DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
I

@xiciyang/inference-diagnose

Inference Diagnose

LLM inference service crash diagnosis: Generate customized collection scripts → Offline desensitized report parsing → Root cause diagnosis + remediation plan → After failure, targeted supplementary collection based on evidence differences (offline/desensitized/evidence-chain-driven, pluggable across

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:xiciyang/inference-diagnose#693515e94f9f762f74eaaca550109ece5e0e621f
READMECompatibilityVersions

Description

LLM inference service crash diagnosis: Generate customized collection scripts → Offline desensitized report parsing → Root cause diagnosis + remediation plan → After failure, targeted supplementary collection based on evidence differences (offline/desensitized/evidence-chain-driven, pluggable across three dimensions)

Compatibility and provenance

Inference Diagnose is published as @xiciyang/inference-diagnose and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
10/19/2026

Versions

0.1.0stable
10/19/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
BSD-3-Clause
Source
github
GitHub
★ 1
Weekly downloads
0
Last push
10/19/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in developer-tools.

MarketdshmarketVisual plugin market inside DeepSeek Harness — browse, search, and one-click install community plugins. · DSH 可视化插件市场:逛一逛,点一下,装好。Opsdsh-opsNative file and PTC tools for DSH on Windows x64, Linux x64 and macOS arm64/x64; Windows-only optional Bash payload and host PowerShell integrationCc Safety Netcc-safety-netA coding agent CLI hook - block destructive commands and secret file accessPlugindsh-pluginA community plugin marketplace for DeepSeek Harness, built to the official plugin spec — browse, search and install 10000+ human-curated community plugins without leaving the app. · DeepSeek Harness 社区插件市场(遵循官方开发规范):10000+ 人工精选社区插件,每日更新。

README

@xiciyang/inference-diagnose

Diagnose an inference service from evidence, not guesswork — and say "unconfirmed" when the evidence is not there.

Generate a collection script → parse the sanitized report offline → produce a ranked root cause with a fix → if the fix fails, re-collect only the missing probes and diff against the previous round. Offline, de-identified, hash-chained audit, and fail-closed when a rule for the framework × runtime × hardware combination is missing.

  • No cloud round-trip for your logs: collection runs on the user's machine; parsing and diagnosis happen in memory.
  • Evidence-driven: every conclusion carries severity, confidence and a falsifier; "not confirmed" is a valid verdict.
  • Three modes: service failure (A), regression against a customer baseline (B), consistency / non-determinism (C).
  • Five tools, all risk: read — no writes, no sandbox requirement, no confirmation token.

安装

git clone https://github.com/xiciyang/inference-diagnose.git
cd inference-diagnose && bash scripts/build.sh
dsh plugin --profile <name> add .

尚未发布到 npm;上面的源码路径装完重启生效。

要求 Node ≥ 20,已在本机 DSH 0.2.0-rc.2 上验证。

从源码构建:

bash scripts/build.sh      # 27 个文件 → lib/
node tests/run.mjs         # 30 spec,无 GPU / 无容器 / 无网络

用法

在会话里直接调用五个工具(裸名,无 inference_ 前缀):

工具作用
generate_collect_script生成内嵌脱敏的采集脚本(在用户自己的机器上执行,本插件不代执行)
parse_collect_report解析已脱敏报告 → 结构化证据(全程内存,明文不落盘)
diagnose_serviceA 范式:服务异常(崩溃/启动失败/挂起/被外部杀/资源耗尽/输出异常)
diagnose_regressionB 范式:相对客户基线的性能/精度劣化(无基线则退化为定性诊断)
diagnose_consistencyC 范式:一致性/非确定性

典型链路:generate_collect_script → 用户在目标机执行 → parse_collect_report → diagnose_service; 修复失败后用返回的 nextSteps 只补采缺失探针,再调一次 diagnose_service(带 priorRound)看 diff。

配置

变量作用默认
INFERENCE_DIAGNOSE_ROOT审计链与运行状态根~/.ai-infra
DSH_HOME会话存储根~/.dsh
INFERENCE_WORKSPACE跑「与兄弟插件工具名不重名」检查时的源码目录未设置则跳过该检查
SPEC_ROOT设计文档仓(门禁 2–4)未设置则跳过

三维词表是 L1 数据:assets/config/dims.json + assets/dimensions/<kind>/<id>.yaml。 新增一个维度取值 = 加一个 YAML + 在 dims.json 登记 + 配规则文件;缺规则文件会让该组合 fail-closed(ERR_ROOTCAUSE_RULES_NOT_LOADED),不会静默降级。

framework:mindie(Ascend)· vllm;runtime:docker; hardware:ascend-arm · gb10 · nvidia · cpu。

治理面

  • 风险分级:五个工具全部 risk: read / sandbox: none / confirmation: not-required。 声明面在 manifest.yaml(给人/审计看)与 src/governance/risk.js(给代码看), 由 tests/unit/governance.spec.mjs 断言逐工具相等,并与实际注册工具名双向一致。
  • 审计哈希链:每次调用追加到 $INFERENCE_DIAGNOSE_ROOT/logs/audit/inference-diagnose/<YYYY-MM-DD>.jsonl; hash = sha256(canonicalJson(record 去掉 hash)),prevHash 首尾相接,只追加(O_APPEND + 0600)。 记录只存参数摘要与参数名,绝不存参数值。
  • 复算:node scripts/verify-audit.mjs [--root R] [--day D] [--tail N],链损坏 exit 1。

兼容与门禁

  • DSH bundle:dsh.bundle.patch + engines.dsh 已声明;entry id inference-diagnose,npm 名 @xiciyang/inference-diagnose。
  • node tests/run.mjs:30 spec 全过(本机实测),只收集 tests/unit/ 与 tests/integration/。
  • bash scripts/verify-all.sh:spec 套件 +(可选)状态机穷举与兄弟仓契约;缺少外部仓时显式 SKIP,不伪造通过。
  • 真机端到端脚本在 tests/realmachine/,不进 CI(见其 README)。

许可

BSD-3-Clause。见 LICENSE。