Plugins

Fork of kirkchinese/dsh-capability-catalog 0.1.4 (cannot be installed alongside the upstream capability catalog / @kirkchinese/dsh-rea): a REA-focused MCP gateway with three fixed search, describe and call tools, cached schemas, session controls and native DSH result handling. Requires DSH 0.2.1-rc.4 or 0.2.2-rc.1 and a Node/npm setup able to run REA.

Drive the NI Multisim 14.3 install on a Windows machine through nine msim_* tools: open and save .ms14 designs, read and edit component values and circuit parameters, run DC operating point, AC sweep, single-frequency AC and transient analyses, export schematics, BOM and netlists. A Win32 channel drives the visible window to run the Analyses dialog and capture Multisim's own schematic view and waveform plot; a SPICE command-file engine handles designs that expose no probes; an offline reader unpacks the .ms14 container without starting Multisim at all. Requires Windows, NI Multisim 14.3, and a 32-bit Python 3.11-3.13 with pywin32.

Indexes public AI-company job boards (Greenhouse, Ashby, Lever, Workable, SmartRecruiters), scores postings for AI relevance, extracts the requirements from each job description, and produces a scheduled daily Markdown digest.

Windows multi-drive dashboard that labels cleanable, caution, and system space in green, yellow, and red, audits download folders, and suggests how to split data across drives.

MySQL and PostgreSQL connection manager with a schema tree, table search, SQL console with completion, and four agent tools for listing connections, searching tables, inspecting structure, and running queries.

Emotion, energy and per-user portrait engine for AI characters: a 303-word leveled emotion library with lowest-level replacement and a promotion buffer, a spirit meter with easter-egg state transitions (excited / suppressed / angry), and per-user portraits. Requires your own OpenAI-compatible LLM endpoint and API key (EMOTION_LLM_KEY or emotion/config.json).

Unified long-term memory hub: captures turns into L0 evidence, distills in the background into L1 facts / L2 scenes / L3 profile (depth configurable), recalls via hybrid BM25+fuzzy search, ships 13 memory_* tools, traceable lineage back to source turns, optional Hindsight backend, and a built-in memory panel with three entry points.

Lingshu (灵枢) is a brain-inspired persistent memory, persona and growth system for AI coding agents: pure Python standard library, zero dependencies, local-first, requires Python 3.9+. Hippocampus/cortex layered memory with forgetting curves, dream consolidation, fuzzy associative recall, emotion system, persona drift protection, knowledge base, self-authored skills, and a local web panel. Ships as a DSH bundled skill; the separately installable cordis startup-injector plugin auto-injects sessions only when Lingshu is installed at ~/.dsh/skills/lingshu (or brainPy is configured) and Python 3 is available; the optional update check contacts GitHub/Gitee.

Obsidian-compatible Markdown notes in the DSH sidebar with search, tags, backlinks, graph, audio notes with transcription, a paint canvas, OCR (needs tesseract), client-side encryption and notes_* agent tools; the release tarball and the npm package carry a prebuilt Linux x64 daemon, other platforms build it from source with Go.

A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).

Windows DSH session manager: recoverable recycle bin, subagent-tree cleanup, workspace file discovery and Explorer highlighting, plus categorized file-path export.

Elides stale, oversized plain-text tool results from the model-visible session surface once the prompt cache goes cold, replacing each with a stub that keeps the tail lines and any error lines, and reports per-request and cumulative savings in the composer footer.

Material library for dsh: collect a folder, file or note from a conversation, keep it in real folders with tags, browse it Finder-style, reopen the source chat's output in one click. Ships a materials_archive tool plus auto-filing rules: file a task's deliverable once, and every later scheduled run files the new documents by itself.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Turns "restarting the host" into one interrupt that many sessions can share. Several sessions queue onto the same restart (8 by default, configurable, joinable at any time including mid-wait); the host is closed once and relaunched once; then each waiting session is woken separately with its own reason and starts running its own work without waiting for the others. Each session decides independently whether to resume, one failed delivery never affects the rest, and a session can drop only itself without cancelling everyone else's restart. Windows desktop only.

Two triggers (a heartbeat and a log marker) that wake a session and let the agent decide whether to say anything; silence is a reply. Off by default: set sessionId (the target session) and enable it in the profile config, and if replies are forwarded to a chat app the send layer must drop the SILENT marker.

Idle-time context truncation for a single DeepSeek Harness session. After a configurable number of idle hours the older conversation is dropped without a summary, so one long-lived session cannot leak one task into the next; it ships a per-session toggle, a tab next to the chat, and a /truncate command that IM bridges can drive.

Turn on the built-in session full-text search backend (session-query-sqlite, SQLite FTS5) that dsh ships disabled by default, so the sidebar magnifier searches message bodies with snippets instead of titles only.

A right-sidebar tab listing the files DSH Sessions produced, newest first, with the Session in view expanded on top: a click copies a row's full path, a double click previews it in the sidebar, and a file can be pinned in one Session or in all of them.

Persona state and slow evolution for DSH: five state dimensions (valence, arousal, energy, intimacy, focus) move after each turn and decay toward baseline over time; four scene types (work, tech, support, chat) modulate reply length and warmth without changing the state itself; the Soul panel keeps a persona card plus weighted evolution entries and injects them into the system prompt persona-first under a 4000-character budget. Ships a browser panel with a persona card editor and a live state view (the five metrics plus the last six events), appends a JSONL trace to disk, and seeds a usable default persona on first install.

Injects a configurable whale-girl persona into every DeepSeek Harness system prompt.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

Connects Qoder models to DeepSeek Harness through the official Qoder CLI over native ACP stdio (no reverse-engineered model API), with qoderclicn (China) having a verified real ACP tool loop; qodercli (international) is selectable but its real inference path is not yet verified. Requires Node.js 22.18+ and the chosen Qoder CLI installed and logged in on the same machine; the plugin does not install or manage accounts.

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider.