Sensitive Content Moderation

{
    "point": "app.moderation.input", // Extension point type, fixed as app.moderation.input
    "params": {
        "app_id": string,  // Application ID
        "inputs": {  // Variable values passed by end user, key is variable name, value is variable value
            "var_1": "value_1",
            "var_2": "value_2",
            ...
        },
        "query": string | null  // Current conversation input content from end user, fixed parameter for conversational applications.
    }
}

{
    "point": "app.moderation.input",
    "params": {
        "app_id": "61248ab4-1125-45be-ae32-0ce91334d021",
        "inputs": {
            "var_1": "My SSN is 123-45-6789.",
            "var_2": "My phone number is 123-456-7890."
        },
        "query": "Please help me update my account."
    }
}

{
    "flagged": bool,  // Whether it violates validation rules
    "action": string, // Action: direct_output outputs preset response; overridden overwrites input variable values
    "preset_response": string,  // Preset response (returned only when action=direct_output)
    "inputs": {  // Variable values passed by end user, key is variable name, value is variable value (returned only when action=overridden)
        "var_1": "value_1",
        "var_2": "value_2",
        ...
    },
    "query": string | null  // Overwritten current conversation input content from end user, fixed parameter for conversational applications. (returned only when action=overridden)
}

{
    "point": "app.moderation.output", // Extension point type, fixed as app.moderation.output
    "params": {
        "app_id": string,  // Application ID
        "text": string  // LLM response content. When LLM output is streaming, this is content segmented into 100-character chunks.
    }
}

{
    "point": "app.moderation.output",
    "params": {
        "app_id": "61248ab4-1125-45be-ae32-0ce91334d021",
        "text": "My SSN is 123-45-6789."
    }
}

{
    "flagged": bool,  // Whether it violates validation rules
    "action": string, // Action: direct_output outputs preset response; overridden overwrites input variable values
    "preset_response": string,  // Preset response (returned only when action=direct_output)
    "text": string  // Overwritten LLM response content. (returned only when action=overridden)
}

import { Hono } from "hono";
import { bearerAuth } from "hono/bearer-auth";
import { z } from "zod";
import { zValidator } from "@hono/zod-validator";
import { generateSchema } from '@anatine/zod-openapi';

type Bindings = {
  TOKEN: string;
};

const app = new Hono<{ Bindings: Bindings }>();

// API format validation ⬇️
const schema = z.object({
  point: z.union([
    z.literal("ping"),
    z.literal("app.external_data_tool.query"),
    z.literal("app.moderation.input"),
    z.literal("app.moderation.output"),
  ]), // Restricts 'point' to two specific values
  params: z
    .object({
      app_id: z.string().optional(),
      tool_variable: z.string().optional(),
      inputs: z.record(z.any()).optional(),
      query: z.any(),
      text: z.any()
    })
    .optional(),
});


// Generate OpenAPI schema
app.get("/", (c) => {
  return c.json(generateSchema(schema));
});

app.post(
  "/",
  (c, next) => {
    const auth = bearerAuth({ token: c.env.TOKEN });
    return auth(c, next);
  },
  zValidator("json", schema),
  async (c) => {
    const { point, params } = c.req.valid("json");
    if (point === "ping") {
      return c.json({
        result: "pong",
      });
    }
    // ⬇️ implement your logic here ⬇️
    // point === "app.external_data_tool.query"
    else if (point === "app.moderation.input"){
    // Input check ⬇️
    const inputkeywords = ["input filter test 1", "input filter test 2", "input filter test 3"];

    if (inputkeywords.some(keyword => params.query.includes(keyword))) 
      {
      return c.json({
        "flagged": true,
        "action": "direct_output",
        "preset_response": "The input contains illegal content. Please try a different question!"
      });
    } else {
      return c.json({
        "flagged": false,
        "action": "direct_output",
        "preset_response": "Input is normal"
      });
    }
    // Input check complete 
    }
    
    else {
      // Output check ⬇️
      const outputkeywords = ["output filter test 1", "output filter test 2", "output filter test 3"]; 

  if (outputkeywords.some(keyword => params.text.includes(keyword))) 
    {
      return c.json({
        "flagged": true,
        "action": "direct_output",
        "preset_response": "The output contains sensitive content and has been filtered by the system. Please try a different question!"
      });
    }
  
  else {
    return c.json({
      "flagged": false,
      "action": "direct_output",
      "preset_response": "Output is normal"
    });
  };
    }
    // Output check complete 
  }
);

export default app;