agent-lattice 0.24.0 → 0.25.1

package/README.md

@@ -544,6 +544,15 @@ The structure is enforced by the harness, not by prompt discipline:
 - The name is reserved: registering your own `submit_output` tool while
   `outputSchema` is set throws from `createAgent`/`addTools`.
 
+By default a valid submission ends the run immediately — the bounded, cheapest
+behavior for schema-delivering workers. For human-facing sessions that should
+close with a natural-language summary, set `submitOutputEndTurn: false`: the
+submission is recorded (re-submitting revises it, last one wins), the tool
+result goes back to the model, and the run ends when the model stops. A text
+ending after a submission succeeds with the last submission as
+`structuredResult`; ending without any submission still fails with
+`error_missing_output`. *Requires 0.25.0 or later.*
+
 Unlike `outputFormat` (which relies on the provider's
 `response_format`/`json_schema` support — DeepSeek ignores it, see
 [Provider Compatibility](https://docs.claude-code-sdk.com/reference/provider-compatibility/)),
@@ -1645,3 +1654,11 @@ returns. Both fields are optional and absent when the client does not report
 them.
 
 *Requires 0.16.0 or later.*
+
+## Invalid tool argument JSON
+
+*Requires 0.25.1 or later.*
+
+When a completed Anthropic-compatible stream contains malformed tool argument JSON, the SDK does not execute the tool. It returns a matching `tool_result` with `is_error: true`, identifies the JSON syntax problem (including a character position when available), lists required top-level fields, and asks the model to regenerate complete arguments from the tool schema. Raw argument excerpts are not echoed in the error.
+
+Incomplete intermediate chunks are not errors if the final JSON is valid. Valid JSON objects, including `{}`, still go through normal schema validation. Valid JSON values that are not objects are rejected before execution. Existing turn limits still apply; this feedback does not guarantee that a model will correct its response.

package/dist/index.d.ts

@@ -603,6 +603,19 @@ export type AgentOptions<TContext = unknown> = {
      * with the same name throws).
      */
     outputSchema?: OutputSchema;
+    /**
+     * Whether a validated `submit_output` call ends the run. Only meaningful with
+     * `outputSchema`; default `true` — submitting finishes the run immediately
+     * with subtype "success", the bounded and cheapest behavior for
+     * schema-delivering workers. Set `false` to keep the loop going after a
+     * submission (e.g. human-facing sessions that should close with a
+     * natural-language summary): the submission is recorded — re-submitting
+     * revises it, last one wins — the tool result goes back to the model, and
+     * the run ends when the model stops. A text ending after a submission
+     * succeeds with the last submission as `SDKResultMessage.structuredResult`;
+     * ending without any submission still fails with `error_missing_output`.
+     */
+    submitOutputEndTurn?: boolean;
     /** Lifecycle callbacks that rewrite tool results and outgoing model requests. */
     hooks?: AgentHooks<TContext>;
     /**