Merge branch 'staging' into feat/custom-llm-provider

tests/e2e_builtin_tool_coverage.rs

@@ -205,7 +205,44 @@ mod tests {
     }
 
     // -----------------------------------------------------------------------
-    // Test 5: routine_manual_create_defaults_to_tools_enabled
+    // Test 5: routine_update_fail_delete_fallback
+    // -----------------------------------------------------------------------
+
+    #[tokio::test]
+    async fn routine_update_fail_delete_fallback() {
+        let trace = LlmTrace::from_file(concat!(
+            env!("CARGO_MANIFEST_DIR"),
+            "/tests/fixtures/llm_traces/tools/routine_update_fail_delete_fallback.json"
+        ))
+        .expect("failed to load routine_update_fail_delete_fallback.json");
+
+        let rig = TestRigBuilder::new()
+            .with_trace(trace.clone())
+            .with_auto_approve_tools(true)
+            .build()
+            .await;
+
+        rig.send_message("Try converting a routine trigger, then recover by deleting it")
+            .await;
+        let responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
+
+        rig.verify_trace_expects(&trace, &responses);
+
+        let completed = rig.tool_calls_completed();
+        assert!(
+            completed.iter().any(|(n, ok)| n == "routine_update" && !ok),
+            "routine_update should fail in this regression path: {completed:?}"
+        );
+        assert!(
+            completed.iter().any(|(n, ok)| n == "routine_delete" && *ok),
+            "routine_delete should recover successfully via preserved routine identity: {completed:?}"
+        );
+
+        rig.shutdown();
+    }
+
+    // -----------------------------------------------------------------------
+    // Test 6: routine_manual_create_defaults_to_tools_enabled
     // -----------------------------------------------------------------------
 
     #[tokio::test]
@@ -246,7 +283,7 @@ mod tests {
     }
 
     // -----------------------------------------------------------------------
-    // Test 6: routine_manual_create_explicit_no_tools
+    // Test 7: routine_manual_create_explicit_no_tools
     // -----------------------------------------------------------------------
 
     #[tokio::test]
@@ -287,7 +324,7 @@ mod tests {
     }
 
     // -----------------------------------------------------------------------
-    // Test 7: routine_history
+    // Test 8: routine_history
     // -----------------------------------------------------------------------
 
     #[tokio::test]

tests/fixtures/llm_traces/tools/routine_update_fail_delete_fallback.json

@@ -0,0 +1,70 @@
+{
+  "model_name": "test-routine-update-fail-delete-fallback",
+  "expects": {
+    "tools_used": ["routine_create", "routine_update", "routine_delete"],
+    "tool_results_contain": {
+      "routine_update": "Cannot update schedule or timezone on a non-cron routine.",
+      "routine_delete": "temp-routine"
+    },
+    "min_responses": 1
+  },
+  "steps": [
+    {
+      "response": {
+        "type": "tool_calls",
+        "tool_calls": [
+          {
+            "id": "call_rc_fallback",
+            "name": "routine_create",
+            "arguments": {
+              "name": "temp-routine",
+              "trigger_type": "manual",
+              "prompt": "Temporary routine for fallback test."
+            }
+          }
+        ],
+        "input_tokens": 120,
+        "output_tokens": 40
+      }
+    },
+    {
+      "response": {
+        "type": "tool_calls",
+        "tool_calls": [
+          {
+            "id": "call_ru_fallback",
+            "name": "routine_update",
+            "arguments": {
+              "name": "temp-routine",
+              "schedule": "0 */10 * * * *"
+            }
+          }
+        ],
+        "input_tokens": 200,
+        "output_tokens": 30
+      }
+    },
+    {
+      "response": {
+        "type": "tool_calls",
+        "tool_calls": [
+          {
+            "id": "call_rd_fallback",
+            "name": "routine_delete",
+            "arguments": {}
+          }
+        ],
+        "input_tokens": 300,
+        "output_tokens": 20
+      }
+    },
+    {
+      "response": {
+        "type": "text",
+        "content": "I recovered from the failed update and cleaned up the original routine.",
+        "input_tokens": 380,
+        "output_tokens": 25
+      }
+    }
+  ]
+}