@lll9p/pi-better-compaction 0.2.0 → 0.2.1

package/README.md

@@ -54,6 +54,12 @@ On the next supported Responses request after a native `/responses/compact`, the
 Requests produced by the native-method fallback carry Pi's standard `{readFiles, modifiedFiles}`
 details, so they replay through Pi's default path — no rewrite, no special handling.
 
+By default, a session whose latest compaction is not a stored native opaque window does not attempt
+`/responses/compact`, preserving strict replay continuity. Set `allowCompactionContinuityBreak` to
+`true` to restart native compaction from Pi's current effective context instead. Any information
+already omitted by Pi's text summary cannot be recovered, but the successful compact response
+becomes the new opaque replay checkpoint for later turns.
+
 ### Selection is by API, not provider
 
 Any provider speaking a Responses API gets a native compact attempt, including OpenAI-compatible
@@ -98,6 +104,7 @@ A missing file silently uses the defaults below. The extension never writes this
 ```json
 {
   "enabled": true,
+  "allowCompactionContinuityBreak": false,
 
   "compactionModel": "openai/gpt-5.1-mini",
   "compactionThinkingLevel": "off",
@@ -116,6 +123,7 @@ A missing file silently uses the defaults below. The extension never writes this
 | Key | Default | Description |
 |-----|---------|-------------|
 | `enabled` | `true` | Master switch. `false` → Pi default compaction everywhere. |
+| `allowCompactionContinuityBreak` | `false` | Opt in to native compact recovery when the latest session compaction was created by Pi or another non-native path. The extension serializes `buildSessionContext().messages`, including Pi's text summary, into a new `/responses/compact` request. This sacrifices strict opaque-window continuity at that boundary; a successful response establishes a new native replay chain. |
 | `compactionModel` | *(unset)* | `"provider/model-id"` used for native-method fallback (non-Responses APIs, or when the compact endpoint fails). `null`/unset → use the current model via Pi's default path. The provider is split on the first `/`, so model ids may contain slashes (e.g. `"openrouter/deepseek/deepseek-chat"`). |
 | `compactionThinkingLevel` | `"off"` | Thinking level passed to the native `compact()` fallback. One of `off, minimal, low, medium, high, xhigh, max`. |
 | `responsesCompactApis` | both Responses APIs | Which Responses APIs use the compact endpoint. May only narrow the built-in set; unknown entries are ignored with a warning. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lll9p/pi-better-compaction",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "type": "module",
   "description": "Better compaction for pi: native /responses/compact replay for OpenAI Responses APIs, plus a configurable compaction model driving pi's native summarization everywhere else.",
   "author": "Lilin Lao",
@@ -14,7 +14,8 @@
   },
   "homepage": "https://github.com/lll9p/pi-better-compaction#readme",
   "publishConfig": {
-    "access": "public"
+    "access": "public",
+    "registry": "https://registry.npmjs.org/"
   },
   "keywords": [
     "pi-package",

package/src/config.ts

@@ -117,6 +117,9 @@ export function loadExtensionConfig(configPath: string = CONFIG_PATH): LoadedExt
 		source = configPath;
 
 		resolved.enabled = toBoolean(raw.enabled, "enabled", warnings) ?? resolved.enabled;
+		resolved.allowCompactionContinuityBreak =
+			toBoolean(raw.allowCompactionContinuityBreak, "allowCompactionContinuityBreak", warnings) ??
+			resolved.allowCompactionContinuityBreak;
 		resolved.notifyOnLoad = toBoolean(raw.notifyOnLoad, "notifyOnLoad", warnings) ?? resolved.notifyOnLoad;
 		resolved.debug = toBoolean(raw.debug, "debug", warnings) ?? resolved.debug;
 		resolved.logProviderPayloads =

package/src/extension-runtime.ts

@@ -105,7 +105,7 @@ async function runResponsesNativeCompact(
 		baseUrl: runtime.baseUrl,
 	});
 
-	let requestSource: "session-context" | "latest-native-replay";
+	let requestSource: "session-context" | "non-native-session-context" | "latest-native-replay";
 	let request: NativeCompactionRequestBody;
 	if (latestNativeCompaction.ok) {
 		const liveTailEntries = branchEntries.slice(latestNativeCompaction.index + 1);
@@ -119,8 +119,13 @@ async function runResponsesNativeCompact(
 			input,
 			instructions,
 		};
-	} else if (latestNativeCompaction.reason === "no-compaction") {
-		requestSource = "session-context";
+	} else if (
+		latestNativeCompaction.reason === "no-compaction" ||
+		(latestNativeCompaction.reason === "latest-compaction-not-native" &&
+			config.allowCompactionContinuityBreak)
+	) {
+		requestSource =
+			latestNativeCompaction.reason === "no-compaction" ? "session-context" : "non-native-session-context";
 		request = serializeMessagesToCompactRequest({
 			model: runtime.currentModel,
 			messages: ctx.sessionManager.buildSessionContext().messages,

package/src/types.ts

@@ -31,6 +31,11 @@ export type DebugArtifactKind =
 
 export type ExtensionConfig = {
 	enabled: boolean;
+	/**
+	 * Allow a Responses session whose latest compaction was not created by this extension
+	 * to restart native compaction from Pi's current serialized session context.
+	 */
+	allowCompactionContinuityBreak: boolean;
 	/**
 	 * "provider/model-id" used for native-method fallback compaction (non-Responses APIs,
 	 * or when the compact endpoint fails). Unset = current model via pi's default path.
@@ -284,6 +289,7 @@ export function createNativeCompactionResult(
 
 export const DEFAULT_EXTENSION_CONFIG: ExtensionConfig = {
 	enabled: true,
+	allowCompactionContinuityBreak: false,
 	compactionModel: undefined,
 	compactionThinkingLevel: "off",
 	responsesCompactApis: [...RESPONSES_COMPACT_CAPABLE_APIS],