4b4f87515d
Phase 7: Directory restructuring (messaging/ and tests/)
...
- Create messaging/platforms/ (base, discord, telegram, factory)
- Create messaging/rendering/ (discord_markdown, telegram_markdown)
- Create messaging/trees/ (data, repository, processor, queue_manager)
- Organize tests/ into api/, providers/, messaging/, cli/, config/
- Add backward-compatible re-exports at old locations
- Update handler.py and test_messaging_factory.py imports
- Fix Telegram type hints for TELEGRAM_AVAILABLE=False case
- Fix Python 3 except syntax in discord_markdown
Co-authored-by: Ali Khokhar <alishahryar2@gmail.com >
2026-02-17 02:25:42 +00:00
bfc781e0ed
Phase 4-6: Dead code removal, performance, minor fixes
...
Phase 4:
- Remove legacy SessionRecord, _sessions, _msg_to_session from SessionStore
- Fix hardcoded provider in root endpoint (use settings.provider_type)
- Update session store tests
Phase 5:
- Use list-based string accumulation in ThinkingSegment, TextSegment, ToolCallSegment
- Cache MAX_MESSAGE_LOG_ENTRIES_PER_CHAT at SessionStore init
- Use iterative DFS in MessageTree.get_descendants
Phase 6:
- Add comment for abstract async generator workaround in BaseProvider
- Rename TELEGRAM_EDIT log tags to PLATFORM_EDIT in handler
Co-authored-by: Ali Khokhar <alishahryar2@gmail.com >
2026-02-17 02:01:01 +00:00
72b7e34999
Phase 3: Fix encapsulation violations
...
- Add MessageTree.set_current_task() method
- Update tree_processor to use set_current_task instead of _current_task
- Move nim_settings out of ProviderConfig, pass only to NvidiaNimProvider
- Update api/dependencies and all tests
Co-authored-by: Ali Khokhar <alishahryar2@gmail.com >
2026-02-17 01:58:51 +00:00
539854fe7b
Refactor done using GLM-5
2026-02-15 21:58:03 -08:00
64e5b10612
Refactor done by z-ai/glm5
2026-02-14 18:47:26 -08:00
959d1bdf5b
Phase 5: Encapsulation - Repository and MessageTree API
...
TreeRepository:
- Add has_node(node_id) -> bool
- Add tree_count() -> int
MessageTree:
- Add cancel_current_task() -> bool
- Add drain_queue_and_mark_cancelled() -> List[MessageNode]
- Add reset_processing_state()
- Add current_node_id property
TreeQueueManager:
- Remove _trees and _node_to_tree properties
- add_to_tree: use has_node() and get_tree_for_node()
- get_tree_count: use repository.tree_count()
- cancel_tree: use tree.cancel_current_task(), drain_queue_and_mark_cancelled(), reset_processing_state()
TreeQueueProcessor:
- cancel_current: delegate to tree.cancel_current_task()
Tests: update to use get_tree_count(), has_node(), get_tree_for_node()
Co-authored-by: Ali Khokhar <alishahryar2@gmail.com >
2026-02-15 01:38:35 +00:00
ff22e9baa2
lint
2026-02-08 04:10:57 -08:00
697bc37faf
Upon dequeue the current request immediately displays processing state instead of position 1 waiting
2026-02-08 04:06:41 -08:00
6d8f13d84e
Added feature to update queue positions on telegram when messages are dequeued and added new tests
2026-02-08 04:00:58 -08:00
3f8b9af2c3
improved test suite and fixed error propagation bug in telegram
2026-01-30 14:04:28 -08:00
3b037932d7
refactor to reduce coupling
2026-01-30 13:39:40 -08:00
Cursor Agent