prompt-cache 11

DeepSeek Harness plugin: automatically adds a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests — fixes 400 MissingSessionID and keeps OpenCode's session affinity / prompt-cache routing working.

Bounded context compaction, session-scoped summary reuse, explicit memory controls, and diagnostic-preserving tool pruning for DeepSeek Harness.

OpenCode on DeepSeek Harness — session affinity, Zen/Go gateway origin headers, free-tier tool fallback, and live Go quota display.

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.

DSH 插件：让 Agent 在一个步骤里批量发起互不依赖的工具调用，减少步数与提示缓存重读量。

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。

Self-contained token usage statistics for DeepSeek Harness.

OpenCode on DeepSeek Harness — session affinity, Zen/Go gateway origin headers, free-tier tool fallback, and live Go quota display.

DeepSeek Harness plugin for OpenCode Go only: attaches a stable per-conversation x-opencode-session header (fixes 400 MissingSessionID) and puts DeepSeek V4.1 Flash first on the opencode-go route.

Per-model custom request headers: inject headers into LLM requests matched by model-name wildcard; values support fixed strings and the ${sessionId} variable. Managed from a settings-page UI.

DeepSeek Harness plugin: attaches a stable per-conversation session header to model requests routed to configured providers. Header name is configurable, so one plugin serves SMG (X-SMG-Routing-Key), OpenCode (x-opencode-session), and any other header-bas