Exclude openai_codex alongside github_copilot from generated config,
filter OAuth-only providers out of the onboarding wizard, and clarify in
README that OAuth login stores session state outside config. Also unify
the GitHub Copilot login command spelling and add regression tests.
Made-with: Cursor
- wire tools.exec.enable and deny_patterns into the current AgentLoop
- preserve the current WebSearchTool config-based registration path
- treat deny_patterns=[] as an explicit override instead of falling back
to the default blacklist
- add regression coverage for disabled exec registration and custom deny
patterns
Made-with: Cursor
Remove the in-progress reaction (reactEmoji) and optionally add a
done reaction (doneEmoji) when the final response is sent, so users
get visual feedback that processing has finished.
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
Add native Ollama support so local models (e.g. nemotron-3-nano) can be
used without an API key. Adds ProviderSpec with ollama_chat LiteLLM
prefix, ProvidersConfig field, and skips API key validation for local
providers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move consolidation policy into MemoryConsolidator, keep backward compatibility for legacy config, and compress history by token budget instead of message count.
- Add `enable` flag to `ExecToolConfig` to conditionally register the tool.
- Add `deny_patterns` to allow users to override the default command blacklist.
- Remove `allow_patterns` (whitelist) to maintain tool flexibility.
- Fix initialization logic to properly handle empty list (`[]`), allowing users to completely clear the default blacklist.
- Add group_policy config: 'open' (default) or 'mention'
- 'open': Respond to all group messages (backward compatible)
- 'mention': Only respond when @mentioned in any group
- Auto-detect bot mentions by pattern matching:
* If open_id configured: match against mentions
* Otherwise: detect bot by empty user_id + ou_ open_id pattern
- Support @_all mentions
- Private chats unaffected (always respond)
- Clean implementation with minimal logging
docs: update Feishu README with group policy documentation
Major changes:
- Replace message-count-based memory window with token-budget-based compression
- Add max_tokens_input, compression_start_ratio, compression_target_ratio config
- Implement _maybe_compress_history() that triggers based on prompt token usage
- Use _build_compressed_history_view() to provide compressed history to LLM
- Refactor MemoryStore.consolidate() -> consolidate_chunk() for chunk-based compression
- Remove last_consolidated from Session, use _compressed_until metadata instead
- Add background compression scheduling to avoid blocking message processing
Key improvements:
- Compression now based on actual token usage, not arbitrary message counts
- Better handling of long conversations with large context windows
- Non-destructive compression: old messages remain in session, but excluded from prompt
- Automatic compression when history exceeds configured token thresholds
- Remove trailing whitespace and normalize blank lines
- Unify string quotes and line breaks for long lines
- Sort imports alphabetically across modules
Xubin RenandXubin Ren
Harvey MackieandXubin Ren
Sihyeon JangandXubin Ren
lihuaandXubin Ren
gaoyiman
Jerome Sonnet (letzdoo)andClaude Opus 4.6
angleyanalbedo
chengyongru
Zek
VITOHJL
Kunal Karmakar
ouyangwulin
gaoyimanandGitHub
worenidewen
Joel Chan
Sense_wang
Jack LuandGitHub
JK_Lu