Enforce AutoResearch ledger frontier integrity

[FluffyAIcode]

Summary

• treat model-emitted obligation IDs as untrusted and repair only high-similarity corruption to the host-owned target
• reject invented IDs and generate all persisted child IDs in host code
• block duplicate lemma names, exact repeats, ancestor semantic cycles, and vague non-falsifiable frontiers

Test plan

• targeted AutoResearch tests: 43 passed
• exact regression for the corrupted Critic ID from br_ebe807d4ef25e337
• invented RH-Cty ID and repeated Angular-Growth ancestor are rejected

The uncommitted candidate.py file is active runtime state and is excluded.

Made with Cursor

[cursor]

Bugbot is not enabled for your account, so this pull request was not reviewed.

Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs.