Neutralize internal Anthropic prose in explanatory comments (#357)

This is a small prose-only follow-up that rewrites clearly internal or
explanatory Anthropic comment language to neutral wording in a handful of
high-confidence files. It avoids runtime strings, flags, command labels,
protocol identifiers, and provider-facing references.

Constraint: Keep this pass narrowly scoped to comments/documentation only
Rejected: Broader Anthropic comment sweep across functional API/protocol references | too ambiguous for a safe prose-only PR
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Leave functional Anthropic references (API behavior, SDKs, URLs, provider labels, protocol docs) for separate reviewed passes
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)

Co-authored-by: anandh8x <test@example.com>

src/tools/BashTool/bashPermissions.ts

@@ -431,7 +431,7 @@ const ANT_ONLY_SAFE_ENV_VARS = new Set([
   'CLOUDSDK_CORE_PROJECT', // GCP project ID
   'CLUSTER', // generic cluster name
 
-  // Anthropic internal cluster selection (just names/identifiers)
+  // Internal cluster selection (just names/identifiers)
   'COO_CLUSTER', // coo cluster name
   'COO_CLUSTER_NAME', // coo cluster name (alternate)
   'COO_NAMESPACE', // coo namespace

src/tools/BashTool/readOnlyValidation.ts

@@ -1141,7 +1141,7 @@ const COMMAND_ALLOWLIST: Record<string, CommandConfig> = {
 const ANT_ONLY_COMMAND_ALLOWLIST: Record<string, CommandConfig> = {
   // All gh read-only commands from shared validation map
   ...GH_READ_ONLY_COMMANDS,
-  // aki — Anthropic internal knowledge-base search CLI.
+  // aki — internal knowledge-base search CLI.
   // Network read-only (same policy as gh). --audit-csv omitted: writes to disk.
   aki: {
     safeFlags: {

src/tools/WebFetchTool/utils.ts

@@ -177,7 +177,7 @@ type DomainCheckResult =
 export async function checkDomainBlocklist(
   domain: string,
 ): Promise<DomainCheckResult> {
-  // Third-party providers should not consult Anthropic's domain policy.
+  // Third-party providers should not consult the first-party domain policy.
   if (getAPIProvider() !== 'firstParty') {
     return { status: 'allowed' }
   }