dsh-think-any-lang
DeepSeek Harness plugin: a General-settings selector that chooses which language the model reasons in, via a system-prompt section.
378 results
DeepSeek Harness plugin: a General-settings selector that chooses which language the model reasons in, via a system-prompt section.
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
Hard-stop consecutive identical DeepSeek Harness tool calls after a configurable streak.
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
Security for DeepSeek Harness in two layers: source-backed pre-install vetting plus fail-closed runtime guardrails and HMAC-chained audit logs. Zero runtime dependencies.
Running-turn TPS badge for DSH Web: live tokens-per-second inside the Deep diving status row
Blue Archive-inspired DSH theme with a Shiroko desktop companion, secure DeepSeek balance lookup, low-balance alerts, Codex-style reply bubbles, and petting effects.
OMV Audit Desk: an evidence-first vulnerability audit workbench for DeepSeek Harness
Export-copy redaction for DeepSeek Harness session telemetry
DSH usage statistics dashboard: token / cost / duration / session aggregation with trend, heatmap and calendar views (settings.section "数据看板").
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
DeepSeek Harness workspace & session enhancement plugin: recycle bin, cross-workspace session drag, ungrouped sessions, multi-folder workspace roots, in-app directory picker, session merge, folder/file sections, multi-select picker, session files & drag-drop upload, file preview — shipped as an overlay patch-set with install scripts
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板
Event-driven development automation, offline standards, CI adapters, and quality gates for Cordis plugins in DeepSeek Harness.
Codex themes (light + dark) for the DSH web GUI as a configurable appearance plugin: maps codex-theme-v1 knobs onto the DSH --dsw-* token system and adds a Codex appearance settings section (colors, contrast, diff/skill semantic colors, UI/code fonts) persisted to settings.yaml.
DeepSeek Harness plugin: auto-detect secrets pasted into the composer, store them in the official credentials seam, and send [secret:REF] placeholders to the model instead of the value.
DSH plugin: Codex-style side conversations (/side, /btw) in an ephemeral right-workspace panel with Side/Subagents/Goal sections and a ChatGPT-style pinned-notes board (置顶摘要小黑板), plus a best-effort sidebar collapse hotzone.
Adds an 'Invert selection' button to the fetch-models dialog of the Models settings section
DSH AI 代码安全审查插件:secure_scan/secure_diff/secure_fix_verify/secure_report/secure_export/secure_baseline/secure_deps/secure_policy_show/secure_policy_set 九工具,40+ 确定性规则、密钥熵检测、git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite,零运行时依赖。
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
Find DSH plugins and security-scan them before install
KnowLP-RAG: dual knowledge-graph retrieval for Markdown notes — DeepSeek Harness (dsh) bundle: MCP server + native Cordis plugin
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness