3 Commits

Author	SHA1	Message	Date
Yufeng He	2cb6c84eeb	feat: context token counting support for multimodal content (images, audio, and chain-of-thought) (#6596) ... EstimateTokenCounter 之前只计算 TextPart，完全忽略 ImageURLPart、 AudioURLPart 和 ThinkPart。多模态对话中图片占 500-2000 token， 不被计入会导致 context 压缩触发过晚，API 先报 context_length_exceeded。 改动： - ImageURLPart 按 765 token 估算（OpenAI vision 低/高分辨率中位数） - AudioURLPart 按 500 token 估算 - ThinkPart 的文本内容正常计算 - 10 个新测试覆盖各类型单独和混合场景 Co-authored-by: Yufeng He <40085740+universeplayer@users.noreply.github.com>	2026-03-19 17:25:49 +08:00
Soulter	418f05f6e4	fix: tests	2026-03-03 16:06:49 +08:00
Soulter	241f1c26d3	feat: context compress (#4322) ... * feat: context compressor Co-authored-by: kawayiYokami <289104862@qq.com> * Add comprehensive tests for ContextManager and ContextTruncator - Implemented a full test suite for ContextManager covering initialization, message processing, token-based compression, and error handling. - Added tests for ContextTruncator focusing on message fixing, truncation by turns, dropping oldest turns, and halving. - Ensured that both test suites validate edge cases and maintain expected behavior with various message types, including system and tool messages. * feat: add MockProvider for LLM compression tests * chore: remove lock * ruff fix * fix * perf * feat: enhance context compression with token tracking and logging * feat: update logging for context compression trigger * feat: implement context compression logic with dynamic threshold and token tracking * fix: reorder import statements for consistency * feat: add token_usage tracking to conversations and update related processing logic --------- Co-authored-by: kawayiYokami <289104862@qq.com>	2026-01-05 17:26:10 +08:00