dsh-perf-patch
仅运行时性能补丁，用于 DeepSeek Harness：合并 agent-mount 工具/变更风暴，按修订版本缓存工具架构，并提前终止 dsh-ops presentation 探测。不修改任何第三方源代码。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:ChenXu233/dsh-perf-patch#96d7dcb1d18b25262cb0294175f154e7232eb886Perf Patch 以 dsh-perf-patch 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Runtime-only performance patches for DeepSeek Harness (DSH) when third-party plugins make
the host O(N) slow. Nothing in node_modules is edited: the patches wrap host services at load
time, and each one fails safe — on any doubt it falls back to the original code path instead
of changing behaviour.
Built and measured on DSH Desktop 0.2.1-rc.2 (Electron 44 / Node 24 / Windows 11) with
dsh-ops and dsh-mcp-connector installed.
tools/change stormMounting an agent registers ~161 tools. Every registration fires tools/change, and every
listener that reacts (discovery reconcile, PTC reconcile, MCP governance) replays its full
O(tools) work. One agents.create therefore emits hundreds of notifications, each listener
re-running hundreds of times.
Fix: while agents.create / agents.resume runs, tools.layers.onChange is suppressed and
the notification is emitted once, synchronously, when the outermost call returns.
Suppress + synchronous flush is deliberate. Flushing via queueMicrotask starves the event
loop (listeners queue more microtasks than the loop drains) and was observed to freeze the UI;
that variant was removed and is not shipped.
tools.schemas() deep-clones on every readschemas(scope) clones every tool's JSON Schema; schemaOf(def, true) clones one. Both are pure
functions of the tool revision / definition, yet listeners call them in loops.
Fix: memoize schemas(scope) per tool revision (WeakMap keyed by scope, invalidated on
tools/change) and schemaOf(definition, true) by definition + parameter identity. Returned
objects are shared between callers, so treat them as read-only.
dsh-ops/lib/presentation.js decides "is this agent on PTC presentation?" by calling
systemPrompt.assemble({scope, signal}) and then reading exactly one thing:
assembly.sections.some(s => s.name === 'tools:ptc-only' && s.text.trim() !== '')
assemble() renders ~36 sections and structuredClones every tool schema (~250–310 ms
measured). dsh-ops does this 6× per live agent, per reconcile.
Fix: wrap systemPrompt.assemble. When — and only when — the call is one of those probes,
return a minimal assembly built from the same layers:
{ sections: [{ name: 'tools:ptc-only', text }], contexts: [], tools: [] }
Probe detection uses dsh-ops' own marker (isPresentationProbe, a WeakSet reached through the
module cache); if that import is unavailable it falls back to "the stack contains
dsh-ops/lib/presentation.js". Every other caller — including the real prompt assemblies in
ptc/index.js and discovery/index.js — passes straight through.
The section text is recomputed on every call. Caching it was tried and reverted: a stale control input turns reconcile into a fixed point that never settles, and freezes the host.
Measured on a 3-agent instance: per probe 254–312 ms → 0 ms (~4.9 s per reconcile sweep), with the PTC decision byte-identical for all 3 agents.
cd ~/.dsh/profiles/desktop
npm install ChenXu233/dsh-perf-patch
Then list "dsh-perf-patch" in the dsh.profile.bundles array of the profile's
package.json. The package ships dsh.bundle.patch → cordis.patch.yml, which inserts the
loader entry. Adding the name to bundles alone is not enough — without the patch layer the
plugin is never loaded.
From a checkout: clone this repo into <profile>/node_modules/dsh-perf-patch and add the name to
bundles the same way.
| Variable | Effect |
|---|---|
DSH_PERF_PATCH=0 | Disables all three patches at load time. |
DSH_PERF_PATCH_VERIFY=1 | Probe short-circuit also computes the full assembly and compares. On divergence it logs an error and permanently disables the short-circuit for the session. |
Runtime counters:
globalThis.__dshPerfPatchProbe // { hits, bypass, mismatches, enabled }
hits = probes answered short, bypass = calls that went to the real assemble. If hits
stays 0, detection is not matching and the plugin is a no-op.
tools/change during
mount would now see one.schemas() / schemaOf().tools.schemas() deep copy with 258 tools, linear slowdownIf this plugin causes a problem: set DSH_PERF_PATCH=0, confirm it disappears, and open an issue
with the numbers.
MIT