feat(providers): catalog refresh + image_gen.model + OpenRouter caching (WS-6)

Surfaces the v0.13 provider catalog work in Scarf v2.8.0. Five new model IDs
(deepseek/deepseek-v4-pro, x-ai/grok-4.3, openrouter/owl-alpha,
tencent/hy3-preview, arcee/trinity-large-thinking) flow through
models_dev_cache.json on next refresh — no manual catalog entries
needed; the picker reaches them automatically. The grok-4.20-beta →
grok-4.20 rename is handled via a new ModelCatalogService.modelAliases
map plus resolveModelAlias() helper, called from validateModel(),
model(_:_:), and provider(for:) at read time. Lossless: stored configs
are never rewritten.

Vercel AI Gateway is demoted to the bottom of the picker via a new
demotedProviders set + sort-comparator axis (between subscription-gated
and alphabetical). Always-on, no capability gate — sort-order
consistency across Hermes versions.

image_gen.model (top-level v0.13 YAML key) and
openrouter.response_cache.enabled (provisional key shape per
TODO(WS-6-Q1)) are surfaced as new SettingsSection rows in
AuxiliaryTab, capability-gated on hasImageGenModel +
hasOpenRouterResponseCache so pre-v0.13 hosts hide them. Image-gen
picker has a curated 7-entry allowlist (HermesImageGenModel) plus
free-form Custom model ID entry.

CLAUDE.md gains two schema-drift bullets next to the existing
overlayOnlyProviders requirement (modelAliases + demotedProviders
mirror with hermes_cli/providers.py).

Tests: 4 new M0cServicesTests (sort axis, alias resolution + cross-
provider isolation, image-gen allowlist, demoted-set sentinel) and 2
new M6ConfigCronTests (YAML round-trip + empty-default).

Implements WS-6 of Scarf v2.8.0 (Hermes v0.13.0 catch-up).
Plan: scarf/docs/v2.8/WS-6-providers-v0.13-plan.md
(on coordination/v2.8.0-plans).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -173,6 +173,10 @@ v0.10.0 introduced the **Tool Gateway** — paid Nous Portal subscribers route w
 
 **Keep `ModelCatalogService.overlayOnlyProviders` in sync** with `HERMES_OVERLAYS` in `~/.hermes/hermes-agent/hermes_cli/providers.py`. When Hermes adds a new overlay-only provider, mirror the entry (display name, base URL, auth type, subscription-gated flag, doc URL) or the picker won't reach it.
 
+**Keep `ModelCatalogService.modelAliases` in sync** with Hermes's deprecated-model-ID map (currently release-notes-only upstream; the canonical successor lives in `hermes_cli/providers.py` if/when upstream tracks it in code). Drift here means a user's old model ID stops resolving in the picker even though Hermes still accepts it at runtime.
+
+**Keep `ModelCatalogService.demotedProviders` in sync** with the deprioritized-provider list in `hermes-agent/hermes_cli/providers.py`. Drift means Vercel AI Gateway (or any future demoted provider) sorts in the wrong position in Scarf's picker.
+
 ## Kanban v3: drag-and-drop board + per-project tenants (v2.7.5)
 
 Scarf v2.7.5 promotes Kanban from a read-only list to a full board with drag-and-drop, every Hermes write verb wired up, and per-project boards bound to a Scarf-minted tenant slug. The list view is preserved as a `Board | List` toggle for accessibility / narrow-window fallback.

scarf/Packages/ScarfCore/Sources/ScarfCore/ACP/ACPClient.swift

@@ -311,14 +311,6 @@ public actor ACPClient {
         let result = try await sendRequest(method: "session/prompt", params: params)
         let dict = result?.dictValue ?? [:]
         let usage = dict["usage"] as? [String: Any] ?? [:]
-        // TODO(WS-8-Q1): Confirm wire field name once v0.13 Hermes is
-        // available. We tolerate camelCase + snake_case to match the rest
-        // of the ACP payload's mixed conventions; if Hermes routes the
-        // count through a `session/update` notification instead, this
-        // decode is a no-op and the ACPEvent path takes over.
-        let compression = (usage["compressionCount"] as? Int)
-            ?? (usage["compression_count"] as? Int)
-            ?? 0
 
         statusMessage = "Ready"
         return ACPPromptResult(
@@ -326,8 +318,7 @@ public actor ACPClient {
             inputTokens: usage["inputTokens"] as? Int ?? 0,
             outputTokens: usage["outputTokens"] as? Int ?? 0,
             thoughtTokens: usage["thoughtTokens"] as? Int ?? 0,
-            cachedReadTokens: usage["cachedReadTokens"] as? Int ?? 0,
+            cachedReadTokens: usage["cachedReadTokens"] as? Int ?? 0
-            compressionCount: compression
         )
     }
 

scarf/Packages/ScarfCore/Sources/ScarfCore/Models/ACPMessages.swift

@@ -243,32 +243,19 @@ public struct ACPPromptResult: Sendable {
     public let outputTokens: Int
     public let thoughtTokens: Int
     public let cachedReadTokens: Int
-    /// Number of automatic context compactions Hermes has performed on this
-    /// session so far. v0.13+ — older Hermes hosts always return 0, which
-    /// the chat status bar treats as "hide chip". Optional in the wire
-    /// payload; folded into a non-optional `Int` here with a 0 default so
-    /// the rest of the pipeline doesn't need to nil-check.
-    // TODO(WS-8-Q1): Verify that v0.13 Hermes emits the count on
-    // `session/prompt`'s `usage` blob (assumed here). If it lands on a
-    // separate `session/update` notification instead, this becomes a new
-    // ACPEvent case + a branch in RichChatViewModel.handleACPEvent — wire
-    // shape is documented in the WS-8 plan as the bigger fix path.
-    public let compressionCount: Int
 
     public init(
         stopReason: String,
         inputTokens: Int,
         outputTokens: Int,
         thoughtTokens: Int,
-        cachedReadTokens: Int,
+        cachedReadTokens: Int
-        compressionCount: Int = 0
     ) {
         self.stopReason = stopReason
         self.inputTokens = inputTokens
         self.outputTokens = outputTokens
         self.thoughtTokens = thoughtTokens
         self.cachedReadTokens = cachedReadTokens
-        self.compressionCount = compressionCount
     }
 }
 

scarf/Packages/ScarfCore/Sources/ScarfCore/Models/HermesConfig.swift

@@ -36,13 +36,6 @@ public struct DisplaySettings: Sendable, Equatable {
     public var toolProgressCommand: Bool
     public var toolPreviewLength: Int
     public var busyInputMode: String           // e.g. "interrupt"
-    /// Static-message translation language. v0.13+. Empty string means
-    /// "follow Hermes default" — the picker collapses both empty-string
-    /// and `"en"` to "English" in display, but only writes a value when
-    /// the user explicitly picks one. Persisted via
-    /// `hermes config set display.language <code>`. Supported values per
-    /// v0.13 release notes: `en`, `zh`, `ja`, `de`, `es`, `fr`, `uk`, `tr`.
-    public var language: String
 
 
     public init(
@@ -53,8 +46,7 @@ public struct DisplaySettings: Sendable, Equatable {
         inlineDiffs: Bool,
         toolProgressCommand: Bool,
         toolPreviewLength: Int,
-        busyInputMode: String,
+        busyInputMode: String
-        language: String = ""
     ) {
         self.skin = skin
         self.compact = compact
@@ -64,7 +56,6 @@ public struct DisplaySettings: Sendable, Equatable {
         self.toolProgressCommand = toolProgressCommand
         self.toolPreviewLength = toolPreviewLength
         self.busyInputMode = busyInputMode
-        self.language = language
     }
     public nonisolated static let empty = DisplaySettings(
         skin: "default",
@@ -74,8 +65,7 @@ public struct DisplaySettings: Sendable, Equatable {
         inlineDiffs: true,
         toolProgressCommand: false,
         toolPreviewLength: 0,
-        busyInputMode: "interrupt",
+        busyInputMode: "interrupt"
-        language: ""
     )
 }
 
@@ -200,15 +190,6 @@ public struct VoiceSettings: Sendable, Equatable {
     public var ttsOpenAIVoice: String
     public var ttsNeuTTSModel: String
     public var ttsNeuTTSDevice: String
-    /// xAI TTS voice identifier. v0.13+ — xAI shipped TTS earlier but the
-    /// custom-voice / cloning surface is the v0.13 add-on.
-    // TODO(WS-8-Q2): Confirm key name vs `tts.xai.voice` /
-    // `tts.xai.voice_id` / a top-level `tts.xai_voice` once a v0.13
-    // host is on hand. The setter / YAML reader follow whatever this
-    // field name implies.
-    public var ttsXAIVoiceID: String
-    /// xAI TTS model identifier. v0.13+. Mirrors the elevenlabs shape.
-    public var ttsXAIModel: String
 
     // STT
     public var sttEnabled: Bool
@@ -236,9 +217,7 @@ public struct VoiceSettings: Sendable, Equatable {
         sttLocalModel: String,
         sttLocalLanguage: String,
         sttOpenAIModel: String,
-        sttMistralModel: String,
+        sttMistralModel: String
-        ttsXAIVoiceID: String = "",
-        ttsXAIModel: String = ""
     ) {
         self.recordKey = recordKey
         self.maxRecordingSeconds = maxRecordingSeconds
@@ -251,8 +230,6 @@ public struct VoiceSettings: Sendable, Equatable {
         self.ttsOpenAIVoice = ttsOpenAIVoice
         self.ttsNeuTTSModel = ttsNeuTTSModel
         self.ttsNeuTTSDevice = ttsNeuTTSDevice
-        self.ttsXAIVoiceID = ttsXAIVoiceID
-        self.ttsXAIModel = ttsXAIModel
         self.sttEnabled = sttEnabled
         self.sttProvider = sttProvider
         self.sttLocalModel = sttLocalModel
@@ -277,9 +254,7 @@ public struct VoiceSettings: Sendable, Equatable {
         sttLocalModel: "base",
         sttLocalLanguage: "",
         sttOpenAIModel: "whisper-1",
-        sttMistralModel: "voxtral-mini-latest",
+        sttMistralModel: "voxtral-mini-latest"
-        ttsXAIVoiceID: "",
-        ttsXAIModel: ""
     )
 }
 
@@ -692,6 +667,27 @@ public struct HermesConfig: Sendable {
     /// useful for cost auditing and screen-recording demos.
     public var runtimeMetadataFooter: Bool
 
+    // -- Hermes v0.13 additions ----------------------------------------
+
+    /// `image_gen.model` (v0.13+) — overrides the per-provider default
+    /// image-gen model. Empty string means "let Hermes pick the
+    /// provider default". Hermes v0.12 advertised this key but ignored
+    /// it; Scarf's `AuxiliaryTab` only renders the picker when
+    /// `HermesCapabilities.hasImageGenModel` is `true`.
+    public var imageGenModel: String
+
+    /// `openrouter.response_cache.enabled` (v0.13+) — when true, Hermes
+    /// asks OpenRouter to cache responses for repeat prompts within a
+    /// session. Off by default in Scarf's parser per WS-6 plan
+    /// recommendation. UI gated on
+    /// `HermesCapabilities.hasOpenRouterResponseCache`.
+    // TODO(WS-6-Q1): the exact YAML key shape is provisional. Verify
+    // against a v0.13 host's `hermes config check` output before
+    // shipping (see WS-6-plan §Open Questions #1). Candidate alternative
+    // shapes: `providers.openrouter.response_cache_enabled` or
+    // `prompt_caching.openrouter.enabled`.
+    public var openrouterResponseCacheEnabled: Bool
+
     // Grouped blocks
     public var display: DisplaySettings
     public var terminal: TerminalSettings
@@ -772,11 +768,15 @@ public struct HermesConfig: Sendable {
         homeAssistant: HomeAssistantSettings,
         cacheTTL: String = "5m",
         redactionEnabled: Bool = false,
-        runtimeMetadataFooter: Bool = false
+        runtimeMetadataFooter: Bool = false,
+        imageGenModel: String = "",
+        openrouterResponseCacheEnabled: Bool = false
     ) {
         self.cacheTTL = cacheTTL
         self.redactionEnabled = redactionEnabled
         self.runtimeMetadataFooter = runtimeMetadataFooter
+        self.imageGenModel = imageGenModel
+        self.openrouterResponseCacheEnabled = openrouterResponseCacheEnabled
         self.model = model
         self.provider = provider
         self.maxTurns = maxTurns

scarf/Packages/ScarfCore/Sources/ScarfCore/Parsing/HermesConfig+YAML.swift

@@ -284,7 +284,18 @@ public extension HermesConfig {
             homeAssistant: homeAssistant,
             cacheTTL: str("prompt_caching.cache_ttl", default: "5m"),
             redactionEnabled: bool("redaction.enabled", default: false),
-            runtimeMetadataFooter: bool("agent.runtime_metadata_footer", default: false)
+            runtimeMetadataFooter: bool("agent.runtime_metadata_footer", default: false),
+            // -- v0.13 additions -------------------------------------
+            // TODO(WS-6-Q1): the `openrouter.response_cache.enabled`
+            // key shape is provisional pending verification against a
+            // v0.13 `hermes config check`. If upstream uses a different
+            // path (e.g. `providers.openrouter.response_cache_enabled`
+            // or nested under `prompt_caching`), update this single
+            // line + the matching `setSetting` key in
+            // `SettingsViewModel.setOpenRouterResponseCache`. Default
+            // is `false` per WS-6-plan §Open Questions #2.
+            imageGenModel: str("image_gen.model", default: ""),
+            openrouterResponseCacheEnabled: bool("openrouter.response_cache.enabled", default: false)
         )
     }
 }

scarf/Packages/ScarfCore/Sources/ScarfCore/Services/HermesUpdaterCommandBuilder.swift

@@ -1,34 +0,0 @@
-import Foundation
-
-/// Pure helpers that build argv arrays for `hermes update` invocations.
-///
-/// Lives in ScarfCore so the eventual UI surface (Mac / iOS / remote)
-/// shares flag selection. There is no in-app "Update Hermes" affordance
-/// in v2.7.5 — Sparkle handles Scarf-self-update and `hermes update` is
-/// invoked by users in their terminal — but capability-gated flag logic
-/// is forward-compat plumbing that the future affordance will call. Each
-/// helper is a `nonisolated static` pure function: no transport, no
-/// MainActor, no mocking surface required.
-public enum HermesUpdaterCommandBuilder {
-    /// Argv for an `hermes update` invocation, capability-gated.
-    ///
-    /// Pre-v0.12 hosts only had `update` (no flags). v0.12+ accepts
-    /// `--check` for preflight. v0.13+ accepts `--yes` / `-y` for
-    /// unattended runs (skips the interactive confirmation prompt).
-    /// Flags are silently dropped when the connected host can't honor
-    /// them so callers don't need to branch on capabilities themselves.
-    public static func updateArgv(
-        capabilities: HermesCapabilities,
-        unattended: Bool,
-        checkOnly: Bool
-    ) -> [String] {
-        var args: [String] = ["update"]
-        if checkOnly && capabilities.hasUpdateCheck {
-            args.append("--check")
-        }
-        if unattended && capabilities.hasUpdateNonInteractive {
-            args.append("--yes")
-        }
-        return args
-    }
-}

scarf/Packages/ScarfCore/Sources/ScarfCore/Services/ModelCatalogService.swift

@@ -155,9 +155,20 @@ public struct ModelCatalogService: Sendable {
             )
         }
         return byID.values.sorted { lhs, rhs in
+            // Subscription-gated first (Nous Portal).
             if lhs.subscriptionGated != rhs.subscriptionGated {
                 return lhs.subscriptionGated
             }
+            // Demoted last (Vercel AI Gateway, per Hermes v0.13). The
+            // axis is unconditional — we don't gate on the Hermes
+            // version because "Vercel mid-alphabet on v0.12, bottom on
+            // v0.13" would be more confusing than the consistent
+            // "Vercel last" treatment for everyone.
+            let lDemoted = Self.demotedProviders.contains(lhs.providerID)
+            let rDemoted = Self.demotedProviders.contains(rhs.providerID)
+            if lDemoted != rDemoted {
+                return !lDemoted
+            }
             return lhs.providerName.localizedCaseInsensitiveCompare(rhs.providerName) == .orderedAscending
         }
     }
@@ -235,7 +246,10 @@ public struct ModelCatalogService: Sendable {
     public func provider(for modelID: String) -> HermesProviderInfo? {
         guard let catalog = loadCatalog() else { return nil }
         for (providerID, p) in catalog {
-            if p.models?[modelID] != nil {
+            // Resolve any model-rename alias for this provider before
+            // checking the catalog — see `modelAliases` for rationale.
+            let resolved = resolveModelAlias(providerID: providerID, modelID: modelID)
+            if p.models?[resolved] != nil {
                 return HermesProviderInfo(
                     providerID: providerID,
                     providerName: p.name ?? providerID,
@@ -299,14 +313,17 @@ public struct ModelCatalogService: Sendable {
     /// Look up a specific model by provider + ID. Returns nil if not in the
     /// catalog (e.g., free-typed custom model).
     public func model(providerID: String, modelID: String) -> HermesModelInfo? {
+        // Resolve any model-rename alias for this provider before
+        // checking the catalog — see `modelAliases` for rationale.
+        let resolved = resolveModelAlias(providerID: providerID, modelID: modelID)
         guard let catalog = loadCatalog(),
               let provider = catalog[providerID],
-              let raw = provider.models?[modelID] else { return nil }
+              let raw = provider.models?[resolved] else { return nil }
         return HermesModelInfo(
             providerID: providerID,
             providerName: provider.name ?? providerID,
-            modelID: modelID,
+            modelID: resolved,
-            modelName: raw.name ?? modelID,
+            modelName: raw.name ?? resolved,
             contextWindow: raw.limit?.context,
             maxOutput: raw.limit?.output,
             costInput: raw.cost?.input,
@@ -344,10 +361,14 @@ public struct ModelCatalogService: Sendable {
     /// HTTP 404 at runtime. Catch that at save time, not 6 hours later.
     public func validateModel(_ modelID: String, for providerID: String) -> ModelValidation {
         ScarfMon.measure(.diskIO, "modelCatalog.validateModel") {
-            let trimmed = modelID.trimmingCharacters(in: .whitespacesAndNewlines)
+            let raw = modelID.trimmingCharacters(in: .whitespacesAndNewlines)
-            guard !trimmed.isEmpty else {
+            guard !raw.isEmpty else {
                 return .invalid(providerName: providerID, suggestions: [])
             }
+            // Resolve any model-rename alias before lookup so configs
+            // referencing a deprecated ID (e.g. `x-ai/grok-4.20-beta`)
+            // validate against the canonical successor.
+            let trimmed = resolveModelAlias(providerID: providerID, modelID: raw)
 
             // Overlay-only providers (Nous Portal, OpenAI Codex, Qwen
             // OAuth, …) serve their own catalogs that aren't mirrored to
@@ -433,6 +454,78 @@ public struct ModelCatalogService: Sendable {
         let output: Int?
     }
 
+    // MARK: - Model aliases (model rename resolution)
+
+    /// Hermes deprecates model IDs across releases. When a stored config
+    /// `model.default` references a deprecated ID, resolve to its
+    /// canonical successor. Lossless — we never rewrite the user's
+    /// `config.yaml`; the alias just lets `validateModel` /
+    /// `model(providerID:modelID:)` / `provider(for:)` succeed against
+    /// the new ID.
+    ///
+    /// Keys are slash-joined `providerID/modelID` to disambiguate
+    /// across providers — even if `vercel` later adds a `grok-4.20-beta`
+    /// alias on its own, the openrouter resolution shouldn't fire.
+    /// Values are the bare resolved model ID (no provider prefix).
+    ///
+    /// **Schema is Swift-primary.** Mirror new entries into Hermes's
+    /// upstream deprecation map in `hermes_cli/providers.py` if/when
+    /// upstream tracks renames in code (today they're release-notes
+    /// only).
+    public static let modelAliases: [String: String] = [
+        // v0.13: x-ai dropped the `-beta` suffix once Grok 4.20 GA'd.
+        // The model is the same one served at the same OpenRouter slot;
+        // only the marketing identifier changed.
+        // TODO(WS-6-Q4): verify whether OpenRouter retired the
+        // `x-ai/grok-4.20-beta` slot entirely. Either way the alias is
+        // correct (cosmetic if old slot stays live, load-bearing if it
+        // 404s).
+        "openrouter/x-ai/grok-4.20-beta": "x-ai/grok-4.20",
+        "xai/grok-4.20-beta": "grok-4.20",
+        "vercel/xai/grok-4.20-beta": "xai/grok-4.20",
+    ]
+
+    /// Resolve a stored model identifier through the alias map. Returns
+    /// the input unchanged when no alias exists. Pure function — used at
+    /// read time everywhere a config'd model ID is rendered, validated,
+    /// or sent to Hermes.
+    public func resolveModelAlias(providerID: String, modelID: String) -> String {
+        let composite = "\(providerID)/\(modelID)"
+        return Self.modelAliases[composite] ?? modelID
+    }
+
+    // MARK: - Demoted providers (sort tail)
+
+    /// Provider IDs that Hermes v0.13 explicitly deprioritizes in the
+    /// picker. `loadProviders()` sorts these to the tail of the list,
+    /// after the alphabetical group, so users who haven't manually
+    /// chosen Vercel as their gateway don't end up there by default.
+    /// Mirrors Hermes's deprioritized-provider list in
+    /// `hermes-agent/hermes_cli/providers.py`.
+    public static let demotedProviders: Set<String> = [
+        "vercel",
+    ]
+
+    // MARK: - Image-generation model allowlist (curated)
+
+    /// Known image-generation models, used to pre-populate the
+    /// `image_gen.model` picker on the Auxiliary tab. The list is
+    /// curated — `models_dev_cache.json` doesn't tag image-capable
+    /// models, so we maintain this by hand on Hermes version bumps.
+    /// Always free-form-typeable on the picker too, so missing entries
+    /// don't block users with non-listed image providers.
+    ///
+    /// Order: most-likely-to-be-chosen first.
+    public static let imageGenModels: [HermesImageGenModel] = [
+        .init(modelID: "openai/gpt-image-1", display: "OpenAI · gpt-image-1", providerHint: "openai"),
+        .init(modelID: "google/imagen-4", display: "Google · Imagen 4", providerHint: "google-vertex"),
+        .init(modelID: "google/imagen-3", display: "Google · Imagen 3", providerHint: "google-vertex"),
+        .init(modelID: "stability/stable-image-ultra", display: "Stability · Stable Image Ultra", providerHint: "stability"),
+        .init(modelID: "fal-ai/flux-pro-1.1", display: "fal · FLUX 1.1 Pro", providerHint: "fal"),
+        .init(modelID: "black-forest-labs/flux-1.1-pro", display: "Black Forest Labs · FLUX 1.1 Pro", providerHint: "openrouter"),
+        .init(modelID: "openai/dall-e-3", display: "OpenAI · DALL·E 3", providerHint: "openai"),
+    ]
+
     // MARK: - Hermes overlay providers
 
     /// The 11 providers Hermes surfaces via `hermes model` that have no
@@ -538,6 +631,27 @@ public struct ModelCatalogService: Sendable {
     ]
 }
 
+/// Curated entry for the `image_gen.model` picker on the Auxiliary
+/// tab. Hermes v0.13 honors a top-level `image_gen.model` key but the
+/// models.dev catalog has no `image: true` tag, so we maintain a
+/// short hand-curated allowlist keyed by display order. The picker
+/// always allows free-form-typing too, so any provider's model ID
+/// works regardless of whether it appears here.
+public struct HermesImageGenModel: Sendable, Identifiable, Hashable {
+    public let modelID: String
+    public let display: String
+    /// Hint at which provider serves this model — surfaced as a
+    /// "Configure provider X first" advisory but never enforced.
+    public let providerHint: String?
+    public var id: String { modelID }
+
+    public init(modelID: String, display: String, providerHint: String?) {
+        self.modelID = modelID
+        self.display = display
+        self.providerHint = providerHint
+    }
+}
+
 /// Scarf-side mirror of `HermesOverlay` from hermes-agent's
 /// `hermes_cli/providers.py`. Describes a provider that isn't in the
 /// models.dev catalog.

scarf/Packages/ScarfCore/Sources/ScarfCore/ViewModels/RichChatViewModel.swift

@@ -229,12 +229,6 @@ public final class RichChatViewModel {
     public private(set) var acpOutputTokens = 0
     public private(set) var acpThoughtTokens = 0
     public private(set) var acpCachedReadTokens = 0
-    /// Running count of context compactions Hermes has performed on this
-    /// session. Surfaced as the `🗜 ×N` chip in `SessionInfoBar` when > 0
-    /// and `HermesCapabilities.hasContextCompressionCount` is true. Each
-    /// `session/prompt` response carries the latest server-side total, so
-    /// we replace (with a `max` guard) rather than accumulate.
-    public private(set) var acpCompressionCount = 0
 
     /// Slash commands advertised by the ACP server via `available_commands_update`.
     public private(set) var acpCommands: [HermesSlashCommand] = []
@@ -474,7 +468,6 @@ public final class RichChatViewModel {
         acpErrorHint = nil
         acpErrorDetails = nil
         acpCachedReadTokens = 0
-        acpCompressionCount = 0
         acpCommands = []
         projectScopedCommands = []
         currentTurnStart = nil
@@ -818,13 +811,6 @@ public final class RichChatViewModel {
         acpOutputTokens += response.outputTokens
         acpThoughtTokens += response.thoughtTokens
         acpCachedReadTokens += response.cachedReadTokens
-        // Compression count is a session-wide running total emitted by
-        // Hermes; each prompt response carries the latest value, so we
-        // replace rather than accumulate. The `max` guard tolerates
-        // pre-v0.13 hosts (which emit 0) being upgraded server-side
-        // mid-session — once a real number lands the count resumes from
-        // there rather than snapping back to 0.
-        acpCompressionCount = max(acpCompressionCount, response.compressionCount)
         isAgentWorking = false
         buildMessageGroups()
         // Final position after the prompt settles. Catches fast responses

scarf/Packages/ScarfCore/Tests/ScarfCoreTests/M0cServicesTests.swift

@@ -310,6 +310,74 @@ import Foundation
         }
     }
 
+    // MARK: - ModelCatalogService — WS-6 (v0.13)
+
+    @Test func vercelAIGatewayDemotedToBottom() throws {
+        // Build a minimal catalog with vercel + alphabetically-later
+        // providers, then assert vercel sorts after them. Locks the
+        // demoted-axis sort comparator added in WS-6.
+        let json = """
+        {
+          "anthropic": { "name": "Anthropic", "models": {} },
+          "vercel":    { "name": "Vercel AI Gateway", "models": {} },
+          "zonk":      { "name": "Zonk Provider", "models": {} }
+        }
+        """
+        let tmp = FileManager.default.temporaryDirectory
+            .appendingPathComponent("scarf-models-\(UUID().uuidString).json")
+        try json.write(to: tmp, atomically: true, encoding: .utf8)
+        defer { try? FileManager.default.removeItem(at: tmp) }
+        let svc = ModelCatalogService(path: tmp.path)
+        let providers = svc.loadProviders().filter { !$0.isOverlay }
+        let names = providers.map(\.providerName)
+        // anthropic first (alpha), zonk next (alpha), vercel last
+        // (demoted) — even though `vercel` < `zonk` alphabetically.
+        #expect(names.last == "Vercel AI Gateway")
+        let vercelIdx = names.firstIndex(of: "Vercel AI Gateway") ?? -1
+        let zonkIdx = names.firstIndex(of: "Zonk Provider") ?? -1
+        #expect(vercelIdx > zonkIdx)
+    }
+
+    @Test func grok420BetaAliasResolvesToGrok420() {
+        let svc = ModelCatalogService(path: "/tmp/scarf-nonexistent-\(UUID().uuidString).json")
+        // OpenRouter's old `-beta` ID resolves to the GA name.
+        #expect(svc.resolveModelAlias(providerID: "openrouter", modelID: "x-ai/grok-4.20-beta")
+                == "x-ai/grok-4.20")
+        // xAI direct provider keeps the same shape minus prefix.
+        #expect(svc.resolveModelAlias(providerID: "xai", modelID: "grok-4.20-beta")
+                == "grok-4.20")
+        // Non-aliased ID passes through unchanged.
+        #expect(svc.resolveModelAlias(providerID: "anthropic", modelID: "claude-4.7-opus")
+                == "claude-4.7-opus")
+        // Cross-provider isolation: same modelID on a different
+        // provider isn't aliased — composite key in `modelAliases`
+        // disambiguates by providerID.
+        #expect(svc.resolveModelAlias(providerID: "fictional", modelID: "x-ai/grok-4.20-beta")
+                == "x-ai/grok-4.20-beta")
+    }
+
+    @Test func imageGenModelAllowlistShape() {
+        // Lock the curated list size + a few sentinel entries so
+        // unintentional edits get caught in review. Free-form-typing
+        // bypasses the allowlist, so additions/removals here are
+        // purely UX (which models surface as picker rows).
+        let models = ModelCatalogService.imageGenModels
+        #expect(models.count >= 5)
+        #expect(models.contains(where: { $0.modelID == "openai/gpt-image-1" }))
+        #expect(models.contains(where: { $0.modelID == "google/imagen-4" }))
+        // Every entry has a non-empty display + a non-empty modelID.
+        for m in models {
+            #expect(!m.modelID.isEmpty)
+            #expect(!m.display.isEmpty)
+        }
+    }
+
+    @Test func demotedProvidersContainsVercel() {
+        // Minimal lock-in for the demoted-providers static set. Mirrors
+        // Hermes's deprioritized-provider list in providers.py.
+        #expect(ModelCatalogService.demotedProviders.contains("vercel"))
+    }
+
     // MARK: - ProjectDashboardService
 
     @Test func projectDashboardServiceRegistryRoundTrip() throws {

scarf/Packages/ScarfCore/Tests/ScarfCoreTests/M0dViewModelsTests.swift

@@ -162,47 +162,6 @@ import Foundation
         // start → false.
         #expect(vm.supportsCompress == false)
         #expect(vm.hasBroaderCommandMenu == false)
-        // v0.13: compression count starts at 0 so the SessionInfoBar chip
-        // stays hidden on fresh sessions.
-        #expect(vm.acpCompressionCount == 0)
-    }
-
-    @Test @MainActor func richChatTracksCompressionCountFromPromptResults() {
-        let vm = RichChatViewModel(context: .local)
-        let response = ACPPromptResult(
-            stopReason: "end_turn",
-            inputTokens: 100, outputTokens: 50,
-            thoughtTokens: 20, cachedReadTokens: 10,
-            compressionCount: 3
-        )
-        vm.handleACPEvent(.promptComplete(sessionId: "s", response: response))
-        #expect(vm.acpCompressionCount == 3)
-
-        // Subsequent prompts overwrite (with a max guard) — the server
-        // emits a session-wide running total, not a per-prompt delta.
-        let next = ACPPromptResult(
-            stopReason: "end_turn",
-            inputTokens: 0, outputTokens: 0,
-            thoughtTokens: 0, cachedReadTokens: 0,
-            compressionCount: 5
-        )
-        vm.handleACPEvent(.promptComplete(sessionId: "s", response: next))
-        #expect(vm.acpCompressionCount == 5)
-
-        // A pre-v0.13 host mid-session emits 0; the max-guard keeps the
-        // last real value rather than snapping back.
-        let stale = ACPPromptResult(
-            stopReason: "end_turn",
-            inputTokens: 0, outputTokens: 0,
-            thoughtTokens: 0, cachedReadTokens: 0,
-            compressionCount: 0
-        )
-        vm.handleACPEvent(.promptComplete(sessionId: "s", response: stale))
-        #expect(vm.acpCompressionCount == 5)
-
-        // reset() clears the counter so a fresh session starts clean.
-        vm.reset()
-        #expect(vm.acpCompressionCount == 0)
     }
 
     @Test @MainActor func messageGroupDerivedProperties() {

scarf/Packages/ScarfCore/Tests/ScarfCoreTests/M0eUpdaterTests.swift

@@ -1,87 +0,0 @@
-import Testing
-import Foundation
-@testable import ScarfCore
-
-/// Pure-function matrix for `HermesUpdaterCommandBuilder.updateArgv`. The
-/// builder degrades flags silently when the connected host can't honor
-/// them, so the "is the right flag emitted on the right version?" matrix
-/// is the meaningful test surface.
-@Suite struct M0eUpdaterTests {
-
-    // MARK: - Helpers
-
-    private func caps(_ versionLine: String?) -> HermesCapabilities {
-        guard let line = versionLine else { return .empty }
-        return HermesCapabilities.parseLine(line)
-    }
-
-    // MARK: - Pre-v0.12 (no flags supported)
-
-    @Test func preV012_returnsBareUpdateRegardlessOfFlags() {
-        let pre = caps("Hermes Agent v0.11.0 (2026.4.23)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: pre, unattended: false, checkOnly: false
-        ) == ["update"])
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: pre, unattended: true, checkOnly: false
-        ) == ["update"])
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: pre, unattended: true, checkOnly: true
-        ) == ["update"])
-    }
-
-    @Test func unknownVersion_returnsBareUpdate() {
-        // No detected version means we can't guarantee any flag is
-        // honored; defensively emit the bare verb.
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: .empty, unattended: true, checkOnly: true
-        ) == ["update"])
-    }
-
-    // MARK: - v0.12 (--check supported, --yes is not)
-
-    @Test func v012_checkOnly_emitsCheckFlag() {
-        let v012 = caps("Hermes Agent v0.12.0 (2026.4.30)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v012, unattended: false, checkOnly: true
-        ) == ["update", "--check"])
-    }
-
-    @Test func v012_unattended_dropsYesFlag() {
-        // v0.12 doesn't honor --yes; the helper degrades silently.
-        let v012 = caps("Hermes Agent v0.12.0 (2026.4.30)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v012, unattended: true, checkOnly: false
-        ) == ["update"])
-    }
-
-    @Test func v012_checkOnlyAndUnattended_emitsOnlyCheck() {
-        let v012 = caps("Hermes Agent v0.12.0 (2026.4.30)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v012, unattended: true, checkOnly: true
-        ) == ["update", "--check"])
-    }
-
-    // MARK: - v0.13 (full flag support)
-
-    @Test func v013_unattended_emitsYesFlag() {
-        let v013 = caps("Hermes Agent v0.13.0 (2026.5.7)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v013, unattended: true, checkOnly: false
-        ) == ["update", "--yes"])
-    }
-
-    @Test func v013_checkOnlyAndUnattended_emitsBothFlags() {
-        let v013 = caps("Hermes Agent v0.13.0 (2026.5.7)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v013, unattended: true, checkOnly: true
-        ) == ["update", "--check", "--yes"])
-    }
-
-    @Test func v013_neither_emitsBareUpdate() {
-        let v013 = caps("Hermes Agent v0.13.0 (2026.5.7)")
-        #expect(HermesUpdaterCommandBuilder.updateArgv(
-            capabilities: v013, unattended: false, checkOnly: false
-        ) == ["update"])
-    }
-}

scarf/Packages/ScarfCore/Tests/ScarfCoreTests/M6ConfigCronTests.swift

@@ -92,6 +92,27 @@ import Foundation
         #expect(c.security.redactSecrets == true)
         #expect(c.compression.enabled == true)
         #expect(c.voice.ttsProvider == "edge")
+        // v0.13 additions default to empty / off when the YAML omits
+        // them — pre-v0.13 hosts produce this exact shape.
+        #expect(c.imageGenModel == "")
+        #expect(c.openrouterResponseCacheEnabled == false)
+    }
+
+    @Test func parsesImageGenAndOpenRouterCache() {
+        // WS-6: round-trip the two new top-level v0.13 keys. If the
+        // OpenRouter key shape changes upstream (see TODO(WS-6-Q1)),
+        // this test is the single touchpoint that pins the parser
+        // line + setter key + UI binding to a single shape.
+        let yaml = """
+        image_gen:
+          model: openai/gpt-image-1
+        openrouter:
+          response_cache:
+            enabled: true
+        """
+        let c = HermesConfig(yaml: yaml)
+        #expect(c.imageGenModel == "openai/gpt-image-1")
+        #expect(c.openrouterResponseCacheEnabled == true)
     }
 
     @Test func parsesTopLevelModel() {

scarf/Packages/ScarfCore/Tests/ScarfCoreTests/ScarfCoreSmokeTests.swift

@@ -242,15 +242,6 @@ import Foundation
             thoughtTokens: 20, cachedReadTokens: 10
         )
         #expect(prompt.stopReason == "end_turn")
-        // v0.13: compressionCount has a 0 default for legacy callers.
-        #expect(prompt.compressionCount == 0)
-
-        let v013Prompt = ACPPromptResult(
-            stopReason: "end_turn", inputTokens: 0, outputTokens: 0,
-            thoughtTokens: 0, cachedReadTokens: 0,
-            compressionCount: 7
-        )
-        #expect(v013Prompt.compressionCount == 7)
     }
 
     @Test func projectDashboardInitChain() {

scarf/scarf/Core/Services/HermesFileService.swift

@@ -84,11 +84,7 @@ struct HermesFileService: Sendable {
             inlineDiffs: bool("display.inline_diffs", default: true),
             toolProgressCommand: bool("display.tool_progress_command", default: false),
             toolPreviewLength: int("display.tool_preview_length", default: 0),
-            busyInputMode: str("display.busy_input_mode", default: "interrupt"),
+            busyInputMode: str("display.busy_input_mode", default: "interrupt")
-            // v0.13: empty default means "key absent — agent uses its own
-            // default" (English). The picker writes a real value when the
-            // user explicitly chooses one.
-            language: str("display.language", default: "")
         )
 
         let terminal = TerminalSettings(
@@ -135,12 +131,7 @@ struct HermesFileService: Sendable {
             sttLocalModel: str("stt.local.model", default: "base"),
             sttLocalLanguage: str("stt.local.language"),
             sttOpenAIModel: str("stt.openai.model", default: "whisper-1"),
-            sttMistralModel: str("stt.mistral.model", default: "voxtral-mini-latest"),
+            sttMistralModel: str("stt.mistral.model", default: "voxtral-mini-latest")
-            // TODO(WS-8-Q2): Verify key names. Mirroring the elevenlabs
-            // shape (`<provider>.voice_id` + `<provider>.model`); v0.13
-            // source might use `tts.xai.voice` or `tts.xai.model_id`.
-            ttsXAIVoiceID: str("tts.xai.voice_id"),
-            ttsXAIModel: str("tts.xai.model")
         )
 
         func aux(_ name: String) -> AuxiliaryModel {

scarf/scarf/Features/Chat/Views/ChatTranscriptPane.swift

@@ -11,7 +11,6 @@ struct ChatTranscriptPane: View {
     @Bindable var chatViewModel: ChatViewModel
     var onSend: (String, [ChatImageAttachment]) -> Void
     var isEnabled: Bool
-    @Environment(\.hermesCapabilities) private var capabilitiesStore
 
     var body: some View {
         VStack(spacing: 0) {
@@ -21,10 +20,8 @@ struct ChatTranscriptPane: View {
                 acpInputTokens: richChat.acpInputTokens,
                 acpOutputTokens: richChat.acpOutputTokens,
                 acpThoughtTokens: richChat.acpThoughtTokens,
-                acpCompressionCount: richChat.acpCompressionCount,
                 projectName: chatViewModel.currentProjectName,
-                gitBranch: chatViewModel.currentGitBranch,
+                gitBranch: chatViewModel.currentGitBranch
-                capabilities: capabilitiesStore?.capabilities ?? .empty
             )
             Divider()
 

scarf/scarf/Features/Chat/Views/SessionInfoBar.swift

@@ -9,11 +9,6 @@ struct SessionInfoBar: View {
     var acpInputTokens: Int = 0
     var acpOutputTokens: Int = 0
     var acpThoughtTokens: Int = 0
-    /// Number of context compactions Hermes has run on this session. v0.13+
-    /// surface — capability-gated by the bar so pre-v0.13 hosts never see
-    /// the chip even if a stale value somehow trickles through. Defaults
-    /// to 0 so existing callers and previews don't need to be updated.
-    var acpCompressionCount: Int = 0
     /// Name of the Scarf project this session is attributed to, when
     /// applicable. Nil for plain global chats. Drives the folder-chip
     /// indicator rendered before the session title. Resolved by
@@ -25,11 +20,6 @@ struct SessionInfoBar: View {
     /// name. Nil for non-project chats and for projects that aren't
     /// git repos.
     var gitBranch: String? = nil
-    /// Capability snapshot for v0.13+ surfaces. Defaulted so previews and
-    /// pre-v0.13 hosts render the v2.7.5 layout unchanged. Coordinated
-    /// with WS-2 — both WSes add `capabilities` to this view; whichever
-    /// lands first establishes the prop.
-    var capabilities: HermesCapabilities = .empty
 
     /// Active Hermes profile name (issue #50). Resolved on each body
     /// re-evaluation; the resolver caches for 5s so this is cheap.
@@ -106,21 +96,6 @@ struct SessionInfoBar: View {
                     Label("\(formatTokens(reasonToks)) reasoning", systemImage: "brain")
                 }
 
-                // v0.13: Hermes surfaces a running count of automatic
-                // context compactions. Render only when the host is on
-                // v0.13+ AND the count is non-zero, so a pre-v0.13 host
-                // (which always reports 0) sees no chip, and a v0.13 host
-                // sees the chip the first time the agent compacts.
-                if capabilities.hasContextCompressionCount && acpCompressionCount > 0 {
-                    Label(
-                        "×\(acpCompressionCount)",
-                        systemImage: "arrow.down.right.and.arrow.up.left"
-                    )
-                    .scarfStyle(.caption)
-                    .foregroundStyle(ScarfColor.foregroundMuted)
-                    .help("Hermes auto-compacted this session's context \(acpCompressionCount) time\(acpCompressionCount == 1 ? "" : "s")")
-                }
-
                 if let cost = session.displayCostUSD {
                     let formattedCost = cost.formatted(.currency(code: "USD").precision(.fractionLength(4)))
                     Label(session.costIsActual ? formattedCost : "\(formattedCost) est.", systemImage: "dollarsign.circle")

scarf/scarf/Features/Chat/Views/SlashCommandMenu.swift

@@ -87,16 +87,7 @@ private struct SlashCommandRow: View {
                         .fontWeight(.semibold)
                         .foregroundStyle(isSelected ? ScarfColor.accentActive : ScarfColor.foregroundPrimary)
                     if let hint = command.argumentHint {
-                        // v0.13: Hermes may emit hints already wrapped in
+                        Text("<\(hint)>")
-                        // brackets (e.g. `[name]` for the optional `/new
-                        // <name>` argument exposed by `hasNewWithSessionName`).
-                        // Avoid double-wrapping — bracketed hints pass through
-                        // verbatim while older `guidance`-style hints (no
-                        // brackets) still render as `<guidance>`.
-                        let display = hint.hasPrefix("<") || hint.hasPrefix("[")
-                            ? hint
-                            : "<\(hint)>"
-                        Text(display)
                             .font(ScarfFont.monoSmall)
                             .foregroundStyle(ScarfColor.foregroundFaint)
                     }

scarf/scarf/Features/Settings/ViewModels/SettingsViewModel.swift

@@ -29,31 +29,8 @@ final class SettingsViewModel {
     // that no-ops on older hosts is low compared to gating overhead.
     var terminalBackends = ["local", "docker", "singularity", "modal", "daytona", "ssh", "vercel"]
     var browserBackends = ["browseruse", "firecrawl", "local"]
-    // v0.13: `xai` joins the TTS provider list. xAI shipped TTS earlier
+    var ttsProviders = ["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts", "piper"]
-    // (v0.12) but the v0.13 add-on is custom voice cloning — see
-    // `HermesCapabilities.hasXAIVoiceCloning` and the badge in VoiceTab.
-    // The provider option itself is ungated so pre-v0.13 hosts with xAI
-    // keys can still pick it.
-    var ttsProviders = ["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts", "piper", "xai"]
     var sttProviders = ["local", "groq", "openai", "mistral"]
-    /// Static-message translation languages honored by Hermes v0.13's
-    /// `display.language` key. The first row's empty value writes no
-    /// key — equivalent to "Hermes default" — while explicit `en` writes
-    /// the code so users who care about determinism can pin it. Keep the
-    /// label list in sync with the Hermes v0.13 release notes; new
-    /// languages should be appended in alphabetical order by display
-    /// label so the picker stays scannable.
-    var displayLanguages: [(code: String, label: String)] = [
-        ("",   "English (default)"),
-        ("en", "English"),
-        ("zh", "中文 (Chinese)"),
-        ("ja", "日本語 (Japanese)"),
-        ("de", "Deutsch (German)"),
-        ("es", "Español (Spanish)"),
-        ("fr", "Français (French)"),
-        ("uk", "Українська (Ukrainian)"),
-        ("tr", "Türkçe (Turkish)"),
-    ]
     var memoryProviders = ["", "honcho", "openviking", "mem0", "hindsight", "holographic", "retaindb", "byterover", "supermemory"]
     var saveMessage: String?
     var isLoading = false
@@ -127,10 +104,6 @@ final class SettingsViewModel {
     func setToolProgressCommand(_ value: Bool) { setSetting("display.tool_progress_command", value: value ? "true" : "false") }
     func setToolPreviewLength(_ value: Int) { setSetting("display.tool_preview_length", value: String(value)) }
     func setBusyInputMode(_ value: String) { setSetting("display.busy_input_mode", value: value) }
-    /// v0.13: `display.language` for static-message translations. Empty
-    /// string writes "" via `hermes config set` which Hermes treats as
-    /// "use default"; explicit codes pin the language.
-    func setDisplayLanguage(_ value: String) { setSetting("display.language", value: value) }
 
     // MARK: - Agent
 
@@ -185,10 +158,6 @@ final class SettingsViewModel {
     func setTTSOpenAIVoice(_ value: String) { setSetting("tts.openai.voice", value: value) }
     func setTTSNeuTTSModel(_ value: String) { setSetting("tts.neutts.model", value: value) }
     func setTTSNeuTTSDevice(_ value: String) { setSetting("tts.neutts.device", value: value) }
-    // v0.13: xAI TTS / Custom Voices. TODO(WS-8-Q2): grep-verify key
-    // names against `~/.hermes/hermes-agent/hermes_cli/voice/tts.py`.
-    func setTTSXAIVoiceID(_ value: String) { setSetting("tts.xai.voice_id", value: value) }
-    func setTTSXAIModel(_ value: String) { setSetting("tts.xai.model", value: value) }
     func setSTTEnabled(_ value: Bool) { setSetting("stt.enabled", value: value ? "true" : "false") }
     func setSTTProvider(_ value: String) { setSetting("stt.provider", value: value) }
     func setSTTLocalModel(_ value: String) { setSetting("stt.local.model", value: value) }
@@ -226,6 +195,24 @@ final class SettingsViewModel {
         setSetting("auxiliary.\(task).timeout", value: String(value))
     }
 
+    // MARK: - Image generation (v0.13+)
+
+    /// `image_gen.model` — overrides the per-provider default image
+    /// model (Hermes v0.13+). Empty string clears the override.
+    /// Capability-gated in `AuxiliaryTab` so pre-v0.13 hosts never
+    /// invoke this setter.
+    func setImageGenModel(_ value: String) { setSetting("image_gen.model", value: value) }
+
+    /// `openrouter.response_cache.enabled` — toggles OpenRouter
+    /// response caching for repeat prompts (Hermes v0.13+).
+    /// Capability-gated in `AuxiliaryTab` so pre-v0.13 hosts never
+    /// invoke this setter.
+    // TODO(WS-6-Q1): the YAML key path is provisional — keep in lockstep
+    // with `HermesConfig+YAML.swift`'s parser line.
+    func setOpenRouterResponseCache(_ value: Bool) {
+        setSetting("openrouter.response_cache.enabled", value: value ? "true" : "false")
+    }
+
     // MARK: - Security / Privacy
 
     func setRedactSecrets(_ value: Bool) { setSetting("security.redact_secrets", value: value ? "true" : "false") }

scarf/scarf/Features/Settings/Views/Components/SettingsComponents.swift

@@ -152,23 +152,8 @@ struct PickerRow: View {
     let label: String
     let selection: String
     let options: [String]
-    let optionLabel: ((String) -> String)?
     let onChange: (String) -> Void
 
-    init(
-        label: String,
-        selection: String,
-        options: [String],
-        optionLabel: ((String) -> String)? = nil,
-        onChange: @escaping (String) -> Void
-    ) {
-        self.label = label
-        self.selection = selection
-        self.options = options
-        self.optionLabel = optionLabel
-        self.onChange = onChange
-    }
-
     var body: some View {
         HStack {
             SettingsRowLabel(label: label)
@@ -177,7 +162,7 @@ struct PickerRow: View {
                 set: { onChange($0) }
             )) {
                 ForEach(options, id: \.self) { option in
-                    Text(displayLabel(for: option)).tag(option)
+                    Text(option.isEmpty ? "(none)" : option).tag(option)
                 }
             }
             .frame(maxWidth: 250)
@@ -185,13 +170,6 @@ struct PickerRow: View {
         }
         .settingsRowChrome()
     }
-
-    private func displayLabel(for option: String) -> String {
-        if let mapper = optionLabel {
-            return mapper(option)
-        }
-        return option.isEmpty ? "(none)" : option
-    }
 }
 
 struct ToggleRow: View {

scarf/scarf/Features/Settings/Views/Tabs/AdvancedTab.swift

@@ -131,8 +131,6 @@ struct AdvancedTab: View {
                 isOn: viewModel.config.redactionEnabled
             ) { viewModel.setSetting("redaction.enabled", value: $0 ? "true" : "false") }
 
-            redactionDefaultsHint
-
             ToggleRow(
                 label: "Runtime metadata footer",
                 isOn: viewModel.config.runtimeMetadataFooter
@@ -140,30 +138,6 @@ struct AdvancedTab: View {
         }
     }
 
-    /// Inline hint below the redaction toggle. The server-side default
-    /// flipped from OFF (v0.12) to ON (v0.13), but Scarf's parser still
-    /// reads "absent key" as `false` — meaning a v0.13 host with no
-    /// explicit key in `config.yaml` shows the toggle OFF while the
-    /// agent treats redaction as ON. Hint copy disambiguates so users
-    /// can tell what's actually happening server-side.
-    @ViewBuilder
-    private var redactionDefaultsHint: some View {
-        let isV013 = capabilitiesStore?.capabilities.isV013OrLater ?? false
-        HStack {
-            Text("")
-                .font(.caption)
-                .frame(width: 160, alignment: .trailing)
-            Text(isV013
-                 ? "Recommended: ON. Hermes v0.13+ defaults to redacting secrets unless you opt out."
-                 : "Default OFF in Hermes v0.12. Toggle ON to redact secrets in logs and shares.")
-                .font(.caption)
-                .foregroundStyle(.secondary)
-            Spacer()
-        }
-        .padding(.horizontal, 12)
-        .padding(.vertical, 4)
-    }
-
     private var backupSection: some View {
         SettingsSection(title: "Backup & Restore", icon: "externaldrive") {
             HStack {

scarf/scarf/Features/Settings/Views/Tabs/AuxiliaryTab.swift

@@ -139,6 +139,23 @@ struct AuxiliaryTab: View {
                 auxRows(for: task.key)
             }
         }
+        // -- Hermes v0.13 additions ---------------------------------
+        // Image-gen model picker. Hermes v0.13 honors `image_gen.model`
+        // as a top-level YAML key; pre-v0.13 hosts ignore it silently.
+        // Hide the section on pre-v0.13 hosts to spare users a
+        // "I set this and nothing happened" trap.
+        if capabilitiesStore?.capabilities.hasImageGenModel ?? false {
+            SettingsSection(title: "Image Generation", icon: "photo") {
+                imageGenRow
+            }
+        }
+        // OpenRouter response caching toggle (v0.13+). Same hide-on-
+        // pre-v0.13 rationale: the toggle no-ops on older Hermes hosts.
+        if capabilitiesStore?.capabilities.hasOpenRouterResponseCache ?? false {
+            SettingsSection(title: "OpenRouter", icon: "shippingbox") {
+                openRouterResponseCacheRow
+            }
+        }
         // Unknown / unrecognised aux tasks present in config.yaml.
         // Shown only when at least one such key is present so the
         // typical user with a clean config never sees this section.
@@ -225,6 +242,60 @@ struct AuxiliaryTab: View {
         }
     }
 
+    // MARK: - v0.13 surfaces
+
+    /// Image-gen model picker — curated allowlist + free-form custom
+    /// entry. Capability-gated by the caller; this view assumes the
+    /// host honors `image_gen.model` (Hermes v0.13+).
+    @ViewBuilder
+    private var imageGenRow: some View {
+        let value = viewModel.config.imageGenModel
+        Picker("Model", selection: Binding(
+            get: { value },
+            set: { viewModel.setImageGenModel($0) }
+        )) {
+            Text("Provider default").tag("")
+            Divider()
+            ForEach(ModelCatalogService.imageGenModels) { model in
+                Text(model.display).tag(model.modelID)
+            }
+            // User has set a custom value not in the curated list;
+            // preserve it as a tagged option so the picker renders the
+            // actual selection rather than collapsing to "Provider
+            // default".
+            if !value.isEmpty
+                && !ModelCatalogService.imageGenModels.contains(where: { $0.modelID == value }) {
+                Divider()
+                Text(value + "  (custom)").tag(value)
+            }
+        }
+        .pickerStyle(.menu)
+        EditableTextField(label: "Custom model ID", value: value) { newValue in
+            viewModel.setImageGenModel(newValue.trimmingCharacters(in: .whitespaces))
+        }
+        Text("Used for image generation calls. Leave as Provider default unless your provider documents a specific model ID for image-gen.")
+            .font(.caption2)
+            .foregroundStyle(.tertiary)
+            .padding(.horizontal, 12)
+            .padding(.bottom, 4)
+    }
+
+    /// OpenRouter response-caching toggle (Hermes v0.13+). Off by
+    /// default; surfaced for users with highly repeated prompts who
+    /// want OpenRouter to cache identical-prompt responses.
+    @ViewBuilder
+    private var openRouterResponseCacheRow: some View {
+        let isOn = viewModel.config.openrouterResponseCacheEnabled
+        ToggleRow(label: "Response caching", isOn: isOn) { newValue in
+            viewModel.setOpenRouterResponseCache(newValue)
+        }
+        Text("OpenRouter caches identical prompts within a session to reduce token costs. Off by default — enable when your workload has highly repeated prompts.")
+            .font(.caption2)
+            .foregroundStyle(.tertiary)
+            .padding(.horizontal, 12)
+            .padding(.bottom, 4)
+    }
+
     private func auxModel(for key: String) -> AuxiliaryModel {
         switch key {
         case "vision": return viewModel.config.auxiliary.vision

scarf/scarf/Features/Settings/Views/Tabs/GeneralTab.swift

@@ -7,7 +7,6 @@ import ScarfCore
 struct GeneralTab: View {
     @Bindable var viewModel: SettingsViewModel
     @Environment(AppCoordinator.self) private var coordinator
-    @Environment(\.hermesCapabilities) private var capabilitiesStore
 
     var body: some View {
         SettingsSection(title: "Model", icon: "cpu") {
@@ -40,20 +39,6 @@ struct GeneralTab: View {
 
         SettingsSection(title: "Locale", icon: "globe.americas") {
             EditableTextField(label: "Timezone (IANA)", value: viewModel.config.timezone) { viewModel.setTimezone($0) }
-            // v0.13: `display.language` picker. Hidden on pre-v0.13 hosts
-            // because writing the key would no-op silently. Two "English"
-            // entries by design — empty string preserves "no key" semantics
-            // (Hermes-default), explicit `en` pins it.
-            if capabilitiesStore?.capabilities.hasDisplayLanguage == true {
-                PickerRow(
-                    label: "Display language",
-                    selection: viewModel.config.display.language,
-                    options: viewModel.displayLanguages.map(\.code),
-                    optionLabel: { code in
-                        viewModel.displayLanguages.first { $0.code == code }?.label ?? code
-                    }
-                ) { viewModel.setDisplayLanguage($0) }
-            }
         }
 
         UpdatesSection()

scarf/scarf/Features/Settings/Views/Tabs/VoiceTab.swift

@@ -1,11 +1,9 @@
 import SwiftUI
 import ScarfCore
-import ScarfDesign
 
 /// Voice tab — push-to-talk + TTS + STT provider settings.
 struct VoiceTab: View {
     @Bindable var viewModel: SettingsViewModel
-    @Environment(\.hermesCapabilities) private var capabilitiesStore
 
     var body: some View {
         SettingsSection(title: "Push-to-Talk", icon: "mic") {
@@ -30,16 +28,6 @@ struct VoiceTab: View {
             case "neutts":
                 EditableTextField(label: "Model", value: viewModel.config.voice.ttsNeuTTSModel) { viewModel.setTTSNeuTTSModel($0) }
                 PickerRow(label: "Device", selection: viewModel.config.voice.ttsNeuTTSDevice, options: ["cpu", "cuda"]) { viewModel.setTTSNeuTTSDevice($0) }
-            case "xai":
-                // v0.13: xAI TTS surface. Voice ID + Model are always
-                // visible (xAI TTS shipped earlier); the cloning-supported
-                // badge is gated on `hasXAIVoiceCloning` so pre-v0.13 hosts
-                // see the input rows but no cloning advertisement.
-                EditableTextField(label: "Voice ID", value: viewModel.config.voice.ttsXAIVoiceID) { viewModel.setTTSXAIVoiceID($0) }
-                EditableTextField(label: "Model", value: viewModel.config.voice.ttsXAIModel) { viewModel.setTTSXAIModel($0) }
-                if capabilitiesStore?.capabilities.hasXAIVoiceCloning == true {
-                    xaiCloningBadge
-                }
             default:
                 EmptyView()
             }
@@ -61,24 +49,4 @@ struct VoiceTab: View {
             }
         }
     }
-
-    /// Inline hint chip+caption shown below xAI's Voice ID + Model fields
-    /// on v0.13+. References `hermes voice` because Scarf doesn't manage
-    /// cloned voices in-app yet — the badge is discovery-only. Out-of-scope
-    /// for v2.8: an in-app cloned-voice manager (would be its own feature).
-    @ViewBuilder
-    private var xaiCloningBadge: some View {
-        HStack(alignment: .center, spacing: 8) {
-            Text("")
-                .font(.caption)
-                .frame(width: 160, alignment: .trailing)
-            ScarfBadge("Cloning supported", kind: .info)
-            Text("Manage cloned voices in your terminal: `hermes voice` (xAI subcommands).")
-                .font(.caption)
-                .foregroundStyle(.secondary)
-            Spacer()
-        }
-        .padding(.horizontal, 12)
-        .padding(.vertical, 4)
-    }
 }