Fix artifact title generation on client side

[Dev10-sys]

Fixes #243

Normalize artifact titles on the client side so that version and content variant strings are not unintentionally included in the displayed title.

Summary by CodeRabbit

• Bug Fixes
  • Improved search result reliability by ensuring documents without titles display a sensible fallback title and by inferring resource types so results show clearer labels.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

📝 Walkthrough

Walkthrough

Adds runtime normalization to ensure fetched documents have a title. For docs missing title, the handler sets title from the document id by extracting the last path segment (or the full id if no path segments).

Changes

Cohort / File(s)	Summary
Runtime Title Normalization public/js/search/search-adapter.js	In the lookup response handler, populate missing d.title from d.id by using the last path segment (fallback to the full id), then call SearchAdapter.inferResourceTypes(docs); whitespace/formatting adjustments only otherwise.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely describes the main change: fixing artifact title generation on the client side, which aligns with the primary objective.
Linked Issues check	✅ Passed	The code adds title normalization logic that derives clean titles from artifact IDs/URIs, directly addressing issue #243's requirement to prevent unwanted inclusion of version and content variant components in displayed titles.
Out of Scope Changes check	✅ Passed	All changes are focused on client-side title normalization in the search adapter, directly supporting the stated objective of fixing artifact title generation without introducing unrelated modifications.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🤖 Fix all issues with AI agents

In `@public/js/search/search-adapter.js`:
- Around line 35-44: The loop in the SearchAdapter response handler (where
docs.forEach and d.id splitting occurs) incorrectly assumes d.id.split("/")[1]
exists; update the logic to guard against absolute URIs and short IDs by: check
that d.id is a non-empty string, ignore URL schemes (e.g., startsWith("http://")
or "https://") or treat them by taking the last path segment, split on "/" and
use the last non-empty segment only if present, and if that still yields nothing
fall back to using the full d.id (or a safe decoded form) as the title so titles
are never left undefined; apply this change inside the docs.forEach callback in
the SearchAdapter response processing.

[Dev10-sys]

Good catch. Updated the title derivation to safely handle absolute URIs and short IDs by normalizing path segments with a fallback.