Skip to content

fix: prepend text message to content blocks in multimodal agent loop #1044

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.

Sign up for GitHub

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

Open
LupoGrigi0 wants to merge 1 commit into
base: main
Choose a base branch
from
+24 −2
Open

fix: prepend text message to content blocks in multimodal agent loop #1044

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 24 additions & 2 deletions crates/openfang-runtime/src/agent_loop.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -279,7 +279,18 @@ pub async fn run_agent_loop(
// Add the user message to session history.
// When content blocks are provided (e.g. text + image from a channel),
// use multimodal message format so the LLM receives the image for vision.
if let Some(blocks) = user_content_blocks {
// The text message is prepended to the blocks so the LLM sees both the
// user's question AND any attached images in a single turn.
if let Some(mut blocks) = user_content_blocks {
if !user_message.is_empty() {
blocks.insert(
0,
ContentBlock::Text {
text: user_message.to_string(),
provider_metadata: None,
},
);
}
session.messages.push(Message::user_with_blocks(blocks));
} else {
session.messages.push(Message::user(user_message));
Expand Down Expand Up @@ -1448,7 +1459,18 @@ pub async fn run_agent_loop_streaming(
// Add the user message to session history.
// When content blocks are provided (e.g. text + image from a channel),
// use multimodal message format so the LLM receives the image for vision.
if let Some(blocks) = user_content_blocks {
// The text message is prepended to the blocks so the LLM sees both the
// user's question AND any attached images in a single turn.
if let Some(mut blocks) = user_content_blocks {
if !user_message.is_empty() {
blocks.insert(
0,
ContentBlock::Text {
text: user_message.to_string(),
provider_metadata: None,
},
);
}
session.messages.push(Message::user_with_blocks(blocks));
} else {
session.messages.push(Message::user(user_message));
Expand Down