agent-gov-core 0.4.1 → 0.4.2

package/README.md

@@ -81,14 +81,14 @@ The JSON schema at [`schemas/finding.schema.json`](./schemas/finding.schema.json
 - `lineOfTomlKey(text, dottedKey, scope?)` — 1-based line of a TOML key, optionally scoped to a byte range. Use scope to disambiguate `[[array]]`-of-tables entries that share the same leaf key.
 
 ### MCP command normalization
-- `normalizeMcpCommand({ command, args, url, serverUrl, env, cwd })` — canonical identity string for an MCP server entry. Drops neutral flags (`-y`, `--yes`), resolves npx/uvx invocations, includes env+cwd in the identity. Used to dedupe `mcp_command_mismatch` false positives when servers are equivalent but syntactically different (`npx -y foo@1.2.3` vs `npx foo@1.2.3`).
+- `normalizeMcpCommand({ command, args, url, env, cwd })` — canonical identity string for an MCP server entry. Drops neutral confirm flags (`-y`, `--yes`), strips Windows executable suffixes (`.cmd`, `.exe`, `.bat`, `.ps1`), sorts non-neutral flags alphabetically, preserves positional argument order, and includes env + cwd in the identity. Used to dedupe `mcp_command_mismatch` false positives when servers are equivalent but syntactically different (`npx -y foo@1.2.3` vs `npx foo@1.2.3`). Does not interpret what npx/uvx invocations resolve to at runtime — that's outside the substrate's scope.
 
 ### Shell tokenization
 - `tokenizeShell(command)` — quote-aware split on `;`, `|`, `&&`, `||` plus trivial obfuscation neutralization (`c""url` → `curl`, `c\\url` → `curl`)
 - `getCommandHead(subcommand)` — extract the leading verb after tokenization
 
 ### GitHub Action helpers
-- `rankSeverity(s)` — numeric rank `none=0 … critical=4`
+- `rankSeverity(s)` — numeric rank `low=1, medium=2, high=3, critical=4` (matches the schema's closed severity enum; there is no `none`)
 - `passesSeverityThreshold(s, threshold)`, `anyAtOrAbove(findings, threshold)` — fail-on plumbing
 - `emitFindingAnnotation(f)` — render a Finding as a `::warning file=…,line=…,title=…::…` GitHub workflow annotation
 

package/dist/locators.d.ts

@@ -11,12 +11,24 @@ export interface ByteRange {
     /** Exclusive end offset. */
     end: number;
 }
-/** 1-based line number for the first occurrence of `"key"` followed by `:`. */
+/**
+ * 1-based line number for the first occurrence of `"key"` followed by `:`.
+ *
+ * The key is JSON-encoded before matching so keys containing backslashes or
+ * quotes (rare but legal) are located in the source bytes. The scan ignores
+ * lines inside JSONC `//` and `/* *\/` comments so a commented-out `"key":`
+ * does not shadow the real one.
+ */
 export declare function lineOfJsonKey(text: string, key: string, scope?: ByteRange): number;
 /**
  * 1-based line number for the first JSON string value equal to `value`.
  * If `scope` is supplied (a byte range), only matches inside that range count —
  * this is the fix for the multi-server-ambiguity bug.
+ *
+ * The value is JSON-encoded before matching so values containing backslashes
+ * (e.g. Windows paths like `C:\Temp` written as `"C:\\Temp"` in JSON) are
+ * located correctly. The scan ignores JSONC comments so a commented-out
+ * matching value does not shadow the real one.
  */
 export declare function lineOfJsonStringValue(text: string, value: string, scope?: ByteRange): number;
 /**

package/dist/locators.js

@@ -5,19 +5,41 @@
  * All returned line numbers are 1-based. `0` is reserved for "not found"; callers
  * generally treat that as "fall back to file-level annotation".
  */
-/** 1-based line number for the first occurrence of `"key"` followed by `:`. */
+import { stripJsonComments } from './jsonc.js';
+/**
+ * 1-based line number for the first occurrence of `"key"` followed by `:`.
+ *
+ * The key is JSON-encoded before matching so keys containing backslashes or
+ * quotes (rare but legal) are located in the source bytes. The scan ignores
+ * lines inside JSONC `//` and `/* *\/` comments so a commented-out `"key":`
+ * does not shadow the real one.
+ */
 export function lineOfJsonKey(text, key, scope) {
-    const needle = `"${escapeForRegex(key)}"\\s*:`;
-    return findLineByRegex(text, new RegExp(needle), scope);
+    const encoded = jsonEncodeForRegex(key);
+    return findLineByRegex(text, new RegExp(`"${encoded}"\\s*:`), scope);
 }
 /**
  * 1-based line number for the first JSON string value equal to `value`.
  * If `scope` is supplied (a byte range), only matches inside that range count —
  * this is the fix for the multi-server-ambiguity bug.
+ *
+ * The value is JSON-encoded before matching so values containing backslashes
+ * (e.g. Windows paths like `C:\Temp` written as `"C:\\Temp"` in JSON) are
+ * located correctly. The scan ignores JSONC comments so a commented-out
+ * matching value does not shadow the real one.
  */
 export function lineOfJsonStringValue(text, value, scope) {
-    const needle = `"${escapeForRegex(value)}"`;
-    return findLineByRegex(text, new RegExp(needle), scope);
+    const encoded = jsonEncodeForRegex(value);
+    return findLineByRegex(text, new RegExp(`"${encoded}"`), scope);
+}
+/**
+ * Convert a string to the form it would appear in JSON source bytes, then
+ * regex-escape. `JSON.stringify('C:\\Temp')` yields `'"C:\\\\Temp"'` — slice
+ * off the surrounding quotes to get the inner byte sequence.
+ */
+function jsonEncodeForRegex(input) {
+    const jsonBody = JSON.stringify(input).slice(1, -1);
+    return escapeForRegex(jsonBody);
 }
 /**
  * 1-based line number for a TOML key. Supports dotted keys (`a.b.c`) — the
@@ -79,7 +101,12 @@ function scopeLineFilter(text, scope) {
     return (line) => line >= startLine && line <= endLine;
 }
 function findLineByRegex(text, regex, scope) {
-    const haystack = scope ? text.slice(scope.start, scope.end) : text;
+    // stripJsonComments is position-preserving: it replaces comment bytes with
+    // spaces while leaving newlines intact. Offsets in the stripped text map
+    // 1:1 to offsets in the original text, so line numbers stay correct, but
+    // commented-out keys/values no longer match.
+    const searchable = stripJsonComments(text);
+    const haystack = scope ? searchable.slice(scope.start, scope.end) : searchable;
     const m = regex.exec(haystack);
     if (!m)
         return 0;

package/dist/shell.js

@@ -127,15 +127,43 @@ export function getCommandHead(subcommand) {
             break;
         s = s.slice(m[0].length);
     }
-    // Strip leading sudo / env wrappers
-    const wrapperMatch = /^(sudo|nohup|env|exec|command|builtin)\s+(.*)$/.exec(s);
+    // Strip leading sudo / env wrappers, then also strip any wrapper flags
+    // (`sudo -E`, `env -i`) and embedded env vars (`env FOO=1 BAZ=qux curl`)
+    // before recursing. Without this, `sudo -E curl` would return `-E`.
+    const wrapperMatch = /^(sudo|nohup|env|exec|command|builtin|stdbuf|nice|ionice|setsid)\s+(.*)$/.exec(s);
     if (wrapperMatch) {
-        return getCommandHead(wrapperMatch[2]);
+        return getCommandHead(stripWrapperPrefixes(wrapperMatch[2]));
     }
     // Now extract first token, honoring quoting and obfuscation neutralization.
     const head = readFirstToken(s);
     return deobfuscate(head);
 }
+/**
+ * Consume any leading flags (`-x`, `--xxx`, `--xxx=value`) and env var
+ * assignments (`FOO=bar`) so the next recursion finds the real command. We
+ * intentionally do NOT consume a non-flag token after a short flag (so
+ * `sudo -u user curl` still misclassifies as `user` — a known edge case
+ * that we accept rather than maintain a per-wrapper flag database).
+ */
+function stripWrapperPrefixes(input) {
+    let s = input.trimStart();
+    while (s.length > 0) {
+        if (s.startsWith('-')) {
+            const flagMatch = /^\S+\s*/.exec(s);
+            if (!flagMatch)
+                break;
+            s = s.slice(flagMatch[0].length);
+            continue;
+        }
+        const envMatch = /^([A-Za-z_][A-Za-z0-9_]*)=([^\s'"]*|"[^"]*"|'[^']*')\s+/.exec(s);
+        if (envMatch) {
+            s = s.slice(envMatch[0].length);
+            continue;
+        }
+        break;
+    }
+    return s;
+}
 function readFirstToken(s) {
     let out = '';
     let i = 0;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-gov-core",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Shared primitives for the AI-agent governance suite: Finding schema, JSONC/TOML readers, line locators, MCP command normalization, shell tokenization, and GitHub Action helpers.",
   "type": "module",
   "main": "./dist/index.js",