@openclaw/codex 2026.7.2-beta.3 → 2026.7.2-beta.5

package/dist/media-understanding-provider.js

@@ -1,2 +1,174 @@
-import { t as buildCodexMediaUnderstandingProvider } from "./media-understanding-provider-IPNNQre6.js";
+import { t as runBoundedCodexAppServerTurn } from "./bounded-turn-FEbUXoYT.js";
+import { validateJsonSchemaValue } from "openclaw/plugin-sdk/json-schema-runtime";
+//#region extensions/codex/media-understanding-provider.ts
+/**
+* Codex-backed media understanding provider for bounded image description and
+* structured extraction turns.
+*/
+const CODEX_MEDIA_PROVIDER_ID = "codex";
+const DEFAULT_CODEX_IMAGE_MODEL = "gpt-5.6-sol";
+const DEFAULT_CODEX_IMAGE_PROMPT = "Describe the image.";
+/**
+* Builds the media-understanding provider that delegates image tasks to an
+* isolated Codex app-server session.
+*/
+function buildCodexMediaUnderstandingProvider(options = {}) {
+	return {
+		id: CODEX_MEDIA_PROVIDER_ID,
+		capabilities: ["image"],
+		defaultModels: { image: DEFAULT_CODEX_IMAGE_MODEL },
+		describeImage: async (req) => describeCodexImages({
+			images: [{
+				buffer: req.buffer,
+				fileName: req.fileName,
+				mime: req.mime
+			}],
+			provider: req.provider,
+			model: req.model,
+			prompt: req.prompt,
+			maxTokens: req.maxTokens,
+			timeoutMs: req.timeoutMs,
+			...req.signal ? { signal: req.signal } : {},
+			profile: req.profile,
+			preferredProfile: req.preferredProfile,
+			authStore: req.authStore,
+			agentDir: req.agentDir,
+			cfg: req.cfg
+		}, options),
+		describeImages: async (req) => describeCodexImages(req, options),
+		extractStructured: async (req) => extractCodexStructured(req, options)
+	};
+}
+async function describeCodexImages(req, options) {
+	const model = req.model.trim();
+	if (!model) throw new Error("Codex image understanding requires model id.");
+	req.signal?.throwIfAborted();
+	const { text } = await runBoundedCodexAppServerTurn({
+		config: req.cfg,
+		model: {
+			mode: "required",
+			id: model
+		},
+		profile: req.profile,
+		timeoutMs: req.timeoutMs,
+		signal: req.signal,
+		agentDir: req.agentDir,
+		authProfileStore: req.authStore,
+		options,
+		taskLabel: "image understanding",
+		developerInstructions: "You are OpenClaw's bounded image-understanding worker. Describe only the provided image content. Do not call tools, edit files, or ask follow-up questions.",
+		input: [{
+			type: "text",
+			text: buildCodexImagePrompt(req),
+			text_elements: []
+		}, ...req.images.map((image) => ({
+			type: "image",
+			url: `data:${image.mime ?? "image/png"};base64,${image.buffer.toString("base64")}`
+		}))],
+		requiredModalities: ["text", "image"],
+		isolation: "configured-transport"
+	});
+	return {
+		text,
+		model
+	};
+}
+async function extractCodexStructured(req, options) {
+	const model = req.model.trim();
+	if (!model) throw new Error("Codex structured extraction requires model id.");
+	if (!req.instructions.trim()) throw new Error("Codex structured extraction requires instructions.");
+	if (req.input.length === 0) throw new Error("Codex structured extraction requires at least one input.");
+	if (!req.input.some((entry) => entry.type === "image")) throw new Error("Codex structured extraction requires at least one image input.");
+	req.signal?.throwIfAborted();
+	const { text } = await runBoundedCodexAppServerTurn({
+		config: req.cfg,
+		model: {
+			mode: "required",
+			id: model
+		},
+		profile: req.profile,
+		timeoutMs: req.timeoutMs,
+		signal: req.signal,
+		agentDir: req.agentDir,
+		authProfileStore: req.authStore,
+		options,
+		taskLabel: "structured extraction",
+		developerInstructions: "You are OpenClaw's bounded structured-extraction worker. Return only the requested extraction. Do not call tools, edit files, ask follow-up questions, or include secrets.",
+		input: buildCodexStructuredInput(req),
+		requiredModalities: requiredStructuredModalities(),
+		isolation: "configured-transport"
+	});
+	return normalizeStructuredExtractionResult({
+		text,
+		model,
+		provider: req.provider,
+		req
+	});
+}
+function buildCodexImagePrompt(req) {
+	const prompt = req.prompt?.trim() || DEFAULT_CODEX_IMAGE_PROMPT;
+	if (req.images.length <= 1) return prompt;
+	return `${prompt}\n\nAnalyze all ${req.images.length} images together.`;
+}
+function requiredStructuredModalities() {
+	return ["text", "image"];
+}
+function buildCodexStructuredInput(req) {
+	return [{
+		type: "text",
+		text: buildStructuredExtractionPrompt(req),
+		text_elements: []
+	}, ...req.input.map((entry) => {
+		if (entry.type === "text") return {
+			type: "text",
+			text: entry.text,
+			text_elements: []
+		};
+		return {
+			type: "image",
+			url: `data:${entry.mime ?? "image/png"};base64,${entry.buffer.toString("base64")}`
+		};
+	})];
+}
+function buildStructuredExtractionPrompt(req) {
+	return [
+		req.instructions.trim(),
+		req.schemaName ? `Schema name: ${req.schemaName}` : void 0,
+		req.jsonSchema ? `JSON schema:\n${JSON.stringify(req.jsonSchema)}` : void 0,
+		req.jsonMode === false ? "Return the extraction as concise text." : "Return valid JSON only. Do not wrap the JSON in Markdown fences."
+	].filter((part) => Boolean(part)).join("\n\n");
+}
+function isJsonSchemaObject(value) {
+	return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+function normalizeStructuredExtractionResult(params) {
+	const result = {
+		text: params.text,
+		model: params.model,
+		provider: params.provider,
+		contentType: params.req.jsonMode === false ? "text" : "json"
+	};
+	if (params.req.jsonMode !== false) {
+		try {
+			result.parsed = JSON.parse(params.text);
+		} catch {
+			throw new Error("Codex structured extraction returned invalid JSON.");
+		}
+		if (isJsonSchemaObject(params.req.jsonSchema)) {
+			const validation = validateJsonSchemaValue({
+				schema: params.req.jsonSchema,
+				cacheKey: "codex.media-understanding.extractStructured",
+				value: result.parsed,
+				cache: false
+			});
+			if (!validation.ok) {
+				const message = validation.errors.map((error) => error.text).join("; ") || "invalid";
+				throw new Error(`Codex structured extraction JSON did not match schema: ${message}`);
+			}
+			result.parsed = validation.value;
+		}
+	}
+	return result;
+}
+//#endregion
 export { buildCodexMediaUnderstandingProvider };

package/dist/{models-DD5zBdX5.js → models-BA01NEez.js}

@@ -1,4 +1,4 @@
-import { h as readCodexModelListResponse } from "./transcript-mirror-D9rTxx2P.js";
+import { c as readCodexModelListResponse } from "./protocol-validators-Dm4eXZmt.js";
 import { uniqueStrings } from "openclaw/plugin-sdk/string-coerce-runtime";
 //#region extensions/codex/src/app-server/models.ts
 /**
@@ -40,7 +40,7 @@ async function listAllCodexAppServerModels(options = {}) {
 async function withCodexAppServerModelClient(options, run) {
 	const timeoutMs = options.timeoutMs ?? 2500;
 	const useSharedClient = options.sharedClient !== false;
-	const { createIsolatedCodexAppServerClient, getLeasedSharedCodexAppServerClient, releaseLeasedSharedCodexAppServerClient } = await import("./shared-client-CSXLtCLE.js").then((n) => n.f);
+	const { createIsolatedCodexAppServerClient, getLeasedSharedCodexAppServerClient, releaseLeasedSharedCodexAppServerClient } = await import("./shared-client-BVKE40c-.js").then((n) => n.p);
 	const client = useSharedClient ? await getLeasedSharedCodexAppServerClient({
 		startOptions: options.startOptions,
 		timeoutMs,

package/dist/{notification-correlation-C8DVQ_Bq.js → notification-correlation-Bj_Ak_jI.js}

@@ -1,6 +1,6 @@
-import { Z as isJsonObject } from "./shared-client-CSXLtCLE.js";
-import { E as resolveCodexSupervisionAppServerRuntimeOptions, b as resolveCodexAppServerRuntimeOptions, y as readCodexPluginConfig } from "./session-binding-Bmt20HfB.js";
-import { t as buildCodexAppServerConnectionFingerprint } from "./plugin-app-cache-key-DJbhLYSK.js";
+import { V as isJsonObject } from "./shared-client-BVKE40c-.js";
+import { T as readCodexPluginConfig, g as resolveCodexSupervisionAppServerRuntimeOptions, p as resolveCodexAppServerRuntimeOptions } from "./session-binding-DlVQ-Pxs.js";
+import { t as buildCodexAppServerConnectionFingerprint } from "./plugin-app-cache-key-DSXX-rXO.js";
 //#region extensions/codex/src/app-server/binding-connection.ts
 /** Requires the native model pair after a supervised pending branch has materialized. */
 function requireCodexSupervisionModelSelection(binding) {

package/dist/{plugin-app-cache-key-DJbhLYSK.js → plugin-app-cache-key-DSXX-rXO.js}

@@ -1,12 +1,12 @@
-import { D as resolveCodexAppServerHomeDir } from "./shared-client-CSXLtCLE.js";
-import { S as resolveCodexAppServerUserHomeDir } from "./session-binding-Bmt20HfB.js";
+import { U as resolveCodexAppServerHomeDir } from "./shared-client-BVKE40c-.js";
+import { x as resolveCodexAppServerUserHomeDir } from "./session-binding-DlVQ-Pxs.js";
 import { createRequire } from "node:module";
 import { isFutureDateTimestampMs, resolveDateTimestampMs, resolveExpiresAtMsFromDurationMs } from "openclaw/plugin-sdk/number-runtime";
-import { truncateUtf16Safe } from "openclaw/plugin-sdk/text-utility-runtime";
-import { createHash } from "node:crypto";
-import { isRecord } from "openclaw/plugin-sdk/string-coerce-runtime";
 import { OPENCLAW_VERSION, embeddedAgentLog } from "openclaw/plugin-sdk/agent-harness-runtime";
+import { createHash } from "node:crypto";
 import { readPluginPackageVersion } from "openclaw/plugin-sdk/extension-shared";
+import { isRecord } from "openclaw/plugin-sdk/string-coerce-runtime";
+import { truncateUtf16Safe } from "openclaw/plugin-sdk/text-utility-runtime";
 //#region extensions/codex/src/app-server/app-inventory-cache.ts
 /**
 * Process-local cache for Codex app-server app inventories, keyed by runtime