by stevenx65

DeepSeek balance and token usage in the web sidebar, with a today/all-time toggle and provider filtering.

by TheTianzz

DeepSeek Harness plugin: account balance + session cost (/balance /cost commands, deepseek_billing tool, Web UI dual capsules), official prices automatically synced every 12 hours

by wss534857356

Codex App Server model provider for DeepSeek Harness using your local Codex login.

by elizax

Support setting the LLM proxy address

by BruceLanLan

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent

by wly8691-jpg

Windows-native real-Office automation plugin (DSH). Contract, task-level, fault-injection and process-leak regressions covered; real-Office tests must be run on the target machine.

by elegant01

dsh-plugin, use Huawei CodeArts credits, token in DSH,

by beijingwahw

DeepSeek Companion — The official companion plugin for DeepSeek Harness: conversation export / handoff summaries / cost optimization / global search + execution trace analysis, Prompt engineering workspace, multi-model arena, task orchestration, security and auditing (nine major modules, E–J, built on Cordis plugin architecture).

by 1035041186

dsh-llm-ollama is a community plugin developed for DeepSeek Harness (dsh), enabling Harness to connect to a local Ollama service through the Ollama native protocol (`/api/chat`). Plug and play: it doesn't modify any official dsh files. After installation, it automatically adds an Ollama page under "Settings" and makes the provider's models available in the session model selector.

by wyouwd1

Manage OpenCode Zen free-tier and Go-tier models in DeepSeek Harness: live listings from opencode.ai, drift per route, four agent tools plus an OpenCode Models settings section.

by Physicolor

Right-hand widget rail for DeepSeek Harness Web UI: live session stats (turns, LLM/tool time, TTFT, speed, cache, tokens) plus OpenCode Go quota via a same-origin host proxy; extensible widget registr

by 1624318455

Exposes OpenCode Zen free models to DeepSeek Harness with no API key, tracking Zen gateway changes.

by 11zld22

Model Information Completion: Automatically complete context, output limit, thinking level, and image capabilities based on model name

by LemCAE

A plugin for deepseek-harness that displays the current account balance and the estimated cost consumption of the current session.

by Faide-cyber

Bring WorkBuddy's free and paid models (domestic and international) into DSH — no WorkBuddy desktop app required.

by fancr-code

DeepSeek Harness Browser Extension: API Usage / Cost / Balance Dashboard — Stacked bar charts by model for today / last 7 days, budget alerts, cross-session ledger.

by SpookySandwich

Detect which conversation model your DeepSeek Harness account is served: score the live chain-of-thought of probe conversations, and immediately abort if judged to be the old model.

by DGPisces

DeepSeek Harness provider for GPT models using managed ChatGPT OAuth through Codex app-server

by jyao-SUSE-power-group

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

by stoneface10

Use your ChatGPT subscription in DeepSeek Harness to access Codex models and generate or edit images with gpt-image-2—no OpenAI Platform API key required.

by MoRanYue

Route OpenRouter requests through a configured provider list and quantization cap, injected as provider.only/order with allow_fallbacks, plus provider.quantizations.

by zgrajdnhj7806-svg

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

by bobcat848

Calculate the real-time cost of DeepSeek API calls made by DeepSeek Harness.

by Visol-456

DeepSeek Harness Fallback Chain Plugin: Automatically switch to a backup provider when the main model fails, with a Web UI configuration panel | Provider fallback chains for DeepSeek Harness