feat(autonomy): guard enforcement works (denylist, budget caps, tool call limits) #1204

Merged

brent.edwards merged 4 commits from feature/m6-guard-enforcement into master 2026-04-01 01:46:37 +00:00

Conversation 2 Commits 4 Files changed 6 +116 -7

brent.edwards commented 2026-03-29 20:30:42 +00:00

Member

Copy link

Summary

• Enforced autonomy guard behavior for denylist/allowlist checks, budget caps, tool-call limits, and write/apply approval gates.
• Added scope-aware guard evaluation (plan vs subplan) using GuardScope(StrEnum) for type-safe scope handling.
• Extracted remediation guidance strings as module-level constants (REMEDIATION_DENYLIST, REMEDIATION_ALLOWLIST, etc.) for consistency and testability.
• Added Behave coverage to validate guard remediation messaging and subplan-scoped tool-call limit behavior.

Review Fix Round (v2)

Addressed review #2910 by @freemo:

1. Reverted resource_dag.robot — Unrelated Robot SQLite/cycle-detection changes removed from this commit; will be submitted as a separate PR.
2. scope parameter → GuardScope enum — Created GuardScope(StrEnum) in automation_guard.py with PLAN and SUBPLAN members. Updated check_guard() signature and all call sites.
3. Removed redundant scope_label — Now uses scope.value directly.
4. Extracted remediation constants — Guidance strings moved to module-level constants in automation_guard.py.

Validation

• nox -s lint — passed
• nox -s typecheck — passed (0 errors, 0 warnings)
• nox -s unit_tests — passed (508 features, 12989 scenarios, 0 failures)
• nox -s coverage_report — passed (97% coverage)
• Rebased onto latest master (532ea100)

Closes #853

## Summary - Enforced autonomy guard behavior for denylist/allowlist checks, budget caps, tool-call limits, and write/apply approval gates. - Added scope-aware guard evaluation (plan vs subplan) using `GuardScope(StrEnum)` for type-safe scope handling. - Extracted remediation guidance strings as module-level constants (`REMEDIATION_DENYLIST`, `REMEDIATION_ALLOWLIST`, etc.) for consistency and testability. - Added Behave coverage to validate guard remediation messaging and subplan-scoped tool-call limit behavior. ## Review Fix Round (v2) Addressed review #2910 by @freemo: 1. **Reverted `resource_dag.robot`** — Unrelated Robot SQLite/cycle-detection changes removed from this commit; will be submitted as a separate PR. 2. **`scope` parameter → `GuardScope` enum** — Created `GuardScope(StrEnum)` in `automation_guard.py` with `PLAN` and `SUBPLAN` members. Updated `check_guard()` signature and all call sites. 3. **Removed redundant `scope_label`** — Now uses `scope.value` directly. 4. **Extracted remediation constants** — Guidance strings moved to module-level constants in `automation_guard.py`. ## Validation - `nox -s lint` — passed - `nox -s typecheck` — passed (0 errors, 0 warnings) - `nox -s unit_tests` — passed (508 features, 12989 scenarios, 0 failures) - `nox -s coverage_report` — passed (97% coverage) - Rebased onto latest `master` (532ea100) Closes #853

brent.edwards added this to the v3.5.0 milestone 2026-03-29 20:30:42 +00:00

brent.edwards added the

Type

Feature

label 2026-03-29 20:30:49 +00:00

brent.edwards added a new dependency 2026-03-29 20:31:17 +00:00

#853 feat(autonomy): guard enforcement works (denylist, budget caps, tool call limits)

brent.edwards force-pushed feature/m6-guard-enforcement from ca701e2ca7 to 47d86c77aa 2026-03-29 20:38:24 +00:00 Compare

freemo requested changes 2026-03-30 04:17:38 +00:00

freemo left a comment

Copy link

Review: REQUEST CHANGES

Issue 1: Unrelated Robot Fix Bundled

The resource_dag.robot changes (replacing create_engine with StaticPool and fixing cycle detection test to use distinct resource types) are unrelated to the guard enforcement feature. Per CONTRIBUTING.md §Atomic Commits: "Do not mix concerns. Never bundle cosmetic changes with functional changes in the same commit."

Please split the Robot SQLite fix into a separate commit.

Issue 2: scope Parameter Should Be an Enum

check_guard() accepts scope as a raw str validated with if scope not in {"plan", "subplan"}. Per CONTRIBUTING.md §Type Safety: "Prefer static typing whenever the language supports it." This should be a proper Enum:

class GuardScope(str, Enum):
    PLAN = "plan"
    SUBPLAN = "subplan"

This provides type safety, IDE autocompletion, and prevents typos at call sites.

Minor Notes

• The scope_label variable is redundant — after validation, it's always equal to scope itself.
• Remediation guidance strings are hardcoded inline in f-strings. Consider extracting them as constants for consistency and testability.
• The core guard enforcement logic (denylist, budget caps, tool-call limits) is well-implemented with clear deny reasons.

## Review: REQUEST CHANGES ### Issue 1: Unrelated Robot Fix Bundled The `resource_dag.robot` changes (replacing `create_engine` with `StaticPool` and fixing cycle detection test to use distinct resource types) are **unrelated** to the guard enforcement feature. Per CONTRIBUTING.md §Atomic Commits: "Do not mix concerns. Never bundle cosmetic changes with functional changes in the same commit." Please split the Robot SQLite fix into a separate commit. ### Issue 2: `scope` Parameter Should Be an Enum `check_guard()` accepts `scope` as a raw `str` validated with `if scope not in {"plan", "subplan"}`. Per CONTRIBUTING.md §Type Safety: "Prefer static typing whenever the language supports it." This should be a proper `Enum`: ```python class GuardScope(str, Enum): PLAN = "plan" SUBPLAN = "subplan" ``` This provides type safety, IDE autocompletion, and prevents typos at call sites. ### Minor Notes - The `scope_label` variable is redundant — after validation, it's always equal to `scope` itself. - Remediation guidance strings are hardcoded inline in f-strings. Consider extracting them as constants for consistency and testability. - The core guard enforcement logic (denylist, budget caps, tool-call limits) is well-implemented with clear deny reasons.

freemo requested reviews from freemo, CoreRasurae 2026-03-30 05:13:59 +00:00

brent.edwards force-pushed feature/m6-guard-enforcement from 47d86c77aa to 45c0242ef5 2026-03-31 03:54:32 +00:00 Compare

brent.edwards referenced this pull request 2026-03-31 03:55:00 +00:00

feat(autonomy): guard enforcement works (denylist, budget caps, tool call limits) #853

brent.edwards commented 2026-03-31 03:55:10 +00:00

Author

Member

Copy link

@freemo — All four items from review #2910 have been addressed. Here's a summary:

Issue 1: Unrelated Robot Fix Bundled ✅

Reverted robot/resource_dag.robot to its master state. The StaticPool migration and distinct resource type changes are no longer in this commit. They'll need a separate PR/issue.

Issue 2: scope Parameter Should Be an Enum ✅

Created GuardScope(StrEnum) in automation_guard.py with PLAN and SUBPLAN members. Updated check_guard() signature to accept GuardScope instead of str, and updated all call sites (service, Behave steps). The runtime if scope not in {...} validation is no longer needed since Pyright enforces the type statically, and StrEnum construction raises ValueError for invalid values.

Minor Notes ✅

• scope_label removed — now uses scope.value directly throughout the guard messages.
• Remediation constants extracted — Six module-level constants (REMEDIATION_DENYLIST, REMEDIATION_ALLOWLIST, REMEDIATION_TOOL_CALL_LIMIT, REMEDIATION_BUDGET, REMEDIATION_WRITE_APPROVAL, REMEDIATION_APPLY_APPROVAL) in automation_guard.py.

Validation

All quality gates pass. Branch rebased onto latest master (532ea100). PR is now mergeable.

@freemo — All four items from review #2910 have been addressed. Here's a summary: ### Issue 1: Unrelated Robot Fix Bundled ✅ Reverted `robot/resource_dag.robot` to its master state. The StaticPool migration and distinct resource type changes are no longer in this commit. They'll need a separate PR/issue. ### Issue 2: `scope` Parameter Should Be an Enum ✅ Created `GuardScope(StrEnum)` in `automation_guard.py` with `PLAN` and `SUBPLAN` members. Updated `check_guard()` signature to accept `GuardScope` instead of `str`, and updated all call sites (service, Behave steps). The runtime `if scope not in {...}` validation is no longer needed since Pyright enforces the type statically, and `StrEnum` construction raises `ValueError` for invalid values. ### Minor Notes ✅ - **`scope_label` removed** — now uses `scope.value` directly throughout the guard messages. - **Remediation constants extracted** — Six module-level constants (`REMEDIATION_DENYLIST`, `REMEDIATION_ALLOWLIST`, `REMEDIATION_TOOL_CALL_LIMIT`, `REMEDIATION_BUDGET`, `REMEDIATION_WRITE_APPROVAL`, `REMEDIATION_APPLY_APPROVAL`) in `automation_guard.py`. ### Validation All quality gates pass. Branch rebased onto latest master (532ea100). PR is now mergeable.

brent.edwards referenced this pull request 2026-03-31 09:58:53 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types #1226

brent.edwards referenced this pull request from a commit 2026-03-31 11:23:53 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

brent.edwards referenced this pull request 2026-03-31 11:24:04 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types #1228

brent.edwards added 1 commit 2026-03-31 23:51:00 +00:00

Merge branch 'master' into feature/m6-guard-enforcement 1e1eb18327

brent.edwards added 1 commit 2026-04-01 00:08:35 +00:00

Merge branch 'master' into feature/m6-guard-enforcement d163f12659

brent.edwards added 1 commit 2026-04-01 00:41:15 +00:00

Merge branch 'master' into feature/m6-guard-enforcement 967c665bf9

brent.edwards removed a dependency 2026-04-01 00:42:39 +00:00

#853 feat(autonomy): guard enforcement works (denylist, budget caps, tool call limits)

brent.edwards scheduled this pull request to auto merge when all checks succeed 2026-04-01 00:42:50 +00:00

brent.edwards merged commit a8d91b94a7 into master 2026-04-01 01:46:37 +00:00

brent.edwards deleted branch feature/m6-guard-enforcement 2026-04-01 01:46:38 +00:00

brent.edwards referenced this pull request from a commit 2026-04-01 01:46:39 +00:00

feat(autonomy): guard enforcement works (denylist, budget caps, tool call limits) (#1204)

freemo referenced this pull request 2026-04-02 16:51:46 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types #1226

freemo referenced this pull request from a commit 2026-04-02 16:56:53 +00:00

docs(spec): align spec with v3.7.0 implementation discoveries

freemo referenced this pull request 2026-04-02 16:58:16 +00:00

[Automated] Product Build Session State #1314

freemo referenced this pull request from a commit 2026-04-03 01:51:57 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

freemo referenced this pull request from a commit 2026-04-03 02:06:01 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

HAL9000 referenced this pull request from a commit 2026-04-24 14:22:25 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

HAL9000 referenced this pull request from a commit 2026-04-24 22:01:20 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

HAL9000 referenced this pull request from a commit 2026-04-25 01:55:40 +00:00

fix(tests): update resource_dag.robot SQLite pool and cycle detection types

Sign in to join this conversation.

Reviewers

No reviewers

CoreRasurae

freemo

Labels

Clear labels   

auto/needs-reevaluation

Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.

  

controller-managed

Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.

  

auto/blocked-by-deps

PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.

  

auto/ci-timeout

Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.

  

auto/claimed-implementer

Currently being processed by an implementer worker.

  

auto/claimed-merge

Currently being processed by the merge driver.

  

auto/claimed-reviewer

Currently being processed by a reviewer worker.

  

auto/driver-down

Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.

  

auto/invariant-violation

Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.

  

auto/last-attempt-tier-0

In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.

  

auto/last-attempt-tier-1

In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.

  

auto/last-attempt-tier-2

In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.

  

auto/last-attempt-tier-min

In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.

  

Automation Tracking

Tracking issues used by the AI Automation system for agents to communicate and report.

  

auto/needs-conflict-resolution

Rebase conflict needs LLM conflict-resolver.

  

auto/needs-implementer

Failing CI needs implementer attention.

  

auto/postmortem

Documenting a driver incident or rollback.

  

auto/ready-to-merge

Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.

  

auto/restart-throttled

Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.

  

auto/revert

Revert PR backing out an invariant violation. Fast-tracked through the merge driver.

  

auto/sentinel

Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.

  

auto/stale-inactivity

No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.

  

auto/unstable

Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.

  

Blocked

A ticket in a blocked state and unable to complete until some other task is completed first.

  

Bounty

$100

A bounty of $100 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$1000

A bounty of $1000 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$10000

A bounty of $10000 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$20

A bounty of $20 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$2000

A bounty of $2000 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$250

A bounty of $250 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$50

A bounty of $50 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$500

A bounty of $500 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$5000

A bounty of $5000 for any open-source contributor who provides a MR that solves this issue

  

Bounty

$750

A bounty of $750 for any open-source contributor who provides a MR that solves this issue

  

MoSCoW

Could have

Could have feature in order to satisfy the epic/legendary.

  

MoSCoW

Must have

Must have feature in order to satisfy the epic/legendary.

  

MoSCoW

Should have

Should have feature in order to satisfy the epic/legendary.

  

Needs Feedback

There are questions in the ticket that can not be completed until the project owner provides clarity.

  

Points

1

1 man-hours worth of work for an expert with no learning curve.

  

Points

13

13 man-hours worth of work for an expert with no learning curve.

  

Points

2

2 man-hours worth of work for an expert with no learning curve.

  

Points

21

21 man-hours worth of work for an expert with no learning curve.

  

Points

3

3 man-hours worth of work for an expert with no learning curve.

  

Points

34

34 man-hours worth of work for an expert with no learning curve.

  

Points

5

5 man-hours worth of work for an expert with no learning curve.

  

Points

55

55 man-hours worth of work for an expert with no learning curve.

  

Points

8

8 man-hours worth of work for an expert with no learning curve.

  

Points

88

88 man-hours worth of work for an expert with no learning curve.

  

Priority

Backlog

This ticket has backlogged priority and is not to be worked on yet

  

Priority

CI Blocker

Critical priority issue that blocks CI/CD pipeline and prevents PR merges

  

Priority

Critical

The priority is critical

  

Priority

High

The priority is high

  

Priority

Low

The priority is low

  

Priority

Medium

The priority is medium

  

Signed-off: Owner

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  

Signed-off: Scrum Master

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  

Signed-off: Tech Lead

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  

Spike

A ticket for learning a tool or technology that is needed to be able to do future planning and design.

  

State

Completed

The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.

  

State

Duplicate

A ticket that represents the same content as an existing ticket.

  

State

In Progress

A ticket that is actively being developed.

  

State

In Review

A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.

  

State

Paused

This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.

  

State

Unverified

All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.

  

State

Verified

The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.

  

State

Wont Do

This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.

  

Type

Automation

Any edits or discussion about the AI automated coding system.

  

Type

Bug

Something that doesnt work as intended.

  

Type

Discussion

Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.

  

Type

Documentation

An error or improvement needed in the documentation.

  

Type

Epic

Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.

  

Type

Feature

Some new functionality not present.

  

Type

Legendary

A type of Epic which will contain other Epics.

  

Type

Refactor

A code change that restructures existing code without changing its external behavior.

  

Type

Support

Someone needs help using the project.

  

Type

Task

A generic task that doesnt fit into the other type categories.

  

Type

Testing

Work exclusively focusing on fixing or expanding testing.

No labels

auto/needs-reevaluation

controller-managed

auto/blocked-by-deps

auto/ci-timeout

auto/claimed-implementer

auto/claimed-merge

auto/claimed-reviewer

auto/driver-down

auto/invariant-violation

auto/last-attempt-tier-0

auto/last-attempt-tier-1

auto/last-attempt-tier-2

auto/last-attempt-tier-min

Automation Tracking

auto/needs-conflict-resolution

auto/needs-implementer

auto/postmortem

auto/ready-to-merge

auto/restart-throttled

auto/revert

auto/sentinel

auto/stale-inactivity

auto/unstable

Blocked

Bounty

$100

Bounty

$1000

Bounty

$10000

Bounty

$20

Bounty

$2000

Bounty

$250

Bounty

$50

Bounty

$500

Bounty

$5000

Bounty

$750

MoSCoW

Could have

MoSCoW

Must have

MoSCoW

Should have

Needs Feedback

Points

1

Points

13

Points

2

Points

21

Points

3

Points

34

Points

5

Points

55

Points

8

Points

88

Priority

Backlog

Priority

CI Blocker

Priority

Critical

Priority

High

Priority

Low

Priority

Medium

Signed-off: Owner

Signed-off: Scrum Master

Signed-off: Tech Lead

Spike

State

Completed

State

Duplicate

State

In Progress

State

In Review

State

Paused

State

Unverified

State

Verified

State

Wont Do

Type

Automation

Type

Bug

Type

Discussion

Type

Documentation

Type

Epic

Type

Feature

Type

Legendary

Type

Refactor

Type

Support

Type

Task

Type

Testing

Milestone

Clear milestone

No items

No milestone

v3.5.0

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

2 participants

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

cleveragents/cleveragents-core!1204

No description provided.