dsh-mask

PII masking middleware for DeepSeek Harness — anonymize personal data before it reaches the model, restore it at the display layer.

Phones, emails, ID cards, bank cards, keys, and more become placeholders at the model boundary; the plaintext never enters your session log.

English · 简体中文 · Español · Português · हिन्दी

Compatibility

What you get

dsh-mask anonymizes personal data at the model boundary — before a message reaches the model — and keeps a restore table so placeholders can be mapped back to the originals at the display layer:

• Request-time masking — agent/pre-step messages are rewritten so phones, emails, ID cards, bank cards, keys, and IPs (each opt-in) become <PHONE_1>-style placeholders. The masked text is what gets logged and sent to the model.
• Restore table — the placeholder → original map lives only in memory and a controlled storage domain (dsh_mask); the plaintext never enters the session log.
• Audit, not plaintext — the mask/applied session event records only "replaced N values + type distribution", never the original text or the mapping.
• /mask command — status (counts + distribution), on/off (runtime toggle), restore <text> (unmap placeholders), help.
• mask_test tool — run a snippet through the detector and see the placeholder result; it never reveals the original values.

user message ──agent/pre-step──▶ placeholders ──model──▶ placeholders ──restore──▶ display
                                   ▲                                                    │
                                   └──────── restore table (memory + dsh_mask) ────────┘

Quick start

# 1. install the bundle into your profile
dsh plugin --profile web add "github:PerryLink/dsh-mask#main"

# or from npm (published releases)
dsh plugin --profile web add dsh-mask

# 2. verify the row mounts
dsh --profile web --dump-config | grep -A2 'id: mask'

Then tailor the entity list in your profile patch:

- insert:
    - id: mask
      name: dsh-mask
      config:
        entities: [phone, email, id-card, bank-card, key]

> /mask status
> /mask restore <PHONE_1>

Install & uninstall

• git channel (latest main): dsh plugin --profile web add "github:PerryLink/dsh-mask#main" (equivalent to installing from git+https://github.com/PerryLink/dsh-mask.git). No build step — index.mjs and lib/ are the shipped artifacts.
• npm channel (published releases): dsh plugin --profile web add dsh-mask.
• tarball channel: pnpm pack in this repo, then dsh plugin --profile web add ./dsh-mask-<version>.tgz.
• uninstall: dsh plugin --profile web remove dsh-mask (or remove the row from the profile patch).

Configuration

All tunables are Schemastery Config fields (changeable from cordis.yml). An id-targeted override replaces the whole row — restate every key you need. cordis.patch.yml documents each key inline.

Example override in your profile patch:

- insert:
    - id: mask
      name: dsh-mask
      config:
        entities: [phone, email, id-card, bank-card, key, ip]
        persistRestoreTable: false
        registerCommand: true

Tools & surfaces

Permissions & data

• Permissions: dsh-mask performs no network requests and stores no credentials; it only reads the session at the agent/pre-step boundary and writes its own dsh_mask storage domain. The dshWorkshop manifest declares network:none and credentials:none.
• Data: the placeholder → original restore table lives in memory and, when persistRestoreTable: true, in the controlled dsh_mask storage domain — this is the only place plaintext PII is stored, and it is never written to the session log.
• Session log: mask/applied is declared in types.d.ts and appended only when the host records the type (see Known limitations). Its payload is counts + type distribution only.

Security boundaries

• Plaintext never enters the session log. The masked (placeholder) form is what gets logged and sent to the model, so model-visible content is reconstructable from the log in placeholder form; the originals stay in the restore table.
• Sanitize before display/log. lib/sanitize.mjs redacts PII, secrets, and URL credentials before any text reaches the model or the log; mask_test and /mask status never echo originals.
• Controlled restore. /mask restore is the single explicit reveal surface, and it only reads the mapping for the active session.
• Fail closed. Unimplemented mode (regex+ner), unknown scope values, NER-only entities, and out-of-bounds numbers all fail loudly at load.
• Registrations are effects. The listener, command, tool, and storage-domain close are all Cordis effects — stop/hot-reload removes them.

Known limitations

• Regex only. Name (person) and address (address) recognition needs an external NER recognizer, which the pure-host zero-dependency form does not bundle; mode: regex+ner and those entities fail loudly at load. The PII types covered out of the box are phone, email, ID card, bank card, key, and (opt-in) IP.
• Display-layer restore needs a client half. Masking is fully host-side, but transparently un-masking the assistant bubbles in the client UI is a browser-half feature this pure-host form does not ship; the restore table and restore() are the complete host-side seam a client plugin would consume, and /mask restore covers interactive needs today.
• Session events on 0.1.1-rc.2. The harness does not yet record mask/* event types, and its Session.append does not stamp the ignorable envelope, so on rc.2 the session-log audit appends are skipped (sessions keep loading); the plugin enables them automatically once a host records the types or supports the ignorable envelope.

Development

pnpm install                                       # node ^22.19 || >=24
pnpm run typecheck && pnpm run typecheck:ci        # tsc --checkJs against the published rc.2 peers
pnpm test                                          # node --test
pnpm run verify:self-contained                     # dependency specs resolve from the registry
pnpm run verify:artifacts                          # shipped files present + index.mjs importable
pnpm run check:readmes                             # five-language README consistency
pnpm pack                                          # the published tarball

There is no build step: pure ESM, index.mjs and lib/ are the shipped artifacts.

Benchmark

The PII benchmark (per-type P/R/F1 over 108 synthetic samples) is published in benchmark/RESULTS.md; regenerate it with node benchmark/run.mjs (no build step, zero new dependencies).

Topics

dsh, dsh-plugin, deepseek-harness, deepseek, cordis, pii, mask, privacy, anonymization, security

Contributors

• @PerryLink — creator and maintainer: the regex PII detector ported from Pii-Stripper-Middleware, the agent/pre-step masking seam, the restore table, the /mask command and mask_test tool, and the five-language docs.

PerryLink DSH Plugin Family

This project is one of the DeepSeek Harness plugins maintained by PerryLink. If this one helps you, the others likely will too:

License

LICENSE (Apache License 2.0) © 2026 dsh-mask contributors