by Missher12

Privacy-bounded self-improvement plugin for DeepSeek Harness

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Cron scheduler for agent tasks: create jobs by natural language or a sidebar UI, inject a user message into a new or fixed session on schedule to trigger a full agent turn, with run history, manual tr

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Engine-enforced guardrails for DeepSeek Harness agent swarms: quality gates reject half-done work, crash-safe checkpoints resume in place — keeps AI teams from breaking, not just running.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to projec

Auto-send every DSH turn result to WeChat: listens for task completion, extracts the final assistant message and pushes it raw via the WeChat iLink bot (real delivery check, never fake success). Requi

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

Visual multi-agent DAG workflows for DeepSeek Harness with live execution, restart recovery, and Feishu integration.

Disk-persisted execution planning for DSH: milestone/step state machines, dependency gating, an audit event stream, and a deterministic completion gate via dsh tools, CLI, or skill.

Scheduled DeepSeek Harness Agent tasks with mandatory end-to-end tests, run history, and bidirectional delivery through nine messaging channels.

Appends ambiguity-handling rules to the dsh system prompt so the agent asks clarifying options before guessing.

Recurring task scheduler with an append-only delivery ledger: window-aligned dedup execution, failure/abandoned rows, and same-window retry redelivery.

Tender search and bid intelligence in DeepSeek Harness with proposed project search, rule screening, human review and Excel/PDF exports using user-authorized Qichacha MCP.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five

Interactive canvas for visualizing Agent, Subagent, Workflow, Phase, and tool relationships in DSH Web.

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ t

Antigravity-style run_command for DSH: short commands return inline within a configurable wait window (default 10s) while longer ones auto-promote into ctx.jobs for later collection and completion not

Turns DSH conversations into reviewable community feedback and, after confirmation, submits it to the official DeepSeek Harness Discussions.

Independent read-only acceptance layer: spawns a read-only verifier before each top-level turn closes and steers non-pass gaps back into the agent.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.