LocalAI

0 Fork 0

mirror of https://github.com/mudler/LocalAI.git synced 2026-11-06 04:23:15 -05:00

Files

T

Ettore Di Giacinto 9ee1407989 feat(studio): load context files and memory_read in every chat

Each turn the chat prompt gets the agent profile and the indexes of the
registered context sources, after the persona and before the skill index.
The scope of a source is derived from the chat record: the saved agent, and
the binding when a connector started the chat. The text is the same at each
turn, so the transcript does not grow, and it feeds the refresh key so the
harness restarts only when a file changes.

memory_read reads a topic next to an index as the user, outside the chat
fence. A scoped agent reads its own notes and the user notes and gains no
access to the files. The service exposes ContextSources and
SetContextWriter so other parts of the host can register a source or plug in
the save path.

Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-11-03 09:28:57 +00:00

application

test(chats): clarify configured timeout success

2026-11-03 09:21:06 +00:00

backend

feat(realtime): LFM3-Audio speech-to-speech on llama.cpp, remove liquid-audio (#12958 )

2026-10-29 22:06:41 +01:00

cli

fix(cli): name the P2P resource limits flag --p2p-enable-limits

2026-11-03 09:21:07 +00:00

clients

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087 )