docs(scribe): rewrite features/api-reference/README to the current product

Resolves issue #1778 — the docs still described the pre-pivot product (in-app
LLM chat, journal, weather, web-research, push, model management) plus the
just-removed calendar/entities.

- features.md: full rewrite to the actual surfaces — notes, tasks & issues,
  projects/milestones (kanban), systems, rules & rulebooks, stored processes,
  search + knowledge-injection, graph, MCP + the Claude Code plugin, sharing,
  export/backup (v4), OIDC. Dropped chat/journal/weather/web-research/calendar/
  push/workspace/model-management; fixed the shortcuts + settings tables.
- api-reference.md: rewrite to the real endpoint surface (verified from the
  route decorators) — added Knowledge/Rulebooks/Systems/Plugin/Trash/Dashboard
  and the milestone/system sub-routes; removed Chat/Journal/Push/Quick-Capture/
  Images/assist/models.
- README.md: Quick Start no longer tells users to pull an Ollama model or size
  RAM/GPU "for LLM inference" — points at the API key + plugin instead.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BPtbSzA4JLMAKgFZ8VTg7Q

README.md

@@ -8,7 +8,7 @@ Notes and tasks with a Markdown editor, sub-tasks, milestones, issues, and kanba
 
 ## Quick Start
 
-**Prerequisites:** Docker and Docker Compose. 8 GB+ RAM recommended for LLM inference.
+**Prerequisites:** Docker and Docker Compose. No GPU or local model needed — Claude is the sole assistant, reached over MCP.
 
 Download [`docker-compose.quickstart.yml`](docker-compose.quickstart.yml) from this repo, then:
 
@@ -19,9 +19,7 @@ export SECRET_KEY=your-random-secret-here
 docker compose -f docker-compose.quickstart.yml up -d
 ```
 
-Open `http://localhost:5000`. The first user to register becomes admin. Go to **Settings → General** to pull an LLM model — `qwen3:8b` or `llama3.1:8b` are good starting points.
-
-> **GPU:** Ollama runs CPU-only by default. See the comments in `docker-compose.quickstart.yml` to enable NVIDIA GPU passthrough.
+Open `http://localhost:5000`. The first user to register becomes admin. To connect Claude, create an API key under **Settings → API Keys** and install the Claude Code plugin — see [API Keys & MCP](docs/api-keys-and-mcp.md).
 
 > **Development:** To build from source, see [Development](docs/development.md).