@sigmashake/ssg 0.24.5 → 0.24.6

package/README.md

@@ -1,209 +1,101 @@
-# sigmashake-gov
+# @sigmashake/ssg
 
-**AI Agent Governance System** — Evaluate tool calls, block dangerous operations, and approve via dashboard.
+`ssg` is SigmaShake's AI agent governance CLI. It helps you apply rules to agent tool calls, review approvals locally, search audit history, and manage rulesets from the SigmaShake Hub.
 
-## Incident Highlight: Claude Code Source Code Leak (March 31, 2026)
-
-> **One rule. Zero source leaks.**
-
-On March 31, 2026, Claude Code's TypeScript source code was exposed because `"sourceMap": true` was set in `tsconfig.json`. Source map files (`.map`) map compiled JavaScript back to the original TypeScript source — if served in production, anyone can reconstruct private code.
-
-The [`rules-typescript`](https://hub.sigmashake.com) ruleset on the SigmaShake Hub includes `no-sourcemap-in-tsconfig`, which blocks any AI agent from enabling source maps in production tsconfig files:
-
-```
-rule no-sourcemap-in-tsconfig {
-  enabled true
-  priority 95
-  severity error
-  DENY write
-  IF path GLOB "**/tsconfig.json"
-     AND content LINE_REGEX "\"sourceMap\"\\s*:\\s*true"
-  MESSAGE "sourceMap: true exposes your TypeScript source via .map files.
-           This configuration caused the Claude Code source code leak (March 31, 2026)."
-}
-```
+## Install
 
 ```bash
-ssg hub pull rules-typescript   # Install the TypeScript ruleset
+npm install -g @sigmashake/ssg
+ssg --help
 ```
 
-This is precisely the category of silent misconfiguration AI agents introduce — and exactly what SigmaShake governance rules are built to prevent.
-
----
-
 ## Quick Start
 
 ```bash
-# Install the CLI
-npm install -g @sigmashake/ssg
-
-# Initialize configuration
+# Install adapters and local project config
 ssg init
 
-# Test a rule (blocks rm -rf)
-echo '{"tool":"Bash","input":{"command":"rm -rf /"}}' | ssg eval
-# → {"decision":"block", "rule_id":"no-destructive-ops", ...}
-
-# Start persistent daemon for sub-2ms eval (recommended)
-ssg daemon &
-echo '{"tool":"Bash","input":{"command":"ls"}}' | nc -U ~/.sigmashake/evald.sock
-# → {"decision":"allow", "duration_ns":150000, ...}
+# Re-run guided setup at any time
+ssg setup
 
-# Start approval dashboard
+# Start the local approval dashboard
 ssg serve
 ```
 
-## Overview
-
-sigmashake-gov provides **runtime safety for AI agents** by:
-
-1. **Evaluating tool calls** against configurable rules (e.g., block `rm -rf`, restrict file access)
-2. **Dashboard approval workflow** for uncertain cases (ASK decisions)
-3. **Local SQLite** storage with audit logging
-
-## Architecture
-
-```
-Agent Tool Call
-    ↓
-Hook → ┌─ Daemon (Unix socket, ~0.1-2ms) ← recommended
-       └─ ssg eval (subprocess, ~73ms+)
-    ↓
-Engine: Native (Zig/Rust, ~5-30µs) → TS Rule Index → TS evaluate
-    ↓
-Decision → Audit Log → Dashboard (if ASK)
-```
+To evaluate a tool call directly:
 
-- **Daemon**: Persistent process (`ssg daemon`) — keeps rules, DB, and native engine hot in memory
-- **Native Engine**: Zig + Rust FFI with SIMD-accelerated matching and zero-alloc eval
-- **Engine Core**: Rules parser, evaluation logic, SQLite database
-- **Server**: Local dashboard (server-rendered HTML + HTMX + SSE for real-time updates)
-
-See `ARCHITECTURE.md` for full system diagrams and performance budget.
-
-## Commands
-
-| Command | Description |
-|---------|-------------|
-| `ssg eval` | Evaluate tool call from stdin JSON |
-| `ssg check [path]` | Scan files for rule violations |
-| `ssg serve` | Start local dashboard (port 5599) |
-| `ssg sync` | Pull rules from edge API to SQLite |
-| `ssg push` | Push local `.rules` files to edge API |
-| `ssg init` | Initialize `.sigmashake/` directory |
-| `ssg lint` | Validate `.rules` file syntax |
-| `ssg format` | Format `.rules` files (normalize + split oversized rules) |
-| `ssg new` | Scaffold a new `.rules` file |
-| `ssg man` | Print `.rules` DSL syntax reference |
-| `ssg list` | Show all loaded rules |
-| `ssg status` | Check setup and dashboard health |
-| `ssg doctor` | Full system health diagnostic (`--json` for machine-readable output) |
-| `ssg setup` | Interactive setup wizard (re-runnable) |
-| `ssg test-rule` | Test rule matching with `--explain` trace |
-| `ssg metrics` | Show session metrics (evals, blocked) |
-| `ssg blocked` | Show blocked/forced commands from this session |
-| `ssg usage` | Show eval usage, storage, and plan limits |
-| `ssg dedupe` | Detect duplicate rules (exact/structural/semantic) |
-| `ssg rule` | Non-interactive rule management for AI agents (list, disable, enable, set-decision, search) |
-| `ssg daemon` | Persistent eval daemon (Unix socket, sub-2ms eval) |
-| `ssg profile` | Eval latency profiling (flight logs + live daemon metrics) |
-| `ssg flight` | Flight recorder stats (latency, memory, CPU) |
-| `ssg install` | Install ssg binary to `~/.local/bin` |
-| `ssg keys` | Manage Ed25519 signing keys (generate, show, register, sign, verify) |
-| `ssg publish` | Publish local `.rules` to GitHub and hub |
-| `ssg hub pull <id>` | Install a ruleset from hub.sigmashake.com (integrity + signature verified) |
-| `ssg hub search <q>` | Search the Hub for rulesets by keyword or technology |
-| `ssg hub update` | Check installed rulesets for newer versions (`--apply` to install) |
-| `ssg hub audit <id>` | Verify a ruleset's transparency log chain integrity locally |
-| `ssg certify` | Run scenario files and produce certification report |
-| `ssg insights` | Analyze conversation history for governance patterns |
-| `ssg audit-sync` | Push local audit log to cloud (Pro/Enterprise) — `--dry-run`, `--quiet`, `--org=<slug>` |
-
-## Rule Syntax
-
-```
-rule no-destructive-ops {
-  enabled true
-  priority 100
-  severity error
-  DENY execution
-  IF command CONTAINS "rm -rf"
-  OR command CONTAINS "git push --force"
-  MESSAGE "Destructive command blocked."
-}
+```bash
+echo '{"tool":"Bash","input":{"command":"ls"}}' | ssg eval
 ```
 
-**Key fields:**
-- `priority`: Higher = checked first (short-circuit evaluation)
-- `decision`: `allow` | `block` | `log` | `shadow` | `ask`
-- `target`: `execution` | `read` | `write` | `edit` | `any`
-- `IF/OR`: Group conditions with AND/OR logic
-- `MESSAGE`: Required human-readable description
+## What `ssg` Does
 
-See `RULE_SYNTAX.md` for full DSL reference.
+- Evaluates agent tool calls against local governance rules
+- Runs a local approval dashboard for `ask` decisions
+- Stores local audit history and makes it searchable from the CLI
+- Manages rules and rulesets from the SigmaShake Hub
+- Exposes an MCP server for AI agents and editor integrations
 
-## Configuration
+## Common Workflows
 
-`.sigmashake/config.toml`:
-```toml
-[project]
-name = "sigmashake-gov"
+### Search Local Audit History
 
-[api]
-url = ""  # Set via SSG_API_URL env var
-
-[dashboard]
-port = 5599
-bind = "127.0.0.1"
+```bash
+ssg audit search --query=rm
+ssg audit search --tool=Bash --decision=block --json
+```
 
-[eval]
-ask_timeout_ms = 60000
-ask_fallback = "block"
+### Manage Rules
 
-[agents]
-claude = true
+```bash
+ssg rule list --json
+ssg rule search destructive
+ssg blocked --json
 ```
 
-## Hot Reload
+### Work with the Hub
 
-Rules from `.sigmashake/rules/*.rules` are loaded fresh on every `ssg eval` invocation. Adding, editing, or removing a `.rules` file takes effect on the very next tool call — no restart needed.
-
-**Note:** If rules were loaded into SQLite via `ssg sync`, file changes are ignored until you re-run `ssg sync`. Use `ssg list` to verify which rules are active.
+```bash
+ssg hub search typescript
+ssg hub pull rules-typescript
+ssg hub update --apply
+```
 
-## Agent Integration
+### Configure Agent Integrations
 
-ssg enforces governance for multiple AI coding agents from a single rule set:
+```bash
+# Configure all supported clients
+ssg init
 
-- **Claude Code**: `ssg hook eval` registered as PreToolUse hook — evaluates tool calls via daemon or subprocess
+# Or configure a single client
+ssg init --client=codex
+```
 
-Both agents share the same rules from `.sigmashake/rules/` and log to the same SQLite audit database.
+## Supported AI Clients
 
-## Safety Features
+`ssg init` supports `claude-code`, `antigravity`, `gemini`, `codex`, `copilot`, and `pi`.
 
-- **Loop guard**: Blocks identical Bash commands repeated 3 times consecutively (prevents agent loops)
-- **Circuit breaker**: After 5 consecutive denies in Claude Code hook, auto-allows to prevent lockout. Reset by deleting `/tmp/ssg-deny-count`.
-- **Rate limiter**: Per-PID token bucket in daemon (1000 burst, 500/s refill) with permanent trip on exhaustion
-- **Fail-open**: If the ssg binary is missing or crashes, tool calls are allowed through — governance never blocks the agent entirely.
-- **Native engine fail-secure**: Invalid regex patterns in native Zig engine default to `match=true` (block) with ReDoS protection
+## Authentication
 
-## Build
+Local rule evaluation, local dashboard usage, and local audit inspection can be used without signing in. Use `ssg auth login` for account-backed features such as Hub publishing, organization workflows, support, and private repository or ruleset access.
 
-```bash
-bun build --compile src/cli.ts --outfile ssg    # Local binary
-bun build:linux                                   # Linux x64
-bun build:macos                                   # macOS ARM
-```
+## Useful Commands
 
-## Tests
+- `ssg init` installs agent adapters and local configuration
+- `ssg setup` walks through recommended setup and ruleset selection
+- `ssg serve` starts the local approval dashboard
+- `ssg audit search` queries local audit history for agents, tools, and actions
+- `ssg doctor` runs a health diagnostic for the local installation
+- `ssg rule ...` lists, searches, enables, disables, and edits rules
+- `ssg hub ...` searches, installs, updates, and audits Hub rulesets
+- `ssg mcp-server` starts the local MCP server for agent integrations
 
-```bash
-bun test                         # All 931 tests
-bun test test/engine.test.ts     # Engine only
-npx gts fix                      # Format + lint
-```
+## Links
 
-Tests: `engine`, `parser`, `evaluate_operators`, `db`, `server`, `html`, `integration`, `e2e-daemon`, `daemon-metrics`, `flight-recorder`, `certify`.
+- Hub: https://hub.sigmashake.com
+- Repository: https://github.com/sigmashake/ssg
+- Accounts: https://accounts.sigmashake.com
 
----
+## License
 
-**License**: Proprietary — Copyright (c) 2026 Sigma Shake. All rights reserved.
+Proprietary. See `LICENSE`.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@sigmashake/ssg",
-  "version": "0.24.5",
-  "description": "AI Agent Governance CLI \u2014 evaluate tool calls against rules, block dangerous operations, and surface blocked commands",
+  "version": "0.24.6",
+  "description": "AI Agent Governance CLI — evaluate tool calls against rules, block dangerous operations, and surface blocked commands",
   "type": "module",
   "bin": {
     "ssg": "bin/ssg.cjs"
@@ -13,11 +13,11 @@
     "README.md"
   ],
   "optionalDependencies": {
-    "@sigmashake/ssg-linux-x64": "0.24.5",
-    "@sigmashake/ssg-linux-arm64": "0.24.5",
-    "@sigmashake/ssg-darwin-arm64": "0.24.5",
-    "@sigmashake/ssg-darwin-x64": "0.24.5",
-    "@sigmashake/ssg-win32-x64": "0.24.5"
+    "@sigmashake/ssg-linux-x64": "0.24.6",
+    "@sigmashake/ssg-linux-arm64": "0.24.6",
+    "@sigmashake/ssg-darwin-arm64": "0.24.6",
+    "@sigmashake/ssg-darwin-x64": "0.24.6",
+    "@sigmashake/ssg-win32-x64": "0.24.6"
   },
   "scripts": {
     "postinstall": "node ./bin/cleanup-globals.cjs",