Plugins

Récupération après redémarrage pour DeepSeek Harness web : après un crash ou un redémarrage, un tour d'agent interrompu reprend automatiquement (listener agent/created côté hôte, pas de conflits de synchronisation navigateur).

Skill d'analyse et de filtrage d'actions A-share : cotations en temps réel, scores de timing technique, signaux d'achat/vente et liste de surveillance gérée.

Rapports de dérive comportementale pour les sessions DSH : compare deux journaux de session et rend compte de l'alignement des séquences d'outils, du mélange d'outils, du volume de raisonnement, du timing, des reprises et des fichiers ciblés, avec un seuil CI facultatif. Zéro dépendance.

Panneau flottant d'apprentissage du code : édite et exécute Python/JavaScript/TypeScript/PowerShell avec code de sortie et durée, note des cours JSON et exporte la progression, conserve notes Markdown et extraits, et envoie code et question dans la conversation pour réponse par le modèle principal.

Task timing for DSH agents: a task_clock tool that measures elapsed time on the host monotonic clock, resumes across DSH or system restarts with the gap estimated, and returns unknown rather than inventing a number; it does not touch presets.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Comparaison côte à côte en lecture seule d'historiques de conversation DeepSeek Harness associés, incluant messages, appels d'outils, réponses, minutage et utilisation.

Per-answer timing breakdown: splits each reply into model, tool and other time, with first-token, decode and per-tool totals, and keeps a local JSONL ledger. Needs Node 24 or newer in the DSH runtime.

Toasts from DeepSeek Harness when a turn finishes, and when it stops for approval, a question or a plan exit. Native on Windows, text and timing configurable.

Gowin (高云) 1.9 FPGA toolchain control for dsh: 15 tools covering environment and license probe, .gprj/.cst project and constraint auditing against a real GW1N board pinout, gw_sh batch synthesis and place-and-route, pnr resource and timing report parsing, programmer_cli JTAG scan and flash, arbitrary gw_sh Tcl, and the GAO on-line logic analyzer capture chain — plus a bundled gowin-fpga skill and three field-note references. Pure JS, zero runtime dependencies.

Prepares context summaries in the background and applies them at safe step boundaries, with native compaction fallback and a per-conversation history of summaries, application status, timings, and token usage.

Checks nursing records for entry timing, signatures and assessment-form completeness, against 《病历书写基本规范》 and other published documents. Reports what is missing or out of sequence for a human to review.

Ships a skill for verifying a change with the cheapest check that still yields a definite answer: an L0-L3 cost ladder from static checks to a single suite, condition polling with a timeout instead of fixed sleeps, assertions that can actually fail, and durations that are measured rather than remembered. The package also carries the two zero-dependency Node tools the skill calls - wait-until.mjs (poll a command, a file, or a port until it is ready) and measure-runtime.mjs (wall-clock timing for any command, plus a segmented timer for library use).

Persistent work-progress row in the band below the composer: task completion, a progress bar, and what the agent is doing right now (generating a reply or running a tool), expandable into the full task list with turns, steps, timings and context usage.

Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.

Reminders and task timing for DeepSeek Harness: interval alerts while the model runs and overdue alerts past the planned time, plus a persistent red decision alert when the model needs your input (in-app reminder cards with sound while you are in DSH, system toasts when you are away, configurable or keep-until-dismissed card dwell time, and clicking a card jumps to its session); plan time per session, count model runtime only, and report actual vs. planned when the task ends, with a task board and persistent local records.

DeepSeek Harness dashboard: per-session statistics (tokens, timing, tool and skill calls) as a dedicated Statistics view tab. Compatible with dsh v0.1.2-alpha.1 ~ rc.1 (see README).

Local Qimen business-timing workbench for DeepSeek Harness, with nine palaces, deterministic scoring, future-window ranking, and direction advice.

DeepSeek Harness (dsh) plugin that exports a session as a self-contained, replayable HTML file — full transcript, faithful tool cards, and playback at the original timing.