dsh-context-provenance

Compare adjacent request evidence as Observed, Estimated, or Unavailable—without returning prompt text, message content, tool schemas, or raw paths.

dsh plugin --profile web add dsh-context-provenance

Community-maintained and not an official DeepSeek project. Related trust-layer plugins: Telemetry Redactor, Verification Receipt, and Evidence Audit.

An observe-only, CPU-only, local-only DeepSeek Harness plugin that reports what public runtime interfaces can actually prove about the requesting Agent's context. It retains only the two most recent ordinary agent-loop request observations in memory and exposes them through the existing Cordis inspect query mechanism. It performs no file, network, subprocess, GPU, persistence, session, permission, tool, model-routing, or request mutation.

Audit verdict

Conditional pass against official DSH commit 47f943859bef60e4160492346772ded9b24f765a. Stable public seams exist for a deliberately incomplete evidence ledger. This plugin is not a complete context provenance graph and cannot explain all behavior differences.

Public collision review found official pluginInventory/list, official token-meter projections, official Cordis inspect, and the community dsh-context-doctor. This plugin does not rescan files, reimplement token estimation, add optimization advice, or add another token-breakdown UI. Its distinct surface is strict evidence labeling plus adjacent actual request comparison.

Evidence matrix

Field	Label	Public interface	Boundary