fix wrong and bad comments

[UnArbosSix]

Summary

This PR corrects inaccurate or stale comments in Subtensor runtime, pallet, mock, and test files. The updates clarify current behavior around TAO weight scaling, set-weights normalization, childkey take scaling, owner cut auto-lock defaults, subnet netuid terminology, and default mock/runtime parameter comments.

Files of Interest

• pallets/subtensor/src/macros/dispatches.rs: Updates set-weights and childkey take rustdoc to describe max-upscaled u16 values rather than percentage/sum-based semantics.
• pallets/subtensor/src/staking/stake_utils.rs: Rewords TAO weight/stake comments to match the actual storage and stake-combination logic.
• pallets/subtensor/src/lib.rs: Corrects default-value comments for DefaultTrue, DefaultCKBurn, and OwnerCutAutoLockEnabled.
• runtime/src/lib.rs, chain-extensions/src/mock.rs, eco-tests/src/mock.rs, and pallet test mocks: Correct TAO weight percentage comments.
• runtime/src/lib.rs: Bumps spec_version from 426 to 427 for the devnet-ready runtime change.

Behavioral Impact

No executable logic is changed. The PR only updates comments/rustdoc and the runtime spec_version.

Migration / Spec Version

No storage migration is introduced. spec_version is bumped to 427.

Testing

No runtime tests were added or run because the implementation logic is unchanged. Static review confirmed the edited comments match the nearby code paths.

[github-actions]

eco-tests changed — indexer review required

This PR modifies files under eco-tests/. and may affect downstream indexing.
cc @evgeny-s — please review manually

Changed files

• eco-tests/src/mock.rs

[github-actions]

🛡️ AI Review — Skeptic (security review)

VERDICT: SAFE

VERY HIGH scrutiny from new account / low public contribution graph, mitigated by repo write permission; no Gittensor association found; branch fix-wrong-and-bad-comments -> devnet-ready.

Findings

No findings.

Conclusion

Static review found documentation/comment corrections plus a runtime spec_version bump, with no hidden logic, dependency, build-script, workflow, or AI-review instruction changes. No security vulnerability or malicious pattern found.

---

🔍 AI Review — Auditor (domain review)

VERDICT: 👍

Gittensor association UNKNOWN by allowlist/heuristic; author account is very new but has repo write permission, so review focused on whether the comment-only changes accurately describe existing behavior.

PR body was empty/trivial; the Auditor has auto-filled it. Please review.

Static audit found documentation/comment corrections plus the expected spec_version bump. The changed comments match the surrounding implementation: TAO weight is stored as a u64 normalized over u64::MAX, set-weights storage uses max-upscaled u16 values, childkey take is scaled by u16::MAX, and owner cut auto-lock defaults to false.

No duplicate PR appeared to be a better candidate; the overlapping PRs are broader feature/deployment/SDK changes rather than competing documentation fixes. I ran git diff --check; no whitespace errors were reported. I did not run cargo tests because this PR does not change executable logic.

Findings

No findings.

Conclusion

Approve: the PR is narrow, comment-only aside from the version bump, and the corrected comments align with the current code paths reviewed.

[github-actions]

🔄 AI review updated — Skeptic: SAFE Auditor: 👍