← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-snapcompact

Deterministic pixel-font visual context compression plugin for DeepSeek Harness using bitmap frames.

VisionUI & ProductivityTerminal & TUIDeveloper Tools
1GitHub Stars0ForksUpdated2026-10-19

Install

No clear install command was found in the current repository evidence.

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.

source-grounded
dsh-snapcompact is a context compression plugin for DeepSeek Harness (DSH). Instead of using lossy LLM summarization, it serializes conversation transcripts and renders them into compact bitmap PNG frames of pixel-font glyphs for vision-capable models to consume directly. Operating locally without additional LLM API overhead, it integrates with DSH attachments, Cordis lifecycle events, and compaction engine interfaces.

Key Capabilities

  • Deterministic local rasterization of transcripts into PNG bitmap frames using native pixel fonts
  • Provider-aware shapes tailored for Anthropic, Google Gemini, OpenAI, and CJK text
  • Structured conversation transcript serialization for user, thinking, AI, and tool call blocks
  • Automatic file operation tracking (Read, Write, RW)
  • DSH attachment integration via ctx.attachments.saveImages
  • Interactive slash commands (/snapcompact) with threshold-based auto-compaction and status inspection
  • Automatic step-pressure and context-overflow recovery hooks

Useful For

  • Preventing context overflow during long-running agent workflows without paying for secondary LLM summaries
  • Preserving exact verbatim historical details, tool invocations, and thinking chains in vision context
  • Compressing East Asian and multilingual conversation transcripts into Silver TrueType bitmap frames

Who It Fits

  • DeepSeek Harness users working on long-context coding sessions
  • Developers looking for deterministic zero-API-cost context archival
  • Engineers using multimodal/vision models within DSH

Documented Limitations

  • Requires a native rasterizer binary (pi_natives node module) installed on the host system or specified via PI_NATIVES_PATH
  • Only effective with vision-capable downstream models that can read back the rendered pixel fonts
  • Requires manual cloning into the profile packages directory and bundle registration in package.json

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 6 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Not Declared

GitHub did not report an SPDX license for this repository snapshot.

low
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
JessenReinhart/dsh-snapcompact
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
22c2d57 · 2026-10-22

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
2026-10-19
Last release
No release detected
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app