scheduling
diapason.engine.scheduling
¶
Admission to Ollama: interactive work precedes pending housekeeping.
This coordinates this process only. An inference already sent to Ollama is never pretended to be preemptible, nor are other programs' requests covered.
BackgroundStopped
¶
Bases: RuntimeError
The memory service stopped before its request reached Ollama.
InferenceQueueTimeout
¶
Bases: RuntimeError
The local admission queue timed out, not the Ollama connection.
InferenceScheduler
¶
interactive_turn()
¶
Protect the whole chat, including gaps between tools and continuations.