Fleet Reasoner quickstart

Get the Qlaw reasoning engine running locally in a few minutes.

Prerequisites

Python 3.10 or newer.
uv for dependency management.
Node.js and pnpm for the tldraw web frontend.
An OpenAI-compatible Chat Completions endpoint and API key.

1. Install

uv sync --extra dev       # pytest / ruff / mypy; add --extra numpy for MIPROv2
cp .env.example .env      # OPENAI_BASE_URL / OPENAI_API_KEY / OPENAI_MODEL

Nothing auto-loads .env. Run any LM-hitting command with uv run --env-file .env. Fleet Reasoner uses one model across all tiers: deepseek-v4-flash by default, addressed as openai/<model> through the OpenAI-compatible endpoint. Any OpenAI-compatible model id works via OPENAI_MODEL.

2. Verify without an API key

Stub-LM tests exercise every signature, Refine loop, and ReActV2 submission without needing credentials:

uv run pytest -q

tests/helpers.py provides StubLM and field_response(...). Every output field must be present in a stubbed response, including reasoning (ChainOfThought adds it).

3. Serve the engine

uv run uvicorn qlaw.serve:app

The FastAPI service exposes:

POST /seed — prompt → graph with ROOT plus the first decomposition layer.
POST /engine — one reasoning step: (graph, active_node_id, action) → expanded graph.
POST /chat/stream — SSE: status and tool events, then a done event with the answer and post-chat graph.
GET /config — the active model id (no credentials) for the web client.

4. Run the web frontend

cd web
pnpm install
pnpm dev                                # http://localhost:5173
pnpm exec tsc --noEmit && pnpm exec vitest run

web/src/state/graphStore.ts (zustand) holds the canonical GraphState, and web/src/canvas/sync.ts is the only writer of qlaw shapes and arrows. Set VITE_API_BASE in web/.env.local if the API port differs from http://localhost:8000.

5. Compile and evaluate

The compile pipeline turns the zero-shot engine into optimized artifacts under artifacts/:

uv run python -m scripts.compile --optimizer mipro   # compile lenses + engine
uv run python -m scripts.evaluate                    # eval harness -> eval_results.json
uv run ruff check . && uv run mypy qlaw              # lint + typecheck

For bounded GEPA prompt optimization of the core lenses (default strategy --strategy omni — explore all engines on a small slice, continue from the validation winner), use the wrapper:

./scripts/optimize --lens decompose --strategy omni --engines gepa --max-evals 44

The wrapper installs the unreleased gepa OA API at run time (DSPy pins gepa 0.1.1). The gepa engine’s proposals and evaluation both use the .env model by default. Pass --codex-model to switch to the native Codex agent proposer.

Next steps

Architecture — the three tiers and DSPy 3.3.0 primitives that power them.
Lenses — one optimizable module per agent.
Engine and router — the reasoning cycle as one dspy.Module.
Chat and tools — the multi-turn ReActV2 Co-Pilot with lenses as tools.
API and streaming — the FastAPI endpoints, SSE frames, and error mapping.
Optimization and evaluation — compile pipeline, trainsets, and metrics.
Gotchas — DSPy 3.3.0 pitfalls that will cost you time.

Fleet-RLM

Fleet Pi

GEPA Omni

Qredence Skills

Fleet Reasoner

Qredence Plugins

Prerequisites

1. Install

2. Verify without an API key

3. Serve the engine

4. Run the web frontend

5. Compile and evaluate

Next steps

​Prerequisites

​1. Install

​2. Verify without an API key

​3. Serve the engine

​4. Run the web frontend

​5. Compile and evaluate

​Next steps

Prerequisites

1. Install

2. Verify without an API key

3. Serve the engine

4. Run the web frontend

5. Compile and evaluate

Next steps