response, OpenAIWire.Moderation.Request>(access, null, {
+        return await openaiPOST<OpenAIWire.Moderation.Response, OpenAIWire.Moderation.Request>(access, null, {
          input: text,
          model: 'text-moderation-latest',
        }, '/v1/moderations');
@@ -370,7 +361,7 @@ export const llmOpenAIRouter = createTRPCRouter({
  dialectLocalAI_galleryModelsAvailable: publicProcedure
    .input(listModelsInputSchema)
    .query(async ({ input: { access } }) => {
-      const wireLocalAIModelsAvailable = await openaiGETOrThrow(access, '/models/available');
+      const wireLocalAIModelsAvailable = await openaiGET(access, '/models/available');
      return wireLocalAIModelsAvailableOutputSchema.parse(wireLocalAIModelsAvailable);
    }),

@@ -383,7 +374,7 @@ export const llmOpenAIRouter = createTRPCRouter({
    }))
    .mutation(async ({ input: { access, galleryName, modelName } }) => {
      const galleryModelId = `${galleryName}@${modelName}`;
-      const wireLocalAIModelApply = await openaiPOSTOrThrow(access, null, { id: galleryModelId }, '/models/apply');
+      const wireLocalAIModelApply = await openaiPOST(access, null, { id: galleryModelId }, '/models/apply');
      return wilreLocalAIModelsApplyOutputSchema.parse(wireLocalAIModelApply);
    }),

@@ -394,7 +385,7 @@ export const llmOpenAIRouter = createTRPCRouter({
      jobId: z.string(),
    }))
    .query(async ({ input: { access, jobId } }) => {
-      const wireLocalAIModelsJobs = await openaiGETOrThrow(access, `/models/jobs/${jobId}`);
+      const wireLocalAIModelsJobs = await openaiGET(access, `/models/jobs/${jobId}`);
      return wireLocalAIModelsListOutputSchema.parse(wireLocalAIModelsJobs);
    }),

@@ -632,12 +623,12 @@ export function openAIChatCompletionPayload(dialect: OpenAIDialects, model: Open
  };
 }

-async function openaiGETOrThrow<TOut extends object>(access: OpenAIAccessSchema, apiPath: string /*, signal?: AbortSignal*/): Promise<TOut> {
+async function openaiGET<TOut extends object>(access: OpenAIAccessSchema, apiPath: string /*, signal?: AbortSignal*/): Promise<TOut> {
  const { headers, url } = openAIAccess(access, null, apiPath);
  return await fetchJsonOrTRPCError<TOut>(url, 'GET', headers, undefined, `OpenAI/${access.dialect}`);
 }

-async function openaiPOSTOrThrow<TOut extends object, TPostBody extends object>(access: OpenAIAccessSchema, modelRefId: string | null, body: TPostBody, apiPath: string /*, signal?: AbortSignal*/): Promise<TOut> {
+async function openaiPOST<TOut extends object, TPostBody extends object>(access: OpenAIAccessSchema, modelRefId: string | null, body: TPostBody, apiPath: string /*, signal?: AbortSignal*/): Promise<TOut> {
  const { headers, url } = openAIAccess(access, modelRefId, apiPath);
  return await fetchJsonOrTRPCError<TOut, TPostBody>(url, 'POST', headers, body, `OpenAI/${access.dialect}`);
 }
@@ -5,20 +5,16 @@ export const wireOpenrouterModelsListOutputSchema = z.object({
  id: z.string(),
  name: z.string(),
  description: z.string(),
-  // NOTE: for 'openrouter/auto', this is:  {
-  //   "prompt": "-1",
-  //   "completion": "-1"
-  // }
  pricing: z.object({
    prompt: z.string(),
    completion: z.string(),
-    image: z.string().optional(),
-    request: z.string().optional(),
+    image: z.string(),
+    request: z.string(),
  }),
  context_length: z.number(),
  architecture: z.object({
-    modality: z.string(), // z.enum(['text', 'multimodal', 'text+image->text]),
-    tokenizer: z.string(), // e.g. 'Mistral', 'Claude'
+    modality: z.string(), // z.enum(['text', 'multimodal']),
+    tokenizer: z.string(), // e.g. 'Mistral'
    instruct_type: z.string().nullable(),
  }),
  top_provider: z.object({
@@ -8,7 +8,7 @@ import type { DLLM, DLLMId, DModelSourceId } from '../store-llms';
 import type { ModelDescriptionSchema } from '../server/llm.server.types';
 import type { ModelVendorId } from './vendors.registry';
 import type { StreamingClientUpdate } from './unifiedStreamingClient';
-import type { VChatContextRef, VChatFunctionIn, VChatGenerateContextName, VChatMessageIn, VChatMessageOrFunctionCallOut, VChatMessageOut, VChatStreamContextName } from '../llm.client';
+import type { VChatFunctionIn, VChatMessageIn, VChatMessageOrFunctionCallOut, VChatMessageOut } from '../llm.client';


 export interface IModelVendor<TSourceSetup = unknown, TAccess = unknown, TLLMOptions = unknown, TDLLM = DLLM<TSourceSetup, TLLMOptions>> {
@@ -44,7 +44,6 @@ export interface IModelVendor<TSourceSetup = unknown, TAccess = unknown, TLLMOpt
    access: TAccess,
    llmOptions: TLLMOptions,
    messages: VChatMessageIn[],
-    contextName: VChatGenerateContextName, contextRef: VChatContextRef | null,
    functions: VChatFunctionIn[] | null, forceFunctionName: string | null,
    maxTokens?: number,
  ) => Promise<VChatMessageOut | VChatMessageOrFunctionCallOut>;
@@ -54,7 +53,6 @@ export interface IModelVendor<TSourceSetup = unknown, TAccess = unknown, TLLMOpt
    llmId: DLLMId,
    llmOptions: TLLMOptions,
    messages: VChatMessageIn[],
-    contextName: VChatStreamContextName, contextRef: VChatContextRef,
    functions: VChatFunctionIn[] | null, forceFunctionName: string | null,
    abortSignal: AbortSignal,
    onUpdate: (update: StreamingClientUpdate, done: boolean) => void,
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Alert } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { ExternalLink } from '~/common/components/ExternalLink';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormTextField } from '~/common/components/forms/FormTextField';
@@ -50,7 +49,7 @@ export function AnthropicSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='anthropic-key' label={!!anthropicHost ? 'API Key' : 'Anthropic API Key'}
      rightLabel={<>{needsUserKey
        ? !anthropicKey && <Link level='body-sm' href='https://www.anthropic.com/earlyaccess' target='_blank'>request Key</Link>
-        : <AlreadySet />
+        : '✔️ already set in server'
      } {anthropicKey && keyValid && <Link level='body-sm' href='https://console.anthropic.com/settings/usage' target='_blank'>show tokens usage</Link>}
      </>}
      value={anthropicKey} onChange={value => updateSetup({ anthropicKey: value })}
@@ -3,7 +3,7 @@ import { apiAsync } from '~/common/util/trpc.client';

 import type { AnthropicAccessSchema } from '../../server/anthropic/anthropic.router';
 import type { IModelVendor } from '../IModelVendor';
-import type { VChatContextRef, VChatGenerateContextName, VChatMessageOut } from '../../llm.client';
+import type { VChatMessageOut } from '../../llm.client';
 import { unifiedStreamingClient } from '../unifiedStreamingClient';

 import { FALLBACK_LLM_RESPONSE_TOKENS, FALLBACK_LLM_TEMPERATURE, LLMOptionsOpenAI } from '../openai/openai.vendor';
@@ -47,7 +47,7 @@ export const ModelVendorAnthropic: IModelVendor<SourceSetupAnthropic, AnthropicA
  rpcUpdateModelsOrThrow: async (access) => await apiAsync.llmAnthropic.listModels.query({ access }),

  // Chat Generate (non-streaming) with Functions
-  rpcChatGenerateOrThrow: async (access, llmOptions, messages, contextName: VChatGenerateContextName, contextRef: VChatContextRef | null, functions, forceFunctionName, maxTokens) => {
+  rpcChatGenerateOrThrow: async (access, llmOptions, messages, functions, forceFunctionName, maxTokens) => {
    if (functions?.length || forceFunctionName)
      throw new Error('Anthropic does not support functions');

@@ -61,11 +61,6 @@ export const ModelVendorAnthropic: IModelVendor<SourceSetupAnthropic, AnthropicA
          maxTokens: maxTokens || llmResponseTokens || FALLBACK_LLM_RESPONSE_TOKENS,
        },
        history: messages,
-        context: contextRef ? {
-          method: 'chat-generate',
-          name: contextName,
-          ref: contextRef,
-        } : undefined,
      }) as VChatMessageOut;
    } catch (error: any) {
      const errorMessage = error?.message || error?.toString() || 'Anthropic Chat Generate Error';
@@ -1,6 +1,5 @@
 import * as React from 'react';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormTextField } from '~/common/components/forms/FormTextField';
 import { InlineError } from '~/common/components/InlineError';
@@ -50,7 +49,7 @@ export function AzureSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='azure-key' label='Azure Key'
      rightLabel={<>{needsUserKey
        ? !azureKey && <Link level='body-sm' href='https://azure.microsoft.com/en-us/products/ai-services/openai-service' target='_blank'>request Key</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={azureKey} onChange={value => updateSetup({ azureKey: value })}
      required={needsUserKey} isError={keyError}
@@ -3,7 +3,6 @@ import * as React from 'react';
 import { FormControl, FormHelperText, Option, Select } from '@mui/joy';
 import HealthAndSafetyIcon from '@mui/icons-material/HealthAndSafety';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormLabelStart } from '~/common/components/forms/FormLabelStart';
 import { InlineError } from '~/common/components/InlineError';
@@ -51,7 +50,7 @@ export function GeminiSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='gemini-key' label='Gemini API Key'
      rightLabel={<>{needsUserKey
        ? !geminiKey && <Link level='body-sm' href={GEMINI_API_KEY_LINK} target='_blank'>request Key</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={geminiKey} onChange={value => updateSetup({ geminiKey: value.trim() })}
      required={needsUserKey} isError={showKeyError}
@@ -1,10 +1,10 @@
 import { GeminiIcon } from '~/common/components/icons/vendors/GeminiIcon';
-import { apiAsync } from '~/common/util/trpc.client';
+ import { apiAsync } from '~/common/util/trpc.client';

 import type { GeminiAccessSchema } from '../../server/gemini/gemini.router';
 import type { GeminiBlockSafetyLevel } from '../../server/gemini/gemini.wiretypes';
 import type { IModelVendor } from '../IModelVendor';
-import type { VChatContextRef, VChatGenerateContextName, VChatMessageOut } from '../../llm.client';
+import type { VChatMessageOut } from '../../llm.client';
 import { unifiedStreamingClient } from '../unifiedStreamingClient';

 import { FALLBACK_LLM_RESPONSE_TOKENS, FALLBACK_LLM_TEMPERATURE } from '../openai/openai.vendor';
@@ -60,7 +60,7 @@ export const ModelVendorGemini: IModelVendor<SourceSetupGemini, GeminiAccessSche
  rpcUpdateModelsOrThrow: async (access) => await apiAsync.llmGemini.listModels.query({ access }),

  // Chat Generate (non-streaming) with Functions
-  rpcChatGenerateOrThrow: async (access, llmOptions, messages, contextName: VChatGenerateContextName, contextRef: VChatContextRef | null, functions, forceFunctionName, maxTokens) => {
+  rpcChatGenerateOrThrow: async (access, llmOptions, messages, functions, forceFunctionName, maxTokens) => {
    if (functions?.length || forceFunctionName)
      throw new Error('Gemini does not support functions');

@@ -74,11 +74,6 @@ export const ModelVendorGemini: IModelVendor<SourceSetupGemini, GeminiAccessSche
          maxTokens: maxTokens || maxOutputTokens || FALLBACK_LLM_RESPONSE_TOKENS,
        },
        history: messages,
-        context: contextRef ? {
-          method: 'chat-generate',
-          name: contextName,
-          ref: contextRef,
-        } : undefined,
      }) as VChatMessageOut;
    } catch (error: any) {
      const errorMessage = error?.message || error?.toString() || 'Gemini Chat Generate Error';
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Typography } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { InlineError } from '~/common/components/InlineError';
 import { Link } from '~/common/components/Link';
@@ -43,7 +42,7 @@ export function GroqSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='groq-key' label='Groq API Key'
      rightLabel={<>{needsUserKey
        ? !groqKey && <Link level='body-sm' href={GROQ_REG_LINK} target='_blank'>API keys</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={groqKey} onChange={value => updateSetup({ groqKey: value })}
      required={needsUserKey} isError={showKeyError}
@@ -6,7 +6,6 @@ import CheckBoxOutlinedIcon from '@mui/icons-material/CheckBoxOutlined';

 import { getBackendCapabilities } from '~/modules/backend/store-backend-capabilities';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { ExpanderAccordion } from '~/common/components/ExpanderAccordion';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { InlineError } from '~/common/components/InlineError';
@@ -82,7 +81,7 @@ export function LocalAISourceSetup(props: { sourceId: DModelSourceId }) {
      noKey
      required={userHostRequired}
      isError={userHostError}
-      rightLabel={backendHasHost ? <AlreadySet /> : <Link level='body-sm' href='https://localai.io' target='_blank'>Learn more</Link>}
+      rightLabel={backendHasHost ? '✔️ already set in server' : <Link level='body-sm' href='https://localai.io' target='_blank'>Learn more</Link>}
      value={localAIHost} onChange={value => updateSetup({ localAIHost: value })}
    />

@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Typography } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { InlineError } from '~/common/components/InlineError';
 import { Link } from '~/common/components/Link';
@@ -40,7 +39,7 @@ export function MistralSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='mistral-key' label='Mistral Key'
      rightLabel={<>{needsUserKey
        ? !mistralKey && <Link level='body-sm' href={MISTRAL_REG_LINK} target='_blank'>request Key</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={mistralKey} onChange={value => updateSetup({ oaiKey: value })}
      required={needsUserKey} isError={showKeyError}
@@ -3,7 +3,7 @@ import { apiAsync } from '~/common/util/trpc.client';

 import type { IModelVendor } from '../IModelVendor';
 import type { OllamaAccessSchema } from '../../server/ollama/ollama.router';
-import type { VChatContextRef, VChatGenerateContextName, VChatMessageOut } from '../../llm.client';
+import type { VChatMessageOut } from '../../llm.client';
 import { unifiedStreamingClient } from '../unifiedStreamingClient';

 import { FALLBACK_LLM_RESPONSE_TOKENS, FALLBACK_LLM_TEMPERATURE, LLMOptionsOpenAI } from '../openai/openai.vendor';
@@ -42,7 +42,7 @@ export const ModelVendorOllama: IModelVendor<SourceSetupOllama, OllamaAccessSche
  rpcUpdateModelsOrThrow: async (access) => await apiAsync.llmOllama.listModels.query({ access }),

  // Chat Generate (non-streaming) with Functions
-  rpcChatGenerateOrThrow: async (access, llmOptions, messages, contextName: VChatGenerateContextName, contextRef: VChatContextRef | null, functions, forceFunctionName, maxTokens) => {
+  rpcChatGenerateOrThrow: async (access, llmOptions, messages, functions, forceFunctionName, maxTokens) => {
    if (functions?.length || forceFunctionName)
      throw new Error('Ollama does not support functions');

@@ -56,11 +56,6 @@ export const ModelVendorOllama: IModelVendor<SourceSetupOllama, OllamaAccessSche
          maxTokens: maxTokens || llmResponseTokens || FALLBACK_LLM_RESPONSE_TOKENS,
        },
        history: messages,
-        context: contextRef ? {
-          method: 'chat-generate',
-          name: contextName,
-          ref: contextRef,
-        } : undefined,
      }) as VChatMessageOut;
    } catch (error: any) {
      const errorMessage = error?.message || error?.toString() || 'Ollama Chat Generate Error';
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Alert } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { Brand } from '~/common/app.config';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormSwitchControl } from '~/common/components/forms/FormSwitchControl';
@@ -49,7 +48,7 @@ export function OpenAISourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='openai-key' label='API Key'
      rightLabel={<>{needsUserKey
        ? !oaiKey && <><Link level='body-sm' href='https://platform.openai.com/account/api-keys' target='_blank'>create key</Link> and <Link level='body-sm' href='https://openai.com/waitlist/gpt-4-api' target='_blank'>request access to GPT-4</Link></>
-        : <AlreadySet />
+        : '✔️ already set in server'
      } {oaiKey && keyValid && <Link level='body-sm' href='https://platform.openai.com/account/usage' target='_blank'>check usage</Link>}
      </>}
      value={oaiKey} onChange={value => updateSetup({ oaiKey: value })}
@@ -3,7 +3,7 @@ import { apiAsync } from '~/common/util/trpc.client';

 import type { IModelVendor } from '../IModelVendor';
 import type { OpenAIAccessSchema } from '../../server/openai/openai.router';
-import type { VChatContextRef, VChatGenerateContextName, VChatMessageOrFunctionCallOut } from '../../llm.client';
+import type { VChatMessageOrFunctionCallOut } from '../../llm.client';
 import { unifiedStreamingClient } from '../unifiedStreamingClient';

 import { OpenAILLMOptions } from './OpenAILLMOptions';
@@ -60,7 +60,7 @@ export const ModelVendorOpenAI: IModelVendor<SourceSetupOpenAI, OpenAIAccessSche
  rpcUpdateModelsOrThrow: async (access) => await apiAsync.llmOpenAI.listModels.query({ access }),

  // Chat Generate (non-streaming) with Functions
-  rpcChatGenerateOrThrow: async (access, llmOptions, messages, contextName: VChatGenerateContextName, contextRef: VChatContextRef | null, functions, forceFunctionName, maxTokens) => {
+  rpcChatGenerateOrThrow: async (access, llmOptions, messages, functions, forceFunctionName, maxTokens) => {
    const { llmRef, llmTemperature, llmResponseTokens } = llmOptions;
    try {
      return await apiAsync.llmOpenAI.chatGenerateWithFunctions.mutate({
@@ -73,11 +73,6 @@ export const ModelVendorOpenAI: IModelVendor<SourceSetupOpenAI, OpenAIAccessSche
        functions: functions ?? undefined,
        forceFunctionName: forceFunctionName ?? undefined,
        history: messages,
-        context: contextRef ? {
-          method: 'chat-generate',
-          name: contextName,
-          ref: contextRef,
-        } : undefined,
      }) as VChatMessageOrFunctionCallOut;
    } catch (error: any) {
      const errorMessage = error?.message || error?.toString() || 'OpenAI Chat Generate Error';
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Button, Typography } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { InlineError } from '~/common/components/InlineError';
 import { Link } from '~/common/components/Link';
@@ -57,7 +56,7 @@ export function OpenRouterSourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='openrouter-key' label='OpenRouter API Key'
      rightLabel={<>{needsUserKey
        ? !oaiKey && <Link level='body-sm' href='https://openrouter.ai/keys' target='_blank'>your keys</Link>
-        : <AlreadySet />
+        : '✔️ already set in server'
      } {oaiKey && keyValid && <Link level='body-sm' href='https://openrouter.ai/activity' target='_blank'>check usage</Link>}
      </>}
      value={oaiKey} onChange={value => updateSetup({ oaiKey: value })}
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Typography } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { InlineError } from '~/common/components/InlineError';
 import { Link } from '~/common/components/Link';
@@ -43,7 +42,7 @@ export function PerplexitySourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='perplexity-key' label='Perplexity API Key'
      rightLabel={<>{needsUserKey
        ? !perplexityKey && <Link level='body-sm' href={PERPLEXITY_REG_LINK} target='_blank'>API keys</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={perplexityKey} onChange={value => updateSetup({ perplexityKey: value })}
      required={needsUserKey} isError={showKeyError}
@@ -2,7 +2,6 @@ import * as React from 'react';

 import { Alert, Typography } from '@mui/joy';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormSwitchControl } from '~/common/components/forms/FormSwitchControl';
 import { InlineError } from '~/common/components/InlineError';
@@ -49,7 +48,7 @@ export function TogetherAISourceSetup(props: { sourceId: DModelSourceId }) {
      autoCompleteId='togetherai-key' label='Together AI Key'
      rightLabel={<>{needsUserKey
        ? !togetherKey && <Link level='body-sm' href={TOGETHERAI_REG_LINK} target='_blank'>request Key</Link>
-        : <AlreadySet />}
+        : '✔️ already set in server'}
      </>}
      value={togetherKey} onChange={value => updateSetup({ togetherKey: value })}
      required={needsUserKey} isError={showKeyError}
@@ -3,7 +3,7 @@ import { frontendSideFetch } from '~/common/util/clientFetchers';

 import type { ChatStreamingInputSchema, ChatStreamingPreambleModelSchema, ChatStreamingPreambleStartSchema } from '../server/llm.server.streaming';
 import type { DLLMId } from '../store-llms';
-import type { VChatContextRef, VChatFunctionIn, VChatMessageIn, VChatStreamContextName } from '../llm.client';
+import type { VChatFunctionIn, VChatMessageIn } from '../llm.client';

 import type { OpenAIAccessSchema } from '../server/openai/openai.router';
 import type { OpenAIWire } from '../server/openai/openai.wiretypes';
@@ -29,7 +29,6 @@ export async function unifiedStreamingClient<TSourceSetup = unknown, TLLMOptions
  llmId: DLLMId,
  llmOptions: TLLMOptions,
  messages: VChatMessageIn[],
-  contextName: VChatStreamContextName, contextRef: VChatContextRef,
  functions: VChatFunctionIn[] | null, forceFunctionName: string | null,
  abortSignal: AbortSignal,
  onUpdate: (update: StreamingClientUpdate, done: boolean) => void,
@@ -56,11 +55,6 @@ export async function unifiedStreamingClient<TSourceSetup = unknown, TLLMOptions
      ...(llmResponseTokens ? { maxTokens: llmResponseTokens } : {}),
    },
    history: messages,
-    context: {
-      method: 'chat-stream',
-      name: contextName, // this errors if the client VChatContextName mismatches the server z.enum
-      ref: contextRef,
-    },
  };

  // connect to the server-side streaming endpoint
@@ -10,7 +10,6 @@ import StayPrimaryPortraitIcon from '@mui/icons-material/StayPrimaryPortrait';

 import { getBackendCapabilities } from '~/modules/backend/store-backend-capabilities';

-import { AlreadySet } from '~/common/components/AlreadySet';
 import { FormInputKey } from '~/common/components/forms/FormInputKey';
 import { FormLabelStart } from '~/common/components/forms/FormLabelStart';
 import { FormRadioControl } from '~/common/components/forms/FormRadioControl';
@@ -81,7 +80,7 @@ export function ProdiaSettings(props: { noSkipKey?: boolean }) {

    {!backendHasProdia && !!props.noSkipKey && <FormInputKey
      autoCompleteId='prodia-key' label='Prodia API Key'
-      rightLabel={<AlreadySet required={!backendHasProdia} />}
+      rightLabel={backendHasProdia ? '✔️ already set in server' : 'required'}
      value={apiKey} onChange={setApiKey}
      required={!backendHasProdia} isError={!isValidKey}
    />}
@@ -157,7 +157,7 @@ export async function downloadAllConversationsJson() {

  // save file
  await fileSave(blob, {
-    fileName: `big-agi-1_conversations_${window?.location?.hostname || 'all'}_${payload.conversations.length}_${prettyTimestampForFilenames(false)}.agi.json`,
+    fileName: `conversations_${window?.location?.hostname || 'all'}_${payload.conversations.length}_${prettyTimestampForFilenames(false)}.agi.json`,
    // mimeTypes: ['application/json', 'application/big-agi'],
    extensions: ['.json'],
  });
@@ -1,7 +1,7 @@
 {
  "functions": {
-    "api/trpc-node/**/*": {
-      "maxDuration": 30
+    "app/api/trpc-node/**/*": {
+      "maxDuration": 25
    }
  }
 }