6 Commits

Author	SHA1	Message	Date
CJACK	1286b02247	refactor: remove legacy compatibility configuration and UI components	2026-05-03 04:14:19 +08:00
CJACK	7c0bc9ec0f	feat: implement support for thinking blocks in Gemini API and enable thinking by default for supported models	2026-05-03 01:00:06 +08:00
CJACK	dc5bffdf89	refactor: centralize assistant turn semantics and stream accumulation into new assistantturn and completionruntime packages	2026-05-02 23:28:43 +08:00
王	d407ccb773	perf(streaming): optimize TTFT and reduce buffering latency ... Core changes: - stream.go: New accumulation buffer architecture with scanner goroutine + select loop, MinChars=16, MaxWait=10ms, first-flush-immediate - dedupe.go: Add TrimContinuationOverlapFromBuilder to avoid string copies - claude/stream_runtime_core.go: Integrate toolstream for incremental text - claude/stream_runtime_finalize.go: toolstream flush support - stream_emitter.js: Reduce DeltaCoalescer thresholds (160->16 chars, 80->20ms) - empty_retry: Add thinking-aware empty output detection - Fix reasoning_content leak and finish_reason=null in edge cases - Fix tail content truncation when max_tokens exceeded Tests: sync test expectations with upstream for thinking content	2026-05-02 20:28:30 +08:00
shern-point	4b4f097006	feat: use model-aware prompt counting in Gemini paths ... Preserve Gemini prompt token text during normalization and remove the hardcoded DeepSeek model from native Gemini usage helpers.	2026-04-30 00:46:05 +08:00
CJACK	abc96a37d8	refactor backend API structure	2026-04-26 06:58:20 +08:00