102 results
Chinese-platform last-30-days research skill covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao. Includes Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output.
Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — THREE agent presets in one install: vibe-math-v2 (probability-driven: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3 (THIRD-generation, recommended: paper-style Markdown knowledge base with Problems/Progress/Propos/Methods/Verified + planner-agent scheduling that decides the next N actions + universal theory/method invention library + agents write their own Markdown directly via a per-file write lock), and vibe-math-v4 (FOURTH-generation: persistent self-organizing resident subagents that message & meet to decide all tasks, verify only by unanimous consensus, /compact at a context threshold, and stop only when all agree the problem is solved). Installing this bundle auto-installs all three presets (v1 was removed at v2.0.0).
DeepSeek Harness URL reader: fetch any webpage (HTML/JSON/RSS/Atom), auto-detect encoding (UTF-16 BOM/GBK/Big5/Shift-JIS), extract clean main content with auto-pagination, output compact text/Markdown to save tokens. Zero runtime dependencies, no API key, drop-in. Follows meta-refresh shells, reads JSON-LD metadata, honors base href.
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 awareness (compaction summaries join recall/search, a compaction notice with one-click /compact fill) layered on the ordinary composer draft only.
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
One DeepSeek Harness Codex capability bundle for ChatGPT login, LLM access, Web Search, and durable Image Creation
A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance
Mobile adaptation for the DeepSeek Harness Web GUI: single-column layout, sidebar drawer, compact header/composer, fullscreen settings, trajectory floating details, stats pill panel
会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）
Codex-style one-line disclosures for DeepSeek Harness reasoning and tool activity
Third-party DSH WebUI enhancement plugin: custom backgrounds, theme colors, prompt presets, token visibility, and manual context compaction.
Merge consecutive same-tool calls in the DSH WebUI chat flow into one card with compact child rows (all built-in tools by default).
Context Assembler DSH V0.99 — Context Assembler plugin for DeepSeek Harness (dsh): context compaction, cache-friendly topic-block management, water-pressure topic splitting, tool trace/rewrite, handoff planning and reality recall injection.
DeepSeek Harness plugin that uses configured model providers for image analysis and context compaction.
Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log. 压缩率精确兑现，历史永不销毁。
为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩，解决极简模式长任务无法持续工作的问题。
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
A compact per-model reasoning effort editor for DeepSeek Harness custom providers.
大 engram 小 KV：外置 engram 转接层（跨会话分层记忆：global/project/session，AI 自主决策归属 + 因果链接索引 + 渐进披露 + 主动唤醒），为 DSH 实现超长上下文记忆稀疏路由，与官方 compact 共存（官方腾 KV，engram 保细节）
DSH context-window relief: knowledge base (ctx_index/search), routing enforcement (deny flood tools), sandboxed execution (ctx_execute/batch Think-in-Code), and session continuity (post-compaction restore).
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
Mobile adaptation for the DeepSeek Harness Web UI: compact typography, drawer sidebar, two-page settings, responsive tables and stats, safe touch targets. Pure CSS injection, no source modification.