Dev & Plugin Tools

DeepSeek Harness dual-face plugin: a visual plugin manager tab in Web Settings — enable/disable any plugin row, check installed plugins (including official @deepseek-ai/* rows) against the npm registry, update them, repair pristine files, and update the h

DeepSeek Harness plugin: live DeepSeek official service status (status.deepseek.com) in the sidebar — overall status, component statuses, incidents, and uptime.

Logical-call context taxonomy for the DeepSeek Harness Web profile

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

A dsh status plugin with host-plane and browser halves: harness runtime health (process, listener, API-key presence, memory, uptime, plugin inventory) as JSON plus server-pushed SSE alerts, surfaced as a header badge with an expanded panel in the Web UI

Local-first failure evidence capsules for DeepSeek Harness sessions

Harness 事件流审计面板：观察事件类型、分发模式、计数与最近事件，帮助插件作者理解 harness 内部发生了什么

Self-editing desktop workbench for DeepSeek Harness: a full dsh web replica with an edit mode in which the agent modifies the workbench (patch layers, plugins, UI) with hot reload.

/repro exports a minimal, secret-scrubbed, replayable problem bundle: the session log, failed commands, and Git diff.

The `dsh pm` plugin manager: multi-source search (awesome list + GitHub + npm), install/remove/update per profile, and a doctor audit of manifests, bundle patches, and version drift.

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration.

Telemetry backend exporting turns, model steps, and tool calls to yiTrace.

Enforced pain-point gate: after two non-converged experiments it injects the three questions, denies non-investigative tool calls until answered, and blocks same-direction retries.

Plugin dependency graph for DeepSeek Harness: which plugin provides the services every other plugin injects, read from the live Cordis runtime.

Automatic bounded test runs with persistent recent results.

Replaces the web profile's pwsh shell executor with a subclass that rewrites every command through `rtk rewrite` before execution for token savings, running the original command unchanged on any rewrite failure (no equivalent, missing rtk, timeout) and keeping sandbox semantics intact.

Preview native WeChat Mini Programs in the DSH sidebar with a local runtime and WXML source locations.

Builds, tests, archives and runs an Xcode project or workspace on iOS or macOS through xcodebuild — a live filterable build log, scheme and destination pickers read from the project, and log streaming for simulators and USB devices, including iOS 16 and earlier over libimobiledevice, whose app logs stay readable while the device is locked. macOS only.

Adds a Check for Updates row in Settings and a right-sidebar card that update the DSH CLI and every profile plugin, with npm channel selection (auto/stable/next/alpha), minimum release age, backups, one-click rollback and a test reminder for the badge and browser notification.

Loopback-only ACP door for DeepSeek Harness: attach an external client (such as the DSH Panel VS Code extension) to the kernel you already have running, exposing session listing and permission presets.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Code graph and knowledge base over an embedded FalkorDB: AST symbols, caller/callee tracing, refactor blast radius, affected-test discovery, clone detection, cross-language porting contracts and spec-to-code traceability.

Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.