feat(agents): enhance agent core with state management

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

backend/app/agents/schemas/__init__.py

@@ -1,5 +1,24 @@
 from app.agents.schemas.event import AgentEvent
+from app.agents.schemas.learning import (
+    LearningDecision,
+    LearningSignal,
+    PatternCandidate,
+    SessionRetrospective,
+    SkillCandidate,
+)
 from app.agents.schemas.message import AgentMessage
+from app.agents.schemas.orchestration import (
+    ExecutionDecision,
+    MergeReport,
+    ParallelWorthiness,
+    RuntimeRequestContext,
+    SubTaskResult,
+    SubTaskSpec,
+    TaskGraph,
+    TaskNode,
+    VerificationReport,
+)
+from app.agents.schemas.skills import SkillActivationRecord, SkillShortlistEntry
 from app.agents.schemas.task import (
     AgentTask,
     CollaborationBudget,
@@ -14,12 +33,28 @@ from app.agents.schemas.task import (
 __all__ = [
     "AgentEvent",
     "AgentMessage",
+    "ExecutionDecision",
     "AgentTask",
     "CollaborationBudget",
     "InterruptRecord",
+    "LearningDecision",
+    "LearningSignal",
+    "MergeReport",
+    "ParallelWorthiness",
+    "PatternCandidate",
     "RecoveryRecord",
+    "RuntimeRequestContext",
+    "SessionRetrospective",
+    "SkillActivationRecord",
+    "SkillCandidate",
+    "SkillShortlistEntry",
+    "SubTaskResult",
+    "SubTaskSpec",
+    "TaskGraph",
+    "TaskNode",
     "TaskLifecycleStatus",
     "TaskResult",
     "TaskResultStatus",
+    "VerificationReport",
     "VerificationStatus",
 ]

backend/app/agents/schemas/event.py

@@ -7,10 +7,21 @@ from pydantic import BaseModel, Field
 
 
 AgentEventType = Literal[
+    "agent.execution.decided",
+    "agent.parallel.assessed",
+    "agent.skill.shortlisted",
+    "agent.task_graph.built",
+    "agent.subtask.started",
+    "agent.subtask.completed",
+    "agent.merge.completed",
     "agent.tool.start",
     "agent.tool.result",
     "agent.verify.started",
     "agent.verify.completed",
+    "agent.retrospective.created",
+    "agent.learning.decision",
+    "agent.skill.lifecycle.changed",
+    "agent.rollback.triggered",
     "agent.created",
     "agent.spawn.blocked",
     "agent.message.sent",