@sema-agent/core 5.7.0 → 5.9.0

package/dist/brain/anthropic.js

@@ -1,9 +1,8 @@
 import {} from "../internal/llm.js";
 import { BrainError } from "./errors.js";
 import { DEGENERATE_MESSAGE, trimDegenerateTail } from "./repetition.js";
-import { createRepetitionPoll, createWalltimeGate, parseStreamedToolArgs } from "./stream-shared.js";
+import { createRepetitionPoll, parseStreamedToolArgs } from "./stream-shared.js";
 import { mintFallbackToolCallId } from "./tool-call-id.js";
-import { WALLTIME_CUTOFF_MESSAGE } from "./walltime.js";
 import { emitBrainTelemetry } from "./status-sink.js";
 import { errorResultMediaNote, IMAGE_OMITTED_NO_VISION, modelSupportsVision, sendableImages } from "./media-degrade.js";
 import { ANTHROPIC_RESERVED, applyExtraBody, stripAuthHeaders } from "./request-params.js";
@@ -233,7 +232,6 @@ export function createAnthropicBrain(config = {}) {
             signal: options?.signal,
             config,
             httpLabel: "anthropic",
-            callDeadlineMs: options?.callDeadlineMs,
             stallTimeouts: options?.stallTimeouts,
             buildRequest: () => {
                 const apiKey = options?.apiKey ?? config.apiKey;
@@ -342,7 +340,6 @@ export function createAnthropicBrain(config = {}) {
                 let degenerate = false;
                 let degenTextBlock;
                 const rep = createRepetitionPoll();
-                const walltime = createWalltimeGate({ callDeadlineMs: options?.callDeadlineMs, isDegenerate: () => degenerate, cancel: () => ctrl.cancel() });
                 let lastDegenCheck = 0;
                 let lastDegenCheckThinking = 0;
                 const detectRep = config.detectRepetition !== false;
@@ -497,10 +494,7 @@ export function createAnthropicBrain(config = {}) {
                             }
                         }
                     },
-                    onDeadline: () => walltime.onDeadline(),
                     onLine(rawLine) {
-                        if (walltime.shouldDropLine())
-                            return;
                         const line = rawLine.trim();
                         if (!line.startsWith("data:"))
                             return;
@@ -576,40 +570,35 @@ export function createAnthropicBrain(config = {}) {
                         const staticReasoningCut = truncatedEmpty && !dynamicCut && reasoningSeen && options?.staticReasoningCutDowngrade === true;
                         const safetyCut = stopReason === "refusal";
                         const contextWindowExceeded = stopReason === "model_context_window_exceeded";
-                        const emptyNoFinish = noUsableContent && stopReason == null && !degenerate && !walltime.cut;
+                        const emptyNoFinish = noUsableContent && stopReason == null && !degenerate;
                         const maxTokensNote = `effective max_tokens=${sentMaxTokens ?? "?"} (from ${sentMaxTokensLane === "options" ? "options.maxTokens" : sentMaxTokensLane === "model" ? "model.maxTokens" : "config default"})`;
-                        const errorMessage = walltime.cut
-                            ? WALLTIME_CUTOFF_MESSAGE
-                            : degenerate
-                                ? DEGENERATE_MESSAGE
-                                : safetyCut
-                                    ? `[refusal] response refused by the model (stop_reason="refusal"${stopDetails?.category ? `, category="${stopDetails.category}"` : ""}) — ${stopDetails?.explanation ?? "the output was withheld for policy and is unreliable"}`
-                                    : contextWindowExceeded
-                                        ? `[invalid_request] model context window exceeded (stop_reason="model_context_window_exceeded") — the conversation no longer fits the model's context window`
-                                        : (toolError ??
-                                            (truncatedEmpty && !dynamicCut && !staticReasoningCut
-                                                ? thinkingRequested
-                                                    ? `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}) — extended thinking likely consumed the entire budget; raise max_tokens or lower thinkingBudgetShare`
-                                                    : reasoningSeen
-                                                        ? `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}) — the model emitted reasoning although no thinking was requested (a budget-ignoring gateway?) and it consumed the entire output budget; raise max_tokens`
-                                                        : `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}); raise max_tokens`
-                                                : emptyNoFinish
-                                                    ? `[stream_torn] model stream ended with no content and no stop_reason — the response was lost (a torn stream or an in-band provider error frame)${malformedFrames > 0 ? ` — ${malformedFrames} unparseable data frame(s) were dropped on this stream (first sample: ${JSON.stringify(malformedSample)})` : ""}`
-                                                    : undefined));
-                        const errored = walltime.cut ||
-                            degenerate ||
+                        const errorMessage = degenerate
+                            ? DEGENERATE_MESSAGE
+                            : safetyCut
+                                ? `[refusal] response refused by the model (stop_reason="refusal"${stopDetails?.category ? `, category="${stopDetails.category}"` : ""}) — ${stopDetails?.explanation ?? "the output was withheld for policy and is unreliable"}`
+                                : contextWindowExceeded
+                                    ? `[invalid_request] model context window exceeded (stop_reason="model_context_window_exceeded") — the conversation no longer fits the model's context window`
+                                    : (toolError ??
+                                        (truncatedEmpty && !dynamicCut && !staticReasoningCut
+                                            ? thinkingRequested
+                                                ? `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}) — extended thinking likely consumed the entire budget; raise max_tokens or lower thinkingBudgetShare`
+                                                : reasoningSeen
+                                                    ? `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}) — the model emitted reasoning although no thinking was requested (a budget-ignoring gateway?) and it consumed the entire output budget; raise max_tokens`
+                                                    : `[length_empty] response truncated at max_tokens with no answer text (${maxTokensNote}); raise max_tokens`
+                                            : emptyNoFinish
+                                                ? `[stream_torn] model stream ended with no content and no stop_reason — the response was lost (a torn stream or an in-band provider error frame)${malformedFrames > 0 ? ` — ${malformedFrames} unparseable data frame(s) were dropped on this stream (first sample: ${JSON.stringify(malformedSample)})` : ""}`
+                                                : undefined));
+                        const errored = degenerate ||
                             safetyCut ||
                             contextWindowExceeded ||
                             emptyNoFinish ||
                             (toolError !== undefined && noUsableContent) ||
                             (truncatedEmpty && !dynamicCut && !staticReasoningCut);
-                        const errorKind = walltime.cut
-                            ? "walltime_cutoff"
-                            : degenerate
-                                ? "degenerate"
-                                : !safetyCut && toolError === undefined && truncatedEmpty && !dynamicCut && !staticReasoningCut
-                                    ? "length_empty"
-                                    : undefined;
+                        const errorKind = degenerate
+                            ? "degenerate"
+                            : !safetyCut && toolError === undefined && truncatedEmpty && !dynamicCut && !staticReasoningCut
+                                ? "length_empty"
+                                : undefined;
                         const finalMessage = {
                             ...partial,
                             content: finalContent.length > 0 ? finalContent : [{ type: "text", text: "" }],

package/dist/brain/open-responses.d.ts

@@ -0,0 +1,11 @@
+import type { Brain } from "../core/types.js";
+import { type StreamEngineConfig } from "./stream-engine.js";
+export interface OpenResponsesBrainConfig extends StreamEngineConfig {
+    baseUrl?: string;
+    apiKey?: string;
+    headers?: Record<string, string>;
+    fetchImpl?: typeof fetch;
+    replayReasoning?: boolean;
+    detectRepetition?: boolean;
+}
+export declare function createOpenResponsesBrain(config?: OpenResponsesBrainConfig): Brain;