@vanillagreen/pi-qol 2.5.0 → 2.5.1

package/README.md

@@ -52,7 +52,7 @@ Open `/extensions:settings`; settings appear under the **QOL** tab. Project sett
 - `gatewayPrivacy.enabled`: require zero data retention and no prompt training for main-agent and QOL model requests through OpenRouter and Vercel AI Gateway. Covers QOL compaction, branch summaries, imported-session summaries, handoff and session naming. Keeps other routing options and overrides weaker privacy values. Pi's built-in compaction and branch summaries cannot carry these fields, so on a gateway session model QOL writes them in place of Pi's, whatever `compaction.customEnabled` and `compaction.branchSummaryEnabled` say, and a failed or refused summary cancels the compaction or tree move instead of falling back to Pi's. Custom remote compaction endpoints keep their own privacy policy.
 - Statusline and editor: `statusline.enabled`, `statusline.showProvider`, `statusline.showAccount`, `replaceFooter`, `compactPrompt`, `showSessionNameTitle`, `showSessionNameWindow`, `inputBottomPaddingLines`, `gitRefreshTimeoutMs`, `showDirtyMarker`, `newlineOnShiftEnter`, `newlineFallbackKey`, `pendingQueue.asciiGreen`, `showImageChips`, `showAttachmentCountInStatus`.
 - Commands: `enableSessionNameCommand`, `enableHandoffCommand`, `enableScheduleCommand`, `enableContextCommand`, `handoffReviewPrompt`.
-- Session naming: `sessionAutoRename.*` (model, fallback model, deterministic fallback, prefix, prompt, limits, notify, debug). `sessionAutoRename.maxTokens` includes the naming model's reasoning tokens. `sessionAutoRename.maxNameChars` limits the title length.
+- Session naming: `sessionAutoRename.*` (model, fallback model, deterministic fallback, prefix, prompt, limits, notify, debug). `sessionAutoRename.maxTokens` includes the naming model's reasoning tokens. The naming request asks for the lowest reasoning effort the model accepts, and turns reasoning off where the model allows it. `sessionAutoRename.maxNameChars` limits the title length.
 - Session search: `sessionSearch.*` (shortcut, result and row limits, snippets, overlay width, cache TTL, summary model and limits).
 - Rate limits: `rateLimitAutoResume.*`.
 - Permission gate: `permissionGate.enabled`, `permissionGate.commands` (comma-separated literal fragments or `/regex/flags`), `permissionGate.previewLines`, `permissionGate.previewChars`.

package/extensions/qol/pi-ai-compat.ts

@@ -18,11 +18,27 @@ type RetryAssistantCall = (
 	},
 ) => Promise<any>;
 
-export async function complete(model: unknown, context: unknown, options?: unknown, deps: PiAiCompatDeps = {}): Promise<any> {
-	const rootComplete = (deps.root ?? piAi as any).complete;
-	if (typeof rootComplete === "function") return await rootComplete(model, context, options);
+async function dispatchCompletion(name: "complete" | "completeSimple", model: unknown, context: unknown, options: unknown, deps: PiAiCompatDeps): Promise<any> {
+	const rootFunction = (deps.root ?? piAi as any)[name];
+	if (typeof rootFunction === "function") return await rootFunction(model, context, options);
 	const compat = deps.loadCompat ? await deps.loadCompat() : await dynamicImport("@earendil-works/pi-ai/compat") as any;
-	return await compat.complete(model, context, options);
+	return await compat[name](model, context, options);
+}
+
+export async function complete(model: unknown, context: unknown, options?: unknown, deps: PiAiCompatDeps = {}): Promise<any> {
+	return await dispatchCompletion("complete", model, context, options, deps);
+}
+
+export async function completeSimple(model: unknown, context: unknown, options?: unknown, deps: PiAiCompatDeps = {}): Promise<any> {
+	return await dispatchCompletion("completeSimple", model, context, options, deps);
+}
+
+// The lowest reasoning level the model accepts, as `SimpleStreamOptions.reasoning`
+// takes it. Simple options express "off" by leaving the level out, so a model that
+// can turn reasoning off gets undefined. Levels come from pi-ai's model catalog.
+export function lowestReasoningLevel(model: unknown, deps: { root?: any } = {}): string | undefined {
+	const [lowest] = (deps.root ?? piAi as any).getSupportedThinkingLevels(model) as string[];
+	return lowest === "off" ? undefined : lowest;
 }
 
 export async function retryAssistantCallCompat(

package/extensions/qol/session-rename.ts

@@ -1,5 +1,5 @@
 import type { Message } from "@earendil-works/pi-ai";
-import { complete } from "./pi-ai-compat.js";
+import { completeSimple, lowestReasoningLevel } from "./pi-ai-compat.js";
 import { gatewayPrivacyOnPayload } from "./gateway-privacy.js";
 import type { ExtensionContext, SessionEntry } from "@earendil-works/pi-coding-agent";
 import { textFromContent } from "./agent-end.js";
@@ -248,6 +248,21 @@ export function headerRecord(headers: unknown): Record<string, string | null> |
 	return entries.length > 0 ? Object.fromEntries(entries) : undefined;
 }
 
+// Pi's agent path sends a request to the base URL the credential resolves, not the
+// catalog's: a Copilot enterprise token names the enterprise proxy host
+// (pi-ai auth/oauth/github-copilot.js `toAuth`, pi-coding-agent
+// core/agent-session.js `_getRequiredRequestAuth`).
+function autoRenameAuth(model: any, auth: { apiKey?: string; baseUrl?: string; env?: Record<string, string>; headers?: unknown }, source: string): AutoRenameAuth {
+	return {
+		apiKey: auth.apiKey,
+		env: auth.env,
+		headers: headerRecord(auth.headers),
+		label: modelLabel(model),
+		model: auth.baseUrl ? { ...model, baseUrl: auth.baseUrl } : model,
+		source,
+	};
+}
+
 function modelCost(model: any): number {
 	const cost = model?.cost;
 	return Number(cost?.input ?? 0) + Number(cost?.output ?? 0);
@@ -267,8 +282,7 @@ async function cheapestAvailableAutoRenameModel(ctx: ExtensionContext): Promise<
 	for (const model of models) {
 		try {
 			const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
-			const headers = headerRecord(auth.headers);
-			if (auth.ok) return { apiKey: auth.apiKey, env: auth.env, headers, label: modelLabel(model), model, source: "cheapest" };
+			if (auth.ok) return autoRenameAuth(model, auth, "cheapest");
 		} catch (error) {
 			if (isStaleCtxError(error)) return undefined;
 			// Try the next available model.
@@ -287,12 +301,11 @@ async function resolveAutoRenameModel(ctx: ExtensionContext, configured: string)
 		}
 		try {
 			const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
-			const headers = headerRecord(auth.headers);
 			if (!auth.ok) {
 				autoRenameDebug(ctx, `auth unavailable for ${modelLabel(model)}: ${auth.error}`, "warning");
 				return undefined;
 			}
-			return { apiKey: auth.apiKey, env: auth.env, headers, label: modelLabel(model), model, source: configured };
+			return autoRenameAuth(model, auth, configured);
 		} catch (error) {
 			if (isStaleCtxError(error)) return undefined;
 			autoRenameDebug(ctx, `auth failed for ${modelLabel(model)}: ${stringifyError(error)}`, "warning");
@@ -329,10 +342,12 @@ export async function generateAutoRenameName(query: string, ctx: ExtensionContex
 			const timeout = setTimeout(() => controller.abort(), timeoutMs);
 			timeout.unref?.();
 			try {
-				const response = await complete(
+				// A reasoning model left at its default effort can spend the whole token
+				// cap reasoning and write no title.
+				const response = await completeSimple(
 					resolved.model,
 					{ messages: [message], systemPrompt: AUTO_RENAME_SYSTEM_PROMPT },
-					{ apiKey: resolved.apiKey, env: resolved.env, headers: resolved.headers, maxTokens, signal: controller.signal, onPayload: gatewayPrivacyOnPayload(ctx) },
+					{ apiKey: resolved.apiKey, env: resolved.env, headers: resolved.headers, maxTokens, reasoning: lowestReasoningLevel(resolved.model), signal: controller.signal, onPayload: gatewayPrivacyOnPayload(ctx) },
 				);
 				if (response.stopReason === "error") {
 					autoRenameDebug(ctx, `${resolved.label} failed: ${response.errorMessage ?? "unknown error"}`, "warning");

package/extensions/qol/thinking-timer.ts

@@ -71,11 +71,15 @@ export function installThinkingTimerPatch(): void {
 			const labelComponents: Text[] = [];
 			for (const child of this.contentContainer.children as any[]) {
 				if (!child || typeof child !== "object") continue;
-				if (typeof child.setText !== "function") continue;
-				if (typeof child.text !== "string") continue;
+				// Pi's SDK setHiddenThinkingLabel applies one label globally, not per block.
+				// Until it supports per-block labels, depend on the private contentContainer
+				// and MouseRegion.child (verified at Pi 0.86.0 and 1.0.1).
+				const label = child.child ?? child;
+				if (typeof label.setText !== "function") continue;
+				if (typeof label.text !== "string") continue;
 				const expectedLabel = thinkingLabel(store.cwd);
-				if (!child.text.includes(expectedLabel) && !child.text.includes("Thinking...")) continue;
-				labelComponents.push(child as Text);
+				if (!label.text.includes(expectedLabel) && !label.text.includes("Thinking...")) continue;
+				labelComponents.push(label as Text);
 			}
 			if (labelComponents.length === 0) return;
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vanillagreen/pi-qol",
-  "version": "2.5.0",
+  "version": "2.5.1",
   "description": "Pi quality-of-life extension: compact statusline/π prompt, reliable multiline input, styled pasted-image chips, session naming/search/context import, scheduled prompts, handoff, permission prompts, notifications, custom compaction, and a collapsed-thinking timer.",
   "license": "MIT",
   "keywords": [