We provided form with from_intent slot mapping in domain file. forms: form_question: required_slots: answer1: - type: from_intent value: yes intent: yes no_intent: [no, greet] answer2: - type: from_intent value: yes intent: yes no_intent: [no, greet] answer3: - type: from_intent value: yes intent: yes no_intent: [no, greet] answer4: - type: from_intent value: yes intent: yes no_intent: [no, greet] answer5: - type: from_intent value: yes intent: yes no_intent: [no, greet]
If during the filling of the form an intent is sent, which leads not to the history, but to the rule, then the ActionExecutionRejected event is called, after which the request for form validation is again executed.
In stories, there is no problem with calling form validation again.
2021-07-28 08:15:56 DEBUG rasa.core.policies.ensemble - Sender: ‘’ → Execution of ‘form_question’ was rejected. Setting its confidence to 0.0 in all predictions.
2021-07-28 08:15:56 DEBUG rasa.core.policies.ensemble - Made prediction using user intent.
2021-07-28 08:15:56 DEBUG rasa.core.policies.ensemble - Added DefinePrevUserUtteredFeaturization(False) event.
2021-07-28 08:15:56 DEBUG rasa.core.policies.ensemble - Sender: '’ → Predicted next action using policy_0_RulePolicy.
2021-07-28 08:15:56 DEBUG rasa.core.processor - Sender: '’ → Predicted next action ‘utter_no_stories’ with confidence 1.00.
2021-07-28 08:15:56 DEBUG rasa.core.nlg.callback - Requesting NLG for utter_no_stories from https://.
2021-07-28 08:15:56 DEBUG rasa.core.processor - Sender: ‘’-> Policy prediction ended with events ‘[<rasa.shared.core.events.DefinePrevUserUtteredFeaturization object at 0x000001835C7422B0>]’.
2021-07-28 08:15:56 DEBUG rasa.core.processor - Sender: '’-> Action ‘utter_no_stories’ ended with events ****
2021-07-28 08:15:56 DEBUG rasa.core.policies.rule_policy - Current tracker state: ****
2021-07-28 08:15:56 DEBUG rasa.core.policies.rule_policy - Predicted loop ‘form_question’ by overwriting ‘action_listen’ predicted by general rule.
2021-07-28 08:15:56 DEBUG rasa.core.policies.ted_policy - TED predicted ‘action_listen’ based on user intent.