Hacktoberfest 2026：維護者為十月標記出來的 issue，仍然開放、適合新手。 瀏覽 Hacktoberfest issue

Chatbot Engine: Dynamic, configurable conversations

未關閉
  • 哪裡不對？
#1,230 0 則留言 0 個 reaction 已指派 1 人 在 GitHub 檢視

維護者通常 2 天內回覆

@Ayush8923 已經在處理了。

開始於 2026年10月5日。

評估

這個 Issue 還沒有評估資料。

描述

Describe the current behavior
As a first step (#1210), we built a read-only /agent endpoint: a single, static LangGraph agent that answers natural-language questions about a tenant own eval runs, datasets, etc. It is "static" in two senses:

  • The graph itself is fixed in code, one agent_node / tool_executor_node loop, hand-written, the same for every caller.
  • The toolset is a fixed, hand-written registry of read-only GET wrappers (list_evaluation_runs, get_collection, etc.), the agent picks which of these to call and in what order, but the set of available tools and the conversation shape never change per request.

That's the right shape for "ask a question, get an answer" over existing data. It is not the right shape for the next use case below, where the conversation itself needs to be admin-configurable, stateful across many turns/days, and able to take write-side actions (set a reminder, etc.), not just read.

Describe the enhancement you'd like
We want to generalize from "one static read-only agent" to a dynamic, admin-configurable conversational bot flow engine, the foundation for use cases like NGO onboarding on Glific:

When an NGO onboards, today they fill out a static form. We want to replace this with a chatbot that asks a configurable sequence of questions one at a time, analyzes each answer, and, if the user doesn't answer a question, retries up to an admin-configured count before applying an admin-configured fallback (skip the question, end the conversation, escalate, etc.). The flow (questions, retry/skip rules, branching) must be fully dynamic/admin-authored, not hand-coded per bot. The bot also has access to an admin-selectable catalogue of tools (Recurring Reminder, One-off Reminder, Delete Reminder, etc.) that it can call autonomously, the same way #1210's agent calls read-only Kaapi endpoints.

we define the overall direction here at a high level, then detail only Stage 0. Later stages are scoped after learnings from the previous one, so we keep room to pivot.

Stage Description
Stage 0 Config-driven question sequence, retry/skip logic, simple per-node tool selection from a fixed catalogue.
Stage 1 TBD based on Stage 0 learnings.
Stage 2+ TBD (scheduling, reminders, branching, admin UI).

Stage 0: detailed spec

Goal: admin authors a flow as a linear sequence of nodes. The bot asks questions one at a time over WhatsApp/Glific, retries on non-answers, and at designated steps can call tools the admin selected when authoring that node. Session state is persisted across turns (conversations can span hours/days).

Example config blob
{
  "nodes": [{
    "id": "intake",
    "type": "collector",
    "goal": "Onboard a new beneficiary warmly; ask one thing at a time, in their language.",
    "fields": [
      {"key": "location", "description": "District and state", "type": "string", "required": true, "max_asks": 2, "on_exhausted": "skip"},
      {"key": "occupation", "description": "Current work", "type": "string", "required": false, "max_asks": 2, "on_exhausted": "skip"},
      {"key": "consent", "description": "Agrees to be contacted", "type": "boolean", "required": true, "max_asks": 2, "on_exhausted": "end_conversation"}
    ],
    "tools": ["end_session"],
    "llm": {"config_id": "...", "version": 3}
  }],
  "edges": []
}

Reference: Open Chat Studio (OCS)

主要語言
Python
星號
18
分支
11
平均合併
3 天 20 小時
30 天內合併 PR
14

環境準備

從這裡開始

  1. 先讀完整個 Issue，再讀專案的貢獻指南。
  2. 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
  3. Fork 儲存庫，在一個分支上完成修改。
  4. 送出 Pull Request，並在描述裡引用這個 Issue 編號。

ProjectTech4DevAI/kaapi-backend 的其他 Issue

查看 ProjectTech4DevAI/kaapi-backend 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。