feat: complete local-model agent ecosystem showcase

[0xjcf]

Summary

• Adds the OpenAI-compatible tool dialect for local and hosted Chat Completions-style providers.
• Extends the smart-home example with local MLX/OpenAI-compatible agent flows, browser bridge support, and actor-web-backed runtime dogfood.
• Documents local-model agent boundaries and validation expectations for the v3 roadmap.
• Includes CodeRabbit closeout fixes for response validation, timeout cleanup, runtime close behavior, and bridge lifecycle ordering.

Validation

• pnpm --filter ignite-element exec vitest --run --root ../../examples/agents/smart-home --config ../../examples/agents/smart-home/vite.config.ts
• fas validate-task
• .fas/scripts/verify.sh --full
• fas runtime process-pressure --stage full-verify --preflight --cleanup-plan reported yellow with reliable counts/RSS.
• coderabbit review --agent -t committed --base beta -c AGENTS.md completed with 0 issues after retrying a recoverable rate limit.
• fas batch close --dry-run and fas batch close completed for all 5 batched tasks.

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: bc7141cd-6b90-4a37-9749-e876d9cba2be

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fas/local-model-agent-ecosystem

---

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

[codecov]

Codecov Report

❌ Patch coverage is 98.30508% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 91.47%. Comparing base (2f86faa) to head (e6b4fd1).
⚠️ Report is 1 commits behind head on beta.

Files with missing lines	Patch %	Lines
packages/ignite-element/src/tools/openai/index.ts	98.30%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             beta      #86      +/-   ##
==========================================
+ Coverage   91.25%   91.47%   +0.22%     
==========================================
  Files          33       34       +1     
  Lines        1830     1889      +59     
  Branches      498      513      +15     
==========================================
+ Hits         1670     1728      +58     
- Misses        150      151       +1     
  Partials       10       10              

Flag	Coverage Δ
unittests	91.47% <98.30%> (+0.22%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
packages/ignite-element/src/tools/openai/index.ts	98.30% <98.30%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.