Hacktoberfest 2026：メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

Chatbot Engine: Dynamic, configurable conversations

オープン
  • 何か問題がありますか？
#1,230 コメント 0 件 リアクション 0 件 担当者 1 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

@Ayush8923 がすでに取り組んでいます。

2026年10月5日 から。

評価

この issue はまだ評価されていません。

説明

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)

主要言語
Python
スター
18
フォーク
11
平均マージ
3日 2時間
マージ済み PR（30日）
7

環境構築

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

ProjectTech4DevAI/kaapi-backend のほかの issue

ProjectTech4DevAI/kaapi-backend の issue をすべて見る

似ている issue

Python の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。