openfang

mirror of https://github.com/RightNow-AI/openfang.git synced 2026-07-30 06:32:17 +00:00

Files

T

Jaber JaberandGitHub ce89d05987 fix(runtime): combine text and image blocks in multimodal user messages (#1043 ) (#1073 )

When an upload supplied image content blocks alongside the user's text, the agent loop pushed only the image blocks and dropped the text. The LLM saw images with no accompanying prompt.

Build the user turn through a single helper that combines text and image blocks into one multimodal message when both are present, and keeps the existing single-mode representation when only one is supplied. Both the streaming and non-streaming paths now share the same builder.

Closes #1043

Made-with: Cursor

2026-04-17 22:47:08 +03:00

openfang-api

fix(api): reject unauth requests from non-loopback by default (#1034 ) (#1071 )

2026-04-17 22:45:58 +03:00

openfang-channels

feat(channels): optional agent name prefix on outbound messages (#980 ) (#1072 )

2026-04-17 22:47:04 +03:00

openfang-cli

fix(cli): config get returns base_url from default_model (#905 ) (#1076 )

2026-04-17 22:46:08 +03:00

openfang-desktop

bump v0.5.9