dsh-rice-patrol
Rice Patrol：DeepSeek Harness 的有界推理重复保护与干净恢复
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:LeeLizuoLiu/rice-patrol#4bde541876a3bb5cb2f7a4bd28712f5a853b4525Rice Patrol 以 dsh-rice-patrol 发布，当前版本为 0.2.11-desktopcompat.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。
Rice Patrol protects reasoning streams in DeepSeek Harness (DSH). When sustained short-line repetition is confirmed, it stops the current generation and resumes the unfinished task in the same conversation.
Enable the plugin; no response-mode selection is needed. Every confirmed loop follows the same stop-and-resume flow. There is no Stop / Observe / Recover selector, observation logger, or n-gram detector.
Legacy mode: stop, mode: observe, and mode: recover values no longer select behavior. They may be removed, but leaving them in an old profile does not prevent automatic recovery. Use DSH's plugin enable/disable control to turn off Rice Patrol entirely.
The Stop recovery button remains available during recovery. New user input also interrupts the current recovery. Unverifiable session or background-job state pauses recovery with an explanation.
The plugin reads reasoning text exposed by DSH, splits it into trimmed nonempty lines, and scores the last 50 lines. A median line length of at most 20 characters, with at least 70% of lines having an exact duplicate inside that window, produces a warning. After at least 50 additional nonempty lines, another matching window confirms the loop and stops generation.
A warning alone does not stop output. The rule is provider-independent and uses a fresh detector for each model request. An ordinary output-token limit is outside its scope. This update does not change detection thresholds.
Rice Patrol waits for the stopped generation and stream cleanup, verifies host background jobs, excludes interrupted reasoning from model-visible history, and continues through the original Agent and session. Completed file edits and tool results remain available. The continuation asks the model to inspect workspace state before repeating side effects.
Each newly confirmed loop can recover; the same stop submits only one handoff. Failed or blocked old recoveries do not restart themselves. The resumed Agent follows normal DSH policies, without an extra summarization model request or plugin-imposed limits on later model/tool calls.
resumeTimeoutMs defaults to five minutes for handoff and the first resumed response, rather than the entire subsequent task. Minimal recovery status and deduplication records remain; there is no per-chunk observation log.
The current package is 0.2.11-desktopcompat.1, with a desktop entry for DSH 0.2.0-rc.2. The source is available on GitHub; this update does not publish an npm package.
Enable Rice Patrol and its components on the Plugins page. The plugin page explains automatic recovery; recovery status appears near the conversation input. See config/recover.example.yml.
Provider/model filters, state directory, and recovery timeouts remain configurable. Response mode is not configurable. Use only one controller that cancels and resumes a given reasoning stream.
Restart DSH after updating installed files to load the new host code. Historical implementation notes are in docs/SINGLE_AGENT_RECOVERY.md. MIT license.