docs: surface Gemini in vision agent node

Make it explicit in the infra diagram that the vision agent worker uses
Gemini to read each screen frame.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuV8W8oNYRsDWKoqK8Mkqc
This commit is contained in:
Ramis
2026-06-28 08:18:53 -07:00
parent f7521fb5df
commit b6447bb12c
+1 -1
View File
@@ -108,7 +108,7 @@ flowchart LR
subgraph DO["DigitalOcean droplet — systemd-supervised"] subgraph DO["DigitalOcean droplet — systemd-supervised"]
WebApi["Caddy + API service<br/>static app · /api · LiveKit tokens"] WebApi["Caddy + API service<br/>static app · /api · LiveKit tokens"]
Agent["Vision agent worker"] Agent["Vision agent worker<br/>Gemini reads each screen frame"]
Coord["Hermes coordinator<br/>detects clashes · intervenes"] Coord["Hermes coordinator<br/>detects clashes · intervenes"]
PyAgent["Live conversation agent<br/>(Python)"] PyAgent["Live conversation agent<br/>(Python)"]
end end