- Use /tmp/persistent-botserver instead of /opt/gbo/data
- Use /tmp/sccache and /tmp/cargo for caches
- Runner has full permissions on /tmp
- Fixes 'Operation not permitted' on chown
- Remove su - and sudo -u which require passwords
- Set HOME=/home/gbuser and USER=gbuser as env vars
- Run git/cargo with proper HOME prefix
- Fix runner hanging on authentication
- Move CI workspace to /home/gbuser/persistent-botserver
- Cache now in /home/gbuser/.cache and /home/gbuser/.cargo
- No more permission conflicts with /opt/gbo/data
- Replace sudo with su - gbuser -c for proper user switching
- Simplify permission handling with chown/chmod as root
- Use su - for all gbuser operations
- Use sudo -u gbuser for all git operations
- Add chown/chmod for cache directories
- Use git pull instead of fetch/reset for cleaner updates
- Ensure consistent gbuser ownership
- Add AzureGPT5Client struct for Responses API
- Add AzureGPT5 to LLMProviderType enum
- Detect provider via azuregpt5 or gpt5 in llm-provider config
- Fix gpt_oss_120b.rs chars.peek() issue
Move logs detalhados de LLM e DriveMonitor de info! para trace!
para reduzir poluição nos logs de produção:
- bot/mod.rs: LLM chunk logs, streaming start, abort
- llm/mod.rs: LLM Request Details, provider creation logs
Estes logs são úteis para debug mas geram muito ruído em produção.
Com trace! só aparecem quando RUST_LOG=trace está configurado.
Aumenta a abrangência da busca em KB para capturar mais contexto
relevante, especialmente em documentos com múltiplas entidades
como listas de ramais.
- inject_kb_context: 5 -> 20 resultados
- think_kb: 10 -> 25 resultados
- search_active_websites: 5 -> 20 resultados
Bug: Using break instead of continue when encountering low-relevance
results caused the search to stop prematurely, missing potentially
relevant chunks in subsequent results.
- Changed break to continue when score < 0.4 in search_single_collection
- Changed break to continue when score < 0.4 in search_single_kb
- Lowered threshold from 0.5 to 0.4 for consistency
This ensures all search results are evaluated, not just those before
the first low-relevance result.
- Broadcast channel allows multiple subscribers for cancellation
- Aborts LLM task when user sends new message
- Properly stops LLM generation when cancelled
- Add active_streams HashMap to AppState to track streaming sessions
- Create cancellation channel for each streaming session
- Cancel existing streaming when new message arrives
- Prevents overlapping responses and improves UX
