114 results
Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions — with structured entry tags (kind/status), a grouped summary view, automatic context injection, an archive on clear, and an optional read-only web panel
Fold each DSH Web turn's thinking, tool calls and context into compact expandable process boxes cut at every piece of model text, and reuse the shipped turn-process disclosure row as the toggle whenever it exists.
Save and load a compact, Git-tracked handoff for DeepSeek Harness sessions
Real-time context occupancy meter for DSH Web: draggable compact/detail panel, per-tool usage, settings-editable cost table (CNY/USD, flat or peak/off-peak), per-provider usage and token totals
A compact DSH model and reasoning quick-switcher showing the last three choices.
提问面板折叠：agent 提问时把问答面板折叠成一条紧凑条（保留标题与取消），展开后回答草稿不丢。Collapse the DSH question panel into a compact strip; the unsent answer draft survives expand.
Workspace History: journals every compaction summary to <workspace>/.dsh/history/<unix-ts>.<short-session-id>.md, and adds a History subtab to the Workspace Overview tab for reading the journal. Per-session toggle lives in the granular Settings tab — requires dsh-granular-settings (hard dependency).
Chat branch tree plugin for DeepSeek Harness: mind-map of conversation branches, group folders, archiving and compaction preview.
Document-review modal for DeepSeek Harness web: design documents and plan reviews open in a full rendered-markdown modal instead of the compact composer card.
Durable DeepSeek Harness bundle: the local-model performance tuning carried as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updates
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Browser-style UI zoom for DeepSeek Harness and DSH Desktop — Ctrl +/−/0, Ctrl+wheel, and a compact zoom widget with a saved level.
取代 DSH 内置 plan mode 的计划交付体验：计划先写成 markdown 文件，经侧边栏「计划面板」展示，聊天里只剩紧凑审批卡（审批流与原版一致）。 | Replaces the built-in plan mode's plan delivery: plans are written to a markdown file first and shown in the better-sidebar plan panel, leaving only a compact review card in chat (approval flow unchanged).
DSH plugin: Codex-style context management — token-budget notice, model-facing new_context, and handoff reset instead of summary compaction.
Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.
Idle-triggered context compaction for DeepSeek Harness: compact a session once it has gone quiet past a token floor
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness
Replace the DSH Web reasoning-effort chooser with a compact animated FX slider that scales with effort level.
AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization
Model-scoped DSH plugin: GPT Responses lifecycle, Native V2 compaction and Hosted/Alpha Search; Grok native Web/X Search
DSH web plugin: shrink chat content density — markdown typography tokens, message-body spacing and the user bubble, live-adjustable from a card under Settings → Plugins. Host half registers the settings namespace that makes the Plugins tab dispatch the card.
DeepSeek Harness plugin: aggressive token optimization without affecting task quality. Trims tool results, manages context window pressure, optional LLM-summary compaction, stable prompt-cache layout.
Summary-free context window rollover, model-authored notes, and scoped raw history lookup plugin for DeepSeek Harness (DSH)
Official-basic Codex compaction with an optional account-owned native summarization seam and legacy structured reader; no core patches or duplicate login.