All plugins

DSH / BUNDLE / BUNDLES

dsh-tool-bandit-search

v0.1.0siruignaw-sys / dsh-tool-bandit-search089dd0d3e5

InstallableBundlesBundles & other modulesCommunity · Topic auto-analysis

Overview

dsh-tool-bandit-search

A search tool for DeepSeek Harness that learns to pick between quick and thorough search strategies using a contextual bandit (Thompson sampling).

README / EN

Package documentation

Registry summary

A search tool for DeepSeek Harness that learns to pick between quick and thorough search strategies using a contextual bandit (Thompson sampling).

dsh.pub verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.

Read the full README on GitHub

LIMITATIONS

Known limitations

- **Bandit state is in-memory** and resets on every restart. Persisting it via `ctx.storage` (which dsh already exposes) is a natural next step. - **Reward is a heuristic**, not a measure of actual answer quality — it captures result count and latency, not whether the results were *relevant* or *correct*. A stronger version might score reward against whether the model's final answer actually used the returned sources. - **The model can still issue multiple `search` calls per turn** even when `thorough` is already broadening internally — the plugin optimizes strategy *per call*, not the model's own multi-call behavior. - Built and tested against dsh's developer preview; the plugin/tool APIs may change before a stable release.