fix(kernel,server,tui,inference): generic resource gauge + F-002/F-003/F-004

- generic SystemResourceProbe: owner-agnostic /proc/meminfo system RAM
  overlaid on the vendor GPU probe, wired on both managed and static paths
  so the VRAM/GPU/RAM gauge renders with an external llama-server (was dormant)
- F-002: classify provider 4xx (e.g. llama.cpp 400) as terminal, not retryable
  (except 408/429); stops retrying deterministic request failures to exhaustion
- F-003: FileSystemPromptLoader expands leading ~ / ~/ to user home
- F-004: map InferenceFailedEvent + RetryAttemptedEvent to new
  ServerMessage.InferenceFailed / RetryAttempted, decoded+rendered in tui-go;
  ArtifactContentStoredEvent explicitly mapped to null (internal, no warn)
- tests: tilde expansion, SystemResourceProbe (static/managed/fail-soft)

apps/tui-go/internal/app/model.go

@@ -183,6 +183,8 @@ type Model struct {
 	gpuTotalMB      *int64
 	gpuUtil         *int
 	ramMB           *int64
+	sysRamUsedMB    *int64
+	sysRamTotalMB   *int64
 
 	// diff / overlay
 	overlay          OverlayKind

apps/tui-go/internal/app/server.go

@@ -3,6 +3,7 @@ package app
 import (
 	"crypto/rand"
 	"encoding/hex"
+	"fmt"
 	"strings"
 	"time"
 
@@ -172,6 +173,16 @@ func (m *Model) applyServer(msg protocol.ServerMessage) {
 			s.Active = false
 			s.addEvent(nowMillis(), "InferenceTimedOut", msg.StageID)
 		}
+	case protocol.TypeInferenceFailed:
+		if s := m.session(msg.SessionID); s != nil {
+			s.Active = false
+			s.addEvent(nowMillis(), "InferenceFailed", msg.StageID+": "+msg.Reason)
+		}
+	case protocol.TypeInferenceRetry:
+		if s := m.session(msg.SessionID); s != nil {
+			s.addEvent(nowMillis(), "RetryAttempted",
+				fmt.Sprintf("%s (%d/%d): %s", msg.StageID, msg.AttemptNumber, msg.MaxAttempts, msg.FailureReason))
+		}
 	case protocol.TypeToolStarted:
 		if s := m.session(msg.SessionID); s != nil {
 			s.Active = true
@@ -274,6 +285,8 @@ func (m *Model) applyServer(msg protocol.ServerMessage) {
 		m.gpuTotalMB = msg.GpuMemoryTotalMb
 		m.gpuUtil = msg.GpuUtilizationPct
 		m.ramMB = msg.ProcessRssMb
+		m.sysRamUsedMB = msg.SystemRamUsedMb
+		m.sysRamTotalMB = msg.SystemRamTotalMb
 	case protocol.TypeArtifactList:
 		m.artifacts = msg.Artifacts
 		m.artifactsFor = msg.SessionID

apps/tui-go/internal/app/view.go

@@ -117,8 +117,11 @@ func (m Model) gaugeText() string {
 	if m.gpuUtil != nil {
 		parts = append(parts, "GPU "+itoa(*m.gpuUtil)+"%")
 	}
+	if m.sysRamUsedMB != nil && m.sysRamTotalMB != nil {
+		parts = append(parts, "RAM "+itoa(int(*m.sysRamUsedMB))+"/"+itoa(int(*m.sysRamTotalMB))+"M")
+	}
 	if m.ramMB != nil {
-		parts = append(parts, "RAM "+itoa(int(*m.ramMB))+"M")
+		parts = append(parts, "proc "+itoa(int(*m.ramMB))+"M")
 	}
 	return strings.Join(parts, " ")
 }

apps/tui-go/internal/protocol/protocol.go

@@ -26,6 +26,8 @@ const (
 	TypeInferenceStarted = "inference.started"
 	TypeInferenceDone    = "inference.completed"
 	TypeInferenceTimeout = "inference.timed_out"
+	TypeInferenceFailed  = "inference.failed"
+	TypeInferenceRetry   = "inference.retry"
 	TypeToolStarted      = "tool.started"
 	TypeToolCompleted    = "tool.completed"
 	TypeToolFailed       = "tool.failed"
@@ -77,6 +79,11 @@ type ServerMessage struct {
 	Outcome       string  `json:"outcome"`       // approval.resolved: APPROVED | REJECTED | AUTO_APPROVED
 	WorkspaceRoot string  `json:"workspaceRoot"` // session.workspace_bound: the bound cwd
 
+	// inference.retry
+	AttemptNumber int    `json:"attemptNumber"`
+	MaxAttempts   int    `json:"maxAttempts"`
+	FailureReason string `json:"failureReason"`
+
 	SteeringEmitted bool  `json:"steeringEmitted"`
 	OccurredAt      int64 `json:"occurredAt"`
 	ElapsedMs       int64 `json:"elapsedMs"`
@@ -99,6 +106,8 @@ type ServerMessage struct {
 	GpuMemoryTotalMb  *int64 `json:"gpuMemoryTotalMb"`
 	GpuUtilizationPct *int   `json:"gpuUtilizationPct"`
 	ProcessRssMb      *int64 `json:"processRssMb"`
+	SystemRamUsedMb   *int64 `json:"systemRamUsedMb"`
+	SystemRamTotalMb  *int64 `json:"systemRamTotalMb"`
 
 	State          *SessionStateDto   `json:"state"`
 	RiskSummary    *RiskSummaryDto    `json:"riskSummary"`
@@ -209,6 +218,7 @@ func (m ServerMessage) IsEventBearing() bool {
 		TypeSessionCompleted, TypeSessionFailed,
 		TypeStageStarted, TypeStageCompleted, TypeStageFailed,
 		TypeInferenceStarted, TypeInferenceDone, TypeInferenceTimeout,
+		TypeInferenceFailed, TypeInferenceRetry,
 		TypeToolStarted, TypeToolCompleted, TypeToolFailed, TypeToolRejected,
 		TypeToolAssessed,
 		TypeApprovalRequired, TypeApprovalResolved, TypeWorkspaceBound, TypeArtifactCreated,