@gajae-code/agent-core 0.16.4 → 0.16.6

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [Unreleased]
 
+## [0.16.6] - 2026-09-07
+
+## [0.16.5] - 2026-09-07
+
+- Compaction summary, turn-prefix summary, and handoff generation now clamp their reasoning effort to the model they are about to call instead of hard-coding `high`. A reasoning-capable model on a transport without reasoning control (the registry strips `thinking` when `openai-codex` or `anthropic` is routed through a non-audited proxy `baseUrl`) rejected the raw effort inside the provider mapper with "Model <provider>/<id> does not support thinking"; since the compaction fallback chain then reaches for the same-provider largest-context model, every candidate died on that throw and auto-compaction reported only the last one. The agent turn already clamps through `clampThinkingLevelForModel`; the maintenance calls were the one path still sending an unclamped effort.
+
 ## [0.16.4] - 2026-09-05
 
 - Provider calls now carry the agent-owned opaque provider conversation identity separately from generic session/cache affinity, including compaction, handoff, turn-prefix summary, and branch-summary maintenance calls. This lets provider-specific conversation headers remain stable without treating prompt-derived gateway cache keys as conversation authority (#5295).

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@gajae-code/agent-core",
-	"version": "0.16.4",
+	"version": "0.16.6",
 	"description": "General-purpose agent with transport abstraction, state management, and attachment support",
 	"homepage": "https://gajae-code.com",
 	"author": "Yeachan-Heo and Gajae Code Contributors",
@@ -32,9 +32,9 @@
 		"fmt": "biome format --write ."
 	},
 	"dependencies": {
-		"@gajae-code/ai": "0.16.4",
-		"@gajae-code/natives": "0.16.4",
-		"@gajae-code/utils": "0.16.4",
+		"@gajae-code/ai": "0.16.6",
+		"@gajae-code/natives": "0.16.6",
+		"@gajae-code/utils": "0.16.6",
 		"@opentelemetry/api": "^1.9.0"
 	},
 	"devDependencies": {

package/src/compaction/compaction.ts

@@ -8,6 +8,7 @@
 import * as os from "node:os";
 import {
 	type AssistantMessage,
+	clampThinkingLevelForModel,
 	Effort,
 	type Message,
 	type MessageAttribution,
@@ -1023,7 +1024,7 @@ export async function generateSummary(
 			maxTokens,
 			signal,
 			apiKey,
-			reasoning: Effort.High,
+			reasoning: maintenanceReasoning(model),
 			initiatorOverride: options?.initiatorOverride,
 			metadata: options?.metadata,
 			sessionId: options?.sessionId,
@@ -1120,7 +1121,7 @@ export async function generateHandoff(
 		{
 			apiKey,
 			signal,
-			reasoning: Effort.High,
+			reasoning: maintenanceReasoning(model),
 			toolChoice: "none",
 			initiatorOverride: options.initiatorOverride,
 			metadata: options.metadata,
@@ -1346,6 +1347,22 @@ export function prepareCompaction(
 
 const TURN_PREFIX_SUMMARIZATION_PROMPT = prompt.render(compactionTurnPrefixPrompt);
 
+/**
+ * Reasoning effort for a maintenance one-shot call (summary, turn-prefix
+ * summary, handoff), sized against the model that will actually run it.
+ *
+ * These calls want `high`, but they must never *demand* it: the fallback
+ * chain hands them whatever same-provider model has the most context, and a
+ * reasoning-capable model on a transport without reasoning control (the
+ * registry strips `thinking` for a proxied `openai-codex` baseUrl) rejects any
+ * explicit effort inside the provider mapper. The agent turn already clamps
+ * through this helper; the maintenance calls must not be the one path that
+ * still sends a raw effort.
+ */
+function maintenanceReasoning(model: Model): Effort | undefined {
+	return clampThinkingLevelForModel(model, Effort.High);
+}
+
 /**
  * Generate summaries for compaction using prepared data.
  * Returns CompactionResult - SessionManager adds id/parentId when saving.
@@ -1555,7 +1572,7 @@ async function generateTurnPrefixSummary(
 			maxTokens,
 			signal,
 			apiKey,
-			reasoning: Effort.High,
+			reasoning: maintenanceReasoning(model),
 			initiatorOverride: options?.initiatorOverride,
 			metadata: options?.metadata,
 			sessionId: options?.sessionId,