12月1月2月3月4月5月6月7月8月9月10月11月
周一周三周五
一年内 263719 次贡献
更少更多
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/dashboard-offline-assets 分支比较 2 提交 »c7f574caf1 test(dashboard): serve vendored assets in the playwright route harness372a4e04bc fix(dashboard): serve tailwind/htmx/alpine locally instead of from CDNs
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/copilot-oauth-endpoint-regression 分支比较 3 提交 »534f7f5593 docs(copilot): document generic-host routing + enterprise override (#610)6c3698b525 fix(copilot): route subscription + OAuth through the generic host (#610)f00b13ece7 fix(copilot): restore generic endpoint for non-subscription OAuth (#610)
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/copilot-completions-host 分支比较 3 提交 »aa38e9c636 fix(copilot): match the completions override by host, not whole string153a1d428f test(e2e): assert the dead overrideAuthType key is not written45b4c476dd fix(copilot): send VS Code inline completions to the host that serves them
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/copilot-native-enterprise-routing 分支0aca48c096 Merge branch 'main' into fix/copilot-native-enterprise-routing
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/context-1m-suffix-budget 分支比较 2 提交 »f42f6d5cc0 fix(pricing): repair the dead LiteLLM cost path and apply the long-context premium4adec64ab4 fix(anthropic): honor the [1m] 1M-context tier when sizing the budget
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/complete-buffered-ccr-lifecycle 分支比较 2 提交 »9a98c5c5bb fix(proxy): reject malformed buffered CCR successes7848fd76a9 fix(proxy): stop committing HTTP 200 before the buffered CCR result is known
- frostbyte_neo 推送了仓库 github-featured/chopratejas--headroom 的 fix/compress-route-tokenizer-and-docs 分支比较 3 提交 »fd7f0d1841 docs(compress): state that /v1/compress ignores system and tools2a06e82834 docs(compress): document the multi-turn recipe for keeping the prefix cachebb65193f09 fix(compress): resolve the /v1/compress tokenizer per model, and document the real contract
