@oh-my-pi/pi-ai 16.1.15 → 16.1.16

package/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 ## [Unreleased]
 
+## [16.1.16] - 2026-06-23
+
+### Fixed
+
+- Fixed Anthropic-compatible thinking requests sending replayed thinking blocks without `context_management.keep: "all"`, preserving multi-turn reasoning context for API-key providers. API-key requests now also advertise the required `context-management-2025-06-27` beta header so the field is honored instead of rejected. Injected SDK clients, GitHub Copilot's Anthropic proxy, and Vertex rawPredict are excluded because this code path cannot add the beta to caller-owned clients, Copilot strips Anthropic betas and demotes thinking blocks to text upstream, and Vertex expects betas in the JSON body rather than the Anthropic HTTP beta header. ([#3288](https://github.com/can1357/oh-my-pi/issues/3288))
+- Fixed OpenRouter Responses native history replay leaking Gemini reasoning item `format` metadata back into follow-up requests, which caused HTTP 400 rejections while preserving encrypted reasoning replay.
+
 ## [16.1.15] - 2026-06-22
 
 ### Fixed

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "16.1.15",
+	"version": "16.1.16",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -38,9 +38,9 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-catalog": "16.1.15",
-		"@oh-my-pi/pi-utils": "16.1.15",
-		"@oh-my-pi/pi-wire": "16.1.15",
+		"@oh-my-pi/pi-catalog": "16.1.16",
+		"@oh-my-pi/pi-utils": "16.1.16",
+		"@oh-my-pi/pi-wire": "16.1.16",
 		"arktype": "^2.2.0",
 		"zod": "^4"
 	},

package/src/providers/anthropic.ts

@@ -120,10 +120,11 @@ export function buildBetaHeader(baseBetas: readonly string[], extraBetas: readon
 }
 
 const midConversationSystemBeta = "mid-conversation-system-2026-04-07";
+const contextManagementBeta = "context-management-2025-06-27";
 const claudeCodeUtilityBetaDefaults = [
 	"oauth-2025-04-20",
 	"interleaved-thinking-2025-05-14",
-	"context-management-2025-06-27",
+	contextManagementBeta,
 	"prompt-caching-scope-2026-01-05",
 	"structured-outputs-2025-12-15",
 ] as const;
@@ -131,7 +132,7 @@ const claudeCodeAgentBetaDefaults = [
 	"claude-code-20250219",
 	"oauth-2025-04-20",
 	"interleaved-thinking-2025-05-14",
-	"context-management-2025-06-27",
+	contextManagementBeta,
 	"prompt-caching-scope-2026-01-05",
 	midConversationSystemBeta,
 	"advanced-tool-use-2025-11-20",
@@ -1680,6 +1681,22 @@ const streamAnthropicOnce = (
 					// carry it in the Claude Code list).
 					extraBetas.push(midConversationSystemBeta);
 				}
+				// `context_management.clear_thinking_20251015` requires this beta. OAuth
+				// requests carry it in `claudeCodeAgentBetaDefaults`; API-key requests
+				// need it added explicitly so the field is honored instead of rejected
+				// (#3288). Skip transports where this package cannot deliver the beta
+				// in the form their adapter accepts: Copilot strips Anthropic betas,
+				// and Vertex rawPredict needs betas in the body (`anthropic_beta`),
+				// not as an `anthropic-beta` HTTP header.
+				if (
+					model.reasoning &&
+					options?.thinkingEnabled &&
+					model.provider !== "github-copilot" &&
+					model.provider !== "google-vertex" &&
+					!extraBetas.includes(contextManagementBeta)
+				) {
+					extraBetas.push(contextManagementBeta);
+				}
 
 				const created = createClient(model, {
 					model,
@@ -2944,11 +2961,28 @@ function buildParams(
 		}
 	}
 
-	// Pre-compute context_management (depends on thinking).
-	const contextManagement =
-		isOAuthToken && thinking?.type === "adaptive"
-			? { edits: [{ type: "clear_thinking_20251015" as const, keep: "all" as const }] }
-			: undefined;
+	// Pre-compute context_management. Send keep: "all" for every enabled or
+	// adaptive thinking request (OAuth + API-key) — not just OAuth. Without
+	// this directive Anthropic-compatible backends (Z.AI, Kimi, DeepSeek, …)
+	// strip the replayed thinking blocks `replayUnsignedThinking` puts back
+	// on the wire, so the model loses the prior reasoning chain across turns
+	// and the KV cache misses every turn (#3288). Narrowing this guard back
+	// to `isOAuthToken` regresses every API-key thinking provider. Skip
+	// injected clients because this code cannot add the required
+	// `context-management-2025-06-27` beta to caller-owned SDK clients. Skip
+	// Copilot because its proxy strips Anthropic betas and demotes thinking
+	// blocks to text upstream, so `keep: "all"` is a no-op that risks proxy
+	// rejection of an unrecognized field. Skip Vertex rawPredict because that
+	// adapter requires betas in the JSON body (`anthropic_beta`) instead of the
+	// Anthropic HTTP beta header this code can add.
+	const shouldKeepThinkingContext =
+		!options?.client &&
+		model.provider !== "github-copilot" &&
+		model.provider !== "google-vertex" &&
+		(thinking?.type === "adaptive" || thinking?.type === "enabled");
+	const contextManagement = shouldKeepThinkingContext
+		? { edits: [{ type: "clear_thinking_20251015" as const, keep: "all" as const }] }
+		: undefined;
 
 	// Pre-compute output_config.
 	const outputConfigEntries: AnthropicOutputConfig = {};

package/src/utils.ts

@@ -78,6 +78,7 @@ function sanitizeOpenAIResponsesHistoryItemForReplay(
 ): OpenAIResponsesReplayItem | undefined {
 	if (item.type === "item_reference") return undefined;
 	if (item.type === "image_generation_call") return sanitizeOpenAIResponsesImageGenerationCallForReplay(item);
+	if (item.type === "reasoning") return sanitizeOpenAIResponsesReasoningItemForReplay(item);
 
 	// providerPayload stores raw output items; replay strips item ids and keeps only normalized call_id.
 	const { id: _id, ...sanitizedItem } = item;
@@ -88,6 +89,19 @@ function sanitizeOpenAIResponsesHistoryItemForReplay(
 	return sanitizedItem as unknown as OpenAIResponsesReplayItem;
 }
 
+function sanitizeOpenAIResponsesReasoningItemForReplay(item: Record<string, unknown>): OpenAIResponsesReplayItem {
+	const sanitizedItem: Record<string, unknown> = { type: "reasoning" };
+	if (Array.isArray(item.summary)) sanitizedItem.summary = item.summary;
+	if (Array.isArray(item.content)) sanitizedItem.content = item.content;
+	if (typeof item.encrypted_content === "string" || item.encrypted_content === null) {
+		sanitizedItem.encrypted_content = item.encrypted_content;
+	}
+	if (item.status === "in_progress" || item.status === "completed" || item.status === "incomplete") {
+		sanitizedItem.status = item.status;
+	}
+	return sanitizedItem as unknown as OpenAIResponsesReplayItem;
+}
+
 function sanitizeOpenAIResponsesImageGenerationCallForReplay(
 	item: Record<string, unknown>,
 ): ResponseInputItem.ImageGenerationCall | undefined {