master

xujing99feat: implement per-command process groups with registry for reliable cleanup

a543df7c创建于 15 天前历史提交

文件	最后提交记录	最后更新时间
auth	feat: initial commit with core features	2 个月前
factory	feat(llm-client): thread cached input tokens through Usage into trace spans Account for cache-read tokens end to end: - Usage carries cached_tokens (OpenAI prompt_tokens_details.cached_tokens; Anthropic cache_read_input_tokens), threaded into LLM_CALL / TURN trace spans. - Anthropic marks cache_control ephemeral on the stable system-prefix block ONLY, never the volatile Context block, so the breakpoint is read back across turns instead of being rewritten every turn. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	17 天前
models	fix(tui): input auto-wrap, Alt+Enter newline, and intelligent arrow key navigation By the way, apply cargo fmt for code style consistency. Co-Authored-By: GLM-5	18 天前
providers	feat: implement per-command process groups with registry for reliable cleanup Co-Authored-By: GLM-5	15 天前
wire_types	feat(llm-client): thread cached input tokens through Usage into trace spans Account for cache-read tokens end to end: - Usage carries cached_tokens (OpenAI prompt_tokens_details.cached_tokens; Anthropic cache_read_input_tokens), threaded into LLM_CALL / TURN trace spans. - Anthropic marks cache_control ephemeral on the stable system-prefix block ONLY, never the volatile Context block, so the breakpoint is read back across turns instead of being rewritten every turn. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	17 天前
convert.rs	feat(llm-client): thread cached input tokens through Usage into trace spans Account for cache-read tokens end to end: - Usage carries cached_tokens (OpenAI prompt_tokens_details.cached_tokens; Anthropic cache_read_input_tokens), threaded into LLM_CALL / TURN trace spans. - Anthropic marks cache_control ephemeral on the stable system-prefix block ONLY, never the volatile Context block, so the breakpoint is read back across turns instead of being rewritten every turn. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	17 天前
error.rs	optimize: log more info when llm failed Co-Authored-By: GLM-5	18 天前
lib.rs	fix(tui): input auto-wrap, Alt+Enter newline, and intelligent arrow key navigation By the way, apply cargo fmt for code style consistency. Co-Authored-By: GLM-5	18 天前
provider_registry.rs	refactor: remove apibasestype	30 天前
resolver.rs	fix(llm-client): isolate missing API key tests from environment variables Co-Authored-By: GLM-5	21 天前
url_fallback.rs	fix(tui): input auto-wrap, Alt+Enter newline, and intelligent arrow key navigation By the way, apply cargo fmt for code style consistency. Co-Authored-By: GLM-5	18 天前