Feature: v3 Actor YAML schema support in CLI and registry As a developer using v3 actor YAML configs I want the CLI and registry to validate, persist, and execute v3 schema actors So that spec-compliant actors with skills, LSP bindings, and LangGraph routes work Scenario: ActorConfiguration.from_blob extracts provider and model from v3 LLM YAML Given a v3 LLM actor blob with model "gpt-4" When I call ActorConfiguration.from_blob with the v3 blob Then the configuration should have provider "custom" And the configuration should have model "gpt-4" Scenario: ActorConfiguration.from_blob infers provider from model with slash Given a v3 LLM actor blob with model "openai/gpt-4" When I call ActorConfiguration.from_blob with the v3 blob Then the configuration should have provider "openai" And the configuration should have model "openai/gpt-4" Scenario: ActorConfiguration.from_blob infers custom provider for slash-prefixed model Given a v3 LLM actor blob with model "/gpt-4" When I call ActorConfiguration.from_blob with the v3 blob Then the configuration should have provider "custom" And the configuration should have model "/gpt-4" Scenario: ActorConfiguration.from_blob builds graph descriptor for graph actors Given a v3 graph actor blob with a route block When I call ActorConfiguration.from_blob with the v3 blob Then the configuration should have a graph_descriptor with type "graph" Scenario: ActorRegistry.add validates v3 LLM actor YAML Given a mock actor service for v3 testing And a v3 LLM actor YAML text When I call ActorRegistry.add with the v3 YAML Then the actor should be persisted with v3 fields in config_blob And the persisted config_blob should contain skills And the persisted config_blob should contain lsp bindings Scenario: ActorRegistry.add rejects v3 YAML without required description Given a mock actor service for v3 testing And a v3 actor YAML text missing description When I call ActorRegistry.add with the invalid v3 YAML Then a ValidationError should be raised mentioning description Scenario: ActorRegistry.add validates and compiles v3 graph actor Given a mock actor service for v3 testing And a v3 graph actor YAML text with route When I call ActorRegistry.add with the v3 graph YAML Then the actor should be persisted with compiled metadata And the graph_descriptor should contain route information Scenario: ReactiveConfigParser handles v3 LLM actor format Given a v3 LLM actor config dict When I parse the v3 config through ReactiveConfigParser Then the reactive config should have one agent And the agent config should contain the model And the agent config should contain skills Scenario: ReactiveConfigParser handles v3 graph actor format Given a v3 graph actor config dict with route When I parse the v3 config through ReactiveConfigParser Then the reactive config should have agents for each node And the reactive config should have a graph route And the graph route edges should use source and target keys # M14: test update=True path Scenario: ActorRegistry.add with update=True overwrites existing actor Given a mock actor service for v3 testing And an existing actor in the mock service And a v3 LLM actor YAML text When I call ActorRegistry.add with update=True for the v3 YAML Then the actor should be persisted successfully with update # M15: test type:tool extraction and parsing paths # from_blob requires model for ActorConfiguration — tool actors without # model raise ValueError. The proper v3 path is ActorRegistry.add(). Scenario: ActorConfiguration.from_blob rejects type tool without model Given a v3 tool actor blob without model When I call ActorConfiguration.from_blob with the v3 tool blob Then the tool actor from_blob should raise ValueError for missing model Scenario: ActorRegistry.add validates v3 tool actor YAML Given a mock actor service for v3 testing And a v3 tool actor YAML text When I call ActorRegistry.add with the v3 tool YAML Then the tool actor should be persisted with type tool # m13: test _build_from_v3 with lsp as dict Scenario: ReactiveConfigParser handles v3 LLM actor with lsp as dict Given a v3 LLM actor config dict with lsp as dict When I parse the v3 config through ReactiveConfigParser Then the reactive config should have one agent And the agent config should contain lsp as dict # m13: test context_view, memory, env_vars, response_format propagation Scenario: ReactiveConfigParser propagates context_view memory env_vars and response_format Given a v3 LLM actor config dict with context_view and memory When I parse the v3 config through ReactiveConfigParser Then the reactive config should have one agent And the agent config should contain context_view And the agent config should contain memory settings And the agent config should contain env_vars And the agent config should contain response_format # m13: positive _is_v3_format test Scenario: v3 format detection returns true for v3 LLM data Given a v3 LLM actor config dict When I check if the v3 LLM config is v3 format Then it should be detected as v3 # Cycle 2 review: defensive guard BDD coverage Scenario: ReactiveConfigParser rejects graph with invalid entry_node Given a v3 graph actor config dict with invalid entry_node When I parse the v3 config through ReactiveConfigParser expecting error Then a ConfigurationError should be raised mentioning entry_node Scenario: ReactiveConfigParser skips edges with missing from_node or to_node Given a v3 graph actor config dict with incomplete edges When I parse the v3 config through ReactiveConfigParser Then the graph route should have fewer edges than the raw input Scenario: ReactiveConfigParser skips non-dict edge entries Given a v3 graph actor config dict with non-dict edges When I parse the v3 config through ReactiveConfigParser Then the graph route should have only valid dict edges # Coverage: v3_registry.py — name without slash gets local/ prefix Scenario: ActorRegistry.add namespaces bare actor name with local prefix Given a mock actor service for v3 testing And a v3 LLM actor YAML text with bare name When I call ActorRegistry.add with the bare-name v3 YAML Then the persisted actor name should be prefixed with local # Coverage: v3_registry.py — unsafe actor rejected without allow_unsafe Scenario: ActorRegistry.add rejects unsafe v3 actor without allow_unsafe flag Given a mock actor service for v3 testing And a v3 LLM actor YAML text marked unsafe When I call ActorRegistry.add with the unsafe v3 YAML Then a ValidationError should be raised mentioning unsafe # Coverage: v3_registry.py — duplicate actor rejected when update=False Scenario: ActorRegistry.add rejects duplicate v3 actor when update is False Given a mock actor service for v3 testing And an existing actor in the mock service And a v3 LLM actor YAML text When I call ActorRegistry.add with the v3 YAML expecting error Then a ValidationError should be raised mentioning already exists # Coverage: v3_registry.py — ActorCompilationError during graph compilation Scenario: ActorRegistry.add persists graph actor even when compilation fails Given a mock actor service for v3 testing And a v3 graph actor YAML text with route When I call ActorRegistry.add with the v3 graph YAML and compilation fails Then the actor should still be persisted without compiled metadata # Coverage: registry.py — _ensure_namespaced via get() Scenario: ActorRegistry.get namespaces bare actor name with local prefix Given a mock actor service for v3 testing When I call ActorRegistry.get with a bare actor name Then the actor service should be queried with local-prefixed name # Coverage: registry.py — add() with non-dict YAML Scenario: ActorRegistry.add rejects non-mapping YAML Given a mock actor service for v3 testing When I call ActorRegistry.add with a non-mapping YAML string Then a ValidationError should be raised mentioning mapping # Coverage: registry.py — upsert_actor v3 validation failure Scenario: ActorRegistry.upsert_actor rejects invalid v3 config_blob Given a mock actor service for v3 testing When I call ActorRegistry.upsert_actor with an invalid v3 config_blob Then a ValidationError should be raised mentioning invalid v3 actor # Coverage: config_parser.py — _merge with new=None Scenario: ReactiveConfigParser merge handles None new dict gracefully When I merge a None dict into a base config Then the base config should remain unchanged # Coverage: config_parser.py — missing model for llm actor Scenario: ReactiveConfigParser rejects v3 LLM actor with missing model Given a v3 LLM actor config dict with no model field When I parse the v3 config through ReactiveConfigParser expecting error Then a ConfigurationError should be raised mentioning model # Coverage: config_parser.py — lsp_capabilities and lsp_context_enrichment propagation Scenario: ReactiveConfigParser propagates lsp_capabilities and lsp_context_enrichment Given a v3 LLM actor config dict with lsp_capabilities and lsp_context_enrichment When I parse the v3 config through ReactiveConfigParser Then the agent config should contain lsp_capabilities And the agent config should contain lsp_context_enrichment # Coverage: config_parser.py — graph actor without route raises ConfigurationError Scenario: ReactiveConfigParser rejects v3 graph actor without route Given a v3 graph actor config dict without route When I parse the v3 config through ReactiveConfigParser expecting error Then a ConfigurationError should be raised mentioning route # Coverage: config_parser.py — non-dict node and empty-id node skipped in graph Scenario: ReactiveConfigParser skips non-dict and empty-id nodes in graph route Given a v3 graph actor config dict with malformed nodes When I parse the v3 config through ReactiveConfigParser Then the reactive config should only have agents for valid nodes # Coverage: config_parser.py — skills and lsp propagated to graph nodes Scenario: ReactiveConfigParser propagates skills and lsp bindings to graph nodes Given a v3 graph actor config dict with skills and lsp When I parse the v3 config through ReactiveConfigParser Then each graph node agent should have skills propagated And each graph node agent should have lsp propagated # Coverage: config_parser.py — lsp as dict propagated to graph nodes (line 330) Scenario: ReactiveConfigParser propagates lsp dict bindings to graph nodes Given a v3 graph actor config dict with skills and lsp as dict When I parse the v3 config through ReactiveConfigParser Then each graph node agent should have lsp dict propagated # M5: options block forwarded to agent_config in _build_from_v3 (#11223). @tdd_issue @tdd_issue_11223 Scenario: ReactiveConfigParser propagates options block to agent config Given a v3 LLM actor config dict with options block When I parse the v3 config through ReactiveConfigParser Then the agent config should contain the options block # M5: actor without options block is unaffected (#11223). @tdd_issue @tdd_issue_11223 Scenario: ReactiveConfigParser handles v3 actor without options block Given a v3 LLM actor config dict without options block When I parse the v3 config through ReactiveConfigParser Then the agent config should not contain an options key # M5: empty options dict is preserved (#11223). @tdd_issue @tdd_issue_11223 Scenario: ReactiveConfigParser preserves empty options block Given a v3 LLM actor config dict with empty options block When I parse the v3 config through ReactiveConfigParser Then the agent config should contain an empty options block