Follow-up for dynamic tempo - removing deprecated activity cutoff by evgeny-s · Pull Request #2774 · opentensor/subtensor

evgeny-s · 2026-06-22T10:10:41Z

Description

Follow-up PR for #2638:

Remove ActivityCutoff storage map
PR comments from [Feature] Configurable Tempo & Owner-Triggered Epochs #2638

Breaking Changes ❗❗❗

On-chain storage & metadata

Removed SubtensorModule::ActivityCutoff and SubtensorModule::MinActivityCutoff. Both are purged from state by the migrate_remove_activity_cutoff runtime migration.
Migration path: read SubtensorModule::ActivityCutoffFactorMilli instead.

Extrinsics

Removed admin_utils.sudo_set_activity_cutoff.
Replacement: subtensor.set_activity_cutoff_factor(netuid, factor_milli).

EVM precompiles — `ISubnet`

Selectors are preserved (deployed contracts do not revert), but semantics changed:

getActivityCutoff(uint16) — now returns the derived effective cutoff.
setActivityCutoff(uint16,uint16) — now converts the block value to the equivalent per-tempo factor at the current tempo and dispatches set_activity_cutoff_factor.
New contracts should use setActivityCutoffFactor(uint16,uint32) / getActivityCutoffFactor(uint16) directly.

Events & Errors — deprecated, not removed (indices preserved)

Event::ActivityCutoffSet and Error::ActivityCutoffTooLow are marked #[deprecated] and are no longer emitted / returned.

Related Issue(s)

Closes #[issue number]

Type of Change

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
Documentation update
Other (please describe):

Breaking Change

If this PR introduces a breaking change, please provide a detailed description of the impact and the migration path for existing applications.

Checklist

I have performed a self-review of my own code
I have commented my code, particularly in hard-to-understand areas
I have run ./scripts/fix_rust.sh to ensure my code is formatted and linted correctly
I have made corresponding changes to the documentation
My changes generate no new warnings
I have added tests that prove my fix is effective or that my feature works
New and existing unit tests pass locally with my changes
Any dependent changes have been merged and published in downstream modules

Screenshots (if applicable)

Please include any relevant screenshots or GIFs that demonstrate the changes made.

Additional Notes

Please provide any additional information or context that may be helpful for reviewers.

github-actions · 2026-06-22T10:11:22Z

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
eco-tests/src/tests_taocom_indexer.rs

github-actions · 2026-06-22T10:13:21Z

🛡️ AI Review — Skeptic (security review)

VERDICT: SAFE

BASELINE scrutiny: established 2012 account with repository write permission, substantial subtensor PR history, and no Gittensor allowlist/index hit; branch chore/dynamic-tempo-cleanup -> devnet-ready.

Static review found no protected .github/ai-review/* or .github/copilot-instructions.md changes, no dependency or build-script changes, and no suspicious runtime execution path. The migration sequence reads legacy ActivityCutoff through a local alias before the new cleanup migration removes the old storage, and the deprecated EVM setter now dispatches to the bounded owner/root-checked set_activity_cutoff_factor path. spec_version is bumped from 423 to 424.

Findings

No findings.

Conclusion

No malicious intent or security vulnerability was identified in the reviewed diff. The previous Skeptic verdict had no finding markers, and the current changes remain consistent with a dynamic-tempo cleanup and backward-compatible precompile behavior.

🔍 AI Review — Auditor (domain review)

VERDICT: 👍

Gittensor: LIKELY by heuristic; no allowlist/index hit, but author has write permission and substantial recent Subtensor PR activity.

The Auditor proposed a replacement PR description, but the current body is non-trivial; not overwriting. Maintainers: ask the Auditor to regenerate if you want it.

Static review covered the legacy ActivityCutoff / MinActivityCutoff removal, the raw storage alias retained for migrate_dynamic_tempo, migration ordering that converts legacy cutoff values before clearing old storage, admin-utils removal, runtime proxy filter update, precompile ABI compatibility, and focused migration tests for wiping legacy storage.

The previous blocker is addressed: deprecated setActivityCutoff(uint16,uint16) now converts the legacy absolute block value to ActivityCutoffFactorMilli and dispatches through the bounded owner/root-checked set_activity_cutoff_factor path instead of returning success as a no-op.

spec_version is bumped from 423 to 424. git diff --check passed. No auto-fixes were applied. I attempted the targeted precompile test, but this runner cannot populate rustup/Cargo caches because $HOME is read-only, so runtime confirmation was not available here.

Duplicate-work check found overlapping files with other open PRs, but no competing PR appears to implement this ActivityCutoff cleanup.

Findings

No findings.

Prior-comment reconciliation

ef3a69cc: addressed — setActivityCutoff(uint16,uint16) now converts legacy block cutoffs to a per-tempo factor and dispatches set_activity_cutoff_factor, so it no longer reports success without changing state.

Conclusion

Approving because the prior behavioral blocker is fixed and the cleanup preserves the dynamic-tempo migration path before deleting legacy storage. Remaining risk is limited to test execution being unavailable in this runner; CI should run the targeted precompile and migration tests.

📜 Previous run (superseded)

~~Sev~~	~~File~~	~~Finding~~	Status
~~HIGH~~	~~`precompiles/src/subnet.rs:487`~~	~~Deprecated precompile setter succeeds without changing state~~	✅ Addressed `setActivityCutoff(uint16,uint16)` now converts legacy block cutoffs to a per-tempo factor and dispatches `set_activity_cutoff_factor`, so it no longer reports success without changing state.

github-actions · 2026-06-22T10:16:43Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-22T10:32:33Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-22T11:03:27Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

…-tempo-cleanup

github-actions · 2026-06-22T14:15:19Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

# Conflicts: # pallets/admin-utils/src/weights.rs

github-actions

AI review — see the sticky summary comment for the verdict and the inline comments below for specific findings.

github-actions · 2026-06-24T11:14:29Z

 	fn sudo_set_difficulty() -> Weight;
 	fn sudo_set_adjustment_interval() -> Weight;
 	fn sudo_set_target_registrations_per_interval() -> Weight;
-	fn sudo_set_activity_cutoff() -> Weight;


[HIGH] Remove the stale generated weight implementations too

Deleting this trait item leaves two generated sudo_set_activity_cutoff() implementations in this same file, around pallets/admin-utils/src/weights.rs:367 and pallets/admin-utils/src/weights.rs:1333. Those methods are no longer members of WeightInfo, and Rust trait impls cannot define extra associated methods, so pallet-admin-utils will not compile after this cleanup. Regenerate pallets/admin-utils/src/weights.rs or manually remove both stale method blocks along with this trait item.

github-actions · 2026-06-24T11:14:37Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👎

github-actions

AI review — see the sticky summary comment for the verdict and the inline comments below for specific findings.

github-actions · 2026-06-24T11:46:03Z

 	fn sudo_trim_to_max_allowed_uids() -> Weight;
 	fn sudo_set_min_non_immune_uids() -> Weight;
 	fn sudo_set_max_epochs_per_block() -> Weight;
+	fn sudo_set_activity_cutoff() -> Weight;


[LOW] Remove the stale generated activity-cutoff weight stub

sudo_set_activity_cutoff was removed from pallets/admin-utils/src/lib.rs and its benchmark was deleted, but the generated WeightInfo trait still exposes the method and both generated impls still define it against the removed SubtensorModule::ActivityCutoff / MinActivityCutoff storage. This no longer appears to be the compile-breaking mismatch from the prior run because the trait and impls are internally consistent, but it leaves dead generated weight code for an extrinsic this PR removes. Regenerate pallets/admin-utils/src/weights.rs or delete the stale trait item and the two sudo_set_activity_cutoff impl blocks.

github-actions · 2026-06-24T11:46:15Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

# Conflicts: # contract-tests/src/contracts/subnet.ts # contract-tests/src/subtensor.ts # contract-tests/test/staking.precompile.reward.test.ts

github-actions

AI review — see the sticky summary comment for the verdict and the inline comments below for specific findings.

github-actions · 2026-06-25T08:34:41Z

 	fn sudo_trim_to_max_allowed_uids() -> Weight;
 	fn sudo_set_min_non_immune_uids() -> Weight;
 	fn sudo_set_max_epochs_per_block() -> Weight;
+	fn sudo_set_activity_cutoff() -> Weight;


[LOW] Remove the stale generated activity-cutoff weight stub

sudo_set_activity_cutoff was removed from pallets/admin-utils/src/lib.rs, but this generated weight method is still re-added to the trait and the file still carries both impl bodies for the removed call. This is dead generated code over storage that the PR deletes; regenerate pallet_admin_utils weights or remove the trait method and both impl methods so the weights file matches the pallet surface.

github-actions · 2026-06-25T08:34:51Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-25T08:45:47Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-25T08:56:35Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-29T14:30:44Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

github-actions · 2026-06-30T11:50:45Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

gztensor · 2026-06-30T13:54:32Z

@@ -1,23 +1,4 @@
 [
-	{


For backward-compatibility, we should keep the getActivityCutoff in precompiles, otherwise the existing contracts will start failing. They may respond with 0 or something hardcoded.

gztensor · 2026-06-30T13:54:48Z

        int16 steepness
    ) external payable;

-    function getActivityCutoff(uint16 netuid) external view returns (uint16);


For backward-compatibility, we should keep the getActivityCutoff in precompiles, otherwise the existing contracts will start failing. They may respond with 0 or something hardcoded.

github-actions · 2026-07-01T08:58:30Z

@opentensor/cerebrum / @opentensor/gyrus / @opentensor/cortex breaking change detected! Please prepare accordingly!

github-actions

AI review — see the sticky summary comment for the verdict and the inline comments below for specific findings.

github-actions · 2026-07-01T11:24:45Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👎

github-actions · 2026-07-01T12:15:30Z

🔄 AI review updated — Skeptic: SAFE Auditor: 👍

Follow-up for dynamic tempo - removing deprecated activity cutoff

48036ef

evgeny-s added the skip-cargo-audit This PR fails cargo audit but needs to be merged anyway label Jun 22, 2026

Hardcode values in the mocks

e9e29f0

fix for the test

43287c5

evgeny-s changed the title ~~Follow-up for dynamic tempo - removing deprecated activity cutoff~~ [DO NOT MERGE] Follow-up for dynamic tempo - removing deprecated activity cutoff Jun 22, 2026

Merge branch 'feat/configure-max-epochs-per-block' into chore/dynamic…

5a0443a

…-tempo-cleanup

Merge branch 'devnet-ready' into chore/dynamic-tempo-cleanup

f96c396

# Conflicts: # pallets/admin-utils/src/weights.rs

evgeny-s changed the base branch from feat/configure-max-epochs-per-block to devnet-ready June 24, 2026 11:08

github-actions Bot reviewed Jun 24, 2026

View reviewed changes

Fix after merge conflict

1eda8d9

github-actions Bot reviewed Jun 24, 2026

View reviewed changes

Merge branch 'devnet-ready' into chore/dynamic-tempo-cleanup

ae90b99

# Conflicts: # contract-tests/src/contracts/subnet.ts # contract-tests/src/subtensor.ts # contract-tests/test/staking.precompile.reward.test.ts

github-actions Bot reviewed Jun 25, 2026

View reviewed changes

Cleanup after conflict

cbca24a

spec version bump

5381d5e

evgeny-s changed the title ~~[DO NOT MERGE] Follow-up for dynamic tempo - removing deprecated activity cutoff~~ Follow-up for dynamic tempo - removing deprecated activity cutoff Jun 29, 2026

Merge branch 'devnet-ready' into chore/dynamic-tempo-cleanup

b6f8f93

Extract constant outside the pallet

0d66c42

github-actions Bot mentioned this pull request Jun 30, 2026

Add eco-tests protecting Mentat indexer storage reads #2818

Open

13 tasks

l0r1s previously approved these changes Jun 30, 2026

View reviewed changes

Comment thread precompiles/src/solidity/subnet.sol

Comment thread pallets/subtensor/src/lib.rs

gztensor requested changes Jun 30, 2026

View reviewed changes

evgeny-s added the breaking-change This PR introduces a noteworthy breaking change label Jul 1, 2026

revert errors/event/precompiles

85e28cf

evgeny-s dismissed l0r1s’s stale review via 85e28cf July 1, 2026 11:19

github-actions Bot reviewed Jul 1, 2026

View reviewed changes

Comment thread precompiles/src/subnet.rs

update the set_activity_cutoff function for backward compatibility

7ce5cd0

gztensor approved these changes Jul 1, 2026

View reviewed changes

Uh oh!

Conversation

evgeny-s commented Jun 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Breaking Changes ❗❗❗

On-chain storage & metadata

Extrinsics

EVM precompiles — ISubnet

Events & Errors — deprecated, not removed (indices preserved)

Related Issue(s)

Type of Change

Breaking Change

Checklist

Screenshots (if applicable)

Additional Notes

Uh oh!

github-actions Bot commented Jun 22, 2026

eco-tests changed — indexer review required

Uh oh!

github-actions Bot commented Jun 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🛡️ AI Review — Skeptic (security review)

Findings

Conclusion

🔍 AI Review — Auditor (domain review)

Findings

Prior-comment reconciliation

Conclusion

Uh oh!

github-actions Bot commented Jun 22, 2026

Uh oh!

github-actions Bot commented Jun 22, 2026

Uh oh!

github-actions Bot commented Jun 22, 2026

Uh oh!

github-actions Bot commented Jun 22, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Jun 24, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Jun 24, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Jun 24, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Jun 24, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Jun 25, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Jun 25, 2026

Uh oh!

github-actions Bot commented Jun 25, 2026

Uh oh!

github-actions Bot commented Jun 25, 2026

Uh oh!

github-actions Bot commented Jun 29, 2026

Uh oh!

github-actions Bot commented Jun 30, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gztensor Jun 30, 2026

Choose a reason for hiding this comment

Uh oh!

gztensor Jun 30, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Jul 1, 2026

evgeny-s commented Jun 22, 2026 •

edited

Loading

EVM precompiles — `ISubnet`

github-actions Bot commented Jun 22, 2026 •

edited

Loading