Commit Graph

13 Commits

Author SHA1 Message Date
Jeff Emmett 829dd4f642 fix: increase VideoGen timeout to 6 minutes for GPU cold starts
Video generation on RunPod can take significant time:
- GPU cold start: 30-120 seconds
- Model loading: 30-60 seconds
- Generation: 60-180 seconds

Increased polling timeout from 4 to 6 minutes and updated UI
to set proper expectations for users.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-30 18:51:41 -08:00
Jeff Emmett 5cd36c3d3c feat: move Mycelial Intelligence to permanent UI bar + fix ImageGen RunPod API
- Mycelial Intelligence UI refactor:
  - Created permanent floating bar at top of screen (MycelialIntelligenceBar.tsx)
  - Bar stays fixed and doesn't zoom with canvas
  - Collapses when clicking outside
  - Removed from toolbar tool menu
  - Added deprecated shape stub for backwards compatibility with old boards

- ImageGen RunPod fix:
  - Changed from async /run to sync /runsync endpoint
  - Fixed output parsing for output.images array format with base64

- Other updates:
  - Added FocusLockIndicator and UserSettingsModal UI components
  - mulTmux server and shape updates
  - Automerge sync and store improvements
  - Various CSS and UI refinements

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-27 23:57:26 -08:00
Jeff Emmett a8c3988e3f feat: add Ollama private AI integration with model selection
- Add Ollama as priority AI provider (FREE, self-hosted)
- Add model selection UI in Settings dialog
- Support for multiple models: Llama 3.1 70B, Devstral, Qwen Coder, etc.
- Ollama server configured at http://159.195.32.209:11434
- Models dropdown shows quality vs speed tradeoffs
- Falls back to RunPod/cloud providers when Ollama unavailable

Models available:
- llama3.1:70b (Best quality, ~7s)
- devstral (Best for coding agents)
- qwen2.5-coder:7b (Fast coding)
- llama3.1:8b (Balanced)
- llama3.2:3b (Fastest)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-26 14:47:07 -08:00
Jeff Emmett 8ea3490fb4 feat: update mulTmux terminal tool and improve shape utilities
Updates to collaborative terminal integration and various shape
improvements across the canvas.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-26 04:08:08 -08:00
Jeff Emmett 1e68150b60 fix: implement real-time Automerge sync across clients
- Add document ID coordination via server to ensure all clients sync to same document
- Add new endpoints GET/POST /room/:roomId/documentId for document ID management
- Store automergeDocumentId in Durable Object storage
- Add enhanced logging to CloudflareAdapter send() method for debugging
- Add sharePolicy to Automerge Repo to enable document sharing
- Fix TypeScript errors in useAutomergeSyncRepo

This fixes the issue where each client was creating its own Automerge document
with a unique ID, preventing real-time sync. Now all clients in a room use the
same document ID, enabling proper real-time collaboration.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-16 19:45:36 -07:00
Jeff Emmett 4d7b05efa2 update obsidian shape deployment 2025-11-12 16:23:08 -08:00
Jeff Emmett ffef04df50 pin object, fix fathom, and a bunch of other things 2025-11-11 22:32:36 -08:00
Jeff Emmett 1b172d7529 update x & y coordinates 2025-11-10 22:42:52 -08:00
Jeff Emmett 62afed445e final automerge errors on cloudflare 2025-11-10 18:01:36 -08:00
Jeff Emmett f2b05a8fe6 fix final bugs for automerge 2025-11-10 17:58:23 -08:00
Jeff Emmett 663c845cab more updates to convert to automerge 2025-11-10 14:00:46 -08:00
Jeff Emmett f8e4647e1a everything working in dev 2025-11-10 11:06:13 -08:00
Jeff Emmett 719a4eb918 automerge, obsidian/quartz, transcribe attempt, fix AI APIs 2025-09-21 11:43:06 +02:00