dsh-limit-break
持久的跨会话记忆，以及能够应对基于主机名拦截的获取阶梯——适用于 DeepSeek Harness 的四个小工具。
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:Ma354/dsh-limit-break#aacea219dffd04fa3c9da2f8c0edee6100627eb1Limit Break 以 dsh-limit-break 发布，当前版本为 1.6.0。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。
Four small tools for DeepSeek Harness that came out of a self-benchmark: two things an agent is normally told it cannot do, made cheap enough to just do.
| Tool | What it does |
|---|---|
memory_recall | Ranked search over a JSON fact store that outlives the session. Omit query to list everything. |
memory_save | Write or overwrite one fact: { id, statement, value?, unit?, details?, tags?, source? }. |
resilient_fetch | Fetch with a four-rung ladder and a report of which rung answered. |
memory_stats | Where the store is, how many facts, how big. |
Zero npm dependencies. No import-time side effects. Everything fails soft — a broken store or a dead network returns an error object, never an exception that could take the host down.
Recall quality. memory_recall is measured, not vibed: tools/recall-bench.mjs runs 20
hand-labelled questions against the live store and prints hit@1 / hit@3 / MRR. At 1.5.0 the ranking
skips English stopwords, stems, matches whole words (with a prefix fallback, so ray finds
raytracer), splits dotted ids into segments, weights each query token by inverse document
frequency, and rewards a whole-phrase hit: hit@1 0.75 → 0.95, MRR 0.867 → 0.975 on the same 20
questions and the same 20 facts. The one remaining miss is a genuinely ambiguous question that
matches two benchmark facts.
Runtime requirement: curl. Rung 1 of the fetch ladder is plain fetch and needs nothing; rungs
2–4 (IPv6 → IPv4 → sibling hostname) shell out to curl, so it has to be on PATH. Windows 10+,
macOS and mainstream Linux all ship it. Without it the ladder degrades to rung 1 and says so in the
report instead of pretending it climbed.
Memory. A session starts from zero. A store on disk plus a read at the start is enough to beat that. Measured with two brand-new agents, zero context, the same five questions: 5/5 with the store, 0/5 without — and the control did not hallucinate, it answered "I don't have that" five times.
Network. The reflex "this host is unreachable" is wrong more often than it is right. Measured on
one network, same edge IP, 75 seconds apart: api.wikimedia.org → 200 in 0.43 s,
en.wikipedia.org → connection reset in 1.21 s, api.wikimedia.org again → 200 in 0.39 s. The
block was keyed on the TLS hostname, not the address. So the ladder tries, in order: plain fetch →
IPv6 → IPv4 → a sibling hostname of the same service whose certificate still verifies
(*/wiki/Title → api.wikimedia.org/core/v1/wikipedia/<lang>/page/<Title>).
It does not disable certificate verification and does not route through a proxy that would impersonate the origin. Those are MITM, not workarounds.
dsh plugin --profile <profile> add dsh-limit-break
Then restart that profile. In the desktop app, install it from Settings → Plugins instead — the desktop profile is owned by the app's plugin manager.
The package declares dsh.bundle and ships cordis.patch.yml, so dsh plugin add mounts it with no
manual editing. If you are mounting it by hand, add to profiles/<profile>/cordis.patch.yml:
- insert:
- id: limit-break
name: dsh-limit-break
A hand-mounted entry still needs the package on the profile's dependency list — a bare insert for a
package the profile does not declare is silently ignored.
$DSH_HOME/memory/facts.json, schema:
{ "schema_version": 1,
"facts": [ { "id": "", "topic": "", "statement": "", "value": "", "unit": "",
"details": "", "source": "", "timestamp": "", "tags": [] } ] }
Plain JSON on purpose: anything that can read a file can use it, with or without this plugin.
Writes are tmp-file + rename, and a save takes a .facts.lock (created O_EXCL, stolen after
15 s if its writer died) around the whole read-modify-write, so two sessions saving at the same
moment both keep their facts. tools/concurrency-selftest.mjs states the numbers: 16–17 of 48
saves lost before the lock, 0 after.
disabled: true on the entry in cordis.patch.yml — Cordis recomposes in about a second.dsh plugin remove dsh-limit-break, then restart.$DSH_HOME/memory/ and is safe to keep.Measured, not guessed — each line is something a session actually hit.
{ ok: false, code: "memory.locked" } rather than hanging. Read paths take no lock, so a save
still cannot stop a reader from seeing the previous snapshot.memory_recall ranks by keyword overlap only (id/topic/tags/statement/details), no
embeddings: stopword-filtered, crudely stemmed word matching weighted by idf, so it is good at
"which fact did I mean" and bad at paraphrase. tools/recall-bench.mjs states the current
numbers (hit@1 0.95 on 20 questions); a query that shares no word with a fact still misses it.resilient_fetch reads at most 2 MiB per response and returns at most 20 000 characters;
bigger payloads are truncated, not streamed.Nothing leaves the machine. resilient_fetch makes the request you asked for; the memory tools read
and write one local file.
MIT.