Troubleshooting.

Chalie logs every LLM call and gives you a full usage breakdown in the Brain dashboard.

1. Open the Brain dashboard.
2. Click Cognition in the left sidebar, then select Usage.
3. You'll see four stat cards: Total Tokens, Cache Hit Rate, Today (UTC), and Top Model.

Use the time-window buttons at the top (Hour, Day, Week, Month, Lifetime) to filter the data. The stacked bar chart below breaks usage into Chat tokens (your conversations) and Subconscious tokens (background processing like memory decay and pattern extraction).

If you're using a paid provider like OpenAI or Anthropic, check the Today (UTC) card for daily cost tracking. Switching to a local model via Ollama removes token costs entirely — usage is still tracked but there's no monetary cost.

Text-to-speech is built into Chalie using the Kokoro v1.0 voice model — everything runs locally on your device, so your text is never sent to an external service.

Listening to responses: Click the speaker icon below any Chalie message to hear it read aloud. You get play/pause, ±10s skip, and a progress slider. The first playback may take a moment while the voice model loads — subsequent responses are faster.

Disabling voice entirely: Voice is enabled by default during installation. To disable it:

• At install time: add the --disable-voice flag to the installer.
• At runtime: start Chalie with ./run.sh --no-voice.
• To re-enable later, re-run the installer without the flag.

The voice and speed are not currently adjustable through the UI. Chalie's Personality sliders (warmth, mood, expressiveness, curiosity, humour) affect the conversational tone of responses but do not change the TTS voice itself.

The chat window loads 12 messages at a time and caps at 120 messages total. This is by design — it keeps the interface fast. Scroll up near the top of the chat to automatically load older messages in batches of 12.

Your conversations aren't lost. All messages are stored in your local SQLite database. When the context sent to your LLM provider reaches 80% of its token limit, Chalie runs automatic compaction — it summarises older turns into a condensed block so the conversation can continue without losing important context.

Finding older conversations:

• Click the Recall button (star icon in the header) to open a search modal. Type a query like "holiday booking" or "conversation about the project" — Chalie searches across your full history and pinned moments.
• You can also pin important information to long-term memory by saying "Remember this" during a conversation, making it retrievable at any time without scrolling.