dsh-optimize
DeepSeek Harness 的长会话资源管理器：测量每个请求实际携带的上下文，跟踪每个会话的增长，在会话运行成本变高之前发出警告，并可选择性地裁剪 Web UI 中呈现的历史记录。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:aoripus/dsh-optimize#c3012f4c79c33b02797e8c4a72ce486d456ea3ebOptimize 以 dsh-optimize 发布，当前版本为 0.1.0。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。
Long-session resource governor for DeepSeek Harness.
A conversation that keeps growing gets expensive long before anything
compacts it: every step re-sends the retained history, the session log grows
without bound, and the web UI has more history to draw. dsh-optimize
measures that growth and reports it, so a heavy session is a visible fact
rather than a surprise.
agent/pre-step.$DSH_HOME/storages/dsh-optimize/state.json.warnTokens, and again at
criticalTokens, with the measured range.optimize host service (snapshot(id), list(), flush()).It does not change what the model receives, does not write session events, and does not touch the session log.
dsh plugin --profile <profile> add dsh-optimize
Or from a checkout:
dsh plugin --profile <profile> add /path/to/dsh-optimize
The bundle patch ships the defaults; override them in your profile's patch
layer (~/.dsh/profiles/<profile>/cordis.patch.yml):
- id: dsh-optimize
config:
warnTokens: 120000
criticalTokens: 300000
verbose: false
| Key | Default | Meaning |
|---|---|---|
warnTokens | 120000 | Estimated request weight that marks a session as heavy. |
criticalTokens | 300000 | Estimated request weight that marks a session as critical. |
verbose | false | Log every measured request, not only threshold crossings. |
The estimate is a range: Latin text is near four characters per token, CJK near one and a half. The upper bound is the one compared against the thresholds, so a mixed-language session errs towards reporting early.
MIT.