chore: wtf.

src/media-understanding/apply.e2e.test.ts

@@ -2,9 +2,9 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 import { beforeEach, describe, expect, it, vi } from "vitest";
+import { resolveApiKeyForProvider } from "../agents/model-auth.js";
 import type { MsgContext } from "../auto-reply/templating.js";
 import type { OpenClawConfig } from "../config/config.js";
-import { resolveApiKeyForProvider } from "../agents/model-auth.js";
 import { fetchRemoteMedia } from "../media/fetch.js";
 
 vi.mock("../agents/model-auth.js", () => ({

src/media-understanding/apply.ts

@@ -1,13 +1,7 @@
 import path from "node:path";
+import { finalizeInboundContext } from "../auto-reply/reply/inbound-context.js";
 import type { MsgContext } from "../auto-reply/templating.js";
 import type { OpenClawConfig } from "../config/config.js";
-import type {
-  MediaUnderstandingCapability,
-  MediaUnderstandingDecision,
-  MediaUnderstandingOutput,
-  MediaUnderstandingProvider,
-} from "./types.js";
-import { finalizeInboundContext } from "../auto-reply/reply/inbound-context.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import {
   extractFileContentFromSource,
@@ -29,6 +23,12 @@ import {
   normalizeMediaAttachments,
   runCapability,
 } from "./runner.js";
+import type {
+  MediaUnderstandingCapability,
+  MediaUnderstandingDecision,
+  MediaUnderstandingOutput,
+  MediaUnderstandingProvider,
+} from "./types.js";
 
 export type ApplyMediaUnderstandingResult = {
   outputs: MediaUnderstandingOutput[];

src/media-understanding/attachments.ts

@@ -5,13 +5,13 @@ import path from "node:path";
 import { fileURLToPath } from "node:url";
 import type { MsgContext } from "../auto-reply/templating.js";
 import type { MediaUnderstandingAttachmentsConfig } from "../config/types.tools.js";
-import type { MediaAttachment, MediaUnderstandingCapability } from "./types.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import { isAbortError } from "../infra/unhandled-rejections.js";
 import { fetchRemoteMedia, MediaFetchError } from "../media/fetch.js";
 import { detectMime, getFileExtension, isAudioFileName, kindFromMime } from "../media/mime.js";
 import { MediaUnderstandingSkipError } from "./errors.js";
 import { fetchWithTimeout } from "./providers/shared.js";
+import type { MediaAttachment, MediaUnderstandingCapability } from "./types.js";
 
 type MediaBufferResult = {
   buffer: Buffer;

src/media-understanding/audio-preflight.ts

@@ -1,6 +1,5 @@
 import type { MsgContext } from "../auto-reply/templating.js";
 import type { OpenClawConfig } from "../config/config.js";
-import type { MediaUnderstandingProvider } from "./types.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import { isAudioAttachment } from "./attachments.js";
 import {
@@ -10,6 +9,7 @@ import {
   normalizeMediaAttachments,
   runCapability,
 } from "./runner.js";
+import type { MediaUnderstandingProvider } from "./types.js";
 
 /**
  * Transcribes the first audio attachment BEFORE mention checking.

src/media-understanding/providers/image.ts

@@ -1,11 +1,11 @@
 import type { Api, Context, Model } from "@mariozechner/pi-ai";
 import { complete } from "@mariozechner/pi-ai";
-import type { ImageDescriptionRequest, ImageDescriptionResult } from "../types.js";
 import { minimaxUnderstandImage } from "../../agents/minimax-vlm.js";
 import { getApiKeyForModel, requireApiKey } from "../../agents/model-auth.js";
 import { ensureOpenClawModelsJson } from "../../agents/models-config.js";
 import { discoverAuthStorage, discoverModels } from "../../agents/pi-model-discovery.js";
 import { coerceImageAssistantText } from "../../agents/tools/image-tool.helpers.js";
+import type { ImageDescriptionRequest, ImageDescriptionResult } from "../types.js";
 
 export async function describeImageWithModel(
   params: ImageDescriptionRequest,

src/media-understanding/providers/index.ts

@@ -1,5 +1,5 @@
-import type { MediaUnderstandingProvider } from "../types.js";
 import { normalizeProviderId } from "../../agents/model-selection.js";
+import type { MediaUnderstandingProvider } from "../types.js";
 import { anthropicProvider } from "./anthropic/index.js";
 import { deepgramProvider } from "./deepgram/index.js";
 import { googleProvider } from "./google/index.js";

src/media-understanding/providers/shared.ts

@@ -1,6 +1,6 @@
 import type { GuardedFetchResult } from "../../infra/net/fetch-guard.js";
-import type { LookupFn, SsrFPolicy } from "../../infra/net/ssrf.js";
 import { fetchWithSsrFGuard } from "../../infra/net/fetch-guard.js";
+import type { LookupFn, SsrFPolicy } from "../../infra/net/ssrf.js";
 export { fetchWithTimeout } from "../../utils/fetch-timeout.js";
 
 const MAX_ERROR_CHARS = 300;

src/media-understanding/resolve.test.ts

@@ -1,7 +1,7 @@
 import { describe, expect, it } from "vitest";
 import type { OpenClawConfig } from "../config/config.js";
-import type { MediaUnderstandingCapability } from "./types.js";
 import { resolveEntriesWithActiveFallback, resolveModelEntries } from "./resolve.js";
+import type { MediaUnderstandingCapability } from "./types.js";
 
 const providerRegistry = new Map<string, { capabilities: MediaUnderstandingCapability[] }>([
   ["openai", { capabilities: ["image"] }],

src/media-understanding/resolve.ts

@@ -5,7 +5,6 @@ import type {
   MediaUnderstandingModelConfig,
   MediaUnderstandingScopeConfig,
 } from "../config/types.tools.js";
-import type { MediaUnderstandingCapability } from "./types.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import {
   DEFAULT_MAX_BYTES,
@@ -15,6 +14,7 @@ import {
 } from "./defaults.js";
 import { normalizeMediaProviderId } from "./providers/index.js";
 import { normalizeMediaUnderstandingChatType, resolveMediaUnderstandingScope } from "./scope.js";
+import type { MediaUnderstandingCapability } from "./types.js";
 
 export function resolveTimeoutMs(seconds: number | undefined, fallbackSeconds: number): number {
   const value = typeof seconds === "number" && Number.isFinite(seconds) ? seconds : fallbackSeconds;

src/media-understanding/runner.entries.ts

@@ -1,21 +1,14 @@
 import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
+import { requireApiKey, resolveApiKeyForProvider } from "../agents/model-auth.js";
 import type { MsgContext } from "../auto-reply/templating.js";
+import { applyTemplate } from "../auto-reply/templating.js";
 import type { OpenClawConfig } from "../config/config.js";
 import type {
   MediaUnderstandingConfig,
   MediaUnderstandingModelConfig,
 } from "../config/types.tools.js";
-import type {
-  MediaUnderstandingCapability,
-  MediaUnderstandingDecision,
-  MediaUnderstandingModelDecision,
-  MediaUnderstandingOutput,
-  MediaUnderstandingProvider,
-} from "./types.js";
-import { requireApiKey, resolveApiKeyForProvider } from "../agents/model-auth.js";
-import { applyTemplate } from "../auto-reply/templating.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import { runExec } from "../process/exec.js";
 import { MediaAttachmentCache } from "./attachments.js";
@@ -30,6 +23,13 @@ import { extractGeminiResponse } from "./output-extract.js";
 import { describeImageWithModel } from "./providers/image.js";
 import { getMediaUnderstandingProvider, normalizeMediaProviderId } from "./providers/index.js";
 import { resolveMaxBytes, resolveMaxChars, resolvePrompt, resolveTimeoutMs } from "./resolve.js";
+import type {
+  MediaUnderstandingCapability,
+  MediaUnderstandingDecision,
+  MediaUnderstandingModelDecision,
+  MediaUnderstandingOutput,
+  MediaUnderstandingProvider,
+} from "./types.js";
 import { estimateBase64Size, resolveVideoMaxBase64Bytes } from "./video.js";
 
 export type ProviderRegistry = Map<string, MediaUnderstandingProvider>;

src/media-understanding/runner.ts

@@ -2,26 +2,18 @@ import { constants as fsConstants } from "node:fs";
 import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
-import type { MsgContext } from "../auto-reply/templating.js";
-import type { OpenClawConfig } from "../config/config.js";
-import type {
-  MediaUnderstandingConfig,
-  MediaUnderstandingModelConfig,
-} from "../config/types.tools.js";
-import type {
-  MediaAttachment,
-  MediaUnderstandingCapability,
-  MediaUnderstandingDecision,
-  MediaUnderstandingModelDecision,
-  MediaUnderstandingOutput,
-  MediaUnderstandingProvider,
-} from "./types.js";
 import { resolveApiKeyForProvider } from "../agents/model-auth.js";
 import {
   findModelInCatalog,
   loadModelCatalog,
   modelSupportsVision,
 } from "../agents/model-catalog.js";
+import type { MsgContext } from "../auto-reply/templating.js";
+import type { OpenClawConfig } from "../config/config.js";
+import type {
+  MediaUnderstandingConfig,
+  MediaUnderstandingModelConfig,
+} from "../config/types.tools.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import { runExec } from "../process/exec.js";
 import { MediaAttachmentCache, normalizeAttachments, selectAttachments } from "./attachments.js";
@@ -46,6 +38,14 @@ import {
   runCliEntry,
   runProviderEntry,
 } from "./runner.entries.js";
+import type {
+  MediaAttachment,
+  MediaUnderstandingCapability,
+  MediaUnderstandingDecision,
+  MediaUnderstandingModelDecision,
+  MediaUnderstandingOutput,
+  MediaUnderstandingProvider,
+} from "./types.js";
 
 export type ActiveMediaModel = {
   provider: string;

src/media-understanding/scope.ts

@@ -1,5 +1,5 @@
-import type { MediaUnderstandingScopeConfig } from "../config/types.tools.js";
 import { normalizeChatType } from "../channels/chat-type.js";
+import type { MediaUnderstandingScopeConfig } from "../config/types.tools.js";
 
 export type MediaUnderstandingScopeDecision = "allow" | "deny";