davsclaus opened a new pull request, #24362: URL: https://github.com/apache/camel/pull/24362
## Summary - Adds a toggleable AI usage stats view inside the TUI AI panel (Ctrl+U) - Tracks per-LLM-call metrics: model, provider, input/output/total tokens, latency, stop reason - Stats view shows: summary line, per-model table, and bar chart of tokens per question turn - Fixes locale-dependent token formatting (comma vs dot as decimal separator) This is a prototype for [CAMEL-23861](https://issues.apache.org/jira/browse/CAMEL-23861) — using `camel ask` token data as a proof of concept for GenAI observability in the TUI. Later, when langchain4j route observability lands, the same UI patterns can show production AI usage from running Camel applications. ## Test plan - [ ] Run `camel tui monitor --mcp`, open AI panel (F8), ask a few questions - [ ] Press Ctrl+U to toggle usage stats view — verify summary, per-model table, and chart - [ ] Press Ctrl+U again to return to chat — verify conversation is intact - [ ] Verify token counts use dot (not comma) as decimal separator _Claude Code on behalf of Claus Ibsen_ 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
