-
Notifications
You must be signed in to change notification settings - Fork 7
Feature/add file support for instagram #186
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: develop
Are you sure you want to change the base?
Changes from all commits
9014f6b
5222577
54def41
d0199b6
698747d
bb4c1b3
ac4e5cd
7227653
c0b334b
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change | ||
|---|---|---|---|---|
| @@ -1,13 +1,16 @@ | ||||
| import base64 | ||||
| import hashlib | ||||
| import hmac | ||||
| import logging | ||||
| import mimetypes | ||||
|
||||
| import mimetypes |
Copilot
AI
Dec 26, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The logic on lines 246-249 has the same issue as in the Messenger integration. When there's only one request and it's an AgentRequestFile or AgentRequestImage (no text), the code will try to call service.run(message_text) where message_text is an empty string. Consider using run_multi for all cases where attachments are present.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The manual session management code directly accesses and manipulates the OpenAI session's internal state using
add_items. This approach bypasses the normal session management flow and could lead to inconsistencies. The comment mentions "OpenAI cannot handle session" for multimodal inputs, but then manually adds items to the session anyway. This workaround needs better documentation explaining why it's necessary and what the limitations are, or consider using a more robust approach through the OpenAI SDK's proper APIs.