Allow Vertex AI config via env vars

As well as upgrading a number of dependencies this change also makes it possible to define the project and location of your GCP project in environment variables:

export VERTEX_AI_PROJECT="..."
export VERTEX_AI_LOCATION="..."

Full Changelog: genesys-web-messaging-tester-cli-v3.0.2...genesys-web-messaging-tester-cli-v3.0.3

Show placeholder values

When the AI command is run any placeholder values will be shown prior to the conversation starting. This allows the user to see the difference between multiple runs without being overloaded with the entire prompt being presenting.

Example:

NAME: John

Conversation
------------
AI: Hello, my name is John
Chatbot: What would you like to do?
AI: Leave feedback

Full Changelog: genesys-web-messaging-tester-cli-v3.0.1...genesys-web-messaging-tester-cli-v3.0.2

genesys-web-messaging-tester-cli-v3.0.1

What's Changed

• Add Google Vertex AI as AI test provider by @SketchingDev in #164
• Generate prompts with placeholders by @SketchingDev in #170

Full Changelog: genesys-web-messaging-tester-cli-v2.0.3...genesys-web-messaging-tester-cli-v3.0.1

Add wait for convo to close method

Adds a new method to the API to wait for a conversation to close.

Example usage:

await expect(convo.waitForConversationToClose()).resolves.toBeUndefined();

Closes #165

Full Changelog: genesys-web-messaging-tester-cli-v2.0.2...genesys-web-messaging-tester-cli-v2.0.3

Fix loading AI config

Fixes the loading of the config section of the AI commands test file.

Also updates the participant attribute IsTest to IsAutomatedTest to remove confusion with Flow.IsTest

Full Changelog: genesys-web-messaging-tester-cli-v2.0.0...genesys-web-messaging-tester-cli-v2.0.2

Add ability to test chatbots using AI

Adds the ability to test chatbots using ChatGPT.

Once OPENAI_API_KEY is set with the API key for OpenAI then tests are started with the ai command:

web-messaging-tester ai example.yml -id $DEPLOYMENT_ID -r $REGION

AI test definitions take the form of a prompt with phrases used for whether the test is considered a success or failure:

scenarios:
  "Accept survey":
    setup:
      prompt: |
        I want you to play the role of a customer talking to a company's online chatbot. You must not
        break from this role, and all of your responses must be based on how a customer would realistically talk to a company's chatbot.

        To help you play the role of a customer consider the following points when writing a response:
        * Respond to questions with as few words as possible
        * Answer with the exact word when given options e.g. if asked to answer with either 'yes' or 'no' answer with either 'yes' or 'no' without punctuation, such as full stops

        As a customer you would like to leave feedback of a recent purchase of a light bulb you made where a customer service
        rep was very helpful in finding the bulb with the correct fitting.

        If at any point in the company's chatbot repeats itself then say the word 'FAIL'.

        If you have understood your role and the purpose of your conversation with the company's chatbot then say the word 'Hello'
        and nothing else.
      terminatingPhrases:
        pass: ["PASS"]
        fail: ["FAIL"]

Full Changelog: genesys-web-messaging-tester-cli-v1.0.14...genesys-web-messaging-tester-cli-v2.0.0

Retry on failure due to unordered message

Adds logic to handle unordered messages coming from Genesys. Previously this would have resulted in test runs failing, however now the CLI will retry individual tests that have failed as a result of unordered messages.

Read more: unordered-messages.md

Full Changelog: genesys-web-messaging-tester-cli-v1.0.13...genesys-web-messaging-tester-cli-v1.0.14

Add timeout option to CLI

Adds an option to the CLI to customise the amount of time the waitFor... assertions will wait before failing the test.

The option is in seconds and can be defined in two ways:

web-messaging-tester example-pass.yml -id $DEPLOYMENT_ID -r $REGION -p 10 --timeout 20
web-messaging-tester example-pass.yml -id $DEPLOYMENT_ID -r $REGION -p 10 -t 20

Full Changelog: genesys-web-messaging-tester-cli-v1.0.11...genesys-web-messaging-tester-cli-v1.0.13

Add RegEx matching

Add ability to match bot responses by regex:

CLI

config:
  deploymentId: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
  region: xxxx.pure.cloud
scenarios:
  "Accept Survey":
    - say: hi
    - waitForReplyContaining: Can we ask you some questions about your experience today?
    - say: Yes
    - waitForReplyMatching: Thank you! Now for the next question[\.]+

API

  await convo.waitForResponseWithTextMatchingPattern(
    new RegExp(/Thank you! Now for the next question[\.]+/, 'im'),
    {
      timeoutInSeconds: 10,
    },
  );

Full Changelog: genesys-web-messaging-tester-cli-v1.0.10...genesys-web-messaging-tester-cli-v1.0.11

Dynamically load PureCloud Client

Only loads package purecloud-platform-client-v2 when needed. This prevents tests failing due to the package's file watcher starting even when the conversation ID wasn't being associated.