Localize README context diagram alt text

## Summary

- Localizes the context-diagram alt text in `README.md`, `README.ja-JP.md`, and `README.ko.md`.
- Leaves the already-present `bash` install fences unchanged.
- Aligns these README variants with the localized alt-text pattern already used by the German and Simplified Chinese READMEs.

## Problem

- #2162 tracks markdown-lint cleanup for root/Japanese/Korean READMEs.
- The install fences are already fixed on current `main`, but the context diagram still used generic English alt text in all three files.

## Solution

- Replace `OpenHuman context diagram` with descriptive localized alt text per README locale.

## Submission Checklist

- [x] Tests added or updated (happy path + at least one failure / edge case) per [Testing Strategy](../gitbooks/developing/testing-strategy.md#failure-path-requirement) — N/A: docs-only alt text change.
- [x] **Diff coverage ≥ 80%** — N/A: docs-only change.
- [x] Coverage matrix updated — N/A: docs-only change.
- [x] All affected feature IDs from the matrix are listed in the PR description under `## Related`
- [x] No new external network dependencies introduced (mock backend used per [Testing Strategy](../gitbooks/developing/testing-strategy.md#mock-policy))
- [x] Manual smoke checklist updated if this touches release-cut surfaces — N/A: docs-only change.
- [x] Linked issue closed via `Closes #NNN` in the `## Related` section

## Impact

- Documentation accessibility metadata improves for screen readers and markdown-lint checks.
- No runtime impact.

## Related

- Closes: #2162
- Follow-up PR(s)/TODOs: N/A
- Coverage matrix feature IDs: N/A: docs-only change.

---

## AI Authored PR Metadata (required for Codex/Linear PRs)

### Linear Issue
- Key: N/A
- URL: N/A

### Commit & Branch
- Branch: codex/2162-readme-alt-locales
- Commit SHA: 0f5a796d

### Validation Run
- [x] `pnpm --filter openhuman-app format:check` — N/A: docs-only change.
- [x] `pnpm typecheck` — N/A: docs-only change.
- [x] Focused tests: N/A: docs-only change.
- [x] Rust fmt/check (if changed): N/A: no Rust files changed.
- [x] Tauri fmt/check (if changed): N/A: no Tauri files changed.
- [x] `git diff --check`
- [x] Verified install fences already use `bash` in the three affected READMEs.

### Validation Blocked
- `command:` N/A
- `error:` N/A
- `impact:` N/A

### Behavior Changes
- Intended behavior change: localized alt text for the README context diagram.
- User-visible effect: better accessibility metadata in README variants.

### Parity Contract
- Legacy behavior preserved: README layout, image path, and install snippets unchanged.
- Guard/fallback/dispatch parity checks: N/A.

### Duplicate / Superseded PR Handling
- Duplicate PR(s): N/A
- Canonical PR: N/A
- Resolution (closed/superseded/updated): N/A

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

## Summary by CodeRabbit

* **Documentation**
  * Improved documentation accessibility and internationalization through refined image alt text descriptions. Updated the OpenHuman context-building diagram descriptions across English, Japanese, and Korean README versions with more accurate, language-appropriate text to better serve all international users and enhance overall documentation clarity.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2324?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Co-authored-by: aqilaziz <gonzes7@gmail.com>
Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>

README.ja-JP.md

@@ -89,7 +89,7 @@ OpenHuman は、あなたの日常生活に統合されるよう設計された
 OpenHuman は、数分であなたのことを理解する初めてのエージェントハーネスです。[Karpathy 氏の LLM ナレッジベース](https://x.com/karpathy/status/2039805659525644595)にインスパイアされました。ほとんどのエージェントは冷えた状態から始まります。Hermes はあなたの作業を見て学習し、OpenClaw はプラグインがコンテキストを運び込むのを待ちます。いずれにせよ、エージェントがあなたのスタックを十分理解して本当に役立つようになるまで、数日から数週間を費やすことになります。
 
 <p align="center">
- <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman context diagram">
+ <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman のコンテキスト構築図">
 </p>
 
 > OpenHuman はあなたのすべてのドキュメント、メール、チャットを要約・圧縮し、エージェントがあなたについてすべてを覚えていられるメモリーグラフを作成します。

README.ko.md

@@ -90,7 +90,7 @@ OpenHuman은 일상 생활에 통합되도록 설계된 오픈 소스 에이전
 OpenHuman은 몇 분 만에 당신을 알게 되는 최초의 에이전트 하네스입니다. [Karpathy의 LLM 지식 베이스](https://x.com/karpathy/status/2039805659525644595)에서 영감을 받았습니다. 대부분의 에이전트는 아무런 정보 없이 시작합니다. Hermes는 당신의 작업을 지켜보며 학습하고, OpenClaw는 플러그인이 컨텍스트를 가져오기를 기다립니다. 어느 쪽이든 에이전트가 당신의 스택에 대해 충분히 알고 정말 유용해지기까지는 며칠 또는 몇 주가 걸립니다.
 
 <p align="center">
- <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman context diagram">
+ <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman 컨텍스트 구축 다이어그램">
 </p>
 
 > OpenHuman은 당신의 모든 문서, 이메일 및 채팅을 요약하고 압축합니다. 그리고 에이전트가 당신에 대한 모든 것을 기억할 수 있도록 메모리 그래프를 생성합니다.

README.md

@@ -89,7 +89,7 @@ Deeper docs: [Architecture](https://tinyhumans.gitbook.io/openhuman/developing/a
 OpenHuman is the first agent harness that gets to know you in minutes. Inspired by [Karpathy's LLM Knowledgebase](https://x.com/karpathy/status/2039805659525644595). Most agents start cold. Hermes learns by watching you work; OpenClaw waits for plugins to ferry context in. Either way, you spend days or weeks before the agent knows enough about your stack to be genuinely useful.
 
 <p align="center">
- <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman context diagram">
+ <img src="./gitbooks/.gitbook/assets/image (1).png" alt="OpenHuman context-building diagram">
 </p>
 
 > OpenHuman summarizes and compresses all your documents, emails & chats; and creates a memory graph that lets your agent remember everything about you.