dsh-daily-brief
Daily activity brief for DSH: per-session turns/messages/tool-call stats across live sessions. Read-only.
39 results
Daily activity brief for DSH: per-session turns/messages/tool-call stats across live sessions. Read-only.
DSH Web plugin for Agent execution quality diagnosis reports.
Fold tool-call cards in the DSH conversation into a minimal expander — maximum collapse, click to expand
DSH client plugin: Think token-count display + optional tool-call grouping.
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
Fail-closed runtime tool-call loop guard for DeepSeek Harness.
DSH client plugin: render a session as an S-shaped (boustrophedon) trajectory timeline, with per-turn nodes and file sub-nodes linked by tool-call edges
DeepSeek Harness web UI plugin: tool-call value graph over conversation trajectories — call cost/count/duration weights, bottleneck split, and next-turn optimization prompts.
Auto-fold context/system messages in DSH conversation — hide the large system prompt / instructions by default, click to expand.
Neutralize tool calls with invalid JSON arguments on the wire, so one malformed model generation cannot brick a session against strict OpenAI-compatible servers (vLLM et al).
DSH plugin: adapts DashScope/闂傚倸鍟锟犲闯闁垮顩查柟瀵稿У椤忋儵鏌?DeepSeek endpoints that lack native tool calling by converting tool definitions to prompt text and parsing model responses for tool calls.
DeepSeek Harness plugin that shows the actual provider/model used by each subagent inside native tool-call rows and the native subagent catalog.
Restyle pwsh tool-call cards in DSH session replies (CSS-injection + optional DOM decoration), modeled on dsh-file-mentions
Serena dashboard lens for DeepSeek Harness — m4/m5 tabs embedding Serena's tool-call stream inside the GUI
Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.