← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-plugin-om

Observational Memory plugin for DeepSeek Harness managing context compression, progress reminders, and raw recall.

UI & ProductivityDeveloper ToolsSkills & WorkflowsRemote Execution
2GitHub Stars0ForksUpdated2026-10-15

Install

$ dsh plugin --profile <profile> add dsh-plugin-om

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-plugin-om implements Observational Memory (OM) style context management for DeepSeek Harness. It automatically compresses long conversation histories using observation and reflection token thresholds while preserving user messages and active skills. The plugin injects system-reminder progress notices, provides a recall tool for exact index or semantic search across uncompressed history, and supplies a WebUI configuration panel with re-compression diagnostic tools.

Key Capabilities

  • Two-stage automated context compaction based on configurable token thresholds (observation and reflection)
  • Progress reminder injection via system-reminder to encourage interim conclusions and planning
  • Raw conversation recall tool supporting both message index lookups and local ONNX-based semantic retrieval
  • Skill text and active user prompt preservation during compaction passes
  • WebUI diagnostic cards displaying compression statistics, token usage, timeline replays, and multi-model re-compression

Useful For

  • Preventing context exhaustion and high token overhead during extended agent workflows
  • Recalling precise historical details or code definitions from earlier steps without cluttering the primary prompt context
  • Testing and comparing compaction quality across different LLMs in the DSH WebUI

Who It Fits

  • DeepSeek Harness users conducting long multi-step agent tasks
  • Developers needing granular control over LLM token consumption and history retention
  • Prompt engineers evaluating context compression strategies

Documented Limitations

  • Requires DeepSeek Harness 0.2.0-rc.2 or newer
  • Semantic recall depends on local ONNX model downloads and native builds (such as onnxruntime-node)
  • Records observation pending status and degradation warnings using the host's feedback/record channel, which may be sent to telemetry unless DSH_TELEMETRY_MODE=DISABLED is set

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 3 runtime, 71 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
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
FanetheDivine/dsh-plugin-om
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
8536156 · 2026-10-15

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
2GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-15
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