fix: keep media provider inventory internal (#75550)

Summary:
- The branch removes the compact image/video provider-inventory output bypass, adds media handler regression tests for hidden and verbose modes, and adds an Unreleased changelog fix entry.
- Reproducibility: yes. On current main, a synthetic image_generate or video_generate list result with details ... ut false reaches emitToolOutput; the existing media handler test locks in that old video_generate behavior.

ClawSweeper fixups:
- Included follow-up commit: chore: rerun ci
- Included follow-up commit: chore: move changelog entry below media fixes

Validation:
- ClawSweeper review passed for head 56069df903.
- Required merge gates passed before the squash merge.

Prepared head SHA: 56069df903
Review: https://github.com/openclaw/openclaw/pull/75550#issuecomment-4358608888

Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>

CHANGELOG.md

@@ -474,6 +474,7 @@ Docs: https://docs.openclaw.ai
 - Telegram/agents: keep typing indicators and optional generation tools off the reply critical path, so fresh Telegram replies no longer stall while provider catalogs and media models load. (#75360) Thanks @obviyus.
 - Agents/commitments: run hidden follow-up extraction on the configured agent/default model instead of falling back to direct OpenAI, so OpenAI Codex OAuth-only gateways no longer spam background API-key failures. Fixes #75334. Thanks @sene1337.
 - Agents/media: keep async music generation completions on the requester-session wake path even when direct-send completion is enabled, so finished audio stays agent-mediated while video can still opt into direct channel delivery. (#75335) Thanks @vincentkoc.
+- Agents/media: keep image and video provider inventory internal when tool output is hidden, so shared chat surfaces no longer expose provider/model/auth-hint details from list results. Fixes #75166. Thanks @MkDev11.
 - Security/config-audit: redact CLI argv and execArgv secrets before persisting config audit records, covering write, observe, and recovery paths. Fixes #60826. Thanks @koshaji.
 - Gateway/models: keep default and configured model-list views responsive when provider catalog discovery stalls, without hiding real catalog load failures, while `--all` still waits for the exact full catalog. Fixes #75297; refs #74404. Thanks @lisandromachado and @najef1979-code.
 - Plugins/runtime-deps: accept already materialized package-level runtime-deps supersets as converged, so later lazy plugin activation no longer prunes and relaunches `pnpm install` after gateway startup pre-staging, reducing event-loop pressure from repeated runtime-deps repair on packaged installs. Fixes #75283; refs #75297 and #72338. Thanks @brokemac79, @lisandromachado, and @midhunmonachan.

src/agents/pi-embedded-subscribe.handlers.tools.media.test.ts

@@ -142,6 +142,44 @@ async function handleCaseVariantBuiltinMedia(mediaPathOrUrl: string) {
   return ctx;
 }
 
+const providerInventoryText = [
+  "openai: default=sora-2 | models=sora-2",
+  "google: default=veo-3.1-fast-generate-preview | models=veo-3.1-fast-generate-preview",
+].join("\n");
+
+async function handleProviderInventoryListResult(params: {
+  toolName: "image_generate" | "video_generate";
+  shouldEmitToolOutput: boolean;
+}) {
+  const ctx = createMockContext({
+    shouldEmitToolOutput: params.shouldEmitToolOutput,
+    onToolResult: vi.fn(),
+    toolResultFormat: "plain",
+  });
+
+  await handleToolExecutionEnd(ctx, {
+    type: "tool_execution_end",
+    toolName: params.toolName,
+    toolCallId: "tc-1",
+    isError: false,
+    result: {
+      content: [{ type: "text", text: providerInventoryText }],
+      details: {
+        providers: [
+          { id: "openai", defaultModel: "sora-2", models: ["sora-2"] },
+          {
+            id: "google",
+            defaultModel: "veo-3.1-fast-generate-preview",
+            models: ["veo-3.1-fast-generate-preview"],
+          },
+        ],
+      },
+    },
+  });
+
+  return ctx;
+}
+
 describe("handleToolExecutionEnd media emission", () => {
   it("does not warn for read tool when path is provided via file_path alias", async () => {
     const ctx = createMockContext();
@@ -424,52 +462,36 @@ describe("handleToolExecutionEnd media emission", () => {
     expect(ctx.state.pendingToolMediaUrls).toEqual(["/tmp/generated.png"]);
   });
 
-  it("emits provider inventory output for compact video_generate list results", async () => {
-    const ctx = createMockContext({
-      shouldEmitToolOutput: false,
-      onToolResult: vi.fn(),
-      toolResultFormat: "plain",
-    });
+  it.each(["image_generate", "video_generate"] as const)(
+    "keeps %s provider inventory internal when tool output is hidden",
+    async (toolName) => {
+      const ctx = await handleProviderInventoryListResult({
+        toolName,
+        shouldEmitToolOutput: false,
+      });
 
-    await handleToolExecutionEnd(ctx, {
-      type: "tool_execution_end",
-      toolName: "video_generate",
-      toolCallId: "tc-1",
-      isError: false,
-      result: {
-        content: [
-          {
-            type: "text",
-            text: [
-              "openai: default=sora-2 | models=sora-2",
-              "google: default=veo-3.1-fast-generate-preview | models=veo-3.1-fast-generate-preview",
-            ].join("\n"),
-          },
-        ],
-        details: {
-          providers: [
-            { id: "openai", defaultModel: "sora-2", models: ["sora-2"] },
-            {
-              id: "google",
-              defaultModel: "veo-3.1-fast-generate-preview",
-              models: ["veo-3.1-fast-generate-preview"],
-            },
-          ],
-        },
-      },
-    });
+      expect(ctx.emitToolOutput).not.toHaveBeenCalled();
+      expect(ctx.state.pendingToolMediaUrls).toEqual([]);
+    },
+  );
 
-    expect(ctx.emitToolOutput).toHaveBeenCalledWith(
-      "video_generate",
-      undefined,
-      [
-        "openai: default=sora-2 | models=sora-2",
-        "google: default=veo-3.1-fast-generate-preview | models=veo-3.1-fast-generate-preview",
-      ].join("\n"),
-      expect.any(Object),
-    );
-    expect(ctx.state.pendingToolMediaUrls).toEqual([]);
-  });
+  it.each(["image_generate", "video_generate"] as const)(
+    "emits %s provider inventory when verbose tool output is enabled",
+    async (toolName) => {
+      const ctx = await handleProviderInventoryListResult({
+        toolName,
+        shouldEmitToolOutput: true,
+      });
+
+      expect(ctx.emitToolOutput).toHaveBeenCalledWith(
+        toolName,
+        undefined,
+        providerInventoryText,
+        expect.any(Object),
+      );
+      expect(ctx.state.pendingToolMediaUrls).toEqual([]);
+    },
+  );
 
   it("does NOT emit media for error results", async () => {
     const onToolResult = vi.fn();

src/agents/pi-embedded-subscribe.handlers.tools.ts

@@ -361,30 +361,6 @@ async function collectEmittedToolOutputMediaUrls(
   return filterToolResultMediaUrls(toolName, mediaUrls, result);
 }
 
-const COMPACT_PROVIDER_INVENTORY_TOOLS = new Set(["image_generate", "video_generate"]);
-
-function hasProviderInventoryDetails(result: unknown): boolean {
-  if (!result || typeof result !== "object") {
-    return false;
-  }
-  const details = readToolResultDetailsRecord(result);
-  return Array.isArray(details?.providers);
-}
-
-function shouldEmitCompactToolOutput(params: {
-  toolName: string;
-  result: unknown;
-  outputText?: string;
-}): boolean {
-  if (!COMPACT_PROVIDER_INVENTORY_TOOLS.has(params.toolName)) {
-    return false;
-  }
-  if (!hasProviderInventoryDetails(params.result)) {
-    return false;
-  }
-  return Boolean(params.outputText?.trim());
-}
-
 function readExecApprovalPendingDetails(result: unknown): {
   approvalId: string;
   approvalSlug: string;
@@ -560,8 +536,7 @@ async function emitToolResultOutput(params: {
       isToolError,
       hasDeliverableStructuredMedia: hasStructuredMedia && mediaUrls.length > 0,
       builtinToolNames: ctx.builtinToolNames,
-    }) &&
-    (ctx.shouldEmitToolOutput() || shouldEmitCompactToolOutput({ toolName, result, outputText }));
+    }) && ctx.shouldEmitToolOutput();
   if (shouldEmitOutput) {
     if (outputText) {
       ctx.emitToolOutput(rawToolName, meta, outputText, result);