The AI provider does not answer
For operators whose chat stays frozen, or whose status dot to the left of the word *Apollia* in the top bar turns amber or red: get a working AI back in under five minutes.
The sidecar runner does not start
The runner (apollia-runner-) is the speech recognition sidecar (STT, whisper). The daemon spawns it at startup and talks to it over HTTP loopback. Local LLM inference does not go through the runner: it is served by the embedded llama-server engine. If it is the local LLM that does not answer, see The AI provider does not answer instead.
An action was refused
For operators whose agent reports a refused action, or seems to have abandoned a task: understand why and unblock what comes next.
An agent is stuck
For operators who see an agent at work with no progress for several minutes: identify the cause and get the work moving again.
Voice dictation transcribes nothing
For operators who press their dictation hotkey without seeing any text appear: get a working transcription back in a few minutes.
Reset Apollia (factory reset)
For operators who want to put Apollia back in its factory state: erase agents, memory, sources, integrations and preferences. This action is irreversible - read every step before acting.