fix(sse): clamp Azure gpt-4o-mini completion tokens to its 16384 ceiling

Azure gpt-4o-mini deployments accept at most 16384 completion tokens and 400 on anything larger: max_tokens is too large: 32000. This model supports at most 16384 completion tokens, whereas you provided 32000. The 32000 is OmniRoute's own doing: adjustMaxTokens raises any smaller max_tokens to DEFAULT_MIN_TOKENS (32000) whenever tools are present, to avoid truncated tool arguments. That floor has no upper bound, so an agentic client asking for far less still trips the model ceiling on its first turn. Add scoped maxOutputCap rules in paramSupport.ts for both Azure wire paths. PROVIDER_MAX_TOKENS is the wrong lever here - it is provider-wide, and the same Azure resource also serves GPT-5 deployments with a much higher ceiling. Regression guard: tests/unit/azure-max-output-clamp.test.ts, which also pins that the clamp does not leak to gpt-5.1 or to gpt-4o-mini on other providers.
fix(sse): apply Azure request-param rules on the azure-ai wire path
2026-08-10 01:02:14 +03:00 · 2026-08-09 01:35:14 -03:00 · 2026-08-09 01:35:14 -03:00 · 2026-08-09 01:09:01 -03:00 · 2026-08-09 00:21:52 -03:00 · 2026-08-09 00:06:06 -03:00
21 changed files with 1837 additions and 1021 deletions
--- a/config/quality/file-size-baseline.json
+++ b/config/quality/file-size-baseline.json
@@ -1,4 +1,5 @@
 {
+  "_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).",
@@ -387,7 +388,7 @@
    "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": 1590,
+    "src/app/api/v1/models/catalog.ts": 1597,
    "src/lib/db/apiKeys.ts": 1529,
    "src/lib/db/core.ts": 1639,
    "src/lib/db/migrationRunner.ts": 1094,
@@ -536,7 +537,7 @@
  "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": "1590",
+  "src/app/api/v1/models/catalog.ts": "1597",
  "src/lib/tokenHealthCheck.ts": "1053",
  "src/lib/db/apiKeys.ts": "1529",
  "src/lib/db/core.ts": "1639",
--- a/open-sse/config/imageRegistry.ts
+++ b/open-sse/config/imageRegistry.ts
@@ -12,6 +12,10 @@ 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;
@@ -22,6 +26,8 @@ interface ImageModelEntry {
  imageRequired?: boolean;
  description?: string;
  isMarket?: boolean;
+  supportedSizes?: string[];
+  mediaCapabilities?: Record<string, unknown>;
 }

 interface ImageProviderConfig {
@@ -35,6 +41,7 @@ interface ImageProviderConfig {
  authHeader: string;
  format: string;
  models: ImageModelEntry[];
+  routingAliases?: readonly string[];
  supportedSizes: string[];
 }

@@ -46,6 +53,7 @@ interface ImageModelAliasEntry {
  inputModalities?: string[];
  imageRequired?: boolean;
  description?: string;
+  mediaCapabilities?: Record<string, unknown>;
 }

 interface ImageCatalogModelEntry {
@@ -55,6 +63,7 @@ interface ImageCatalogModelEntry {
  supportedSizes: string[];
  inputModalities: string[];
  description?: string;
+  mediaCapabilities?: Record<string, unknown>;
 }

 const IMAGE_MODEL_ALIASES: Record<string, ImageModelAliasEntry> = {
@@ -678,55 +687,9 @@ export const IMAGE_PROVIDERS: Record<string, ImageProviderConfig> = {
    authType: "apikey",
    authHeader: "bearer",
    format: "adobe-firefly-image",
-    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"],
+    models: toRegistryImageModels(),
+    routingAliases: ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
+    supportedSizes: [],
  },

  // Cheaper Inference (OSS-sponsor gateway). Declared AFTER adobe-firefly on
@@ -887,7 +850,7 @@ 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.models.some((m) => m.id === modelStr)) {
+    if (config.routingAliases?.includes(modelStr) || config.models.some((m) => m.id === modelStr)) {
      return { provider: providerId, model: modelStr };
    }
  }
@@ -906,9 +869,10 @@ function imageProviderCatalogEntries(
    id: `${providerId}/${model.id}`,
    name: model.name,
    provider: providerId,
-    supportedSizes: config.supportedSizes,
+    supportedSizes: model.supportedSizes || config.supportedSizes,
    inputModalities: model.inputModalities || ["text"],
    description: model.description || undefined,
+    mediaCapabilities: model.mediaCapabilities,
  }));
 }

--- a/open-sse/config/videoRegistry.ts
+++ b/open-sse/config/videoRegistry.ts
@@ -5,14 +5,17 @@
 * Supports local providers plus hosted task-based APIs such as Runway.
 */

-import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
+import { parseModelFromRegistry } 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 {
@@ -326,8 +329,7 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
  },

  // Adobe Firefly (unofficial) — same IMS/cookie credential as the image entry.
-  // Async 3P video generate + poll (Sora 2, Veo 3.1, Kling …). Fallback list
-  // from models/discovery capture (adobe/get_models.txt).
+  // Exact async video models and capabilities from the verified discovery snapshot.
  "adobe-firefly": {
    id: "adobe-firefly",
    alias: "firefly",
@@ -335,18 +337,7 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
    authType: "apikey",
    authHeader: "bearer",
    format: "adobe-firefly-video",
-    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" },
-    ],
+    models: toRegistryVideoModels(),
  },
 };

@@ -368,5 +359,17 @@ export function parseVideoModel(modelStr: string | null) {
 * Get all video models as a flat list
 */
 export function getAllVideoModels() {
-  return getAllModelsFromRegistry(VIDEO_PROVIDERS);
+  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,
+        }))
+      )
+  );
 }
--- a/open-sse/executors/azure-ai.ts
+++ b/open-sse/executors/azure-ai.ts
@@ -0,0 +1,35 @@
+import { DefaultExecutor } from "./default.ts";
+import type { ProviderCredentials } from "./base.ts";
+import { applyAzureParamRules } from "./azureParamRules.ts";
+
+/**
+ * Azure AI Foundry (`azure-ai`).
+ *
+ * URL building, auth headers and the `responses` vs `chat` apiType switch all
+ * live in `DefaultExecutor`, keyed on the `azure-ai` provider id — this subclass
+ * inherits them unchanged and adds only the Azure request-param rules.
+ *
+ * Before this existed, `azure-ai` fell through to the bare `DefaultExecutor`
+ * while `azure-openai` had the rules inline, so the same Azure deployment
+ * behaved differently depending on which connection served it: `azure-openai`
+ * succeeded and `azure-ai` returned HTTP 400 for `max_tokens` /
+ * `reasoning_effort`.
+ */
+export class AzureAiExecutor extends DefaultExecutor {
+  constructor() {
+    super("azure-ai");
+  }
+
+  override transformRequest(
+    model: string,
+    body: unknown,
+    stream: boolean,
+    credentials: ProviderCredentials
+  ): unknown {
+    return applyAzureParamRules(
+      model,
+      body,
+      super.transformRequest(model, body, stream, credentials)
+    );
+  }
+}
--- a/open-sse/executors/azure-openai.ts
+++ b/open-sse/executors/azure-openai.ts
@@ -1,9 +1,9 @@
 import { DefaultExecutor } from "./default.ts";
 import type { ProviderCredentials } from "./base.ts";
 import { stripTrailingSlashes } from "../utils/urlSanitize.ts";
+import { applyAzureParamRules } from "./azureParamRules.ts";

 const DEFAULT_API_VERSION = "2024-12-01-preview";
-const GPT5_OR_REASONING_DEPLOYMENT = /(?:^|[/_-])(?:gpt-5|o(?:1|3|4))(?:[._-]|$)/i;

 function normalizeAzureBaseUrl(rawBaseUrl?: string | null): string {
  const normalized = stripTrailingSlashes((rawBaseUrl || "").trim());
@@ -57,37 +57,10 @@ export class AzureOpenAIExecutor extends DefaultExecutor {
    stream: boolean,
    credentials: ProviderCredentials
  ): unknown {
-    const transformed = super.transformRequest(model, body, stream, credentials);
-    if (!GPT5_OR_REASONING_DEPLOYMENT.test(model)) return transformed;
-    if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
-      return transformed;
-    }
-
-    const original =
-      body && typeof body === "object" && !Array.isArray(body)
-        ? (body as Record<string, unknown>)
-        : null;
-    const normalized = { ...(transformed as Record<string, unknown>) };
-
-    if (original?.max_completion_tokens !== undefined) {
-      normalized.max_completion_tokens = original.max_completion_tokens;
-    } else if (
-      normalized.max_completion_tokens === undefined &&
-      original?.max_tokens !== undefined
-    ) {
-      normalized.max_completion_tokens = original.max_tokens;
-    }
-    delete normalized.max_tokens;
-
-    if (normalized.temperature !== undefined && normalized.temperature !== 1) {
-      delete normalized.temperature;
-    }
-
-    const hasTools = Array.isArray(normalized.tools) && normalized.tools.length > 0;
-    if (hasTools || normalized.reasoning_effort === "none") {
-      delete normalized.reasoning_effort;
-    }
-
-    return normalized;
+    return applyAzureParamRules(
+      model,
+      body,
+      super.transformRequest(model, body, stream, credentials)
+    );
  }
 }
--- a/open-sse/executors/azureParamRules.ts
+++ b/open-sse/executors/azureParamRules.ts
@@ -0,0 +1,76 @@
+/**
+ * Azure Chat Completions param rules, shared by every Azure wire path.
+ *
+ * Azure's newer deployments reject a handful of stock OpenAI Chat Completions
+ * params and return HTTP 400 rather than ignoring them:
+ *
+ *   - `max_tokens`      -> "Unsupported parameter: 'max_tokens' is not supported
+ *                          with this model. Use 'max_completion_tokens' instead."
+ *   - `temperature`     -> only the default (1) is accepted.
+ *   - `reasoning_effort` -> "Function tools with reasoning_effort are not
+ *                          supported ... Please use /v1/responses instead."
+ *
+ * This logic previously lived inline in `AzureOpenAIExecutor`, so it only
+ * covered the `azure-openai` provider. `azure-ai` (Azure AI Foundry) routes
+ * through `DefaultExecutor` and inherited none of it, which meant an identical
+ * deployment 400'd on one connection and succeeded on the other. Extracted here
+ * so both executors apply exactly the same rules.
+ */
+
+/**
+ * Deployments that require `max_completion_tokens` instead of `max_tokens`.
+ *
+ * Matches the GPT-5 family and the o1/o3/o4 reasoning series at a token
+ * boundary, so a deployment named `my-gpt-5-prod` matches while an unrelated
+ * `piston-o4-legacy`-style name does not match by accident. `gpt-chat-latest`
+ * is listed explicitly: it is a moving alias that currently resolves to a
+ * GPT-5-era model and rejects `max_tokens`, but carries no version number for
+ * the boundary pattern to key on.
+ */
+export const AZURE_COMPLETION_TOKEN_DEPLOYMENT =
+  /(?:^|[/_-])(?:gpt-5|o(?:1|3|4))(?:[._-]|$)|^gpt-chat-latest$/i;
+
+/**
+ * Apply the Azure param rules to an already-translated Chat Completions body.
+ *
+ * `originalBody` is the pre-translation request, consulted only to recover a
+ * caller-supplied token budget that translation may have moved or dropped.
+ * Returns `transformed` untouched when the deployment is unaffected or the body
+ * is not a plain object, and never mutates either input.
+ */
+export function applyAzureParamRules(
+  model: string,
+  originalBody: unknown,
+  transformed: unknown
+): unknown {
+  if (!AZURE_COMPLETION_TOKEN_DEPLOYMENT.test(model)) return transformed;
+  if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
+    return transformed;
+  }
+
+  const original =
+    originalBody && typeof originalBody === "object" && !Array.isArray(originalBody)
+      ? (originalBody as Record<string, unknown>)
+      : null;
+  const normalized = { ...(transformed as Record<string, unknown>) };
+
+  if (original?.max_completion_tokens !== undefined) {
+    normalized.max_completion_tokens = original.max_completion_tokens;
+  } else if (normalized.max_completion_tokens === undefined && original?.max_tokens !== undefined) {
+    normalized.max_completion_tokens = original.max_tokens;
+  }
+  delete normalized.max_tokens;
+
+  if (normalized.temperature !== undefined && normalized.temperature !== 1) {
+    delete normalized.temperature;
+  }
+
+  // Azure 400s on reasoning_effort as soon as tools are present, which is every
+  // agentic client (Claude Code, Cursor agent) on every turn.
+  const hasTools = Array.isArray(normalized.tools) && normalized.tools.length > 0;
+  if (hasTools || normalized.reasoning_effort === "none") {
+    delete normalized.reasoning_effort;
+  }
+
+  return normalized;
+}
--- a/open-sse/executors/index.ts
+++ b/open-sse/executors/index.ts
@@ -25,6 +25,7 @@ import { ChatGptWebExecutor } from "./chatgpt-web.ts";
 import { BlackboxWebExecutor } from "./blackbox-web.ts";
 import { MuseSparkWebExecutor } from "./muse-spark-web.ts";
 import { AzureOpenAIExecutor } from "./azure-openai.ts";
+import { AzureAiExecutor } from "./azure-ai.ts";
 import { CommandCodeExecutor } from "./commandCode.ts";
 import { GitlabExecutor } from "./gitlab.ts";
 import { NlpCloudExecutor } from "./nlpcloud.ts";
@@ -89,6 +90,7 @@ const executors = {
  glmt: new GlmExecutor("glmt"),
  cu: new CursorExecutor(), // Alias for cursor
  "azure-openai": new AzureOpenAIExecutor(),
+  "azure-ai": new AzureAiExecutor(),
  "command-code": new CommandCodeExecutor(),
  cmd: new CommandCodeExecutor(), // Alias
  gitlab: new GitlabExecutor(),
@@ -263,6 +265,7 @@ export { ChatGptWebExecutor } from "./chatgpt-web.ts";
 export { BlackboxWebExecutor } from "./blackbox-web.ts";
 export { MuseSparkWebExecutor } from "./muse-spark-web.ts";
 export { AzureOpenAIExecutor } from "./azure-openai.ts";
+export { AzureAiExecutor } from "./azure-ai.ts";
 export { CommandCodeExecutor } from "./commandCode.ts";
 export { GitlabExecutor } from "./gitlab.ts";
 export { NlpCloudExecutor } from "./nlpcloud.ts";
--- a/open-sse/handlers/imageGeneration/providers/adobeFirefly.ts
+++ b/open-sse/handlers/imageGeneration/providers/adobeFirefly.ts
@@ -16,11 +16,11 @@ import {
  AdobeFireflyError,
  adobeFireflyGenerateImage,
  adobeFireflyImageTimeoutMs,
-  adobeFireflyMaxImageRefs,
  resolveAdobeAccessToken,
-  resolveAdobeSourceImageIds,
+  resolveAdobeSourceImageReferences,
  resolveAdobeImageModel,
 } from "../../../services/adobeFireflyClient.ts";
+import { getAdobeReferenceUploadLimit } from "../../../services/adobeFireflyModels.ts";
 import { isAdobeFireflyUpscaleModel } from "../../../services/adobeFireflyUpscale.ts";
 import { handleAdobeFireflyImageUpscale } from "../../imageUpscale/adobeFirefly.ts";

@@ -90,7 +90,8 @@ 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()) ||
@@ -98,15 +99,11 @@ export async function handleAdobeFireflyImageGeneration({
        ? credentials.accessToken
        : undefined);

-    // 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({
+    const { spec } = resolveAdobeImageModel(model);
+    const references = await resolveAdobeSourceImageReferences({
      accessToken,
      body,
-      max: maxRefs,
+      max: getAdobeReferenceUploadLimit(spec, "image"),
      sessionCookie,
      prompt,
      fetchImpl,
@@ -121,13 +118,13 @@ export async function handleAdobeFireflyImageGeneration({
          : undefined;
    const timeoutMs = adobeFireflyImageTimeoutMs({
      timeoutMs: explicitTimeout,
-      refCount: sourceImageIds.length,
+      refCount: references.length,
    });

    log?.info?.(
      "IMAGE",
      `${provider}/${model} (adobe-firefly) | prompt: "${prompt.slice(0, 60)}${prompt.length > 60 ? "..." : ""}"` +
-        (sourceImageIds.length ? ` | refs: ${sourceImageIds.length}/${maxRefs}` : "") +
+        (references.length ? ` | refs: ${references.length}` : "") +
        ` | pollTimeoutMs=${timeoutMs}`
    );

@@ -139,9 +136,8 @@ 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,
-      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
+      negativePrompt: typeof body.negative_prompt === "string" ? body.negative_prompt : undefined,
+      references: references.length ? references : undefined,
      sessionCookie,
      timeoutMs,
      fetchImpl,
--- a/open-sse/handlers/videoGeneration/adobeFireflyHandler.ts
+++ b/open-sse/handlers/videoGeneration/adobeFireflyHandler.ts
@@ -10,9 +10,10 @@ import {
  AdobeFireflyError,
  adobeFireflyGenerateVideo,
  resolveAdobeAccessToken,
-  resolveAdobeSourceImageIds,
+  resolveAdobeSourceImageReferences,
  resolveAdobeVideoModel,
 } from "../../services/adobeFireflyClient.ts";
+import { getAdobeReferenceUploadLimit } from "../../services/adobeFireflyModels.ts";

 function normalizePositiveNumber(value: unknown, fallback: number): number {
  const n = Number(value);
@@ -55,7 +56,8 @@ 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()) ||
@@ -63,13 +65,11 @@ export async function handleAdobeFireflyVideoGeneration({
        ? credentials.accessToken
        : undefined);

-    // 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({
+    const { spec } = resolveAdobeVideoModel(String(model));
+    const references = await resolveAdobeSourceImageReferences({
      accessToken,
      body,
-      max: maxFrames,
+      max: getAdobeReferenceUploadLimit(spec, "image"),
      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 ? "..." : ""}"` +
-        (sourceImageIds.length ? ` | frames: ${sourceImageIds.length}` : "")
+        (references.length ? ` | refs: ${references.length}` : "")
    );

    const result = await adobeFireflyGenerateVideo({
@@ -99,7 +99,7 @@ export async function handleAdobeFireflyVideoGeneration({
            ? body.negativePrompt
            : undefined,
      generateAudio: body.generate_audio !== false && body.generateAudio !== false,
-      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
+      references: references.length ? references : undefined,
      sessionCookie,
      timeoutMs,
      fetchImpl,
--- a/open-sse/services/adobeFireflyClient.ts
+++ b/open-sse/services/adobeFireflyClient.ts
--- a/open-sse/services/adobeFireflyModelSnapshot.ts
+++ b/open-sse/services/adobeFireflyModelSnapshot.ts
--- a/open-sse/services/adobeFireflyModels.ts
+++ b/open-sse/services/adobeFireflyModels.ts
@@ -1,328 +1,590 @@
 /**
- * Adobe Firefly model catalog: live discovery + static fallback from browser capture.
+ * Adobe Firefly model discovery and normalized media capabilities.
 *
- * 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.
+ * The live discovery schema is authoritative. The generated snapshot is used only
+ * when a request cannot perform authenticated discovery (for example /v1/models).
 */

-import {
-  type AdobeFireflyDiscoveredModel,
-  discoverAdobeFireflyModels,
-  resolveAdobeAccessToken,
-} from "./adobeFireflyClient.ts";
+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;
+}

 export interface AdobeFireflyCatalogModel {
-  /** OpenAI-style id without provider prefix, e.g. nano-banana-pro or flux-fluxPro */
+  /** Stable API id without the provider prefix. */
  id: string;
  name: string;
  modality: "image" | "video";
-  /** Upstream wire modelId for generate-async */
  upstreamModelId: string;
-  /** Upstream wire modelVersion for generate-async */
  upstreamModelVersion: string;
-  inputModalities?: string[];
+  providerName: string;
+  backingModel: string;
+  inputModalities: string[];
+  capabilities: AdobeFireflyMediaCapabilities;
 }

-/**
- * 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 AdobeFireflyImageModelSpec extends AdobeFireflyCatalogModel {
+  modality: "image";
+  /** Payload dialect observed for this model family. */
+  family: "gemini" | "gpt-image" | "generic";
+}

-/** Stable slug for upstream modelId + modelVersion (catalog id when not a friendly alias). */
+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. */
 export function slugifyAdobeModel(modelId: string, modelVersion: string): string {
-  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}`;
+  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}`;
 }

-/** Map discovery rows → catalog entries (image/video only). */
-export function mapDiscoveredToCatalog(
-  rows: AdobeFireflyDiscoveredModel[]
-): AdobeFireflyCatalogModel[] {
-  const out: AdobeFireflyCatalogModel[] = [];
-  const seen = new Set<string>();
+/** 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[] = [];

-  // 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,
+  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,
      });
    }
  }

-  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
+  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))
      )
-    ) {
-      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 out;
-}
-
-export function getAdobeFireflyFallbackCatalog(modality?: "image" | "video"): AdobeFireflyCatalogModel[] {
-  if (!modality) return [...ADOBE_FIREFLY_FALLBACK_MODELS];
-  return ADOBE_FIREFLY_FALLBACK_MODELS.filter((m) => m.modality === modality);
-}
-
-/**
- * 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
-  }
+    ),
+  ];
+  const duration = integerBranch(schema.properties.duration);
+  const outputCount = integerBranch(schema.properties.n);
+  const prompt =
+    schemaBranches(schema.properties.prompt).find((branch) => branch.type === "string") || {};

  return {
-    models: getAdobeFireflyFallbackCatalog(opts.modality),
-    source: "fallback",
+    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 || "",
  };
 }

-/** 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"],
-    }));
+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()));
 }

-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}`,
-    }));
+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. */
+export function mapDiscoveredToCatalog(
+  rows: AdobeFireflyDiscoveredModel[]
+): AdobeFireflyCatalogModel[] {
+  const output: 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)"}`
+    );
+  }
+  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)"}`
+    );
+  }
+  return { id, spec };
+}
+
+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 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),
+  }));
+}
+
+/** 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,
+  };
+}
+
+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));
 }
--- a/open-sse/translator/paramSupport.ts
+++ b/open-sse/translator/paramSupport.ts
@@ -63,7 +63,12 @@ const STRIP_RULES: StripRule[] = [
  // MoonshotAI/kimi-cli#1124), and by upstream decolua/9router#2460. Scoped to
  // OmniRoute's actual volcengine Kimi id (not a broad /kimi/i regex) so it
  // never clamps an unrelated future Kimi listing whose Ark cap may differ.
-  { provider: "volcengine", match: /^kimi-k2-5-260127$/, maxOutputCap: 32768, clampToModelMaxOutput: true },
+  {
+    provider: "volcengine",
+    match: /^kimi-k2-5-260127$/,
+    maxOutputCap: 32768,
+    clampToModelMaxOutput: true,
+  },
  // #7364: Z.AI's glm-4.6v vision endpoint enforces a 32768 max_tokens ceiling
  // server-side and 400s when a client sends a larger explicit max_tokens (e.g. a
  // client defaulting to 65536). Scoped to both wire paths that can reach this
@@ -75,6 +80,19 @@ const STRIP_RULES: StripRule[] = [
  // glmProvider.ts, maxOutputTokens: 32768, so clampToModelMaxOutput suffices).
  { provider: "zai", match: /^glm-4\.6v$/i, maxOutputCap: 32768 },
  { provider: "glm", match: /^glm-4\.6v$/i, clampToModelMaxOutput: true },
+  // Azure gpt-4o-mini deployments cap completion tokens at 16384 and 400 on
+  // anything larger: "max_tokens is too large: 32000. This model supports at
+  // most 16384 completion tokens". OmniRoute's own tool-calling floor
+  // (DEFAULT_MIN_TOKENS = 32000, applied by adjustMaxTokens) raises even a tiny
+  // explicit max_tokens to 32000 whenever tools are present, so every agentic
+  // client trips this on its first turn. PROVIDER_MAX_TOKENS is not the right
+  // lever here: it is provider-wide, and the same Azure resource also serves
+  // GPT-5 deployments whose ceiling is far higher. Azure deployment names are
+  // operator-chosen, hence a prefix match rather than an exact id, and the
+  // models are passthrough (no catalog maxOutputTokens for clampToModelMaxOutput
+  // to read), hence the fixed cap.
+  { provider: "azure-openai", match: /^gpt-4o-mini/i, maxOutputCap: 16384 },
+  { provider: "azure-ai", match: /^gpt-4o-mini/i, maxOutputCap: 16384 },
 ];

 function matches(rule: StripRule, model: string): boolean {
--- a/scripts/dev/generate-adobe-firefly-snapshot.mjs
+++ b/scripts/dev/generate-adobe-firefly-snapshot.mjs
@@ -0,0 +1,207 @@
+#!/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}`);
--- a/src/app/api/providers/[id]/models/adobeFireflyDiscovery.ts
+++ b/src/app/api/providers/[id]/models/adobeFireflyDiscovery.ts
@@ -0,0 +1,73 @@
+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)
+      )}`
+    );
+  }
+}
--- a/src/app/api/providers/[id]/models/route.ts
+++ b/src/app/api/providers/[id]/models/route.ts
@@ -84,10 +84,8 @@ import {
  isAutoFetchModelsEnabled,
  persistDiscoveredModels,
 } from "@/lib/providerModels/modelDiscovery";
-import {
-  buildProviderModelsUrl,
-  getDiscoveryClientVersionOptions,
-} from "./discoveryClientVersion";
+import { buildProviderModelsUrl, getDiscoveryClientVersionOptions } from "./discoveryClientVersion";
+import { getAdobeModels } from "./adobeFireflyDiscovery";
 import {
  parseGeminiModelsList,
  type GeminiDiscoveryModel,
@@ -422,10 +420,7 @@ 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
-      // 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).
+      // Redirect blocks degrade to the local/cached catalog; invalid URLs remain hard errors.
      if (error instanceof SafeOutboundFetchError && error.code === "REDIRECT_BLOCKED") {
        return buildDiscoveryFallbackResponse(warnings);
      }
@@ -434,6 +429,11 @@ 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();
--- a/src/app/api/v1/models/catalog.ts
+++ b/src/app/api/v1/models/catalog.ts
@@ -1113,6 +1113,7 @@ async function buildUnifiedModelsResponseCore(
        input_modalities: imgModel.inputModalities || ["text"],
        output_modalities: ["image"],
        ...(imgModel.description ? { description: imgModel.description } : {}),
+        ...(imgModel.mediaCapabilities ? { media_capabilities: imgModel.mediaCapabilities } : {}),
      });
    }

@@ -1178,6 +1179,12 @@ 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 }
+          : {}),
      });
    }

--- a/tests/unit/adobe-firefly-references.test.ts
+++ b/tests/unit/adobe-firefly-references.test.ts
@@ -0,0 +1,90 @@
+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/);
+});
--- a/tests/unit/adobe-firefly.test.ts
+++ b/tests/unit/adobe-firefly.test.ts
@@ -78,6 +78,11 @@ 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", () => {
@@ -154,20 +159,25 @@ test("normalizeAdobeOutputResolution maps quality tiers", () => {
  assert.equal(normalizeAdobeOutputResolution(undefined, undefined), "2K");
 });

-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");
+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/
+  );
  assert.ok(ADOBE_FIREFLY_IMAGE_MODELS["nano-banana-pro"].upstreamModelVersion);
 });

-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("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("buildAdobeImagePayload produces nano and gpt-image shapes", () => {
@@ -265,41 +275,12 @@ 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: "subject" },
+    { id: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee", usage: "source" },
  ]);
  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("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);
-
+test("adobeFireflyImageTimeoutMs scales boundedly with reference count", () => {
  assert.equal(adobeFireflyImageTimeoutMs({ refCount: 0 }), DEFAULT_IMAGE_TIMEOUT_MS);
  assert.equal(
    adobeFireflyImageTimeoutMs({ refCount: 2 }),
@@ -381,16 +362,7 @@ test("resolveAdobeSourceImageIds uploads data URLs then returns blob ids", async
  assert.equal(ADOBE_FIREFLY_IMAGE_UPLOAD_URL.includes("storage/image"), true);
 });

-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);
-
+test("buildAdobeVideoPayload follows discovered fields and reference roles", () => {
  const veo = buildAdobeVideoPayload({
    prompt: "city flyover",
    aspectRatio: "9:16",
@@ -399,12 +371,30 @@ test("buildAdobeVideoPayload produces sora and veo shapes", () => {
  });
  assert.equal(veo.modelId, "veo");
  assert.equal(veo.modelVersion, "3.1-generate");
-  assert.equal(
-    (veo.modelSpecificPayload as Record<string, Record<string, unknown>>).parameters
-      .durationSeconds,
-    6
-  );
+  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/
+  );
 });

 test("extractAdobeResultLink prefers x-override-status-link then links.result", () => {
@@ -539,7 +529,7 @@ test("adobe-firefly is in USAGE_SUPPORTED_PROVIDERS for Limits", () => {
  assert.ok(USAGE_SUPPORTED_PROVIDERS.includes("firefly"));
 });

-test("parseAdobeModelsDiscovery extracts image/video versions", () => {
+test("parseAdobeModelsDiscovery preserves schemas and maps exact ids", () => {
  const rows = parseAdobeModelsDiscovery({
    models: [
      {
@@ -550,16 +540,44 @@ test("parseAdobeModelsDiscovery extracts image/video versions", () => {
            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: "sora",
+        modelId: "veo",
        modelVersions: {
-          "sora-2": {
+          "3.1-generate": {
            enabled: true,
            outputModality: ["video"],
-            modelDisplayName: "Sora 2",
+            modelDisplayName: "Veo 3.1",
+            requestSchema: {
+              allOf: [
+                {
+                  properties: {
+                    prompt: { type: "string" },
+                    duration: { anyOf: [{ type: "integer", enum: [4, 6, 8] }] },
+                  },
+                },
+              ],
+            },
          },
        },
      },
@@ -569,14 +587,35 @@ test("parseAdobeModelsDiscovery extracts image/video versions", () => {
  assert.equal(rows[0].modality, "image");
  assert.equal(rows[1].modality, "video");
  const catalog = mapDiscoveredToCatalog(rows);
-  assert.ok(catalog.some((m) => m.id === "nano-banana-pro"));
-  assert.ok(catalog.some((m) => m.id === "sora-2"));
+  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]);
 });

-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("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("extractAdobeAccountIdFromToken reads user_id claim", () => {
@@ -716,7 +755,7 @@ test("adobeFireflyGenerateVideo submit+poll happy path (mocked)", async () => {
  const result = await adobeFireflyGenerateVideo({
    accessToken: "tok",
    prompt: "drone over forest",
-    model: "sora-2",
+    model: "veo-3.1",
    duration: 4,
    aspectRatio: "16:9",
    fetchImpl: fetchImpl as typeof fetch,
@@ -727,7 +766,7 @@ test("adobeFireflyGenerateVideo submit+poll happy path (mocked)", async () => {

 test("handleAdobeFireflyVideoGeneration returns 400 without prompt", async () => {
  const result = await handleAdobeFireflyVideoGeneration({
-    model: "sora-2",
+    model: "veo-3.1",
    provider: "adobe-firefly",
    body: {},
    credentials: { apiKey: "aaa.bbb.ccc" },
--- a/tests/unit/azure-max-output-clamp.test.ts
+++ b/tests/unit/azure-max-output-clamp.test.ts
@@ -0,0 +1,58 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import { stripUnsupportedParams } from "../../open-sse/translator/paramSupport.ts";
+
+/**
+ * Regression guard for the Azure gpt-4o-mini completion-token ceiling.
+ *
+ * Observed against a live Azure deployment:
+ *   azure-openai/gpt-4o-mini-dz
+ *     -> 400 "max_tokens is too large: 32000. This model supports at most
+ *            16384 completion tokens, whereas you provided 32000."
+ *
+ * The 32000 is OmniRoute's own doing: `adjustMaxTokens` raises any smaller
+ * max_tokens to DEFAULT_MIN_TOKENS (32000) whenever tools are present, so an
+ * agentic client trips this on its first turn even when it asked for far less.
+ */
+
+test("azure gpt-4o-mini clamps max_tokens to the 16384 ceiling", () => {
+  const out = stripUnsupportedParams("azure-openai", "gpt-4o-mini-dz", {
+    max_tokens: 32000,
+    messages: [],
+  }) as Record<string, unknown>;
+
+  assert.equal(out.max_tokens, 16384);
+});
+
+test("the clamp applies on the azure-ai wire path too", () => {
+  const out = stripUnsupportedParams("azure-ai", "gpt-4o-mini", {
+    max_completion_tokens: 32000,
+  }) as Record<string, unknown>;
+
+  assert.equal(out.max_completion_tokens, 16384);
+});
+
+test("a value already under the ceiling is left alone", () => {
+  const out = stripUnsupportedParams("azure-openai", "gpt-4o-mini", {
+    max_tokens: 800,
+  }) as Record<string, unknown>;
+
+  assert.equal(out.max_tokens, 800);
+});
+
+test("the clamp is scoped — larger Azure deployments keep their budget", () => {
+  const out = stripUnsupportedParams("azure-ai", "gpt-5.1", {
+    max_tokens: 32000,
+  }) as Record<string, unknown>;
+
+  assert.equal(out.max_tokens, 32000);
+});
+
+test("the clamp does not leak to gpt-4o-mini on other providers", () => {
+  const out = stripUnsupportedParams("openai", "gpt-4o-mini", {
+    max_tokens: 32000,
+  }) as Record<string, unknown>;
+
+  assert.equal(out.max_tokens, 32000);
+});
--- a/tests/unit/azure-param-rules.test.ts
+++ b/tests/unit/azure-param-rules.test.ts
@@ -0,0 +1,96 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import {
+  applyAzureParamRules,
+  AZURE_COMPLETION_TOKEN_DEPLOYMENT,
+} from "../../open-sse/executors/azureParamRules.ts";
+import { getExecutor, AzureAiExecutor } from "../../open-sse/executors/index.ts";
+
+/**
+ * Regression guards for two Azure 400s observed against a live Azure AI Foundry
+ * resource:
+ *
+ *   azure-ai/gpt-chat-latest
+ *     -> 400 "Unsupported parameter: 'max_tokens' is not supported with this
+ *            model. Use 'max_completion_tokens' instead."
+ *   azure-ai/<any gpt-5 deployment> with tools
+ *     -> 400 "Function tools with reasoning_effort are not supported ...
+ *            Please use /v1/responses instead."
+ *
+ * Both rules already existed inline in AzureOpenAIExecutor, so the identical
+ * deployment succeeded on the `azure-openai` connection and failed on
+ * `azure-ai`, which routed through the bare DefaultExecutor.
+ */
+
+test("gpt-chat-latest converts max_tokens to max_completion_tokens", () => {
+  const out = applyAzureParamRules(
+    "gpt-chat-latest",
+    { max_tokens: 4096 },
+    { max_tokens: 4096, messages: [] }
+  ) as Record<string, unknown>;
+
+  assert.equal(out.max_tokens, undefined);
+  assert.equal(out.max_completion_tokens, 4096);
+});
+
+test("gpt-5 family converts max_tokens too", () => {
+  for (const model of ["gpt-5.1", "gpt-5.4-nano", "my-gpt-5-prod", "o3", "o4-mini"]) {
+    const out = applyAzureParamRules(model, { max_tokens: 100 }, { max_tokens: 100 }) as Record<
+      string,
+      unknown
+    >;
+    assert.equal(out.max_tokens, undefined, `${model} should drop max_tokens`);
+    assert.equal(out.max_completion_tokens, 100, `${model} should set max_completion_tokens`);
+  }
+});
+
+test("reasoning_effort is dropped when tools are present", () => {
+  const out = applyAzureParamRules(
+    "gpt-5.1",
+    {},
+    { reasoning_effort: "high", tools: [{ name: "read_file" }] }
+  ) as Record<string, unknown>;
+
+  assert.equal(out.reasoning_effort, undefined);
+  assert.equal((out.tools as unknown[]).length, 1);
+});
+
+test("reasoning_effort survives when there are no tools", () => {
+  const out = applyAzureParamRules("gpt-5.1", {}, { reasoning_effort: "high" }) as Record<
+    string,
+    unknown
+  >;
+  assert.equal(out.reasoning_effort, "high");
+});
+
+test("non-default temperature is dropped, temperature=1 kept", () => {
+  const dropped = applyAzureParamRules("gpt-5.1", {}, { temperature: 0.7 }) as Record<
+    string,
+    unknown
+  >;
+  assert.equal(dropped.temperature, undefined);
+
+  const kept = applyAzureParamRules("gpt-5.1", {}, { temperature: 1 }) as Record<string, unknown>;
+  assert.equal(kept.temperature, 1);
+});
+
+test("unaffected deployments pass through untouched", () => {
+  const body = { max_tokens: 500, temperature: 0.2, reasoning_effort: "low" };
+  const out = applyAzureParamRules("Phi-4", {}, body);
+  assert.deepEqual(out, body);
+});
+
+test("the regex does not match unrelated names by accident", () => {
+  assert.equal(AZURE_COMPLETION_TOKEN_DEPLOYMENT.test("gpt-4o-mini"), false);
+  assert.equal(AZURE_COMPLETION_TOKEN_DEPLOYMENT.test("DeepSeek-V4-Flash"), false);
+  assert.equal(AZURE_COMPLETION_TOKEN_DEPLOYMENT.test("Kimi-K2.7-Code"), false);
+});
+
+test("azure-ai resolves to AzureAiExecutor, not the bare DefaultExecutor", () => {
+  const executor = getExecutor("azure-ai");
+  assert.ok(
+    executor instanceof AzureAiExecutor,
+    "azure-ai must have its own executor so it inherits the Azure param rules"
+  );
+});
Author	SHA1	Message	Date
Mihaly Bodo	06541b1036	fix(sse): clamp Azure gpt-4o-mini completion tokens to its 16384 ceiling Azure gpt-4o-mini deployments accept at most 16384 completion tokens and 400 on anything larger: max_tokens is too large: 32000. This model supports at most 16384 completion tokens, whereas you provided 32000. The 32000 is OmniRoute's own doing: adjustMaxTokens raises any smaller max_tokens to DEFAULT_MIN_TOKENS (32000) whenever tools are present, to avoid truncated tool arguments. That floor has no upper bound, so an agentic client asking for far less still trips the model ceiling on its first turn. Add scoped maxOutputCap rules in paramSupport.ts for both Azure wire paths. PROVIDER_MAX_TOKENS is the wrong lever here - it is provider-wide, and the same Azure resource also serves GPT-5 deployments with a much higher ceiling. Regression guard: tests/unit/azure-max-output-clamp.test.ts, which also pins that the clamp does not leak to gpt-5.1 or to gpt-4o-mini on other providers.	2026-08-09 01:35:14 -03:00
Mihaly Bodo	37129db6af	fix(sse): apply Azure request-param rules on the azure-ai wire path Azure rejects several stock Chat Completions params on its newer deployments and returns HTTP 400 rather than ignoring them: max_tokens -> 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead. reasoning_effort -> Function tools with reasoning_effort are not supported. Those rules lived inline in AzureOpenAIExecutor, so they only covered the azure-openai provider. azure-ai (Azure AI Foundry) had no executor entry and fell through to the bare DefaultExecutor, so the SAME Azure deployment succeeded on one connection and 400'd on the other. Every agentic client sends tools on every turn, so azure-ai failed on the first request. Extract the rules to open-sse/executors/azureParamRules.ts, add an AzureAiExecutor that inherits DefaultExecutor's azure-ai URL/header/apiType handling unchanged and applies the shared rules, and register it for azure-ai. Also widen the deployment pattern to cover gpt-chat-latest: it is a moving alias that resolves to a GPT-5-era model and rejects max_tokens, but carries no version number for the token-boundary pattern to key on. Verified against the base regex - gpt-chat-latest did not match, which is exactly the observed 400. Regression guard: tests/unit/azure-param-rules.test.ts, including an assertion that getExecutor("azure-ai") no longer resolves to a bare DefaultExecutor.	2026-08-09 01:35:14 -03:00
Diego Rodrigues de Sa e Souza	aae408f585	Merge pull request #9296 from artickc/fix/adobe-firefly-model-capabilities fix(adobe-firefly): sync discovered models and capabilities	2026-08-09 01:09:01 -03:00
diegosouzapw	3e1c31c606	fix(adobe-firefly): retain Topaz catalog models	2026-08-09 00:21:52 -03:00
diegosouzapw	2e12ee89f7	Merge remote-tracking branch 'origin/release/v3.8.50' into fix/merge-pr-9296 # Conflicts: # open-sse/config/imageRegistry.ts # open-sse/handlers/imageGeneration/providers/adobeFirefly.ts # open-sse/services/adobeFireflyClient.ts # tests/unit/adobe-firefly.test.ts	2026-08-09 00:06:06 -03:00
artickc	723ce0b166	fix(adobe-firefly): sync models and media capabilities	2026-08-03 17:22:08 +03:00