feat(tools): add background embedding queue for thoughts

* Implement QueueThought method in BackfillTool for embedding generation
* Update CaptureTool to utilize embedding queuer for failed embeddings
* Add EmbeddingStatus field to Thought type for tracking embedding state

internal/tools/backfill.go

@@ -51,6 +51,30 @@ func NewBackfillTool(db *store.DB, provider ai.Provider, sessions *session.Activ
 	return &BackfillTool{store: db, provider: provider, sessions: sessions, logger: logger}
 }
 
+// QueueThought queues a single thought for background embedding generation.
+// It is used by capture when the embedding provider is temporarily unavailable.
+func (t *BackfillTool) QueueThought(ctx context.Context, id uuid.UUID, content string) {
+	go func() {
+		vec, err := t.provider.Embed(ctx, content)
+		if err != nil {
+			t.logger.Warn("background embedding retry failed",
+				slog.String("thought_id", id.String()),
+				slog.String("error", err.Error()),
+			)
+			return
+		}
+		model := t.provider.EmbeddingModel()
+		if err := t.store.UpsertEmbedding(ctx, id, model, vec); err != nil {
+			t.logger.Warn("background embedding upsert failed",
+				slog.String("thought_id", id.String()),
+				slog.String("error", err.Error()),
+			)
+			return
+		}
+		t.logger.Info("background embedding retry succeeded", slog.String("thought_id", id.String()))
+	}()
+}
+
 func (t *BackfillTool) Handle(ctx context.Context, req *mcp.CallToolRequest, in BackfillInput) (*mcp.CallToolResult, BackfillOutput, error) {
 	limit := in.Limit
 	if limit <= 0 {

internal/tools/capture.go

@@ -6,6 +6,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/google/uuid"
 	"github.com/modelcontextprotocol/go-sdk/mcp"
 	"golang.org/x/sync/errgroup"
 
@@ -17,6 +18,11 @@ import (
 	thoughttypes "git.warky.dev/wdevs/amcs/internal/types"
 )
 
+// EmbeddingQueuer queues a thought for background embedding generation.
+type EmbeddingQueuer interface {
+	QueueThought(ctx context.Context, id uuid.UUID, content string)
+}
+
 type CaptureTool struct {
 	store           *store.DB
 	provider        ai.Provider
@@ -24,6 +30,7 @@ type CaptureTool struct {
 	sessions        *session.ActiveProjects
 	metadataTimeout time.Duration
 	retryer         *MetadataRetryer
+	embedRetryer    EmbeddingQueuer
 	log             *slog.Logger
 }
 
@@ -36,8 +43,8 @@ type CaptureOutput struct {
 	Thought thoughttypes.Thought `json:"thought"`
 }
 
-func NewCaptureTool(db *store.DB, provider ai.Provider, capture config.CaptureConfig, metadataTimeout time.Duration, sessions *session.ActiveProjects, retryer *MetadataRetryer, log *slog.Logger) *CaptureTool {
-	return &CaptureTool{store: db, provider: provider, capture: capture, sessions: sessions, metadataTimeout: metadataTimeout, retryer: retryer, log: log}
+func NewCaptureTool(db *store.DB, provider ai.Provider, capture config.CaptureConfig, metadataTimeout time.Duration, sessions *session.ActiveProjects, retryer *MetadataRetryer, embedRetryer EmbeddingQueuer, log *slog.Logger) *CaptureTool {
+	return &CaptureTool{store: db, provider: provider, capture: capture, sessions: sessions, metadataTimeout: metadataTimeout, retryer: retryer, embedRetryer: embedRetryer, log: log}
 }
 
 func (t *CaptureTool) Handle(ctx context.Context, req *mcp.CallToolRequest, in CaptureInput) (*mcp.CallToolResult, CaptureOutput, error) {
@@ -54,12 +61,18 @@ func (t *CaptureTool) Handle(ctx context.Context, req *mcp.CallToolRequest, in C
 	var embedding []float32
 	rawMetadata := metadata.Fallback(t.capture)
 	metadataNeedsRetry := false
+	embeddingNeedsRetry := false
 
 	group, groupCtx := errgroup.WithContext(ctx)
 	group.Go(func() error {
 		vector, err := t.provider.Embed(groupCtx, content)
 		if err != nil {
-			return err
+			t.log.Warn("embedding failed, thought will be saved without embedding",
+				slog.String("provider", t.provider.Name()),
+				slog.String("error", err.Error()),
+			)
+			embeddingNeedsRetry = true
+			return nil
 		}
 		embedding = vector
 		return nil
@@ -106,6 +119,9 @@ func (t *CaptureTool) Handle(ctx context.Context, req *mcp.CallToolRequest, in C
 	if metadataNeedsRetry && t.retryer != nil {
 		t.retryer.QueueThought(created.ID)
 	}
+	if embeddingNeedsRetry && t.embedRetryer != nil {
+		t.embedRetryer.QueueThought(ctx, created.ID, content)
+	}
 
 	return nil, CaptureOutput{Thought: created}, nil
 }