@xiyiyiru/dsh-state
mycel 会话状态作为纯文本笔记本：提供 add_state / read_state / compact_state，以及基于每个会话文件的 focus 任务栈，文件位于 <cwd>/.mycel/state/<sessionId>/；可在压缩和恢复后保留，绝不会自动注入，不写入任何会话事件
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add @xiyiyiru/dsh-state@0.2.0-rc.1State 以 @xiyiyiru/dsh-state 发布，当前版本为 0.2.0-rc.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A plain-text session notebook for dsh agents: add_state / read_state / compact_state over per-session files, plus a two-tool task stack (focus_task / focus_complete).
dsh agent 的会话状态笔记本：抗上下文压缩、跨 resume 存活的纯文本笔记层，外加一个任务栈。零自动注入——想看笔记就调
read_state，没有后台魔法。
Context compaction deletes working memory. An agent that just learned "the bug is in the retry loop, user confirmed fix #2" loses exactly that when the window compresses. Auto-injected state has the inverse failure: it burns the same tokens every request and trains the model to ignore it.
This plugin persists working facts as plain files under the workspace — they survive compaction and resume — and keeps the notebook out of every request unless the agent explicitly reads it. Five verbs, no storage to manage, no schema to migrate, zero session events (dsh session-log readers refuse event types outside the harness vocabulary, so since 0.2.0 the plugin touches no log at all).
Everything lives under <session-cwd>/.mycel/state/<sessionId>/:
notebook.md — the notebook, one appended paragraph per notefocus.json — the task stack, bottom frame firstThe session id keys the container: two conversations in one workspace never share state, and a resumed session (same id, same cwd) finds its files back.
| tool | verb | semantics |
|---|---|---|
add_state | append | append one note. Mistakes are corrected by appending a correction line — there is no edit verb |
read_state | read | full text + size; appends a compress hint once the notebook passes 8K |
compact_state | replace | the compression verb: read first, then rewrite the whole file with a summary |
add_state's model-facing guidance carries hard triggers (record the moment it happens, not at task end):
focus.json; frames are plain one-line task descriptions.
| tool | verb | semantics |
|---|---|---|
focus_task | push | lock a multi-step task; the previous task is pushed down automatically |
focus_complete | pop | declare done with a one-line conclusion and fall back to the previous task (or clear the stack). Call it before delivering the answer — the task's completion standard is the artifact landing |
focus_task's guidance on when not to use it: single-turn Q&A, or a change of working posture within the same task (that is the mode plugin's business — the two are orthogonal by design: the stack restores your task, a re-switch restores your methodology; frames carry no mode snapshot).
Interrupted mid-task? Lock the blocker with focus_task, solve it, focus_complete back to the main task.
As a convenience, focus calls also append to <session-cwd>/.mycel/focus.log — best-effort, for grepping a workspace's task history; focus.json remains authoritative.
dsh plugin --profile <name> add @xiyiyiru/dsh-state
Peer dependencies (@deepseek-ai/cordis, dsh-agent, dsh-session, dsh-system-prompt, dsh-tools) resolve from your dsh installation automatically.
import {
ADD_STATE, READ_STATE, COMPACT_STATE,
FOCUS_TASK, FOCUS_COMPLETE, FOCUS_TASK_DESCRIPTION, FOCUS_COMPLETE_DESCRIPTION,
SIZE_WARN_THRESHOLD,
} from '@xiyiyiru/dsh-state'
| export | what it is |
|---|---|
SIZE_WARN_THRESHOLD | 8000 — where read_state starts appending the compress hint |
ADD_STATE … FOCUS_COMPLETE | tool names; *_DESCRIPTION their model-facing descriptions |
The invariant companion (@xiyiyiru/dsh-state/invariant) still validates legacy mycel/state events in stored logs written before 0.2.0; the plugin itself writes zero session events.
focus.log is a convenience projection, lossy by design.MIT