feat(docs): add LLM-driven narrative doc sync pipeline

[dylandepass]

When a source repo (e.g. helix-commerce-api) merges to main, the new llm-doc-sync workflow computes diffs since each doc's lastReviewedCommit, sends them to GPT-5.6 Terra along with the current doc and style guide, and opens a PR with the drafted updates.

What's included

• scripts/docs/llm-sync.mjs — Core sync script: scans docs/*.md frontmatter, computes filtered diffs (excludes tests, CI, lock files), calls the OpenAI API, writes updated docs
• .github/workflows/llm-doc-sync.yaml — GitHub Actions workflow triggered by repository_dispatch (from source repos) or workflow_dispatch (manual). Checks out both repos, runs the sync, opens a PR labeled ai-authored
• scripts/docs/README.md — Updated with LLM doc sync documentation, local run instructions, and env var reference

How it works

1. Source repo fires a repository_dispatch event on merge to main
2. Workflow identifies affected docs via sources frontmatter mapping
3. Computes git diff lastReviewedCommit..HEAD (filtered to non-test code)
4. Sends diff + current doc + CLAUDE.md style guide to GPT-5.6 Terra
5. Opens a PR with the LLM-drafted updates for human review

Still needed (separate PRs)

• Dispatch trigger added to each source repo's release workflow
• SOURCE_REPOS_TOKEN and OPENAI_API_KEY secrets on this repo

[aem-code-sync]

Hello, I'm the AEM Code Sync Bot and I will run some actions to deploy your branch and validate page speed.
In case there are problems, just click a checkbox below to rerun the respective action.

• Re-run all PSI checks
• Re-run failed PSI checks
• Re-sync branch

Commits

• 87ba7f0 ✅ (latest)
• a1d4a24 ✅