feat: forward transcribed text to AI processor

[thiagobodevan]

Passa o conteúdo de ranscribed_text do webhook do CRM para o campo principal MessageContent, resolvendo o problema onde áudios transcritos não chegam à IA na camada do Processor.

Summary by Sourcery

Forward transcribed audio text from CRM webhooks into the main message content so it reaches the AI processor layer.

New Features:

• Add support for a transcribed_text field in message events received from the CRM webhook.
• Append transcribed audio text to the primary message content before processing.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

This PR ensures that any transcribed audio text coming from the CRM webhook is appended to the main message content so it reaches the AI processor, by introducing a new field on MessageEvent and wiring it into the processing pipeline.

Sequence diagram for forwarding transcribed audio to AI processor

sequenceDiagram
  actor CRMWebhook
  participant pipelineService
  participant AIProcessor

  CRMWebhook ->> pipelineService: Process(ctx, event)
  alt [event.TranscribedText != ""]
    pipelineService ->> pipelineService: append TranscribedText to MessageContent
  end
  pipelineService ->> AIProcessor: invoke AI processing

Loading

File-Level Changes

Change	Details	Files
Propagate transcribed audio text from CRM into the main message content processed by the pipeline.	Add a TranscribedText field to MessageEvent with JSON serialization support On message processing, when TranscribedText is non-empty, append it to MessageContent with a clear separator and label so the AI processor can consume it	pkg/pipeline/model/pipeline.go pkg/pipeline/service/pipeline_service.go

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider centralizing the formatting of transcribed audio (e.g., the "[Transcrição do Áudio]" label and separators) in a helper or constant so it is easier to reuse and maintain if the format or localization changes.
• By mutating event.MessageContent in Process, you’re mixing raw and derived fields; if other consumers rely on the original message content, it may be clearer to either construct a derived payload locally or add a dedicated combined field instead of overwriting MessageContent.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider centralizing the formatting of transcribed audio (e.g., the "[Transcrição do Áudio]" label and separators) in a helper or constant so it is easier to reuse and maintain if the format or localization changes.
- By mutating `event.MessageContent` in `Process`, you’re mixing raw and derived fields; if other consumers rely on the original message content, it may be clearer to either construct a derived payload locally or add a dedicated combined field instead of overwriting `MessageContent`.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}