feat(vision): add configurable image analysis model and workspace file editing

- Add VISION_MODEL and VISION_PROVIDER env options with openrouter
  default and provider auto-detection from the model id
- Add /veriavision, /configiavision and /about commands
- Support natural-language editing of files inside workspace/ and a
  /baixar command to download them
- Replace config-based timezone with system-local time detection
- Add module version/author/license metadata
- Document development conventions in new RULES.md and update
  README.md/DEPLOY.md with the new commands and env vars

.env

@@ -39,6 +39,10 @@ MAX_HISTORY_LENGTH=50
 WEB_SEARCH_ENABLED=true
 WEB_SEARCH_MAX_RESULTS=5
 
+# Vision / image analysis model
+VISION_MODEL=meta-llama/llama-4-maverick-17b-128e-instruct
+VISION_PROVIDER=openrouter
+
 # Upload file context max characters sent to AI (0 = no truncation)
 UPLOAD_CONTEXT_MAX_CHARS=0