dsh-cache-warmer
Estimated prompt cache tracking and opt-in, cost-aware background cache warming for DeepSeek Harness.
Install
$ dsh plugin --profile web add 'https://github.com/yoggu/dsh-cache-warmer.git#v0.1.7'Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Displays estimated cache lifetime countdown and draining ring indicators in the conversation UI
- Evaluates expected savings versus refresh costs before scheduling background prompt-cache warming
- Supports per-chat opt-in and per-model cache policies with configurable lifetime and warming toggles
- Integrates with native llm-pi-ai provider routes, reusing existing credentials and OAuth refreshes
- Separates warm request accounting from standard transcript token totals into a dedicated plugin storage domain
Useful For
- Keeping long prompt prefixes cached across conversational pauses without manual re-querying
- Visualizing prompt cache decay and observed cache hits across different LLM backends
- Controlling API expenses by requiring positive net expected savings before executing cache refresh requests
Who It Fits
- DeepSeek Harness users working with large system prompts, codebases, or context windows
- Developers looking to minimize LLM inference costs and latency via provider prompt caching
Documented Limitations
- Disabled by default; requires genuine model requests, model enablement, and per-chat opt-in
- Non-pi-ai adapters and unsupported protocols operate in observation-only mode without warming
- Client cancellation does not guarantee backend provider generation stops for routes lacking server-side output caps (e.g., Codex)
- Cost projections are API-equivalent list-price estimates rather than billing or quota guarantees
- Restarting DSH or updating credentials invalidates captured requests until a new genuine request is completed
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 6 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- yoggu/dsh-cache-warmer
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- ed80a47 · 2026-10-25
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-01
- Last release
- 2026-10-01
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Import and resume conversation histories from 25+ AI coding agents directly into DeepSeek Harness.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Agent-native multi-market trading terminal and quantitative research plugin bundle for DeepSeek Harness.
View plugin →Free frontier LLM provider plugin for DeepSeek Harness with upstream probing and local OpenAI-compatible gateway.
View plugin →