ai-lcr 0.5.4 → 0.5.5

package/CHANGELOG.md

@@ -4,6 +4,43 @@ All notable changes to `ai-lcr` are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project adheres to
 [Semantic Versioning](https://semver.org/).
 
+## [0.5.5] — 2026-06-06
+
+Kunavo media (image + video) verified live and properly wired. The Kunavo
+adapter previously had a working image path but an unverified, broken video
+path; this release fixes the video path against the real API and adds the
+reference-image edit endpoint. Backward compatible — `videoMode` defaults to
+the new async path, and existing image routes are unchanged.
+
+### Fixed
+
+- **Kunavo video hit the wrong endpoints.** `createKunavoMediaAdapter`'s
+  `runVideo` POSTed to the sync `POST /v1/video/generations` but then polled a
+  non-existent `GET /v1/video/generations/{id}` — unreachable dead code that
+  only ever worked through an inline early-return. Replaced with Kunavo's real,
+  live-verified endpoints (see Added). Long video SKUs no longer risk a hung,
+  timeout-less `fetch`: both video paths are now bounded.
+
+### Added
+
+- **Kunavo async video (default).** Verified live 2026-06-06: `veo-3-lite`
+  renders a real 720p mp4 via `POST /v1/videos` → poll `GET /v1/videos/{id}`
+  (~80s). This is the adapter's default and mirrors the fal submit→poll shape.
+  A poll timeout surfaces as a retryable `504` so the media router fails over.
+- **Kunavo sync video fallback.** New `KunavoMediaConfig.videoMode: "sync"`
+  uses the blocking `POST /v1/video/generations` (~108s for veo-3-lite),
+  hard-capped by `syncVideoTimeoutMs` (default 10m, remapped to a retryable
+  `504` on timeout). `pollIntervalMs` / `pollTimeoutMs` now actually drive the
+  async path.
+- **Kunavo image edit (reference image).** `*-edit` slugs
+  (`nano-banana-edit`, `gpt-image-2-edit`) route to `POST /v1/images/edits`
+  with the caller's `image` / `image_urls[]` — the character-reference path.
+- **`scripts/check-kunavo-media.sh`** — a `bash` + `curl` + `jq` live media
+  integrity probe (image gen, edit, async + sync video) mirroring the text
+  `check-provider.sh`.
+- **Test coverage for the Kunavo media adapter**, which previously shipped with
+  none (fal and Runware had tests; Kunavo did not).
+
 ## [0.5.4] — 2026-06-03
 
 ### Changed

package/README.md

@@ -232,7 +232,7 @@ Any OpenAI-compatible endpoint works — and so does any AI SDK provider package
 
 - **Model vendors' own APIs (native):** route straight to [DeepSeek](https://platform.deepseek.com), [OpenAI](https://openai.com), [Anthropic](https://anthropic.com), [Google](https://ai.google.dev), [xAI](https://x.ai), etc. via their AI SDK provider packages — no markup, full native features. See [Route to a model vendor's own API](#route-to-a-model-vendors-own-api-native-providers).
 - **Text aggregators:** [OpenRouter](https://openrouter.ai) (widest coverage, list pricing) · [Kunavo](https://kunavo.com/?ref=victorimf) (**20% off** every model) · [TokenMart](https://thetokenmart.ai) (15–65% off, varies by model)
-- **Image / video:** [Kunavo](https://kunavo.com/?ref=victorimf) (**20% off**) · [TokenMart](https://thetokenmart.ai) · [fal.ai](https://fal.ai) · [Runware](https://runware.ai) — routing via `createMediaLCR`. Image: Kunavo + Runware + fal. Video: fal (live, via its async queue API); Kunavo's Veo poll path is implemented but unverified
+- **Image / video:** [Kunavo](https://kunavo.com/?ref=victorimf) (**20% off**) · [TokenMart](https://thetokenmart.ai) · [fal.ai](https://fal.ai) · [Runware](https://runware.ai) — routing via `createMediaLCR`. Image: Kunavo (generations + `*-edit` reference-image endpoints) + Runware + fal. Video: fal (async queue) and Kunavo (async `POST /v1/videos` + poll, sync fallback) — both verified live
 
 ## Text model pricing
 
@@ -277,6 +277,8 @@ USD per image, as of 2026-05 (provider list / retail; verify current rates). Kun
 
 USD per second, as of 2026-05 — verify current rates. Video billing differs by provider, so a clean cross-provider table isn't apples-to-apples: fal.ai and Runware charge per second, while Kunavo's Veo is per clip (Fast ~$0.28 / Lite ~$0.168 / Quality ~$1.34). Below are fal.ai's per-second rates (the video workhorse in testing); a normalized fal / Runware / Kunavo comparison is a TODO.
 
+> **Kunavo video — verified live 2026-06-06.** `veo-3-lite` renders a real 720p mp4 via Kunavo's async API (`POST /v1/videos` → poll `GET /v1/videos/{id}`, ~80s) and its sync fallback (`POST /v1/video/generations`, ~108s). The `createMediaLCR` Kunavo adapter defaults to async (non-blocking, fal-isomorphic). Two caveats: per-clip prices are hand-entered (`GET /v1/models` returns no pricing), and the async queue can occasionally sit much longer than 80s — the adapter's `pollTimeoutMs` bounds it so the router can fail over.
+
 | Model | fal.ai ($/s) |
 |---|---|
 | Seedance Lite | $0.036 |
@@ -293,6 +295,8 @@ USD per second, as of 2026-05 — verify current rates. Video billing differs by
 
 A discount is worthless if the provider quietly breaks the wire protocol. `ai-lcr` ships a zero-dependency check (`scripts/check-provider.sh`, just `bash` + `curl` + `python3`) that vets the things that actually cost you money or corrupt output, **per model**:
 
+> **Media providers** have their own probe: `scripts/check-kunavo-media.sh` (`bash` + `curl` + `jq`) live-tests Kunavo's image generation, `*-edit` reference endpoint, and async + sync video — the same checks used to verify the routes above. Run it before trusting a media route in production.
+
 - **tool calling** — single call and a multi-step round-trip with `content: null` (the shape every agent loop sends)
 - **`max_tokens` honored** — caps must bound output
 - **hidden-prompt injection** — sends a neutral message; flags the provider if the model starts reacting to a system prompt it was never given
@@ -349,8 +353,8 @@ Two OpenAI-compatible providers, same probe, same day. Cells cover both families
 - [ ] Bundled price table for zero-config pricing (drop the manual `cost` numbers)
 - [ ] Provider-quirk middleware (transparently patch known per-provider request quirks, e.g. Kunavo's ignored `max_tokens`)
 - [ ] Feed probe results into routing automatically (auto-exclude a model from a provider that fails its probe)
-- [x] Image & video model routing (`createMediaLCR`) — image via Kunavo + Runware + fal; **video live via fal** (async queue API)
-- [ ] Normalized cross-provider video price comparison + verified Kunavo/Runware video adapters
+- [x] Image & video model routing (`createMediaLCR`) — image via Kunavo (incl. `*-edit`) + Runware + fal; **video live via fal and Kunavo** (both verified)
+- [ ] Normalized cross-provider video price comparison + verified Runware video adapter
 
 ## Affiliate disclosure
 

package/dist/index.cjs

@@ -909,11 +909,15 @@ var MEDIA_PRICING = {
     ]
   },
   // ── Google video (Veo) ──────────────────────────────────────
-  // ⚠️ Version/SKU mismatch across providers: Kunavo bills "veo-3" per CALL
-  // (flat fee per clip; Veo 3 generates ~8s, audio/res tier unconfirmed); fal
-  // bills "veo3.1" per SECOND. Normalized to a 5s clip the per-call price wins
-  // by a wide margin — verify the clip's duration/resolution/audio before
-  // trusting the gap. See note fields.
+  // Kunavo video VERIFIED live 2026-06-06: veo-3-lite renders via both the async
+  // path (POST /v1/videos + poll, ~80s) and the sync path (POST /v1/video/
+  // generations, ~108s), real 720p mp4 out. The adapter defaults to async.
+  // ⚠️ Two caveats remain on the PRICE gap, not the capability: (1) Version/SKU
+  // mismatch — Kunavo bills "veo-3" per CALL (flat per clip, ~8s 720p) while fal
+  // bills "veo3.1" per SECOND, so normalized to a 5s clip the per-call price wins
+  // by a wide margin; (2) /v1/models exposes NO pricing, so the per-call cents
+  // below are hand-entered — verify clip duration/resolution/audio before
+  // trusting the gap. veo-3 / veo-3-quality capability not individually rendered.
   "google/veo-3": {
     id: "google/veo-3",
     modality: "video",
@@ -926,7 +930,7 @@ var MEDIA_PRICING = {
     id: "google/veo-3-lite",
     modality: "video",
     routes: [
-      { provider: "kunavo", externalId: "veo-3-lite", pricing: { unit: "call", cents: 16 }, note: "flat per clip (SKU unverified)" },
+      { provider: "kunavo", externalId: "veo-3-lite", pricing: { unit: "call", cents: 16 }, note: "flat per clip; rendering verified 2026-06-06 (720p, async+sync); price hand-entered" },
       { provider: "fal", externalId: "fal-ai/veo3.1/lite", pricing: { unit: "second", cents: 8 }, note: "veo3.1 lite, 1080p audio-on" }
     ]
   },
@@ -946,12 +950,26 @@ function extractImageUrls(body) {
   if (!Array.isArray(data)) return [];
   return data.map((d) => d?.url).filter((u) => typeof u === "string" && u.length > 0);
 }
+function extractVideoUrls(body) {
+  const output = body.output;
+  if (output) {
+    if (Array.isArray(output.urls)) {
+      const urls = output.urls.filter((u) => typeof u === "string" && u.length > 0);
+      if (urls.length > 0) return urls;
+    }
+    if (typeof output.url === "string" && output.url.length > 0) return [output.url];
+  }
+  if (typeof body.url === "string" && body.url.length > 0) return [body.url];
+  return extractImageUrls(body);
+}
 function createKunavoMediaAdapter(config) {
   const {
     apiKey,
     baseUrl = DEFAULT_BASE,
+    videoMode = "async",
     pollIntervalMs = 5e3,
-    pollTimeoutMs = 3e5,
+    pollTimeoutMs = 6e5,
+    syncVideoTimeoutMs = 6e5,
     fetchImpl = fetch
   } = config;
   const headers = {
@@ -959,7 +977,8 @@ function createKunavoMediaAdapter(config) {
     authorization: `Bearer ${apiKey}`
   };
   async function runImage(req) {
-    const res = await fetchImpl(`${baseUrl}/v1/images/generations`, {
+    const path = /-edit$/i.test(req.externalId) ? "/v1/images/edits" : "/v1/images/generations";
+    const res = await fetchImpl(`${baseUrl}${path}`, {
       method: "POST",
       headers,
       body: JSON.stringify({ model: req.externalId, ...req.input })
@@ -967,16 +986,15 @@ function createKunavoMediaAdapter(config) {
     if (!res.ok) {
       throw new KunavoMediaError(res.status, await safeText(res));
     }
-    const body = await res.json();
-    const urls = extractImageUrls(body);
+    const urls = extractImageUrls(await res.json());
     if (urls.length === 0) {
       throw new Error(`ai-lcr: Kunavo returned no image URL for "${req.externalId}"`);
     }
     const outputs = urls.map((url) => ({ url, type: "image" }));
     return { outputs };
   }
-  async function runVideo(req) {
-    const submit = await fetchImpl(`${baseUrl}/v1/video/generations`, {
+  async function runVideoAsync(req) {
+    const submit = await fetchImpl(`${baseUrl}/v1/videos`, {
       method: "POST",
       headers,
       body: JSON.stringify({ model: req.externalId, ...req.input })
@@ -985,51 +1003,75 @@ function createKunavoMediaAdapter(config) {
       throw new KunavoMediaError(submit.status, await safeText(submit));
     }
     const submitBody = await submit.json();
-    const inlineUrls = extractImageUrls(submitBody);
-    if (inlineUrls.length > 0) {
-      return { outputs: inlineUrls.map((url) => ({ url, type: "video" })) };
-    }
-    const jobId = submitBody.id ?? submitBody.task_id ?? submitBody.request_id;
+    const jobId = submitBody.id;
     if (!jobId) {
       throw new Error(
-        `ai-lcr: Kunavo video submit returned no job id (got keys: ${Object.keys(
-          submitBody
-        ).join(", ")})`
+        `ai-lcr: Kunavo video submit returned no job id (got keys: ${Object.keys(submitBody).join(
+          ", "
+        )})`
       );
     }
     const deadline = Date.now() + pollTimeoutMs;
     while (Date.now() < deadline) {
-      await sleep(pollIntervalMs);
-      const poll = await fetchImpl(`${baseUrl}/v1/video/generations/${jobId}`, {
-        headers
-      });
+      const poll = await fetchImpl(`${baseUrl}/v1/videos/${jobId}`, { headers });
       if (!poll.ok) {
         throw new KunavoMediaError(poll.status, await safeText(poll));
       }
-      const pollBody = await poll.json();
-      const status = String(pollBody.status ?? "").toLowerCase();
-      if (status === "succeeded" || status === "completed" || status === "success") {
-        const urls = extractImageUrls(pollBody);
-        const direct = pollBody.url;
-        const all = urls.length > 0 ? urls : direct ? [direct] : [];
-        if (all.length === 0) {
-          throw new Error(`ai-lcr: Kunavo video job ${jobId} finished with no URL`);
+      const body = await poll.json();
+      const status = String(body.status ?? "").toLowerCase();
+      if (status === "completed" || status === "succeeded" || status === "success") {
+        const urls = extractVideoUrls(body);
+        if (urls.length === 0) {
+          throw new Error(`ai-lcr: Kunavo video job ${jobId} completed with no URL`);
         }
-        return { outputs: all.map((url) => ({ url, type: "video" })) };
+        return { outputs: urls.map((url) => ({ url, type: "video" })) };
       }
       if (status === "failed" || status === "error") {
+        const err = body.error;
         throw new Error(
-          `ai-lcr: Kunavo video job ${jobId} failed: ${JSON.stringify(pollBody)}`
+          `ai-lcr: Kunavo video job ${jobId} failed: ${err?.message ?? JSON.stringify(body)}`
+        );
+      }
+      await sleep(pollIntervalMs);
+    }
+    throw new KunavoMediaError(
+      504,
+      `Kunavo video job ${jobId} timed out after ${pollTimeoutMs}ms`
+    );
+  }
+  async function runVideoSync(req) {
+    let res;
+    try {
+      res = await fetchImpl(`${baseUrl}/v1/video/generations`, {
+        method: "POST",
+        headers,
+        body: JSON.stringify({ model: req.externalId, ...req.input }),
+        signal: AbortSignal.timeout(syncVideoTimeoutMs)
+      });
+    } catch (err) {
+      if (err?.name === "TimeoutError" || err?.name === "AbortError") {
+        throw new KunavoMediaError(
+          504,
+          `Kunavo sync video timed out after ${syncVideoTimeoutMs}ms`
         );
       }
+      throw err;
+    }
+    if (!res.ok) {
+      throw new KunavoMediaError(res.status, await safeText(res));
+    }
+    const urls = extractImageUrls(await res.json());
+    if (urls.length === 0) {
+      throw new Error(`ai-lcr: Kunavo sync video returned no URL for "${req.externalId}"`);
     }
-    throw new Error(`ai-lcr: Kunavo video job ${jobId} timed out after ${pollTimeoutMs}ms`);
+    return { outputs: urls.map((url) => ({ url, type: "video" })) };
   }
   return {
     provider: "kunavo",
     async run(req) {
       const isVideo = /(^|\/)veo/i.test(req.externalId);
-      return isVideo ? runVideo(req) : runImage(req);
+      if (!isVideo) return runImage(req);
+      return videoMode === "sync" ? runVideoSync(req) : runVideoAsync(req);
     }
   };
 }

package/dist/index.d.cts

@@ -476,34 +476,50 @@ declare const MEDIA_PRICING: MediaRegistry;
 declare const OFFICIAL_PRICES: Record<string, MediaPricing>;
 
 /**
- * Kunavo media adapter — image (sync) + video (async poll).
+ * Kunavo media adapter — image (sync) + video (async poll, sync fallback).
  *
  * Kunavo is NOT an AI-SDK chat provider for media: image/video generation uses
  * its own REST endpoints, not `/v1/chat/completions`. So this is a hand-rolled
- * `MediaAdapter`, not a `createOpenAICompatible` wrapper.
+ * `MediaAdapter`, not a `createOpenAICompatible` wrapper. All paths VERIFIED
+ * live against the real API (image 2026-05-31, edit + async video 2026-06-06).
  *
- *   - Image:  POST /v1/images/generations  → returns a files.kunavo.com URL.
- *             Synchronous (~11s for nano-banana). VERIFIED end-to-end.
- *   - Video:  POST /v1/video/generations   (singular "video"; /videos/ → 405).
- *             Long-running. The submit→poll path here is IMPLEMENTED FROM THE
- *             DOCS SHAPE BUT NOT YET RUN against a real job (veo-3 generation
- *             was skipped to save cost). Treat the poll loop as unverified:
- *             the field names (`id`/`status`/`url`) may differ from what the
- *             live API returns. Verify before relying on video in production.
+ *   - Image gen:  POST /v1/images/generations  → { created, data:[{url}] }.
+ *                 Synchronous (~11s nano-banana, ~42s nano-banana-2).
+ *   - Image edit: POST /v1/images/edits         → same shape. Triggered for
+ *                 `*-edit` slugs (nano-banana-edit, gpt-image-2-edit); the
+ *                 caller supplies `image` (url/data-uri) or `image_urls[]`.
+ *   - Video:      Kunavo has TWO video endpoints; this adapter defaults to the
+ *                 ASYNC one (Kunavo's own "recommended for production"):
+ *                   submit  POST /v1/videos        → { id:"vid_…", status }
+ *                   poll    GET  /v1/videos/{id}    → status queued→in_progress
+ *                                                     →completed, output:{url,urls}
+ *                 Set `videoMode:"sync"` to use the blocking single-call path
+ *                 POST /v1/video/generations instead (returns { data:[{url}] }
+ *                 inline, ~108s for veo-3-lite; longer SKUs need a long timeout).
  *
- * Kunavo does NOT return a per-call cost in the generation response, so cost is
- * left to the router's normalized estimate (MediaGenerateResult.costCents
- * stays undefined; `units` defaults to 1 — one image / one clip per call).
+ * Kunavo does NOT return a per-call cost in the generation response, and
+ * `GET /v1/models` carries no pricing — so cost is left to the router's
+ * normalized estimate (MediaGenerateResult.costCents stays undefined; `units`
+ * defaults to 1 — one image / one clip per call).
  */
 
 interface KunavoMediaConfig {
     apiKey: string;
     /** Override for testing. Defaults to https://api.kunavo.com. */
     baseUrl?: string;
-    /** Video poll cadence (ms). Default 5000. */
+    /**
+     * Video execution path. "async" (default) submits to POST /v1/videos and
+     * polls GET /v1/videos/{id} — non-blocking, survives proxy/LB connection
+     * limits, and is Kunavo's recommended production path. "sync" uses the
+     * blocking POST /v1/video/generations single call.
+     */
+    videoMode?: "async" | "sync";
+    /** Async-video poll cadence (ms). Default 5000. */
     pollIntervalMs?: number;
-    /** Max time to wait for a video job before giving up (ms). Default 300000 (5m). */
+    /** Max time to wait for an async video job before giving up (ms). Default 600000 (10m). */
     pollTimeoutMs?: number;
+    /** Hard cap for the blocking sync-video HTTP call (ms). Default 600000 (10m). */
+    syncVideoTimeoutMs?: number;
     /** Injected for testing; defaults to global fetch. */
     fetchImpl?: typeof fetch;
 }

package/dist/index.d.ts

@@ -476,34 +476,50 @@ declare const MEDIA_PRICING: MediaRegistry;
 declare const OFFICIAL_PRICES: Record<string, MediaPricing>;
 
 /**
- * Kunavo media adapter — image (sync) + video (async poll).
+ * Kunavo media adapter — image (sync) + video (async poll, sync fallback).
  *
  * Kunavo is NOT an AI-SDK chat provider for media: image/video generation uses
  * its own REST endpoints, not `/v1/chat/completions`. So this is a hand-rolled
- * `MediaAdapter`, not a `createOpenAICompatible` wrapper.
+ * `MediaAdapter`, not a `createOpenAICompatible` wrapper. All paths VERIFIED
+ * live against the real API (image 2026-05-31, edit + async video 2026-06-06).
  *
- *   - Image:  POST /v1/images/generations  → returns a files.kunavo.com URL.
- *             Synchronous (~11s for nano-banana). VERIFIED end-to-end.
- *   - Video:  POST /v1/video/generations   (singular "video"; /videos/ → 405).
- *             Long-running. The submit→poll path here is IMPLEMENTED FROM THE
- *             DOCS SHAPE BUT NOT YET RUN against a real job (veo-3 generation
- *             was skipped to save cost). Treat the poll loop as unverified:
- *             the field names (`id`/`status`/`url`) may differ from what the
- *             live API returns. Verify before relying on video in production.
+ *   - Image gen:  POST /v1/images/generations  → { created, data:[{url}] }.
+ *                 Synchronous (~11s nano-banana, ~42s nano-banana-2).
+ *   - Image edit: POST /v1/images/edits         → same shape. Triggered for
+ *                 `*-edit` slugs (nano-banana-edit, gpt-image-2-edit); the
+ *                 caller supplies `image` (url/data-uri) or `image_urls[]`.
+ *   - Video:      Kunavo has TWO video endpoints; this adapter defaults to the
+ *                 ASYNC one (Kunavo's own "recommended for production"):
+ *                   submit  POST /v1/videos        → { id:"vid_…", status }
+ *                   poll    GET  /v1/videos/{id}    → status queued→in_progress
+ *                                                     →completed, output:{url,urls}
+ *                 Set `videoMode:"sync"` to use the blocking single-call path
+ *                 POST /v1/video/generations instead (returns { data:[{url}] }
+ *                 inline, ~108s for veo-3-lite; longer SKUs need a long timeout).
  *
- * Kunavo does NOT return a per-call cost in the generation response, so cost is
- * left to the router's normalized estimate (MediaGenerateResult.costCents
- * stays undefined; `units` defaults to 1 — one image / one clip per call).
+ * Kunavo does NOT return a per-call cost in the generation response, and
+ * `GET /v1/models` carries no pricing — so cost is left to the router's
+ * normalized estimate (MediaGenerateResult.costCents stays undefined; `units`
+ * defaults to 1 — one image / one clip per call).
  */
 
 interface KunavoMediaConfig {
     apiKey: string;
     /** Override for testing. Defaults to https://api.kunavo.com. */
     baseUrl?: string;
-    /** Video poll cadence (ms). Default 5000. */
+    /**
+     * Video execution path. "async" (default) submits to POST /v1/videos and
+     * polls GET /v1/videos/{id} — non-blocking, survives proxy/LB connection
+     * limits, and is Kunavo's recommended production path. "sync" uses the
+     * blocking POST /v1/video/generations single call.
+     */
+    videoMode?: "async" | "sync";
+    /** Async-video poll cadence (ms). Default 5000. */
     pollIntervalMs?: number;
-    /** Max time to wait for a video job before giving up (ms). Default 300000 (5m). */
+    /** Max time to wait for an async video job before giving up (ms). Default 600000 (10m). */
     pollTimeoutMs?: number;
+    /** Hard cap for the blocking sync-video HTTP call (ms). Default 600000 (10m). */
+    syncVideoTimeoutMs?: number;
     /** Injected for testing; defaults to global fetch. */
     fetchImpl?: typeof fetch;
 }

package/dist/index.js

@@ -863,11 +863,15 @@ var MEDIA_PRICING = {
     ]
   },
   // ── Google video (Veo) ──────────────────────────────────────
-  // ⚠️ Version/SKU mismatch across providers: Kunavo bills "veo-3" per CALL
-  // (flat fee per clip; Veo 3 generates ~8s, audio/res tier unconfirmed); fal
-  // bills "veo3.1" per SECOND. Normalized to a 5s clip the per-call price wins
-  // by a wide margin — verify the clip's duration/resolution/audio before
-  // trusting the gap. See note fields.
+  // Kunavo video VERIFIED live 2026-06-06: veo-3-lite renders via both the async
+  // path (POST /v1/videos + poll, ~80s) and the sync path (POST /v1/video/
+  // generations, ~108s), real 720p mp4 out. The adapter defaults to async.
+  // ⚠️ Two caveats remain on the PRICE gap, not the capability: (1) Version/SKU
+  // mismatch — Kunavo bills "veo-3" per CALL (flat per clip, ~8s 720p) while fal
+  // bills "veo3.1" per SECOND, so normalized to a 5s clip the per-call price wins
+  // by a wide margin; (2) /v1/models exposes NO pricing, so the per-call cents
+  // below are hand-entered — verify clip duration/resolution/audio before
+  // trusting the gap. veo-3 / veo-3-quality capability not individually rendered.
   "google/veo-3": {
     id: "google/veo-3",
     modality: "video",
@@ -880,7 +884,7 @@ var MEDIA_PRICING = {
     id: "google/veo-3-lite",
     modality: "video",
     routes: [
-      { provider: "kunavo", externalId: "veo-3-lite", pricing: { unit: "call", cents: 16 }, note: "flat per clip (SKU unverified)" },
+      { provider: "kunavo", externalId: "veo-3-lite", pricing: { unit: "call", cents: 16 }, note: "flat per clip; rendering verified 2026-06-06 (720p, async+sync); price hand-entered" },
       { provider: "fal", externalId: "fal-ai/veo3.1/lite", pricing: { unit: "second", cents: 8 }, note: "veo3.1 lite, 1080p audio-on" }
     ]
   },
@@ -900,12 +904,26 @@ function extractImageUrls(body) {
   if (!Array.isArray(data)) return [];
   return data.map((d) => d?.url).filter((u) => typeof u === "string" && u.length > 0);
 }
+function extractVideoUrls(body) {
+  const output = body.output;
+  if (output) {
+    if (Array.isArray(output.urls)) {
+      const urls = output.urls.filter((u) => typeof u === "string" && u.length > 0);
+      if (urls.length > 0) return urls;
+    }
+    if (typeof output.url === "string" && output.url.length > 0) return [output.url];
+  }
+  if (typeof body.url === "string" && body.url.length > 0) return [body.url];
+  return extractImageUrls(body);
+}
 function createKunavoMediaAdapter(config) {
   const {
     apiKey,
     baseUrl = DEFAULT_BASE,
+    videoMode = "async",
     pollIntervalMs = 5e3,
-    pollTimeoutMs = 3e5,
+    pollTimeoutMs = 6e5,
+    syncVideoTimeoutMs = 6e5,
     fetchImpl = fetch
   } = config;
   const headers = {
@@ -913,7 +931,8 @@ function createKunavoMediaAdapter(config) {
     authorization: `Bearer ${apiKey}`
   };
   async function runImage(req) {
-    const res = await fetchImpl(`${baseUrl}/v1/images/generations`, {
+    const path = /-edit$/i.test(req.externalId) ? "/v1/images/edits" : "/v1/images/generations";
+    const res = await fetchImpl(`${baseUrl}${path}`, {
       method: "POST",
       headers,
       body: JSON.stringify({ model: req.externalId, ...req.input })
@@ -921,16 +940,15 @@ function createKunavoMediaAdapter(config) {
     if (!res.ok) {
       throw new KunavoMediaError(res.status, await safeText(res));
     }
-    const body = await res.json();
-    const urls = extractImageUrls(body);
+    const urls = extractImageUrls(await res.json());
     if (urls.length === 0) {
       throw new Error(`ai-lcr: Kunavo returned no image URL for "${req.externalId}"`);
     }
     const outputs = urls.map((url) => ({ url, type: "image" }));
     return { outputs };
   }
-  async function runVideo(req) {
-    const submit = await fetchImpl(`${baseUrl}/v1/video/generations`, {
+  async function runVideoAsync(req) {
+    const submit = await fetchImpl(`${baseUrl}/v1/videos`, {
       method: "POST",
       headers,
       body: JSON.stringify({ model: req.externalId, ...req.input })
@@ -939,51 +957,75 @@ function createKunavoMediaAdapter(config) {
       throw new KunavoMediaError(submit.status, await safeText(submit));
     }
     const submitBody = await submit.json();
-    const inlineUrls = extractImageUrls(submitBody);
-    if (inlineUrls.length > 0) {
-      return { outputs: inlineUrls.map((url) => ({ url, type: "video" })) };
-    }
-    const jobId = submitBody.id ?? submitBody.task_id ?? submitBody.request_id;
+    const jobId = submitBody.id;
     if (!jobId) {
       throw new Error(
-        `ai-lcr: Kunavo video submit returned no job id (got keys: ${Object.keys(
-          submitBody
-        ).join(", ")})`
+        `ai-lcr: Kunavo video submit returned no job id (got keys: ${Object.keys(submitBody).join(
+          ", "
+        )})`
       );
     }
     const deadline = Date.now() + pollTimeoutMs;
     while (Date.now() < deadline) {
-      await sleep(pollIntervalMs);
-      const poll = await fetchImpl(`${baseUrl}/v1/video/generations/${jobId}`, {
-        headers
-      });
+      const poll = await fetchImpl(`${baseUrl}/v1/videos/${jobId}`, { headers });
       if (!poll.ok) {
         throw new KunavoMediaError(poll.status, await safeText(poll));
       }
-      const pollBody = await poll.json();
-      const status = String(pollBody.status ?? "").toLowerCase();
-      if (status === "succeeded" || status === "completed" || status === "success") {
-        const urls = extractImageUrls(pollBody);
-        const direct = pollBody.url;
-        const all = urls.length > 0 ? urls : direct ? [direct] : [];
-        if (all.length === 0) {
-          throw new Error(`ai-lcr: Kunavo video job ${jobId} finished with no URL`);
+      const body = await poll.json();
+      const status = String(body.status ?? "").toLowerCase();
+      if (status === "completed" || status === "succeeded" || status === "success") {
+        const urls = extractVideoUrls(body);
+        if (urls.length === 0) {
+          throw new Error(`ai-lcr: Kunavo video job ${jobId} completed with no URL`);
         }
-        return { outputs: all.map((url) => ({ url, type: "video" })) };
+        return { outputs: urls.map((url) => ({ url, type: "video" })) };
       }
       if (status === "failed" || status === "error") {
+        const err = body.error;
         throw new Error(
-          `ai-lcr: Kunavo video job ${jobId} failed: ${JSON.stringify(pollBody)}`
+          `ai-lcr: Kunavo video job ${jobId} failed: ${err?.message ?? JSON.stringify(body)}`
+        );
+      }
+      await sleep(pollIntervalMs);
+    }
+    throw new KunavoMediaError(
+      504,
+      `Kunavo video job ${jobId} timed out after ${pollTimeoutMs}ms`
+    );
+  }
+  async function runVideoSync(req) {
+    let res;
+    try {
+      res = await fetchImpl(`${baseUrl}/v1/video/generations`, {
+        method: "POST",
+        headers,
+        body: JSON.stringify({ model: req.externalId, ...req.input }),
+        signal: AbortSignal.timeout(syncVideoTimeoutMs)
+      });
+    } catch (err) {
+      if (err?.name === "TimeoutError" || err?.name === "AbortError") {
+        throw new KunavoMediaError(
+          504,
+          `Kunavo sync video timed out after ${syncVideoTimeoutMs}ms`
         );
       }
+      throw err;
+    }
+    if (!res.ok) {
+      throw new KunavoMediaError(res.status, await safeText(res));
+    }
+    const urls = extractImageUrls(await res.json());
+    if (urls.length === 0) {
+      throw new Error(`ai-lcr: Kunavo sync video returned no URL for "${req.externalId}"`);
     }
-    throw new Error(`ai-lcr: Kunavo video job ${jobId} timed out after ${pollTimeoutMs}ms`);
+    return { outputs: urls.map((url) => ({ url, type: "video" })) };
   }
   return {
     provider: "kunavo",
     async run(req) {
       const isVideo = /(^|\/)veo/i.test(req.externalId);
-      return isVideo ? runVideo(req) : runImage(req);
+      if (!isVideo) return runImage(req);
+      return videoMode === "sync" ? runVideoSync(req) : runVideoAsync(req);
     }
   };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-lcr",
-  "version": "0.5.4",
+  "version": "0.5.5",
   "description": "Least Cost Routing for LLMs — route every model call to the cheapest available provider, fall back automatically, and track real cost. Built for the Vercel AI SDK.",
   "keywords": [
     "ai",