dsh-maze
The execution maze for DeepSeek Harness agents: see how the agent actually worked — main path, detours and backtracks on one timeline, with data tracks, deterministic analysis, and multi-session comparison
17 results
The execution maze for DeepSeek Harness agents: see how the agent actually worked — main path, detours and backtracks on one timeline, with data tracks, deterministic analysis, and multi-session comparison
Deployment-configured prompt prefix for DeepSeek Harness: ordered system-prompt sections ahead of the persona and reference user/assistant exchanges injected into every ordinary conversation request as real alternating messages (request-path interception, zero session-log writes).
Session-log usage dashboard for DeepSeek Harness
DSH 插件:零侵入运行事实遥测——纯观察者(零工具注册/零 LLM 调用),session 结束时自动把任务/模型/工具/失败/状态/时长按一行一会话写入观测卡,附自动统计汇总区与 raw sidecar。Zero-intrusion run-fact telemetry for DeepSeek Harness: one row per session in the observation card + auto stats + raw sidecar.
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
Frozen, topology-aware session maps for DeepSeek Harness
DSH web GUI token-consumption heatmap: a daily/weekly total-token usage panel fed by session-log usage events
Agentic Surface Compaction (ASC) for DeepSeek Harness: the model decides when and what to compact, committed as durable session-log replacements with full replay, search, and degradation
dsh-memory — cited memory over DSH's lossless session log: post-session distillation into human-auditable markdown files, a compact recall index, memory_read/memory_expand tools, and a dsh-memory CLI
DSH web plugin: right-side context-and-files panel (directory browser, injected-context documents, read-only git commit graph) plus the session-log download action
Timesheet for DeepSeek Harness (dsh): turn-based time tracking from session logs — totals, per-day, per-project, per-provider, per-source rollups, tool-call counts, failure rates, and time-to-first-token. CLI + agent-callable timesheet tool, zero runtime dependencies.
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
DSH 助手消息锻造台:可创建/修改/注入测试用 assistant 消息,并可导入识别 session.jsonl(.zstd) 会话日志。
DSH plugin: context archiving + historical retrieval — archive_session / search_archive tools over the session-archive skill (zstd session-log decode).
Memory Standard Protocol (mm) for the DeepSeek Harness: layered MEMORY.md + deterministic budgets + frozen snapshots + cross-agent markdown/URI interop + session-log digestion. Ships as a dsh bundle (tools: mem_read, mem_write, mem_search, mem_budget, mem_digest) and a standalone CLI.
DSH_HOME single-instance lock plugin: aborts startup loudly when another dsh server already uses the same data directory, preventing concurrent session-log writes (the 'seq gap in committed region' corruption class)
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests