@graysilver/dsh-evolve-modes
Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.
162 results
Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.
滑动变祖:an opt-in adaptive reasoning slider skin for DeepSeek Harness
为 DSH 的 pi-ai 第三方模型补充可配置的思考强度档位,并设置子 agent 默认思考强度。
Bundles the J-Space Cognition Suite as a DSH skill provider: an on-demand inner-workspace skill (reasoning, planning, ledger) for DeepSeek Harness agents.
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models page card.
Advanced per-model reasoning and capacity settings for DeepSeek Harness
强制 DeepSeek Harness 的回答与思考使用简体中文
Provider Model Configurator for DeepSeek Harness: view, create, edit, copy and delete model entries (context window, max output, modalities, reasoning efforts) across your configured providers, with quick-fill from the pi-ai preset catalog.
Think-step bounce pet for the DeepSeek Harness Web UI: a ball launches in from a random screen edge whenever a reasoning step starts, bounces around with energy loss, can be poked or flung with the mouse, and shrinks away when the think step ends
DSH 实时思维链锚定监控插件: we/let's/let me 指纹波段检测(spec/mixed/react) + L1温和引导/L2强制重置/L3会话重启分级干预; 左侧栏入口 + 液体毛玻璃浮层 + 变阻器式思考强度条; 独立监控进程 + JSONL 实验日志 + 离线回放/参数校准; 变阻器条可选严肃/「滑动变祖器」梗双皮肤。
Reasoning effort settings and per-call subagent model routing for DeepSeek Harness custom providers
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
NoLetMe — real-time reasoning-trajectory keyword stats for the DeepSeek Harness web chat. Tracks the We-need/Let's efficient trajectory vs the Let-me hesitant trajectory vs the The-user-wants neutral framing in the model's streaming reasoning blocks.
Codex-style one-line disclosures for DeepSeek Harness reasoning and tool activity
DSH host plugin: thinking-level (reasoning_effort) control for dsh — auto-adjust per tool round, with optional manual lock and per-tool timing telemetry.
DSH host plugin: cuts tool-call latency by auto-downgrading reasoning_effort for simple tool tasks, with per-tool timing telemetry.
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)
Codex-style reasoning-effort slider embedded in the DSH model selector
DSH extension suite: runtime injector, task-aware reasoning-mode routing preset, cross-session mailbox, agent teams, model delegation, skill manager, and plugin-manager UI.
唯稳律(Weiwen's Law)通用因果引擎(白箱呈现)—— DeepSeek Harness (Cordis) 插件实现
J-Space Cognition Suite V3.6 - Inference-time cognitive control and deep reasoning for DeepSeek models
DeepSeek Harness composer model seat: model picker plus a three-stop reasoning bar (小难梁 / 梁子 / 梁圣)
View and manage archived sessions in DSH: browse the archive, read full transcripts in a chat-style dialog (turns, reasoning, tool executions), and remove unwanted records. Works on desktop and web.
Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, and per-session measurement records