fix(telegram): avoid leaking acknowledged failed tool warnings

CHANGELOG.md

@@ -36,7 +36,7 @@ Docs: https://docs.openclaw.ai
 - CLI/status: fall back to a bounded local `status` RPC when loopback detail probes time out or report unknown capability, so reachable local gateways are no longer marked unreachable by slow read diagnostics. Fixes #73535; refs #48360, #62762, #51357, and #42019. Thanks @RacecarGuy, @justinschille, @DJBlackhawk, @tianyaqpzm, and @0xrsydn.
 - CLI/gateway: reuse cached paired-device auth during `gateway probe` and report post-connect diagnostic failures as degraded reachability, so healthy local gateways are no longer marked unreachable after loopback auth or read timeouts. Fixes #48360. Thanks @RacecarGuy.
 - Channels/Discord: give Discord Gateway WebSocket handshakes a 30s timeout so stalled TLS/network transitions emit an error and Carbon can continue its reconnect loop instead of leaving the bot silent until restart. Refs #50046. Thanks @codexGW.
-- Channels/Telegram: suppress standalone failed edit/write warning payloads when an assistant error reply already covers the turn, while keeping unresolved mutating failures visible behind success-looking replies. Fixes #39631; carries forward #39636 and #39717. Thanks @Bartok9 and @Bortlesboat.
+- Channels/Telegram: suppress standalone failed edit/write warning payloads when a user-facing assistant error reply already covers the turn, while keeping unresolved mutating failures visible behind success-looking or suppressed-error replies. Fixes #39631; refs #73750; carries forward #39636 and #39717; leaves #39406 for configurable delivery policy. Thanks @Bartok9 and @Bortlesboat.
 - NVIDIA/NIM: persist the `NVIDIA_API_KEY` provider marker and mark bundled NVIDIA Chat Completions models as string-content compatible, so NIM models load from `models.json` and OpenAI-compatible subagent calls send plain text content. Fixes #73013 and #50107; refs #73014. Thanks @bautrey, @iot2edge, @ifearghal, and @futhgar.
 - Channels/Discord: let text-only configs drop the `GuildVoiceStates` gateway intent and expose a bounded `/gateway/bot` metadata timeout with rate-limited fallback logs, reducing idle CPU and warning floods. Fixes #73709 and #73585. Thanks @sanchezm86 and @trac3r00.
 - Agents/sessions: mark same-turn `sessions_send` and A2A reply prompts with an inter-session `isUser=false` envelope before they reach the model, so foreign session output no longer lands as bare active user text. Fixes #73702; refs #73698, #73609, #73595, and #73622. Thanks @alvelda.

src/agents/pi-embedded-runner/run/payloads.errors.test.ts

@@ -94,6 +94,21 @@ describe("buildEmbeddedRunPayloads", () => {
     expect(payloads.some((payload) => payload.text?.includes("missing"))).toBe(false);
   });
 
+  it("keeps mutating tool warnings when assistant error artifacts are not user-facing", () => {
+    const payloads = buildPayloads({
+      assistantTexts: [errorJson],
+      lastAssistant: makeAssistant({}),
+      lastToolError: { toolName: "edit", error: "file missing" },
+      didSendDeterministicApprovalPrompt: true,
+      sessionKey: "agent:main:telegram:direct:u123",
+    });
+
+    expectSingleToolErrorPayload(payloads, {
+      title: "Edit",
+      absentDetail: "missing",
+    });
+  });
+
   it("suppresses pretty-printed error JSON that differs from the errorMessage", () => {
     const payloads = buildPayloads({
       assistantTexts: [errorJsonPretty],