@poolzin/pool-bot 2026.2.0 → 2026.2.2

package/dist/media-understanding/attachments.js

@@ -3,16 +3,18 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 import { fileURLToPath } from "node:url";
+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 { logVerbose, shouldLogVerbose } from "../globals.js";
-import { fetchWithTimeout } from "./providers/shared.js";
 import { MediaUnderstandingSkipError } from "./errors.js";
+import { fetchWithTimeout } from "./providers/shared.js";
 const DEFAULT_MAX_ATTACHMENTS = 1;
 function normalizeAttachmentPath(raw) {
     const value = raw?.trim();
-    if (!value)
+    if (!value) {
         return undefined;
+    }
     if (value.startsWith("file://")) {
         try {
             return fileURLToPath(value);
@@ -30,8 +32,9 @@ export function normalizeAttachments(ctx) {
     const resolveMime = (count, index) => {
         const typeHint = typesFromArray?.[index];
         const trimmed = typeof typeHint === "string" ? typeHint.trim() : "";
-        if (trimmed)
+        if (trimmed) {
             return trimmed;
+        }
         return count === 1 ? ctx.MediaType : undefined;
     };
     if (pathsFromArray && pathsFromArray.length > 0) {
@@ -59,8 +62,9 @@ export function normalizeAttachments(ctx) {
     }
     const pathValue = ctx.MediaPath?.trim();
     const url = ctx.MediaUrl?.trim();
-    if (!pathValue && !url)
+    if (!pathValue && !url) {
         return [];
+    }
     return [
         {
             path: pathValue || undefined,
@@ -72,15 +76,19 @@ export function normalizeAttachments(ctx) {
 }
 export function resolveAttachmentKind(attachment) {
     const kind = kindFromMime(attachment.mime);
-    if (kind === "image" || kind === "audio" || kind === "video")
+    if (kind === "image" || kind === "audio" || kind === "video") {
         return kind;
+    }
     const ext = getFileExtension(attachment.path ?? attachment.url);
-    if (!ext)
+    if (!ext) {
         return "unknown";
-    if ([".mp4", ".mov", ".mkv", ".webm", ".avi", ".m4v"].includes(ext))
+    }
+    if ([".mp4", ".mov", ".mkv", ".webm", ".avi", ".m4v"].includes(ext)) {
         return "video";
-    if (isAudioFileName(attachment.path ?? attachment.url))
+    }
+    if (isAudioFileName(attachment.path ?? attachment.url)) {
         return "audio";
+    }
     if ([".png", ".jpg", ".jpeg", ".webp", ".gif", ".bmp", ".tiff", ".tif"].includes(ext)) {
         return "image";
     }
@@ -95,25 +103,22 @@ export function isAudioAttachment(attachment) {
 export function isImageAttachment(attachment) {
     return resolveAttachmentKind(attachment) === "image";
 }
-function isAbortError(err) {
-    if (!err)
-        return false;
-    if (err instanceof Error && err.name === "AbortError")
-        return true;
-    return false;
-}
 function resolveRequestUrl(input) {
-    if (typeof input === "string")
+    if (typeof input === "string") {
         return input;
-    if (input instanceof URL)
+    }
+    if (input instanceof URL) {
         return input.toString();
+    }
     return input.url;
 }
 function orderAttachments(attachments, prefer) {
-    if (!prefer || prefer === "first")
+    if (!prefer || prefer === "first") {
         return attachments;
-    if (prefer === "last")
-        return [...attachments].reverse();
+    }
+    if (prefer === "last") {
+        return [...attachments].toReversed();
+    }
     if (prefer === "path") {
         const withPath = attachments.filter((item) => item.path);
         const withoutPath = attachments.filter((item) => !item.path);
@@ -129,14 +134,17 @@ function orderAttachments(attachments, prefer) {
 export function selectAttachments(params) {
     const { capability, attachments, policy } = params;
     const matches = attachments.filter((item) => {
-        if (capability === "image")
+        if (capability === "image") {
             return isImageAttachment(item);
-        if (capability === "audio")
+        }
+        if (capability === "audio") {
             return isAudioAttachment(item);
+        }
         return isVideoAttachment(item);
     });
-    if (matches.length === 0)
+    if (matches.length === 0) {
         return [];
+    }
     const ordered = orderAttachments(matches, policy?.prefer);
     const mode = policy?.mode ?? "first";
     const maxAttachments = policy?.maxAttachments ?? DEFAULT_MAX_ATTACHMENTS;
@@ -291,15 +299,18 @@ export class MediaAttachmentCache {
     }
     resolveLocalPath(attachment) {
         const rawPath = normalizeAttachmentPath(attachment.path);
-        if (!rawPath)
+        if (!rawPath) {
             return undefined;
+        }
         return path.isAbsolute(rawPath) ? rawPath : path.resolve(rawPath);
     }
     async ensureLocalStat(entry) {
-        if (!entry.resolvedPath)
+        if (!entry.resolvedPath) {
             return undefined;
-        if (entry.statSize !== undefined)
+        }
+        if (entry.statSize !== undefined) {
             return entry.statSize;
+        }
         try {
             const stat = await fs.stat(entry.resolvedPath);
             if (!stat.isFile()) {

package/dist/media-understanding/defaults.js

@@ -26,5 +26,21 @@ export const DEFAULT_AUDIO_MODELS = {
     openai: "gpt-4o-mini-transcribe",
     deepgram: "nova-3",
 };
+export const AUTO_AUDIO_KEY_PROVIDERS = ["openai", "groq", "deepgram", "google"];
+export const AUTO_IMAGE_KEY_PROVIDERS = [
+    "openai",
+    "anthropic",
+    "google",
+    "minimax",
+    "zai",
+];
+export const AUTO_VIDEO_KEY_PROVIDERS = ["google"];
+export const DEFAULT_IMAGE_MODELS = {
+    openai: "gpt-5-mini",
+    anthropic: "claude-opus-4-6",
+    google: "gemini-3-flash-preview",
+    minimax: "MiniMax-VL-01",
+    zai: "glm-4.6v",
+};
 export const CLI_OUTPUT_MAX_BUFFER = 5 * MB;
 export const DEFAULT_MEDIA_CONCURRENCY = 2;

package/dist/media-understanding/providers/deepgram/audio.js

@@ -1,4 +1,4 @@
-import { fetchWithTimeout, normalizeBaseUrl, readErrorResponse } from "../shared.js";
+import { fetchWithTimeoutGuarded, normalizeBaseUrl, readErrorResponse } from "../shared.js";
 export const DEFAULT_DEEPGRAM_AUDIO_BASE_URL = "https://api.deepgram.com/v1";
 export const DEFAULT_DEEPGRAM_AUDIO_MODEL = "nova-3";
 function resolveModel(model) {
@@ -8,15 +8,18 @@ function resolveModel(model) {
 export async function transcribeDeepgramAudio(params) {
     const fetchFn = params.fetchFn ?? fetch;
     const baseUrl = normalizeBaseUrl(params.baseUrl, DEFAULT_DEEPGRAM_AUDIO_BASE_URL);
+    const allowPrivate = Boolean(params.baseUrl?.trim());
     const model = resolveModel(params.model);
     const url = new URL(`${baseUrl}/listen`);
     url.searchParams.set("model", model);
-    if (params.language?.trim())
+    if (params.language?.trim()) {
         url.searchParams.set("language", params.language.trim());
+    }
     if (params.query) {
         for (const [key, value] of Object.entries(params.query)) {
-            if (value === undefined)
+            if (value === undefined) {
                 continue;
+            }
             url.searchParams.set(key, String(value));
         }
     }
@@ -28,20 +31,25 @@ export async function transcribeDeepgramAudio(params) {
         headers.set("content-type", params.mime ?? "application/octet-stream");
     }
     const body = new Uint8Array(params.buffer);
-    const res = await fetchWithTimeout(url.toString(), {
+    const { response: res, release } = await fetchWithTimeoutGuarded(url.toString(), {
         method: "POST",
         headers,
         body,
-    }, params.timeoutMs, fetchFn);
-    if (!res.ok) {
-        const detail = await readErrorResponse(res);
-        const suffix = detail ? `: ${detail}` : "";
-        throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+    }, params.timeoutMs, fetchFn, allowPrivate ? { ssrfPolicy: { allowPrivateNetwork: true } } : undefined);
+    try {
+        if (!res.ok) {
+            const detail = await readErrorResponse(res);
+            const suffix = detail ? `: ${detail}` : "";
+            throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+        }
+        const payload = (await res.json());
+        const transcript = payload.results?.channels?.[0]?.alternatives?.[0]?.transcript?.trim();
+        if (!transcript) {
+            throw new Error("Audio transcription response missing transcript");
+        }
+        return { text: transcript, model };
     }
-    const payload = (await res.json());
-    const transcript = payload.results?.channels?.[0]?.alternatives?.[0]?.transcript?.trim();
-    if (!transcript) {
-        throw new Error("Audio transcription response missing transcript");
+    finally {
+        await release();
     }
-    return { text: transcript, model };
 }

package/dist/media-understanding/providers/google/audio.js

@@ -1,12 +1,13 @@
 import { normalizeGoogleModelId } from "../../../agents/models-config.providers.js";
-import { fetchWithTimeout, normalizeBaseUrl, readErrorResponse } from "../shared.js";
+import { fetchWithTimeoutGuarded, normalizeBaseUrl, readErrorResponse } from "../shared.js";
 export const DEFAULT_GOOGLE_AUDIO_BASE_URL = "https://generativelanguage.googleapis.com/v1beta";
 const DEFAULT_GOOGLE_AUDIO_MODEL = "gemini-3-flash-preview";
 const DEFAULT_GOOGLE_AUDIO_PROMPT = "Transcribe the audio.";
 function resolveModel(model) {
     const trimmed = model?.trim();
-    if (!trimmed)
+    if (!trimmed) {
         return DEFAULT_GOOGLE_AUDIO_MODEL;
+    }
     return normalizeGoogleModelId(trimmed);
 }
 function resolvePrompt(prompt) {
@@ -16,6 +17,7 @@ function resolvePrompt(prompt) {
 export async function transcribeGeminiAudio(params) {
     const fetchFn = params.fetchFn ?? fetch;
     const baseUrl = normalizeBaseUrl(params.baseUrl, DEFAULT_GOOGLE_AUDIO_BASE_URL);
+    const allowPrivate = Boolean(params.baseUrl?.trim());
     const model = resolveModel(params.model);
     const url = `${baseUrl}/models/${model}:generateContent`;
     const headers = new Headers(params.headers);
@@ -41,24 +43,29 @@ export async function transcribeGeminiAudio(params) {
             },
         ],
     };
-    const res = await fetchWithTimeout(url, {
+    const { response: res, release } = await fetchWithTimeoutGuarded(url, {
         method: "POST",
         headers,
         body: JSON.stringify(body),
-    }, params.timeoutMs, fetchFn);
-    if (!res.ok) {
-        const detail = await readErrorResponse(res);
-        const suffix = detail ? `: ${detail}` : "";
-        throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+    }, params.timeoutMs, fetchFn, allowPrivate ? { ssrfPolicy: { allowPrivateNetwork: true } } : undefined);
+    try {
+        if (!res.ok) {
+            const detail = await readErrorResponse(res);
+            const suffix = detail ? `: ${detail}` : "";
+            throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+        }
+        const payload = (await res.json());
+        const parts = payload.candidates?.[0]?.content?.parts ?? [];
+        const text = parts
+            .map((part) => part?.text?.trim())
+            .filter(Boolean)
+            .join("\n");
+        if (!text) {
+            throw new Error("Audio transcription response missing text");
+        }
+        return { text, model };
     }
-    const payload = (await res.json());
-    const parts = payload.candidates?.[0]?.content?.parts ?? [];
-    const text = parts
-        .map((part) => part?.text?.trim())
-        .filter(Boolean)
-        .join("\n");
-    if (!text) {
-        throw new Error("Audio transcription response missing text");
+    finally {
+        await release();
     }
-    return { text, model };
 }

package/dist/media-understanding/providers/google/video.js

@@ -1,12 +1,13 @@
 import { normalizeGoogleModelId } from "../../../agents/models-config.providers.js";
-import { fetchWithTimeout, normalizeBaseUrl, readErrorResponse } from "../shared.js";
+import { fetchWithTimeoutGuarded, normalizeBaseUrl, readErrorResponse } from "../shared.js";
 export const DEFAULT_GOOGLE_VIDEO_BASE_URL = "https://generativelanguage.googleapis.com/v1beta";
 const DEFAULT_GOOGLE_VIDEO_MODEL = "gemini-3-flash-preview";
 const DEFAULT_GOOGLE_VIDEO_PROMPT = "Describe the video.";
 function resolveModel(model) {
     const trimmed = model?.trim();
-    if (!trimmed)
+    if (!trimmed) {
         return DEFAULT_GOOGLE_VIDEO_MODEL;
+    }
     return normalizeGoogleModelId(trimmed);
 }
 function resolvePrompt(prompt) {
@@ -16,6 +17,7 @@ function resolvePrompt(prompt) {
 export async function describeGeminiVideo(params) {
     const fetchFn = params.fetchFn ?? fetch;
     const baseUrl = normalizeBaseUrl(params.baseUrl, DEFAULT_GOOGLE_VIDEO_BASE_URL);
+    const allowPrivate = Boolean(params.baseUrl?.trim());
     const model = resolveModel(params.model);
     const url = `${baseUrl}/models/${model}:generateContent`;
     const headers = new Headers(params.headers);
@@ -41,24 +43,29 @@ export async function describeGeminiVideo(params) {
             },
         ],
     };
-    const res = await fetchWithTimeout(url, {
+    const { response: res, release } = await fetchWithTimeoutGuarded(url, {
         method: "POST",
         headers,
         body: JSON.stringify(body),
-    }, params.timeoutMs, fetchFn);
-    if (!res.ok) {
-        const detail = await readErrorResponse(res);
-        const suffix = detail ? `: ${detail}` : "";
-        throw new Error(`Video description failed (HTTP ${res.status})${suffix}`);
+    }, params.timeoutMs, fetchFn, allowPrivate ? { ssrfPolicy: { allowPrivateNetwork: true } } : undefined);
+    try {
+        if (!res.ok) {
+            const detail = await readErrorResponse(res);
+            const suffix = detail ? `: ${detail}` : "";
+            throw new Error(`Video description failed (HTTP ${res.status})${suffix}`);
+        }
+        const payload = (await res.json());
+        const parts = payload.candidates?.[0]?.content?.parts ?? [];
+        const text = parts
+            .map((part) => part?.text?.trim())
+            .filter(Boolean)
+            .join("\n");
+        if (!text) {
+            throw new Error("Video description response missing text");
+        }
+        return { text, model };
     }
-    const payload = (await res.json());
-    const parts = payload.candidates?.[0]?.content?.parts ?? [];
-    const text = parts
-        .map((part) => part?.text?.trim())
-        .filter(Boolean)
-        .join("\n");
-    if (!text) {
-        throw new Error("Video description response missing text");
+    finally {
+        await release();
     }
-    return { text, model };
 }

package/dist/media-understanding/providers/image.js

@@ -1,5 +1,5 @@
 import { complete } from "@mariozechner/pi-ai";
-import { discoverAuthStorage, discoverModels } from "@mariozechner/pi-coding-agent";
+import { discoverAuthStorage, discoverModels } from "../../agents/pi-model-discovery.js";
 import { getApiKeyForModel, requireApiKey } from "../../agents/model-auth.js";
 import { ensurePoolbotModelsJson } from "../../agents/models-config.js";
 import { minimaxUnderstandImage } from "../../agents/minimax-vlm.js";
@@ -46,10 +46,10 @@ export async function describeImageWithModel(params) {
             },
         ],
     };
-    const message = (await complete(model, context, {
+    const message = await complete(model, context, {
         apiKey,
         maxTokens: params.maxTokens ?? 512,
-    }));
+    });
     const text = coerceImageAssistantText({
         message,
         provider: model.provider,

package/dist/media-understanding/providers/index.js

@@ -5,18 +5,21 @@ import { googleProvider } from "./google/index.js";
 import { groqProvider } from "./groq/index.js";
 import { minimaxProvider } from "./minimax/index.js";
 import { openaiProvider } from "./openai/index.js";
+import { zaiProvider } from "./zai/index.js";
 const PROVIDERS = [
     groqProvider,
     openaiProvider,
     googleProvider,
     anthropicProvider,
     minimaxProvider,
+    zaiProvider,
     deepgramProvider,
 ];
 export function normalizeMediaProviderId(id) {
     const normalized = normalizeProviderId(id);
-    if (normalized === "gemini")
+    if (normalized === "gemini") {
         return "google";
+    }
     return normalized;
 }
 export function buildMediaUnderstandingRegistry(overrides) {

package/dist/media-understanding/providers/openai/audio.js

@@ -1,5 +1,5 @@
 import path from "node:path";
-import { fetchWithTimeout, normalizeBaseUrl, readErrorResponse } from "../shared.js";
+import { fetchWithTimeoutGuarded, normalizeBaseUrl, readErrorResponse } from "../shared.js";
 export const DEFAULT_OPENAI_AUDIO_BASE_URL = "https://api.openai.com/v1";
 const DEFAULT_OPENAI_AUDIO_MODEL = "gpt-4o-mini-transcribe";
 function resolveModel(model) {
@@ -9,6 +9,7 @@ function resolveModel(model) {
 export async function transcribeOpenAiCompatibleAudio(params) {
     const fetchFn = params.fetchFn ?? fetch;
     const baseUrl = normalizeBaseUrl(params.baseUrl, DEFAULT_OPENAI_AUDIO_BASE_URL);
+    const allowPrivate = Boolean(params.baseUrl?.trim());
     const url = `${baseUrl}/audio/transcriptions`;
     const model = resolveModel(params.model);
     const form = new FormData();
@@ -19,28 +20,35 @@ export async function transcribeOpenAiCompatibleAudio(params) {
     });
     form.append("file", blob, fileName);
     form.append("model", model);
-    if (params.language?.trim())
+    if (params.language?.trim()) {
         form.append("language", params.language.trim());
-    if (params.prompt?.trim())
+    }
+    if (params.prompt?.trim()) {
         form.append("prompt", params.prompt.trim());
+    }
     const headers = new Headers(params.headers);
     if (!headers.has("authorization")) {
         headers.set("authorization", `Bearer ${params.apiKey}`);
     }
-    const res = await fetchWithTimeout(url, {
+    const { response: res, release } = await fetchWithTimeoutGuarded(url, {
         method: "POST",
         headers,
         body: form,
-    }, params.timeoutMs, fetchFn);
-    if (!res.ok) {
-        const detail = await readErrorResponse(res);
-        const suffix = detail ? `: ${detail}` : "";
-        throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+    }, params.timeoutMs, fetchFn, allowPrivate ? { ssrfPolicy: { allowPrivateNetwork: true } } : undefined);
+    try {
+        if (!res.ok) {
+            const detail = await readErrorResponse(res);
+            const suffix = detail ? `: ${detail}` : "";
+            throw new Error(`Audio transcription failed (HTTP ${res.status})${suffix}`);
+        }
+        const payload = (await res.json());
+        const text = payload.text?.trim();
+        if (!text) {
+            throw new Error("Audio transcription response missing text");
+        }
+        return { text, model };
     }
-    const payload = (await res.json());
-    const text = payload.text?.trim();
-    if (!text) {
-        throw new Error("Audio transcription response missing text");
+    finally {
+        await release();
     }
-    return { text, model };
 }

package/dist/media-understanding/providers/shared.js

@@ -1,26 +1,31 @@
+import { fetchWithSsrFGuard } from "../../infra/net/fetch-guard.js";
+export { fetchWithTimeout } from "../../utils/fetch-timeout.js";
 const MAX_ERROR_CHARS = 300;
 export function normalizeBaseUrl(baseUrl, fallback) {
     const raw = baseUrl?.trim() || fallback;
     return raw.replace(/\/+$/, "");
 }
-export async function fetchWithTimeout(url, init, timeoutMs, fetchFn) {
-    const controller = new AbortController();
-    const timer = setTimeout(() => controller.abort(), Math.max(1, timeoutMs));
-    try {
-        return await fetchFn(url, { ...init, signal: controller.signal });
-    }
-    finally {
-        clearTimeout(timer);
-    }
+export async function fetchWithTimeoutGuarded(url, init, timeoutMs, fetchFn, options) {
+    return await fetchWithSsrFGuard({
+        url,
+        fetchImpl: fetchFn,
+        init,
+        timeoutMs,
+        policy: options?.ssrfPolicy,
+        lookupFn: options?.lookupFn,
+        pinDns: options?.pinDns,
+    });
 }
 export async function readErrorResponse(res) {
     try {
         const text = await res.text();
         const collapsed = text.replace(/\s+/g, " ").trim();
-        if (!collapsed)
+        if (!collapsed) {
             return undefined;
-        if (collapsed.length <= MAX_ERROR_CHARS)
+        }
+        if (collapsed.length <= MAX_ERROR_CHARS) {
             return collapsed;
+        }
         return `${collapsed.slice(0, MAX_ERROR_CHARS)}…`;
     }
     catch {

package/dist/media-understanding/providers/zai/index.js

@@ -0,0 +1,6 @@
+import { describeImageWithModel } from "../image.js";
+export const zaiProvider = {
+    id: "zai",
+    capabilities: ["image"],
+    describeImage: describeImageWithModel,
+};