Integration test: AI service OCR regression harness on multiple languages

[kilodesodiq-arch]

Problem Statement. regression_harness/evaluator.py runs against
regression_harness/dataset/ground_truth.json but a single language is supported.

Technical Context.
app/ai-service/regression_harness/.

Expected Outcome. Add Spanish + Arabic datasets, asserting OCR tolerance ≥ 0.7.

Acceptance Criteria.

• CI runs the harness on both languages.

Files or modules likely to be affected.
new app/ai-service/regression_harness/dataset/{es,ar}/ground_truth.json,
cli.py.

Difficulty. Medium
Estimated effort. M

---

---

Backlog item #70 from `docs/maintainer-issue-backlog.md.

[samsolo247]

Hi Maintainer,

I’m a smart contract and full-stack developer and would love to contribute to this issue. I’m an experienced contributor with hands-on expertise in Rust, Soroban, Cairo, and TypeScript.

I’m passionate about building secure, scalable blockchain solutions, with a strong emphasis on writing clean and maintainable code. Based on the scope of this issue, I’m confident I can deliver a complete solution within 24 hours of assignment.

I’d greatly appreciate the opportunity to contribute and help move this forward.

[devfoma]

Hello, I would love to take on this issue. I'm a software engineer with over 4 years experience. and i'm confident I can resolve this issue

[grantfox-oss]

🦊 GrantFox — @devfoma has been assigned to this issue as part of the Official Campaign | FWC26 campaign!

Next steps:

1. Open a Pull Request referencing this issue (e.g., Closes #278)
2. Your PR will be reviewed by the ChainForgee maintainers

Good luck! Track your progress on GrantFox.