@oh-my-pi/pi-coding-agent 15.10.0 → 15.10.1

package/src/debug/index.ts

@@ -19,6 +19,7 @@ import {
 } from "@oh-my-pi/pi-tui";
 import { getSessionsDir } from "@oh-my-pi/pi-utils";
 import { DynamicBorder } from "../modes/components/dynamic-border";
+import { TranscriptBlock } from "../modes/components/transcript-container";
 import { getSelectListTheme, getSymbolTheme, theme } from "../modes/theme/theme";
 import type { InteractiveModeContext } from "../modes/types";
 import { formatBytes } from "../tools/render-utils";
@@ -150,13 +151,13 @@ export class DebugSelectorComponent extends Container {
 		}
 
 		// Show message and wait for keypress
-		this.ctx.chatContainer.addChild(new Spacer(1));
-		this.ctx.chatContainer.addChild(new Text(theme.fg("accent", `${theme.status.info} CPU profiling started`), 1, 0));
-		this.ctx.chatContainer.addChild(new Spacer(1));
-		this.ctx.chatContainer.addChild(
+		const block = new TranscriptBlock();
+		block.addChild(new Text(theme.fg("accent", `${theme.status.info} CPU profiling started`), 1, 0));
+		block.addChild(new Spacer(1));
+		block.addChild(
 			new Text(theme.fg("muted", "Reproduce the performance issue, then press Enter to stop profiling."), 1, 0),
 		);
-		this.ctx.ui.requestRender();
+		this.ctx.present(block);
 
 		// Wait for Enter keypress
 		const { promise, resolve } = Promise.withResolvers<void>();
@@ -201,19 +202,16 @@ export class DebugSelectorComponent extends Container {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(
-				new Text(theme.fg("success", `${theme.status.success} Performance report saved`), 1, 0),
-			);
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			const block = new TranscriptBlock();
+			block.addChild(new Text(theme.fg("success", `${theme.status.success} Performance report saved`), 1, 0));
+			block.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
+			block.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			this.ctx.present(block);
 		} catch (err) {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 			this.ctx.showError(`Failed to create report: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	async #handleWorkReport(): Promise<void> {
@@ -231,15 +229,13 @@ export class DebugSelectorComponent extends Container {
 
 			openPath(tmpPath);
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(
+			this.ctx.present([
+				new Spacer(1),
 				new Text(theme.fg("dim", `Opened flamegraph (${workProfile.sampleCount} samples)`), 1, 0),
-			);
+			]);
 		} catch (err) {
 			this.ctx.showError(`Failed to open profile: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	async #handleDumpReport(): Promise<void> {
@@ -262,19 +258,16 @@ export class DebugSelectorComponent extends Container {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(
-				new Text(theme.fg("success", `${theme.status.success} Report bundle saved`), 1, 0),
-			);
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			const block = new TranscriptBlock();
+			block.addChild(new Text(theme.fg("success", `${theme.status.success} Report bundle saved`), 1, 0));
+			block.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
+			block.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			this.ctx.present(block);
 		} catch (err) {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 			this.ctx.showError(`Failed to create report: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	async #handleMemoryReport(): Promise<void> {
@@ -301,19 +294,16 @@ export class DebugSelectorComponent extends Container {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(
-				new Text(theme.fg("success", `${theme.status.success} Memory report saved`), 1, 0),
-			);
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
-			this.ctx.chatContainer.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			const block = new TranscriptBlock();
+			block.addChild(new Text(theme.fg("success", `${theme.status.success} Memory report saved`), 1, 0));
+			block.addChild(new Text(theme.fg("dim", formatFileHyperlink(result.path)), 1, 0));
+			block.addChild(new Text(theme.fg("dim", `Files: ${result.files.length}`), 1, 0));
+			this.ctx.present(block);
 		} catch (err) {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 			this.ctx.showError(`Failed to create report: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	async #handleViewLogs(): Promise<void> {
@@ -365,15 +355,14 @@ export class DebugSelectorComponent extends Container {
 			const info = await collectSystemInfo();
 			const formatted = formatSystemInfo(info);
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(new DynamicBorder());
-			this.ctx.chatContainer.addChild(new Text(formatted, 1, 0));
-			this.ctx.chatContainer.addChild(new DynamicBorder());
+			const block = new TranscriptBlock();
+			block.addChild(new DynamicBorder());
+			block.addChild(new Text(formatted, 1, 0));
+			block.addChild(new DynamicBorder());
+			this.ctx.present(block);
 		} catch (err) {
 			this.ctx.showError(`Failed to collect system info: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	async #handleViewTerminalState(): Promise<void> {
@@ -384,11 +373,11 @@ export class DebugSelectorComponent extends Container {
 		});
 		const formatted = formatTerminalState(info);
 
-		this.ctx.chatContainer.addChild(new Spacer(1));
-		this.ctx.chatContainer.addChild(new DynamicBorder());
-		this.ctx.chatContainer.addChild(new Text(formatted, 1, 0));
-		this.ctx.chatContainer.addChild(new DynamicBorder());
-		this.ctx.ui.requestRender();
+		const block = new TranscriptBlock();
+		block.addChild(new DynamicBorder());
+		block.addChild(new Text(formatted, 1, 0));
+		block.addChild(new DynamicBorder());
+		this.ctx.present(block);
 	}
 
 	async #handleViewProtocols(): Promise<void> {
@@ -407,15 +396,14 @@ export class DebugSelectorComponent extends Container {
 			TERMINAL.sendNotification(notification);
 		}
 
-		this.ctx.chatContainer.addChild(new Spacer(1));
-		this.ctx.chatContainer.addChild(
+		this.ctx.present([
+			new Spacer(1),
 			new ProtocolProbeComponent({
 				image: buildSampleImage(),
 				imageBudget: this.ctx.ui.imageBudget,
 				notificationSuppressed: suppressed,
 			}),
-		);
-		this.ctx.ui.requestRender();
+		]);
 	}
 
 	async #handleTranscriptExport(): Promise<void> {
@@ -487,21 +475,19 @@ export class DebugSelectorComponent extends Container {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 
-			this.ctx.chatContainer.addChild(new Spacer(1));
-			this.ctx.chatContainer.addChild(
+			this.ctx.present([
+				new Spacer(1),
 				new Text(
 					theme.fg("success", `${theme.status.success} Cleared ${result.removed} artifact directories`),
 					1,
 					0,
 				),
-			);
+			]);
 		} catch (err) {
 			loader.stop();
 			this.ctx.statusContainer.clear();
 			this.ctx.showError(`Failed to clear cache: ${err instanceof Error ? err.message : String(err)}`);
 		}
-
-		this.ctx.ui.requestRender();
 	}
 
 	#getResolvedSettings(): Record<string, unknown> {

package/src/edit/renderer.ts

@@ -4,7 +4,7 @@
 
 import { HL_FILE_PREFIX, HL_FILE_SUFFIX } from "@oh-my-pi/hashline";
 import type { Component } from "@oh-my-pi/pi-tui";
-import { Text, visibleWidth, wrapTextWithAnsi } from "@oh-my-pi/pi-tui";
+import { visibleWidth, wrapTextWithAnsi } from "@oh-my-pi/pi-tui";
 import { sanitizeText } from "@oh-my-pi/pi-utils";
 import type { RenderResultOptions } from "../extensibility/custom-tools/types";
 import type { FileDiagnosticsResult } from "../lsp";
@@ -16,7 +16,6 @@ import {
 	formatDiffStats,
 	formatExpandHint,
 	formatStatusIcon,
-	formatTitle,
 	getDiffStats,
 	getLspBatchRequest,
 	type LspBatchRequest,
@@ -25,7 +24,7 @@ import {
 	shortenPath,
 	truncateDiffByHunk,
 } from "../tools/render-utils";
-import { fileHyperlink, Hasher, type RenderCache, renderStatusLine, truncateToWidth } from "../tui";
+import { fileHyperlink, framedBlock, Hasher, type RenderCache, renderStatusLine, truncateToWidth } from "../tui";
 import type { EditMode } from "../utils/edit-mode";
 import type { DiffError, DiffResult } from "./diff";
 import { type ApplyPatchEntry, expandApplyPatchToEntries, expandApplyPatchToPreviewEntries } from "./modes/apply-patch";
@@ -186,10 +185,14 @@ function getOperationTitle(op: Operation | undefined): string {
 function formatEditPathDisplay(
 	rawPath: string,
 	uiTheme: Theme,
-	options?: { rename?: string; firstChangedLine?: number },
+	options?: { rename?: string; firstChangedLine?: number; linkPath?: string; renameLinkPath?: string },
 ): string {
+	// `rawPath`/`rename` are shown (cwd-relative) but the OSC 8 link targets the
+	// absolute path when known — a relative `rawPath` would yield a `file:///rel`
+	// URI that resolves against filesystem root instead of cwd.
+	const linkTarget = options?.linkPath || rawPath;
 	let pathDisplay = rawPath
-		? fileHyperlink(rawPath, uiTheme.fg("accent", shortenPath(rawPath)))
+		? fileHyperlink(linkTarget, uiTheme.fg("accent", shortenPath(rawPath)))
 		: uiTheme.fg("toolOutput", "…");
 
 	if (options?.firstChangedLine) {
@@ -197,7 +200,8 @@ function formatEditPathDisplay(
 	}
 
 	if (options?.rename) {
-		pathDisplay += ` ${uiTheme.fg("dim", "→")} ${fileHyperlink(options.rename, uiTheme.fg("accent", shortenPath(options.rename)))}`;
+		const renameTarget = options.renameLinkPath || options.rename;
+		pathDisplay += ` ${uiTheme.fg("dim", "→")} ${fileHyperlink(renameTarget, uiTheme.fg("accent", shortenPath(options.rename)))}`;
 	}
 
 	return pathDisplay;
@@ -206,7 +210,7 @@ function formatEditPathDisplay(
 function formatEditDescription(
 	rawPath: string,
 	uiTheme: Theme,
-	options?: { rename?: string; firstChangedLine?: number },
+	options?: { rename?: string; firstChangedLine?: number; linkPath?: string; renameLinkPath?: string },
 ): { language: string; description: string } {
 	const language = getLanguageFromPath(rawPath) ?? "text";
 	const icon = uiTheme.fg("muted", uiTheme.getLangIcon(language));
@@ -459,23 +463,31 @@ export const editToolRenderer = {
 		const rename = editArgs.rename || firstEdit?.rename || firstEdit?.move || firstApplyPatchEntry?.rename;
 		const op = editArgs.op || firstEdit?.op || firstApplyPatchEntry?.op;
 		const { description } = formatEditDescription(rawPath, uiTheme, { rename });
-		const spinner =
-			options?.spinnerFrame !== undefined ? formatStatusIcon("running", uiTheme, options.spinnerFrame) : "";
-		let text = `${formatTitle(getOperationTitle(op), uiTheme)} ${spinner ? `${spinner} ` : ""}${description}`;
-		// Show file count hint for multi-file edits
 		let fileCount = hashlineInputSummary?.entries.length ?? applyPatchSummary?.entries.length ?? 0;
 		if (Array.isArray(editArgs.edits)) {
 			fileCount = countEditFiles(editArgs.edits);
 		}
-		if (fileCount > 1) {
-			text += uiTheme.fg("dim", ` (+${fileCount - 1} more)`);
-		}
-		text += getCallPreview(editArgs, rawPath, uiTheme, renderContext, options.expanded);
-		if (applyPatchSummary?.error) {
-			text += `\n\n${uiTheme.fg("error", truncateToWidth(replaceTabs(applyPatchSummary.error, rawPath), CALL_TEXT_PREVIEW_WIDTH))}`;
-		}
-
-		return new Text(text, 0, 0);
+		return framedBlock(uiTheme, width => {
+			let header = renderStatusLine(
+				{ icon: "pending", spinnerFrame: options?.spinnerFrame, title: getOperationTitle(op), description },
+				uiTheme,
+			);
+			if (fileCount > 1) header += uiTheme.fg("dim", ` (+${fileCount - 1} more)`);
+			let body = getCallPreview(editArgs, rawPath, uiTheme, renderContext, options.expanded);
+			if (applyPatchSummary?.error) {
+				body += `\n${uiTheme.fg("error", truncateToWidth(replaceTabs(applyPatchSummary.error, rawPath), Math.max(1, width - 2)))}`;
+			}
+			const bodyLines = body ? body.split("\n") : [];
+			while (bodyLines.length > 0 && bodyLines[0].trim() === "") bodyLines.shift();
+			return {
+				header,
+				sections: bodyLines.length > 0 ? [{ lines: bodyLines }] : [],
+				state: applyPatchSummary?.error ? "error" : "pending",
+				borderColor: applyPatchSummary?.error ? "error" : "borderMuted",
+				width,
+				contentPaddingLeft: 0,
+			};
+		});
 	},
 
 	renderResult(
@@ -525,65 +537,57 @@ function renderSingleFileResult(
 			(result.content?.find(c => c.type === "text")?.text ?? "")
 		: "";
 
-	let cached: RenderCache | undefined;
-
-	return {
-		render(width) {
-			const { expanded, renderContext } = options;
-			const editDiffPreview = renderContext?.editDiffPreview;
-			const renderDiffFn = renderContext?.renderDiff ?? ((t: string) => t);
-			const key = new Hasher().bool(expanded).u32(width).digest();
-			if (cached?.key === key) return cached.lines;
-
-			const firstChangedLine =
-				(editDiffPreview && "firstChangedLine" in editDiffPreview ? editDiffPreview.firstChangedLine : undefined) ||
-				(details && !isError ? details.firstChangedLine : undefined);
-			const { description } = formatEditDescription(rawPath, uiTheme, { rename, firstChangedLine });
-
-			// Change stats ride inline on the header next to the path rather than a separate row.
-			const previewDiff = editDiffPreview && !("error" in editDiffPreview) ? editDiffPreview.diff : undefined;
-			const headerDiff = isError ? undefined : details?.diff || previewDiff;
-			const statsSuffix = headerDiff ? formatDiffStatsSuffix(headerDiff, uiTheme) : "";
-
-			const header = renderStatusLine(
-				{
-					icon: isError ? "error" : "success",
-					title: getOperationTitle(op),
-					description,
-				},
-				uiTheme,
+	return framedBlock(uiTheme, width => {
+		const { expanded, renderContext } = options;
+		const editDiffPreview = renderContext?.editDiffPreview;
+		const renderDiffFn = renderContext?.renderDiff ?? ((t: string) => t);
+
+		const firstChangedLine =
+			(editDiffPreview && "firstChangedLine" in editDiffPreview ? editDiffPreview.firstChangedLine : undefined) ||
+			(details && !isError ? details.firstChangedLine : undefined);
+		const linkPath = details && "path" in details ? details.path : undefined;
+		const { description } = formatEditDescription(rawPath, uiTheme, { rename, firstChangedLine, linkPath });
+
+		// Change stats ride inline on the header bar next to the path.
+		const previewDiff = editDiffPreview && !("error" in editDiffPreview) ? editDiffPreview.diff : undefined;
+		const headerDiff = isError ? undefined : details?.diff || previewDiff;
+		const statsSuffix = headerDiff ? formatDiffStatsSuffix(headerDiff, uiTheme) : "";
+		const header =
+			renderStatusLine({ icon: isError ? "error" : "success", title: getOperationTitle(op), description }, uiTheme) +
+			statsSuffix;
+
+		let body = "";
+		if (isError) {
+			if (errorText) body = uiTheme.fg("error", replaceTabs(errorText, rawPath));
+		} else if (details?.diff) {
+			body = renderDiffSection(details.diff, rawPath, expanded, uiTheme, renderDiffFn);
+		} else if (editDiffPreview) {
+			if ("error" in editDiffPreview) body = uiTheme.fg("error", replaceTabs(editDiffPreview.error, rawPath));
+			else if (editDiffPreview.diff)
+				body = renderDiffSection(editDiffPreview.diff, rawPath, expanded, uiTheme, renderDiffFn);
+		}
+		if (details?.diagnostics) {
+			body += formatDiagnostics(details.diagnostics, expanded, uiTheme, (fp: string) =>
+				uiTheme.getLangIcon(getLanguageFromPath(fp)),
 			);
-			let text = header + statsSuffix;
-
-			if (isError) {
-				if (errorText) {
-					text += `\n\n${uiTheme.fg("error", replaceTabs(errorText, rawPath))}`;
-				}
-			} else if (details?.diff) {
-				text += renderDiffSection(details.diff, rawPath, expanded, uiTheme, renderDiffFn);
-			} else if (editDiffPreview) {
-				if ("error" in editDiffPreview) {
-					text += `\n\n${uiTheme.fg("error", replaceTabs(editDiffPreview.error, rawPath))}`;
-				} else if (editDiffPreview.diff) {
-					text += renderDiffSection(editDiffPreview.diff, rawPath, expanded, uiTheme, renderDiffFn);
-				}
-			}
-
-			if (details?.diagnostics) {
-				text += formatDiagnostics(details.diagnostics, expanded, uiTheme, (fp: string) =>
-					uiTheme.getLangIcon(getLanguageFromPath(fp)),
-				);
-			}
+		}
 
-			const lines =
-				width > 0 ? text.split("\n").flatMap(line => wrapEditRendererLine(line, width)) : text.split("\n");
-			cached = { key, lines };
-			return lines;
-		},
-		invalidate() {
-			cached = undefined;
-		},
-	};
+		// Diff lines self-wrap with a continuation gutter; pre-wrap to the frame's
+		// inner width so renderOutputBlock's generic wrap is a no-op. Edit frames
+		// use a flush left border because code-frame gutters already provide padding.
+		const innerWidth = Math.max(1, width - 2);
+		const bodyLines = body.length > 0 ? body.split("\n").flatMap(line => wrapEditRendererLine(line, innerWidth)) : [];
+		while (bodyLines.length > 0 && bodyLines[0].trim() === "") bodyLines.shift();
+
+		return {
+			header,
+			sections: bodyLines.length > 0 ? [{ lines: bodyLines }] : [],
+			state: isError ? "error" : options.isPartial ? "pending" : "success",
+			borderColor: isError ? "error" : "borderMuted",
+			width,
+			contentPaddingLeft: 0,
+		};
+	});
 }
 
 function renderMultiFileResult(
@@ -638,7 +642,7 @@ function renderMultiFileResult(
 		},
 		invalidate() {
 			cached = undefined;
-			for (const c of fileComponents) c.invalidate();
+			for (const c of fileComponents) c.invalidate?.();
 		},
 	};
 }

package/src/eval/__tests__/llm-bridge.test.ts

@@ -4,6 +4,7 @@ import type { Api, AssistantMessage, Model } from "@oh-my-pi/pi-ai";
 import * as ai from "@oh-my-pi/pi-ai";
 import { Effort } from "@oh-my-pi/pi-ai";
 import { TempDir } from "@oh-my-pi/pi-utils";
+import { $ } from "bun";
 import type { ModelRegistry } from "../../config/model-registry";
 import { Settings } from "../../config/settings";
 import type { ToolSession } from "../../tools";
@@ -13,7 +14,7 @@ import { IdleTimeout } from "../idle-timeout";
 import { disposeAllVmContexts } from "../js/context-manager";
 import { executeJs } from "../js/executor";
 import { runEvalLlm } from "../llm-bridge";
-import { disposeAllKernelSessions, executePython } from "../py/executor";
+import { disposeAllKernelSessions, type PythonResult } from "../py/executor";
 
 function makeModel(provider: string, id: string, extra: Partial<Model<Api>> = {}): Model<Api> {
 	return {
@@ -57,6 +58,7 @@ function makeSession(opts: SessionOptions = {}): ToolSession {
 	const modelRegistry = {
 		getAvailable: () => opts.available ?? [SMOL, DEFAULT, SLOW],
 		getApiKey: async () => (opts.apiKey === undefined ? "test-key" : opts.apiKey),
+		resolver: () => async () => (opts.apiKey === undefined ? "test-key" : opts.apiKey),
 	} as unknown as ModelRegistry;
 	return {
 		settings,
@@ -96,6 +98,77 @@ function assistant(opts: {
 	};
 }
 
+async function runPythonLlmInSubprocess(options: { structured: boolean; tempDir: TempDir }): Promise<PythonResult> {
+	const repoRoot = path.resolve(import.meta.dir, "../../../..");
+	const scriptPath = path.join(options.tempDir.path(), "run-python-llm.ts");
+	const resultPath = path.join(options.tempDir.path(), "python-llm-result.json");
+	const aiPath = path.resolve(import.meta.dir, "../../../../ai/src/index.ts");
+	const executorPath = path.resolve(import.meta.dir, "../py/executor.ts");
+	const settingsPath = path.resolve(import.meta.dir, "../../config/settings.ts");
+	const code = options.structured
+		? 'import json\nprint(json.dumps(llm("hi", schema={"type": "object"})))'
+		: 'print(llm("hi", model="smol"))';
+	const responseContent = options.structured
+		? '[{ type: "toolCall", id: "tc-1", name: "respond", arguments: { ok: true } }]'
+		: '[{ type: "text", text: "hello from python" }]';
+	await Bun.write(
+		scriptPath,
+		`
+import { vi } from "bun:test";
+import * as ai from ${JSON.stringify(aiPath)};
+import { executePython } from ${JSON.stringify(executorPath)};
+import { Settings } from ${JSON.stringify(settingsPath)};
+
+const SMOL = {
+	id: "smol",
+	name: "smol",
+	api: "openai-responses",
+	provider: "p",
+	baseUrl: "https://example.test/v1",
+	reasoning: false,
+	input: ["text"],
+	cost: { input: 1, output: 1, cacheRead: 0, cacheWrite: 1 },
+	contextWindow: 128000,
+	maxTokens: 4096,
+};
+const settings = Settings.isolated({ "async.enabled": false, "task.isolation.mode": "none" });
+settings.setModelRole("smol", "p/smol");
+settings.setModelRole("slow", "p/slow");
+const session = {
+	settings,
+	modelRegistry: {
+		getAvailable: () => [SMOL],
+		getApiKey: async () => "test-key",
+		resolver: () => async () => "test-key",
+	},
+	getActiveModelString: () => "p/smol",
+};
+vi.spyOn(ai, "completeSimple").mockResolvedValue({
+	role: "assistant",
+	api: "openai-responses",
+	provider: "p",
+	model: "smol",
+	stopReason: "stop",
+	content: ${responseContent},
+});
+const result = await executePython(${JSON.stringify(code)}, {
+	cwd: ${JSON.stringify(options.tempDir.path())},
+	sessionId: ${JSON.stringify(`py-llm:${options.structured ? "struct" : "plain"}`)},
+	sessionFile: ${JSON.stringify(path.join(options.tempDir.path(), "session.jsonl"))},
+	toolSession: session,
+	kernelMode: "per-call",
+});
+await Bun.write(${JSON.stringify(resultPath)}, JSON.stringify(result));
+process.exit(0);
+`,
+	);
+	const child = await $`bun ${scriptPath}`.cwd(repoRoot).quiet().nothrow();
+	const stdout = child.stdout.toString();
+	const stderr = child.stderr.toString();
+	if (child.exitCode !== 0) throw new Error(stderr || stdout || `Python llm subprocess exited with ${child.exitCode}`);
+	return (await Bun.file(resultPath).json()) as PythonResult;
+}
+
 describe("runEvalLlm", () => {
 	afterEach(() => {
 		vi.restoreAllMocks();
@@ -290,38 +363,24 @@ describe("llm() through eval runtimes", () => {
 	});
 
 	it("exposes llm() in the Python runtime", async () => {
-		using tempDir = TempDir.createSync("@omp-eval-llm-py-");
-		const sessionFile = path.join(tempDir.path(), "session.jsonl");
-		const sessionId = `py-llm:${crypto.randomUUID()}`;
-		vi.spyOn(ai, "completeSimple").mockResolvedValue(assistant({ text: "hello from python" }));
-
-		const result = await executePython('print(llm("hi", model="smol"))', {
-			cwd: tempDir.path(),
-			sessionId,
-			sessionFile,
-			toolSession: makeSession(),
-		});
-
-		expect(result.exitCode).toBe(0);
-		expect(result.output.trim()).toBe("hello from python");
+		const tempDir = TempDir.createSync("@omp-eval-llm-py-");
+		try {
+			const result = await runPythonLlmInSubprocess({ structured: false, tempDir });
+			expect(result.exitCode).toBe(0);
+			expect(result.output.trim()).toBe("hello from python");
+		} finally {
+			tempDir.removeSync();
+		}
 	});
 
 	it("parses structured llm() output in the Python runtime", async () => {
-		using tempDir = TempDir.createSync("@omp-eval-llm-py-struct-");
-		const sessionFile = path.join(tempDir.path(), "session.jsonl");
-		const sessionId = `py-llm-struct:${crypto.randomUUID()}`;
-		vi.spyOn(ai, "completeSimple").mockResolvedValue(
-			assistant({ toolCall: { name: "respond", arguments: { ok: true } } }),
-		);
-
-		const result = await executePython('import json\nprint(json.dumps(llm("hi", schema={"type": "object"})))', {
-			cwd: tempDir.path(),
-			sessionId,
-			sessionFile,
-			toolSession: makeSession(),
-		});
-
-		expect(result.exitCode).toBe(0);
-		expect(JSON.parse(result.output.trim())).toEqual({ ok: true });
+		const tempDir = TempDir.createSync("@omp-eval-llm-py-struct-");
+		try {
+			const result = await runPythonLlmInSubprocess({ structured: true, tempDir });
+			expect(result.exitCode).toBe(0);
+			expect(JSON.parse(result.output.trim())).toEqual({ ok: true });
+		} finally {
+			tempDir.removeSync();
+		}
 	});
 });

package/src/eval/llm-bridge.ts

@@ -15,6 +15,7 @@ import { instrumentedCompleteSimple, resolveTelemetry } from "@oh-my-pi/pi-agent
 import { type Api, Effort, getSupportedEfforts, type Model, type Tool } from "@oh-my-pi/pi-ai";
 import * as z from "zod/v4";
 import { extractTextContent, extractToolCall, parseJsonPayload } from "../commit/utils";
+
 import { expandRoleAlias, formatModelString, resolveModelFromString } from "../config/model-resolver";
 import type { ToolSession } from "../tools";
 import { ToolError } from "../tools/tool-errors";
@@ -112,8 +113,9 @@ export async function runEvalLlm(args: unknown, options: EvalLlmBridgeOptions):
 		);
 	}
 
-	const apiKey = await options.session.modelRegistry?.getApiKey(model);
-	if (!apiKey) {
+	const registry = options.session.modelRegistry;
+	const apiKey = await registry?.getApiKey(model);
+	if (!registry || !apiKey) {
 		throw new ToolError(
 			`llm() has no API key for ${formatModelString(model)}. Configure credentials for this provider or choose another tier.`,
 		);
@@ -143,7 +145,10 @@ export async function runEvalLlm(args: unknown, options: EvalLlmBridgeOptions):
 				tools,
 			},
 			{
-				apiKey,
+				apiKey: registry.resolver(model.provider, {
+					sessionId: options.session.getSessionId?.() ?? undefined,
+					baseUrl: model.baseUrl,
+				}),
 				signal: options.signal,
 				reasoning: reasoningForTier(tier, model),
 				toolChoice: schema ? { type: "tool", name: STRUCTURED_TOOL_NAME } : undefined,