mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-08-29 04:26:38 +00:00
ds-review-bot 首轮意见修复: - 摘要收缩比较改用所选节点的路由价 shadowedRouteTokenCount,修复图片消息启发式价低于带框摘要时压缩被误拒;日志影子价仍为启发式 - DeepSeek 定价经序列化器同一套 access 解析构建句柄与占位文本,消除逐图数十 token 的低估;uncatalogued 分支 JSDoc 指明复现 projectImagesForTextModel 替换 - llm-replay 在加载时拒绝纯文本模型上的 imageRequestTokens 声明 - contextBreakdown 的 README 与 JSDoc 改为等于 heuristicTokens 之和,不再声称等于路由价 surfaceTokens
compaction/ — compaction capability family
English | 中文
A compaction capability family (see capability seams): a Service Definition, a summarizing provider, a model-free tool-result pruning companion, and a human command Consumer. All product packages.
| Package | Role | ctx key |
|---|---|---|
compaction/ |
Compaction seam and event vocabulary | ctx.compaction |
compaction-basic/ |
Token-pressure and summarization backend | registers ctx.compaction |
compaction-tool-result-pruner/ |
Optional model-free tool-result pruning | ctx.toolResultPruner |
command-compact/ |
Human compaction command | registers on ctx.commands |
The backend, optional pruner, and human command compose through the seam; token measurement remains a separate LLM-family service. The compaction capability-seam Agent Note owns the dependency rationale.
The subsystem reference — the compaction/* events, CompactionResult, the service, pruning outcomes — is docs/subsystems/compaction.md; the seam's deliberate dsh-session/dsh-llm dependency is recorded in the compaction capability-seam Agent Note.