dsh-cache-miss
DSH web plugin: a yellow one-line cache-miss notice under the first assistant reply of each turn, when that turn's first request rebuilt the prompt cache.
179 results
DSH web plugin: a yellow one-line cache-miss notice under the first assistant reply of each turn, when that turn's first request rebuilt the prompt cache.
DSH Web UI plugin: listens to GitHub issues/PRs across the account's repositories, auto-fixes issues whose repos are checked out locally, and turns PRs / feature requests / other items into a review-and-run queue with one-click agent execution and push.
Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.
Prompt Studio plugin for DeepSeek Harness: compose runtime prompts, overrides, and request-local synthetic turns in one live editor
DeepSeek Harness web-GUI plugin: a Settings「账户」page showing DeepSeek platform balance/usage (daily cost chart, per-model requests & tokens, selectable time range) and the OpenCode Go 5h/weekly/monthly quota with reset times.
DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0)
DeepSeek Harness (cordis) client plugin: a right-side session stats panel showing average cache-hit rate, session cost, runtime, request count and cumulative tokens (DeepSeek pricing).
Aggregated web-search provider for DeepSeek Harness: one prioritized queue over AnySearch / TinyFish / Tavily / Brave / Exa / Firecrawl / Jina / SerpApi / Serper, multiple API keys per entry, ordered fallback per request.
DSH plugin — Hermes-style Mixture-of-Agents request aggregator: router → parallel reference advisors → aggregator stream, with dual-provider failover (official + OpenCode Go) and V4P triple-gate cost guard.
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
DeepSeek Harness plugin: generate_ui — the model turns a request (+ data) into an A2UI document rendered as an interactive surface in the chat, generated through dsh's own model service (valuz-genui core)
/code-review slash command for DeepSeek Harness — multi-agent review of pull requests and local code, with configurable confidence scoring
Real-time attention alerts for DeepSeek Harness: a global banner plus flashing workspace entries when the agent is blocked (approval request / sandbox denial), with an audible chime and OS-level notifications for new blockers.
Browser audio alert for human-attention events: approval requests, ask-user questions, and finished turns, with per-trigger sounds configurable through the audio-alert settings namespace
DSH (DeepSeek Harness) web plugin: a draggable whale floating widget showing per-request token cost, session/total spend, and the official DeepSeek account balance
VS Code (from a code-server release) inside DSH: a right-sidebar tab driven by the plugin's own launcher over the in-process VS Code server (lib/launcher.mjs). Since 0.3.0 the bundle also ships an editor bridge (assets/extensions/dshcs-editor-bridge): a read-only channel between the in-tree VS Code extension host and DSH, giving the agent what only the editor knows (unsaved buffers, language-server diagnostics, the active selection) and letting editor gestures drive the session. Since 0.3.22 the ask panel renders that session's new content with DSH's own Markdown renderer (pinned to the deployed DSH UI version); since 0.3.23 it is a full-width dialog with collapsible thinking rows and can answer approval requests in place — the bridge's only non-read-only route (POST /approve, constrained to pending in-process requests and the outcomes allowed-once/rejected; panel-first for 5 minutes, handed back to the official card the moment the panel closes). The tab claims DSH file addresses (dsh-resource://file/**) by file type (setting claimExtensions), so the product's own produced-file chips, delivered-file previews and inline prose mentions open in the workbench. The IDE is a resident surface moved with Element.moveBefore instead of being remounted, so switching sidebar tabs no longer reloads it. Opening the tab switches the right sidebar to fullscreen by default (setting fullscreenOnOpen). Following a workspace switch is lightweight: the workbench re-navigates with the new ?folder= and the IDE process is not restarted (since 0.2.12). Requires a DSH with the right-sidebar services (sidebarRightTabs/sidebarRight, >= 0.1.5-alpha.1); older DSH versions get a single upgrade notice on the settings page and no other UI. Two serving modes: loopback port (default) or same-origin mount on DSH's own webServer (/code-server, protected by ctx.connection.requestRejection). No code-server Node layer, no argon2, no C++ toolchain.
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
Codex-style per-session memory for DeepSeek Harness: qualified sessions auto-distill into per-session drafts (rollout_summaries); manual add/change/forget runs only on explicit user request; layered disclosure (summary + registry); idempotent integration watermark. / 一会话一草稿记忆插件:合格会话自动提炼草稿;手动增/改/忘仅在显式请求时执行;分层披露(总纲+注册表);幂等整合水印。
DSH Skill MCP Manager for DeepSeek Harness Desktop: manage MCP servers and Skills from Settings, publish compact capability descriptions, and progressively load each MCP server's tools only into the requesting session. Dual-face dsh plugin, no DSH source changes.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
Agent loop rate limiter — prevents TPM/RPM limit violations by intercepting the LLM streaming pipeline and adding adaptive delays between requests
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由:三级难度 + 视觉自动路由,模型从「设置-模型」已配置模型中选取,虚拟 smart 模型零配置接入。
Outbound LLM request header modification for DeepSeek Harness (DSH): client-identity header presets (Codex / Claude Code / opencode), per-request dynamic headers, X-Stainless fingerprint stripping, URL rewriting and Anthropic body patching at the fetch transport layer.