Firmware 1.8.0
The biggest SCOUT Vision advancement yet: seven dedicated field scan modes with structured triage cards, danger flags, and confidence ratings. Plus faster performance, smarter hardware use, real-time adaptation, and a deep bug-squashing pass. The current shipping build.
SCOUT Field Modes
SCOUT gains seven dedicated scan modes: General, Plant ID, Mushroom, Bug, Tracks, First Aid, and Read Text. Each returns a card structured for that exact job, key markers, dangerous lookalikes, edible parts and prep, confidence, and field notes.
Fine-Tuned Vision
Sharper identifications and honest confidence on every scan. Hazardous subjects lead with a clear DO NOT EAT / caution verdict and an explicit "if this ID is wrong" risk line. A photo is never treated as a green light to eat.
Faster + Smarter
A performance pass across chat, voice, and SCOUT, plus fuller use of your VRAM and CPU. Routing, context sizing, and workload placement now adapt to your machine in real time, no config required.
Bug-Squashing Pass
A deep stability sweep across the codebase, crash fixes, leak fixes, and cleaner error recovery in chat, voice, and SCOUT, all on top of the 1.7.1 hardening line.
- SCOUT Field Modes: seven dedicated scan modes (General, Plant ID, Mushroom, Bug, Tracks, First Aid, Read Text).
- Structured SCOUT triage cards: verdict banner, key markers, dangerous lookalikes, edible parts + prep, confidence rating, field notes.
- Optional context input (gill color, spore print, where growing) sharpens each identification.
- Fine-tuned vision stack with danger-first safety guardrails on every ID.
- Faster inference across chat, voice, and SCOUT; snappier model loading and switching.
- Better hardware utilization: fuller use of available VRAM and CPU threads.
- Smart adaptation: routing, context size, and workload placement track your hardware in real time.
- Deep bug-squashing pass across the whole runtime.
- SCOUT scan pipeline hardened for the new field modes; structured results render reliably on every scan.
- Stability sweep across chat, voice, and SCOUT: crash fixes, leak fixes, cleaner transient-error recovery.
- Tighter resource cleanup between turns on the faster inference paths.
- Adaptive routing refinements so model choice and context sizing follow real VRAM live.
- All 1.7.1 hardening (TTS mutex coverage, stream timeouts, EOF retries) carried forward intact.