fix: wire allowed_tools/disallowed_tools inputs through to Claude SDK

The disallowed tools env var read in run.ts was DISALLOWED_TOOLS_INPUT
(raw user input) instead of DISALLOWED_TOOLS (computed value including
WebSearch/WebFetch defaults). This meant default tool disallowance was
never enforced. Also removes orphaned ALLOWED_TOOLS env var export from
createPrompt() (tag mode passes allowed tools via claudeArgs instead),
extracts shared parseToolsInput utility to eliminate duplication, and
adds tests.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/entrypoints/run.ts

@@ -245,6 +245,7 @@ async function run() {
 
     const claudeResult: ClaudeRunResult = await runClaude(promptConfig.path, {
       claudeArgs: prepareResult.claudeArgs,
+      disallowedTools: process.env.DISALLOWED_TOOLS || undefined,
       appendSystemPrompt: process.env.APPEND_SYSTEM_PROMPT,
       model: process.env.ANTHROPIC_MODEL,
       pathToClaudeCodeExecutable: