feat(recall): cap injected memory context

[YOMXXX]

Summary

• Add recall.maxCharsPerMemory and recall.maxTotalRecallChars with defaults of 800 and 3000.
• Apply the budget after L1 search and before <relevant-memories> injection, preserving score order while truncating oversized entries and dropping overflow.
• Document the new guards in README, README_CN, and openclaw.plugin.json.
• Keep the npm tarball under the existing 512KB Size Guard by shipping built runtime files instead of raw src/ and pointing OpenClaw to dist/index.mjs.

Test Plan

• npm test
• npm run build
• npm pack --dry-run --json
• git diff --check

Notes

• Addresses L1 auto-recall needs atomization and token-budget safeguards #70 as an MVP focused on recall-time safeguards.
• npx tsc --noEmit ... still fails on current upstream/main due unrelated existing type issues in commander/OpenAI settings/offload strict initialization; this PR does not touch those areas.