🛡️ dsh-permission-rules

August 30, 2026 · View on GitHub

🛡️ dsh-permission-rules

  • 1024 store channel: npm i -g dsh1024 once, then dsh1024 plugin --profile web add dsh-permission-rules (counts toward the deepseek1024.com install ranking). Gitee

Claude Code-style declarative permission rules for DeepSeek Harness.

Rules decide what is known. A reviewer model decides what is not.

License DSH plugin Node CI Version npm version npm downloads

English · 简体中文 · Español · Português · हिन्दी


Compatibility

SurfaceStatus
HarnessDeepSeek Harness 0.1.1-rc.2
Node`^22.19.0
PlatformsAll (host + web settings client)
ModelAny (deny/ask reasons surface through tool results)

What you get

dsh-permission-rules puts an ordered allow / deny / ask rule list in front of every tool call on the tools/pre-execute waterfall — deterministic, instant, auditable, and written by you in plain YAML:

  • deny blocks the call; the rule's reason becomes the model-visible error.
  • ask rides the official approval seam (mount dsh-auto-review for a second-model answerer, or a human answers; with neither, the harness fails closed).
  • allow (and no-match) strictly delegates via next() — downstream listeners are never short-circuited.

Every hit and every passthrough is audit-logged as a permissionRules/decision session event (log-only — nothing extra is injected into the model context).

  • Rich matching — tool-name globs (including mcp__*), agent-identity selectors (main / subagent / preset:*), argument key/value globs or regexes (with !pattern negation and an absent key dimension), workspace-relative path globs at any nesting depth, when host conditions (env vars, platform), and shell command decomposition (argv: command word, argument tokens, pipeline signature) for token-precise command matching.
  • Built-in high-risk baseline — a shipped deny/ask ruleset (destructive commands, privilege escalation, download-and-execute, sensitive paths) enabled by default and appended after user rules so a nearer user rule can override it; toggle with builtin.enabled.
  • Hierarchical rule files — optional searchUp merges every .dsh/rules.yaml from the session cwd to the filesystem root, nearest first.
  • Dry-run rolloutenforce: false audits what the policy would do while passing every call through.
  • Hot reload — Chokidar watch with debounce; a broken edit keeps the previous rules, never crashes.
  • Fail loud — invalid YAML, unknown actions/fields, bad globs/regexes, backtracking-prone patterns, or more than maxRules rules fail the load.

Rule syntax

# <project>/.dsh/rules.yaml
rules:
  - match: { tools: [bash, pwsh], params: { command: "git push*" }, paths: ["**/secrets/**"] }
    action: deny
    reason: "No pushes from protected paths"

  - match: { tools: [edit, write] }
    action: ask
    reason: "File writes need confirmation"
  • Match dimensionstools (globs, incl. mcp__*), agents (main / subagent / preset:<name>; unknown identity never matches — fail closed), params (key/value globs or regexes, !pattern negation, absent key dimension), paths (workspace-relative globs extracted at any nesting depth), when (env var globs/regexes + a closed platform list), and network (domains / ips / ports / schemes — globs, wildcards, CIDRs, port ranges).
  • Actionsallow / deny / ask, evaluated in file order, first match wins.
  • Rule metadataenabled: false (visible but inert), description, tags; unknown fields fail the load.
  • Schema — a JSON Schema ships at docs/rules-format.schema.json (editor completion via # yaml-language-server: $schema=...); the full vocabulary and a 5-rule security baseline live in docs/rules-format.en.md.

Network policy

A Codex-style process-level network policy: shell subprocess traffic flows through a built-in local HTTP/CONNECT proxy, and every connection is decided by ordered network rules or by three modes mapped onto the official sandbox presets:

  • deny-all — the read-only sandbox preset: block all outbound.

  • whitelist — the workspace-write preset: allow listed targets, unlisted: ask (or deny) for the rest.

  • allow-all — the danger-full-access preset: allow everything.

  • auto (default) — follows the sandbox preset; on hosts without the sandbox-policy service it resolves to autoFallback (allow-all).

  • Matchingmatch.network with domains / ips / ports / schemes (globs, wildcards, CIDRs, port ranges; numeric YAML ports are accepted). URL-candidate extraction on the tools/pre-execute hot path fires on web-tool arguments and URLs embedded in bash/pwsh command text; loopback targets can short-circuit rules per loopback policy.

  • Audit — denied connections append permissionRules/network to the owning session (same adaptive ignorable gate), with block counters and recent interceptions in /rules network and the settings page.

Quick start

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

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

# 2. restart and verify the row
dsh --profile web --dump-config | grep -A4 'id: permission-rules'

Install & uninstall

  • git channel (latest main): dsh plugin --profile web add "github:PerryLink/dsh-permission-rules#main" — the prepare script builds with production dependencies only.
  • npm channel (published releases): dsh plugin --profile web add dsh-permission-rules.
  • tarball channel: pnpm pack in this repo, then dsh plugin --profile web add ./dsh-permission-rules-<version>.tgz.
  • uninstall: dsh plugin --profile web remove dsh-permission-rules.

Configuration

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

KeyDefaultMeaning
rulesFile.dsh/rules.yamlRule file location; relative = resolved against the calling session's cwd, absolute = global and validated at mount
fallbackPath(none)Rule file used when per-cwd discovery finds nothing; validated at mount
badFilePolicyfailBad rule file: fail errors the pending tool call loudly; ignore-with-warning warns and continues empty
maxRules256Hard cap on rule count across the effective source chain
maxCachedWorkspaces512Hard cap on cached per-workspace rule loads (LRU eviction)
patternModeglobparams/paths/when.env pattern flavor: glob or regex (tool names are always globs)
watchtrueChokidar watch + reload on change
watchStabilityThresholdMs200Reload debounce window (ms)
languageen/rules output language: en, zh, es, pt, hi
caseInsensitivePaths(win32)paths patterns and workspace-root comparison ignore ASCII case; true on Windows
auditallAudit granularity: all logs every hit AND passthrough; hits skips passthrough events
searchUpfalseWalk parent directories from the session cwd and merge every found rule file, nearest first
maxGlobStars2Hard cap on unbounded */** quantifiers per glob pattern
enforcetruefalse = dry-run mode: deny/ask hits are audit-logged with a dryRun marker and every call passes through
allowUnmarkedAuditfalsePre-marker hosts drop the ignorable marker; the plugin disables session-log audit with a warning. Set true to opt back in
network.enabledtrueMaster switch for the proxy, env injection, and web-tool mode defaults
network.modeautoPolicy mode: auto follows the sandbox preset, or deny-all / whitelist / allow-all
network.autoFallbackallow-allMode used when auto has no sandbox-policy service
network.unlistedaskWhitelist-mode handling of targets no rule matched: ask or deny
network.proxyBind127.0.0.1Local proxy bind address (loopback only)
network.proxyPort0Local proxy port; 0 picks a free ephemeral port
network.proxyMaxRecent100Cap on recent-block records kept for the settings page
network.loopbackallowLoopback targets: allow (Codex parity) or policy
network.injectEnvtrueWhether proxy environment variables are injected for subprocesses
network.noProxyclearSubprocess NO_PROXY handling: clear enforces the policy or preserve
builtin.enabledtrueBuilt-in high-risk baseline: false disables the shipped deny/ask ruleset entirely
builtin.path(shipped)Replacement baseline file (absolute, or relative to process.cwd()); validated at mount

Tools & surfaces

SurfaceKindNotes
tools/pre-executelistenerFirst-match allow/deny/ask rules + network URL-candidate extraction
/rulescommandlist · reload · decisions [n] · test <tool> <json>
permissionRules/decisioneventLog-only audit for every hit and passthrough
permissionRules/networkeventProxy-layer audit for blocked connections
HTTP/CONNECT proxyserviceBuilt-in local proxy governing shell subprocess traffic
settings pageclientNetwork-mode editor, rule editor, block counters, recent interceptions
/rules                        list the active rules, their source files, and any last-reload error
/rules list                   explicit alias for the bare listing
/rules reload                 re-read the rule-file chain for this workspace
/rules decisions [n]          show the last n permission decisions of this session (default 10)
/rules test <tool> <json>     dry-evaluate the rules against a hypothetical call

/rules test also accepts leading flags: --cwd <dir>, --env KEY=VALUE (repeatable), --agent <selector> (repeatable), and --platform <name>. In multi-file chains (e.g. searchUp), every listed rule line is attributed to its own source file.

Permissions & data

  • Permissions: declares files:read, files:watch, files:write, session:append, and network:outbound in its workshop manifest. ask decisions ride the official approval seam — nothing is re-implemented or bypassed.
  • Data: rule files are read from disk; no rule data is written. No model calls, no reviewer subagents.
  • Session log: permissionRules/decision is never injected into the model context and is appended with the envelope's ignorable: true marker so any harness build loads the log.

Security boundaries

  • Policy, not a kernel. paths candidates come only from a documented set of argument keys (at any nesting depth, depth-capped), and only workspace-relative paths match.
  • No reviewer here. The plugin never spawns subagents or calls models — producing an ask decision is the end of its work.
  • No sandbox changes. OS-level sandbox policy belongs to the sandbox seam, not this plugin.
  • Loud misconfiguration. Unknown YAML fields, unknown actions, and bad patterns are rejected at load.
  • Backtracking bounds. Glob patterns are capped at maxGlobStars unbounded star expansions; regex-mode patterns reject nested unbounded quantifiers and quantified overlapping literal alternations.

Known limitations

  • Audit marker on pre-marker and refusing hosts. permissionRules/decision is appended with ignorable: true; hosts whose Session.append predates the marker (the 0.1.0-rc.1rc.7 and 0.1.1-rc.1rc.7 lines) silently drop it, and the 0.1.2-alpha line refuses plugin events on read even when marked — the runtime detects both before the first append and disables session-log audit with a one-time warning. Set allowUnmarkedAudit: true to opt back in; repair already-written logs with scripts/repair-session-logs.mjs (its strip mode removes audit rows where the marker cannot help).
  • Path candidates are heuristic. Only the documented argument keys feed path matching, and workspace-relative matching is ASCII-case-insensitive only when caseInsensitivePaths is on.
  • Globs are a conservative subset. No brace expansion — write two patterns, or use regex mode.
  • The regex backtracking guard is structural, not exhaustive. Prefer glob mode for untrusted files.

Collaborating with dsh-auto-review

  • dsh-permission-rules produces ask; dsh-auto-review answers on the approval/request waterfall with a read-only second-model verdict (or delegates to humans). Mount both for the full closed loop.
  • Integration-tested: permissionRules/decisionapproval/askedautoReview/verdictapproval/decided, with the reviewer replaced by a scripted mock.
  • The never approval policy and every fail-closed guarantee of the official harness stay untouched.

Session log repair

Session logs written before the ignorable marker existed can be refused by newer harness builds (SessionFormatUnsupportedError). The shipped scripts/repair-session-logs.mjs rewrites only the targeted audit rows to carry ignorable: true, frame-preserving, with backups:

node scripts/repair-session-logs.mjs scan [--home DIR]      # report foreign rows, change nothing
node scripts/repair-session-logs.mjs repair [--home DIR] [--dry-run]

--home defaults to $DSH_HOME/sessions (or ~/.dsh/sessions).

Development

pnpm install            # node ^22.19 || >=24
pnpm run typecheck      # tsc, src + tests
pnpm run lint           # eslint, src + tests + scripts
pnpm test               # vitest: 236 tests, 20 files
pnpm run test:coverage  # coverage gate (90/80/90/90)
pnpm run build          # tsc declarations + tsdown bundles (lib/)
pnpm run pack:check     # build + pack (the published artifact)
node scripts/check-readme-sync.mjs   # five-language README sync gate (also in CI)

See VERIFICATION.md for the headless end-to-end verification record.

Topics

dsh, dsh-plugin, deepseek-harness, permission, policy, allow-deny-ask, approval, safety, network, network-policy, proxy

Contributors

  • @PerryLink — creator and maintainer: rule vocabulary and evaluation, runtime, HMR watch, session-log audit, network policy + proxy, and the five-language docs.
  • @22xuan — the detailed report on rc.6 hosts silently dropping the audit event's ignorable marker (#2) and the upstream harness discussion; the v0.4.1 runtime host-capability detection and the documentation correction drew directly from that analysis.
  • @sjh9714 — proposed the shared rule-syntax test-vector corpus (#4, #5), shipped in v0.5.1 as docs/rule-test-vectors/, and supplied the AST-decomposition boundary cases on the design discussion.
  • @weipeng1999 — the AST-based command-decomposition feature proposal (#8) behind the design discussion.
  • @alexchenzl — the DSH Directory listing request (#7).
  • @zl190 — reported and verified the 0.1.0-rc.7 harness compatibility gap (PR #9).
  • @cuohua — reported that the 0.1.1-rc line still drops the ignorable marker even though the version gate covered only 0.1.0 (#11); the widened gate drew directly from that analysis.

This project is one of the 33 DeepSeek Harness plugins maintained by PerryLink. If this one helps you, the others likely will too:

PluginOne-liner
dsh-dsh-auto-reviewSecond-model auto-review on the approval chain, fail-closed by default
dsh-dsh-background-agentsDurable background child agents with a Web UI sidebar, messaging and interrupt
dsh-dsh-budgetCost governance for DeepSeek Harness: budgets, carbon, and latency in one panel.
dsh-dsh-checkpoint-rewindClaude Code /rewind-equivalent: snapshots, session forks, one-shot restore
dsh-dsh-claude-moveMigrate Claude Code sessions, memory, skills and CLAUDE.md into DSH
dsh-dsh-clickCross-platform native desktop control for DeepSeek Harness — Windows first.
dsh-dsh-composer-historyTerminal-style input history for the web composer: arrows, Ctrl+R search
dsh-dsh-data-qualityDataset quality checks and citation cross-checks (the optional numeric bridge consumed here)
dsh-dsh-defendPrompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness.
dsh-dsh-doublecheckEngineering-discipline guard: requirements grill, test gates, adversary review
dsh-dsh-drawUnified static-image generation routing for DeepSeek Harness.
dsh-dsh-fastRead-only performance diagnostics for DeepSeek Harness.
dsh-dsh-fund-researchDeterministic research reports for Chinese public mutual funds
dsh-dsh-githubGitHub PR/issues integration for DSH, every write gated by approval
dsh-dsh-industry-researchIndustry research orchestration that seals its deliverables through this plugin's ctx.researchReport.assemble
dsh-dsh-libraryLocal document knowledge base for DeepSeek Harness.
dsh-dsh-local-aiLocal-model (Ollama) integration for DeepSeek Harness.
dsh-dsh-lsp-actionsLSP diagnostics, formatting, completion, code actions and rename over language servers
dsh-dsh-maskPII masking middleware: anonymize at the model boundary, restore at the display layer
dsh-dsh-mcp-panelRead-only MCP runtime panel: /mcp command + Settings tab with status, tools and errors
dsh-dsh-mementoApproval-gated cross-session memory: ctx.memory seam + SQLite + memory tool
dsh-dsh-observeOpenTelemetry and Langfuse observability exporter for DeepSeek Harness.
dsh-dsh-output-stylesClaude Code outputStyles-equivalent runtime style switching
dsh-dsh-plugin-guidePlugin-development knowledge base as an on-demand agent skill
dsh-dsh-research-reportVerifiable research-report engine: content-addressed evidence ledger and sealed versions
dsh-dsh-scoreMulti-dimensional quality scoring for DeepSeek Harness plugins.
dsh-dsh-session-pinPin sessions in the Web sidebar with durable ordering
dsh-dsh-session-syncCross-device session sync for DeepSeek Harness — a dedicated git mirror of your session store.
dsh-dsh-skill-pack-securitySecurity-audit skill pack: secret scan, dependency and supply-chain review
dsh-dsh-talkVoice-first session loop for DeepSeek Harness: talk to it, hear it answer.
dsh-dsh-test-driveIsolated install-and-smoke test drives for DeepSeek Harness plugins.
dsh-dsh-translateVendor parameter translation and deterministic JSON repair for DeepSeek Harness.

License

Apache License 2.0 © 2026 dsh-permission-rules contributors