2746 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
khyari hamza	493e5cf8a1	fix(security): wire read_only through ExecuteStubActor and replace stubs with real tests ... - Add read_only kwarg to ExecuteStubActor.execute(), propagated to ChangeSetCapture; PlanExecutor._run_execute_with_stub passes plan.read_only through the execution path (P1 #2 fix) - Replace CLI fail-fast and Action-Skill stub scenarios with real ExecuteStubActor spy test and SkillContext.enforce_write_guard integration tests (P2 #1 fix) - Update docs: remove unimplemented Layer 5 (Action-Skill), add ExecuteStubActor wiring description, fix test command (P2 #2 fix) ISSUES CLOSED: #322	2026-02-26 20:33:20 +00:00
khyari hamza	2b09568cfa	feat(security): enforce read-only actions ... 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	2026-02-26 20:33:20 +00:00
freemo	4ed057fa58	Docs: Fixed refs in docs	2026-02-26 14:40:17 -05:00
freemo	c88b432beb	Docs: Daily timeline update	2026-02-26 14:32:59 -05:00
brent.edwards	1ec2200e34	test(e2e): verify M6 success criteria — Firefox-scale autonomous porting ... Robot Framework E2E test suite exercising the complete M6 success criteria verification sequence: - Porting action creation from YAML config via CLI - Plan use + execute via CLI with mocked lifecycle service - Hierarchical decomposition: 4+ levels (root + L1-L4 = 21+ plans) - Decision correction recomputes only affected subtree (CorrectionImpact) - Parallel execution scales to 15 concurrent subplans (10+ required) - Realistic porting task: full ACTION → STRATEGIZE → EXECUTE → APPLY lifecycle with 10 subplans completing autonomously - Plan apply transitions to APPLIED terminal state - SubplanFailureHandler retry/stop-others logic verification - SubplanConfig supports all execution modes and merge strategies - Decision tree structure: PROMPT_DEFINITION root with SUBPLAN_PARALLEL_SPAWN children and superseded_by flow Ten subcommands in the Python helper, each printing a sentinel string on success. All subcommands verified passing locally. Closes #407	2026-02-26 19:27:53 +00:00
brent.edwards	93f2d396a1	Merge pull request 'test: consolidated Brent QA batch — issues #179, #180, #404, #405, #187' (#442) from develop-brent-5 into master ... Reviewed-on: #442 Reviewed-by: Jeffrey Phillips Freeman <jeffrey.freeman@cleverthis.com>	2026-02-26 16:54:21 +00:00
brent.edwards	fd1612c38f	test(e2e): verify M5 success criteria — ACMS and large-project context ... Robot Framework E2E test suite exercising the complete M5 success criteria verification sequence: - Large project creation with 10,000+ simulated files - Resource registration and linking to a project - Indexing verification (resource linked, project shows correctly) - Context tier management (hot/warm/cold) via ContextConfig - ACMS v1 context policy set/show with persistence round-trip - Phase view inheritance (default → strategize → execute → apply) - Scoped context output per ACMS phase with narrowing size limits - Policy clear and inheritance fallback - ContextView validation rules (size limits, VALID_PHASES) Nine subcommands in the Python helper, each printing a sentinel string on success. All subcommands verified passing locally. Closes #406	2026-02-26 16:32:01 +00:00
brent.edwards	ffdd2f2b19	Merge branch 'master' into develop-brent-5	2026-02-26 16:14:07 +00:00
brent.edwards	32b81793a2	refactor(test): rename decision persistence files to avoid conflict with master ... Rename our serialization-focused decision persistence suites to *_serialization to avoid add/add conflicts with the repository-based decision persistence suites that landed on master independently: - decision_persistence.feature -> decision_persistence_serialization.feature - decision_persistence_steps.py -> decision_persistence_serialization_steps.py - decision_persistence_bench.py -> decision_persistence_serialization_bench.py - decision_persistence.robot -> decision_persistence_serialization.robot - helper_decision_persistence.py -> helper_decision_persistence_serialization.py Updated robot helper path, step docstring, and testing.md references.	2026-02-26 16:13:44 +00:00
hamza.khyari	074f884f14	Merge pull request 'fix(security): close async resources and leaks' (#435) from feature/m4-security-async-cleanup into master ... Reviewed-on: #435	2026-02-26 15:19:16 +00:00
aditya	76db58414a	Merge branch 'master' into feature/m3-agent-skills-loader	2026-02-26 14:51:41 +00:00
aditya	f8bc02869a	Merge branch 'master' into feature/m3-agent-skills-loader	2026-02-26 14:43:52 +00:00
aditya	d0337a0881	fix(skill): eliminate Any from agent_skills_loader type signatures ... Replace dict[str, Any] with a private _YamlMapping type alias (dict[str, object]) in AgentSkillSpec Pydantic fields and all internal helper function signatures. Add isinstance guard for allowed-tools list iteration to satisfy pyright. Refs: #160	2026-02-26 14:40:44 +00:00
khyari hamza	c406781b86	fix(security): address PR #435 review feedback ... 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	2026-02-26 14:30:43 +00:00
khyari hamza	5d5d3fde2c	fix(security): close async resources and leaks ... 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	2026-02-26 14:30:43 +00:00
aditya	7ad9f2bf4a	chore: update CHANGELOG for feat(skill): add agent skills loader ... ISSUE CLOSED #160	2026-02-26 14:28:09 +00:00
hamza.khyari	db58a3bb62	Merge pull request 'feat(decision): add decision persistence layer' (#131) from feature/m4-decision-persistence into master ... Reviewed-on: #131 Reviewed-by: Brent Edwards <brent.edwards@cleverthis.com>	2026-02-26 14:25:27 +00:00
khyari hamza	7f2b1c61fc	fix(decision): rebase migration onto merged changeset head ... After rebasing onto master, m4_001_decision_tables and d0_002_merge_changeset_and_locks were both leaf heads. Update down_revision so the decision migration chains after the merge migration, restoring a single Alembic head. ISSUES CLOSED: #171	2026-02-26 13:40:07 +00:00
khyari hamza	27bef69ddd	feat(decision): add decision persistence ... 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	2026-02-26 13:40:07 +00:00
aditya	595cfd172f	Merge branch 'master' into feature/m3-mcp-adapter	2026-02-26 13:30:29 +00:00
aditya	e05afdcd27	Merge pull request 'feature/m2-actor-yaml' (#432) from feature/m2-actor-yaml into master ... Reviewed-on: #432 Reviewed-by: Luis Mendes <luis.mendes@cleverthis.com>	2026-02-26 13:19:00 +00:00
aditya	b25a886df8	feat(skill): add MCP refresh hooks ... Implement SkillRegistry.refresh(name) and refresh_all() to recompute flattened tool sets on demand. Wire MCPToolAdapter.dispatch_notification() to MCPRefreshHook, which debounces rapid notifications/tools/list_changed bursts into a single refresh_all() call (default 0.5 s window). Add safeguard that skips tool-ref validation when no ToolRegistry is configured, emitting a single WARNING with recovery steps. Introduce immutable SkillRefreshResult (refreshed/failed/skipped counts) with to_summary() and merge() for CLI and log output. New files: - src/cleveragents/skills/refresh.py (SkillRefreshResult) - src/cleveragents/mcp/refresh_hook.py (MCPRefreshHook) - features/skill_refresh.feature (19 Behave scenarios) - features/steps/skill_refresh_steps.py - robot/skill_refresh.robot (10 Robot tests) - robot/helper_skill_refresh.py - benchmarks/skill_refresh_bench.py (ASV benchmarks) - docs/reference/skill_refresh.md Modified: - src/cleveragents/skills/registry.py (refresh, refresh_all) - src/cleveragents/mcp/adapter.py (notification listener API) - src/cleveragents/skills/__init__.py (export SkillRefreshResult) - src/cleveragents/mcp/__init__.py (export MCPRefreshHook) - CHANGELOG.md ISSUES CLOSED #168	2026-02-26 12:29:49 +00:00
aditya	c40ea014dc	feat(cli): add skill tools and refresh commands ... Implemented agents skill refresh command to recompute tool flattening and sync MCP-backed skills. Enhanced skill list/show/tools outputs with capability summary fields. - agents skill refresh <name>|--all to recompute flattening - Enhanced skill list/show/tools with capability summary and tool counts - Added --format json/yaml schemas for refresh output - CLI errors for nonexistent skills and MCP sync failures - Behave tests (skill_cli.feature), Robot tests (skill_cli.robot) - ASV benchmarks (skill_cli_bench.py) for CLI overhead baseline - Updated docs/reference/skill_cli.md with refresh command examples - Documented refresh side effects and caching behavior ISSUES CLOSED: #167	2026-02-26 10:57:07 +00:00
aditya	cb82fc51df	feat(skill): add agent skills loader ... Implemented AgentSkillSpec loader that parses SKILL.md frontmatter and progressive disclosure sections (discover/activate/deactivate) into structured SkillStep objects with stable 1-based ordering. Mapped Agent Skills to AgentSkillToolDescriptor with namespaced naming (namespace/short_name), source="agent_skill", read-only defaults, and AgentSkillResourceSlot bindings for scripts/, references/, and assets/ directories. All resource slots are unconditionally read_only. Added explicit validation for missing frontmatter fields (name, description) and invalid namespace format with actionable error messages. Added docs/reference/agent_skills.md covering folder layout, SKILL.md parsing rules, progressive disclosure model, and tool mapping. Added Behave scenarios covering valid/invalid SKILL.md parsing, namespaced naming, step ordering, missing frontmatter errors, progressive disclosure lifecycle, tool mapping, and resource binding slots. Added Robot Framework integration tests using the deploy-to-staging example skill folder (robot/agent_skills_loader.robot). Added ASV benchmarks for parsing throughput, folder load, progressive disclosure lifecycle, and resource listing (benchmarks/agent_skills_loader_bench.py). ISSUES CLOSED: #160	2026-02-26 09:10:35 +00:00
aditya	519e26fb02	Merge branch 'master' into feature/m3-mcp-adapter	2026-02-26 06:44:38 +00:00
aditya	b8d7c4c893	Merge branch 'master' into feature/m2-actor-yaml	2026-02-26 06:21:39 +00:00
brent.edwards	c53b880a5e	Merge branch 'master' into develop-brent-5	2026-02-26 03:44:19 +00:00
freemo	e3fcce413b	feat(changeset): persist changesets and diff artifacts ... Add SQLite persistence for ChangeSet entries and ToolInvocation records via new changeset_repository module implementing the ChangeSetStore protocol. - Alembic migration d0_001 creates changeset_entries and tool_invocations tables - SqliteChangeSetStore, ChangeSetEntryRepository, ToolInvocationRepository - PlanApplyService.cleanup_changeset() for cancel/failure cleanup - Behave tests (17 scenarios), Robot tests (5 cases), ASV benchmarks - Reference documentation in docs/reference/changeset.md Closes #163	2026-02-26 02:47:14 +00:00
brent.edwards	cf59f285fd	Merge feature/m4-correction-subplan-smoke into develop-brent-5	2026-02-26 02:15:24 +00:00
brent.edwards	a00c33c4c6	Merge test/m4-e2e-verification into develop-brent-5	2026-02-26 02:15:19 +00:00
brent.edwards	2e2ae3b9b8	Merge test/m3-e2e-verification into develop-brent-5	2026-02-26 02:15:14 +00:00
brent.edwards	3d3c8fda33	Merge feature/m4-decision-tests into develop-brent-5	2026-02-26 02:15:01 +00:00
brent.edwards	b3f126b147	Merge feature/m3-decision-validation-smoke into develop-brent-5	2026-02-26 02:14:14 +00:00
brent.edwards	3c9a3efdf1	fix(test): correct mock targets, method names, ULIDs, and CLI args in M4 smoke suite ... - 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.	2026-02-26 02:01:47 +00:00
brent.edwards	4f079c20ea	fix(test): route M3 E2E subcommands through CLI rendering path ... - decision-tree-view, decision-explain, and decision-tree-persistence now invoke 'plan status --format plain' via mocked lifecycle service so regressions in CLI rendering/serialization are caught - plan-generates-decisions now asserts use_action was called by the CLI and verifies plan status renders the strategize phase after creation - Updated robot test case documentation to reflect CLI integration	2026-02-26 01:26:02 +00:00
brent.edwards	b99510d016	fix(test): derive decision type count from enum instead of hard-coding 11 ... Replace hard-coded '11 decision types' with dynamic len(DecisionType) in the assertion and remove the literal from scenario names, step patterns, docstrings, and docs so the tests stay correct when new DecisionType values are added.	2026-02-26 01:19:28 +00:00
brent.edwards	93730067a2	fix(test): address review findings in M3 smoke tests ... - Replace dead after_scenario() hook with context.add_cleanup() calls so patchers are properly stopped (Behave only runs hooks from environment.py) - Fix invalid ULID constants: pad DECISION/CORRECTION to 26 chars, replace invalid 'I' with 'J' in INVARIANT_ULID - Add temp file cleanup for NamedTemporaryFile(delete=False) via context.add_cleanup() in behave steps and try/finally in robot helper - Remove decision-persistence doc sections from testing.md that belong in PR #438, not this PR	2026-02-26 01:13:16 +00:00
brent.edwards	ef58883f7a	fix(test): harden retry_patterns feature against flaky CI failures ... The jitter-spread scenario used millisecond-bucketed wall-clock timestamps to assert that retried operations did not cluster. On busy CI runners — especially when a preceding scenario's time.sleep patch leaked through a late cleanup — tenacity's retry waits became no-ops and all five operations landed in the same millisecond bucket, tripping the max_in_bucket <= 3 assertion. Three hardening changes: 1. Jitter test: switch from time.time() to time.monotonic_ns() and replace the fragile bucket assertion with a unique-timestamp count (>= 2 distinct readings among 5 sequential operations). 2. Timeout test: eagerly restore time.sleep in a try/finally block so subsequent scenarios never observe the patched no-op, regardless of behave's cleanup ordering. 3. Async circuit breaker: lower recovery_timeout from 0.2 s to 0.1 s (the sleep step already waits 0.2 s) to give a wider safety margin on slow CI machines.	2026-02-26 00:51:11 +00:00
freemo	3a2b134f3c	test(coverage): add Behave scenarios for remaining under-tested modules ... Added Behave BDD feature files and step definitions targeting coverage gaps in six modules: - container.py: exercise get_database_url env-var fallback, AI provider None path, cached container singleton, override_providers edge cases (lines 66-69, 125-130; branches at 51, 57, 82, 87, 256, 284-288) - correction_service.py: exercise exception-handling paths in execute_revert and execute_append via monkeypatched analyze_impact and ULID failures (lines 254-262, 320-328) - plan_lifecycle_service.py: exercise _persisted UoW commit paths, InvalidPhaseTransitionError custom message branch, non-reusable action archive, and error_details merge logic (branches at 100, 216, 237, 327, 461, 570, 576, 607) - plan.py (CLI): exercise spec-dict optional field branches, _print_lifecycle_plan conditional rendering, use_action argument parsing, auto-resolve paths, legacy wrappers, and validation error branches across 66 scenarios - skill.py (CLI): exercise singleton cache, timestamp-absent show, no-tools MCP, add/remove/list/show format and error branches across 26 scenarios - models.py (DB): exercise to_domain/from_domain None-field branches in SkillModel, SessionModel, ToolModel, LifecycleActionModel, LifecyclePlanModel, NamespacedProjectModel, and SessionMessageModel across 41 scenarios All 302 features, 6503 scenarios, 28271 steps pass (nox -e unit_tests). ISSUES CLOSED: #446	2026-02-25 19:38:43 -05:00
brent.edwards	c80cda2590	Merge feature/m4-correction-subplan-smoke into develop-brent-5	2026-02-25 22:11:33 +00:00
brent.edwards	a2b0611722	Merge branch 'test/m4-e2e-verification' into develop-brent-5	2026-02-25 22:10:46 +00:00
brent.edwards	49f097472a	Merge branch 'test/m3-e2e-verification' into develop-brent-5	2026-02-25 22:10:42 +00:00
brent.edwards	5a212481e1	Merge branch 'feature/m4-decision-tests' into develop-brent-5	2026-02-25 22:10:38 +00:00
brent.edwards	22986aaaf9	fix(test): correct dry-run assertion in M3 decision validation smoke ... The CLI plain format output does not include the literal text "Dry Run" (that string only appears in the Rich panel title). Assert against "risk_level" which is present in the dry-run impact output instead.	2026-02-25 22:09:26 +00:00
brent.edwards	55df1915f1	fix(test): correct patch targets and ULID validation in M4 smoke helper ... - Patch CorrectionService at its definition site instead of the lazy import location in plan.py (same fix as M3 helper) - Replace hardcoded fake subplan/correction IDs with real ULIDs generated via ulid.ULID() to satisfy Pydantic pattern validation - Add missing --guidance flag to correction dry-run CLI invocation - Fix subplan-status-sequential assertion to check for plan_id (subplan_count is not part of the status JSON output)	2026-02-25 22:06:45 +00:00
brent.edwards	2e53caaef1	fix(test): correct patch target for CorrectionService in M3 e2e helper ... The CorrectionService import in plan.py is a lazy import inside the correct() function body, so it does not exist as a module-level attribute. Patch the class at its definition site instead: cleveragents.application.services.correction_service.CorrectionService Fixes CI integration_tests failure for PR #439.	2026-02-25 22:00:39 +00:00
brent.edwards	917c2bc546	test(e2e): add M4 correction + subplan suites	2026-02-25 21:51:26 +00:00
brent.edwards	cfc319ad27	test(e2e): verify M4 success criteria — subplans and parallel execution	2026-02-25 21:46:58 +00:00
brent.edwards	ace7311de4	test(e2e): add M3 decision + validation suites	2026-02-25 21:26:19 +00:00
brent.edwards	f4c4884d03	test(persistence): add decision persistence suites ... Add comprehensive persistence test suites for the Decision domain model covering serialization round-trips (model_dump/model_validate, JSON), context-snapshot persistence, correction-chain reconstruction, and decision-tree reconstruction from serialized data. Deliverables: - Behave: 21 scenarios in features/decision_persistence.feature - Robot Framework: 7 integration tests in robot/decision_persistence.robot - ASV benchmarks: 4 suites (17 benchmarks) in benchmarks/decision_persistence_bench.py - Documentation: Updated docs/development/testing.md ISSUES CLOSED: #180	2026-02-25 21:19:57 +00:00