context-window 30

Maintain deployment-specific context windows for custom DeepSeek Harness model routes.

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys — plus sliding-context aware

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.

Keeps long coding-agent sessions lean: wrap a stretch of work in a named task, and when it ends, fold that whole span into one short titled summary. The conversation stays readable, context costs stay low, and any fold's original content can be read back

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

Usage statistics for DeepSeek Harness: a lifetime token dashboard (52-week activity heatmap with daily/weekly/cumulative modes, per-model trend and donut, streaks) plus a context lens for the current session

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.

Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.

DSH plugin: counts completed compactions per session and raises a floating reminder — with bilingual UI — only after repeated compactions plus heavy extra token spend.

Model-autonomous context compaction for DeepSeek Harness: mind_map surveys the agent's own context surface (seqs, token weights, clear-boundary markers and the clear-mind playbook), clear_mind replaces a chosen span with a model-written checkpoint through

Model-free /trim for DeepSeek Harness — drop the oldest, least valuable span of context on demand (the `/trim` command) or automatically when a request hits the model's context wall, without any model call.

Context Guardian as a native DeepSeek Harness (DSH) bundle: deterministic, seq-pointer-preserving compaction with model-facing recall and search. Companion to dsh-tool-guardian.

Tool Guardian as a native DeepSeek Harness (DSH) bundle: keeps tool definitions out of the context window by fronting your MCP servers behind a small native router. A bridge to the Python tool-guardian, not a rewrite.

Deterministic, zero-LLM, byte-budget context compaction for DeepSeek Harness, with byte-exact recall of compacted history.

Send one-liner questions to DeepSeek's web chat instead of burning your DSH context. Composer button + global hotkey palette, with history.

CWL — Context Window Lifecycle for DeepSeek Harness: structured context eviction (arXiv:2606.11213). Graduated, deterministic, zero-LLM eviction of exploration/action episodes when context pressure exceeds budget — no summarization lossiness, no hallucina

DSH 插件：上下文压力到阈值、或本会话被压缩次数到上限时，自动把工作交接给一个新会话——交接包从会话机械提取（改动过的文件 / 用过的工具 / 最近几轮消息 / 停在哪儿），不过模型，落盘可审阅。

MULTIVERS engine for DeepSeek Harness: Zero-Bloat Payload Diet, Context Synthesizer, Flatline Rolling Window, and Settings Dashboard.

Capability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.d

Jev/System-One semantic pruning of stale tool results for DeepSeek Harness; keeps conversation text verbatim and forgets stale tool output before summary compaction is needed

T3 Code's session-context UX for DeepSeek Harness: a session-row context block, provider chip, status pill, header context strip, and a context-window meter with compaction.

Put DSH's automatic context compaction trigger where you want it, per provider/model. Stops DeepSeek Harness from condensing a conversation far earlier than the configured threshold on models with smaller context windows.

DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.

A friendly status and context-pressure companion for DeepSeek Harness Web

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

DSH Web 上下文窗口归因面板：通过 host token meter 按消息显示当前 surface 的 token 占用与摘要。Read-only per-message context-window attribution for DSH Web using the host token meter.

Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider