{{define "content"}} {{$m := .Data.Mind}}{{$c := .Data.Conversation}}

conversations › {{$c.Channel}}{{if $c.Person}} · {{$c.Person}}{{end}}{{if $c.Project}} · {{$c.Project}}{{end}}

{{if $c.Title}}{{$c.Title}}{{else}}Conversation with {{$m.DisplayName}}{{end}}

connecting…{{if not .Data.LLM}}no respond model{{end}}
    {{range .Data.Messages}}
  1. {{.Actor}} {{.CreatedAt.Local.Format "15:04:05"}}{{if .EventID}} event{{end}}{{if .LLMCallID}} model{{else if eq .Role "mind"}} state{{end}}
    {{.Content}}
    {{if .Intent}}
    why this reply
    {{pretty .Intent}}
    {{end}}
  2. {{else}}
  3. Say something.
  4. {{end}}
{{if .Principal.User.Role.AtLeast "operator"}}
{{end}}

How a reply forms

  1. message → observation
  2. perception: intent, entities, claims
  3. recall + workspace competition
  4. intent built from beliefs and memories
  5. wording by the respond model, or a direct rendering of state
  6. response_generated with cited evidence

Open “why this reply” under any answer, or its event, to see the evidence.

Try asking

    {{range .Data.Suggestions}}
  • “{{.}}”
  • {{end}}
{{end}}