Add image input to the AI Coach (multimodal)

[saksham2001]

Summary

Lets users attach a photo to a coach message, sent alongside text to whichever provider is active: OpenAI (Responses), Gemini (generateContent), or OpenRouter (Chat Completions). Off by default behind a new Settings toggle.

• Providers: images enter at the one canonical request builder; each adapter translates to its own shape (input_image / inlineData / image_url). Text content stays a String, so existing text + tool-call flows are untouched.
• Storage: images compressed to JPEG in Documents/coach_attachments/; CoachMessage stores only a small JSON ref (additive SwiftData field).
• UI: camera button in the composer (only when enabled) → staged thumbnail → image rendered in the user bubble. Image-only sends allowed.
• Tests: 172 existing tests still pass; 7 new tests cover each provider's image shape + text-only regression.

Related issues

#27

Type of change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 📟 New / improved wearable support (BLE driver layer)
• 🤖 Coach / LLM change (tools, prompts, orchestration)
• 🎨 UI / DesignSystem change
• 🧹 Refactor / chore (no behavior change)
• 📝 Docs only
• ⚠️ Breaking change (existing data, settings, or APIs change)

How was this tested?

• Added / updated unit tests (PulseLoopTests)
• Ran the test suite locally (⌘U in Xcode)
• Tested on a physical device with a real ring — model:
• Tested with demo data (-seedDemo YES, no hardware)
• N/A (docs / non-code change)

Privacy & data

• This change does not send health data off-device without explicit user action.
• No secrets, API keys, or personal data are committed.
• N/A

Screenshots / recordings

Checklist

• My code follows the project's style (SwiftLint passes).
• I ran the tests and they pass.
• I updated docs / README where relevant.
• I read the Contributing guide.