bvandeusen
87fcaa6a0d
The frontend hardcoded think=true on every chat send (ChatPanel full + widget variants, KnowledgeView minichat), which defeated the _should_think gate on the backend and made qwen3:14b spend 5-20s on chain-of-thought reasoning for every turn — even "hi". This was the root cause of the warm-path TTFT variance tracked in followup_ttft_variance.md: the logged ttft_ms was really prefill + full thinking phase, bouncing with the depth of the model's reasoning, not with cache or eviction. All three frontend callers now pass think=false and let _should_think be authoritative. The classifier is now a real content-based gate: explicit think_requested=True still forces on as an override (briefing discuss actions, future UI toggles, MCP callers), otherwise messages <80 chars without reasoning keywords skip thinking, messages >=400 chars or containing keywords like why/explain/analyze/debug/review/etc. get it. Generation timing now separately records think_requested, the final think decision, first_token_ms (first any chunk), and thinking_ms (duration of the thinking phase). ttft_ms keeps its existing semantic (first content token) so existing log analysis still works. The timing log line surfaces all four fields so the old "just a big ttft number" ambiguity is gone. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fabled Assistant
A self-hosted second brain and project management application with integrated LLM capabilities. Write, organise, and act on your notes and tasks with the help of a local AI assistant — all running on your own hardware.
Features
Notes and tasks with a Markdown editor, sub-tasks, milestones, and kanban project workspaces. AI chat with streaming responses, RAG over your notes, and tool use (web search, calendar, weather). A daily briefing that digests your tasks, RSS feeds, and weather on a schedule. Knowledge graph, per-user/group sharing, PWA with push notifications, an MCP server for external AI clients, and an Android companion app.
Quick Start
Prerequisites: Docker and Docker Compose. 8 GB+ RAM recommended for LLM inference.
Download docker-compose.quickstart.yml from this repo, then:
# Optional but recommended — set a secret key
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.ymlto enable NVIDIA GPU passthrough.
Development: To build from source, see Development.
Documentation
| Doc | Contents |
|---|---|
| Architecture | Stack, design decisions, data models, key services |
| Configuration | Environment variables, Docker Compose, production setup, security |
| Features | Detailed feature breakdown and keyboard shortcuts |
| Development | Dev workflow, CI/CD, migrations, release process |
| API Keys & MCP | API key management and Fable MCP install guide |
| SSO / OAuth | OIDC setup for Authentik, Keycloak, and other providers |
| API Reference | All REST API endpoints |
| Android App | Flutter companion app architecture and feature status |
License
This project is privately maintained.