Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt

Use this file to discover all available pages before exploring further.

Generated from openapi.json. Start with the Introduction and Quickstart if you are new to the project. Base URL: http://localhost:3000

​
POST /api/chat

Send a chat message and receive a streaming response.

​
Request body

{
  "sessionFile": "<string>",
  "sessionId": "<string>",
  "message": "<string>",
  "model": "<selected model>",
  "mode": "<chat mode>",
  "planAction": "<plan action>",
  "streamingBehavior": "<streaming behavior>"
}

​
Responses

  • 200 — NDJSON stream of chat events. Each line is one of: start, delta, tool, plan, state, steering, text, phase, retry, done, or error.
  • 400 — Bad request.

​
GET /api/chat/models

List available chat models.

​
Responses

  • 200 — { models, selectedModelKey, defaultProvider, defaultModel, defaultThinkingLevel, diagnostics }
  • 500 — { message }

​
GET /api/chat/resources

List available chat resources (skills, prompts, extensions).

​
Responses

  • 200 — { packages, skills, prompts, extensions, themes, agentsFiles, diagnostics }
  • 500 — { message }

​
GET /api/chat/session

Hydrate a chat session by query parameters.

​
Parameters

NameInRequiredDescription
sessionFilequeryNoSession file path
sessionIdqueryNoSession ID

​
Responses

  • 200 — { session, messages, sessionReset }
  • 500 — { message }

​
GET /api/chat/sessions

List all chat sessions.

​
Responses

  • 200 — { sessions }
  • 500 — { message }

​
POST /api/chat/new

Create a new chat session.

​
Responses

  • 200 — { sessionFile, sessionId }
  • 500 — { message }

​
POST /api/chat/resume

Resume an existing chat session.

​
Request body

{
  "sessionFile": "<session file path>",
  "sessionId": "<session ID>"
}

​
Responses

  • 200 — { session, messages, sessionReset }
  • 500 — { message }

​
POST /api/chat/abort

Abort the active chat session.

​
Request body

{
  "sessionFile": "<session file path>",
  "sessionId": "<session ID>"
}

​
Responses

  • 200 — { aborted }
  • 500 — { message }

​
POST /api/chat/question

Answer a question prompt from the assistant.

​
Request body

{
  "sessionFile": "<string>",
  "sessionId": "<string>",
  "toolCallId": "<string>",
  "answer": { "...": "question answer" }
}

​
Responses

  • 200 — { ok, message, mode, planAction }
  • 400 — Bad request.
  • 404 — { ok, message, mode, planAction }

​
GET /api/health

Health check endpoint.

​
Responses

  • 200 — { status }