Refresh models catalog and website

[konard]

Summary

• Refreshes the generated models.dev catalog into 4,490 provider .lino files plus website/public/models.json.
• Rebuilds the website as a searchable model table with summary metrics, provider/capability/modality search, and GitHub Pages-safe model detail routes.
• Adds a manual and weekly scheduled catalog refresh workflow, and tightens PR/deploy workflows with explicit permissions, timeouts, data validation, and build artifacts.
• Rewrites the README coverage and adds the Issue 10 case study under docs/case-studies/issue-10.

Verification

• npm --prefix website run check:data
• npm --prefix website run lint
• npm --prefix website run test
• npm --prefix website run build
• Playwright render check for desktop table, model detail page, and mobile table; browser console had no warnings or errors.

Screenshots

Fixes #10

[konard]

Working session summary

Done. PR 11 is updated, pushed, and ready for review:

#11

Pushed commit f30276b with:

• models.dev refresh into 4,490 .lino model files across 120 providers plus website/public/models.json
• searchable React catalog table and model detail routes
• manual + weekly update workflow
• tightened PR/deploy workflows
• README updates, issue case study, and committed screenshots

Verified locally:

• npm --prefix website run check:data
• npm --prefix website run lint
• npm --prefix website run test
• npm --prefix website run build
• Playwright desktop/detail/mobile render checks with no browser console warnings/errors

Fresh CI is green: PR Checks run 25757854820 passed on f30276b. Local working tree is clean.

---

This summary was automatically extracted from the AI working session output.

[konard]

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost estimation:

• Model: GPT-5.5
• Provider: OpenAI
• Public pricing estimate: $20.642831

📊 Context and tokens usage:

• 422.4K / 1.1M (40%) input tokens, 60.8K / 128K (48%) output tokens

Total: (422.4K + 13.7M cached) input tokens, 60.8K output tokens, $20.642831 cost

🤖 Models used:

• Tool: OpenAI Codex
• Requested: gpt-5.5
• Model: GPT-5.5 (gpt-5.5)

📎 Log file uploaded as Repository (89212KB)

• View complete solution draft log

---

Now working session is ended, feel free to review and add any feedback on the solution draft.

[konard]

✅ Ready to merge

This pull request is now ready to be merged:

• All CI checks have passed
• No merge conflicts
• No pending changes

---

Monitored by hive-mind with --auto-restart-until-mergeable flag