dsh-lineage
Run the following command in DeepSeek Harness:
dsh plugin install dongsheng123132/dsh-lineage
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness using the command `dsh plugin install dongsheng123132/dsh-lineage`; the source repository is available at https://github.com/dongsheng123132/dsh-lineage.
About this plugin
Ensuring the authenticity and traceability of evidence objects—such as artifacts, facts, and action reports—is a critical challenge in data-driven workflows. The dsh-lineage plugin, designed for the DeepSeek Harness ecosystem, addresses this by building a local, content-addressed object graph. Each node (e.g., an artifact or fact) is defined by a typed ID, workspace-relative path, and expected SHA-256 hash, creating a lightweight yet verifiable map that clearly tracks where data comes from, how it's used, and what it produces. It doesn't store raw chat content, focusing instead on the structural relationships of evidence, making auditing and verification transparent and efficient.
Use Cases
- Auditing the provenance of data artifacts and generated reports.
- Verifying the integrity of intermediate products in model training or inference pipelines.
- Building trusted data pipelines with version and change tracking records.
Best For
- Data engineers requiring data governance and auditing.
- R&D teams building reproducible AI workflows.
- Data scientists concerned with the credibility of model outputs.
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.