Implement SubplanExecutionService and SubplanMergeService to enable
parent plans to decompose work into coordinated child subplans with
configurable execution modes (sequential, parallel, dependency-ordered)
and merge strategies (git_three_way, sequential_apply, fail_on_conflict,
last_wins).
- SubplanExecutionService: schedules subplan execution with retry
support via SubplanFailureHandler, max_parallel limits, fail_fast
semantics, and topological DAG ordering for dependency mode
- SubplanMergeService: wraps sandbox merge infrastructure to combine
subplan sandbox outputs using the configured merge strategy
- BDD tests: 21 scenarios covering all execution modes, merge
strategies, validation, and integration flows
- Robot tests: 11 integration test cases with helper module
- ASV benchmarks: performance benchmarks for execution and merge
- Documentation: reference guide in docs/reference/subplans.md
ISSUES CLOSED: #184
Implement the complete configuration system with multi-level resolution
chain, typed key registry, and CLI integration per specification.
ConfigService changes:
- Expand _build_catalog() to register all 102 spec-aligned config keys
across 8 groups: core (14), server (4), actor (5), plan (8),
sandbox (5), index (12), context (43), provider (11)
- Each key carries exact dotted-dash name, Python type, default value,
explicit env var name per spec, project-scopability flag, and
description
- Fix _env_name() to convert dots and dashes to underscores
- Provider keys use standard env var names (e.g., OPENAI_API_KEY)
CLI commands rewiring:
- Rewrite config set/get/list to use ConfigService instead of Settings
- Add --verbose flag to config get showing full 5-level resolution chain
- Add --project flag to config set/get/list for project-scoped overrides
- Support both glob and regex patterns in config list
- Validate keys against ConfigService registry with actionable errors
- Retain backward-compatible helper functions delegating to ConfigService
Documentation:
- Add docs/reference/config_resolution.md covering resolution chain,
all 102 config keys, CLI commands, TOML format, and provider credentials
Testing:
- Update all 4 Behave feature files and step definitions to use new
spec-aligned key names, env vars, and defaults (119 scenarios passing)
- Add robot/config_resolution.robot with 10 integration test cases
- Add benchmarks/config_resolution_bench.py with 8 time + 2 memory suites
ISSUES CLOSED: #258
Added targeted Behave BDD feature files and step definitions to improve
unit test coverage for:
- decision_service.py: Full coverage of all 7 service methods (18 scenarios)
- plan_apply_service.py: Branch coverage for handle_merge_failure (2 scenarios)
- plan_executor.py: Edge cases for rollback, checkpoint, and parse_steps (15 scenarios)
- cli/commands/plan.py: Uncovered region lines 1950-2273 (23 scenarios)
- repositories.py: Remaining missed branches and lines (14 scenarios)
- sandbox/checkpoint.py: Full coverage of CheckpointManager (26 scenarios)
- langgraph/bridge.py: Remaining uncovered lines and branches (10 scenarios)
- cli/commands/config.py: Safety net to maintain 100% coverage (42 scenarios)
Total: 150 new scenarios, 596 steps, all passing.
Also fixed a step definition collision in plan_lifecycle_coverage by renaming
"the delete result should be false" to "the plan delete result should be false".
ISSUES CLOSED: #475
Add runtime autonomy constraints (max steps, tool budget, required
confirmations) and a structured audit trail for plan execution.
New domain models:
- AutonomyGuardrails: enforces step limits, tool budgets, and
confirmation gates with validators and check methods
- GuardrailAuditEntry: records each enforcement event with timestamp,
event type, guard name, result, reason, and context
- GuardrailAuditTrail: ordered collection of audit entries persisted
to plan metadata
New service:
- AutonomyGuardrailService: high-level service for configuring
guardrails per plan, checking constraints, recording audit entries,
and serializing/restoring state via plan metadata
Tests:
- Behave: 69 scenarios covering model validation, step/budget/
confirmation checks, audit trail recording, and service operations
- Robot: 8 test cases for autonomy guardrail CLI flag smoke testing
- ASV: 6 benchmark suites measuring enforcement overhead
Documentation:
- Updated docs/reference/automation_profiles.md with guardrail fields,
enforcement behavior, audit trail schema, and event type reference
ISSUES CLOSED: #204
Implemented namespace/project/plan/skill permission model with role
bindings (owner/admin/editor/viewer) and default deny policy. Added
enforcement hooks at CLI/service boundaries that are server-only; local
mode returns permissive defaults. Includes role enums, permission check
service, role matrix documentation.
Includes Behave BDD scenarios, Robot integration tests, ASV benchmarks,
and reference documentation.
ISSUES CLOSED: #344
Patch time.monotonic alongside time.sleep in the retry timeout step
so stop_after_delay cannot elapse due to wall-clock overhead on
busy CI runners. The fake monotonic clock advances by 1µs per call,
keeping elapsed time well under the 0.01s timeout while preserving
retry semantics.
Closes#200
Revert module-level import refactor and instead patch at
cleveragents.application.container.get_container — matching the
established pattern used by all existing context CLI tests.
Lazy imports inside each function re-read from the source module,
so patching there intercepts correctly.
Closes#200
Introduce a lightweight checkpoint/rollback system for sandbox state
during plan execute and apply flows. CheckpointManager snapshots
the sandbox working directory before each phase and can restore it
on failure, giving the execution engine a reliable undo mechanism.
Key changes:
- SandboxCheckpoint model, Checkpointable protocol, and
CheckpointManager in infrastructure/sandbox/checkpoint.py
- PlanExecutor gains optional checkpoint_manager with pre/post
execute hooks and automatic rollback on failure
- PlanApplyService gains optional checkpoint_manager with pre-apply
checkpoint and rollback helper
- 12 BDD scenarios (features/sandbox_checkpoints.feature)
- 5 Robot Framework smoke tests (robot/sandbox_checkpoint_smoke.robot)
- ASV benchmarks for creation, rollback, and listing operations
- Reference documentation in docs/reference/sandbox.md
ISSUES CLOSED: #183
- Add CHANGELOG.md entry for M6 autonomy acceptance suite
- Split m6_autonomy_acceptance_steps.py (774 lines) into
m6_facade_steps.py (398 lines) and m6_guardrails_steps.py (399 lines)
to comply with the project's 500-line guideline
Closes#211
Fix 4 errored scenarios: patch get_container instead of the lazily-
imported ContextService (which is not a module-level attribute of
cleveragents.cli.commands.context).
Fix project context show (line 112): mock _get_namespaced_project_repo
to return a repo (not a tuple), mock get_container for session_factory,
and mock _read_policy to bypass DB access.
Fix context exclusion pattern (line 152): replace fnmatch.fnmatch with
PurePosixPath.match for proper ** glob handling and use a path with a
leading directory segment.
Also fix context list empty assertion to match actual CLI output
('No files in context' rather than 'No context'), and patch
Path.exists for the add command so the mock service is reached.
Add Alembic migration m4_002_skill_flattened_tools to extend the skills
table with five new columns: flattened_tools_json, includes_json,
capability_summary_json, yaml_text, and flattening_hash (SHA-256). A
defence-in-depth uniqueness constraint (uq_skills_name) is also added.
Update SkillModel with the new column definitions and extend
SkillRepository with update_flattened_tools(), get_flattened_tools(),
needs_refresh(), recompute_flattening_hash(), and
invalidate_cached_summaries() methods. The existing update() method
now nulls all cached fields on mutation (hash-based invalidation).
All new repository methods follow the session-factory pattern with
@database_retry and flush-but-don-t-commit semantics. Structured
logging via structlog records cache updates and invalidations.
Database schema docs updated with the new skills table columns and a
persistence-field-to-domain-model mapping table.
Tests:
- 6 Behave scenarios covering create, invalidation, hash staleness,
refresh recomputation, uniqueness constraint, and namespace filtering
- 2 Robot Framework smoke tests (round-trip and invalidation)
- 3 ASV benchmarks (persist, refresh check, namespace list)
ISSUES CLOSED: #166
Remove FakeListLLM as a silent fallback in agent graph constructors
(plan_generation.py, context_analysis.py, auto_debug.py). All three now
raise ValueError when llm=None, making missing-provider errors explicit.
Add Settings.mock_providers flag and validate_provider_availability()
method. Update container.get_ai_provider() to check Settings.mock_providers
first, with env-var fallback for backward compatibility.
Add resolve_provider_by_name() helper to the provider registry and export
it from cleveragents.providers. Add structlog trace logging to
ProviderRegistry.get_default_provider_type() to record selection reasoning.
Update all existing behave step files, robot tests, and benchmarks that
relied on the implicit FakeListLLM default to pass an explicit LLM
instance instead.
Add new BDD tests (features/provider_fixes.feature with 17 scenarios),
Robot Framework integration tests (robot/provider_detection_smoke.robot),
and ASV benchmarks (benchmarks/provider_selection_bench.py).
ISSUES CLOSED: #323
Create DecisionService application-layer service that wraps
DecisionRepository with structured logging and UnitOfWork transaction
management. Wire DecisionService and PlanLifecycleService into the DI
container as Factory providers.
Inject DecisionService into PlanLifecycleService so that phase
transitions automatically record decisions: start_strategize records a
strategy_choice decision and start_execute records an
implementation_choice decision. Decision recording is optional and
never blocks lifecycle transitions.
Add Behave feature (5 scenarios), Robot Framework smoke tests (2 test
cases), ASV benchmarks (3 benchmark classes), and DI reference
documentation.
ISSUES CLOSED: #173
Tighten ToolRuntime._enforce_capabilities() to block ANY tool with
writes=True when plan_read_only is set, removing the not-cap.read_only
loophole that allowed certain write tools through. Tool name is now
always included in the ToolAccessDeniedError message.
Add read_only flag to ChangeSetCapture with ReadOnlyViolationError
raised when write-capable tools are wrapped on a read-only plan.
Add CLI fail-fast guards on plan execute and plan apply commands that
abort before calling the service layer if plan.read_only is True.
SkillContext.enforce_write_guard() already included tool name
correctly and required no changes.
Includes 18 Behave scenarios (90 steps), Robot integration tests,
ASV benchmarks, and docs/reference/read_only_actions.md.
ISSUES CLOSED: #322
P0: reject register() after close_all() with RuntimeError.
P1: catch CancelledError in close_all(), use WeakKeyDictionary for
cancellation_reasons to prevent memory leak, guard StateManager
update_state/reset/load_checkpoint/time_travel after close().
P2: contextlib.suppress in __del__ for partial construction, re-cancel
pending tasks in cleanup_tasks_async, handle late tasks added during
await window, guard AcpEventQueue.publish() after close with _is_closed
flag and is_closed property, fix ASV TimeRegisterBatch crash.
Tests: 5 new Behave scenarios (T1-T4 + is_closed), log handler and
event loop cleanup in after_scenario (T5-T6).
Docs: async_safety.md updated for register-after-close and state
mutation guards.
ISSUES CLOSED: #321
Add AsyncResourceTracker (core/async_cleanup.py) providing a central
registry for async resources with timeout-bounded close_all(), async
context manager support, and a __del__ finalizer that logs leaked
resources by name.
Enhance LangGraphBridge with cleanup_tasks_async() that awaits
in-flight tasks with a deadline instead of fire-and-forget cancel().
Add cancellation_reasons dict to trace why tasks were cancelled.
Add StateManager.close() to properly release checkpoint file handles
and complete the RxPY BehaviorSubject. Add AcpEventQueue.close() to
dispose all subscriptions.
Includes 14 Behave scenarios (67 steps), Robot integration tests,
ASV benchmarks, and docs/reference/async_safety.md.
ISSUES CLOSED: #321
Add decision persistence layer with DecisionRepository, DecisionModel,
and Alembic migration. Includes tree queries (BFS traversal via deque,
path-to-root), superseded lookup, ordered decision path retrieval,
concrete Decision type annotations (via TYPE_CHECKING), and comprehensive
test coverage (Behave BDD, Robot Framework, ASV benchmarks). Updated
database_schema.md, CHANGELOG.md, and CONTRIBUTORS.md.
ISSUES CLOSED: #171
- Patch CorrectionService at its module path, not the local-import site
- Use request_correction/execute_correction/analyze_impact (real API)
- Replace invalid 27-char subplan_id values with valid 26-char ULIDs
- Add required --guidance flag to dry-run CLI invocation
- Fix feature file assertions to match actual CLI output
Resolves CI failures in unit_tests (job 4) and coverage (job 6) for
run 645 on PR #441.
Luis Mendes
freemo
brent.edwards
aditya
khyari hamza