DSH Plugins Marketplace

DSH Plugins

Plugins

/

dsh-compaction-guard

z

dsh-compaction-guard

Manifest valid

Compaction integrity for DeepSeek Harness — constraints from the compacted range are verified against the summary; what the agent was told to remember and silently forgot is reported loudly

hasBundlePatch

dsh-compaction-guard

Compaction integrity for DeepSeek Harness (dsh).

Long sessions compact; the compacted range takes constraints with it — "never commit to main", "必须先跑测试" — and the agent silently forgets rules it was told to keep. This plugin watches compaction/summary session events: it extracts directive lines from the user-authored events being shadowed, verifies each against the summary (verbatim, whitespace-normalized, or in substance — a coverage threshold on content words), and reports every constraint the agent just forgot — console plus a durable JSONL ledger. Pinned constraints from config are verified on every compaction. Zero LLM calls in the trust path.

Family channel #9: read / write / do / call / leave-behind / egress / told / running / remembered — what the agent forgets.

Why now (checked 2026-10-17)

The awesome list has 209 memory plugins and an entire compaction package family in dsh itself — and not one verifies that constraints survive compaction. Memory plugins add recall; this audits loss. The compaction/summary event even ships shadowedSeqs (exactly what was compact away) — the integrity check is deterministic by construction.

How it works

compaction/summary event
  ├── shadowedSeqs → session.eventAt(seq) → user/message directive lines
  ├── pinned constraints from config (always verified)
  ├── verify against the summary text:
  │     verbatim (whitespace-normalized substring)  → kept
  │     content-word coverage ≥ threshold (default 0.6) → kept
  │     otherwise                                     → LOST (reported + ledgered)
  └── ledger: .dsh-compaction-guard/ledger.jsonl (CI-consumable)

Honest limitation, on purpose: word coverage tracks words, not meaning — a summary that rewords "run the tests" as "execute the checks" with no shared vocabulary counts as lost (conservative direction: false alarm, not silent loss). Synonym-aware matching would need embeddings or an LLM, which is exactly what this family refuses to put in the trust path.

Install

dsh plugin --profile default add github:zhengqiuyang/dsh-compaction-guard

Prebuilt lib/ ships in the repo — no build step, no allowBuilds.

Configure

- id: dsh-compaction-guard
  name: dsh-compaction-guard
  config:
    pinned: ["Never force-push to main"]   # always verified, verbatim
    coverage: 0.6
    ledgerPath: .dsh-compaction-guard/ledger.jsonl

Develop

npm install && npm test

Roadmap

  • reinject mode: steer the lost constraints back into the session after compaction (default stays observe — auto-injection deserves live testing first)
  • Post-compaction reassertion listener (a constraint restated after the summary also counts as survived)
  • Turn-boundary constraints (task briefs in the first turn pinned per-turn)

Kill criteria

If dsh ships first-party compaction-integrity verification, this freezes at its last working version with a postmortem here.

Comments

Loading…

Similar plugins

dsh-hindsight-advanced

by paulalesius

Long-term memory for DeepSeek Harness agents: automatic recall each turn, a retain/recall/reflect tool, standing rules, and visibility you scope to the whole bank, a preset, or a session.

Manifest valid

★ 3

NOASSERTION

JavaScript

Oct 15, 2026

dsh plugin --profile web add dsh-plugin-hindsight-advanced

by yoza10635

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph evict

Memory & ContextManifest valid

★ 11

↓ 732/wk

MIT

TypeScript

Oct 17, 2026

dsh plugin --profile web add dsh-argp

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and st

Security & AuditTools & CapabilitiesMemory & ContextManifest valid

★ 0

Apache-2.0

TypeScript

dsh plugin --profile web add dsh-completion-guard

by menotbobbybrown

Persistent long-term memory for DeepSeek Harness: a JSON store of typed entries (fact, preference, entity, rule, episodic) exposed as the memory_remember and memory_recall agent tools, with recall ran

Memory & ContextManifest valid

★ 0

MIT

TypeScript

Sep 8, 2026

dsh plugin --profile web add @modelnorth/dsh-plugin-memory

by john-walks-slow

Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.

Development & InfrastructureMemory & ContextSessions & MessagesManifest valid

★ 4

↓ 446/wk

MIT

TypeScript

Oct 13, 2026

dsh plugin --profile web add dsh-clear-mind

by zhengqiuyang

Signed chain-of-custody for DeepSeek Harness sessions — hash-chained, ed25519-signed records of what the agent actually did, commits bound into the chain

Manifest valid

★ 0

MIT

JavaScript

Oct 12, 2026

dsh plugin --profile web add dsh-attest-chain