Plugins

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

DSH Web GUI plugin: first-position 【概览】tab in the right panel (context window / session metrics with active-only 1s runtime / per-model usage & cost analysis) plus a settings entry 【DeepSeek 开放平台】that opens platform.deepseek.com. Web profile only, theme-a

DeepSeek account-wide usage & balance panel from the official platform API (api/v0/usage/by_api_key): cache hit/miss & output tokens, cost, 24h–90d ranges, persistent platform token, and a model-visible `deepseek_usage_query` tool.

Dual-model auto-routing plugin: low-cost direct / high-cost upgrade with an escape-learning closed loop (wrong direct answers auto-learn fingerprints, force-upgrading the same fingerprint next time), persisted and interoperable with the Python ModelRouter.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

A right-side session stats panel showing average cache-hit rate, session cost, runtime, request count, cumulative tokens and account balance.

A DeepSeek Harness plugin (dual-face host + browser) for watching your DeepSeek account **balance** and estimating **token-based costs**, with prices configured per **model × peak/off-peak period** online. Everything lives in a unified modal (opened from the sidebar-footer **Balance** button); a **session-header** button shows a live "Session ≈xx CNY". UI copy is bilingual (Chinese / English, following the host UI language).

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

DeepSeek account balance and model cost tracking with official peak/off-peak pricing, three-tier token billing (cache miss, cache hit, output), per-model and per-session breakdowns, a composer summary bar with hover details, CSV export, and a settings panel.

Shows DeepSeek API balance and local DSH Flash and Pro usage costs.

Adds a sentient floating eye to DeepSeek Harness — injects a taming kernel that makes the AI truly understand you, with 11 dynamic eye skins, ghost mode, and zero token cost when AI mode is off.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

Cost tracking plugin for the DeepSeek Harness Web GUI — snapshot-anchored per-turn pricing, account balance, and live cost estimates.

DSH web plugin: a real-pricing usage-cost line beside the official token stats — per-model cost breakdown with a verified price table. / DSH 费用统计行：在官方 Token 用量行旁按模型显示真实费用（按模型分别标注，价格均来自官方定价页）。

DSH plugin: visible cost/balance stats pill below the composer, with settings page and one-click reset. Fixed fork-level issues of dsh-cost-balance (slot id collision, missing ctx, invisible 5px bar).

The DeepSeek time-of-use meter for dsh: what this session cost, which tariff is running, when it flips, and the account balance behind it — one line under the composer.

Real-time stage, ETA & cost dashboard for headless dsh tasks: turns the black-box session event stream into a live multi-task grid (cordis plugin + standalone local dashboard, no API calls).

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

DeepSeek Harness plugin: query AI Monitor balance / usage from local SQLite — cost-aware agent, auto bookkeeping with the AI Monitor proxy.

Balance and live session usage for the DSH web UI: header balance button (left of the Session log), dropdown with account balance, real-time token breakdown (cache miss/hit, cache write, output), cache hit rate, and official-rate cost estimates with peak/off-peak auto-switch.

Progressive long-term memory for DSH: sharded markdown bodies under ~/.dsh/memory/topics/, with only a live-generated index (shard · count · path · per-entry line numbers) injected into the system prompt — so the prompt cost stays flat however large the m

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the