fix(agents): detect Kimi model-token-limit overflows

Co-authored-by: Danilo Falcão <danilo@falcao.org>

CHANGELOG.md

@@ -63,6 +63,7 @@ Docs: https://docs.openclaw.ai
 - Agents/Compaction: count auto-compactions only after a non-retry `auto_compaction_end`, keeping session `compactionCount` aligned to completed compactions.
 - Security/CLI: redact sensitive values in `openclaw config get` output before printing config paths, preventing credential leakage to terminal output/history. (#13683) Thanks @SleuthCo.
 - Agents/Moonshot: force `supportsDeveloperRole=false` for Moonshot-compatible `openai-completions` models (provider `moonshot` and Moonshot base URLs), so initial runs no longer send unsupported `developer` roles that trigger `ROLE_UNSPECIFIED` errors. (#21060, #22194) Thanks @ShengFuC.
+- Agents/Kimi: classify Moonshot `Your request exceeded model token limit` failures as context overflows so auto-compaction and user-facing overflow recovery trigger correctly instead of surfacing raw invalid-request errors. (#9562) Thanks @danilofalcao.
 - Install/Discord Voice: make `@discordjs/opus` an optional dependency so `openclaw` install/update no longer hard-fails when native Opus builds fail, while keeping `opusscript` as the runtime fallback decoder for Discord voice flows. (#23737, #23733, #23703) Thanks @jeadland, @Sheetaa, and @Breakyman.
 - Docker/Setup: precreate `$OPENCLAW_CONFIG_DIR/identity` during `docker-setup.sh` so CLI commands that need device identity (for example `devices list`) avoid `EACCES ... /home/node/.openclaw/identity` failures on restrictive bind mounts. (#23948) Thanks @ackson-beep.
 - Exec/Background: stop applying the default exec timeout to background sessions (`background: true` or explicit `yieldMs`) when no explicit timeout is set, so long-running background jobs are no longer terminated at the default timeout boundary. (#23303)

src/agents/pi-embedded-helpers.formatassistanterrortext.test.ts

@@ -29,6 +29,12 @@ describe("formatAssistantErrorText", () => {
     );
     expect(formatAssistantErrorText(msg)).toContain("Context overflow");
   });
+  it("returns context overflow for Kimi 'model token limit' errors", () => {
+    const msg = makeAssistantError(
+      "error, status code: 400, message: Invalid request: Your request exceeded model token limit: 262144 (requested: 291351)",
+    );
+    expect(formatAssistantErrorText(msg)).toContain("Context overflow");
+  });
   it("returns a friendly message for Anthropic role ordering", () => {
     const msg = makeAssistantError('messages: roles must alternate between "user" and "assistant"');
     expect(formatAssistantErrorText(msg)).toContain("Message ordering conflict");

src/agents/pi-embedded-helpers.isbillingerrormessage.test.ts

@@ -178,6 +178,17 @@ describe("isContextOverflowError", () => {
     }
   });
 
+  it("matches Kimi 'model token limit' context overflow errors", () => {
+    const samples = [
+      "Invalid request: Your request exceeded model token limit: 262144 (requested: 291351)",
+      "error, status code: 400, message: Invalid request: Your request exceeded model token limit: 262144 (requested: 291351)",
+      "Your request exceeded model token limit",
+    ];
+    for (const sample of samples) {
+      expect(isContextOverflowError(sample)).toBe(true);
+    }
+  });
+
   it("ignores normal conversation text mentioning context overflow", () => {
     // These are legitimate conversation snippets, not error messages
     expect(isContextOverflowError("Let's investigate the context overflow bug")).toBe(false);

src/agents/pi-embedded-helpers/errors.ts

@@ -51,6 +51,7 @@ export function isContextOverflowError(errorMessage?: string): boolean {
     lower.includes("maximum context length") ||
     lower.includes("prompt is too long") ||
     lower.includes("exceeds model context window") ||
+    lower.includes("model token limit") ||
     (hasRequestSizeExceeds && hasContextWindow) ||
     lower.includes("context overflow:") ||
     (lower.includes("413") && lower.includes("too large"))