@kortyx/hooks 0.31.0 → 0.32.1

package/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## [0.32.1](https://github.com/kortyx-io/kortyx/compare/hooks-v0.32.0...hooks-v0.32.1) (2026-10-09)
+
+
+### Dependencies
+
+* The following workspace dependencies were updated
+  * dependencies
+    * @kortyx/core bumped to 0.13.0
+    * @kortyx/providers bumped to 0.9.1
+
+## [0.32.0](https://github.com/kortyx-io/kortyx/compare/hooks-v0.31.0...hooks-v0.32.0) (2026-10-08)
+
+
+### Features
+
+* **hooks:** support mixed tools outputs and interrupts ([#297](https://github.com/kortyx-io/kortyx/issues/297)) ([0aa4aa6](https://github.com/kortyx-io/kortyx/commit/0aa4aa6b08cd2ef44f603b8dbe8e35b30c54cbdc))
+
 ## [0.31.0](https://github.com/kortyx-io/kortyx/compare/hooks-v0.30.2...hooks-v0.31.0) (2026-10-08)
 
 

package/README.md

@@ -49,6 +49,31 @@ and `result.output` remain available during migration, but are deprecated and
 scheduled for removal in the next major release. TypeSafe Jev's provider-native
 decision schema is a temporary exception until a non-tool replacement ships.
 
+## Mixed tools, outputs, and interrupts
+
+A model turn may request multiple domain tools, `emit` outputs, and interrupt
+contracts together. They run in the requested order, so an emitted card can
+appear before a question about it. Each interrupt pauses the remaining calls;
+resume reuses completed tool results, emissions, and human responses. Tool
+approval still applies, and `interrupts.maxRequests` and `outputs.maxEmissions`
+still bound their respective calls.
+
+A terminal `return` runs after every other call in that turn, regardless of its
+position. When an output follows domain or interrupt results from the same turn,
+Kortyx generates its value in a separate schema-constrained model pass using
+those results, rather than publishing the original draft. Streamed contracts use
+their normal streamed generation pass; other contracts use a buffered pass.
+These passes, including failed attempts, consume `toolExecution.maxSteps` across
+resume. Budget exhaustion throws a `ProviderRequestError` with code
+`REASON_OUTPUT_BUDGET_EXHAUSTED` and guidance to increase `maxSteps`.
+
+There is one terminal `result.returned` value. If the model requests multiple
+returns, each receives an error result asking the model to select one. Other
+calls proceed normally, and completed calls are not replayed for correction.
+Correction consumes the remaining `maxSteps`; exhaustion throws a typed
+`REASON_OUTPUT_CONTRACT_CORRECTION_EXHAUSTED` failure. Multiple `emit` outputs
+are supported without this restriction.
+
 ## Runtime Resume Behavior
 
 On resume, the node function is replayed from the top.

package/dist/index.d.ts

@@ -96,6 +96,8 @@ type HookNodeRuntimeContext = {
     config: NodeConfig;
     emit: (event: string, payload: unknown) => void;
     awaitInterrupt: (args: InterruptInput) => InterruptResumeValue;
+    /** Consume an already-resolved engine interrupt when a durable hook skips it. */
+    replayInterrupt?: ((args: InterruptInput) => void) | undefined;
     callWorkflow?: WorkflowCallService;
     workflowCallTelemetry?: KortyxTelemetryConfig | undefined;
 };
@@ -258,6 +260,7 @@ type UseReasonInterruptConfig<TRequest extends InterruptInput = InterruptInput,
     schemaVersion?: string | undefined;
 };
 type UseReasonToolExecution = {
+    /** Model-pass budget, including output generation and correction across resume. */
     maxSteps?: number | undefined;
     approval?: boolean | Record<string, boolean> | undefined;
     emit?: boolean | Record<string, boolean> | undefined;