nuabase 3.0.1 → 3.1.0

package/dist/esm/index.mjs

@@ -293,21 +293,27 @@ function renderPrompt(cast, enforcement) {
 }
 
 function refusedCast(reason) {
-  return { success: false, error: reason, reason, attempts: 0 };
+  return { success: false, error: reason, reason, attempts: 0, cancelled: false };
 }
 const RETRY_DELAYS_MS = [1e3, 2e3];
 const MAX_ATTEMPTS = RETRY_DELAYS_MS.length + 1;
-async function runCast(engine, request, logger) {
+async function runCast(engine, request, logger, controls = {}) {
   const validate = validatorFor(request.schema);
   let plan = planAttempt(request, chooseEnforcement(engine, request.jsonSchema));
   let lastFailure = { error: "", prompt: plan.prompt };
   for (let attempt = 1; attempt <= MAX_ATTEMPTS; attempt++) {
-    const outcome = await engine.attempt({
-      prompt: plan.prompt.full,
-      reusablePrefix: plan.prompt.reusablePrefix,
-      maxTokens: request.maxTokens,
-      enforcement: plan.enforcement
-    });
+    if (controls.signal?.aborted) {
+      return cancelledCast(attempt - 1, attempt > 1 ? lastFailure.prompt : void 0);
+    }
+    const outcome = await engine.attempt(
+      {
+        prompt: plan.prompt.full,
+        reusablePrefix: plan.prompt.reusablePrefix,
+        maxTokens: request.maxTokens,
+        enforcement: plan.enforcement
+      },
+      controls
+    );
     const verdict = judgeOutcome(outcome, validate);
     if (verdict.kind === "accept") {
       return {
@@ -320,7 +326,17 @@ async function runCast(engine, request, logger) {
       };
     }
     if (verdict.kind === "give-up") {
-      return { success: false, error: verdict.error, reason: verdict.error, attempts: attempt, prompt: plan.prompt };
+      return {
+        success: false,
+        error: verdict.error,
+        reason: verdict.error,
+        attempts: attempt,
+        cancelled: false,
+        prompt: plan.prompt
+      };
+    }
+    if (verdict.kind === "cancelled") {
+      return cancelledCast(attempt, plan.prompt);
     }
     lastFailure = { error: verdict.error, prompt: plan.prompt };
     if (verdict.kind === "retry-in-prompt") {
@@ -334,7 +350,7 @@ async function runCast(engine, request, logger) {
     if (attempt < MAX_ATTEMPTS) {
       const delayMs = RETRY_DELAYS_MS[attempt - 1];
       logger.warn("LLM call attempt failed; retrying", { attempt, delayMs, error: verdict.error });
-      await delay(delayMs);
+      await delay(delayMs, controls.signal);
     }
   }
   return {
@@ -342,6 +358,7 @@ async function runCast(engine, request, logger) {
     error: `LLM call failed after ${MAX_ATTEMPTS} attempts. Last error: ${lastFailure.error}`,
     reason: lastFailure.error,
     attempts: MAX_ATTEMPTS,
+    cancelled: false,
     prompt: lastFailure.prompt
   };
 }
@@ -386,6 +403,8 @@ function verdictForFailure(failure) {
       return { kind: "retry-in-prompt", error: failure.message };
     case "fatal":
       return { kind: "give-up", error: failure.message };
+    case "cancelled":
+      return { kind: "cancelled" };
   }
 }
 function readAnswer(answer) {
@@ -421,8 +440,20 @@ function readStructuredAnswer(envelope) {
 function errorMessage(error) {
   return error instanceof Error ? error.message : String(error);
 }
-function delay(ms) {
-  return new Promise((resolve) => setTimeout(resolve, ms));
+function cancelledCast(attempts, prompt) {
+  const reason = "The call was cancelled.";
+  return { success: false, error: reason, reason, attempts, cancelled: true, prompt };
+}
+function delay(ms, signal) {
+  return new Promise((resolve) => {
+    const done = () => {
+      clearTimeout(timer);
+      signal?.removeEventListener("abort", done);
+      resolve();
+    };
+    const timer = setTimeout(done, ms);
+    signal?.addEventListener("abort", done, { once: true });
+  });
 }
 
 const DEFAULT_MAX_TOKENS = 4096;
@@ -445,7 +476,10 @@ class NuaLlmClient {
       jsonSchema,
       maxTokens: params.maxTokens ?? DEFAULT_MAX_TOKENS
     };
-    return runCast(route.engine, request, this.engines.logger);
+    return runCast(route.engine, request, this.engines.logger, {
+      onOutput: params.onOutput,
+      signal: params.signal
+    });
   }
   async castArray(params) {
     const { primaryKey, outputName, schema } = params.output;
@@ -468,7 +502,10 @@ class NuaLlmClient {
       jsonSchema,
       maxTokens: params.maxTokens ?? DEFAULT_MAX_TOKENS
     };
-    return runCast(route.engine, request, this.engines.logger);
+    return runCast(route.engine, request, this.engines.logger, {
+      onOutput: params.onOutput,
+      signal: params.signal
+    });
   }
 }
 
@@ -903,7 +940,8 @@ async function callProvider(call, logger) {
     const response = await fetch(request.url, {
       method,
       headers: request.headers ?? {},
-      body: toFetchableBody(request.body)
+      body: toFetchableBody(request.body),
+      signal: call.signal
     });
     status = response.status;
     const reply = await call.parseResponse(response);
@@ -949,7 +987,7 @@ class HttpEngine {
     if (!providerConfigs[provider].strictSchemaModels?.has(model)) return null;
     return toStrictSchema(envelopeSchema);
   }
-  async attempt(request) {
+  async attempt(request, { signal } = {}) {
     const { provider, model, apiKey } = this.target;
     const config = providerConfigs[provider];
     const responseSchema = request.enforcement.kind === "native" ? request.enforcement.schema : void 0;
@@ -970,11 +1008,15 @@ class HttpEngine {
         ),
         parseResponse: config.parseResponse,
         responseLength: (reply) => reply.text.length,
-        usage: (reply) => reply.usage
+        usage: (reply) => reply.usage,
+        signal
       },
       this.logger
     );
     if (call.kind === "failed") {
+      if (signal?.aborted) {
+        return { kind: "failed", failure: { kind: "cancelled", message: "The call was cancelled." } };
+      }
       return { kind: "failed", failure: failureForStatus(call.status, call.message, responseSchema !== void 0) };
     }
     const answer = responseSchema ? readEnvelope(call.reply.text) : { kind: "text", text: call.reply.text };
@@ -1077,7 +1119,9 @@ class Nua {
     const result = await this.client.castValue({
       model: options?.model,
       input: { prompt, data: options?.input ?? null },
-      output: { name: outputName, schema: outputSchema }
+      output: { name: outputName, schema: outputSchema },
+      onOutput: options?.onOutput,
+      signal: options?.signal
     });
     return toDirectResult(result, Date.now() - startTime);
   }
@@ -1100,7 +1144,9 @@ class Nua {
     const result = await this.client.castArray({
       model: options.model,
       input: { prompt, data: options.input },
-      output
+      output,
+      onOutput: options.onOutput,
+      signal: options.signal
     });
     return toDirectResult(result, Date.now() - startTime);
   }
@@ -1113,8 +1159,8 @@ function enginesFor(config) {
 }
 function toDirectResult(result, latencyMs) {
   if (!result.success) {
-    const { error, reason, attempts } = result;
-    return { success: false, error, reason, attempts, source: "direct", latencyMs };
+    const { error, reason, attempts, cancelled } = result;
+    return { success: false, error, reason, attempts, cancelled, source: "direct", latencyMs };
   }
   return {
     success: true,