DeepSeek Harness PluginManifest Valid

dsh-eta-forecast

Estimated completion time and progress forecast widget for DeepSeek Harness web and desktop interfaces.

UI & ProductivitySecurity & PolicyRemote Execution

2GitHub Stars0ForksUpdated2026-10-27

Source

Install

$ dsh plugin --profile desktop add link:<本目录绝对路径>

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-eta-forecast adds an estimated time of arrival (ETA) and progress forecasting widget to DeepSeek Harness web and desktop interfaces. Instead of naive extrapolation, it calculates remaining task time primarily from the model's active todo checklist combined with step-pacing corrections, historical round durations, and timeout tracking. It supports both embedded web viewing and a dedicated transparent desktop floating window via Electron, with customizable scaling, wallpaper themes, session switching, and click-through lock states.

Key Capabilities

Predicts round completion time (ETA) based on todo checklist completion, pace, unit steps, and historical averages
Provides real-time timeout tracking with mature anchor baselines and dynamic re-estimation without stalling countdowns
Exposes a dual-display interface supporting embedded web widgets and an Electron-based transparent desktop floating window
Excludes user authorization and prompt-wait intervals from task duration calculations to avoid skewed predictions
Supports interactive multi-session switching with active running indicators and responsive UI redraws
Offers appearance customization including scaling (with auto-compact layouts below 70%), wallpaper overlays, card opacity, and mouse click-through locking

Useful For

Tracking execution progress and projected completion times during lengthy multi-step DeepSeek Harness agent workflows
Monitoring background agent runs from a desktop floating window without keeping the main browser window in focus
Inspecting historical task paces, timeout learning factors, and model execution accuracy across sessions

Who It Fits

DeepSeek Harness desktop and web users executing complex, multi-step LLM tasks
Developers looking for visible pacing metrics and transparent runtime indicators for agent rounds

Documented Limitations

ETA accuracy degrades significantly when the model fails to generate a structured todo checklist
Desktop floating window requires a pre-existing Electron runtime (e.g., from dsh-pet or via DSH_ETA_ELECTRON_PATH) and will not automatically download it
Client appearance and lock preferences stored in localStorage do not synchronize automatically across different browsers or domains
Widget locking mode blocks mouse events only; keyboard tab focus can still navigate into the web widget element

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, 0 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: qwq-wny/dsh-eta-forecast
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin
Source checked: aaefca6 · 2026-10-27

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.