A React Native app for the ultimate thinking partner.

Revert to Haiku 4 (multimodal support confirmed)

Haiku 4 DOES support vision/images. The server crash was due to
a bug in letta-cloud utils.py (now fixed in ea5b1c9a5).

Once server deployed, Haiku will work with images.

🐾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

Changed files
+1 -1
src
utils
+1 -1
src/utils/coAgent.ts
··· 16 16 description: 'Co - A comprehensive knowledge management assistant designed to learn, adapt, and think alongside the user', 17 17 // agentType: Letta.AgentType.LettaV1Agent, // currently pending sleeptime fixes 18 18 // agentType: Letta.AgentType.MemgptV2Agent, 19 - model: 'anthropic/claude-sonnet-4-5-20250929', 19 + model: 'anthropic/claude-haiku-4-5-20251001', 20 20 system: CO_SYSTEM_PROMPT, 21 21 tags: [CO_TAG], 22 22 memoryBlocks: getDefaultMemoryBlocks(),