10 results
Per-conversation x-opencode-session header injection for OpenCode Go in DeepSeek Harness (DSH). Fixes 400 MissingSessionID, keeps prompt-cache routing optimal, scoped strictly to opencode.ai, runtime-switchable without restart.
DSH Web GUI 轻量记忆系统：四个大写 Markdown 文件（USER.md / PROJECT.md / WORKLOG.md / CONVENTION.md）+ 两个动作（append 流水 / distill 沉降）。零外部依赖，只用 Node 内置模块；文件可视化、可 diff、可 git 管理。
DSH web plugin: a yellow one-line cache-miss notice under the first assistant reply of each turn, when that turn's first request rebuilt the prompt cache.
Cache-prefix stabilization and evidence-based cache metrics for DeepSeek Harness
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
Cache-aware API token usage bar for the DeepSeek Harness Web UI
Self-contained token usage statistics for DeepSeek Harness.
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.
DeepSeek Harness plugin: aggressive token optimization without affecting task quality. Trims tool results, manages context window pressure, optional LLM-summary compaction, stable prompt-cache layout.
DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费，峰时正好是上班时间。