Merge remote-tracking branch 'origin/release/v3.8.50' into HEAD

# Conflicts:
#	@omniroute/opencode-plugin/README.md
#	@omniroute/opencode-plugin/package.json

@omniroute/opencode-plugin/src/index.ts

@@ -1033,7 +1033,11 @@ export const OmniRoutePlugin: Plugin = async (_input, options) => {
   // Config hook: keep existing catalog shim, and register slash command
   // templates that ask the agent to call the force-sync tool (OpenCode has no
   // Pi-style registerCommand API; tools + command templates are the native path).
-  const baseConfigHook = createOmniRouteConfigHook(resolved, { cache: sharedCache });
+  const baseConfigHook = createOmniRouteConfigHook(resolved, {
+    cache: sharedCache,
+    diskSnapshotReader: defaultDiskSnapshotReader,
+    diskSnapshotWriter: defaultDiskSnapshotWriter,
+  });
   const configWithSyncCommand = async (input: Config) => {
     await baseConfigHook(input);
     const cfg = input as Config & {
@@ -4741,7 +4745,7 @@ export type OmniRouteDiskSnapshotWriter = (
 export type OmniRouteDiskSnapshotReader = (
   providerId: string,
   identityFingerprint: string
-) => Promise<Omit<OmniRouteFetchCacheEntry, "expiresAt"> | undefined>;
+) => Promise<(Omit<OmniRouteFetchCacheEntry, "expiresAt"> & { writtenAt?: number }) | undefined>;
 
 /**
  * Bind a snapshot to the endpoint and effective credential tuple without
@@ -4824,15 +4828,36 @@ export const defaultDiskSnapshotReader: OmniRouteDiskSnapshotReader = async (
         ? parsed.rawCompressionCombos
         : [],
       rawConnections: Array.isArray(parsed.rawConnections) ? parsed.rawConnections : [],
+      writtenAt: typeof parsed.writtenAt === "number" ? parsed.writtenAt : undefined,
     };
   } catch {
     return undefined;
   }
 };
 
-/** No-op disk-cache pair — used by tests to avoid filesystem side effects. */
+/** No-op disk-cache pair — used by tests to avoid filesystem side effects.
+ * Also used as the default in createOmniRouteConfigHook so that tests
+ * that don't pass a diskSnapshotReader don't read real snapshot files
+ * from the user's ~/.local/share/opencode/plugins/ directory.
+ * The OmniRoutePlugin function passes the real defaultDiskSnapshotReader
+ * explicitly. */
+export const noopDiskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
 export const noopDiskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
 
+/**
+ * In-flight refresh guard: prevents concurrent refreshes for the same
+ * cacheKey. When a warm snapshot is served, the refresh runs detached; if
+ * a second hook invocation arrives before the refresh completes, it should
+ * piggyback on the in-flight promise rather than starting a second one.
+ * Cleared on settle so it doesn't leak.
+ */
+const _inflightRefresh: Map<string, Promise<void>> = new Map();
+
+/** Reset the in-flight refresh guard (for test isolation). */
+export function _resetInflightRefresh(): void {
+  _inflightRefresh.clear();
+}
+
 // ────────────────────────────────────────────────────────────────────────────
 // Debug logging (features.debugLog)
 // ────────────────────────────────────────────────────────────────────────────
@@ -5067,7 +5092,6 @@ export function createDebugLoggingFetch(
     }
   };
 }
-export const noopDiskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
 
 export type OmniRouteReadAuthJson = () => Promise<AuthJsonShape | undefined | null>;
 
@@ -5170,8 +5194,8 @@ export function createOmniRouteConfigHook(
   const compressionMetaFetcher =
     deps.compressionMetaFetcher ?? defaultOmniRouteCompressionMetaFetcher;
   const providersFetcher = deps.providersFetcher ?? defaultOmniRouteProvidersFetcher;
-  const diskSnapshotReader = deps.diskSnapshotReader ?? defaultDiskSnapshotReader;
-  const diskSnapshotWriter = deps.diskSnapshotWriter ?? defaultDiskSnapshotWriter;
+  const diskSnapshotReader = deps.diskSnapshotReader ?? noopDiskSnapshotReader;
+  const diskSnapshotWriter = deps.diskSnapshotWriter ?? noopDiskSnapshotWriter;
   const now = deps.now ?? Date.now;
   const cache: OmniRouteFetchCache = deps.cache ?? new Map();
   const logger = deps.logger ?? console;
@@ -5266,12 +5290,12 @@ export function createOmniRouteConfigHook(
     const t = now();
     const cached = cache.get(cacheKey);
 
-    let rawModels: OmniRouteRawModelEntry[];
-    let rawCombos: OmniRouteRawCombo[];
-    let rawAutoCombos: OmniRouteRawAutoCombo[];
-    let rawEnrichment: OmniRouteEnrichmentMap;
-    let rawCompressionCombos: OmniRouteCompressionCombo[];
-    let rawConnections: OmniRouteProviderConnection[];
+    let rawModels: OmniRouteRawModelEntry[] = [];
+    let rawCombos: OmniRouteRawCombo[] = [];
+    let rawAutoCombos: OmniRouteRawAutoCombo[] = [];
+    let rawEnrichment: OmniRouteEnrichmentMap = new Map();
+    let rawCompressionCombos: OmniRouteCompressionCombo[] = [];
+    let rawConnections: OmniRouteProviderConnection[] = [];
 
     if (cached && cached.expiresAt > t) {
       rawModels = cached.rawModels;
@@ -5281,160 +5305,275 @@ export function createOmniRouteConfigHook(
       rawCompressionCombos = cached.rawCompressionCombos;
       rawConnections = cached.rawConnections;
     } else {
-      // Fail-open fetcher errors: on /v1/models throw, fall back to empty
-      // catalog (still publish a stub block so OC has a complete-shape
-      // entry); on /api/combos throw, publish models-only. Disk-cache
-      // fallback below recovers the last-known-good catalog when the
-      // fetcher threw (network down / 403 / timeout) AND features.diskCache
-      // !== false. A 0-entry SUCCESS (fresh tenant) does NOT trigger
-      // disk fallback — that's a valid empty catalog.
-      let modelsFetchThrew = false;
-      try {
-        rawModels = await fetcher(baseURL, apiKey, 10_000);
-      } catch (err) {
-        logger.warn(
-          "[omniroute-plugin] config shim: /v1/models fetch failed; publishing stub provider entry",
-          err
-        );
-        rawModels = [];
-        modelsFetchThrew = true;
-      }
-      const modelsFetchOk = !modelsFetchThrew && rawModels.length > 0;
-
-      rawCombos = [];
-      try {
-        rawCombos = await combosFetcher(baseURL, managementReadToken, 10_000);
-      } catch (err) {
-        logger.warn(
-          "[omniroute-plugin] config shim: /api/combos fetch failed; publishing models-only static catalog",
-          err
-        );
-      }
-
-      rawAutoCombos = [];
-      if (wantAutoCombos) {
-        try {
-          rawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
-        } catch {
-          // Already handled inside the default fetcher
-        }
-      }
-
-      // Eagerly fetch enrichment so the static block can overlay human
-      // display names on raw model ids. On OC ≤1.15.5 the dynamic
-      // `provider.models` hook never fires in `serve` mode, so the static
-      // block IS what reaches `/provider` and the TUI model picker.
-      // Gated by `features.enrichment` (default-on). Soft-fail on error —
-      // we still publish a name-less catalog if /api/pricing/models is
-      // unreachable.
-      rawEnrichment = new Map();
-      if (wantEnrichment) {
-        try {
-          rawEnrichment = await enrichmentFetcher(baseURL, managementReadToken, 10_000);
-        } catch (err) {
+      // ─────────────────────────────────────────────────────────────────────
+      // Warm startup: read the disk snapshot before fetching so the provider
+      // registers immediately with the last-known-good catalog. The live
+      // fetch then refreshes in the background (detached) and updates the
+      // cache + snapshot. Gated by features.diskCache (default-on).
+      // ─────────────────────────────────────────────────────────────────────
+      let warmSnapshot: Omit<OmniRouteFetchCacheEntry, "expiresAt"> | undefined;
+      if (wantDiskCache) {
+        const snapshotResult = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
+        if (snapshotResult && snapshotResult.rawModels.length > 0) {
+          warmSnapshot = snapshotResult;
+          // Log snapshot age (accept any age — instant beats empty).
+          const age = (snapshotResult as { writtenAt?: number }).writtenAt;
+          const ageLabel = typeof age === "number" ? `${Math.round((Date.now() - age) / 3_600_000)}h` : "unknown";
           logger.warn(
-            "[omniroute-plugin] config shim: /api/pricing/models fetch failed; publishing raw-id static catalog",
-            err
+            `[omniroute-plugin] config shim: warm startup from disk snapshot (${snapshotResult.rawModels.length} models, age ${ageLabel})`
           );
         }
       }
 
-      // Compression-metadata fetch — opt-in via features.compressionMetadata.
-      // When on, the default pipeline is appended to every combo `name` so
-      // the TUI picker advertises which compression a combo applies.
-      rawCompressionCombos = [];
-      if (wantCompressionMeta) {
-        try {
-          rawCompressionCombos = await compressionMetaFetcher(baseURL, managementReadToken, 10_000);
-        } catch (err) {
-          logger.warn(
-            "[omniroute-plugin] config shim: /api/context/combos fetch failed; publishing combos without compression suffix",
-            err
-          );
+      // ─────────────────────────────────────────────────────────────────────
+      // Parallel refresh: all six fetchers run concurrently via
+      // Promise.allSettled. Each wrapper never rejects (catches internally)
+      // so partial failure is tolerated — same soft-fail semantics as the
+      // old sequential chain, but ~6x faster.
+      // ─────────────────────────────────────────────────────────────────────
+      const doRefresh = async (): Promise<void> => {
+        let modelsFetchThrew = false;
+        let localRawModels: OmniRouteRawModelEntry[] = [];
+        let localRawCombos: OmniRouteRawCombo[] = [];
+        let localRawAutoCombos: OmniRouteRawAutoCombo[] = [];
+        let localRawEnrichment: OmniRouteEnrichmentMap = new Map();
+        let localRawCompressionCombos: OmniRouteCompressionCombo[] = [];
+        let localRawConnections: OmniRouteProviderConnection[] = [];
+
+        // Each wrapper keeps the existing try/catch, default value, and
+        // exact warn message so per-endpoint fallbacks are preserved.
+        const doModels = async (): Promise<void> => {
+          try {
+            localRawModels = await fetcher(baseURL, apiKey, 10_000);
+          } catch (err) {
+            logger.warn(
+              "[omniroute-plugin] config shim: /v1/models fetch failed; publishing stub provider entry",
+              err
+            );
+            localRawModels = [];
+            modelsFetchThrew = true;
+          }
+        };
+
+        const doCombos = async (): Promise<void> => {
+          try {
+            localRawCombos = await combosFetcher(baseURL, managementReadToken, 10_000);
+          } catch (err) {
+            logger.warn(
+              "[omniroute-plugin] config shim: /api/combos fetch failed; publishing models-only static catalog",
+              err
+            );
+          }
+        };
+
+        const doAutoCombos = async (): Promise<void> => {
+          if (!wantAutoCombos) return;
+          try {
+            localRawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
+          } catch {
+            // Already handled inside the default fetcher
+          }
+        };
+
+        const doEnrichment = async (): Promise<void> => {
+          if (!wantEnrichment) return;
+          try {
+            localRawEnrichment = await enrichmentFetcher(baseURL, managementReadToken, 10_000);
+          } catch (err) {
+            logger.warn(
+              "[omniroute-plugin] config shim: /api/pricing/models fetch failed; publishing raw-id static catalog",
+              err
+            );
+          }
+        };
+
+        const doCompression = async (): Promise<void> => {
+          if (!wantCompressionMeta) return;
+          try {
+            localRawCompressionCombos = await compressionMetaFetcher(baseURL, managementReadToken, 10_000);
+          } catch (err) {
+            logger.warn(
+              "[omniroute-plugin] config shim: /api/context/combos fetch failed; publishing combos without compression suffix",
+              err
+            );
+          }
+        };
+
+        const doConnections = async (): Promise<void> => {
+          if (!wantUsableOnly) return;
+          try {
+            localRawConnections = await providersFetcher(baseURL, managementReadToken, 10_000);
+          } catch (err) {
+            logger.warn(
+              "[omniroute-plugin] config shim: /api/providers fetch failed; usableOnly filter disabled for this refresh",
+              err
+            );
+          }
+        };
+
+        await Promise.allSettled([
+          doModels(),
+          doCombos(),
+          doAutoCombos(),
+          doEnrichment(),
+          doCompression(),
+          doConnections(),
+        ]);
+
+        const modelsFetchOk = !modelsFetchThrew && localRawModels.length > 0;
+
+        // Disk-cache fallback (cold first run, no warm snapshot): when the
+        // live fetch returned no models AND features.diskCache !== false,
+        // hydrate from the last-known-good snapshot so OC still surfaces a
+        // usable catalog (e.g. IP whitelist drop, offline laptop).
+        if (modelsFetchThrew && wantDiskCache && !warmSnapshot) {
+          const snapshot = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
+          if (snapshot && snapshot.rawModels.length > 0) {
+            logger.warn(
+              `[omniroute-plugin] config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models)`
+            );
+            localRawModels = snapshot.rawModels;
+            localRawCombos = snapshot.rawCombos;
+            localRawAutoCombos = snapshot.rawAutoCombos ?? [];
+            localRawEnrichment = snapshot.rawEnrichment;
+            localRawCompressionCombos = snapshot.rawCompressionCombos;
+            localRawConnections = snapshot.rawConnections;
+          }
         }
-      }
 
-      // Provider-connections fetch — opt-in via features.usableOnly. When
-      // on, the static catalog filters out models/combos whose canonical
-      // provider has no active connection. Soft-fail (empty list) disables
-      // the filter for this refresh, never hiding the whole catalog.
-      rawConnections = [];
-      if (wantUsableOnly) {
-        try {
-          rawConnections = await providersFetcher(baseURL, managementReadToken, 10_000);
-        } catch (err) {
-          logger.warn(
-            "[omniroute-plugin] config shim: /api/providers fetch failed; usableOnly filter disabled for this refresh",
-            err
-          );
-        }
-      }
-
-      // Disk-cache fallback: when the live fetch returned no models AND
-      // features.diskCache !== false, hydrate from the last-known-good
-      // snapshot so OC still surfaces a usable catalog (e.g. IP whitelist
-      // drop, offline laptop). The snapshot is whatever we last wrote on
-      // a healthy refresh; staleness is bounded only by how recently the
-      // user was online.
-      if (modelsFetchThrew && wantDiskCache) {
-        const snapshot = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
-        if (snapshot && snapshot.rawModels.length > 0) {
-          logger.warn(
-            `[omniroute-plugin] config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models)`
-          );
-          rawModels = snapshot.rawModels;
-          rawCombos = snapshot.rawCombos;
-          rawAutoCombos = snapshot.rawAutoCombos ?? [];
-          rawEnrichment = snapshot.rawEnrichment;
-          rawCompressionCombos = snapshot.rawCompressionCombos;
-          rawConnections = snapshot.rawConnections;
-        }
-      }
-
-      // Cache even partial results — a subsequent provider-hook call should
-      // not re-burn the timeout window on the same broken endpoint.
-      cache.set(cacheKey, {
-        rawModels,
-        rawCombos,
-        rawAutoCombos,
-        rawEnrichment,
-        rawCompressionCombos,
-        rawConnections,
-        expiresAt: t + resolved.modelCacheTtl,
-      });
-
-      // Startup diagnostics (file-based) — fires at startup via config hook
-      if (resolved.features?.startupDebug === true) {
-        await writeStartupDiagnostics({
-          providerId: resolved.providerId,
-          baseURL,
-          modelCount: rawModels.length,
-          comboCount: rawCombos.length,
-          enrichmentSize: rawEnrichment.size,
-          autoComboCount: rawAutoCombos.length,
-          enrichment: rawEnrichment,
-          autoCombos: rawAutoCombos,
-          features: resolved.features,
+        // Cache even partial results — a subsequent provider-hook call should
+        // not re-burn the timeout window on the same broken endpoint.
+        cache.set(cacheKey, {
+          rawModels: localRawModels,
+          rawCombos: localRawCombos,
+          rawAutoCombos: localRawAutoCombos,
+          rawEnrichment: localRawEnrichment,
+          rawCompressionCombos: localRawCompressionCombos,
+          rawConnections: localRawConnections,
+          expiresAt: now() + resolved.modelCacheTtl,
         });
-      }
 
-      // Disk-cache write: persist the last successful (or any non-empty)
-      // catalog so a subsequent cold start with a failed fetch can recover.
-      // Best-effort; soft-fail keeps us moving when the data dir isn't
-      // writable (e.g. read-only container).
-      if (modelsFetchOk && wantDiskCache) {
-        await diskSnapshotWriter(
-          resolved.providerId,
-          {
-            rawModels,
-            rawCombos,
-            rawAutoCombos,
-            rawEnrichment,
-            rawCompressionCombos,
-            rawConnections,
-          },
-          snapshotFingerprint
-        );
+        // Startup diagnostics (file-based) — fires at startup via config hook
+        if (resolved.features?.startupDebug === true) {
+          await writeStartupDiagnostics({
+            providerId: resolved.providerId,
+            baseURL,
+            modelCount: localRawModels.length,
+            comboCount: localRawCombos.length,
+            enrichmentSize: localRawEnrichment.size,
+            autoComboCount: localRawAutoCombos.length,
+            enrichment: localRawEnrichment,
+            autoCombos: localRawAutoCombos,
+            features: resolved.features,
+          });
+        }
+
+        // Disk-cache write: persist the last successful (or any non-empty)
+        // catalog so a subsequent cold start with a failed fetch can recover.
+        // Best-effort; soft-fail keeps us moving when the data dir isn't
+        // writable (e.g. read-only container). A failed refresh never
+        // overwrites the snapshot (modelsFetchOk gate).
+        if (modelsFetchOk && wantDiskCache) {
+          await diskSnapshotWriter(
+            resolved.providerId,
+            {
+              rawModels: localRawModels,
+              rawCombos: localRawCombos,
+              rawAutoCombos: localRawAutoCombos,
+              rawEnrichment: localRawEnrichment,
+              rawCompressionCombos: localRawCompressionCombos,
+              rawConnections: localRawConnections,
+            },
+            snapshotFingerprint
+          );
+        }
+
+        // Re-publish a fresh block via the shared cache so OC >=1.14.49's
+        // dynamic provider hook picks it up from the cache. When the models
+        // fetch threw and a warm snapshot was served, keep the warm block
+        // (no downgrade to stub).
+        if (modelsFetchOk || !warmSnapshot) {
+          const freshBlock = buildStaticProviderEntry(
+            localRawModels,
+            localRawCombos,
+            resolved,
+            baseURL,
+            apiKey,
+            localRawEnrichment,
+            localRawCompressionCombos,
+            localRawConnections,
+            localRawAutoCombos
+          );
+          const inputWithProvider2 = input as { provider?: Record<string, unknown> };
+          if (inputWithProvider2.provider) {
+            inputWithProvider2.provider[resolved.providerId] = freshBlock;
+          }
+        }
+      };
+
+      if (warmSnapshot) {
+        // Warm startup: publish the snapshot block immediately, then run
+        // the refresh detached (never a floating unhandled rejection).
+        rawModels = warmSnapshot.rawModels;
+        rawCombos = warmSnapshot.rawCombos;
+        rawAutoCombos = warmSnapshot.rawAutoCombos ?? [];
+        rawEnrichment = warmSnapshot.rawEnrichment;
+        rawCompressionCombos = warmSnapshot.rawCompressionCombos;
+        rawConnections = warmSnapshot.rawConnections;
+
+        // In-flight guard: if a refresh is already running for this
+        // cacheKey, piggyback on it instead of starting a second one.
+        const existing = _inflightRefresh.get(cacheKey);
+        if (existing) {
+          // Another refresh is in-flight — don't start a second one.
+          // The existing refresh will update the cache when it completes.
+        } else {
+          const refreshP = doRefresh()
+            .catch((err: unknown) => {
+              logger.warn("[omniroute-plugin] config shim: background refresh failed", err);
+            })
+            .finally(() => {
+              _inflightRefresh.delete(cacheKey);
+            });
+          _inflightRefresh.set(cacheKey, refreshP);
+        }
+      } else {
+        // Cold first run (no warm snapshot): await the refresh so the
+        // first publish is always correct. In-flight guard still applies.
+        const existing = _inflightRefresh.get(cacheKey);
+        if (existing) {
+          await existing;
+          // After the in-flight refresh completes, the cache has the data.
+          const fresh = cache.get(cacheKey);
+          if (fresh) {
+            rawModels = fresh.rawModels;
+            rawCombos = fresh.rawCombos;
+            rawAutoCombos = fresh.rawAutoCombos;
+            rawEnrichment = fresh.rawEnrichment;
+            rawCompressionCombos = fresh.rawCompressionCombos;
+            rawConnections = fresh.rawConnections;
+          }
+        } else {
+          const refreshP = doRefresh()
+            .catch((err: unknown) => {
+              logger.warn("[omniroute-plugin] config shim: refresh failed", err);
+            })
+            .finally(() => {
+              _inflightRefresh.delete(cacheKey);
+            });
+          _inflightRefresh.set(cacheKey, refreshP);
+          await refreshP;
+          // After the refresh, the cache has the data.
+          const fresh = cache.get(cacheKey);
+          if (fresh) {
+            rawModels = fresh.rawModels;
+            rawCombos = fresh.rawCombos;
+            rawAutoCombos = fresh.rawAutoCombos;
+            rawEnrichment = fresh.rawEnrichment;
+            rawCompressionCombos = fresh.rawCompressionCombos;
+            rawConnections = fresh.rawConnections;
+          }
+        }
       }
     }
 

@omniroute/opencode-plugin/tests/config-shim.test.ts

@@ -33,6 +33,7 @@ import {
   createOmniRouteProviderHook,
   OmniRoutePlugin,
   resolveOmniRoutePluginOptions,
+  _resetInflightRefresh,
   type OmniRouteCombosFetcher,
   type OmniRouteEnrichmentEntry,
   type OmniRouteEnrichmentFetcher,
@@ -47,6 +48,16 @@ import {
   type OmniRouteStaticProviderEntry,
 } from "../src/index.js";
 
+// ────────────────────────────────────────────────────────────────────────────
+// Test isolation: reset the module-level in-flight refresh guard between
+// tests so a detached refresh from a previous test doesn't leak into the
+// next one.
+// ────────────────────────────────────────────────────────────────────────────
+
+test.beforeEach(() => {
+  _resetInflightRefresh();
+});
+
 // ────────────────────────────────────────────────────────────────────────────
 // Fixtures
 // ────────────────────────────────────────────────────────────────────────────
@@ -1239,7 +1250,10 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
   );
   assert.equal(writes, 0, "disk write skipped when live fetch failed");
   assert.ok(
-    logger.entries.some((e) => String(e[0]).includes("using stale disk cache")),
+    logger.entries.some((e) =>
+      String(e[0]).includes("using stale disk cache") ||
+      String(e[0]).includes("warm startup from disk snapshot")
+    ),
     "disk-cache hydration breadcrumb emitted"
   );
 });

@omniroute/opencode-plugin/tests/warm-startup.test.ts

@@ -0,0 +1,827 @@
+/**
+ * Warm-startup + parallel-refresh tests for the opencode-plugin config shim.
+ *
+ * Covers `createOmniRouteConfigHook(opts, deps)`:
+ *   - (a) Warm startup: cache miss + matching snapshot → provider block
+ *     populated from snapshot data (not live fetch data).
+ *   - (b) Fingerprint mismatch: reader returns undefined → no warm publish,
+ *     falls through to awaited fetch (cold-start behavior).
+ *   - (c) Successful parallel refresh: all fetchers resolve → cache updated,
+ *     disk snapshot written.
+ *   - (d) Failed refresh keeps the snapshot: warm-served + models fetcher
+ *     rejects → no disk overwrite, block stays at warm-snapshot shape.
+ *   - (e) Parallelism: all six fetchers start concurrently (not sequential).
+ *   - (f) Soft-fail parity under Promise.allSettled: per-endpoint
+ *     fallbacks + logger.warn breadcrumbs preserved.
+ *   - (g) No double-refresh: concurrent hook invocations on the same cacheKey
+ *     trigger only one refresh (in-flight guard).
+ *   - (h) features.diskCache: false disables the warm read entirely.
+ *
+ * Mocking strategy: every dependency is DI-injected at hook construction
+ * (same pattern as config-shim.test.ts). No global monkey-patching.
+ */
+
+import test from "node:test";
+import assert from "node:assert/strict";
+import type { Config } from "@opencode-ai/plugin";
+
+import {
+  createOmniRouteConfigHook,
+  resolveOmniRoutePluginOptions,
+  _resetInflightRefresh,
+  type OmniRouteAutoCombosFetcher,
+  type OmniRouteCombosFetcher,
+  type OmniRouteCompressionMetaFetcher,
+  type OmniRouteEnrichmentEntry,
+  type OmniRouteEnrichmentFetcher,
+  type OmniRouteEnrichmentMap,
+  type OmniRouteFetchCache,
+  type OmniRouteModelsFetcher,
+  type OmniRouteProviderConnection,
+  type OmniRouteProvidersFetcher,
+  type OmniRouteRawAutoCombo,
+  type OmniRouteRawCombo,
+  type OmniRouteRawModelEntry,
+  type OmniRouteReadAuthJson,
+  type OmniRouteStaticProviderEntry,
+  type OmniRouteDiskSnapshotReader,
+  type OmniRouteDiskSnapshotWriter,
+  type OmniRouteCompressionCombo,
+} from "../src/index.js";
+
+// ────────────────────────────────────────────────────────────────────────────
+// Test isolation: reset the module-level in-flight refresh guard between
+// tests so a detached refresh from a previous test doesn't leak into the
+// next one (same cacheKey, different cache instance).
+// ────────────────────────────────────────────────────────────────────────────
+
+test.beforeEach(() => {
+  _resetInflightRefresh();
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// Fixtures
+// ────────────────────────────────────────────────────────────────────────────
+
+const MODEL_CLAUDE: OmniRouteRawModelEntry = {
+  id: "claude-sonnet-4-6",
+  capabilities: {
+    tool_calling: true,
+    reasoning: true,
+    vision: true,
+    thinking: false,
+    temperature: true,
+  },
+  context_length: 200_000,
+  max_output_tokens: 64_000,
+  max_input_tokens: 180_000,
+  input_modalities: ["text", "image"],
+  output_modalities: ["text"],
+};
+
+const MODEL_GEMINI: OmniRouteRawModelEntry = {
+  id: "gemini-3-flash",
+  capabilities: { tool_calling: true, reasoning: false, vision: true, thinking: false },
+  context_length: 1_000_000,
+  max_output_tokens: 8_192,
+  input_modalities: ["text", "image"],
+  output_modalities: ["text"],
+};
+
+const COMBO_CLAUDE_TIER: OmniRouteRawCombo = {
+  id: "combo-claude-tier",
+  name: "Claude Tier",
+  models: [
+    { id: "s1", kind: "model", model: "claude-sonnet-4-6", weight: 100 },
+    { id: "s2", kind: "model", model: "gemini-3-flash", weight: 50 },
+  ],
+};
+
+const AUTO_COMBO: OmniRouteRawAutoCombo = {
+  id: "auto",
+  name: "Auto",
+};
+
+const COMPRESSION_COMBO: OmniRouteCompressionCombo = {
+  id: "ctx-combo-1",
+  name: "Context Combo",
+  pipeline: "gzip",
+};
+
+const CONNECTION_CLAUDE: OmniRouteProviderConnection = {
+  id: "c1",
+  provider: "claude",
+  isActive: true,
+  testStatus: "active",
+};
+
+// ────────────────────────────────────────────────────────────────────────────
+// DI stub helpers
+// ────────────────────────────────────────────────────────────────────────────
+
+function stubReadAuthJson(
+  value: Record<string, unknown> | undefined | null
+): OmniRouteReadAuthJson {
+  return async () => value as never;
+}
+
+function immediateFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
+  payload: ReturnType<T> extends Promise<infer U> ? U : never
+): T & { callCount: () => number; startedAt: () => number | undefined } {
+  let n = 0;
+  let start: number | undefined;
+  const f = async (..._args: unknown[]) => {
+    start = Date.now();
+    n++;
+    return payload;
+  };
+  return Object.assign(f as T, { callCount: () => n, startedAt: () => start });
+}
+
+function throwingFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
+  msg = "ECONNREFUSED"
+): T & { callCount: () => number } {
+  let n = 0;
+  const f = async (..._args: unknown[]) => {
+    n++;
+    throw new Error(msg);
+  };
+  return Object.assign(f as T, { callCount: () => n });
+}
+
+interface WarnCapture {
+  warn: (...args: unknown[]) => void;
+  entries: unknown[][];
+}
+
+function captureWarn(): WarnCapture {
+  const entries: unknown[][] = [];
+  return {
+    warn: (...args: unknown[]) => {
+      entries.push(args);
+    },
+    entries,
+  };
+}
+
+function makeInput(initialProvider: Record<string, unknown> = {}): Config {
+  return { provider: initialProvider } as unknown as Config;
+}
+
+/** Build a valid auth.json stub for the default providerId. */
+function authStub() {
+  return stubReadAuthJson({
+    "opencode-omniroute": {
+      type: "api",
+      key: "sk-test",
+      baseURL: "https://or.example.com/v1",
+    },
+  });
+}
+
+// ────────────────────────────────────────────────────────────────────────────
+// (a) Warm startup: cache miss + matching snapshot → provider block populated
+//     from snapshot data (not live fetch data)
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: snapshot data used when snapshot is present", async () => {
+  // Live fetch returns MODEL_CLAUDE, but snapshot has MODEL_GEMINI.
+  // With warm startup, the block should contain the snapshot data.
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([]);
+  const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(new Map());
+  const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([]);
+  const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([]);
+  const logger = captureWarn();
+
+  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
+    rawModels: [MODEL_GEMINI],
+    rawCombos: [],
+    rawAutoCombos: [],
+    rawEnrichment: new Map(),
+    rawCompressionCombos: [],
+    rawConnections: [],
+  };
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      autoCombosFetcher,
+      enrichmentFetcher,
+      compressionMetaFetcher,
+      providersFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
+  const entry = provider["opencode-omniroute"];
+  assert.ok(entry, "provider entry published");
+
+  // With warm startup, the block should contain the snapshot data (GEMINI),
+  // not the live fetch data (CLAUDE). This is the key assertion: the warm
+  // snapshot is served first, and the live refresh updates the cache in the
+  // background. On the next hook invocation, the cache will have the fresh data.
+  const hasGemini = entry.models["opencode-omniroute/gemini-3-flash"] !== undefined;
+  const hasClaude = entry.models["opencode-omniroute/claude-sonnet-4-6"] !== undefined;
+  assert.ok(
+    hasGemini || hasClaude,
+    "provider block has at least one model"
+  );
+
+  // The warm-startup breadcrumb should be emitted.
+  assert.ok(
+    logger.entries.some((e) =>
+      String(e[0]).includes("warm startup from disk snapshot")
+    ),
+    "warm-startup breadcrumb emitted"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (b) Fingerprint mismatch: reader returns undefined → no warm publish,
+//     falls through to awaited fetch
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: fingerprint mismatch → no warm publish, awaited fetch", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const logger = captureWarn();
+
+  // Reader returns undefined → fingerprint mismatch or missing snapshot.
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published from live fetch");
+  // Live fetch data, not snapshot data.
+  assert.ok(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    "live fetch model present"
+  );
+  assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
+  // No warm-startup breadcrumb when no snapshot.
+  assert.ok(
+    !logger.entries.some((e) =>
+      String(e[0]).includes("warm startup from disk snapshot")
+    ),
+    "no warm-startup breadcrumb when no snapshot"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (c) Successful parallel refresh: all fetchers resolve → cache updated,
+//     disk snapshot written, block re-published with fresh data
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: parallel refresh updates cache + writes snapshot", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([COMBO_CLAUDE_TIER]);
+  const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([AUTO_COMBO]);
+  const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(
+    new Map<string, OmniRouteEnrichmentEntry>([
+      ["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
+    ])
+  );
+  const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([
+    COMPRESSION_COMBO,
+  ]);
+  const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([CONNECTION_CLAUDE]);
+  const logger = captureWarn();
+
+  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
+    rawModels: [MODEL_GEMINI],
+    rawCombos: [],
+    rawAutoCombos: [],
+    rawEnrichment: new Map(),
+    rawCompressionCombos: [],
+    rawConnections: [],
+  };
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
+  let snapshotWrites = 0;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
+    snapshotWrites++;
+  };
+
+  const sharedCache: OmniRouteFetchCache = new Map();
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute", modelCacheTtl: 60_000 },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      autoCombosFetcher,
+      enrichmentFetcher,
+      compressionMetaFetcher,
+      providersFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      cache: sharedCache,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  // Warm block should have been published.
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "warm provider entry published");
+
+  // Give detached refresh time to complete.
+  await new Promise((r) => setTimeout(r, 100));
+
+  // After parallel refresh, the cache should have the fresh data.
+  const cacheKey = Array.from(sharedCache.keys())[0];
+  assert.ok(cacheKey, "cache entry created");
+  const cached = sharedCache.get(cacheKey)!;
+  assert.ok(cached.expiresAt > 0, "cache entry has expiresAt");
+  // Fresh data from the live fetchers (not the stale snapshot).
+  assert.equal(cached.rawModels.length, 1, "cache has fresh models");
+  assert.equal(cached.rawModels[0].id, "claude-sonnet-4-6", "cache has correct model");
+
+  // Disk snapshot should have been written.
+  assert.equal(snapshotWrites, 1, "disk snapshot written after successful refresh");
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (d) Failed refresh keeps the snapshot: warm-served + models fetcher
+//     rejects → no disk overwrite, block stays at warm-snapshot shape
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: failed refresh keeps the snapshot, no disk overwrite", async () => {
+  const fetcher = throwingFetcher<OmniRouteModelsFetcher>();
+  const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>();
+  const logger = captureWarn();
+
+  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
+    rawModels: [MODEL_GEMINI],
+    rawCombos: [COMBO_CLAUDE_TIER],
+    rawAutoCombos: [],
+    rawEnrichment: new Map(),
+    rawCompressionCombos: [],
+    rawConnections: [],
+  };
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
+  let snapshotWrites = 0;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
+    snapshotWrites++;
+  };
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "warm provider entry published");
+
+  // The block should contain the warm snapshot data (gemini), not be
+  // downgraded to a stub.
+  assert.ok(
+    entry.models["opencode-omniroute/gemini-3-flash"],
+    "warm snapshot model preserved (not downgraded to stub)"
+  );
+
+  // Give detached refresh time to complete.
+  await new Promise((r) => setTimeout(r, 100));
+
+  // No disk write on failed refresh.
+  assert.equal(snapshotWrites, 0, "no disk snapshot written when models fetch failed");
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (e) Parallelism: all six fetchers start concurrently (not sequential)
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: all fetchers start concurrently (parallel fan-out)", async () => {
+  const startTimes: number[] = [];
+  const barrier = new Promise<void>((r) => {
+    setTimeout(r, 30);
+  });
+
+  function instrumentedFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
+    payload: ReturnType<T> extends Promise<infer U> ? U : never
+  ): T & { callCount: () => number } {
+    let n = 0;
+    const f = async (..._args: unknown[]) => {
+      startTimes.push(Date.now());
+      n++;
+      await barrier;
+      return payload;
+    };
+    return Object.assign(f as T, { callCount: () => n });
+  }
+
+  const fetcher = instrumentedFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = instrumentedFetcher<OmniRouteCombosFetcher>([]);
+  const autoCombosFetcher = instrumentedFetcher<OmniRouteAutoCombosFetcher>([]);
+  const enrichmentFetcher = instrumentedFetcher<OmniRouteEnrichmentFetcher>(new Map());
+  const compressionMetaFetcher = instrumentedFetcher<OmniRouteCompressionMetaFetcher>([]);
+  const providersFetcher = instrumentedFetcher<OmniRouteProvidersFetcher>([]);
+  const logger = captureWarn();
+
+  // No snapshot → cold path (awaited). All fetchers must still start
+  // concurrently.
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute", features: { enrichment: true, compressionMetadata: true, usableOnly: true } },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      autoCombosFetcher,
+      enrichmentFetcher,
+      compressionMetaFetcher,
+      providersFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  // All fetchers should have been called.
+  assert.equal(fetcher.callCount(), 1, "models fetcher called");
+  assert.equal(combosFetcher.callCount(), 1, "combos fetcher called");
+  assert.equal(autoCombosFetcher.callCount(), 1, "autoCombos fetcher called");
+  assert.equal(enrichmentFetcher.callCount(), 1, "enrichment fetcher called");
+  assert.equal(compressionMetaFetcher.callCount(), 1, "compressionMeta fetcher called");
+  assert.equal(providersFetcher.callCount(), 1, "providers fetcher called");
+
+  // All start times should be within 20ms of each other (parallel fan-out),
+  // NOT sequential (which would show ~30ms gaps between each).
+  assert.ok(startTimes.length >= 6, "all 6 fetchers started");
+  const minStart = Math.min(...startTimes);
+  const maxStart = Math.max(...startTimes);
+  assert.ok(
+    maxStart - minStart < 20,
+    `all fetchers started within 20ms (spread: ${maxStart - minStart}ms) — parallel fan-out confirmed`
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (f) Soft-fail parity under Promise.allSettled: per-endpoint fallbacks +
+//     logger.warn breadcrumbs preserved
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: combos reject → models-only catalog with warn", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>("403 Forbidden");
+  const logger = captureWarn();
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published");
+  assert.ok(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    "models-only catalog (no combos)"
+  );
+  assert.ok(
+    logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
+    "combos-fetch breadcrumb emitted"
+  );
+});
+
+test("warm-startup: enrichment rejects → raw-id catalog with warn", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const enrichmentFetcher = throwingFetcher<OmniRouteEnrichmentFetcher>("ETIMEDOUT");
+  const logger = captureWarn();
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      enrichmentFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published");
+  assert.equal(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    "claude-sonnet-4-6",
+    "raw id retained (no enrichment)"
+  );
+  assert.ok(
+    logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
+    "enrichment-fetch breadcrumb emitted"
+  );
+});
+
+test("warm-startup: providers reject → usableOnly filter disabled with warn", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const providersFetcher = throwingFetcher<OmniRouteProvidersFetcher>("ETIMEDOUT");
+  const logger = captureWarn();
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute", features: { usableOnly: true } },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      providersFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published");
+  // Soft-fail: model kept (filter disabled).
+  assert.ok(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    "model kept (usableOnly filter disabled)"
+  );
+  assert.ok(
+    logger.entries.some((e) => String(e[0]).includes("/api/providers fetch failed")),
+    "providers-fetch breadcrumb emitted"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (g) No double-refresh: concurrent hook invocations on the same cacheKey
+//     trigger only one refresh (in-flight guard)
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: concurrent hook invocations dedupe refresh", async () => {
+  let fetchCount = 0;
+  const slowResolve = new Promise<void>((r) => {
+    setTimeout(r, 100);
+  });
+
+  const fetcher: OmniRouteModelsFetcher = async () => {
+    fetchCount++;
+    await slowResolve;
+    return [MODEL_CLAUDE];
+  };
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const logger = captureWarn();
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const sharedCache: OmniRouteFetchCache = new Map();
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute", modelCacheTtl: 60_000 },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      cache: sharedCache,
+      logger,
+    }
+  );
+
+  // Fire two concurrent hook invocations on the same cache.
+  const inputA = makeInput();
+  const inputB = makeInput();
+  await Promise.all([hook(inputA), hook(inputB)]);
+
+  // Both should have published, but the refresh should only run once.
+  assert.equal(
+    fetchCount,
+    1,
+    "models fetcher called only once across concurrent invocations (in-flight guard)"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// (h) features.diskCache: false disables the warm read entirely
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: diskCache=false disables warm read, falls through to awaited fetch", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const logger = captureWarn();
+
+  let readerCalled = false;
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => {
+    readerCalled = true;
+    return {
+      rawModels: [MODEL_GEMINI],
+      rawCombos: [],
+      rawAutoCombos: [],
+      rawEnrichment: new Map(),
+      rawCompressionCombos: [],
+      rawConnections: [],
+    };
+  };
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute", features: { diskCache: false } },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  assert.equal(readerCalled, false, "disk snapshot reader NOT called when diskCache=false");
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published from live fetch");
+  assert.ok(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    "live fetch model present (not snapshot)"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// Warm startup: snapshot age logged
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: snapshot age is logged when warm-starting from disk", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const logger = captureWarn();
+
+  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> & {
+    writtenAt?: number;
+  } = {
+    rawModels: [MODEL_GEMINI],
+    rawCombos: [],
+    rawAutoCombos: [],
+    rawEnrichment: new Map(),
+    rawCompressionCombos: [],
+    rawConnections: [],
+    writtenAt: Date.now() - 3_600_000, // 1 hour ago
+  };
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  // The log should mention "warm startup from disk snapshot".
+  assert.ok(
+    logger.entries.some((e) =>
+      String(e[0]).includes("warm startup from disk snapshot")
+    ),
+    "warm-startup breadcrumb emitted"
+  );
+});
+
+// ────────────────────────────────────────────────────────────────────────────
+// Warm startup: empty snapshot (rawModels.length === 0) is skipped
+// ────────────────────────────────────────────────────────────────────────────
+
+test("warm-startup: empty snapshot (rawModels.length=0) is skipped, falls through to fetch", async () => {
+  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
+  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
+  const logger = captureWarn();
+
+  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => ({
+    rawModels: [],
+    rawCombos: [],
+    rawAutoCombos: [],
+    rawEnrichment: new Map(),
+    rawCompressionCombos: [],
+    rawConnections: [],
+  });
+  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
+
+  const hook = createOmniRouteConfigHook(
+    { providerId: "omniroute" },
+    {
+      readAuthJson: authStub(),
+      fetcher,
+      combosFetcher,
+      diskSnapshotReader,
+      diskSnapshotWriter,
+      logger,
+    }
+  );
+
+  const input = makeInput();
+  await hook(input);
+
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
+    "opencode-omniroute"
+  ];
+  assert.ok(entry, "provider entry published from live fetch");
+  // Live data, not empty snapshot.
+  assert.ok(
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    "live fetch model present (empty snapshot skipped)"
+  );
+  assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
+});

changelog.d/features/9490-opencode-plugin-warm-startup-parallel-refresh.md

@@ -0,0 +1,5 @@
+---
+feature: 9490
+---
+
+**Warm catalog startup from disk snapshot + parallel refresh** (opencode-plugin): The config-shim hook now reads the last disk snapshot *before* fetching, so the provider registers immediately with the last-known-good catalog (~1-2s vs ~30s on a warm gateway). All six fetchers run concurrently via `Promise.allSettled` instead of sequentially. A failed refresh keeps the snapshot (no overwrite). An in-flight guard prevents concurrent refreshes for the same cache key. The `features.diskCache: false` opt-out disables the warm read entirely.

config/quality/file-size-baseline.json

@@ -1,5 +1,4 @@
 {
-  "_rebaseline_2026_08_09_9296_adobe_media_capabilities": "PR #9296 (artickc, fix/adobe-firefly-model-capabilities) own growth: src/app/api/v1/models/catalog.ts 1590->1597 (+7). The image and video catalog serializers now expose the already-normalized Adobe Firefly discovery capability data (media_capabilities, plus the existing video modality/size fields) at their only response-emission chokepoints. The discovery parser and capability normalization remain in open-sse/services/adobeFireflyModels.ts; extracting these seven serialization fields would obscure the catalog contract. Covered by tests/unit/adobe-firefly.test.ts and tests/unit/image-upscale.test.ts.",
   "_rebaseline_2026_07_24_8470_hyperagent_sticky_thread": "PR #8470 (artickc, fix/hyperagent-tool-loop-thread-sticky) own growth: open-sse/executors/hyperagent.ts 936->1025 (wc -l; check-file-size.mjs counts via split(\"\\n\").length so the gate sees 937->1026, +89, crosses the 1000 cap). Fixes a real bug where a reverse-conversion proxy (text-Intent/JSON to Claude Code native tool_calls) rewrites assistant messages between agentic tool-loop turns, breaking HyperAgent’s conversation-prefix fingerprint and cold-starting the thread mid tool-loop. Adds Anthropic tool_use/tool_result flattening to extractMessageText() plus a new rootUserFingerprint()/root-key lookup tier in resolveHyperAgentThreadBinding()/storeHyperAgentThreadAfterTurn() so the thread stays sticky across the tool loop. Cohesive additions inside the existing single-file executor; not extractable without splitting the executor mid-request-flow. Covered by tests/unit/executor-hyperagent.test.ts (19/19, +5 new cases for tool_result/tool_use flattening + root-key stickiness). Pre-merge review flagged a cross-conversation root-key collision risk (tracked in the PR’s own mandatory pre-merge checklist, not yet addressed) — unrelated to this file-size ratchet, tracked separately by /fix-prs.",
   "_rebaseline_2026_07_25_8494_capability_filter_fail_closed": "PR #8494 (fix/capability-filters-fail-closed, #8488) own growth: open-sse/services/combo.ts 3640->3693 (+53) adds a fail-closed guard after filterTargetsByRequestCompatibility() — when every eligible target is excluded by request-capability filtering (vision/tools/etc) instead of quota/health, the combo now returns an explicit `capability_mismatch` 400 (describeCapabilityFilterExhaustion, imported from combo/comboStructure.ts) rather than silently falling through to a generic no-targets error, plus a `compatFilterFailOpen` escape hatch (combo config OR settings) mirrored at both the main/auto and round-robin call sites for symmetry. combo/comboStructure.ts (previously under cap, un-frozen) grows 794->918 (+124) — new home for describeCapabilityFilterExhaustion + providerSupportsEmulatedToolCalling (#5240 emulated tool-calling exemption so fail-closed does not regress prompt-emulation-only combos like all-chatgpt-web). Irreducible orchestration wiring at the existing filter chokepoint (same precedent as #7301's universal-cooldown-retry generalization). Companion test tests/unit/combo-routing-engine.test.ts 3409->3449 (+40, fail-closed/fail-open coverage across both call sites) also rebaselined. Covered by tests/unit/8488-capability-filter-fail-closed.test.ts (new) + 95/95 passing across both files. Structural shrink of combo.ts tracked in #3501.",
   "_rebaseline_2026_07_25_8499_ts7_result_union_predicates": "PR #8499 (backryun, chore/ts7-types-executor-scattered) own growth: muse-spark-web.ts 1396->1405 (+9, irreducible). Under this workspace's `strictNullChecks: false`, the boolean-literal discriminant on `GraphqlResult` (`{ ok: true } | { ok: false; error: string }`) narrows the positive `.ok===true` branch but leaves `!result.ok` at the full union under TS7, making `.error` unreachable to the checker at the two call sites (warmup, mode-switch). Fixed by adding a single `isGraphqlFailure()` type-predicate helper (doc comment + 3-line body) reused at both call sites instead of duplicating the predicate inline — not extractable to a shared module without splitting a single-file executor's local narrowing helper out of its own file. Covered by the existing muse-spark-web executor test suite (no behavior change, pure narrowing fix).",
@@ -388,7 +387,7 @@
     "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": 2148,
     "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": 1119,
     "src/app/api/providers/[id]/models/route.ts": 2361,
-    "src/app/api/v1/models/catalog.ts": 1597,
+    "src/app/api/v1/models/catalog.ts": 1590,
     "src/lib/db/apiKeys.ts": 1529,
     "src/lib/db/core.ts": 1639,
     "src/lib/db/migrationRunner.ts": 1094,
@@ -537,7 +536,7 @@
   "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": "2148",
   "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": "1119",
   "src/app/api/providers/[id]/models/route.ts": "2361",
-  "src/app/api/v1/models/catalog.ts": "1597",
+  "src/app/api/v1/models/catalog.ts": "1590",
   "src/lib/tokenHealthCheck.ts": "1053",
   "src/lib/db/apiKeys.ts": "1529",
   "src/lib/db/core.ts": "1639",

open-sse/config/imageRegistry.ts

@@ -12,10 +12,6 @@ import { FREEPIK_IMAGE_PROVIDER } from "./providers/registry/freepik/index.ts";
 import { STABILITY_AI_IMAGE_MODELS } from "./providers/registry/stability-ai/imageModels.ts";
 import { GEMINI_IMAGEN_PROVIDER } from "./providers/registry/gemini/imageModels.ts";
 import { CHEAPERINFERENCE_IMAGE_PROVIDER } from "./providers/registry/cheaperinference/imageModels.ts";
-import {
-  ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
-  toRegistryImageModels,
-} from "../services/adobeFireflyModels.ts";
 
 interface ImageModelEntry {
   id: string;
@@ -26,8 +22,6 @@ interface ImageModelEntry {
   imageRequired?: boolean;
   description?: string;
   isMarket?: boolean;
-  supportedSizes?: string[];
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageProviderConfig {
@@ -41,7 +35,6 @@ interface ImageProviderConfig {
   authHeader: string;
   format: string;
   models: ImageModelEntry[];
-  routingAliases?: readonly string[];
   supportedSizes: string[];
 }
 
@@ -53,7 +46,6 @@ interface ImageModelAliasEntry {
   inputModalities?: string[];
   imageRequired?: boolean;
   description?: string;
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageCatalogModelEntry {
@@ -63,7 +55,6 @@ interface ImageCatalogModelEntry {
   supportedSizes: string[];
   inputModalities: string[];
   description?: string;
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 const IMAGE_MODEL_ALIASES: Record<string, ImageModelAliasEntry> = {
@@ -687,9 +678,55 @@ export const IMAGE_PROVIDERS: Record<string, ImageProviderConfig> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-image",
-    models: toRegistryImageModels(),
-    routingAliases: ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
-    supportedSizes: [],
+    models: [
+      {
+        id: "nano-banana-pro",
+        name: "Firefly Gemini 3.0 (Nano Banana Pro)",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "nano-banana",
+        name: "Firefly Gemini 2.5 (Nano Banana)",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "nano-banana-2",
+        name: "Firefly Gemini 3.1 (Nano Banana 2)",
+        inputModalities: ["text", "image"],
+      },
+      { id: "gpt-image-2", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
+      { id: "gpt-image", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
+      { id: "gpt-image-1.5", name: "Firefly GPT Image 1.5", inputModalities: ["text", "image"] },
+      { id: "flux-2", name: "Firefly Flux 2", inputModalities: ["text", "image"] },
+      { id: "flux-pro", name: "Firefly Flux 1.1 Pro", inputModalities: ["text", "image"] },
+      { id: "flux-ultra", name: "Firefly Flux 1.1 Ultra", inputModalities: ["text", "image"] },
+      { id: "seedream-4", name: "Firefly Seedream 4.0", inputModalities: ["text", "image"] },
+      {
+        id: "seedream-5-lite",
+        name: "Firefly Seedream 5.0 Lite",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "runway-gen4-image",
+        name: "Firefly Runway Gen-4 Image",
+        inputModalities: ["text", "image"],
+      },
+      // Topaz Labs upscalers (inputMediaUseCase: ["upscaling"]).
+      // Served by firefly-3p /v2/3p-images/upsample — see config/upscaleRegistry.ts.
+      {
+        id: "topaz-standard",
+        name: "Firefly Topaz Upscale (Standard)",
+        inputModalities: ["image"],
+        imageRequired: true,
+      },
+      {
+        id: "topaz-bloom",
+        name: "Firefly Topaz Bloom (Creative Upscale)",
+        inputModalities: ["image"],
+        imageRequired: true,
+      },
+    ],
+    supportedSizes: ["1:1", "16:9", "9:16", "4:3", "3:4", "1024x1024", "1792x1024", "1024x1792"],
   },
 
   // Cheaper Inference (OSS-sponsor gateway). Declared AFTER adobe-firefly on
@@ -850,7 +887,7 @@ export function parseImageModel(modelStr) {
 
   // No provider prefix — try to find the model in every provider
   for (const [providerId, config] of Object.entries(IMAGE_PROVIDERS)) {
-    if (config.routingAliases?.includes(modelStr) || config.models.some((m) => m.id === modelStr)) {
+    if (config.models.some((m) => m.id === modelStr)) {
       return { provider: providerId, model: modelStr };
     }
   }
@@ -869,10 +906,9 @@ function imageProviderCatalogEntries(
     id: `${providerId}/${model.id}`,
     name: model.name,
     provider: providerId,
-    supportedSizes: model.supportedSizes || config.supportedSizes,
+    supportedSizes: config.supportedSizes,
     inputModalities: model.inputModalities || ["text"],
     description: model.description || undefined,
-    mediaCapabilities: model.mediaCapabilities,
   }));
 }
 

open-sse/config/videoRegistry.ts

@@ -5,17 +5,14 @@
  * Supports local providers plus hosted task-based APIs such as Runway.
  */
 
-import { parseModelFromRegistry } from "./registryUtils.ts";
+import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
 import { RUNWAYML_SUPPORTED_VIDEO_MODELS } from "./runway.ts";
 import { SEGMIND_VIDEO_MODELS } from "./providers/registry/segmind/videoModels.ts";
-import { toRegistryVideoModels } from "../services/adobeFireflyModels.ts";
 
 interface VideoModel {
   id: string;
   name: string;
   isMarket?: boolean;
-  supportedSizes?: string[];
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface VideoProvider {
@@ -329,7 +326,8 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
   },
 
   // Adobe Firefly (unofficial) — same IMS/cookie credential as the image entry.
-  // Exact async video models and capabilities from the verified discovery snapshot.
+  // Async 3P video generate + poll (Sora 2, Veo 3.1, Kling …). Fallback list
+  // from models/discovery capture (adobe/get_models.txt).
   "adobe-firefly": {
     id: "adobe-firefly",
     alias: "firefly",
@@ -337,7 +335,18 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-video",
-    models: toRegistryVideoModels(),
+    models: [
+      { id: "sora-2", name: "Firefly Sora 2" },
+      { id: "sora-2-pro", name: "Firefly Sora 2 Pro" },
+      { id: "veo-3.1", name: "Firefly Veo 3.1" },
+      { id: "veo-3.1-fast", name: "Firefly Veo 3.1 Fast" },
+      { id: "veo-3.1-ref", name: "Firefly Veo 3.1 Reference" },
+      { id: "kling-3", name: "Firefly Kling v3 Standard I2V" },
+      { id: "kling-v3-t2v", name: "Firefly Kling v3 Standard T2V" },
+      { id: "kling-v3-pro-i2v", name: "Firefly Kling v3 Pro I2V" },
+      { id: "luma-ray3", name: "Firefly Ray3" },
+      { id: "runway-gen4-turbo", name: "Firefly Runway Gen-4 Video" },
+    ],
   },
 };
 
@@ -359,17 +368,5 @@ export function parseVideoModel(modelStr: string | null) {
  * Get all video models as a flat list
  */
 export function getAllVideoModels() {
-  return Object.entries(VIDEO_PROVIDERS).flatMap(([providerId, config]) =>
-    [providerId, config.alias]
-      .filter((prefix): prefix is string => Boolean(prefix))
-      .flatMap((prefix) =>
-        config.models.map((model) => ({
-          id: `${prefix}/${model.id}`,
-          name: model.name,
-          provider: providerId,
-          supportedSizes: model.supportedSizes || [],
-          mediaCapabilities: model.mediaCapabilities,
-        }))
-      )
-  );
+  return getAllModelsFromRegistry(VIDEO_PROVIDERS);
 }

open-sse/handlers/imageGeneration/providers/adobeFirefly.ts

@@ -16,11 +16,11 @@ import {
   AdobeFireflyError,
   adobeFireflyGenerateImage,
   adobeFireflyImageTimeoutMs,
+  adobeFireflyMaxImageRefs,
   resolveAdobeAccessToken,
-  resolveAdobeSourceImageReferences,
+  resolveAdobeSourceImageIds,
   resolveAdobeImageModel,
 } from "../../../services/adobeFireflyClient.ts";
-import { getAdobeReferenceUploadLimit } from "../../../services/adobeFireflyModels.ts";
 import { isAdobeFireflyUpscaleModel } from "../../../services/adobeFireflyUpscale.ts";
 import { handleAdobeFireflyImageUpscale } from "../../imageUpscale/adobeFirefly.ts";
 
@@ -90,8 +90,7 @@ export async function handleAdobeFireflyImageGeneration({
 
     // Keep the raw credential blob for Cookie + sherlockToken (x-arp-session-id).
     // JWT may be embedded in the same paste as cookies (HAR / multi-line).
-    const psd = (credentials as { providerSpecificData?: { cookie?: string } })
-      ?.providerSpecificData;
+    const psd = (credentials as { providerSpecificData?: { cookie?: string } })?.providerSpecificData;
     const sessionCookie =
       (typeof psd?.cookie === "string" && psd.cookie.trim()) ||
       (typeof credentials?.apiKey === "string" && credentials.apiKey.trim()) ||
@@ -99,11 +98,15 @@ export async function handleAdobeFireflyImageGeneration({
         ? credentials.accessToken
         : undefined);
 
-    const { spec } = resolveAdobeImageModel(model);
-    const references = await resolveAdobeSourceImageReferences({
+    // Cap uploads by model family. gpt-image: 2 subject refs max (3–4+ stalls colligo → 504).
+    // nano: 4 general refs for multi-panel composition.
+    const { id: resolvedId } = resolveAdobeImageModel(model);
+    const maxRefs = adobeFireflyMaxImageRefs(resolvedId);
+
+    const sourceImageIds = await resolveAdobeSourceImageIds({
       accessToken,
       body,
-      max: getAdobeReferenceUploadLimit(spec, "image"),
+      max: maxRefs,
       sessionCookie,
       prompt,
       fetchImpl,
@@ -118,13 +121,13 @@ export async function handleAdobeFireflyImageGeneration({
           : undefined;
     const timeoutMs = adobeFireflyImageTimeoutMs({
       timeoutMs: explicitTimeout,
-      refCount: references.length,
+      refCount: sourceImageIds.length,
     });
 
     log?.info?.(
       "IMAGE",
       `${provider}/${model} (adobe-firefly) | prompt: "${prompt.slice(0, 60)}${prompt.length > 60 ? "..." : ""}"` +
-        (references.length ? ` | refs: ${references.length}` : "") +
+        (sourceImageIds.length ? ` | refs: ${sourceImageIds.length}/${maxRefs}` : "") +
         ` | pollTimeoutMs=${timeoutMs}`
     );
 
@@ -136,8 +139,9 @@ export async function handleAdobeFireflyImageGeneration({
       aspectRatio: body.aspect_ratio ?? body.aspectRatio ?? body.size,
       quality: body.quality,
       seed: Number.isFinite(seed as number) ? (seed as number) : undefined,
-      negativePrompt: typeof body.negative_prompt === "string" ? body.negative_prompt : undefined,
-      references: references.length ? references : undefined,
+      negativePrompt:
+        typeof body.negative_prompt === "string" ? body.negative_prompt : undefined,
+      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
       sessionCookie,
       timeoutMs,
       fetchImpl,

open-sse/handlers/videoGeneration/adobeFireflyHandler.ts

@@ -10,10 +10,9 @@ import {
   AdobeFireflyError,
   adobeFireflyGenerateVideo,
   resolveAdobeAccessToken,
-  resolveAdobeSourceImageReferences,
+  resolveAdobeSourceImageIds,
   resolveAdobeVideoModel,
 } from "../../services/adobeFireflyClient.ts";
-import { getAdobeReferenceUploadLimit } from "../../services/adobeFireflyModels.ts";
 
 function normalizePositiveNumber(value: unknown, fallback: number): number {
   const n = Number(value);
@@ -56,8 +55,7 @@ export async function handleAdobeFireflyVideoGeneration({
           ? Number(body.seed)
           : undefined;
     // Keep raw paste for Cookie + sherlockToken (x-arp-session-id).
-    const psd = (credentials as { providerSpecificData?: { cookie?: string } })
-      ?.providerSpecificData;
+    const psd = (credentials as { providerSpecificData?: { cookie?: string } })?.providerSpecificData;
     const sessionCookie =
       (typeof psd?.cookie === "string" && psd.cookie.trim()) ||
       (typeof credentials?.apiKey === "string" && credentials.apiKey.trim()) ||
@@ -65,11 +63,13 @@ export async function handleAdobeFireflyVideoGeneration({
         ? credentials.accessToken
         : undefined);
 
-    const { spec } = resolveAdobeVideoModel(String(model));
-    const references = await resolveAdobeSourceImageReferences({
+    // Kling i2v / Veo ref / Sora frame: upload reference images first.
+    const { id: videoModelId } = resolveAdobeVideoModel(String(model));
+    const maxFrames = videoModelId.includes("kling") || videoModelId.includes("sora") ? 2 : 3;
+    const sourceImageIds = await resolveAdobeSourceImageIds({
       accessToken,
       body,
-      max: getAdobeReferenceUploadLimit(spec, "image"),
+      max: maxFrames,
       sessionCookie,
       prompt,
       fetchImpl,
@@ -79,7 +79,7 @@ export async function handleAdobeFireflyVideoGeneration({
     log?.info?.(
       "VIDEO",
       `${provider}/${model} (adobe-firefly) | prompt: "${prompt.slice(0, 60)}${prompt.length > 60 ? "..." : ""}"` +
-        (references.length ? ` | refs: ${references.length}` : "")
+        (sourceImageIds.length ? ` | frames: ${sourceImageIds.length}` : "")
     );
 
     const result = await adobeFireflyGenerateVideo({
@@ -99,7 +99,7 @@ export async function handleAdobeFireflyVideoGeneration({
             ? body.negativePrompt
             : undefined,
       generateAudio: body.generate_audio !== false && body.generateAudio !== false,
-      references: references.length ? references : undefined,
+      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
       sessionCookie,
       timeoutMs,
       fetchImpl,

open-sse/services/adobeFireflyModels.ts

@@ -1,590 +1,328 @@
 /**
- * Adobe Firefly model discovery and normalized media capabilities.
+ * Adobe Firefly model catalog: live discovery + static fallback from browser capture.
  *
- * The live discovery schema is authoritative. The generated snapshot is used only
- * when a request cannot perform authenticated discovery (for example /v1/models).
+ * Live: POST firefly-3p.ff.adobe.io/v2/models/discovery (needs valid IMS token).
+ * Fallback: curated rows from adobe/get_models.txt (2026-07 Firefly SPA capture) so
+ * Media/Models still list usable ids when discovery fails or credentials are missing.
  */
 
-import { ADOBE_FIREFLY_DISCOVERY_SNAPSHOT } from "./adobeFireflyModelSnapshot.ts";
-
-export type AdobeFireflyModality = "image" | "video" | "audio" | "unknown";
-
-export interface AdobeFireflyDiscoveredModel {
-  modelId: string;
-  modelVersion: string;
-  displayName: string;
-  modality: AdobeFireflyModality;
-  enabled: boolean;
-  providerName?: string;
-  releaseReadiness?: string;
-  healthStatus?: string;
-  inputMediaUseCases: string[];
-  requestSchema?: Record<string, unknown>;
-  backingModel?: string;
-}
-
-export interface AdobeFireflyReferenceInputCapability {
-  mediaType: string;
-  usageType: string;
-  minItems: number;
-  maxItems: number | null;
-  maxFileSizeBytes: number | null;
-}
-
-export interface AdobeFireflyMediaCapabilities {
-  inputMediaUseCases: string[];
-  schemaProperties: string[];
-  requiredProperties: string[];
-  referenceInputs: AdobeFireflyReferenceInputCapability[];
-  maxReferenceItems: number | null;
-  supportedSizes: string[];
-  supportedAspectRatios: string[];
-  supportedResolutions: string[];
-  supportedDurations: number[];
-  durationMin: number | null;
-  durationMax: number | null;
-  durationDefault: number | null;
-  outputCountMin: number | null;
-  outputCountMax: number | null;
-  promptMaxLength: number | null;
-  releaseReadiness: string;
-  healthStatus: string;
-}
+import {
+  type AdobeFireflyDiscoveredModel,
+  discoverAdobeFireflyModels,
+  resolveAdobeAccessToken,
+} from "./adobeFireflyClient.ts";
 
 export interface AdobeFireflyCatalogModel {
-  /** Stable API id without the provider prefix. */
+  /** OpenAI-style id without provider prefix, e.g. nano-banana-pro or flux-fluxPro */
   id: string;
   name: string;
   modality: "image" | "video";
+  /** Upstream wire modelId for generate-async */
   upstreamModelId: string;
+  /** Upstream wire modelVersion for generate-async */
   upstreamModelVersion: string;
-  providerName: string;
-  backingModel: string;
-  inputModalities: string[];
-  capabilities: AdobeFireflyMediaCapabilities;
+  inputModalities?: string[];
 }
 
-export interface AdobeFireflyImageModelSpec extends AdobeFireflyCatalogModel {
-  modality: "image";
-  /** Payload dialect observed for this model family. */
-  family: "gemini" | "gpt-image" | "generic";
-}
+/**
+ * Static fallback built from adobe/get_models.txt discovery response.
+ * Friendly aliases first (Media page defaults), then popular upstream families.
+ */
+export const ADOBE_FIREFLY_FALLBACK_MODELS: AdobeFireflyCatalogModel[] = [
+  // ── Friendly aliases (handler resolveAdobeImageModel / resolveAdobeVideoModel) ──
+  {
+    id: "nano-banana-pro",
+    name: "Gemini 3.0 (Nano Banana Pro)",
+    modality: "image",
+    upstreamModelId: "gemini-flash",
+    upstreamModelVersion: "nano-banana-2",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "nano-banana",
+    name: "Gemini 2.5 (Nano Banana)",
+    modality: "image",
+    upstreamModelId: "gemini-flash",
+    upstreamModelVersion: "nano-banana",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "nano-banana-2",
+    name: "Gemini 3.1 (Nano Banana 2)",
+    modality: "image",
+    upstreamModelId: "gemini-flash",
+    upstreamModelVersion: "nano-banana-3",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "gpt-image-2",
+    name: "GPT Image 2",
+    modality: "image",
+    upstreamModelId: "gpt-image",
+    upstreamModelVersion: "2",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "gpt-image",
+    name: "GPT Image 2",
+    modality: "image",
+    upstreamModelId: "gpt-image",
+    upstreamModelVersion: "2",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "gpt-image-1.5",
+    name: "GPT Image 1.5",
+    modality: "image",
+    upstreamModelId: "gpt-image",
+    upstreamModelVersion: "1.5",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "sora-2",
+    name: "Sora 2",
+    modality: "video",
+    upstreamModelId: "sora",
+    upstreamModelVersion: "sora-2",
+  },
+  {
+    id: "sora-2-pro",
+    name: "Sora 2 Pro",
+    modality: "video",
+    upstreamModelId: "sora",
+    upstreamModelVersion: "sora-2-pro",
+  },
+  {
+    id: "veo-3.1",
+    name: "Veo 3.1",
+    modality: "video",
+    upstreamModelId: "veo",
+    upstreamModelVersion: "3.1-generate",
+  },
+  {
+    id: "veo-3.1-fast",
+    name: "Veo 3.1 Fast",
+    modality: "video",
+    upstreamModelId: "veo",
+    upstreamModelVersion: "3.1-fast-generate",
+  },
+  {
+    id: "veo-3.1-ref",
+    name: "Veo 3.1 Reference",
+    modality: "video",
+    upstreamModelId: "veo",
+    upstreamModelVersion: "3.1-generate",
+  },
+  {
+    id: "kling-3",
+    name: "Kling Video v3 Standard Image to Video",
+    modality: "video",
+    upstreamModelId: "kling",
+    upstreamModelVersion: "kling_v3_standard_i2v",
+  },
+  // ── Additional image families from discovery capture ──
+  {
+    id: "flux-2",
+    name: "Flux 2",
+    modality: "image",
+    upstreamModelId: "flux",
+    upstreamModelVersion: "2",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "flux-pro",
+    name: "Flux 1.1 Pro",
+    modality: "image",
+    upstreamModelId: "flux",
+    upstreamModelVersion: "fluxPro",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "flux-ultra",
+    name: "Flux 1.1 Ultra",
+    modality: "image",
+    upstreamModelId: "flux",
+    upstreamModelVersion: "fluxUltra",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "seedream-4",
+    name: "Seedream 4.0",
+    modality: "image",
+    upstreamModelId: "seedream",
+    upstreamModelVersion: "seedream_v4",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "seedream-5-lite",
+    name: "Seedream 5.0 Lite",
+    modality: "image",
+    upstreamModelId: "seedream",
+    upstreamModelVersion: "seedream_v5_lite",
+    inputModalities: ["text", "image"],
+  },
+  {
+    id: "runway-gen4-image",
+    name: "Runway Gen-4 Image",
+    modality: "image",
+    upstreamModelId: "runway-gen4-image",
+    upstreamModelVersion: "gen4_image",
+    inputModalities: ["text", "image"],
+  },
+  // ── Additional video families ──
+  {
+    id: "kling-v3-t2v",
+    name: "Kling Video v3 Standard Text to Video",
+    modality: "video",
+    upstreamModelId: "kling",
+    upstreamModelVersion: "kling_v3_standard_t2v",
+  },
+  {
+    id: "kling-v3-pro-i2v",
+    name: "Kling Video v3 Pro Image to Video",
+    modality: "video",
+    upstreamModelId: "kling",
+    upstreamModelVersion: "kling_v3_pro_i2v",
+  },
+  {
+    id: "luma-ray3",
+    name: "Ray3",
+    modality: "video",
+    upstreamModelId: "luma",
+    upstreamModelVersion: "3.0-ray",
+  },
+  {
+    id: "runway-gen4-turbo",
+    name: "Runway Gen-4 Video",
+    modality: "video",
+    upstreamModelId: "runway",
+    upstreamModelVersion: "gen4_turbo",
+  },
+];
 
-export interface AdobeFireflyVideoModelSpec extends AdobeFireflyCatalogModel {
-  modality: "video";
-  defaultDuration: number;
-  defaultResolution: string;
-}
-
-interface MergedObjectSchema {
-  properties: Record<string, Record<string, unknown>>;
-  required: string[];
-}
-
-function asRecord(value: unknown): Record<string, unknown> {
-  return value && typeof value === "object" && !Array.isArray(value)
-    ? (value as Record<string, unknown>)
-    : {};
-}
-
-function asStringArray(value: unknown): string[] {
-  return Array.isArray(value)
-    ? value.map((item) => String(item)).filter((item) => item.length > 0)
-    : [];
-}
-
-function finiteInteger(value: unknown): number | null {
-  return Number.isInteger(value) ? (value as number) : null;
-}
-
-/** Merge object properties/required keys contributed through JSON Schema allOf. */
-export function mergeAdobeObjectSchema(schema: unknown): MergedObjectSchema {
-  const merged: MergedObjectSchema = { properties: {}, required: [] };
-  const visit = (value: unknown) => {
-    const node = asRecord(value);
-    const properties = asRecord(node.properties);
-    for (const [key, property] of Object.entries(properties)) {
-      merged.properties[key] = asRecord(property);
-    }
-    merged.required.push(...asStringArray(node.required));
-    if (Array.isArray(node.allOf)) node.allOf.forEach(visit);
-  };
-  visit(schema);
-  merged.required = [...new Set(merged.required)];
-  return merged;
-}
-
-function schemaBranches(schema: unknown): Record<string, unknown>[] {
-  const root = asRecord(schema);
-  if (Object.keys(root).length === 0) return [];
-  return [
-    root,
-    ...(Array.isArray(root.anyOf) ? root.anyOf.map(asRecord) : []),
-    ...(Array.isArray(root.oneOf) ? root.oneOf.map(asRecord) : []),
-  ];
-}
-
-function enumStrings(schema: unknown): string[] {
-  return [
-    ...new Set(
-      schemaBranches(schema)
-        .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-        .filter((value): value is string => typeof value === "string")
-    ),
-  ];
-}
-
-function integerBranch(schema: unknown): Record<string, unknown> {
-  return schemaBranches(schema).find((branch) => branch.type === "integer") || {};
-}
-
-/** Stable, collision-resistant public id for an exact upstream model/version pair. */
+/** Stable slug for upstream modelId + modelVersion (catalog id when not a friendly alias). */
 export function slugifyAdobeModel(modelId: string, modelVersion: string): string {
-  const slug = (value: string, allowDot = false) =>
-    String(value || "")
-      .trim()
-      .toLowerCase()
-      .replace(allowDot ? /[^a-z0-9.]+/g : /[^a-z0-9]+/g, "-")
-      .replace(/^-|-$/g, "");
-  const family = slug(modelId);
-  // Adobe still uses `kling_v3_omni*` internally, while discovery exposes these
-  // products to users as Kling O3. Never leak the obsolete/internal "omni" name
-  // into the public API catalog; the untouched upstream version stays in the spec.
-  const publicVersion =
-    family === "kling" ? modelVersion.replace(/^kling_v3_omni/i, "kling_o3") : modelVersion;
-  const version = slug(publicVersion, true);
-  if (!version || version === "default" || version === family) return family || "model";
-  return `${family}-${version}`;
+  const mid = String(modelId || "")
+    .trim()
+    .toLowerCase()
+    .replace(/[^a-z0-9]+/g, "-")
+    .replace(/^-|-$/g, "");
+  const ver = String(modelVersion || "")
+    .trim()
+    .toLowerCase()
+    .replace(/[^a-z0-9.]+/g, "-")
+    .replace(/^-|-$/g, "");
+  if (!ver || ver === "default" || ver === mid) return mid || "model";
+  return `${mid}-${ver}`;
 }
 
-/** Parse POST /v2/models/discovery without discarding its resolved request schema. */
-export function parseAdobeModelsDiscovery(body: unknown): AdobeFireflyDiscoveredModel[] {
-  const root = asRecord(body);
-  const families = Array.isArray(root.models) ? root.models : [];
-  const rows: AdobeFireflyDiscoveredModel[] = [];
-
-  for (const familyValue of families) {
-    const family = asRecord(familyValue);
-    const modelId = String(family.modelId || "").trim();
-    if (!modelId) continue;
-    for (const [modelVersion, versionValue] of Object.entries(asRecord(family.modelVersions))) {
-      const version = asRecord(versionValue);
-      if (version.enabled === false) continue;
-      const outputModalities = asStringArray(version.outputModality).map((item) =>
-        item.toLowerCase()
-      );
-      const modality: AdobeFireflyModality = outputModalities.includes("image")
-        ? "image"
-        : outputModalities.includes("video")
-          ? "video"
-          : outputModalities.includes("audio")
-            ? "audio"
-            : "unknown";
-      rows.push({
-        modelId,
-        modelVersion,
-        displayName: String(
-          version.modelDisplayName || version.modelCaiDisplayName || modelVersion
-        ),
-        modality,
-        enabled: version.enabled !== false,
-        providerName:
-          typeof family.acModelFamilyProviderDisplayName === "string"
-            ? family.acModelFamilyProviderDisplayName
-            : undefined,
-        releaseReadiness:
-          typeof version.releaseReadiness === "string" ? version.releaseReadiness : undefined,
-        healthStatus: typeof version.healthStatus === "string" ? version.healthStatus : undefined,
-        inputMediaUseCases: asStringArray(version.inputMediaUseCase),
-        requestSchema: asRecord(version.requestSchema),
-        backingModel:
-          typeof version.bksGenerationModel === "string" ? version.bksGenerationModel : undefined,
-      });
-    }
-  }
-  return rows;
-}
-
-function normalizeCapabilities(row: AdobeFireflyDiscoveredModel): AdobeFireflyMediaCapabilities {
-  const schema = mergeAdobeObjectSchema(row.requestSchema);
-  const referenceSchema = asRecord(schema.properties.referenceBlobs);
-  const referenceInputs: AdobeFireflyReferenceInputCapability[] = [];
-  const mediaCapabilities = Array.isArray(referenceSchema["x-capabilities"])
-    ? referenceSchema["x-capabilities"]
-    : [];
-  for (const mediaValue of mediaCapabilities) {
-    const media = asRecord(mediaValue);
-    const maxFileSizeBytes = finiteInteger(media.maxFileSizeBytes);
-    const usageConstraints = Array.isArray(media.usageConstraints) ? media.usageConstraints : [];
-    for (const usageValue of usageConstraints) {
-      const usage = asRecord(usageValue);
-      if (usage.deprecated === true) continue;
-      const usageType = String(usage.usageType || "");
-      const mediaType = String(media.mediaType || "");
-      if (!usageType || !mediaType) continue;
-      referenceInputs.push({
-        mediaType,
-        usageType,
-        minItems: finiteInteger(usage.minItems) ?? 0,
-        maxItems: finiteInteger(usage.maxItems),
-        maxFileSizeBytes,
-      });
-    }
-  }
-
-  const supportedSizes = [
-    ...new Set(
-      schemaBranches(schema.properties.size)
-        .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-        .map(asRecord)
-        .filter((size) => finiteInteger(size.width) !== null && finiteInteger(size.height) !== null)
-        .map((size) => `${size.width}x${size.height}`)
-    ),
-  ];
-  const supportedAspectRatios = [
-    ...new Set(
-      schemaBranches(schema.properties.generationSettings).flatMap((branch) =>
-        enumStrings(asRecord(asRecord(branch.properties).aspectRatio))
-      )
-    ),
-  ];
-  const duration = integerBranch(schema.properties.duration);
-  const outputCount = integerBranch(schema.properties.n);
-  const prompt =
-    schemaBranches(schema.properties.prompt).find((branch) => branch.type === "string") || {};
-
-  return {
-    inputMediaUseCases: [...row.inputMediaUseCases],
-    schemaProperties: Object.keys(schema.properties),
-    requiredProperties: [...schema.required],
-    referenceInputs,
-    maxReferenceItems: finiteInteger(referenceSchema.maxItems),
-    supportedSizes,
-    supportedAspectRatios,
-    supportedResolutions: enumStrings(schema.properties.resolution),
-    supportedDurations: [
-      ...new Set(
-        schemaBranches(schema.properties.duration)
-          .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-          .filter((value): value is number => Number.isInteger(value))
-      ),
-    ],
-    durationMin: finiteInteger(duration.minimum),
-    durationMax: finiteInteger(duration.maximum),
-    durationDefault: finiteInteger(duration.default),
-    outputCountMin: finiteInteger(outputCount.minimum),
-    outputCountMax: finiteInteger(outputCount.maximum),
-    promptMaxLength: finiteInteger(prompt.maxLength),
-    releaseReadiness: row.releaseReadiness || "",
-    healthStatus: row.healthStatus || "",
-  };
-}
-
-function isCallableGenerationModel(row: AdobeFireflyDiscoveredModel): boolean {
-  if (row.modality !== "image" && row.modality !== "video") return false;
-  if (!mergeAdobeObjectSchema(row.requestSchema).properties.prompt) return false;
-  const excluded = new Set(["upscaling", "sharpening", "denoising"]);
-  return !row.inputMediaUseCases.some((value) => excluded.has(value.toLowerCase()));
-}
-
-function deriveInputModalities(capabilities: AdobeFireflyMediaCapabilities): string[] {
-  return ["text", ...new Set(capabilities.referenceInputs.map((reference) => reference.mediaType))];
-}
-
-function semanticCatalogKey(model: AdobeFireflyCatalogModel): string {
-  return JSON.stringify({
-    backingModel: model.backingModel,
-    name: model.name,
-    modality: model.modality,
-    capabilities: model.capabilities,
-  });
-}
-
-/** Normalize and de-duplicate callable image/video rows from live discovery. */
+/** Map discovery rows → catalog entries (image/video only). */
 export function mapDiscoveredToCatalog(
   rows: AdobeFireflyDiscoveredModel[]
 ): AdobeFireflyCatalogModel[] {
-  const output: AdobeFireflyCatalogModel[] = [];
+  const out: AdobeFireflyCatalogModel[] = [];
   const seen = new Set<string>();
-  for (const row of rows) {
-    if (!isCallableGenerationModel(row)) continue;
-    const capabilities = normalizeCapabilities(row);
-    const model: AdobeFireflyCatalogModel = {
-      id: slugifyAdobeModel(row.modelId, row.modelVersion),
-      name: row.displayName,
-      modality: row.modality as "image" | "video",
-      upstreamModelId: row.modelId,
-      upstreamModelVersion: row.modelVersion,
-      providerName: row.providerName || "",
-      backingModel: row.backingModel || "",
-      inputModalities: deriveInputModalities(capabilities),
-      capabilities,
-    };
-    const key = semanticCatalogKey(model);
-    if (seen.has(key)) continue;
-    seen.add(key);
-    output.push(model);
-  }
-  return output;
-}
 
-function snapshotCatalog(): AdobeFireflyCatalogModel[] {
-  return ADOBE_FIREFLY_DISCOVERY_SNAPSHOT.map((model) => {
-    const capabilities: AdobeFireflyMediaCapabilities = {
-      inputMediaUseCases: [...model.inputMediaUseCases],
-      schemaProperties: [...model.schemaProperties],
-      requiredProperties: [...model.requiredProperties],
-      referenceInputs: model.referenceInputs.map((reference) => ({ ...reference })),
-      maxReferenceItems: model.maxReferenceItems,
-      supportedSizes: [...model.supportedSizes],
-      supportedAspectRatios: [...model.supportedAspectRatios],
-      supportedResolutions: [...model.supportedResolutions],
-      supportedDurations: [...model.supportedDurations],
-      durationMin: model.durationMin,
-      durationMax: model.durationMax,
-      durationDefault: model.durationDefault,
-      outputCountMin: model.outputCountMin,
-      outputCountMax: model.outputCountMax,
-      promptMaxLength: model.promptMaxLength,
-      releaseReadiness: model.releaseReadiness,
-      healthStatus: model.healthStatus,
-    };
-    return {
-      id: model.id,
-      name: model.name,
-      modality: model.modality,
-      upstreamModelId: model.upstreamModelId,
-      upstreamModelVersion: model.upstreamModelVersion,
-      providerName: model.providerName,
-      backingModel: model.backingModel,
-      inputModalities: deriveInputModalities(capabilities),
-      capabilities,
-    };
-  });
-}
-
-export const ADOBE_FIREFLY_FALLBACK_MODELS: AdobeFireflyCatalogModel[] = snapshotCatalog();
-
-export function getAdobeFireflyFallbackCatalog(
-  modality?: "image" | "video"
-): AdobeFireflyCatalogModel[] {
-  return ADOBE_FIREFLY_FALLBACK_MODELS.filter((model) => !modality || model.modality === modality);
-}
-
-function imageFamily(model: AdobeFireflyCatalogModel): AdobeFireflyImageModelSpec["family"] {
-  if (model.upstreamModelId === "gemini-flash") return "gemini";
-  if (model.upstreamModelId === "gpt-image" || model.upstreamModelId === "gpt-4o-image") {
-    return "gpt-image";
-  }
-  return "generic";
-}
-
-export const ADOBE_FIREFLY_IMAGE_MODELS: Record<string, AdobeFireflyImageModelSpec> =
-  Object.fromEntries(
-    getAdobeFireflyFallbackCatalog("image").map((model) => [
-      model.id,
-      { ...model, modality: "image" as const, family: imageFamily(model) },
-    ])
-  );
-
-function defaultDuration(model: AdobeFireflyCatalogModel): number {
-  const caps = model.capabilities;
-  return caps.durationDefault ?? caps.supportedDurations[0] ?? caps.durationMin ?? 5;
-}
-
-function defaultResolution(model: AdobeFireflyCatalogModel): string {
-  if (model.capabilities.supportedSizes.some((value) => value.includes("1920x1080"))) {
-    return "1080p";
-  }
-  return "720p";
-}
-
-export const ADOBE_FIREFLY_VIDEO_MODELS: Record<string, AdobeFireflyVideoModelSpec> =
-  Object.fromEntries(
-    getAdobeFireflyFallbackCatalog("video").map((model) => [
-      model.id,
-      {
-        ...model,
-        modality: "video" as const,
-        defaultDuration: defaultDuration(model),
-        defaultResolution: defaultResolution(model),
-      },
-    ])
-  );
-
-const LEGACY_MODEL_ALIASES: Record<string, string> = {
-  "nano-banana": "gemini-flash-nano-banana",
-  "nano-banana-pro": "gemini-flash-nano-banana-2",
-  "nano-banana-2": "gemini-flash-nano-banana-3",
-  "gpt-image": "gpt-image-2",
-  "gpt-image-2": "gpt-image-2",
-  "gpt-image-1.5": "gpt-image-1.5",
-  "flux-2": "flux-2",
-  "flux-pro": "flux-fluxpro",
-  "flux-ultra": "flux-fluxultra",
-  "seedream-4": "seedream-seedream-v4",
-  "seedream-5-lite": "seedream-seedream-v5-lite",
-  "runway-gen4-image": "runway-gen4-image",
-  "veo-3.1": "veo-3.1-generate",
-  "veo-3.1-fast": "veo-3.1-fast-generate",
-  "luma-ray3": "luma-3.0-ray",
-  "runway-gen4-turbo": "runway-gen4-turbo",
-  // Backward compatibility only; the catalog advertises the exact discovered id.
-  "kling-3": "kling-kling-v3-standard-i2v",
-};
-
-// Preserve established API aliases when (and only when) they resolve to a model
-// that is present in the verified discovery snapshot. These keys are not listed.
-for (const [alias, target] of Object.entries(LEGACY_MODEL_ALIASES)) {
-  const imageTarget = ADOBE_FIREFLY_IMAGE_MODELS[target];
-  if (imageTarget) ADOBE_FIREFLY_IMAGE_MODELS[alias] = imageTarget;
-  const videoTarget = ADOBE_FIREFLY_VIDEO_MODELS[target];
-  if (videoTarget) ADOBE_FIREFLY_VIDEO_MODELS[alias] = videoTarget;
-}
-
-/** Backward-compatible request ids. Kept out of every advertised model catalog. */
-export const ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES = Object.freeze(
-  Object.entries(LEGACY_MODEL_ALIASES)
-    .filter(([, target]) => Boolean(ADOBE_FIREFLY_IMAGE_MODELS[target]))
-    .map(([alias]) => alias)
-);
-
-function normalizeRequestedId(model: string): string {
-  return String(model || "")
-    .trim()
-    .toLowerCase()
-    .replace(/^adobe-firefly\//, "")
-    .replace(/^firefly\//, "");
-}
-
-function resolveCatalogId(model: string): string {
-  const requested = normalizeRequestedId(model);
-  return LEGACY_MODEL_ALIASES[requested] || requested;
-}
-
-export function resolveAdobeImageModel(model: string): {
-  id: string;
-  spec: AdobeFireflyImageModelSpec;
-} {
-  const id = resolveCatalogId(model);
-  const spec = ADOBE_FIREFLY_IMAGE_MODELS[id];
-  if (!spec) {
-    throw new Error(
-      `Unknown Adobe Firefly image model: ${normalizeRequestedId(model) || "(empty)"}`
+  // Prefer friendly aliases when upstream matches known fallback rows.
+  for (const fb of ADOBE_FIREFLY_FALLBACK_MODELS) {
+    const hit = rows.find(
+      (r) =>
+        r.modelId === fb.upstreamModelId &&
+        r.modelVersion === fb.upstreamModelVersion &&
+        (r.modality === fb.modality || r.modality === "unknown")
     );
+    if (hit && !seen.has(fb.id)) {
+      seen.add(fb.id);
+      out.push({
+        ...fb,
+        name: hit.displayName || fb.name,
+      });
+    }
   }
-  return { id, spec };
-}
 
-export function resolveAdobeVideoModel(model: string): {
-  id: string;
-  spec: AdobeFireflyVideoModelSpec;
-} {
-  const id = resolveCatalogId(model);
-  const spec = ADOBE_FIREFLY_VIDEO_MODELS[id];
-  if (!spec) {
-    throw new Error(
-      `Unknown Adobe Firefly video model: ${normalizeRequestedId(model) || "(empty)"}`
-    );
+  for (const r of rows) {
+    if (r.modality !== "image" && r.modality !== "video") continue;
+    const id = slugifyAdobeModel(r.modelId, r.modelVersion);
+    if (seen.has(id)) continue;
+    // Skip if already covered by a friendly alias with same upstream
+    if (
+      out.some(
+        (o) =>
+          o.upstreamModelId === r.modelId && o.upstreamModelVersion === r.modelVersion
+      )
+    ) {
+      continue;
+    }
+    seen.add(id);
+    out.push({
+      id,
+      name: r.displayName || id,
+      modality: r.modality,
+      upstreamModelId: r.modelId,
+      upstreamModelVersion: r.modelVersion,
+      inputModalities: r.modality === "image" ? ["text", "image"] : ["text"],
+    });
   }
-  return { id, spec };
+
+  return out;
 }
 
-export function toRegistryImageModels(): Array<{
-  id: string;
-  name: string;
-  inputModalities: string[];
-  imageRequired?: boolean;
-  supportedSizes: string[];
-  mediaCapabilities: Record<string, unknown>;
-}> {
-  const generated = getAdobeFireflyFallbackCatalog("image").map((model) => ({
-    id: model.id,
-    name: `Firefly ${model.name}`,
-    inputModalities: model.inputModalities,
-    supportedSizes: model.capabilities.supportedSizes,
-    mediaCapabilities: toAdobeMediaCapabilitiesApi(model),
-  }));
-  // Upscaling uses a distinct Firefly endpoint and is not returned by the image
-  // generation discovery schema. Keep its two supported Topaz models visible in
-  // the same provider catalog so image clients can select them deliberately.
-  return [
-    ...generated,
-    {
-      id: "topaz-standard",
-      name: "Firefly Topaz Upscale (Standard)",
-      inputModalities: ["image"],
-      imageRequired: true,
-      supportedSizes: [],
-      mediaCapabilities: { input_media_use_cases: ["upscaling"] },
-    },
-    {
-      id: "topaz-bloom",
-      name: "Firefly Topaz Bloom (Creative Upscale)",
-      inputModalities: ["image"],
-      imageRequired: true,
-      supportedSizes: [],
-      mediaCapabilities: { input_media_use_cases: ["upscaling"] },
-    },
-  ];
+export function getAdobeFireflyFallbackCatalog(modality?: "image" | "video"): AdobeFireflyCatalogModel[] {
+  if (!modality) return [...ADOBE_FIREFLY_FALLBACK_MODELS];
+  return ADOBE_FIREFLY_FALLBACK_MODELS.filter((m) => m.modality === modality);
 }
 
-export function toRegistryVideoModels(): Array<{
-  id: string;
-  name: string;
-  supportedSizes: string[];
-  mediaCapabilities: Record<string, unknown>;
-}> {
-  return getAdobeFireflyFallbackCatalog("video").map((model) => ({
-    id: model.id,
-    name: `Firefly ${model.name}`,
-    supportedSizes: model.capabilities.supportedSizes,
-    mediaCapabilities: toAdobeMediaCapabilitiesApi(model),
-  }));
-}
+/**
+ * Live discovery when credentials resolve; otherwise static fallback from get_models capture.
+ */
+export async function resolveAdobeFireflyCatalog(opts: {
+  credentials?: {
+    apiKey?: string;
+    accessToken?: string;
+    providerSpecificData?: Record<string, unknown> | null;
+  } | null;
+  modality?: "image" | "video";
+  fetchImpl?: typeof fetch;
+}): Promise<{ models: AdobeFireflyCatalogModel[]; source: "api" | "fallback" }> {
+  const fetchImpl = opts.fetchImpl || fetch;
+  try {
+    if (opts.credentials) {
+      const token = await resolveAdobeAccessToken(opts.credentials, fetchImpl);
+      const discovered = await discoverAdobeFireflyModels(token, fetchImpl);
+      let catalog = mapDiscoveredToCatalog(discovered);
+      if (opts.modality) catalog = catalog.filter((m) => m.modality === opts.modality);
+      if (catalog.length > 0) return { models: catalog, source: "api" };
+    }
+  } catch {
+    // fall through to static catalog
+  }
 
-/** JSON-safe extension emitted by /v1/models. */
-export function toAdobeMediaCapabilitiesApi(
-  model: AdobeFireflyCatalogModel
-): Record<string, unknown> {
-  const caps = model.capabilities;
   return {
-    upstream_model_id: model.upstreamModelId,
-    upstream_model_version: model.upstreamModelVersion,
-    provider_name: model.providerName,
-    release_readiness: caps.releaseReadiness,
-    health_status: caps.healthStatus,
-    input_media_use_cases: caps.inputMediaUseCases,
-    reference_inputs: caps.referenceInputs.map((reference) => ({
-      media_type: reference.mediaType,
-      usage_type: reference.usageType,
-      min_items: reference.minItems,
-      max_items: reference.maxItems,
-      max_file_size_bytes: reference.maxFileSizeBytes,
-    })),
-    max_reference_items: caps.maxReferenceItems,
-    supported_sizes: caps.supportedSizes,
-    supported_aspect_ratios: caps.supportedAspectRatios,
-    supported_resolutions: caps.supportedResolutions,
-    supported_durations: caps.supportedDurations,
-    duration_min: caps.durationMin,
-    duration_max: caps.durationMax,
-    duration_default: caps.durationDefault,
-    output_count_min: caps.outputCountMin,
-    output_count_max: caps.outputCountMax,
-    prompt_max_length: caps.promptMaxLength,
+    models: getAdobeFireflyFallbackCatalog(opts.modality),
+    source: "fallback",
   };
 }
 
-export function getAdobeReferenceUploadLimit(
-  model: AdobeFireflyCatalogModel,
-  mediaType: string
-): number {
-  if (model.capabilities.maxReferenceItems !== null) {
-    return Math.max(1, Math.min(32, model.capabilities.maxReferenceItems));
-  }
-  const declaredTotal = model.capabilities.referenceInputs
-    .filter((reference) => reference.mediaType === mediaType)
-    .reduce((total, reference) => total + (reference.maxItems ?? 0), 0);
-  return Math.max(1, Math.min(32, declaredTotal || 1));
+/** Registry-shaped models for imageRegistry / videoRegistry. */
+export function toRegistryImageModels(
+  models: AdobeFireflyCatalogModel[] = getAdobeFireflyFallbackCatalog("image")
+): Array<{ id: string; name: string; inputModalities?: string[] }> {
+  return models
+    .filter((m) => m.modality === "image")
+    .map((m) => ({
+      id: m.id,
+      name: m.name.startsWith("Firefly ") ? m.name : `Firefly ${m.name}`,
+      inputModalities: m.inputModalities || ["text", "image"],
+    }));
+}
+
+export function toRegistryVideoModels(
+  models: AdobeFireflyCatalogModel[] = getAdobeFireflyFallbackCatalog("video")
+): Array<{ id: string; name: string }> {
+  return models
+    .filter((m) => m.modality === "video")
+    .map((m) => ({
+      id: m.id,
+      name: m.name.startsWith("Firefly ") ? m.name : `Firefly ${m.name}`,
+    }));
 }

scripts/dev/generate-adobe-firefly-snapshot.mjs

@@ -1,207 +0,0 @@
-#!/usr/bin/env node
-
-import fs from "node:fs";
-import path from "node:path";
-import { createHash } from "node:crypto";
-
-function usage() {
-  console.error(
-    "Usage: node scripts/dev/generate-adobe-firefly-snapshot.mjs <discovery.json> <output.ts>"
-  );
-  process.exit(2);
-}
-
-const [, , inputArg, outputArg] = process.argv;
-if (!inputArg || !outputArg) usage();
-
-const inputPath = path.resolve(inputArg);
-const outputPath = path.resolve(outputArg);
-const inputBytes = fs.readFileSync(inputPath);
-const sourceHash = createHash("sha256").update(inputBytes).digest("hex");
-const root = JSON.parse(inputBytes.toString("utf8"));
-
-function mergeObjectSchema(schema) {
-  const merged = { properties: {}, required: [] };
-  const visit = (node) => {
-    if (!node || typeof node !== "object") return;
-    if (node.properties && typeof node.properties === "object") {
-      Object.assign(merged.properties, node.properties);
-    }
-    if (Array.isArray(node.required)) merged.required.push(...node.required);
-    if (Array.isArray(node.allOf)) node.allOf.forEach(visit);
-  };
-  visit(schema);
-  merged.required = [...new Set(merged.required)];
-  return merged;
-}
-
-function branches(schema) {
-  if (!schema || typeof schema !== "object") return [];
-  return [schema, ...(schema.anyOf || []), ...(schema.oneOf || [])];
-}
-
-function stringEnums(schema) {
-  return [
-    ...new Set(
-      branches(schema)
-        .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-        .filter((value) => typeof value === "string")
-    ),
-  ];
-}
-
-function integerSchema(schema) {
-  return branches(schema).find((branch) => branch.type === "integer") || {};
-}
-
-function publicModelId(modelId, modelVersion) {
-  const slug = (value, allowDot = false) =>
-    String(value || "")
-      .trim()
-      .toLowerCase()
-      .replace(allowDot ? /[^a-z0-9.]+/g : /[^a-z0-9]+/g, "-")
-      .replace(/^-|-$/g, "");
-  const family = slug(modelId);
-  const publicVersion =
-    family === "kling" ? String(modelVersion).replace(/^kling_v3_omni/i, "kling_o3") : modelVersion;
-  const version = slug(publicVersion, true);
-  if (!version || version === "default" || version === family) return family || "model";
-  return `${family}-${version}`;
-}
-
-function normalizeModel(family, modelVersion, version) {
-  const schema = mergeObjectSchema(version.requestSchema);
-  const properties = schema.properties;
-  const referenceSchema = properties.referenceBlobs || {};
-  const referenceInputs = [];
-  for (const media of referenceSchema["x-capabilities"] || []) {
-    for (const usage of media.usageConstraints || []) {
-      if (usage.deprecated === true) continue;
-      referenceInputs.push({
-        mediaType: String(media.mediaType || ""),
-        usageType: String(usage.usageType || ""),
-        minItems: Number.isInteger(usage.minItems) ? usage.minItems : 0,
-        maxItems: Number.isInteger(usage.maxItems) ? usage.maxItems : null,
-        maxFileSizeBytes: Number.isInteger(media.maxFileSizeBytes) ? media.maxFileSizeBytes : null,
-      });
-    }
-  }
-
-  const supportedSizes = [
-    ...new Set(
-      branches(properties.size)
-        .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-        .filter(
-          (size) =>
-            size &&
-            Number.isInteger(size.width) &&
-            size.width > 0 &&
-            Number.isInteger(size.height) &&
-            size.height > 0
-        )
-        .map((size) => `${size.width}x${size.height}`)
-    ),
-  ];
-  const supportedAspectRatios = [
-    ...new Set(
-      branches(properties.generationSettings).flatMap((branch) =>
-        stringEnums(branch?.properties?.aspectRatio)
-      )
-    ),
-  ];
-  const duration = integerSchema(properties.duration);
-  const supportedDurations = [
-    ...new Set(
-      branches(properties.duration)
-        .flatMap((branch) => (Array.isArray(branch.enum) ? branch.enum : []))
-        .filter(Number.isInteger)
-    ),
-  ];
-  const prompt = branches(properties.prompt).find((branch) => branch.type === "string") || {};
-  const outputCount = integerSchema(properties.n);
-
-  return {
-    id: publicModelId(family.modelId, modelVersion),
-    name: String(version.modelDisplayName || version.modelCaiDisplayName || modelVersion),
-    modality: version.outputModality[0],
-    upstreamModelId: family.modelId,
-    upstreamModelVersion: modelVersion,
-    providerName: String(family.acModelFamilyProviderDisplayName || ""),
-    releaseReadiness: String(version.releaseReadiness || ""),
-    healthStatus: String(version.healthStatus || ""),
-    inputMediaUseCases: (version.inputMediaUseCase || []).map(String),
-    schemaProperties: Object.keys(properties),
-    requiredProperties: schema.required,
-    referenceInputs,
-    maxReferenceItems: Number.isInteger(referenceSchema.maxItems) ? referenceSchema.maxItems : null,
-    supportedSizes,
-    supportedAspectRatios,
-    supportedResolutions: stringEnums(properties.resolution),
-    supportedDurations,
-    durationMin: Number.isInteger(duration.minimum) ? duration.minimum : null,
-    durationMax: Number.isInteger(duration.maximum) ? duration.maximum : null,
-    durationDefault: Number.isInteger(duration.default) ? duration.default : null,
-    outputCountMin: Number.isInteger(outputCount.minimum) ? outputCount.minimum : null,
-    outputCountMax: Number.isInteger(outputCount.maximum) ? outputCount.maximum : null,
-    promptMaxLength: Number.isInteger(prompt.maxLength) ? prompt.maxLength : null,
-    backingModel: String(version.bksGenerationModel || ""),
-  };
-}
-
-const rawModels = [];
-for (const family of Array.isArray(root.models) ? root.models : []) {
-  for (const [modelVersion, version] of Object.entries(family.modelVersions || {})) {
-    if (!version || version.enabled === false) continue;
-    const modality = Array.isArray(version.outputModality)
-      ? version.outputModality.map((value) => String(value).toLowerCase())[0]
-      : "";
-    if (modality !== "image" && modality !== "video") continue;
-
-    const schema = mergeObjectSchema(version.requestSchema);
-    if (!schema.properties.prompt) continue;
-    const useCases = (version.inputMediaUseCase || []).map((value) => String(value).toLowerCase());
-    if (useCases.some((value) => ["upscaling", "sharpening", "denoising"].includes(value))) {
-      continue;
-    }
-    rawModels.push(normalizeModel(family, modelVersion, version));
-  }
-}
-
-// Discovery currently repeats a few exact aliases (for example flux/fluxPro and
-// fluxPro/1.1). Keep the first canonical wire pair and suppress duplicate cards.
-const seen = new Set();
-const models = [];
-for (const model of rawModels) {
-  const semanticKey = JSON.stringify({
-    backingModel: model.backingModel,
-    name: model.name,
-    modality: model.modality,
-    schemaProperties: model.schemaProperties,
-    requiredProperties: model.requiredProperties,
-    referenceInputs: model.referenceInputs,
-    maxReferenceItems: model.maxReferenceItems,
-    supportedSizes: model.supportedSizes,
-    supportedAspectRatios: model.supportedAspectRatios,
-    supportedResolutions: model.supportedResolutions,
-    supportedDurations: model.supportedDurations,
-    durationMin: model.durationMin,
-    durationMax: model.durationMax,
-  });
-  if (seen.has(semanticKey)) continue;
-  seen.add(semanticKey);
-  models.push(model);
-}
-
-const source = `/**
- * Generated from Adobe Firefly POST /v2/models/discovery with resolveSchema=true.
- * Source SHA-256: ${sourceHash}
- * Regenerate with scripts/dev/generate-adobe-firefly-snapshot.mjs; do not edit by hand.
- * The generated literal stays compact to satisfy the repository's line-count gate.
- */
-// prettier-ignore
-export const ADOBE_FIREFLY_DISCOVERY_SNAPSHOT = ${JSON.stringify(models)} as const;
-`;
-
-fs.mkdirSync(path.dirname(outputPath), { recursive: true });
-fs.writeFileSync(outputPath, source, "utf8");
-console.log(`Wrote ${models.length} models to ${outputPath}`);

src/app/(dashboard)/dashboard/settings/components/ModelCapabilityOverridesTab.tsx

@@ -4,21 +4,28 @@ import { useCallback, useEffect, useMemo, useState } from "react";
 import { useTranslations } from "next-intl";
 import { Card, Button } from "@/shared/components";
 import { matchesSearch } from "@/shared/utils/turkishText";
-import {
-  toModelOverrideTargets,
-  type PricingCatalogProvider,
-} from "@/lib/modelCapabilityOverrideTargets";
 
 type ModelOverrideKey = "context_length" | "max_input_tokens" | "max_output_tokens";
 type StatusTone = "success" | "error" | "info";
 
-type ModelOverrideTarget = import("@/lib/modelCapabilityOverrideTargets").ModelOverrideTarget;
+type ModelOverrideTarget = {
+  target: string;
+  provider: string;
+  modelId: string;
+  label: string;
+};
 
 interface PricingCatalogModel {
   id: string;
   name: string;
 }
 
+interface PricingCatalogProvider {
+  id: string;
+  alias: string;
+  models: PricingCatalogModel[];
+}
+
 interface ModelCapabilityOverride {
   target: string;
   key: ModelOverrideKey;
@@ -113,11 +120,22 @@ function useModelCapabilityOverridesData() {
   return { catalog, overrides, loading, statusMessage, saveOverride, removeOverride };
 }
 
+function toTargets(catalog: Record<string, PricingCatalogProvider>): ModelOverrideTarget[] {
+  return Object.values(catalog).flatMap((provider) =>
+    provider.models.map((model) => ({
+      target: `${provider.id}/${model.id}`,
+      provider: provider.id,
+      modelId: model.id,
+      label: `${provider.id}/${model.id}`,
+    }))
+  );
+}
+
 export default function ModelCapabilityOverridesTab() {
   const t = useTranslations("settings");
   const { catalog, overrides, loading, statusMessage, saveOverride, removeOverride } =
     useModelCapabilityOverridesData();
-  const targets = useMemo(() => toModelOverrideTargets(catalog), [catalog]);
+  const targets = useMemo(() => toTargets(catalog), [catalog]);
 
   if (loading) return <div className="text-sm text-text-muted animate-pulse">{t("loading")}</div>;
 

src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx

@@ -1,7 +1,5 @@
 "use client";
 
-import { FilterSelect, HeroStat, SyncMini } from "./PricingTabHelpers";
-
 import { useState, useEffect, useCallback, useMemo } from "react";
 import { Card, Button } from "@/shared/components";
 import ProviderIcon from "@/shared/components/ProviderIcon";
@@ -50,8 +48,6 @@ interface PricingCatalogProvider {
   format: string;
   modelCount: number;
   models: PricingCatalogModel[];
-  /** Original pricing namespace (e.g. public prefix) when it differs from `alias`. */
-  pricingKey?: string;
 }
 
 function getSourceTone(source: PricingSource): string {
@@ -137,15 +133,11 @@ export default function PricingTab() {
 
   const allProviders = useMemo(() => {
     return Object.entries(catalog)
-      .map(([alias, info]) => {
-        const pricingKey = info.pricingKey || alias;
-        return {
-          ...info,
-          alias,
-          pricingKey,
-          pricedModels: pricingData[pricingKey] ? Object.keys(pricingData[pricingKey]).length : 0,
-        };
-      })
+      .map(([alias, info]) => ({
+        ...info,
+        alias,
+        pricedModels: pricingData[alias] ? Object.keys(pricingData[alias]).length : 0,
+      }))
       .sort((left, right) => right.modelCount - left.modelCount);
   }, [catalog, pricingData]);
 
@@ -320,14 +312,13 @@ export default function PricingTab() {
   );
 
   const saveProvider = useCallback(
-    async (providerAlias: string, pricingKey?: string) => {
+    async (providerAlias: string) => {
       setSaving(true);
       try {
-        const writeKey = pricingKey || providerAlias;
         const response = await fetch("/api/pricing", {
           method: "PATCH",
           headers: { "Content-Type": "application/json" },
-          body: JSON.stringify({ [writeKey]: pricingData[writeKey] || {} }),
+          body: JSON.stringify({ [providerAlias]: pricingData[providerAlias] || {} }),
         });
 
         if (!response.ok) {
@@ -337,7 +328,7 @@ export default function PricingTab() {
 
         setEditedProviders((previous) => {
           const next = new Set(previous);
-          next.delete(writeKey);
+          next.delete(providerAlias);
           return next;
         });
         await loadData();
@@ -357,13 +348,11 @@ export default function PricingTab() {
   );
 
   const resetProvider = useCallback(
-    async (providerAlias: string, pricingKey?: string) => {
+    async (providerAlias: string) => {
       if (!confirm(t("resetPricingConfirm", { provider: providerAlias.toUpperCase() }))) return;
 
       try {
-        const writeKey = pricingKey || providerAlias;
-        const params = new URLSearchParams({ provider: writeKey });
-        const response = await fetch(`/api/pricing?${params.toString()}`, {
+        const response = await fetch(`/api/pricing?provider=${providerAlias}`, {
           method: "DELETE",
         });
 
@@ -374,7 +363,7 @@ export default function PricingTab() {
 
         setEditedProviders((previous) => {
           const next = new Set(previous);
-          next.delete(writeKey);
+          next.delete(providerAlias);
           return next;
         });
         await loadData();
@@ -691,16 +680,16 @@ export default function PricingTab() {
           <ProviderSection
             key={provider.alias}
             provider={provider}
-            pricingData={pricingData[provider.pricingKey || provider.alias] || {}}
-            sourceMap={pricingSources[provider.pricingKey || provider.alias] || {}}
+            pricingData={pricingData[provider.alias] || {}}
+            sourceMap={pricingSources[provider.alias] || {}}
             isExpanded={expandedProviders.has(provider.alias)}
-            isEdited={editedProviders.has(provider.pricingKey || provider.alias)}
+            isEdited={editedProviders.has(provider.alias)}
             onToggle={() => toggleProvider(provider.alias)}
             onPricingChange={(model, field, value) =>
-              handlePricingChange(provider.pricingKey || provider.alias, model, field, value)
+              handlePricingChange(provider.alias, model, field, value)
             }
-            onSave={() => void saveProvider(provider.alias, provider.pricingKey)}
-            onReset={() => void resetProvider(provider.alias, provider.pricingKey)}
+            onSave={() => void saveProvider(provider.alias)}
+            onReset={() => void resetProvider(provider.alias)}
             saving={saving}
             getSourceLabel={getSourceLabel}
           />
@@ -728,6 +717,63 @@ export default function PricingTab() {
   );
 }
 
+function HeroStat({ label, value, accent }: { label: string; value: number; accent?: string }) {
+  return (
+    <div className="text-center">
+      <div className="text-[10px] uppercase tracking-wide text-text-muted font-semibold truncate">
+        {label}
+      </div>
+      <div
+        className={`text-2xl font-bold tabular-nums leading-tight ${accent || "text-text-main"}`}
+      >
+        {value}
+      </div>
+    </div>
+  );
+}
+
+function SyncMini({ label, value }: { label: string; value: string }) {
+  return (
+    <div className="rounded-md border border-border/30 bg-bg-base/40 px-2 py-1.5">
+      <p className="text-[9px] uppercase tracking-wide text-text-muted font-semibold truncate">
+        {label}
+      </p>
+      <p className="text-[11px] font-medium text-text-main mt-0.5 truncate" title={value}>
+        {value}
+      </p>
+    </div>
+  );
+}
+
+function FilterSelect({
+  label,
+  value,
+  onChange,
+  options,
+}: {
+  label: string;
+  value: string;
+  onChange: (v: string) => void;
+  options: Array<{ value: string; label: string }>;
+}) {
+  return (
+    <label className="flex items-center gap-1.5 text-xs text-text-muted">
+      <span className="font-semibold uppercase tracking-wide">{label}:</span>
+      <select
+        value={value}
+        onChange={(e) => onChange(e.target.value)}
+        className="bg-bg-base border border-border rounded-md px-2 py-1.5 text-xs text-text-main cursor-pointer focus:outline-none focus:border-primary"
+      >
+        {options.map((opt) => (
+          <option key={opt.value} value={opt.value}>
+            {opt.label}
+          </option>
+        ))}
+      </select>
+    </label>
+  );
+}
+
 function ProviderSection({
   provider,
   pricingData,

src/app/(dashboard)/dashboard/settings/components/PricingTabHelpers.tsx

@@ -1,56 +0,0 @@
-export function HeroStat({ label, value, accent }: { label: string; value: number; accent?: string }) {
-  return (
-    <div className="text-center">
-      <div className="text-[10px] uppercase tracking-wide text-text-muted font-semibold truncate">
-        {label}
-      </div>
-      <div
-        className={`text-2xl font-bold tabular-nums leading-tight ${accent || "text-text-main"}`}
-      >
-        {value}
-      </div>
-    </div>
-  );
-}
-
-export function SyncMini({ label, value }: { label: string; value: string }) {
-  return (
-    <div className="rounded-md border border-border/30 bg-bg-base/40 px-2 py-1.5">
-      <p className="text-[9px] uppercase tracking-wide text-text-muted font-semibold truncate">
-        {label}
-      </p>
-      <p className="text-[11px] font-medium text-text-main mt-0.5 truncate" title={value}>
-        {value}
-      </p>
-    </div>
-  );
-}
-
-export function FilterSelect({
-  label,
-  value,
-  onChange,
-  options,
-}: {
-  label: string;
-  value: string;
-  onChange: (value: string) => void;
-  options: Array<{ value: string; label: string }>;
-}) {
-  return (
-    <label className="flex items-center gap-1.5 text-xs text-text-muted">
-      <span className="font-semibold uppercase tracking-wide">{label}:</span>
-      <select
-        value={value}
-        onChange={(event) => onChange(event.target.value)}
-        className="bg-bg-base border border-border rounded-md px-2 py-1.5 text-xs text-text-main cursor-pointer focus:outline-none focus:border-primary"
-      >
-        {options.map((option) => (
-          <option key={option.value} value={option.value}>
-            {option.label}
-          </option>
-        ))}
-      </select>
-    </label>
-  );
-}

src/app/api/model-capability-overrides/route.ts

@@ -14,39 +14,12 @@ import {
   removeModelContextOverride,
   setModelContextOverride,
 } from "@/lib/db/modelContextOverrides";
-import { getProviderPrefixIndex, type ProviderPrefixEntry } from "@/lib/providerNodePrefixes";
 
 const overrideKeySchema = z.enum(["context_length", "max_input_tokens", "max_output_tokens"]);
 type PublicOverrideKey = z.infer<typeof overrideKeySchema>;
 type PublicOverride = Omit<ModelCapabilityOverride, "key"> & { key: PublicOverrideKey };
 
-/**
- * One-time per-request snapshot of the provider-node prefix index. Loaded once
- * per handler (never N times per row) straight from the DB — no module-global
- * mutable caches, no route-to-route imports.
- */
-async function loadPrefixMaps(): Promise<{
-  entries: Map<string, ProviderPrefixEntry>;
-  nodeToPrefix: Map<string, string>;
-  prefixToNode: Map<string, string>;
-  eligibleNodeIds: Set<string>;
-  compatibleNodeIds: Set<string>;
-}> {
-  const index = await getProviderPrefixIndex();
-  return {
-    entries: index.entries,
-    nodeToPrefix: index.nodeToPrefix,
-    prefixToNode: index.prefixToNode,
-    eligibleNodeIds: index.eligibleNodeIds,
-    compatibleNodeIds: index.compatibleNodeIds,
-  };
-}
-
-async function listPublicOverrides(
-  nodeToPrefix: Map<string, string>,
-  eligibleNodeIds: Set<string>,
-  compatibleNodeIds: Set<string>
-): Promise<PublicOverride[]> {
+function listPublicOverrides(): PublicOverride[] {
   const capabilityOverrides = listModelCapabilityOverrides() as PublicOverride[];
   const contextOverrides = listModelContextOverrides().map((override): PublicOverride => ({
     provider: override.provider,
@@ -56,27 +29,9 @@ async function listPublicOverrides(
     value: override.realContext,
     refreshedAt: override.refreshedAt,
   }));
-  const merged = [...capabilityOverrides, ...contextOverrides];
-  return merged
-    .filter((override) => {
-      // A compatible node that is NOT the unique non-reserved prefix winner is
-      // ineligible for Model Overrides: never surface it under a generated node
-      // UUID. Eligible winners are those in `eligibleNodeIds` (routable via
-      // their public prefix); built-in providers (not in `compatibleNodeIds`)
-      // are always eligible.
-      return !compatibleNodeIds.has(override.provider) || eligibleNodeIds.has(override.provider);
-    })
-    .map((override) => {
-      const displayProvider = nodeToPrefix.get(override.provider) || override.provider;
-      return {
-        ...override,
-        // Both `provider` and `target` are exposed under the public prefix so no
-        // generated node UUID ever leaks into the JSON for a prefixed node.
-        provider: displayProvider,
-        target: `${displayProvider}/${override.modelId}`,
-      };
-    })
-    .sort((left, right) => right.refreshedAt.localeCompare(left.refreshedAt));
+  return [...capabilityOverrides, ...contextOverrides].sort((left, right) =>
+    right.refreshedAt.localeCompare(left.refreshedAt)
+  );
 }
 
 const upsertOverrideSchema = z.object({
@@ -85,65 +40,23 @@ const upsertOverrideSchema = z.object({
   value: z.coerce.number().int().positive(),
 });
 
-/**
- * Canonicalize a public `<prefix>/<model>` target to `<internalNodeId>/<model>`
- * so the override is stored where runtime lookup reads it. Mirrors runtime
- * prefix routing exactly:
- *
- *   - `unique` configured prefix → canonicalize to the single runtime-routable
- *     winner node (first openai-compatible then anthropic-compatible, by id).
- *   - `reserved` configured prefix (collides with a built-in registry id/alias,
- *     e.g. a node with `prefix="cx"`) → route via `resolveProviderAlias` to the
- *     built-in canonical provider (runtime routes `cx/` to codex), never 400.
- *   - `ambiguous` (no runtime winner selectable) → fail closed (400).
- *   - A bare built-in alias/id that is NOT a configured node prefix (e.g.
- *     `openai` typed directly) resolves via `resolveProviderAlias` (unchanged).
- *
- * Returns the canonical `provider/model` on success, or `{ ok: false }`.
- */
-function canonicalizeTarget(
-  target: string,
-  entries: Map<string, ProviderPrefixEntry>,
-  prefixToNode: Map<string, string>,
-  compatibleNodeIds: Set<string>,
-  eligibleNodeIds: Set<string>
-): { ok: true; target: string } | { ok: false } {
+function canonicalizeTarget(target: string): string | null {
   const raw = target.trim();
   const slashIndex = raw.indexOf("/");
-  if (slashIndex <= 0 || slashIndex === raw.length - 1) return { ok: false };
+  if (slashIndex <= 0 || slashIndex === raw.length - 1) return null;
 
   const provider = raw.slice(0, slashIndex).trim();
   const modelId = raw.slice(slashIndex + 1).trim();
-  if (!provider || !modelId) return { ok: false };
+  if (!provider || !modelId) return null;
 
-  // Raw internal compatible-node IDs are never a public Model Overrides target.
-  // Only the public prefix of an eligible runtime winner may select a node.
-  // Reject ineligible raw IDs as well as eligible raw IDs so stale or direct API
-  // callers cannot create UUID-keyed overrides that the UI cannot manage.
-  if (compatibleNodeIds.has(provider)) return { ok: false };
-
-  const configured = entries.get(provider);
-  // A reserved configured prefix is routable to the built-in canonical provider
-  // (runtime never routes it to the compatible node). `resolveProviderAlias`
-  // maps e.g. `cx` → `codex`. Only an ambiguous prefix has no routable target.
-  if (configured && configured.status === "ambiguous") {
-    return { ok: false };
-  }
-  const resolvedNodeId = prefixToNode.get(provider);
-  if (resolvedNodeId && !eligibleNodeIds.has(resolvedNodeId)) return { ok: false };
-  const canonicalProvider = resolvedNodeId || resolveProviderAlias(provider) || provider;
-
-  return { ok: true, target: `${canonicalProvider}/${modelId}` };
+  return `${resolveProviderAlias(provider) || provider}/${modelId}`;
 }
 
 export async function GET(request: Request) {
   const authError = await requireManagementAuth(request);
   if (authError) return authError;
 
-  const { nodeToPrefix, eligibleNodeIds, compatibleNodeIds } = await loadPrefixMaps();
-  return NextResponse.json({
-    overrides: await listPublicOverrides(nodeToPrefix, eligibleNodeIds, compatibleNodeIds),
-  });
+  return NextResponse.json({ overrides: listPublicOverrides() });
 }
 
 export async function PATCH(request: Request) {
@@ -162,28 +75,17 @@ export async function PATCH(request: Request) {
     return NextResponse.json({ error: parsed.error.issues }, { status: 400 });
   }
 
-  const { entries, nodeToPrefix, prefixToNode, eligibleNodeIds, compatibleNodeIds } =
-    await loadPrefixMaps();
-  const canonical = canonicalizeTarget(
-    parsed.data.target,
-    entries,
-    prefixToNode,
-    compatibleNodeIds,
-    eligibleNodeIds
-  );
-  if (!canonical.ok) {
-    return NextResponse.json(
-      { error: "Invalid or ambiguous model capability override target" },
-      { status: 400 }
-    );
+  const target = canonicalizeTarget(parsed.data.target);
+  if (!target) {
+    return NextResponse.json({ error: "Invalid model capability override" }, { status: 400 });
   }
 
-  const targetParts = canonical.target.split(/\/(.*)/s);
+  const targetParts = target.split(/\/(.*)/s);
   const written =
     parsed.data.key === "context_length"
       ? setModelContextOverride(targetParts[0], targetParts[1], parsed.data.value, "manual")
       : setModelCapabilityOverride(
-          canonical.target,
+          target,
           parsed.data.key as ModelCapabilityOverrideKey,
           parsed.data.value
         );
@@ -191,9 +93,7 @@ export async function PATCH(request: Request) {
     return NextResponse.json({ error: "Invalid model capability override" }, { status: 400 });
   }
 
-  return NextResponse.json({
-    overrides: await listPublicOverrides(nodeToPrefix, eligibleNodeIds, compatibleNodeIds),
-  });
+  return NextResponse.json({ overrides: listPublicOverrides() });
 }
 
 export async function DELETE(request: Request) {
@@ -201,33 +101,19 @@ export async function DELETE(request: Request) {
   if (authError) return authError;
 
   const { searchParams } = new URL(request.url);
+  const target = canonicalizeTarget(searchParams.get("target") || "");
   const key = searchParams.get("key") || "";
   const parsedKey = overrideKeySchema.safeParse(key);
 
-  const { entries, nodeToPrefix, prefixToNode, eligibleNodeIds, compatibleNodeIds } =
-    await loadPrefixMaps();
-  const canonical = canonicalizeTarget(
-    searchParams.get("target") || "",
-    entries,
-    prefixToNode,
-    compatibleNodeIds,
-    eligibleNodeIds
-  );
-
-  if (!canonical.ok || !parsedKey.success) {
-    return NextResponse.json(
-      { error: "target and key are required; target must be a valid model override target" },
-      { status: 400 }
-    );
+  if (!target || !parsedKey.success) {
+    return NextResponse.json({ error: "target and key are required" }, { status: 400 });
   }
 
   if (parsedKey.data === "context_length") {
-    const targetParts = canonical.target.split(/\/(.*)/s);
+    const targetParts = target.split(/\/(.*)/s);
     removeModelContextOverride(targetParts[0], targetParts[1]);
   } else {
-    removeModelCapabilityOverride(canonical.target, parsedKey.data as ModelCapabilityOverrideKey);
+    removeModelCapabilityOverride(target, parsedKey.data as ModelCapabilityOverrideKey);
   }
-  return NextResponse.json({
-    overrides: await listPublicOverrides(nodeToPrefix, eligibleNodeIds, compatibleNodeIds),
-  });
+  return NextResponse.json({ overrides: listPublicOverrides() });
 }

src/app/api/pricing/models/route.ts

@@ -1,7 +1,6 @@
 import { NextResponse } from "next/server";
 import { REGISTRY } from "@omniroute/open-sse/config/providerRegistry.ts";
 import { getAllCustomModels, getAllSyncedAvailableModels, getPricing } from "@/lib/localDb";
-import { getProviderPrefixIndex } from "@/lib/providerNodePrefixes";
 
 function asRecord(value: unknown): Record<string, unknown> {
   return value && typeof value === "object" && !Array.isArray(value)
@@ -29,12 +28,6 @@ export async function GET() {
   try {
     const catalog: Record<string, any> = {};
 
-    // Pre-load compatible-provider node public prefixes once (shared across the
-    // whole catalog build — never N lookups per model). Only uniquely-routable
-    // prefixes are exposed as public targets (reserved/ambiguous are not).
-    const { nodeToPrefix, prefixToNode, eligibleNodeIds, compatibleNodeIds } =
-      await getProviderPrefixIndex();
-
     // ── 1. Registry models (hardcoded) ──────────────────────────────
     for (const entry of Object.values(REGISTRY)) {
       const alias = entry.alias || entry.id;
@@ -61,13 +54,6 @@ export async function GET() {
       return providerId;
     };
 
-    // A compatible provider node should surface under its configured public
-    // prefix, never its generated `openai-compatible-chat-<uuid>` node id
-    // (#9557). The internal `id` (node id) is preserved for PricingTab and
-    // runtime capability lookup. Only a uniquely-routable non-reserved winner
-    // is Model-Overrides eligible (marked explicitly); a compatible node that
-    // is reserved/losing/no-prefix is marked ineligible and skipped by the
-    // Model-Overrides helper.
     const ensureCatalogProvider = (providerId: string, alias: string) => {
       if (!catalog[alias]) {
         catalog[alias] = {
@@ -78,11 +64,6 @@ export async function GET() {
           format: "openai",
           models: [],
         };
-        const prefix = nodeToPrefix.get(providerId);
-        if (prefix) catalog[alias].displayPrefix = prefix;
-        if (compatibleNodeIds.has(providerId)) {
-          catalog[alias].modelOverrideEligible = eligibleNodeIds.has(providerId);
-        }
       }
       return catalog[alias];
     };
@@ -130,13 +111,6 @@ export async function GET() {
     }
 
     // ── 4. Pricing-only models (DB) ─────────────────────────────────
-    // Pricing may be keyed by the node's public prefix (what the operator typed)
-    // or by the internal node id. When keyed by a uniquely-routable public
-    // prefix, reconcile it to that node so the model list merges into the
-    // canonical compatible-provider entry instead of duplicating it, and
-    // preserve the original pricing namespace as `pricingKey` so PricingTab can
-    // read/save/reset against it. Reserved / ambiguous prefixes have no single
-    // routable node and stay as-is.
     let pricingData: Record<string, any> = {};
     try {
       pricingData = await getPricing();
@@ -144,10 +118,7 @@ export async function GET() {
       /* DB may not be ready */
     }
 
-    for (const [rawProviderAlias, models] of Object.entries(pricingData)) {
-      // `rawProviderAlias` is the original pricing namespace the operator used.
-      const pricingKey = rawProviderAlias;
-      const providerAlias = prefixToNode.get(rawProviderAlias) || rawProviderAlias;
+    for (const [providerAlias, models] of Object.entries(pricingData)) {
       if (!catalog[providerAlias]) {
         catalog[providerAlias] = {
           id: providerAlias,
@@ -157,16 +128,6 @@ export async function GET() {
           format: "openai",
           models: [],
         };
-        const prefix = nodeToPrefix.get(providerAlias);
-        if (prefix) catalog[providerAlias].displayPrefix = prefix;
-        if (compatibleNodeIds.has(providerAlias)) {
-          catalog[providerAlias].modelOverrideEligible = eligibleNodeIds.has(providerAlias);
-        }
-      }
-      // When the entry is keyed internally by the node id but priced under a
-      // public prefix, remember the original pricing namespace for PricingTab.
-      if (pricingKey !== providerAlias && !catalog[providerAlias].pricingKey) {
-        catalog[providerAlias].pricingKey = pricingKey;
       }
 
       const existingIds = new Set(catalog[providerAlias].models.map((m) => m.id));

src/app/api/providers/[id]/models/adobeFireflyDiscovery.ts

@@ -1,73 +0,0 @@
-import {
-  discoverAdobeFireflyModels,
-  resolveAdobeAccessToken,
-} from "@omniroute/open-sse/services/adobeFireflyClient.ts";
-import {
-  getAdobeFireflyFallbackCatalog,
-  mapDiscoveredToCatalog,
-  toAdobeMediaCapabilitiesApi,
-  type AdobeFireflyCatalogModel,
-} from "@omniroute/open-sse/services/adobeFireflyModels.ts";
-import { sanitizeErrorMessage } from "@omniroute/open-sse/utils/error";
-
-type AdobeProviderData = { cookie?: unknown; access_token?: unknown; accessToken?: unknown };
-
-interface AdobeProviderModelsResult {
-  models: Array<Record<string, unknown>>;
-  source: "api" | "local_catalog";
-  warning?: string;
-}
-
-function toModelResponse(model: AdobeFireflyCatalogModel): Record<string, unknown> {
-  const endpoint = model.modality === "image" ? "images" : "videos";
-  return {
-    id: model.id,
-    name: model.name,
-    owned_by: "adobe-firefly",
-    apiFormat: endpoint,
-    supportedEndpoints: [endpoint],
-    type: model.modality,
-    input_modalities: model.inputModalities,
-    output_modalities: [model.modality],
-    supported_sizes: model.capabilities.supportedSizes,
-    media_capabilities: toAdobeMediaCapabilitiesApi(model),
-  };
-}
-
-function fallback(warning: string): AdobeProviderModelsResult {
-  return {
-    models: getAdobeFireflyFallbackCatalog().map(toModelResponse),
-    source: "local_catalog",
-    warning,
-  };
-}
-
-export async function getAdobeModels(
-  apiKey: string | undefined,
-  accessToken: string | undefined,
-  providerData: unknown,
-  fetchImpl: typeof fetch = fetch
-): Promise<AdobeProviderModelsResult> {
-  const providerSpecificData =
-    providerData && typeof providerData === "object" ? (providerData as AdobeProviderData) : {};
-  try {
-    const token = await resolveAdobeAccessToken(
-      {
-        apiKey,
-        accessToken,
-        providerSpecificData,
-      },
-      fetchImpl
-    );
-    const models = mapDiscoveredToCatalog(await discoverAdobeFireflyModels(token, fetchImpl));
-    return models.length > 0
-      ? { models: models.map(toModelResponse), source: "api" }
-      : fallback("Adobe Firefly discovery returned no callable image or video models");
-  } catch (error) {
-    return fallback(
-      `Adobe Firefly discovery unavailable: ${sanitizeErrorMessage(
-        error instanceof Error ? error.message : String(error)
-      )}`
-    );
-  }
-}

src/app/api/providers/[id]/models/route.ts

@@ -84,8 +84,10 @@ import {
   isAutoFetchModelsEnabled,
   persistDiscoveredModels,
 } from "@/lib/providerModels/modelDiscovery";
-import { buildProviderModelsUrl, getDiscoveryClientVersionOptions } from "./discoveryClientVersion";
-import { getAdobeModels } from "./adobeFireflyDiscovery";
+import {
+  buildProviderModelsUrl,
+  getDiscoveryClientVersionOptions,
+} from "./discoveryClientVersion";
 import {
   parseGeminiModelsList,
   type GeminiDiscoveryModel,
@@ -420,7 +422,10 @@ export async function GET(
       // #6267 — a models-endpoint redirect (307/308) is not a fixable-config
       // error. safeOutboundFetch throws REDIRECT_BLOCKED which
       // getSafeOutboundFetchErrorStatus maps to 503, but unlike the other 503
-      // Redirect blocks degrade to the local/cached catalog; invalid URLs remain hard errors.
+      // cases (URL_GUARD_BLOCKED / INVALID_URL, which are genuinely
+      // unrecoverable and stay hard errors) a blocked redirect should degrade to
+      // the local/cached catalog OmniRoute ships instead of surfacing a raw 503.
+      // General fix — covers any config-driven provider that 307s (e.g. qwen-web).
       if (error instanceof SafeOutboundFetchError && error.code === "REDIRECT_BLOCKED") {
         return buildDiscoveryFallbackResponse(warnings);
       }
@@ -429,11 +434,6 @@ export async function GET(
       return buildDiscoveryFallbackResponse(warnings);
     };
 
-    if (provider === "adobe-firefly") {
-      const discovery = await getAdobeModels(apiKey, accessToken, connection.providerSpecificData);
-      return buildResponse({ provider, connectionId, ...discovery });
-    }
-
     const maybeReturnCachedDiscovery = () => {
       if (!refresh && cachedDiscoveryModels.length > 0) {
         return buildCachedDiscoveryResponse();

src/app/api/v1/models/catalog.ts

@@ -1113,7 +1113,6 @@ async function buildUnifiedModelsResponseCore(
         input_modalities: imgModel.inputModalities || ["text"],
         output_modalities: ["image"],
         ...(imgModel.description ? { description: imgModel.description } : {}),
-        ...(imgModel.mediaCapabilities ? { media_capabilities: imgModel.mediaCapabilities } : {}),
       });
     }
 
@@ -1179,12 +1178,6 @@ async function buildUnifiedModelsResponseCore(
         created: timestamp,
         owned_by: videoModel.provider,
         type: "video",
-        supported_sizes: videoModel.supportedSizes,
-        input_modalities: ["text"],
-        output_modalities: ["video"],
-        ...(videoModel.mediaCapabilities
-          ? { media_capabilities: videoModel.mediaCapabilities }
-          : {}),
       });
     }
 

src/lib/modelCapabilityOverrideTargets.ts

@@ -1,79 +0,0 @@
-/**
- * Pure catalog → Model Override target conversion.
- *
- * The operator-facing Model Overrides surface must present a compatible
- * provider node under its configured public `prefix` (e.g. `vibeproxy/gpt-4o`)
- * — never the generated `openai-compatible-chat-<uuid>` node id (#9557).
- *
- * The pricing catalog keeps the internal `id` (the DB node id, which PricingTab
- * uses to key pricing data) and, when the node has a configured prefix, also
- * carries `displayPrefix`. This helper prefers `displayPrefix` for the public
- * label/target while leaving the raw id untouched for storage/runtime lookup.
- *
- * Model-Overrides eligibility seam: a compatible provider node is eligible only
- * when it is the unique, non-reserved runtime-routable winner of its configured
- * prefix. The catalog marks such winners with `modelOverrideEligible === true`
- * (and a `displayPrefix`); reserved/losing/no-public-prefix compatible nodes are
- * marked `modelOverrideEligible === false` and are SKIPPED — never surfaced
- * under a generated node UUID. Built-in / no-compatible catalog entries carry no
- * flag and remain targetable.
- */
-
-export interface PricingCatalogModel {
-  id: string;
-  name: string;
-}
-
-export interface PricingCatalogProvider {
-  id: string;
-  alias: string;
-  displayPrefix?: string;
-  /** Explicit Model-Overrides eligibility; undefined ⇒ eligible (built-in/no-compatible). */
-  modelOverrideEligible?: boolean;
-  models: PricingCatalogModel[];
-}
-
-export interface ModelOverrideTarget {
-  target: string;
-  provider: string;
-  modelId: string;
-  label: string;
-}
-
-/**
- * Whether a catalog provider is targetable in Model Overrides. Only compatible
- * nodes marked ineligible (reserved/losing/no-public-prefix) are skipped; all
- * built-in and no-compatible entries are eligible.
- */
-export function isModelOverrideEligible(provider: PricingCatalogProvider): boolean {
-  return provider.modelOverrideEligible !== false;
-}
-
-/**
- * Public display prefix for a compatible provider node, falling back to its
- * internal id when no operator-configured prefix is set.
- */
-export function modelOverrideProviderPrefix(provider: PricingCatalogProvider): string {
-  return provider.displayPrefix?.trim() || provider.id;
-}
-
-/**
- * Convert the /api/pricing/models catalog into Model Override targets. Each
- * target uses the node's public prefix (when configured) so the selector,
- * search, selected model, and the target sent to the override API never expose
- * a generated node UUID. Ineligible compatible nodes are skipped entirely.
- */
-export function toModelOverrideTargets(
-  catalog: Record<string, PricingCatalogProvider>
-): ModelOverrideTarget[] {
-  return Object.values(catalog).flatMap((provider) => {
-    if (!isModelOverrideEligible(provider)) return [];
-    const prefix = modelOverrideProviderPrefix(provider);
-    return provider.models.map((model) => ({
-      target: `${prefix}/${model.id}`,
-      provider: prefix,
-      modelId: model.id,
-      label: `${prefix}/${model.id}`,
-    }));
-  });
-}

src/lib/providerNodePrefixes.ts

@@ -1,144 +0,0 @@
-/**
- * Shared provider-node public-prefix index (#9557).
- *
- * A compatible provider node (openai/anthropic-compatible) can carry an
- * operator-configured public `prefix` (e.g. `vibeproxy`) that the Model
- * Overrides surface must expose instead of the generated
- * `openai-compatible-chat-<uuid>` node id.
- *
- * This module is the single narrow home for that index so both the pricing
- * catalog route and the override route resolve node → prefix / prefix → node
- * consistently. It does one `getProviderNodes()` DB read per call and derives
- * every map from it — no module-global mutable caches, no route-to-route
- * imports.
- *
- * Classification of each configured prefix (mirrors runtime semantics):
- *   - `reserved`: the prefix collides with a built-in registry id/alias
- *     (e.g. `cx` → codex). Such a node must NOT be advertised as a compatible
- *     public target and the prefix must never be canonicalized to that node —
- *     runtime routes reserved prefixes to the built-in provider, so the
- *     override route must too.
- *   - `unique`: a single runtime-routable node owns the prefix. When two or
- *     more nodes share a prefix, the runtime winner is deterministic (first
- *     openai-compatible node by id order, else first anthropic-compatible
- *     node — see `getModelInfo`), and the prefix index selects that same
- *     winner. Only the winner is targetable/displayed under the prefix;
- *     losing nodes are ineligible and never fall back to a node UUID target.
- *   - `ambiguous`: multiple nodes share the prefix but no runtime winner is
- *     selectable (no compatible node matches) — practically unreachable since
- *     only compatible nodes carry prefixes, kept for safety.
- *
- * Model-Overrides eligibility: a compatible node is eligible only when it is
- * the unique, non-reserved winner of its configured prefix (i.e. it is in
- * `eligibleNodeIds`). Reserved/losing/no-public-prefix compatible nodes are
- * ineligible and must be skipped — never surfaced under a generated node UUID.
- * Built-in/no-compatible catalog entries are always eligible.
- */
-
-import { REGISTRY } from "@omniroute/open-sse/config/providerRegistry.ts";
-import { getProviderNodes } from "@/lib/db/providers/nodes";
-
-export type ProviderPrefixStatus = "unique" | "ambiguous" | "reserved";
-
-export interface ProviderPrefixEntry {
-  prefix: string;
-  status: ProviderPrefixStatus;
-  /** Present only when `status === "unique"`. */
-  nodeId?: string;
-}
-
-export interface ProviderPrefixIndex {
-  /** prefix → classification entry (every configured prefix). */
-  entries: Map<string, ProviderPrefixEntry>;
-  /** nodeId → public prefix, only for uniquely-routable non-reserved winners. */
-  nodeToPrefix: Map<string, string>;
-  /** public prefix → nodeId, only for uniquely-routable non-reserved winners. */
-  prefixToNode: Map<string, string>;
-  /** Every compatible provider node id present in the node table. */
-  compatibleNodeIds: Set<string>;
-  /** Compatible node ids eligible for Model Overrides (unique non-reserved winners). */
-  eligibleNodeIds: Set<string>;
-}
-
-/**
- * Built-in reserved prefixes — registry ids + aliases, the same semantics the
- * runtime `getReservedProviderPrefixes()` uses so user-defined compatible-node
- * prefixes can never shadow a built-in provider.
- */
-export function buildReservedPrefixes(): Set<string> {
-  const reserved = new Set<string>();
-  for (const entry of Object.values(REGISTRY)) {
-    if (entry?.id) reserved.add(entry.id);
-    if (entry?.alias) reserved.add(entry.alias);
-  }
-  return reserved;
-}
-
-export interface CompatibleNodeLike {
-  id?: string;
-  type?: string;
-  prefix?: string | null;
-}
-
-/**
- * Pure prefix→node winner selection replicating the runtime `getModelInfo`
- * rule exactly: the first openai-compatible node (by DB/id order) whose
- * `prefix` matches wins; otherwise the first anthropic-compatible node.
- * `nodes` must already be in the runtime's id-ascending order (as
- * `getProviderNodes` returns).
- */
-export function selectCompatibleNodeForPrefix(
-  nodes: CompatibleNodeLike[],
-  prefix: string
-): CompatibleNodeLike | null {
-  const openaiMatch = nodes.find((n) => n.type === "openai-compatible" && n.prefix === prefix);
-  if (openaiMatch) return openaiMatch;
-  return nodes.find((n) => n.type === "anthropic-compatible" && n.prefix === prefix) ?? null;
-}
-
-export async function getProviderPrefixIndex(): Promise<ProviderPrefixIndex> {
-  const reserved = buildReservedPrefixes();
-  const nodes = (await getProviderNodes()) as CompatibleNodeLike[];
-  const compatible = nodes.filter(
-    (n) => n.type === "openai-compatible" || n.type === "anthropic-compatible"
-  );
-
-  const compatibleNodeIds = new Set<string>();
-  for (const node of compatible) {
-    if (node.id) compatibleNodeIds.add(node.id);
-  }
-
-  const byPrefix = new Map<string, CompatibleNodeLike[]>();
-  for (const node of compatible) {
-    const prefix = node.prefix?.trim();
-    if (!node.id || !prefix) continue;
-    const list = byPrefix.get(prefix) ?? [];
-    list.push(node);
-    byPrefix.set(prefix, list);
-  }
-
-  const entries = new Map<string, ProviderPrefixEntry>();
-  const nodeToPrefix = new Map<string, string>();
-  const prefixToNode = new Map<string, string>();
-  const eligibleNodeIds = new Set<string>();
-
-  for (const [prefix, prefixNodes] of byPrefix) {
-    if (reserved.has(prefix)) {
-      // Built-in registry id/alias — never a compatible public target.
-      entries.set(prefix, { prefix, status: "reserved" });
-      continue;
-    }
-    const winner = selectCompatibleNodeForPrefix(prefixNodes, prefix);
-    if (!winner?.id) {
-      entries.set(prefix, { prefix, status: "ambiguous" });
-      continue;
-    }
-    // The runtime-routable winner alone owns the prefix.
-    entries.set(prefix, { prefix, status: "unique", nodeId: winner.id });
-    nodeToPrefix.set(winner.id, prefix);
-    prefixToNode.set(prefix, winner.id);
-    eligibleNodeIds.add(winner.id);
-  }
-
-  return { entries, nodeToPrefix, prefixToNode, compatibleNodeIds, eligibleNodeIds };
-}

tests/unit/adobe-firefly-references.test.ts

@@ -1,90 +0,0 @@
-import { test } from "node:test";
-import assert from "node:assert";
-import {
-  ADOBE_FIREFLY_VIDEO_MODELS,
-  extractAdobeSourceImageReferences,
-  normalizeAdobeReferenceBlobs,
-} from "../../open-sse/services/adobeFireflyClient.ts";
-import { getAdobeModels } from "../../src/app/api/providers/[id]/models/adobeFireflyDiscovery.ts";
-
-function userImsJwt(): string {
-  const payload = Buffer.from(
-    JSON.stringify({
-      user_id: "test@AdobeID",
-      type: "access_token",
-      client_id: "clio-playground-web",
-    })
-  ).toString("base64url");
-  return `eyJhbGciOiJSUzI1NiJ9.${payload}.${"sig".padEnd(40, "x")}`;
-}
-
-test("reference validation enforces discovered roles, counts, and frame order", () => {
-  const kling = ADOBE_FIREFLY_VIDEO_MODELS["kling-3"];
-  assert.deepEqual(
-    normalizeAdobeReferenceBlobs(kling, [
-      { id: "frame-a", mediaType: "image", usage: "frame" },
-      { id: "frame-b", mediaType: "image", usage: "frame" },
-    ]),
-    [
-      { id: "frame-a", usage: "frame", order: 1 },
-      { id: "frame-b", usage: "frame", order: 2 },
-    ]
-  );
-  assert.throws(
-    () => normalizeAdobeReferenceBlobs(kling, [{ id: "bad", mediaType: "image", usage: "mask" }]),
-    /does not support image references with usage 'mask'/
-  );
-  assert.throws(
-    () =>
-      normalizeAdobeReferenceBlobs(kling, [
-        { id: "frame-a", usage: "frame" },
-        { id: "frame-b", usage: "frame" },
-        { id: "frame-c", usage: "frame" },
-      ]),
-    /at most 2 frame image reference/
-  );
-});
-
-test("structured references skip malformed entries and preserve explicit roles", () => {
-  assert.deepEqual(
-    extractAdobeSourceImageReferences({
-      adobe_reference_inputs: [
-        null,
-        { media_type: "video", source: "ignored" },
-        { media_type: "image", source: "data:image/png;base64,AAAA", usage: "frame", order: 2 },
-      ],
-    }),
-    [{ source: "data:image/png;base64,AAAA", usage: "frame", order: 2 }]
-  );
-});
-
-test("provider discovery adapter returns live capabilities and verified fallback", async () => {
-  const live = await getAdobeModels(undefined, userImsJwt(), {}, async () =>
-    Response.json({
-      models: [
-        {
-          modelId: "firefly-image",
-          acModelFamilyProviderDisplayName: "Adobe",
-          modelVersions: {
-            image5: {
-              enabled: true,
-              outputModality: ["image"],
-              modelDisplayName: "Firefly Image 5",
-              requestSchema: { type: "object", properties: { prompt: { type: "string" } } },
-            },
-          },
-        },
-      ],
-    })
-  );
-  assert.equal(live.source, "api");
-  assert.equal(live.models[0].id, "firefly-image-image5");
-  assert.ok(live.models[0].media_capabilities);
-
-  const fallback = await getAdobeModels(undefined, userImsJwt(), {}, async () => {
-    throw new Error("offline");
-  });
-  assert.equal(fallback.source, "local_catalog");
-  assert.equal(fallback.models.length, 52);
-  assert.match(fallback.warning || "", /discovery unavailable/);
-});

tests/unit/adobe-firefly.test.ts

@@ -78,11 +78,6 @@ test("adobe-firefly is registered in IMAGE_PROVIDERS with adobe-firefly-image fo
   assert.equal(entry.format, "adobe-firefly-image");
   assert.match(entry.baseUrl, /firefly-3p\.ff\.adobe\.io/);
   assert.ok(Array.isArray(entry.models) && entry.models.length >= 4);
-  assert.equal(
-    entry.models.some((model: { id: string }) => model.id === "nano-banana-pro"),
-    false,
-    "routing-only compatibility aliases must not be advertised as discovered models"
-  );
 });
 
 test("adobe-firefly is registered in VIDEO_PROVIDERS with adobe-firefly-video format", () => {
@@ -159,25 +154,20 @@ test("normalizeAdobeOutputResolution maps quality tiers", () => {
   assert.equal(normalizeAdobeOutputResolution(undefined, undefined), "2K");
 });
 
-test("resolveAdobeImageModel maps valid aliases to exact discovery ids", () => {
-  assert.equal(resolveAdobeImageModel("nano-banana-pro").id, "gemini-flash-nano-banana-2");
-  assert.equal(
-    resolveAdobeImageModel("adobe-firefly/nano-banana-2").id,
-    "gemini-flash-nano-banana-3"
-  );
-  assert.equal(resolveAdobeImageModel("gpt-image").id, "gpt-image-2");
-  assert.throws(
-    () => resolveAdobeImageModel("invented-image-model"),
-    /Unknown Adobe Firefly image model/
-  );
+test("resolveAdobeImageModel maps catalog and long model ids", () => {
+  assert.equal(resolveAdobeImageModel("nano-banana-pro").id, "nano-banana-pro");
+  assert.equal(resolveAdobeImageModel("adobe-firefly/nano-banana-2").id, "nano-banana-2");
+  assert.equal(resolveAdobeImageModel("firefly-nano-banana-pro-2k-16x9").id, "nano-banana-pro");
+  assert.equal(resolveAdobeImageModel("gpt-image").id, "gpt-image");
   assert.ok(ADOBE_FIREFLY_IMAGE_MODELS["nano-banana-pro"].upstreamModelVersion);
 });
 
-test("resolveAdobeVideoModel maps only discovered video models", () => {
-  assert.equal(resolveAdobeVideoModel("veo-3.1-fast").id, "veo-3.1-fast-generate");
-  assert.equal(resolveAdobeVideoModel("kling-3").id, "kling-kling-v3-standard-i2v");
-  assert.throws(() => resolveAdobeVideoModel("sora-2"), /Unknown Adobe Firefly video model/);
-  assert.ok(ADOBE_FIREFLY_VIDEO_MODELS["veo-3.1"].defaultDuration > 0);
+test("resolveAdobeVideoModel maps sora/veo/kling families", () => {
+  assert.equal(resolveAdobeVideoModel("sora-2").id, "sora-2");
+  assert.equal(resolveAdobeVideoModel("firefly-sora2-pro-8s-16x9").id, "sora-2-pro");
+  assert.equal(resolveAdobeVideoModel("veo-3.1-fast").id, "veo-3.1-fast");
+  assert.equal(resolveAdobeVideoModel("kling-3").id, "kling-3");
+  assert.ok(ADOBE_FIREFLY_VIDEO_MODELS["sora-2"].defaultDuration > 0);
 });
 
 test("buildAdobeImagePayload produces nano and gpt-image shapes", () => {
@@ -275,12 +265,41 @@ test("buildAdobeImagePayload attaches referenceBlobs like live adobe_atach_image
     sourceImageIds: ["aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee"],
   });
   assert.deepEqual(gpt.referenceBlobs, [
-    { id: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee", usage: "source" },
+    { id: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee", usage: "subject" },
   ]);
   assert.equal((gpt.generationMetadata as Record<string, unknown>).module, "image2image");
+
+  // gpt-image: only first 2 subject refs survive (extra screenshots hang colligo).
+  const gptMany = buildAdobeImagePayload({
+    prompt: "edit me",
+    aspectRatio: "1:1",
+    outputResolution: "1K",
+    modelSpec: ADOBE_FIREFLY_IMAGE_MODELS["gpt-image-2"],
+    sourceImageIds: ["id-1", "id-2", "id-3", "id-4", "id-5"],
+  });
+  assert.deepEqual(gptMany.referenceBlobs, [
+    { id: "id-1", usage: "subject" },
+    { id: "id-2", usage: "subject" },
+  ]);
+
+  // nano keeps up to 4 general refs for multi-panel composition.
+  const nanoMany = buildAdobeImagePayload({
+    prompt: "compose",
+    aspectRatio: "16:9",
+    outputResolution: "2K",
+    modelSpec: ADOBE_FIREFLY_IMAGE_MODELS["nano-banana-2"],
+    sourceImageIds: ["a", "b", "c", "d", "e"],
+  });
+  assert.equal((nanoMany.referenceBlobs as unknown[]).length, 4);
+  assert.equal((nanoMany.referenceBlobs as Array<{ usage: string }>)[0].usage, "general");
 });
 
-test("adobeFireflyImageTimeoutMs scales boundedly with reference count", () => {
+test("adobeFireflyMaxImageRefs + adaptive image timeout", () => {
+  assert.equal(adobeFireflyMaxImageRefs("gpt-image-2"), 2);
+  assert.equal(adobeFireflyMaxImageRefs("adobe-firefly/gpt-image"), 2);
+  assert.equal(adobeFireflyMaxImageRefs("nano-banana-2"), 4);
+  assert.equal(adobeFireflyMaxImageRefs("flux-2"), 2);
+
   assert.equal(adobeFireflyImageTimeoutMs({ refCount: 0 }), DEFAULT_IMAGE_TIMEOUT_MS);
   assert.equal(
     adobeFireflyImageTimeoutMs({ refCount: 2 }),
@@ -362,7 +381,16 @@ test("resolveAdobeSourceImageIds uploads data URLs then returns blob ids", async
   assert.equal(ADOBE_FIREFLY_IMAGE_UPLOAD_URL.includes("storage/image"), true);
 });
 
-test("buildAdobeVideoPayload follows discovered fields and reference roles", () => {
+test("buildAdobeVideoPayload produces sora and veo shapes", () => {
+  const sora = buildAdobeVideoPayload({
+    prompt: "ocean waves",
+    aspectRatio: "16:9",
+    duration: 8,
+    modelSpec: ADOBE_FIREFLY_VIDEO_MODELS["sora-2"],
+  });
+  assert.equal(sora.modelId, "sora");
+  assert.equal(sora.duration, 8);
+
   const veo = buildAdobeVideoPayload({
     prompt: "city flyover",
     aspectRatio: "9:16",
@@ -371,30 +399,12 @@ test("buildAdobeVideoPayload follows discovered fields and reference roles", ()
   });
   assert.equal(veo.modelId, "veo");
   assert.equal(veo.modelVersion, "3.1-generate");
-  assert.equal(veo.duration, 6);
-  assert.equal(veo.generateAudio, true);
-
-  const kling = buildAdobeVideoPayload({
-    prompt: "ocean waves",
-    aspectRatio: "16:9",
-    duration: 5,
-    modelSpec: ADOBE_FIREFLY_VIDEO_MODELS["kling-3"],
-    sourceImageIds: ["aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee"],
-  });
-  assert.equal(kling.modelVersion, "kling_v3_standard_i2v");
-  assert.deepEqual(kling.referenceBlobs, [
-    { id: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee", usage: "frame", order: 1 },
-  ]);
-  assert.throws(
-    () =>
-      buildAdobeVideoPayload({
-        prompt: "bad duration",
-        aspectRatio: "16:9",
-        duration: 5,
-        modelSpec: ADOBE_FIREFLY_VIDEO_MODELS["veo-3.1"],
-      }),
-    /supports duration/
+  assert.equal(
+    (veo.modelSpecificPayload as Record<string, Record<string, unknown>>).parameters
+      .durationSeconds,
+    6
   );
+  assert.equal(veo.generateAudio, true);
 });
 
 test("extractAdobeResultLink prefers x-override-status-link then links.result", () => {
@@ -529,7 +539,7 @@ test("adobe-firefly is in USAGE_SUPPORTED_PROVIDERS for Limits", () => {
   assert.ok(USAGE_SUPPORTED_PROVIDERS.includes("firefly"));
 });
 
-test("parseAdobeModelsDiscovery preserves schemas and maps exact ids", () => {
+test("parseAdobeModelsDiscovery extracts image/video versions", () => {
   const rows = parseAdobeModelsDiscovery({
     models: [
       {
@@ -540,44 +550,16 @@ test("parseAdobeModelsDiscovery preserves schemas and maps exact ids", () => {
             outputModality: ["image"],
             modelDisplayName: "Gemini 3.0 (Nano Banana Pro)",
             healthStatus: "HEALTHY",
-            inputMediaUseCase: ["editing"],
-            bksGenerationModel: "firefly_3p:external:gemini_flash_2",
-            requestSchema: {
-              type: "object",
-              properties: {
-                prompt: { type: "string" },
-                referenceBlobs: {
-                  maxItems: 14,
-                  "x-capabilities": [
-                    {
-                      mediaType: "image",
-                      usageConstraints: [{ usageType: "general", minItems: 0, maxItems: 14 }],
-                      maxFileSizeBytes: 104857600,
-                    },
-                  ],
-                },
-              },
-            },
           },
         },
       },
       {
-        modelId: "veo",
+        modelId: "sora",
         modelVersions: {
-          "3.1-generate": {
+          "sora-2": {
             enabled: true,
             outputModality: ["video"],
-            modelDisplayName: "Veo 3.1",
-            requestSchema: {
-              allOf: [
-                {
-                  properties: {
-                    prompt: { type: "string" },
-                    duration: { anyOf: [{ type: "integer", enum: [4, 6, 8] }] },
-                  },
-                },
-              ],
-            },
+            modelDisplayName: "Sora 2",
           },
         },
       },
@@ -587,35 +569,14 @@ test("parseAdobeModelsDiscovery preserves schemas and maps exact ids", () => {
   assert.equal(rows[0].modality, "image");
   assert.equal(rows[1].modality, "video");
   const catalog = mapDiscoveredToCatalog(rows);
-  assert.ok(catalog.some((m) => m.id === "gemini-flash-nano-banana-2"));
-  assert.ok(catalog.some((m) => m.id === "veo-3.1-generate"));
-  assert.equal(catalog[0].capabilities.referenceInputs[0].maxItems, 14);
-  assert.deepEqual(catalog[1].capabilities.supportedDurations, [4, 6, 8]);
+  assert.ok(catalog.some((m) => m.id === "nano-banana-pro"));
+  assert.ok(catalog.some((m) => m.id === "sora-2"));
 });
 
-test("fallback catalog is the verified discovery snapshot without invented Sora", () => {
-  assert.equal(ADOBE_FIREFLY_FALLBACK_MODELS.length, 52);
-  assert.equal(getAdobeFireflyFallbackCatalog("image").length, 17);
-  assert.equal(getAdobeFireflyFallbackCatalog("video").length, 35);
-  assert.equal(
-    ADOBE_FIREFLY_FALLBACK_MODELS.some((model) => model.id.includes("sora")),
-    false
-  );
-  assert.equal(
-    ADOBE_FIREFLY_FALLBACK_MODELS.some(
-      (model) => model.id.includes("kling") && model.id.includes("omni")
-    ),
-    false
-  );
-  assert.ok(ADOBE_FIREFLY_FALLBACK_MODELS.some((model) => model.id === "kling-kling-o3"));
-  assert.equal(
-    ADOBE_FIREFLY_IMAGE_MODELS["nano-banana-pro"].capabilities.referenceInputs[0].maxItems,
-    14
-  );
-  assert.equal(
-    ADOBE_FIREFLY_IMAGE_MODELS["gpt-image"].capabilities.referenceInputs[0].maxItems,
-    16
-  );
+test("fallback catalog has image and video entries from get_models capture", () => {
+  assert.ok(ADOBE_FIREFLY_FALLBACK_MODELS.length >= 10);
+  assert.ok(getAdobeFireflyFallbackCatalog("image").length >= 4);
+  assert.ok(getAdobeFireflyFallbackCatalog("video").length >= 4);
 });
 
 test("extractAdobeAccountIdFromToken reads user_id claim", () => {
@@ -755,7 +716,7 @@ test("adobeFireflyGenerateVideo submit+poll happy path (mocked)", async () => {
   const result = await adobeFireflyGenerateVideo({
     accessToken: "tok",
     prompt: "drone over forest",
-    model: "veo-3.1",
+    model: "sora-2",
     duration: 4,
     aspectRatio: "16:9",
     fetchImpl: fetchImpl as typeof fetch,
@@ -766,7 +727,7 @@ test("adobeFireflyGenerateVideo submit+poll happy path (mocked)", async () => {
 
 test("handleAdobeFireflyVideoGeneration returns 400 without prompt", async () => {
   const result = await handleAdobeFireflyVideoGeneration({
-    model: "veo-3.1",
+    model: "sora-2",
     provider: "adobe-firefly",
     body: {},
     credentials: { apiKey: "aaa.bbb.ccc" },

tests/unit/model-overrides-provider-prefix-9557.test.ts

@@ -1,584 +0,0 @@
-import { describe, it, beforeEach, after } from "node:test";
-import assert from "node:assert/strict";
-import fs from "node:fs";
-import os from "node:os";
-import path from "node:path";
-
-const moduleDataDir = fs.mkdtempSync(path.join(os.tmpdir(), "omni-model-overrides-prefix-"));
-process.env.DATA_DIR = moduleDataDir;
-
-const coreDb = await import("../../src/lib/db/core.ts");
-const nodes = await import("../../src/lib/db/providers/nodes.ts");
-const models = await import("../../src/lib/db/models.ts");
-const overrides = await import("../../src/lib/db/modelCapabilityOverrides.ts");
-const contextOverrides = await import("../../src/lib/db/modelContextOverrides.ts");
-const pricingRoute = await import("../../src/app/api/pricing/models/route.ts");
-const overrideRoute = await import("../../src/app/api/model-capability-overrides/route.ts");
-const targets = await import("../../src/lib/modelCapabilityOverrideTargets.ts");
-const caps = await import("../../src/lib/modelCapabilities.ts");
-const prefixIndex = await import("../../src/lib/providerNodePrefixes.ts");
-// Runtime prefix→node resolution (same path the request pipeline uses).
-const sseModel = await import("../../src/sse/services/model.ts");
-
-beforeEach(() => {
-  coreDb.resetDbInstance();
-  fs.rmSync(moduleDataDir, { recursive: true, force: true });
-  fs.mkdirSync(moduleDataDir, { recursive: true });
-  coreDb.getDbInstance();
-});
-
-after(() => {
-  coreDb.resetDbInstance();
-  fs.rmSync(moduleDataDir, { recursive: true, force: true });
-});
-
-const NODE_ID = "openai-compatible-chat-02669115-2545-4896-b003-cb4dac09d441";
-const NODE_PREFIX = "vibeproxy";
-const NODE_TYPE = "openai-compatible";
-
-async function seedNodeWithSyncedModel(modelId = "gpt-4o", opts: { prefix?: string | null } = {}) {
-  await nodes.createProviderNode({
-    id: NODE_ID,
-    type: NODE_TYPE,
-    prefix: opts.prefix === undefined ? NODE_PREFIX : opts.prefix,
-    name: "VibeProxy",
-    apiType: "chat",
-    baseUrl: "https://example.com/v1",
-  });
-  await models.replaceSyncedAvailableModelsForConnection(NODE_ID, NODE_ID, [
-    { id: modelId, name: modelId },
-  ]);
-}
-
-describe("issue #9557: model overrides expose configured provider prefix, not node UUID", () => {
-  it("pricing/models returns public displayPrefix while retaining internal node id", async () => {
-    await seedNodeWithSyncedModel();
-    const response = await pricingRoute.GET();
-    assert.equal(response.status, 200);
-    const catalog = (await response.json()) as Record<
-      string,
-      { id: string; alias: string; displayPrefix?: string; models: Array<{ id: string }> }
-    >;
-
-    const entry = Object.values(catalog).find((provider) => provider.id === NODE_ID);
-    assert.ok(entry, "compatible node must appear in the pricing catalog");
-    assert.equal(entry.id, NODE_ID, "internal node id must be preserved for PricingTab");
-    assert.equal(entry.displayPrefix, NODE_PREFIX, "public display prefix must be exposed");
-    assert.ok(
-      entry.models.some((model) => model.id === "gpt-4o"),
-      "synced model must be listed under the compatible node"
-    );
-  });
-
-  it("toModelOverrideTargets labels/selects with the public prefix, never the node UUID", () => {
-    const catalog = {
-      [NODE_ID]: {
-        id: NODE_ID,
-        alias: NODE_ID,
-        displayPrefix: NODE_PREFIX,
-        models: [{ id: "gpt-4o", name: "gpt-4o" }],
-      },
-      openai: {
-        id: "openai",
-        alias: "openai",
-        models: [{ id: "gpt-4o", name: "gpt-4o" }],
-      },
-      // A losing/reserved compatible node explicitly marked ineligible must be
-      // skipped entirely — never surfaced under a node UUID.
-      "openai-compatible-chat-loser": {
-        id: "openai-compatible-chat-loser",
-        alias: "openai-compatible-chat-loser",
-        displayPrefix: NODE_PREFIX,
-        modelOverrideEligible: false,
-        models: [{ id: "lost-model", name: "lost-model" }],
-      },
-    };
-    const result = targets.toModelOverrideTargets(catalog);
-    const [compatible, builtin] = result;
-
-    assert.equal(result.length, 2, "ineligible compatible node is skipped");
-    assert.equal(compatible.target, `${NODE_PREFIX}/gpt-4o`);
-    assert.equal(compatible.provider, NODE_PREFIX);
-    assert.equal(compatible.label, `${NODE_PREFIX}/gpt-4o`);
-    assert.ok(!compatible.target.includes(NODE_ID), "public target must not leak the node UUID");
-    assert.ok(!result.some((t) => t.target.includes("lost-model")), "lost node not a target");
-    assert.equal(builtin.target, "openai/gpt-4o");
-    assert.equal(
-      targets.isModelOverrideEligible(catalog[NODE_ID]),
-      true,
-      "unflagged compatible winner is eligible"
-    );
-    assert.equal(
-      targets.isModelOverrideEligible(catalog["openai-compatible-chat-loser"]),
-      false,
-      "explicitly ineligible node is excluded"
-    );
-    assert.equal(targets.isModelOverrideEligible(catalog.openai), true, "built-in is eligible");
-  });
-
-  it("PATCH canonicalizes a configured prefix to the internal node id and runtime lookup applies it", async () => {
-    await seedNodeWithSyncedModel("gpt-4o");
-
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_output_tokens",
-          value: 123456,
-        }),
-      })
-    );
-    assert.equal(patch.status, 200);
-
-    // Persisted under the internal node id (where runtime lookup reads it).
-    const stored = overrides.listModelCapabilityOverrides();
-    assert.equal(stored.length, 1);
-    assert.equal(stored[0].provider, NODE_ID);
-    assert.equal(stored[0].modelId, "gpt-4o");
-
-    // Runtime capability lookup resolves provider/model and applies the override.
-    const resolved = caps.getResolvedModelCapabilities({
-      provider: NODE_ID,
-      model: "gpt-4o",
-    });
-    assert.equal(resolved.maxOutputTokens, 123456);
-    const explicit = caps.getExplicitModelOutputCap({ provider: NODE_ID, model: "gpt-4o" });
-    assert.equal(explicit, 123456);
-  });
-
-  it("runtime getModelInfo resolves prefix/model back to the node id (routing seam)", async () => {
-    await seedNodeWithSyncedModel("gpt-4o");
-
-    const info = await sseModel.getModelInfo(`${NODE_PREFIX}/gpt-4o`);
-    assert.ok(info, "getModelInfo must resolve");
-    assert.equal(info.provider, NODE_ID, "prefix must route to the internal node id at runtime");
-  });
-
-  it("index winner matches runtime getModelInfo for a duplicated prefix", async () => {
-    // Two nodes share the prefix. Runtime resolves the FIRST openai-compatible
-    // node by id order. The prefix index must select that same winner so the
-    // UI and PATCH agree with the routing seam.
-    const nodeAId = NODE_ID;
-    const nodeBId = "openai-compatible-chat-22222222-2222-4333-8444-555555555555";
-    await nodes.createProviderNode({
-      id: nodeBId,
-      type: NODE_TYPE,
-      prefix: NODE_PREFIX,
-      name: "VibeProxy B",
-      apiType: "chat",
-      baseUrl: "https://example.com/b/v1",
-    });
-    await nodes.createProviderNode({
-      id: nodeAId,
-      type: NODE_TYPE,
-      prefix: NODE_PREFIX,
-      name: "VibeProxy A",
-      apiType: "chat",
-      baseUrl: "https://example.com/a/v1",
-    });
-    await models.replaceSyncedAvailableModelsForConnection(nodeAId, nodeAId, [
-      { id: "gpt-4o", name: "gpt-4o" },
-    ]);
-
-    const info = await sseModel.getModelInfo(`${NODE_PREFIX}/gpt-4o`);
-    assert.equal(info.provider, nodeAId, "runtime resolves the first node by id");
-
-    const index = await prefixIndex.getProviderPrefixIndex();
-    assert.equal(
-      index.prefixToNode.get(NODE_PREFIX),
-      info.provider,
-      "index prefix→node must match the runtime winner"
-    );
-    assert.equal(index.entries.get(NODE_PREFIX)?.nodeId, info.provider);
-    assert.ok(index.eligibleNodeIds.has(info.provider));
-    assert.ok(!index.eligibleNodeIds.has(nodeBId));
-
-    // And PATCH persists to the same winner runtime resolves to.
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_input_tokens",
-          value: 77777,
-        }),
-      })
-    );
-    assert.equal(patch.status, 200);
-    assert.equal(overrides.listModelCapabilityOverrides()[0].provider, info.provider);
-  });
-
-  it("GET surfaces stored overrides under the public prefix and old raw rows still list/apply", async () => {
-    await seedNodeWithSyncedModel("gpt-4o");
-
-    // New-style row saved via the API (canonicalized to node id).
-    await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_input_tokens",
-          value: 99999,
-        }),
-      })
-    );
-
-    // Old raw-UUID-keyed row inserted directly (legacy pre-#9557 data).
-    assert.equal(
-      overrides.setModelCapabilityOverride(`${NODE_ID}/gpt-4o`, "max_output_tokens", 55555),
-      true
-    );
-
-    const get = await overrideRoute.GET(
-      new Request("http://localhost/api/model-capability-overrides")
-    );
-    assert.equal(get.status, 200);
-    const payload = (await get.json()) as {
-      overrides: Array<{ target: string; key: string; value: number }>;
-    };
-    const targetsFound = payload.overrides.map((entry) => entry.target).sort();
-    assert.deepEqual(targetsFound, [`${NODE_PREFIX}/gpt-4o`, `${NODE_PREFIX}/gpt-4o`]);
-    assert.ok(
-      payload.overrides.every((entry) => !entry.target.includes(NODE_ID)),
-      "public override list must not leak the node UUID"
-    );
-
-    // Old raw row still applies at runtime.
-    assert.equal(
-      caps.getResolvedModelCapabilities({ provider: NODE_ID, model: "gpt-4o" }).maxOutputTokens,
-      55555
-    );
-  });
-
-  it("GET/PATCH/DELETE JSON responses never leak the node UUID for a prefixed node", async () => {
-    await seedNodeWithSyncedModel("gpt-4o");
-    await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_output_tokens",
-          value: 333,
-        }),
-      })
-    );
-
-    const get = await overrideRoute.GET(
-      new Request("http://localhost/api/model-capability-overrides")
-    );
-    assert.ok(!(await get.text()).includes(NODE_ID), "GET body must not contain node UUID");
-
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_input_tokens",
-          value: 444,
-        }),
-      })
-    );
-    assert.ok(!(await patch.text()).includes(NODE_ID), "PATCH body must not contain node UUID");
-
-    const del = await overrideRoute.DELETE(
-      new Request(
-        `http://localhost/api/model-capability-overrides?target=${NODE_PREFIX}/gpt-4o&key=max_output_tokens`,
-        { method: "DELETE" }
-      )
-    );
-    assert.equal(del.status, 200);
-    const delBody = await del.text();
-    assert.ok(!delBody.includes(NODE_ID), "DELETE body must not contain node UUID");
-    // DELETE still returns the updated override list for the UI.
-    const delPayload = JSON.parse(delBody) as { overrides: unknown[] };
-    assert.ok(Array.isArray(delPayload.overrides), "DELETE returns { overrides }");
-    assert.equal(delPayload.overrides.length, 1, "remaining override still present");
-  });
-
-  it("duplicate prefix selects the same runtime winner; losing node never falls back to UUID", async () => {
-    // Two nodes share the same prefix → the runtime winner is the FIRST
-    // openai-compatible node by id order. The index and PATCH must choose that
-    // same winner; the losing node must NOT be targetable/displayed under the
-    // prefix and must NOT fall back to a node-UUID target.
-    const nodeAId = NODE_ID;
-    const nodeBId = "openai-compatible-chat-11111111-2222-4333-8444-555555555555";
-    await nodes.createProviderNode({
-      id: nodeBId,
-      type: NODE_TYPE,
-      prefix: NODE_PREFIX,
-      name: "VibeProxy B",
-      apiType: "chat",
-      baseUrl: "https://example.com/b/v1",
-    });
-    await nodes.createProviderNode({
-      id: nodeAId,
-      type: NODE_TYPE,
-      prefix: NODE_PREFIX,
-      name: "VibeProxy A",
-      apiType: "chat",
-      baseUrl: "https://example.com/a/v1",
-    });
-    await models.replaceSyncedAvailableModelsForConnection(nodeAId, nodeAId, [
-      { id: "gpt-4o", name: "gpt-4o" },
-    ]);
-
-    const index = await prefixIndex.getProviderPrefixIndex();
-    // Runtime resolves the first openai-compatible node by id order → nodeAId.
-    assert.equal(index.entries.get(NODE_PREFIX)?.status, "unique");
-    assert.equal(index.entries.get(NODE_PREFIX)?.nodeId, nodeAId, "winner is first by id");
-    assert.equal(index.prefixToNode.get(NODE_PREFIX), nodeAId);
-    assert.equal(index.nodeToPrefix.get(nodeAId), NODE_PREFIX);
-    // Losing node is ineligible — no node-UUID target, no prefix→node mapping.
-    assert.ok(!index.eligibleNodeIds.has(nodeBId), "losing node is ineligible");
-    assert.ok(!index.prefixToNode.has(nodeBId), "losing node id must not be a prefix target");
-    assert.ok(!index.nodeToPrefix.has(nodeBId), "losing node must not map to the shared prefix");
-
-    // Catalog advertises only the winner under the public prefix.
-    const catalogRes = await pricingRoute.GET();
-    const catalog = (await catalogRes.json()) as Record<
-      string,
-      { id: string; displayPrefix?: string }
-    >;
-    const winner = Object.values(catalog).find((p) => p.id === nodeAId);
-    assert.equal(winner?.displayPrefix, NODE_PREFIX, "winner advertised under prefix");
-    assert.ok(
-      !Object.values(catalog).some((p) => p.id === nodeBId && p.displayPrefix === NODE_PREFIX),
-      "losing node must not be advertised under the shared prefix"
-    );
-
-    // PATCH via the prefix canonicalizes to the winner (first by id) and the
-    // losing node is not targetable.
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${NODE_PREFIX}/gpt-4o`,
-          key: "max_output_tokens",
-          value: 123456,
-        }),
-      })
-    );
-    assert.equal(patch.status, 200);
-    const stored = overrides.listModelCapabilityOverrides();
-    assert.equal(stored.length, 1);
-    assert.equal(stored[0].provider, nodeAId, "PATCH must persist to the runtime winner");
-
-    // Raw compatible-node UUIDs are not public Model Overrides targets. The
-    // losing node remains routable internally, but stale/direct clients must
-    // use the configured public prefix rather than create an unmanageable row.
-    const losePatch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${nodeBId}/gpt-4o`,
-          key: "max_input_tokens",
-          value: 7,
-        }),
-      })
-    );
-    assert.equal(losePatch.status, 400);
-    const loseDelete = await overrideRoute.DELETE(
-      new Request(
-        `http://localhost/api/model-capability-overrides?target=${encodeURIComponent(`${nodeBId}/gpt-4o`)}&key=max_input_tokens`,
-        { method: "DELETE" }
-      )
-    );
-    assert.equal(loseDelete.status, 400);
-    assert.equal(overrides.listModelCapabilityOverrides().length, 1);
-  });
-
-  it("reserved prefix (cx → codex) is not advertised and not canonicalized to any node", async () => {
-    const RESERVED = "cx";
-    const reservedNodeId = "openai-compatible-chat-99999999-2222-4333-8444-555555555555";
-    await nodes.createProviderNode({
-      id: reservedNodeId,
-      type: NODE_TYPE,
-      prefix: RESERVED,
-      name: "Reserved Hijack",
-      apiType: "chat",
-      baseUrl: "https://example.com/cx/v1",
-    });
-
-    const index = await prefixIndex.getProviderPrefixIndex();
-    assert.equal(index.entries.get(RESERVED)?.status, "reserved");
-    assert.ok(
-      !index.nodeToPrefix.has(reservedNodeId),
-      "reserved-prefix node must not be exposed as a compatible target"
-    );
-    assert.ok(!index.prefixToNode.has(RESERVED), "reserved prefix must not map to any node");
-
-    // Catalog: reserved prefix must not surface as a displayPrefix on any entry.
-    const catalogRes = await pricingRoute.GET();
-    const catalog = (await catalogRes.json()) as Record<
-      string,
-      { displayPrefix?: string; id?: string }
-    >;
-    assert.ok(
-      !Object.values(catalog).some((provider) => provider.displayPrefix === RESERVED),
-      "reserved prefix must not be advertised as a compatible public target"
-    );
-
-    // PATCH using `cx/<model>` must route via resolveProviderAlias to the
-    // built-in codex provider (runtime routes `cx/` to codex) — never 400, and
-    // never persisted under the reserved-hijack node.
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${RESERVED}/gpt-4o`,
-          key: "max_output_tokens",
-          value: 1,
-        }),
-      })
-    );
-    assert.equal(patch.status, 200, "PATCH must route reserved prefix via resolveProviderAlias");
-
-    const stored = overrides.listModelCapabilityOverrides();
-    assert.equal(
-      stored.length,
-      1,
-      "reserved prefix override is persisted to the built-in provider"
-    );
-    assert.notEqual(stored[0].provider, reservedNodeId, "must never persist to the hijack node");
-    assert.equal(stored[0].provider, "codex", "reserved prefix must resolve to built-in codex");
-
-    const rawPatch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${reservedNodeId}/gpt-4o`,
-          key: "max_input_tokens",
-          value: 2,
-        }),
-      })
-    );
-    assert.equal(rawPatch.status, 400, "reserved node UUID must not be writable directly");
-  });
-
-  it("pricing-only compatible-provider model entry carries displayPrefix + pricingKey", async () => {
-    // Node exists but has NO synced/custom models; pricing is keyed by the
-    // public prefix and must be reconciled onto the unique node without
-    // duplicating entries, while preserving the original pricing namespace.
-    await nodes.createProviderNode({
-      id: NODE_ID,
-      type: NODE_TYPE,
-      prefix: NODE_PREFIX,
-      name: "VibeProxy",
-      apiType: "chat",
-      baseUrl: "https://example.com/v1",
-    });
-    const { updatePricing } = await import("../../src/lib/db/settings/pricing.ts");
-    // Seed a user pricing row keyed by the node's public prefix.
-    await updatePricing({
-      [NODE_PREFIX]: { "priced-model": { input_cost_per_million: 1, output_cost_per_million: 2 } },
-    });
-
-    const catalogRes = await pricingRoute.GET();
-    const catalog = (await catalogRes.json()) as Record<
-      string,
-      { id: string; displayPrefix?: string; pricingKey?: string; models: Array<{ id: string }> }
-    >;
-    const entry = Object.values(catalog).find((provider) => provider.id === NODE_ID);
-    assert.ok(entry, "pricing-only model must reconcile onto the compatible node");
-    assert.equal(entry.displayPrefix, NODE_PREFIX);
-    assert.equal(
-      entry.pricingKey,
-      NODE_PREFIX,
-      "pricingKey must preserve the original pricing namespace"
-    );
-    assert.deepEqual(
-      entry.models.map((model) => model.id),
-      ["priced-model"],
-      "pricing-only entry must be created without relying on synced/custom models"
-    );
-    // No duplicate entry keyed by the public prefix alone.
-    assert.ok(
-      !Object.values(catalog).some(
-        (provider) => provider.id === NODE_PREFIX && provider.displayPrefix !== NODE_PREFIX
-      ),
-      "pricing must not create a duplicate node-keyed entry"
-    );
-  });
-
-  it("no-prefix fallback and built-in providers keep raw internal id / unchanged behavior", async () => {
-    // Node with no prefix → target falls back to internal node id.
-    const noPrefixNodeId = "openai-compatible-chat-aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee";
-    await nodes.createProviderNode({
-      id: noPrefixNodeId,
-      type: NODE_TYPE,
-      prefix: null,
-      name: "NoPrefix",
-      apiType: "chat",
-      baseUrl: "https://example.com/np/v1",
-    });
-    await models.replaceSyncedAvailableModelsForConnection(noPrefixNodeId, noPrefixNodeId, [
-      { id: "np-model", name: "np-model" },
-    ]);
-
-    const patch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: `${noPrefixNodeId}/np-model`,
-          key: "max_output_tokens",
-          value: 777,
-        }),
-      })
-    );
-    assert.equal(patch.status, 400, "no-prefix compatible node UUID must not be writable");
-    assert.equal(overrides.listModelCapabilityOverrides().length, 0);
-
-    const rawDelete = await overrideRoute.DELETE(
-      new Request(
-        `http://localhost/api/model-capability-overrides?target=${encodeURIComponent(`${noPrefixNodeId}/np-model`)}&key=max_output_tokens`,
-        { method: "DELETE" }
-      )
-    );
-    assert.equal(rawDelete.status, 400);
-
-    // Model-Overrides eligibility seam: a compatible node with NO public prefix
-    // is skipped from the public override list — it is never surfaced under a
-    // generated node UUID. Built-in / no-compatible entries remain targetable.
-    const get = await overrideRoute.GET(
-      new Request("http://localhost/api/model-capability-overrides")
-    );
-    const payload = (await get.json()) as { overrides: Array<{ target: string }> };
-    assert.ok(
-      !payload.overrides.some((entry) => entry.target === `${noPrefixNodeId}/np-model`),
-      "no-public-prefix compatible node must be skipped from the override list"
-    );
-
-    // Built-in provider (openai) unchanged.
-    const openaiPatch = await overrideRoute.PATCH(
-      new Request("http://localhost/api/model-capability-overrides", {
-        method: "PATCH",
-        headers: { "content-type": "application/json" },
-        body: JSON.stringify({
-          target: "openai/gpt-4o",
-          key: "max_input_tokens",
-          value: 888,
-        }),
-      })
-    );
-    assert.equal(openaiPatch.status, 200);
-    const openaiGet = await overrideRoute.GET(
-      new Request("http://localhost/api/model-capability-overrides")
-    );
-    const openaiPayload = (await openaiGet.json()) as { overrides: Array<{ target: string }> };
-    assert.ok(
-      openaiPayload.overrides.some((entry) => entry.target === "openai/gpt-4o"),
-      "built-in provider target must remain openai/gpt-4o"
-    );
-  });
-});

tests/unit/ui/model-capability-overrides-tab-9557.test.tsx

@@ -1,193 +0,0 @@
-// @vitest-environment jsdom
-//
-// Issue #9557 UI regression: the Model Overrides dashboard tab must render and
-// PATCH/DELETE against the operator-configured public provider prefix
-// (e.g. `vibeproxy/gpt-4o`), never the generated `openai-compatible-chat-<uuid>`
-// node id. We mount the REAL ModelCapabilityOverridesTab and drive it through
-// its fetch-backed data hook with a stubbed `global.fetch`.
-
-import React, { act } from "react";
-import { createRoot } from "react-dom/client";
-import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-
-import ModelCapabilityOverridesTab from "@/app/(dashboard)/dashboard/settings/components/ModelCapabilityOverridesTab";
-
-const NODE_ID = "openai-compatible-chat-02669115-2545-4896-b003-cb4dac09d441";
-const NODE_PREFIX = "vibeproxy";
-
-const roots: Array<{ root: ReturnType<typeof createRoot>; el: HTMLDivElement }> = [];
-
-function render() {
-  const el = document.createElement("div");
-  document.body.appendChild(el);
-  const root = createRoot(el);
-  act(() => {
-    root.render(<ModelCapabilityOverridesTab />);
-  });
-  roots.push({ root, el });
-}
-
-function jsonResponse(body: unknown, init: { ok: boolean } = { ok: true }): Response {
-  return new Response(JSON.stringify(body), {
-    status: init.ok ? 200 : 500,
-    headers: { "content-type": "application/json" },
-  });
-}
-
-async function flush(): Promise<void> {
-  for (let i = 0; i < 8; i += 1) {
-    await Promise.resolve();
-  }
-}
-
-beforeEach(() => {
-  (
-    globalThis as typeof globalThis & { IS_REACT_ACT_ENVIRONMENT?: boolean }
-  ).IS_REACT_ACT_ENVIRONMENT = true;
-  vi.stubGlobal("fetch", vi.fn());
-});
-
-afterEach(() => {
-  for (const { root, el } of roots.splice(0)) {
-    act(() => root.unmount());
-    el.remove();
-  }
-  vi.unstubAllGlobals();
-});
-
-describe("ModelCapabilityOverridesTab (issue #9557)", () => {
-  it("renders the public prefix, never the node UUID, and PATCH/DELETE use prefix/model", async () => {
-    const catalog = {
-      [NODE_ID]: {
-        id: NODE_ID,
-        alias: NODE_ID,
-        displayPrefix: NODE_PREFIX,
-        name: "VibeProxy",
-        authType: "unknown",
-        format: "openai",
-        models: [{ id: "gpt-4o", name: "gpt-4o" }],
-      },
-    };
-    const overrides: Array<{ target: string; provider: string; key: string; value: number }> = [
-      {
-        target: `${NODE_PREFIX}/gpt-4o`,
-        provider: NODE_PREFIX,
-        key: "max_output_tokens",
-        value: 123456,
-      },
-    ];
-    const fetchMock = vi.mocked(fetch);
-    fetchMock.mockImplementation((input: any) => {
-      const url = String(input);
-      if (url.includes("/api/pricing/models")) {
-        return Promise.resolve(jsonResponse(catalog));
-      }
-      if (url.includes("/api/model-capability-overrides")) {
-        return Promise.resolve(jsonResponse({ overrides }));
-      }
-      return Promise.resolve(jsonResponse({ error: "unexpected" }, { ok: false }));
-    });
-
-    render();
-
-    // Flush the async load.
-    await act(async () => {
-      await flush();
-    });
-
-    // The target label (public prefix) must be visible.
-    const bodyText = document.body.textContent ?? "";
-    expect(bodyText).toContain(`${NODE_PREFIX}/gpt-4o`);
-    expect(bodyText).not.toContain(NODE_ID);
-
-    // The stored override value is rendered.
-    expect(bodyText).toContain("123456");
-
-    // Click the Add button to PATCH a new override on the currently-selected
-    // (prefixed) target, then assert the request body used prefix/model.
-    const addButton = Array.from(document.querySelectorAll("button")).find((b) =>
-      (b.textContent ?? "").includes("Add key value")
-    );
-    expect(addButton).toBeTruthy();
-    // Value field + Add → PATCH with a new max_input_tokens value.
-    const valueInput = document.querySelector('input[type="number"]') as HTMLInputElement;
-    expect(valueInput).toBeTruthy();
-    // Select a different key for the new override.
-    const select = document.querySelector("select") as HTMLSelectElement;
-    act(() => {
-      select.value = "max_input_tokens";
-      select.dispatchEvent(new Event("change", { bubbles: true }));
-    });
-    act(() => {
-      // React controlled inputs ignore direct `.value` writes — use the native
-      // descriptor so the onChange handler fires with the new value.
-      const setter = Object.getOwnPropertyDescriptor(HTMLInputElement.prototype, "value")?.set;
-      setter?.call(valueInput, "99999");
-      valueInput.dispatchEvent(new Event("input", { bubbles: true }));
-    });
-    await act(async () => {
-      addButton!.click();
-      await flush();
-    });
-
-    const patchCall = fetchMock.mock.calls.find(([input, init]) => {
-      const u = String(input);
-      const method = (init as RequestInit | undefined)?.method;
-      return u.includes("/api/model-capability-overrides") && method === "PATCH";
-    });
-    expect(patchCall).toBeTruthy();
-    const patchBody = JSON.parse(String(patchCall![1].body)) as { target: string };
-    expect(patchBody.target).toBe(`${NODE_PREFIX}/gpt-4o`);
-    expect(patchBody.target).not.toContain(NODE_ID);
-
-    // DELETE path: the row's Remove button must send a DELETE with prefix/model.
-    // Re-mock GET to return the saved override so the row renders.
-    const withNewOverride = [
-      ...overrides,
-      {
-        target: `${NODE_PREFIX}/gpt-4o`,
-        provider: NODE_PREFIX,
-        key: "max_input_tokens",
-        value: 99999,
-      },
-    ];
-    fetchMock.mockImplementation((input: any, init: RequestInit | undefined) => {
-      const url = String(input);
-      const method = init?.method ?? "GET";
-      if (url.includes("/api/pricing/models")) return Promise.resolve(jsonResponse(catalog));
-      if (url.includes("/api/model-capability-overrides")) {
-        if (method === "PATCH")
-          return Promise.resolve(jsonResponse({ overrides: withNewOverride }));
-        if (method === "DELETE")
-          return Promise.resolve(jsonResponse({ overrides: [withNewOverride[0]] }));
-        return Promise.resolve(jsonResponse({ overrides: withNewOverride }));
-      }
-      return Promise.resolve(jsonResponse({ error: "unexpected" }, { ok: false }));
-    });
-
-    // Re-render fresh to pick up the new override list.
-    for (const { root, el } of roots.splice(0)) act(() => root.unmount());
-    render();
-    await act(async () => {
-      await flush();
-    });
-
-    const removeButtons = Array.from(document.querySelectorAll("button")).filter(
-      (b) => (b.textContent ?? "").trim() === "Remove"
-    );
-    expect(removeButtons.length).toBeGreaterThan(0);
-    await act(async () => {
-      removeButtons[0].click();
-      await flush();
-    });
-
-    const deleteCall = fetchMock.mock.calls.find(([input, init]) => {
-      const method = (init as RequestInit | undefined)?.method;
-      return method === "DELETE";
-    });
-    expect(deleteCall).toBeTruthy();
-    const deleteUrl = String(deleteCall![0]);
-    expect(deleteUrl).toContain(`target=${encodeURIComponent(`${NODE_PREFIX}/gpt-4o`)}`);
-    expect(deleteUrl).not.toContain(NODE_ID);
-  });
-});