373 Commits

Author	SHA1	Message	Date
CoreRasurae	53455275ba	feat(automation): add autonomy guardrails and audit trail ... 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	2026-02-28 22:06:57 +00:00
Luis Mendes	64af753aab	feat(security): add permission system ... 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	2026-02-28 20:21:18 +00:00
CoreRasurae	a2be3e67b0	feat(validation): add semantic validation service ... Added SemanticValidationService with built-in Python checks for syntax errors, missing imports, broken references, dependency cycles, API misuse, and missing symbols. Implemented SemanticRuleRegistry for extensible validator registration. Integrated with ValidationPipeline as informational by default. Added per-project/per-plan config keys, severity mapping (info/warn/error), output schema normalization, and file-hash-based caching. Includes Behave BDD scenarios, Robot integration tests, ASV benchmarks, and reference documentation. ISSUES CLOSED: #207	2026-02-28 17:46:54 +00:00
brent.edwards	38e75342a9	refactor: merge from master ... This code is a merge from master.	2026-02-28 05:49:26 +00:00
brent.edwards	e3a93bf32c	Merge branch 'master' into feature/m5-acms-smoke	2026-02-28 02:32:51 +00:00
brent.edwards	158a99c543	Merge branch 'master' into feature/m6-autonomy-smoke	2026-02-28 01:10:08 +00:00
freemo	0ca1303927	feat(sandbox): add checkpoint and rollback hooks ... 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	2026-02-27 23:08:55 +00:00
brent.edwards	c9782637d9	Merge branch 'master' into feature/m5-acms-smoke	2026-02-27 22:45:53 +00:00
brent.edwards	f90cf24617	Merge branch 'master' into feature/m6-autonomy-smoke	2026-02-27 22:14:54 +00:00
brent.edwards	348c230bc5	test(e2e): add M6 autonomy acceptance suite ... Add comprehensive M6 autonomy acceptance test suites covering the ACP local-mode facade, autonomy guardrails, automation profile resolution, event queue pub/sub, HTTP transport stub, and version negotiation. Behave suite (52 scenarios): - ACP facade dispatch for all 11 operations - Guard enforcement (denylist, allowlist, budget, call limit, write/apply) - Automation profile built-in validation and custom creation - Profile resolution precedence (plan > action > project > global) - Event queue lifecycle (publish, subscribe, unsubscribe, close) - HTTP transport stub rejection in local mode - ACP version negotiation (accept/reject) - Model validation (AcpRequest, AcpResponse, AcpEvent, AcpErrorDetail) Robot integration suite (11 tests): - Facade session/plan lifecycle, unknown operation error - Event queue publish/subscribe, transport stub, version negotiation - Guard denylist/budget enforcement, profile resolution - Fixture loading, full end-to-end flow ASV benchmarks (5 suites): - Facade dispatch, guard evaluation, profile resolution - Event queue operations, fixture loading Fixtures: acp_facade_flows.json, autonomy_guardrails.json, automation_profiles.json Closes #211	2026-02-27 20:31:15 +00:00
brent.edwards	ece5e61725	test(e2e): add M5 ACMS + context suites	2026-02-27 20:20:13 +00:00
freemo	7235d46ade	feat(skill): persist flattened tool sets ... 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	2026-02-27 20:09:26 +00:00
freemo	a074b4846f	fix(provider): remove FakeListLLM defaults ... 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	2026-02-27 09:47:10 -05:00
aditya	9af9ff8d95	Merge branch 'master' into feature/m4-skill-registry-refresh	2026-02-27 12:27:10 +00:00
aditya	174d1dc334	Merge branch 'master' into feature/m4-skill-registry-cli	2026-02-27 10:40:42 +00:00
aditya	4c4bd74d94	Merge branch 'master' into feature/m3-agent-skills-loader	2026-02-27 09:34:00 +00:00
aditya	2b5b73c689	Merge branch 'master' into feature/m5-subplan-actor	2026-02-27 08:43:40 +00:00
aditya	b888afab71	feat(actor): add plan_subplan tool and decision emission ... Add builtin/plan-subplan tool for strategy actors to emit SUBPLAN_SPAWN or SUBPLAN_PARALLEL_SPAWN decisions when decomposing a plan into child plans. Implements all acceptance criteria from issue #198: - SubplanPayload (Pydantic) validates goal, resource_scopes/project_ref (at least one required), merge_strategy, max_parallel (1-50), parallel flag, dependencies, and context_view override. - Defaults: merge_strategy=git_three_way, max_parallel=5, parallel=False, dependencies=[]. Omitted fields inherit sensible values automatically. - make_plan_subplan_spec(decision_service=None) factory supports optional DecisionService injection for persistent decision recording. - _build_rationale() generates human-readable rationale text (goal, scope, execution mode, dependencies, context_view) surfaced in plan explain. - register_subplan_tool() added to tool/builtins/__init__.py for bulk registration. PLAN_SUBPLAN_SPEC exported as the default ready-to-use spec. - Actor YAML example (examples/actors/strategy_with_subplan.yaml) with annotated serial and parallel spawn payload examples. - Behave BDD: 20 scenarios, 70 steps covering validation, defaults, decision type, rationale, service injection, registry, and ToolRunner. - Robot Framework: 9 smoke tests via robot/plan_subplan_tool.robot. - ASV benchmarks: benchmarks/subplan_actor_tool_bench.py (5 suites). - Coverage: 100% on subplan_tool.py. Lint, typecheck, and security clean. ISSUES CLOSED: #198	2026-02-27 08:02:48 +00:00
aditya	a0f56228e2	Merge branch 'master' into feature/m3-mcp-adapter	2026-02-27 06:40:15 +00:00
freemo	120274da99	feat(di): wire decision services ... 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	2026-02-27 02:33:42 +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
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
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
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
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	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	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
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	5a212481e1	Merge branch 'feature/m4-decision-tests' into develop-brent-5	2026-02-25 22:10:38 +00:00
brent.edwards	917c2bc546	test(e2e): add M4 correction + subplan suites	2026-02-25 21:51:26 +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
brent.edwards	d055b59d7c	Merge branch 'master' into develop-brent-4	2026-02-25 20:05:18 +00:00
brent.edwards	3b58432ecc	docs(merge): merge new docs into branch	2026-02-25 19:41:56 +00:00
freemo	c4f71e930d	feat(concurrency): add plan resume ... Implement step-level progress persistence and plan resume with graceful shutdown handling. - Add ResumeCheckpoint, ResumeMetadata, ResumeEligibility, ResumeSummary domain models (resume.py) - Add PlanResumeService with validate_eligibility(), build_resume_summary(), resume_plan(dry_run), record_step_checkpoint(), record_shutdown() - Add last_completed_step and last_checkpoint_id fields to Plan model - Add 'plan resume' CLI command with --dry-run flag - Update plan lifecycle docs (ADR-006) with resume behavior section - Add Behave tests (24 scenarios in plan_resume.feature) - Add Robot Framework integration tests (10 tests) - Add ASV benchmarks for resume overhead Closes #328	2026-02-25 14:00:04 -05:00
freemo	134dce896a	feat(provider): add cost controls and fallback ... Add token/cost tracking, budget enforcement (per-plan and per-day), provider fallback selection with capability filtering, and cost metadata for plan models. New modules: - providers/cost_table.py: CostEntry + ProviderCostTable with default pricing for OpenAI, Anthropic, Google, Groq, Together, Cohere, Mock - providers/cost_tracker.py: BudgetStatus enum, BudgetCheckResult, CostTracker with warn-at-90%/block-at-100% enforcement - providers/fallback_selector.py: FallbackSelector with capability filtering (tool_calls, streaming, vision, json_mode) and budget - domain/models/core/cost_metadata.py: CostMetadata + BudgetExhaustionEvent Modified: - config/settings.py: budget_per_plan, budget_per_day, fallback_providers - domain/models/core/plan.py: cost_metadata field + CLI dict surfacing - providers/__init__.py: public exports for new classes Testing: - 71 Behave scenarios in features/cost_controls.feature (all pass) - 6 Robot Framework integration tests (all pass) - ASV benchmarks in benchmarks/cost_controls_bench.py - nox lint, typecheck, format, docs, build, dead_code, security_scan pass Closes #324	2026-02-25 12:08:01 -05:00
freemo	7a298ede6e	feat(concurrency): add plan and project locks ... Implemented plan-level and project-level locking with configurable timeouts. Added locks table via Alembic migration storing owner_id, resource_type, resource_id, acquired_at, and expires_at. Locks enforced in PlanLifecycleService transitions. Support for re-entrant acquisition, lock renewal, graceful shutdown release, and startup cleanup of expired locks. Added diagnostics check for stale lock reporting. ISSUES CLOSED: #327	2026-02-25 10:48:05 -05:00
aditya	ee82d6101e	feat(skill): add MCP adapter for external tools ... Implement MCPToolAdapter to connect to external MCP servers, enumerate tools, and register them in ToolRegistry with source="mcp". Includes connect/reconnect/disconnect lifecycle with timeout enforcement, input validation on invoke, capability inference, Behave/Robot/ASV tests, and docs/reference/mcp_adapter.md. ISSUES CLOSED: #159	2026-02-25 13:17:26 +00:00