agent: rename reasoning → Agent

The inner struct that holds agent-specific state (history, runtime,
backend, tools, hooks) is now called Agent — because that's what it
is. A session owns an Agent; the Agent performs reasoning within
the session's environment.

agent/core.go

@@ -311,7 +311,7 @@ type AgentCoreConfig struct {
 // but has no knowledge of how output is rendered.
 type agent struct {
 	sess            *session.Session
-	r            *reasoning
+	r            *Agent
 	log             *olog.Logger
 	sessionsDir     string
 	readPlanStep    func() string
@@ -459,7 +459,7 @@ func NewAgentCore(cfg AgentCoreConfig) Core {
 			Uname: cfg.Uname,
 			CWD:   paths.ExpandHome(cfg.CWD),
 		}),
-		r: &reasoning{
+		r: &Agent{
 			history:        cfg.History,
 			runtime:        rt,
 			agentName:      cfg.AgentName,

agent/reasoning.go

@@ -8,11 +8,11 @@ import (
 	"ollie/tools"
 )
 
-// reasoning holds the state of the current reasoning entity (the "agent"
+// Agent holds the state of the current Agent entity (the "agent"
 // in the traditional sense). It is swappable: when the user runs /agent,
-// a new reasoning is built from the new agent config while the session
+// a new Agent is built from the new agent config while the session
 // host remains stable.
-type reasoning struct {
+type Agent struct {
 	history        *History
 	runtime        *Runtime
 	cfg            agentConfig // per-turn config built from runtime
@@ -28,7 +28,7 @@ type reasoning struct {
 }
 
 // Backend returns the active backend from the runtime.
-func (r *reasoning) Backend() backend.Backend {
+func (r *Agent) Backend() backend.Backend {
 	if r.runtime == nil {
 		return nil
 	}