API and streaming

Fleet Reasoner ships as a FastAPI service in qlaw/serve.py. Start it locally:

uv run uvicorn qlaw.serve:app

Configuration is set once at startup with configure_research() — dspy.configure has an owner-thread rule and must not be called inside request handlers. Use dspy.context for per-request overrides.

Endpoints

Endpoint	Purpose
`POST /seed`	Inception: prompt → graph with `ROOT` plus the first decomposition layer.
`POST /engine`	One step of the reasoning cycle: `(graph, active_node_id, action)` → expanded graph.
`POST /chat/stream`	SSE from the Qlaw chat agent (`dspy.streamify`), status events plus a `done` frame with the answer and post-chat graph.
`GET /config`	Runtime config: `{"model": "..."}` from `OPENAI_MODEL`. Never credentials.

`POST /seed`

{ "prompt": "Launch a sustainable fashion brand" }

Returns the serialized GraphState. Errors map through the DSPy 3.3.0 exception hierarchy (see “Error mapping” below).

`POST /engine`

{
  "nodes": { "root": { "...": "..." } },
  "root_id": "root",
  "active_node_id": "root",
  "action": null
}

Returns:

{
  "graph": { "...": "..." },
  "lens": "decompose",
  "outputs": { "sub_nodes": [ /* ... */ ] }
}

outputs uses Prediction.toDict() — DSPy 3.3.0 has no Prediction.model_dump(). max_depth is not a request field. It is a constructor argument on ReasoningEngine and ReasoningLoop.

`POST /chat/stream`

{
  "session_id": "<opaque per-tab id>",
  "nodes": { "root": { "...": "..." } },
  "root_id": "root",
  "question": "What matters most for the brand-identity component?",
  "history": [],
  "active_node_id": "root"
}

The server maps session_id to a bounded, independently locked QlawChat in ChatSessionStore. Missing or expired entries start a fresh conversation. history is used only to bootstrap a fresh instance for HTTP compatibility. Later turns use the instance-owned history.

SSE frames

event: status
data: {"event": "status", "message": "run_lens.start"}

event: done
data: {
  "event": "done",
  "answer": "...",
  "termination_reason": "submit",
  "graph": { "...": "..." }
}

Non-Prediction yields are StatusMessage and stream events. ChatStatusProvider turns tool start and end into compact status lines.
ReActV2 emits its final answer as submit tool-call arguments, so token-level streaming of answer does not apply. Surface tool activity as status events and the complete answer in the done frame.
The done frame carries the final graph. Chat tools expand the graph during the agent run, so the client must adopt done.graph.

`GET /config`

Returns {"model": "..."} from OPENAI_MODEL (default deepseek-v4-flash). Credentials are never exposed. The web client reads this to display the active model id.

Error mapping

DSPy 3.3.0 normalizes LM errors under dspy.LMError. Catch subclasses and map:

Exception	HTTP status
`dspy.LMRateLimitError`	`429`
`dspy.ContextWindowExceededError`	`413`
`dspy.LMError` (base and others)	`502`

For the streamed /chat/stream route, the response has already started when an error occurs mid-stream. HTTPException is not an option there — the generator catches the exception and emits:

{"event": "error", "status": 429, "message": "Rate limited: ..."}

Streaming configuration

Relevant DSPy settings:

dspy.configure(allow_tool_async_sync_conversion=True) — allow sync tool implementations in async paths.
async_max_workers=... — control async concurrency.
dspy.asyncify(fn) — wrap a sync function for the async path.

dspy.stream does not exist in 3.3.0. Streaming goes through dspy.streamify(program, status_message_provider=...), which returns an async generator ending with the final dspy.Prediction.

Fleet-RLM

Fleet Pi

GEPA Omni

Qredence Skills

Fleet Reasoner

Qredence Plugins

Endpoints

`POST /seed`

`POST /engine`

`POST /chat/stream`

SSE frames

`GET /config`

Error mapping

Streaming configuration

​Endpoints

​POST /seed

​POST /engine

​POST /chat/stream

​SSE frames

​GET /config

​Error mapping

​Streaming configuration

Endpoints

`POST /seed`

`POST /engine`

`POST /chat/stream`

SSE frames

`GET /config`

Error mapping

Streaming configuration