internal/database/schema/002_cache_eviction.sql

@@ -0,0 +1,25 @@
+-- Migration 002: cache size accounting and eviction
+--
+-- Tracks processed variants in the database (source content blobs are
+-- already tracked in source_content) so total cache usage can be
+-- computed without directory scans, and adds last-access timestamps
+-- for LRU eviction ordering.
+
+-- Processed variant blobs
+-- Files stored at: cache/variants/<ab>/<cd>/<cache_key> (plus a
+-- .meta sidecar with the content type)
+CREATE TABLE IF NOT EXISTS variant_content (
+    cache_key TEXT PRIMARY KEY,
+    size_bytes INTEGER NOT NULL,
+    content_type TEXT NOT NULL,
+    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
+);
+CREATE INDEX IF NOT EXISTS idx_variant_content_last_accessed
+    ON variant_content(last_accessed_at);
+
+-- LRU timestamp for source content blobs. Rows written before this
+-- migration have NULL here; eviction falls back to fetched_at.
+ALTER TABLE source_content ADD COLUMN last_accessed_at DATETIME;
+CREATE INDEX IF NOT EXISTS idx_source_content_last_accessed
+    ON source_content(last_accessed_at);

internal/handlers/handlers.go

@@ -53,6 +53,13 @@ func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
 		OnStart: func(_ context.Context) error {
 			return s.initImageService()
 		},
+		OnStop: func(_ context.Context) error {
+			if s.imgCache != nil {
+				s.imgCache.StopEviction()
+			}
+
+			return nil
+		},
 	})
 
 	return s, nil
@@ -60,11 +67,15 @@ func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
 
 // initImageService initializes the image cache and service.
 func (s *Handlers) initImageService() error {
-	// Create the cache
+	// Create the cache. cache_max_bytes: 0 disables the disk cache
+	// entirely; any other value is the eviction limit in bytes.
 	cache, err := imgcache.NewCache(s.db.DB(), imgcache.CacheConfig{
-		StateDir:    s.config.StateDir,
+		StateDir:         s.config.StateDir,
-		CacheTTL:    imgcache.DefaultCacheTTL,
+		CacheTTL:         imgcache.DefaultCacheTTL,
-		NegativeTTL: imgcache.DefaultNegativeTTL,
+		NegativeTTL:      imgcache.DefaultNegativeTTL,
+		MaxBytes:         s.config.CacheMaxBytes,
+		DisableDiskCache: s.config.CacheMaxBytes == 0,
+		Logger:           s.log,
 	})
 	if err != nil {
 		return err
@@ -72,6 +83,10 @@ func (s *Handlers) initImageService() error {
 
 	s.imgCache = cache
 
+	// Background eviction: startup reconciliation, then periodic and
+	// write-pressure passes. No-op when the disk cache is disabled.
+	cache.StartEviction(imgcache.DefaultEvictionInterval)
+
 	// Create the fetcher config
 	fetcherCfg := httpfetcher.DefaultConfig()
 	fetcherCfg.AllowHTTP = s.config.AllowHTTP

internal/imgcache/cache.go

@@ -9,6 +9,7 @@ import (
 	"io"
 	"log/slog"
 	"path/filepath"
+	"sync"
 	"time"
 
 	"sneak.berlin/go/pixa/internal/httpfetcher"
@@ -29,12 +30,18 @@ type CacheConfig struct {
 	CacheTTL    time.Duration
 	NegativeTTL time.Duration
 
-	// MaxBytes is the disk cache size limit in bytes. Zero disables
+	// MaxBytes is the disk cache size limit in bytes that eviction
-	// the disk cache entirely (no reads, no writes, no eviction); the
+	// enforces. Zero means no limit is enforced (no eviction). The
 	// config layer supplies the computed default when the operator
 	// omits cache_max_bytes.
 	MaxBytes int64
 
+	// DisableDiskCache turns the disk cache off entirely: no cache
+	// directories are created, lookups always miss, stores are
+	// no-ops, and no eviction machinery runs. The config layer sets
+	// this when the operator configures cache_max_bytes: 0.
+	DisableDiskCache bool
+
 	// Logger receives accounting and eviction log output. A nil
 	// Logger means slog.Default().
 	Logger *slog.Logger
@@ -53,6 +60,19 @@ type Cache struct {
 	variants    *VariantStorage  // processed variants by cache key
 	srcMetadata *MetadataStorage // source metadata by host/path
 	config      CacheConfig
+	log         *slog.Logger
+
+	// disabled means the disk cache is turned off entirely: lookups
+	// always miss, stores are no-ops, and no eviction runs.
+	disabled bool
+
+	// Eviction machinery. The channels are created in NewCache so
+	// stores can signal write pressure without racing StartEviction.
+	evictionPressure chan struct{}
+	evictionStop     chan struct{}
+	evictionDone     chan struct{}
+	evictionStarted  bool
+	evictionStopOnce sync.Once
 
 	// In-memory cache of variant metadata (content type, size) to avoid reading .meta files
 	metaCache map[VariantKey]variantMeta
@@ -60,6 +80,26 @@ type Cache struct {
 
 // NewCache creates a new cache instance.
 func NewCache(db *sql.DB, config CacheConfig) (*Cache, error) {
+	log := config.Logger
+	if log == nil {
+		log = slog.Default()
+	}
+
+	c := &Cache{
+		db:               db,
+		config:           config,
+		log:              log,
+		disabled:         config.DisableDiskCache,
+		evictionPressure: make(chan struct{}, 1),
+		evictionStop:     make(chan struct{}),
+		evictionDone:     make(chan struct{}),
+		metaCache:        make(map[VariantKey]variantMeta),
+	}
+
+	if c.disabled {
+		return c, nil
+	}
+
 	srcContent, err := NewContentStorage(filepath.Join(config.StateDir, "cache", "sources"))
 	if err != nil {
 		return nil, fmt.Errorf("failed to create source content storage: %w", err)
@@ -75,14 +115,11 @@ func NewCache(db *sql.DB, config CacheConfig) (*Cache, error) {
 		return nil, fmt.Errorf("failed to create source metadata storage: %w", err)
 	}
 
-	return &Cache{
+	c.srcContent = srcContent
-		db:          db,
+	c.variants = variants
-		srcContent:  srcContent,
+	c.srcMetadata = srcMetadata
-		variants:    variants,
+
-		srcMetadata: srcMetadata,
+	return c, nil
-		config:      config,
-		metaCache:   make(map[VariantKey]variantMeta),
-	}, nil
 }
 
 // LookupResult contains the result of a cache lookup.
@@ -94,12 +131,15 @@ type LookupResult struct {
 	CacheStatus CacheStatus
 }
 
-// Lookup checks if a processed variant exists on disk (no DB access for hits).
+// Lookup checks if a processed variant exists on disk. Hits touch the
-func (c *Cache) Lookup(_ context.Context, req *ImageRequest) (*LookupResult, error) {
+// variant's LRU timestamp; a disabled cache always misses.
+func (c *Cache) Lookup(ctx context.Context, req *ImageRequest) (*LookupResult, error) {
 	cacheKey := CacheKey(req)
 
 	// Check variant storage directly - no DB needed for cache hits
-	if c.variants.Exists(cacheKey) {
+	if !c.disabled && c.variants.Exists(cacheKey) {
+		c.touchVariant(ctx, cacheKey)
+
 		return &LookupResult{
 			Hit:         true,
 			CacheKey:    cacheKey,
@@ -114,18 +154,53 @@ func (c *Cache) Lookup(_ context.Context, req *ImageRequest) (*LookupResult, err
 	}, nil
 }
 
+// touchVariant updates the LRU timestamp of a variant, best-effort:
+// a failed touch only makes the entry look colder to eviction.
+func (c *Cache) touchVariant(ctx context.Context, cacheKey VariantKey) {
+	_, err := c.db.ExecContext(ctx, `
+		UPDATE variant_content SET last_accessed_at = CURRENT_TIMESTAMP
+		WHERE cache_key = ?
+	`, string(cacheKey))
+	if err != nil {
+		c.log.Debug("failed to touch variant LRU timestamp",
+			"cache_key", cacheKey, "error", err)
+	}
+}
+
+// touchSourceContent updates the LRU timestamp of a source content
+// blob, best-effort: a failed touch only makes the blob look colder.
+func (c *Cache) touchSourceContent(ctx context.Context, contentHash ContentHash) {
+	_, err := c.db.ExecContext(ctx, `
+		UPDATE source_content SET last_accessed_at = CURRENT_TIMESTAMP
+		WHERE content_hash = ?
+	`, string(contentHash))
+	if err != nil {
+		c.log.Debug("failed to touch source content LRU timestamp",
+			"content_hash", contentHash, "error", err)
+	}
+}
+
 // GetVariant returns a reader, size, and content type for a cached variant.
 func (c *Cache) GetVariant(cacheKey VariantKey) (io.ReadCloser, int64, string, error) {
+	if c.disabled {
+		return nil, 0, "", ErrNotFound
+	}
+
 	return c.variants.LoadWithMeta(cacheKey)
 }
 
-// StoreSource stores fetched source content and metadata.
+// StoreSource stores fetched source content and metadata. On a
+// disabled cache it is a no-op returning an empty hash.
 func (c *Cache) StoreSource(
 	ctx context.Context,
 	req *ImageRequest,
 	content io.Reader,
 	result *httpfetcher.FetchResult,
 ) (ContentHash, error) {
+	if c.disabled {
+		return "", nil
+	}
+
 	// Store content
 	contentHash, size, err := c.srcContent.Store(content)
 	if err != nil {
@@ -182,19 +257,52 @@ func (c *Cache) StoreSource(
 		_ = err
 	}
 
+	c.notifyWritePressure()
+
 	return contentHash, nil
 }
 
-// StoreVariant stores a processed variant by its cache key.
+// StoreVariant stores a processed variant by its cache key and records
+// it in the size accounting. On a disabled cache it is a no-op. The
+// accounting insert is best-effort (the startup reconciliation pass
+// adopts any variant file that misses its accounting row).
 func (c *Cache) StoreVariant(cacheKey VariantKey, content io.Reader, contentType string) error {
-	_, err := c.variants.Store(cacheKey, content, contentType)
+	if c.disabled {
+		return nil
+	}
 
-	return err
+	size, err := c.variants.Store(cacheKey, content, contentType)
+	if err != nil {
+		return err
+	}
+
+	_, err = c.db.Exec(`
+		INSERT INTO variant_content (cache_key, size_bytes, content_type)
+		VALUES (?, ?, ?)
+		ON CONFLICT(cache_key) DO UPDATE SET
+			size_bytes = excluded.size_bytes,
+			content_type = excluded.content_type,
+			last_accessed_at = CURRENT_TIMESTAMP
+	`, string(cacheKey), size, contentType)
+	if err != nil {
+		c.log.Warn("failed to record variant in size accounting",
+			"cache_key", cacheKey, "error", err)
+	}
+
+	c.notifyWritePressure()
+
+	return nil
 }
 
 // LookupSource checks if we have cached source content for a request.
-// Returns the content hash and content type if found, or empty values if not.
+// Returns the content hash and content type if found, or empty values
+// if not. Hits touch the blob's LRU timestamp; a disabled cache always
+// reports no cached source.
 func (c *Cache) LookupSource(ctx context.Context, req *ImageRequest) (ContentHash, string, error) {
+	if c.disabled {
+		return "", "", nil
+	}
+
 	var hashStr, contentType string
 
 	err := c.db.QueryRowContext(ctx, `
@@ -217,6 +325,8 @@ func (c *Cache) LookupSource(ctx context.Context, req *ImageRequest) (ContentHas
 		return "", "", nil
 	}
 
+	c.touchSourceContent(ctx, contentHash)
+
 	return contentHash, contentType, nil
 }
 
@@ -289,6 +399,10 @@ func (c *Cache) GetSourceMetadataID(ctx context.Context, req *ImageRequest) (int
 
 // GetSourceContent returns a reader for cached source content by its hash.
 func (c *Cache) GetSourceContent(contentHash ContentHash) (io.ReadCloser, error) {
+	if c.disabled {
+		return nil, ErrNotFound
+	}
+
 	return c.srcContent.Load(contentHash)
 }
 

internal/imgcache/eviction.go

@@ -2,6 +2,12 @@ package imgcache
 
 import (
 	"context"
+	"encoding/json"
+	"fmt"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"strings"
 	"time"
 )
 
@@ -10,32 +16,726 @@ import (
 // write-pressure wakeups triggered by stores.
 const DefaultEvictionInterval = 5 * time.Minute
 
+// evictionBatchSize is how many LRU candidates of each class (variants
+// and source blobs) one eviction pass fetches from the database.
+const evictionBatchSize = 100
+
+// staleTempFileAge is how old an orphaned temp file (left behind by a
+// crashed write) must be before reconciliation removes it. Fresh temp
+// files may still belong to an in-flight store.
+const staleTempFileAge = time.Hour
+
+// sqliteTimestampLayout matches SQLite's CURRENT_TIMESTAMP format, so
+// timestamps written by reconciliation order correctly against ones
+// written by the hot path.
+const sqliteTimestampLayout = "2006-01-02 15:04:05"
+
+// tempFilePrefix is the prefix os.CreateTemp uses for in-flight cache
+// writes (".tmp-*" patterns in the storage layer).
+const tempFilePrefix = ".tmp-"
+
+// variantMetaSuffix is the sidecar suffix VariantStorage writes next
+// to each variant file.
+const variantMetaSuffix = ".meta"
+
+// fallbackContentType is recorded when a reconciled variant file has
+// no readable .meta sidecar.
+const fallbackContentType = "application/octet-stream"
+
 // UsageBytes returns the total number of bytes of cache content
 // tracked in the database (source content blobs plus processed
 // variants). It never scans the cache directories.
-func (c *Cache) UsageBytes(_ context.Context) (int64, error) {
+func (c *Cache) UsageBytes(ctx context.Context) (int64, error) {
-	// Red phase: implementation follows the failing tests.
+	if c.disabled {
-	return 0, nil
+		return 0, nil
+	}
+
+	var total int64
+
+	err := c.db.QueryRowContext(ctx, `
+		SELECT (SELECT COALESCE(SUM(size_bytes), 0) FROM source_content)
+		     + (SELECT COALESCE(SUM(size_bytes), 0) FROM variant_content)
+	`).Scan(&total)
+	if err != nil {
+		return 0, fmt.Errorf("failed to compute cache usage: %w", err)
+	}
+
+	return total, nil
+}
+
+// evictionCandidate is one LRU eviction victim candidate: either a
+// processed variant (isVariant true, identified by cacheKey) or a
+// source content blob (identified by contentHash).
+type evictionCandidate struct {
+	isVariant      bool
+	cacheKey       VariantKey
+	contentHash    ContentHash
+	sizeBytes      int64
+	lastAccessedAt string
 }
 
 // EvictToLimit evicts least-recently-used cache entries until total
 // tracked usage is at or below the configured MaxBytes limit. It is a
-// no-op when the cache is disabled (MaxBytes zero).
+// no-op when the cache is disabled or no limit is configured.
-func (c *Cache) EvictToLimit(_ context.Context) error {
+func (c *Cache) EvictToLimit(ctx context.Context) error {
-	// Red phase: implementation follows the failing tests.
+	if c.disabled || c.config.MaxBytes <= 0 {
+		return nil
+	}
+
+	for {
+		usage, err := c.UsageBytes(ctx)
+		if err != nil {
+			return err
+		}
+
+		if usage <= c.config.MaxBytes {
+			return nil
+		}
+
+		freed, err := c.evictBatch(ctx, usage-c.config.MaxBytes)
+		if err != nil {
+			return err
+		}
+
+		if freed == 0 {
+			c.log.Warn("cache eviction made no progress",
+				"usage_bytes", usage,
+				"cache_max_bytes", c.config.MaxBytes,
+			)
+
+			return nil
+		}
+
+		c.log.Info("evicted cache content",
+			"freed_bytes", freed,
+			"usage_bytes", usage-freed,
+			"cache_max_bytes", c.config.MaxBytes,
+		)
+	}
+}
+
+// evictBatch fetches one batch of LRU candidates across variants and
+// source blobs and evicts them oldest-first until excessBytes are
+// freed or the batch is exhausted. It returns the bytes freed.
+func (c *Cache) evictBatch(ctx context.Context, excessBytes int64) (int64, error) {
+	candidates, err := c.evictionCandidates(ctx)
+	if err != nil {
+		return 0, err
+	}
+
+	var freed int64
+
+	for _, candidate := range candidates {
+		if freed >= excessBytes {
+			break
+		}
+
+		if err := c.evictCandidate(ctx, candidate); err != nil {
+			c.log.Warn("failed to evict cache entry",
+				"cache_key", candidate.cacheKey,
+				"content_hash", candidate.contentHash,
+				"error", err,
+			)
+
+			continue
+		}
+
+		freed += candidate.sizeBytes
+	}
+
+	return freed, nil
+}
+
+// evictCandidate removes a single eviction victim.
+func (c *Cache) evictCandidate(ctx context.Context, candidate evictionCandidate) error {
+	if candidate.isVariant {
+		return c.evictVariant(ctx, candidate.cacheKey)
+	}
+
+	return c.evictSourceBlob(ctx, candidate.contentHash)
+}
+
+// evictionCandidates returns up to evictionBatchSize variants and
+// evictionBatchSize source blobs, merged into a single list ordered by
+// last access time (oldest first).
+func (c *Cache) evictionCandidates(ctx context.Context) ([]evictionCandidate, error) {
+	variants, err := c.variantCandidates(ctx)
+	if err != nil {
+		return nil, err
+	}
+
+	sources, err := c.sourceCandidates(ctx)
+	if err != nil {
+		return nil, err
+	}
+
+	// Merge the two lists, each already sorted oldest-first. SQLite
+	// CURRENT_TIMESTAMP strings compare correctly lexicographically.
+	merged := make([]evictionCandidate, 0, len(variants)+len(sources))
+
+	for len(variants) > 0 && len(sources) > 0 {
+		if variants[0].lastAccessedAt <= sources[0].lastAccessedAt {
+			merged = append(merged, variants[0])
+			variants = variants[1:]
+		} else {
+			merged = append(merged, sources[0])
+			sources = sources[1:]
+		}
+	}
+
+	merged = append(merged, variants...)
+	merged = append(merged, sources...)
+
+	return merged, nil
+}
+
+// variantCandidates returns the least recently used variants.
+func (c *Cache) variantCandidates(ctx context.Context) ([]evictionCandidate, error) {
+	rows, err := c.db.QueryContext(ctx, `
+		SELECT cache_key, size_bytes, last_accessed_at
+		FROM variant_content
+		ORDER BY last_accessed_at ASC, cache_key ASC
+		LIMIT ?
+	`, evictionBatchSize)
+	if err != nil {
+		return nil, fmt.Errorf("failed to query variant eviction candidates: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var candidates []evictionCandidate
+
+	for rows.Next() {
+		candidate := evictionCandidate{isVariant: true}
+
+		var key string
+		if err := rows.Scan(&key, &candidate.sizeBytes, &candidate.lastAccessedAt); err != nil {
+			return nil, fmt.Errorf("failed to scan variant candidate: %w", err)
+		}
+
+		candidate.cacheKey = VariantKey(key)
+		candidates = append(candidates, candidate)
+	}
+
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("variant candidate iteration failed: %w", err)
+	}
+
+	return candidates, nil
+}
+
+// sourceCandidates returns the least recently used source blobs. Rows
+// written before the LRU column existed fall back to fetched_at.
+func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, error) {
+	rows, err := c.db.QueryContext(ctx, `
+		SELECT content_hash, size_bytes,
+		       COALESCE(last_accessed_at, fetched_at, '1970-01-01 00:00:00') AS lru
+		FROM source_content
+		ORDER BY lru ASC, content_hash ASC
+		LIMIT ?
+	`, evictionBatchSize)
+	if err != nil {
+		return nil, fmt.Errorf("failed to query source eviction candidates: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var candidates []evictionCandidate
+
+	for rows.Next() {
+		var candidate evictionCandidate
+
+		var hash string
+		if err := rows.Scan(&hash, &candidate.sizeBytes, &candidate.lastAccessedAt); err != nil {
+			return nil, fmt.Errorf("failed to scan source candidate: %w", err)
+		}
+
+		candidate.contentHash = ContentHash(hash)
+		candidates = append(candidates, candidate)
+	}
+
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("source candidate iteration failed: %w", err)
+	}
+
+	return candidates, nil
+}
+
+// evictVariant removes one variant: accounting row first, then the
+// content and .meta files, so the database never references a deleted
+// file.
+func (c *Cache) evictVariant(ctx context.Context, cacheKey VariantKey) error {
+	_, err := c.db.ExecContext(ctx,
+		`DELETE FROM variant_content WHERE cache_key = ?`, string(cacheKey))
+	if err != nil {
+		return fmt.Errorf("failed to delete variant accounting row: %w", err)
+	}
+
+	if err := c.variants.DeleteWithMeta(cacheKey); err != nil {
+		return err
+	}
+
 	return nil
 }
 
+// sourceReference identifies one source_metadata row's JSON sidecar.
+type sourceReference struct {
+	host     string
+	pathHash PathHash
+}
+
+// evictSourceBlob removes one source content blob. All source_metadata
+// rows referencing the blob are deleted together with its
+// source_content row in a single transaction BEFORE the file is
+// unlinked: a blob referenced by multiple source paths is only ever
+// removed together with all of its references, and database rows never
+// point at deleted files. The JSON metadata sidecars for the removed
+// rows are deleted afterwards.
+func (c *Cache) evictSourceBlob(ctx context.Context, contentHash ContentHash) error {
+	references, err := c.sourceReferences(ctx, contentHash)
+	if err != nil {
+		return err
+	}
+
+	tx, err := c.db.BeginTx(ctx, nil)
+	if err != nil {
+		return fmt.Errorf("failed to begin eviction transaction: %w", err)
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	if _, err := tx.ExecContext(ctx,
+		`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash)); err != nil {
+		return fmt.Errorf("failed to delete source metadata rows: %w", err)
+	}
+
+	if _, err := tx.ExecContext(ctx,
+		`DELETE FROM source_content WHERE content_hash = ?`, string(contentHash)); err != nil {
+		return fmt.Errorf("failed to delete source content row: %w", err)
+	}
+
+	if err := tx.Commit(); err != nil {
+		return fmt.Errorf("failed to commit eviction transaction: %w", err)
+	}
+
+	// Only after the rows are gone may the files be removed.
+	for _, reference := range references {
+		if err := c.srcMetadata.Delete(reference.host, reference.pathHash); err != nil {
+			c.log.Warn("failed to delete metadata sidecar",
+				"host", reference.host, "path_hash", reference.pathHash, "error", err)
+		}
+	}
+
+	if err := c.srcContent.Delete(contentHash); err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// sourceReferences lists the metadata sidecar locations of every
+// source_metadata row referencing the given blob.
+func (c *Cache) sourceReferences(
+	ctx context.Context, contentHash ContentHash,
+) ([]sourceReference, error) {
+	rows, err := c.db.QueryContext(ctx, `
+		SELECT source_host, path_hash FROM source_metadata WHERE content_hash = ?
+	`, string(contentHash))
+	if err != nil {
+		return nil, fmt.Errorf("failed to query source references: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var references []sourceReference
+
+	for rows.Next() {
+		var reference sourceReference
+
+		var pathHash string
+		if err := rows.Scan(&reference.host, &pathHash); err != nil {
+			return nil, fmt.Errorf("failed to scan source reference: %w", err)
+		}
+
+		reference.pathHash = PathHash(pathHash)
+		references = append(references, reference)
+	}
+
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("source reference iteration failed: %w", err)
+	}
+
+	return references, nil
+}
+
+// notifyWritePressure wakes the background evictor after a store, so
+// eviction under write pressure happens promptly without blocking the
+// storing request. The notification channel has capacity one and drops
+// when a wakeup is already pending.
+func (c *Cache) notifyWritePressure() {
+	if c.disabled || c.config.MaxBytes <= 0 {
+		return
+	}
+
+	select {
+	case c.evictionPressure <- struct{}{}:
+	default:
+	}
+}
+
 // StartEviction launches the background eviction goroutine, which
 // reconciles the database accounting with the cache directories once
 // at startup and then evicts to the configured limit on the given
-// periodic interval and on write-pressure notifications.
+// periodic interval and on write-pressure notifications. It is a
-func (c *Cache) StartEviction(_ time.Duration) {
+// no-op on a disabled cache or when already started.
-	// Red phase: implementation follows the failing tests.
+func (c *Cache) StartEviction(interval time.Duration) {
+	if c.disabled || c.evictionStarted {
+		return
+	}
+
+	c.evictionStarted = true
+
+	go c.evictionLoop(interval)
 }
 
 // StopEviction stops the background eviction goroutine and waits for
-// it to exit. It is safe to call when eviction was never started.
+// it to exit. It is safe to call when eviction was never started, and
+// safe to call more than once.
 func (c *Cache) StopEviction() {
-	// Red phase: implementation follows the failing tests.
+	if !c.evictionStarted {
+		return
+	}
+
+	c.evictionStopOnce.Do(func() {
+		close(c.evictionStop)
+		<-c.evictionDone
+	})
+}
+
+// evictionLoop is the body of the background eviction goroutine.
+func (c *Cache) evictionLoop(interval time.Duration) {
+	defer close(c.evictionDone)
+
+	ctx := context.Background()
+
+	if err := c.reconcileAccounting(ctx); err != nil {
+		c.log.Warn("cache accounting reconciliation failed", "error", err)
+	}
+
+	c.runEvictionPass(ctx)
+
+	ticker := time.NewTicker(interval)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-c.evictionStop:
+			return
+		case <-ticker.C:
+		case <-c.evictionPressure:
+		}
+
+		c.runEvictionPass(ctx)
+	}
+}
+
+// runEvictionPass runs one eviction pass, logging failures instead of
+// propagating them (the loop must keep running).
+func (c *Cache) runEvictionPass(ctx context.Context) {
+	if err := c.EvictToLimit(ctx); err != nil {
+		c.log.Warn("cache eviction pass failed", "error", err)
+	}
+}
+
+// reconcileAccounting synchronizes the database size accounting with
+// the actual contents of the cache directories. It runs once when the
+// background evictor starts, off the request hot path: it adopts
+// variant files that predate the accounting table, drops accounting
+// rows whose files are missing, removes source blob files the database
+// does not know (and rows whose files are gone), and sweeps stale temp
+// files left behind by crashed writes.
+func (c *Cache) reconcileAccounting(ctx context.Context) error {
+	if c.disabled {
+		return nil
+	}
+
+	if err := c.reconcileVariantFiles(ctx); err != nil {
+		return err
+	}
+
+	if err := c.reconcileVariantRows(ctx); err != nil {
+		return err
+	}
+
+	if err := c.reconcileSourceFiles(ctx); err != nil {
+		return err
+	}
+
+	if err := c.reconcileSourceRows(ctx); err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// reconcileVariantFiles walks the variant storage directory, adopting
+// files without accounting rows and sweeping stale temp files.
+func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
+	return filepath.WalkDir(c.variants.baseDir, func(path string, entry fs.DirEntry, err error) error {
+		if err != nil || entry.IsDir() {
+			return err
+		}
+
+		name := entry.Name()
+
+		if strings.HasPrefix(name, tempFilePrefix) {
+			c.sweepStaleTempFile(path, entry)
+
+			return nil
+		}
+
+		if strings.HasSuffix(name, variantMetaSuffix) {
+			return nil
+		}
+
+		return c.adoptVariantFile(ctx, path, entry, VariantKey(name))
+	})
+}
+
+// adoptVariantFile inserts an accounting row for a variant file that
+// has none, using the file's size and modification time.
+func (c *Cache) adoptVariantFile(
+	ctx context.Context, path string, entry fs.DirEntry, cacheKey VariantKey,
+) error {
+	var rowExists int
+
+	err := c.db.QueryRowContext(ctx,
+		`SELECT COUNT(*) FROM variant_content WHERE cache_key = ?`, string(cacheKey),
+	).Scan(&rowExists)
+	if err != nil {
+		return fmt.Errorf("failed to check variant accounting row: %w", err)
+	}
+
+	if rowExists > 0 {
+		return nil
+	}
+
+	info, err := entry.Info()
+	if err != nil {
+		return fmt.Errorf("failed to stat variant file: %w", err)
+	}
+
+	modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
+	contentType := c.variantContentTypeFromSidecar(path)
+
+	_, err = c.db.ExecContext(ctx, `
+		INSERT INTO variant_content
+			(cache_key, size_bytes, content_type, created_at, last_accessed_at)
+		VALUES (?, ?, ?, ?, ?)
+	`, string(cacheKey), info.Size(), contentType, modTime, modTime)
+	if err != nil {
+		return fmt.Errorf("failed to adopt variant file into accounting: %w", err)
+	}
+
+	c.log.Info("adopted untracked variant file into size accounting",
+		"cache_key", cacheKey, "size_bytes", info.Size())
+
+	return nil
+}
+
+// variantContentTypeFromSidecar reads the content type from a variant
+// .meta sidecar, falling back to application/octet-stream.
+func (c *Cache) variantContentTypeFromSidecar(variantPath string) string {
+	metaData, err := os.ReadFile(variantPath + variantMetaSuffix) //nolint:gosec // path from cache walk
+	if err != nil {
+		return fallbackContentType
+	}
+
+	var meta VariantMeta
+	if json.Unmarshal(metaData, &meta) != nil || meta.ContentType == "" {
+		return fallbackContentType
+	}
+
+	return meta.ContentType
+}
+
+// reconcileVariantRows drops accounting rows whose variant files are
+// missing, so the database never references deleted content.
+func (c *Cache) reconcileVariantRows(ctx context.Context) error {
+	keys, err := c.allVariantKeys(ctx)
+	if err != nil {
+		return err
+	}
+
+	for _, key := range keys {
+		if c.variants.Exists(key) {
+			continue
+		}
+
+		if _, err := c.db.ExecContext(ctx,
+			`DELETE FROM variant_content WHERE cache_key = ?`, string(key)); err != nil {
+			return fmt.Errorf("failed to drop stale variant accounting row: %w", err)
+		}
+
+		c.log.Info("dropped accounting row for missing variant file", "cache_key", key)
+	}
+
+	return nil
+}
+
+// allVariantKeys returns every tracked variant cache key.
+func (c *Cache) allVariantKeys(ctx context.Context) ([]VariantKey, error) {
+	rows, err := c.db.QueryContext(ctx, `SELECT cache_key FROM variant_content`)
+	if err != nil {
+		return nil, fmt.Errorf("failed to query variant keys: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var keys []VariantKey
+
+	for rows.Next() {
+		var key string
+		if err := rows.Scan(&key); err != nil {
+			return nil, fmt.Errorf("failed to scan variant key: %w", err)
+		}
+
+		keys = append(keys, VariantKey(key))
+	}
+
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("variant key iteration failed: %w", err)
+	}
+
+	return keys, nil
+}
+
+// reconcileSourceFiles walks the source content directory, removing
+// blob files the database does not track (they are unreachable: source
+// lookups always go through source_metadata) and sweeping stale temp
+// files.
+func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
+	return filepath.WalkDir(c.srcContent.baseDir, func(path string, entry fs.DirEntry, err error) error {
+		if err != nil || entry.IsDir() {
+			return err
+		}
+
+		name := entry.Name()
+
+		if strings.HasPrefix(name, tempFilePrefix) {
+			c.sweepStaleTempFile(path, entry)
+
+			return nil
+		}
+
+		return c.removeUntrackedSourceFile(ctx, path, ContentHash(name))
+	})
+}
+
+// removeUntrackedSourceFile deletes a source blob file that has no
+// source_content row. Any source_metadata rows referencing the hash
+// are removed first so no row ever points at a deleted file.
+func (c *Cache) removeUntrackedSourceFile(
+	ctx context.Context, path string, contentHash ContentHash,
+) error {
+	var rowExists int
+
+	err := c.db.QueryRowContext(ctx,
+		`SELECT COUNT(*) FROM source_content WHERE content_hash = ?`, string(contentHash),
+	).Scan(&rowExists)
+	if err != nil {
+		return fmt.Errorf("failed to check source content row: %w", err)
+	}
+
+	if rowExists > 0 {
+		return nil
+	}
+
+	if _, err := c.db.ExecContext(ctx,
+		`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash)); err != nil {
+		return fmt.Errorf("failed to delete metadata rows for untracked blob: %w", err)
+	}
+
+	//nolint:gosec // G703: path comes from walking our own cache directory
+	if err := os.Remove(path); err != nil && !os.IsNotExist(err) {
+		return fmt.Errorf("failed to remove untracked source file: %w", err)
+	}
+
+	c.log.Info("removed untracked source content file", "content_hash", contentHash)
+
+	return nil
+}
+
+// reconcileSourceRows removes source_content rows (and their metadata
+// references and sidecars) whose blob files are missing on disk.
+func (c *Cache) reconcileSourceRows(ctx context.Context) error {
+	hashes, err := c.allSourceContentHashes(ctx)
+	if err != nil {
+		return err
+	}
+
+	for _, hash := range hashes {
+		if c.srcContent.Exists(hash) {
+			continue
+		}
+
+		// The blob file is already gone; evictSourceBlob removes the
+		// rows and sidecars and tolerates the missing file.
+		if err := c.evictSourceBlob(ctx, hash); err != nil {
+			return err
+		}
+
+		c.log.Info("dropped rows for missing source content file", "content_hash", hash)
+	}
+
+	return nil
+}
+
+// allSourceContentHashes returns every tracked source content hash.
+func (c *Cache) allSourceContentHashes(ctx context.Context) ([]ContentHash, error) {
+	rows, err := c.db.QueryContext(ctx, `SELECT content_hash FROM source_content`)
+	if err != nil {
+		return nil, fmt.Errorf("failed to query source content hashes: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var hashes []ContentHash
+
+	for rows.Next() {
+		var hash string
+		if err := rows.Scan(&hash); err != nil {
+			return nil, fmt.Errorf("failed to scan content hash: %w", err)
+		}
+
+		hashes = append(hashes, ContentHash(hash))
+	}
+
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("content hash iteration failed: %w", err)
+	}
+
+	return hashes, nil
+}
+
+// sweepStaleTempFile removes a temp file left behind by a crashed
+// write once it is old enough that no in-flight store can own it.
+func (c *Cache) sweepStaleTempFile(path string, entry fs.DirEntry) {
+	info, err := entry.Info()
+	if err != nil {
+		return
+	}
+
+	if time.Since(info.ModTime()) < staleTempFileAge {
+		return
+	}
+
+	//nolint:gosec // G703: path comes from walking our own cache directory
+	if err := os.Remove(path); err != nil && !os.IsNotExist(err) {
+		c.log.Warn("failed to remove stale temp file", "path", path, "error", err)
+
+		return
+	}
+
+	c.log.Info("removed stale temp file", "path", path)
 }

internal/imgcache/eviction_test.go

@@ -50,11 +50,16 @@ func newEvictionTestCache(t *testing.T, maxBytes int64) (*Cache, string) {
 	tmpDir := t.TempDir()
 	db := evictionTestDB(t)
 
+	// maxBytes zero mirrors the production mapping of
+	// cache_max_bytes: 0 (handlers sets DisableDiskCache); at the
+	// CacheConfig layer itself a zero MaxBytes means "no limit" for
+	// backwards compatibility with existing fixtures.
 	cache, err := NewCache(db, CacheConfig{
-		StateDir:    tmpDir,
+		StateDir:         tmpDir,
-		CacheTTL:    time.Hour,
+		CacheTTL:         time.Hour,
-		NegativeTTL: 5 * time.Minute,
+		NegativeTTL:      5 * time.Minute,
-		MaxBytes:    maxBytes,
+		MaxBytes:         maxBytes,
+		DisableDiskCache: maxBytes == 0,
 	})
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)

internal/imgcache/storage.go

@@ -493,6 +493,24 @@ func (s *VariantStorage) Delete(key VariantKey) error {
 	return nil
 }
 
+// DeleteWithMeta removes the content at the given key together with
+// its .meta sidecar file. A missing file is not an error.
+func (s *VariantStorage) DeleteWithMeta(key VariantKey) error {
+	if err := s.Delete(key); err != nil {
+		return err
+	}
+
+	metaPath := s.keyToPath(key) + ".meta"
+
+	//nolint:gosec // G703: path derived from cache key
+	err := os.Remove(metaPath)
+	if err != nil && !os.IsNotExist(err) {
+		return fmt.Errorf("failed to delete variant metadata: %w", err)
+	}
+
+	return nil
+}
+
 // keyToPath converts a key to a file path: <basedir>/<ab>/<cd>/<key>
 func (s *VariantStorage) keyToPath(key VariantKey) string {
 	k := string(key)