feat(security): add safety profile enforcement #518

Merged

CoreRasurae merged 1 commit from feature/m7-post-safety into master 2026-03-03 22:29:29 +00:00

Conversation 2 Commits 1 Files changed 13 +2126 -60

CoreRasurae commented 2026-03-02 23:33:08 +00:00

Member

Copy link

Summary

Implements safety profile resolution and enforcement in the tool execution pipeline, replacing the NotImplementedError stub with working precedence logic and runtime safety checks.

Closes #345

Changes

Core Implementation

• resolve_safety_profile() — plan > action > project > global precedence; returns DEFAULT_SAFETY_PROFILE with GLOBAL provenance when all levels are None
• ToolExecutionContext.safety_profile — optional field carrying the resolved profile
• ToolRuntime._enforce_capabilities() — extended with:
  • Unsafe tool gating (allow_unsafe_tools vs ToolCapability.unsafe)
  • Skill category allow-list (allowed_skill_categories vs tool_skill_category metadata)
  • Checkpoint requirement OR-combined from context flag and safety profile
• ToolSafetyViolationError — new error class in the tool error hierarchy

Files Modified

File	Change
src/cleveragents/domain/models/core/safety_profile.py	Replace NotImplementedError stub with resolution logic
src/cleveragents/tool/context.py	Add safety_profile field to ToolExecutionContext
src/cleveragents/tool/lifecycle.py	Add ToolSafetyViolationError, extend _enforce_capabilities()
src/cleveragents/tool/__init__.py	Export ToolSafetyViolationError

Files Added

File	Purpose
features/safety_profile_enforcement.feature	24 BDD scenarios for enforcement
features/steps/safety_profile_enforcement_steps.py	Step definitions
robot/safety_profile_enforcement.robot	9 Robot integration tests
robot/helper_safety_profile_enforcement.py	Robot helper
benchmarks/safety_profile_bench.py	4 ASV benchmark suites
docs/reference/safety_profiles.md	Reference documentation

Test Updates

• features/safety_profile.feature — replaced NotImplementedError stub test with 5 resolution precedence scenarios (30 total)
• features/steps/safety_profile_steps.py — added resolution step definitions

Verification

Check	Result
nox -e typecheck	0 errors, 0 warnings
nox -e unit_tests	7735 scenarios, 0 failures
nox -e coverage_report	97% overall
nox -e integration_tests	9/9 passed
nox -e benchmark	All suites complete

Backward Compatibility

When no SafetyProfile is set on ToolExecutionContext (the default), the new enforcement checks are skipped entirely. All existing tool execution paths are unaffected.

## Summary Implements safety profile resolution and enforcement in the tool execution pipeline, replacing the `NotImplementedError` stub with working precedence logic and runtime safety checks. Closes #345 ## Changes ### Core Implementation - **`resolve_safety_profile()`** — plan > action > project > global precedence; returns `DEFAULT_SAFETY_PROFILE` with GLOBAL provenance when all levels are None - **`ToolExecutionContext.safety_profile`** — optional field carrying the resolved profile - **`ToolRuntime._enforce_capabilities()`** — extended with: - Unsafe tool gating (`allow_unsafe_tools` vs `ToolCapability.unsafe`) - Skill category allow-list (`allowed_skill_categories` vs `tool_skill_category` metadata) - Checkpoint requirement OR-combined from context flag and safety profile - **`ToolSafetyViolationError`** — new error class in the tool error hierarchy ### Files Modified | File | Change | |------|--------| | `src/cleveragents/domain/models/core/safety_profile.py` | Replace `NotImplementedError` stub with resolution logic | | `src/cleveragents/tool/context.py` | Add `safety_profile` field to `ToolExecutionContext` | | `src/cleveragents/tool/lifecycle.py` | Add `ToolSafetyViolationError`, extend `_enforce_capabilities()` | | `src/cleveragents/tool/__init__.py` | Export `ToolSafetyViolationError` | ### Files Added | File | Purpose | |------|---------| | `features/safety_profile_enforcement.feature` | 24 BDD scenarios for enforcement | | `features/steps/safety_profile_enforcement_steps.py` | Step definitions | | `robot/safety_profile_enforcement.robot` | 9 Robot integration tests | | `robot/helper_safety_profile_enforcement.py` | Robot helper | | `benchmarks/safety_profile_bench.py` | 4 ASV benchmark suites | | `docs/reference/safety_profiles.md` | Reference documentation | ### Test Updates - `features/safety_profile.feature` — replaced `NotImplementedError` stub test with 5 resolution precedence scenarios (30 total) - `features/steps/safety_profile_steps.py` — added resolution step definitions ## Verification | Check | Result | |-------|--------| | `nox -e typecheck` | 0 errors, 0 warnings | | `nox -e unit_tests` | 7735 scenarios, 0 failures | | `nox -e coverage_report` | 97% overall | | `nox -e integration_tests` | 9/9 passed | | `nox -e benchmark` | All suites complete | ## Backward Compatibility When no `SafetyProfile` is set on `ToolExecutionContext` (the default), the new enforcement checks are skipped entirely. All existing tool execution paths are unaffected.

CoreRasurae referenced this pull request 2026-03-02 23:33:23 +00:00

feat(security): add safety profile enforcement #345

CoreRasurae force-pushed feature/m7-post-safety from e09201af29 to 5e247d05e2 2026-03-03 17:12:44 +00:00 Compare

brent.edwards approved these changes 2026-03-03 19:18:24 +00:00

Dismissed

brent.edwards left a comment

Copy link

Review — PR #518 feat(security): add safety profile enforcement

Verdict: APPROVED with comments

The implementation is well-structured. resolve_safety_profile() implements clean plan > action > project > global precedence with keyword-only args and tuple return. The _enforce_capabilities() extension adds 8 ordered checks (read-only, checkpoint, unsafe gating, skill category, sandbox, human approval, cost limits, retry limits) with a clear error hierarchy (ToolSafetyViolationError, ToolSandboxRequiredError, ToolHumanApprovalRequiredError, ToolCostLimitExceededError, ToolRetryLimitExceededError — all inheriting from ToolRuntimeError). The SafetyProfile model is frozen/immutable with field and cross-field validators. New types are properly re-exported in tool/__init__.py. The ToolExecutionContext.safety_profile field is optional (None = no enforcement), preserving backward compatibility. BDD scenarios are comprehensive with stub tool instances.

No P0 or P1 findings.

---

P2:should-fix

1. Missing PR label — Per CONTRIBUTING.md, every PR must carry exactly one Type/ label. This PR has no labels. The linked issue #345 carries Type/Feature.

2. Missing PR milestone — Per CONTRIBUTING.md, the PR milestone must match the linked issue. This PR has no milestone set. Issue #345 is assigned to milestone v3.6.0.

3. Commit footer uses Refs: #345 instead of a closing keyword — Per CONTRIBUTING.md, every commit must reference the issue with a closing keyword (e.g. ISSUES CLOSED: #345). The PR body correctly says Closes #345, but the commit footer only has Refs: #345, which will not auto-close the issue on merge.

4. Scenario count mismatch in PR body — The PR description claims "11 BDD scenarios" in safety_profile_enforcement.feature, but the file actually contains 24 scenarios (verified by counting Scenario: / Scenario Outline: entries plus their Examples expansions). Please update the PR body to reflect the correct count.

P3:nit

5. Nox flag typo in verification table — The PR body's verification table uses nox -e (not a valid nox flag) instead of nox -s in all entries.

---

P2 items should be addressed in a follow-up within 3 business days.

## Review — PR #518 `feat(security): add safety profile enforcement` **Verdict: APPROVED with comments** The implementation is well-structured. `resolve_safety_profile()` implements clean `plan > action > project > global` precedence with keyword-only args and tuple return. The `_enforce_capabilities()` extension adds 8 ordered checks (read-only, checkpoint, unsafe gating, skill category, sandbox, human approval, cost limits, retry limits) with a clear error hierarchy (`ToolSafetyViolationError`, `ToolSandboxRequiredError`, `ToolHumanApprovalRequiredError`, `ToolCostLimitExceededError`, `ToolRetryLimitExceededError` — all inheriting from `ToolRuntimeError`). The `SafetyProfile` model is frozen/immutable with field and cross-field validators. New types are properly re-exported in `tool/__init__.py`. The `ToolExecutionContext.safety_profile` field is optional (`None` = no enforcement), preserving backward compatibility. BDD scenarios are comprehensive with stub tool instances. No P0 or P1 findings. --- ### P2:should-fix 1. **Missing PR label** — Per `CONTRIBUTING.md`, every PR must carry exactly one `Type/` label. This PR has no labels. The linked issue #345 carries `Type/Feature`. 2. **Missing PR milestone** — Per `CONTRIBUTING.md`, the PR milestone must match the linked issue. This PR has no milestone set. Issue #345 is assigned to milestone `v3.6.0`. 3. **Commit footer uses `Refs: #345` instead of a closing keyword** — Per `CONTRIBUTING.md`, every commit must reference the issue with a closing keyword (e.g. `ISSUES CLOSED: #345`). The PR body correctly says `Closes #345`, but the commit footer only has `Refs: #345`, which will not auto-close the issue on merge. 4. **Scenario count mismatch in PR body** — The PR description claims "11 BDD scenarios" in `safety_profile_enforcement.feature`, but the file actually contains **24 scenarios** (verified by counting `Scenario:` / `Scenario Outline:` entries plus their `Examples` expansions). Please update the PR body to reflect the correct count. ### P3:nit 5. **Nox flag typo in verification table** — The PR body's verification table uses `nox -e` (not a valid nox flag) instead of `nox -s` in all entries. --- P2 items should be addressed in a follow-up within 3 business days.

CoreRasurae added this to the v3.6.0 milestone 2026-03-03 20:49:28 +00:00

CoreRasurae added the

Type

Feature

label 2026-03-03 20:49:36 +00:00

CoreRasurae force-pushed feature/m7-post-safety from 5e247d05e2 to 57a99f2521 2026-03-03 20:54:15 +00:00 Compare

CoreRasurae force-pushed feature/m7-post-safety from 57a99f2521 to 809fcd223b 2026-03-03 22:04:11 +00:00 Compare

brent.edwards approved these changes 2026-03-03 22:11:05 +00:00

brent.edwards left a comment

Copy link

Approved. No notes.

Approved. No notes.

CoreRasurae force-pushed feature/m7-post-safety from 809fcd223b to b4b96d213c 2026-03-03 22:21:27 +00:00 Compare

CoreRasurae scheduled this pull request to auto merge when all checks succeed 2026-03-03 22:22:18 +00:00

CoreRasurae merged commit b4b96d213c into master 2026-03-03 22:29:29 +00:00

CoreRasurae deleted branch feature/m7-post-safety 2026-03-03 22:29:29 +00:00

freemo added the

State

Completed

label 2026-03-04 00:41:39 +00:00

HAL9000 referenced this pull request 2026-04-18 17:13:50 +00:00

[AUTO-UAT-POOL] Status: v3.6.0 & v3.7.0 Feature Validation (Cycle 1) #10557

HAL9000 referenced this pull request 2026-04-18 18:47:52 +00:00

[AUTO-UAT-POOL] Status: v3.6.0 & v3.7.0 Feature Validation (Cycle 1) #10557

Sign in to join this conversation.

Reviewers

No reviewers

brent.edwards

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

v3.6.0

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!518

No description provided.