@fakechris/dsh-track
Track Bridge: embedded task-management engine for DeepSeek Harness — decision-point protocol, capture wall, and Linear-shaped issue store over session events + storage KV
34 results
Track Bridge: embedded task-management engine for DeepSeek Harness — decision-point protocol, capture wall, and Linear-shaped issue store over session events + storage KV
Delivery quality gate for DeepSeek Harness: grill the requirements, test the implementation, prove the delivery, and gate the handoff with a deliverable/rework decision.
Cross-session agent-to-agent messaging for DeepSeek Harness: claims, verification and a decision ledger, so two agent sessions don't repeat, contradict or deadlock each other.
决策分屏:agent 消息尾部提供「在侧栏查看全文」入口,右侧详情栏独立滚动展示该条消息的完整 markdown,边看全文边回主窗口操作。
An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
Ask DeepSeek to falsify a file or gate a PR. Receipt: PASS / PASS_WITH_DEBT / BLOCK. Adjudicator, not a second opinion. Green lint is not a ship.
Advisor strategy for DeepSeek Harness: escalate hard decisions from the executor (deepseek-v4-flash) to deepseek-v4-pro through the official subagents channel.
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 automatic context injection, an archive on clear, and an optional read-only web panel
Auto-capture key decisions from dsh sessions into a versionable DECISIONS.md and inject them into future sessions
DeepSeek Harness plugin: cross-session memory for the model. Full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context — recall earlier decisions, commands, and mistakes.
Decision-driven AI company orchestration with HR governance, monetary budgets, model discovery, and deterministic audit for DeepSeek Harness
Work Continuity for DSH — goal/decisions/checkpoints/next-steps as explicit WorkState, decoupled from generic memory
Content-addressed proof that recorded DSH authorization decisions and effects agree
Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.
Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
Windows-grade notifications for DeepSeek Harness: system toasts, custom sounds, and a taskbar tray badge for task completion and decision prompts — a native DSH profile plugin (bundle + client + settings namespace), zero patching of built-in packages.
Skill bundles for DeepSeek Harness: a bundle box holds a root skill and sub-skills, loaded by metadata (loadSubskills) or by model decision from body text.
Durable delayed decisions that wake cold DeepSeek Harness sessions with bounded authorization
Track human decisions for related DeepSeek Harness conversation branches.
决策地图 (Decision Map) — a DeepSeek Harness bundle plugin that renders the current session's execution trace as a readable timeline plus stat cards.
DeepSeek Harness 插件:Host 半区向系统提示词注入规则,要求 LLM 把需要用户决策的内容用 <!-- dsh-todo:start -->…<!-- dsh-todo:end --> 成对标记包裹(渲染不可见);Client 半区仅对标记块在输入框上方显示带复选框的表格增强 UI,支持单行/整体编辑与「直接发送」「填入对话框」「关闭」,任意操作完成后关闭。
A visual decision workbench for DeepSeek Harness: explore ideas, focus branches, turn choices into execution graphs, and run them one node at a time.