merge: fix Bash tool bridge deadlock

.project-docs/30-worklog/tasks/20260902-fix-bash-tool-bridge-9c4e7a12.md

@@ -0,0 +1,84 @@
+# Task: Fix Bash tool execution bridge
+
+## Identity
+
+- Task ID: 20260902-fix-bash-tool-bridge-9c4e7a12
+- Mode: Feature
+- Branch: codex/20260902-fix-bash-tool-bridge-9c4e7a12-fix-bash-tool-bridge
+- Worktree: /Users/inmanx/Documents/makelore-fix-bash-tool-bridge-9c4e7a12
+- Base commit: 6073bd6f4ce269b067b13e1eed0371b38dc2c054
+- Owner: codex
+- Status: Completed
+
+## Scope
+
+- Reproduce and fix the Makelore-managed Pi tool-batch deadlock that delays
+  parallel Bash calls until the five-minute HTTP idle timeout.
+- Preserve project-scoped write-lease isolation while making Bash/edit/write
+  tools execute sequentially inside one assistant tool batch.
+- Add real Agent Server coverage for two Bash calls, including a command-level
+  timeout, and verify the same resource path used by packaged builds.
+
+## Intent And Constraints
+
+- Keep Pi `0.84.2` as the sole runtime and keep Renderer isolated from Pi wire.
+- Do not replay an accepted mutation or weaken the cross-Conversation/project
+  write lease; only remove the same-batch pre-execution self-deadlock.
+- Retain parallel execution for batches containing only read-only tools where
+  Pi supports it.
+- Treat packaging as a verification path, not as a substitute for the source
+  correction.
+
+## Outcome
+
+- Reproduced the stall with the real Pi Agent Server process. Pi `0.84.2`
+  prepares every tool in a parallel batch before it executes any of them, while
+  Makelore acquires the project write lease in `tool_call` and releases it in
+  `tool_result`. Two Bash calls in one assistant response therefore self-deadlocked:
+  the first held the lease without starting and the second waited for that lease.
+- Confirmed that the apparent five-minute Bash hang came from the Agent Server
+  HTTP idle timeout around the managed-extension request, not from a missing
+  shell dependency or the Bash command timeout. Packaging alone would retain the
+  same behavior because it ships this Agent Server resource and extension bundle.
+- Marked built-in `bash`, `edit`, and `write` tools as sequential whenever an
+  Agent thread is rebound. Marked dynamically declared product tools that require
+  the same project write lease as sequential in the generated Makelore extension.
+  Read-only tool batches keep Pi's parallel behavior.
+- Advanced the managed extension artifact from v4 to v5 and synchronized the
+  release proof and worker-opening expectations.
+- Added a real-process regression that emits two Bash calls in one assistant
+  response. The first exercises its explicit command timeout and the second must
+  still run successfully without waiting for the HTTP idle timeout.
+
+## Verification
+
+- Pre-fix regression: the new real-process test failed with the second Bash result
+  equal to `fetch failed`, reproducing the production failure under a 250 ms HTTP
+  idle timeout.
+- Focused regression: `pnpm exec vitest run
+  tests/unit/pi-agent-server-process-real.test.ts
+  tests/unit/pi-extension-bundle.test.ts
+  tests/unit/pi-managed-worker-opener.test.ts --maxWorkers=2` passed 3 files and
+  9 tests.
+- `pnpm run typecheck` passed.
+- `pnpm test` passed 213 files and 1,733 tests; 3 tests were skipped.
+- `pnpm run lint:check` passed with 0 errors and 5 existing warnings in
+  `src/pages/Home/index.tsx` and `src/pages/Makelore/index.tsx`.
+- `pnpm run build:vite` passed for Renderer, Electron Main, Preload, and the
+  release utility worker, proving the fixed Agent Server resource is included by
+  the production build path.
+- `git diff --check` passed.
+
+## Follow-ups
+
+- Integrate this feature branch into local `main`, update the canonical current
+  state/README, restart Makelore, and use the real-process regression as the
+  non-destructive smoke check instead of replaying the user's accepted turn.
+
+## Promotion Candidates
+
+- Promote the write-lease batch rule to README/current state: write-leased Pi
+  tools are serialized within one assistant batch, while read-only tools may
+  remain parallel.
+- Record the full-suite, production-build, and real-process regression results in
+  the evidence index during integration.

electron/coding-runtime/pi/extensions/makelore-runtime.ts

@@ -1,7 +1,7 @@
 import path from 'node:path';
 import { atomicWriteText } from '../../../coding-projects/atomic-json';
 
-export const MAKELORE_PI_EXTENSION_VERSION = 4;
+export const MAKELORE_PI_EXTENSION_VERSION = 5;
 export const MAKELORE_PI_EXTENSION_FILENAME = `makelore-runtime-v${MAKELORE_PI_EXTENSION_VERSION}.mjs`;
 
 const BUNDLE_SOURCE = String.raw`
@@ -172,12 +172,13 @@ export function createMakeloreRuntime(runtimeDefaults = {}) {
     return response.result;
   }
 
-  function registerProductTool(name, label, description, parameters) {
+  function registerProductTool(name, label, description, parameters, projectWriteLease = false) {
     pi.registerTool({
       name,
       label,
       description,
       parameters,
+      ...(projectWriteLease ? { executionMode: 'sequential' } : {}),
       async execute(toolCallId, params, signal) {
         return await invokeProduct(toolCallId, name, params, signal);
       },
@@ -219,6 +220,7 @@ export function createMakeloreRuntime(runtimeDefaults = {}) {
         declaration.label,
         declaration.description,
         declaration.inputSchema,
+        dynamicLeaseTools.has(declaration.name),
       );
     }
   }

electron/coding-runtime/pi/release-proof.ts

@@ -1416,7 +1416,7 @@ export async function runFinalAsarExtensionProof(): Promise<PiReleaseExtensionPr
     providerRequests: requestCounts,
     subagentStatus: 'complete',
     subagentSummary: 'REAL_CHILD_COMPLETE',
-    materializedExtension: 'makelore-runtime-v4.mjs',
+    materializedExtension: 'makelore-runtime-v5.mjs',
     providerFirstEventDelayMs: PROOF_PROVIDER_FIRST_EVENT_DELAY_MS,
     managedTurns,
     managedWorkerMilestones: composition.telemetry,

resources/pi-agent-server.mjs

@@ -46,6 +46,7 @@ function configureNetwork(settingsManager) {
 
 const SERVER_CHANNEL = '@makelore/server';
 const PROTOCOL_VERSION = 1;
+const PROJECT_WRITE_LEASE_TOOL_NAMES = new Set(['bash', 'edit', 'write']);
 const threads = new Map();
 const openingThreads = new Set();
 let shuttingDown = false;
@@ -106,6 +107,14 @@ function referencedEnvironmentNames(value) {
   return names;
 }
 
+function serializeProjectWriteLeaseTools(session) {
+  session.agent.state.tools = session.agent.state.tools.map((tool) => (
+    PROJECT_WRITE_LEASE_TOOL_NAMES.has(tool.name) && tool.executionMode !== 'sequential'
+      ? { ...tool, executionMode: 'sequential' }
+      : tool
+  ));
+}
+
 async function credentialStoreFor(options, providerId) {
   const models = JSON.parse(await readFile(path.join(options.configDir, 'models.json'), 'utf8'));
   const provider = record(record(models)?.providers)?.[providerId];
@@ -368,6 +377,12 @@ class AgentThread {
 
   async rebind() {
     const session = this.runtime.session;
+    // Pi prepares every tool_call hook before starting a parallel tool batch.
+    // Makelore acquires its project write lease in that hook and releases it in
+    // tool_result, so two parallel mutation tools would otherwise wait on each
+    // other before either command can start. Mark only the built-in mutation
+    // tools sequential; read-only batches retain Pi's parallel execution.
+    serializeProjectWriteLeaseTools(session);
     await session.bindExtensions({
       uiContext: this.createExtensionUiContext(),
       mode: 'rpc',

tests/unit/pi-agent-server-process-real.test.ts

@@ -6,6 +6,7 @@ import { tmpdir } from 'node:os';
 import path from 'node:path';
 import { afterEach, describe, expect, it } from 'vitest';
 import { PiAgentServerProcess } from '../../electron/coding-runtime/pi/agent-server-process';
+import { PiManagedExtensionHost } from '../../electron/coding-runtime/pi/extension-host';
 import { materializeMakelorePiExtension } from '../../electron/coding-runtime/pi/extensions/makelore-runtime';
 import { MAKELORE_DEFAULT_LANGUAGE_PROMPT } from '../../electron/coding-runtime/pi/resource-loader';
 import type { PiRpcEvent } from '../../electron/coding-runtime/pi/rpc-client';
@@ -81,11 +82,207 @@ async function startHeldProvider(): Promise<{
   };
 }
 
+async function startBashBatchProvider(): Promise<{
+  baseUrl: string;
+  requests: Array<Record<string, unknown>>;
+  close(): Promise<void>;
+}> {
+  const requests: Array<Record<string, unknown>> = [];
+  const provider = createServer((request, response) => {
+    const chunks: Buffer[] = [];
+    request.on('data', (chunk: Buffer) => chunks.push(chunk));
+    request.on('end', () => {
+      const body = JSON.parse(Buffer.concat(chunks).toString('utf8')) as Record<string, unknown>;
+      requests.push(body);
+      const messages = Array.isArray(body.messages) ? body.messages : [];
+      const hasToolResult = messages.some((message) => (
+        message && typeof message === 'object' && !Array.isArray(message)
+          && (message as { role?: unknown }).role === 'tool'
+      ));
+      response.writeHead(200, { 'content-type': 'text/event-stream' });
+      const writeChunk = (delta: Record<string, unknown>, finishReason: string | null) => {
+        response.write(`data: ${JSON.stringify({
+          id: 'chatcmpl-bash-batch-test',
+          object: 'chat.completion.chunk',
+          created: Math.floor(Date.now() / 1_000),
+          model: 'test-model',
+          choices: [{ index: 0, delta, finish_reason: finishReason }],
+          ...(finishReason ? { usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 } } : {}),
+        })}\n\n`);
+      };
+      if (!hasToolResult) {
+        writeChunk({
+          role: 'assistant',
+          tool_calls: [
+            {
+              index: 0,
+              id: 'bash-timeout',
+              type: 'function',
+              function: {
+                name: 'bash',
+                arguments: JSON.stringify({ command: 'sleep 1', timeout: 0.05 }),
+              },
+            },
+            {
+              index: 1,
+              id: 'bash-success',
+              type: 'function',
+              function: {
+                name: 'bash',
+                arguments: JSON.stringify({ command: 'printf SECOND_OK' }),
+              },
+            },
+          ],
+        }, null);
+        writeChunk({}, 'tool_calls');
+      } else {
+        writeChunk({ role: 'assistant', content: 'BASH_BATCH_DONE' }, null);
+        writeChunk({}, 'stop');
+      }
+      response.end('data: [DONE]\n\n');
+    });
+  });
+  await new Promise<void>((resolve, reject) => {
+    provider.once('error', reject);
+    provider.listen(0, '127.0.0.1', resolve);
+  });
+  const address = provider.address();
+  if (!address || typeof address === 'string') throw new Error('Test Provider did not bind');
+  return {
+    baseUrl: `http://127.0.0.1:${address.port}/v1`,
+    requests,
+    close: async () => {
+      await new Promise<void>((resolve, reject) => {
+        provider.close((error) => error ? reject(error) : resolve());
+        provider.closeIdleConnections?.();
+      });
+    },
+  };
+}
+
 afterEach(async () => {
   await Promise.all(roots.splice(0).map((root) => rm(root, { recursive: true, force: true })));
 });
 
 describe('Pi Agent Server real process', () => {
+  it('executes two write-leased Bash calls without waiting for the HTTP idle timeout', async () => {
+    const root = await mkdtemp(path.join(tmpdir(), 'makelore-pi-agent-server-bash-batch-'));
+    roots.push(root);
+    const projectPath = path.join(root, 'project');
+    const configDir = path.join(root, 'config');
+    const sessionDir = path.join(root, 'sessions');
+    const extensionDir = path.join(root, 'extensions');
+    await Promise.all([
+      mkdir(projectPath, { recursive: true }),
+      mkdir(configDir, { recursive: true }),
+      mkdir(sessionDir, { recursive: true }),
+      mkdir(extensionDir, { recursive: true }),
+    ]);
+    const provider = await startBashBatchProvider();
+    await Promise.all([
+      writeFile(path.join(configDir, 'settings.json'), JSON.stringify({ httpIdleTimeoutMs: 250 })),
+      writeFile(path.join(configDir, 'models.json'), JSON.stringify({
+        providers: {
+          'makelore-test': {
+            baseUrl: provider.baseUrl,
+            api: 'openai-completions',
+            apiKey: '$MAKELORE_TEST_KEY',
+            models: [{
+              id: 'test-model',
+              name: 'Test model',
+              reasoning: false,
+              input: ['text'],
+              contextWindow: 32_000,
+              maxTokens: 4_096,
+              cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+            }],
+          },
+        },
+      })),
+    ]);
+    const promptPath = path.join(root, 'system.md');
+    const languagePromptPath = path.join(root, 'language.md');
+    await Promise.all([
+      writeFile(promptPath, 'Use the provided Bash calls.'),
+      writeFile(languagePromptPath, MAKELORE_DEFAULT_LANGUAGE_PROMPT),
+    ]);
+    const extensionHost = new PiManagedExtensionHost();
+    const registration = await extensionHost.registerWorker({
+      conversationId: 'bash-batch',
+      generation: 1,
+      projectId: 'project-a',
+      projectPath,
+      extensionsDir: extensionDir,
+    });
+    const runtimeRoot = path.resolve('node_modules/@earendil-works/pi-coding-agent');
+    const server = new PiAgentServerProcess({
+      executablePath: process.execPath,
+      serverPath: path.resolve('resources/pi-agent-server.mjs'),
+      runtimeRoot,
+      configDir,
+    });
+    const worker = server.createWorker({
+      executablePath: process.execPath,
+      cliPath: path.join(runtimeRoot, 'dist', 'cli.js'),
+      cwd: projectPath,
+      configDir,
+      sessionDir,
+      conversationId: 'bash-batch',
+      workerGeneration: 1,
+      tools: ['bash'],
+      additionalArgs: [
+        '--provider', 'makelore-test',
+        '--model', 'test-model',
+        '--thinking', 'off',
+        '--system-prompt', promptPath,
+        '--append-system-prompt', languagePromptPath,
+        '--extension', registration.extensionPath,
+        '--session-id', 'session-bash-batch',
+      ],
+      env: { MAKELORE_TEST_KEY: 'secret-bash-batch', ...registration.env },
+      sensitiveValues: ['secret-bash-batch', ...registration.sensitiveValues],
+    });
+    try {
+      await worker.start();
+      await extensionHost.bindRun('bash-batch', 1, 'run-bash-batch');
+      const settled = new Promise<void>((resolve) => {
+        const unsubscribe = worker.subscribe((event) => {
+          if (event.type !== 'agent_settled') return;
+          unsubscribe();
+          resolve();
+        });
+      });
+      const startedAt = Date.now();
+      await worker.request({ type: 'prompt', message: 'RUN_BASH_BATCH' });
+      await settled;
+      expect(Date.now() - startedAt).toBeLessThan(2_000);
+      const messagesResponse = await worker.request<{ messages: Array<Record<string, unknown>> }>({
+        type: 'get_messages',
+      });
+      const toolResults = messagesResponse.data?.messages.filter(({ role }) => role === 'toolResult') ?? [];
+      const textFor = (toolCallId: string) => {
+        const message = toolResults.find((candidate) => candidate.toolCallId === toolCallId);
+        const content = Array.isArray(message?.content) ? message.content : [];
+        return content.flatMap((item) => (
+          item && typeof item === 'object' && !Array.isArray(item)
+            && typeof (item as { text?: unknown }).text === 'string'
+            ? [(item as { text: string }).text]
+            : []
+        )).join('\n');
+      };
+      expect(textFor('bash-timeout')).toContain('Command timed out after 0.05 seconds');
+      expect(textFor('bash-success')).toContain('SECOND_OK');
+      expect(JSON.stringify(toolResults)).not.toContain('fetch failed');
+      expect(provider.requests).toHaveLength(2);
+    } finally {
+      await worker.stop('test_injection').catch(() => undefined);
+      await server.stop().catch(() => undefined);
+      await registration.dispose().catch(() => undefined);
+      await extensionHost.close().catch(() => undefined);
+      await provider.close().catch(() => undefined);
+    }
+  }, 10_000);
+
   it('hosts isolated Conversation threads in one long-lived process', async () => {
     const root = await mkdtemp(path.join(tmpdir(), 'makelore-pi-agent-server-'));
     roots.push(root);

tests/unit/pi-extension-bundle.test.ts

@@ -22,6 +22,7 @@ type ExtensionHandler = (...arguments_: unknown[]) => Promise<unknown> | unknown
 type ExtensionTool = {
   name: string;
   parameters?: Record<string, unknown>;
+  executionMode?: 'sequential';
   execute?: (...arguments_: unknown[]) => Promise<unknown>;
 };
 
@@ -213,6 +214,7 @@ describe('Makelore Pi extension bundle', () => {
       expect(tools.has('data_service_inspect')).toBe(true);
       expect(tools.has('data_service_put_document')).toBe(false);
       expect(tools.get('data_service_inspect')?.parameters).toEqual(pluginTool.inputSchema);
+      expect(tools.get('data_service_inspect')?.executionMode).toBe('sequential');
       const context = JSON.parse(await readFile(registration.env.MAKELORE_PI_CONTEXT_FILE as string, 'utf8'));
       expect(context).toMatchObject({
         catalogRevision: 19,

tests/unit/pi-managed-worker-opener.test.ts

@@ -227,7 +227,7 @@ describe('managed Pi worker opener', () => {
       expect(argv).toContain('grilling');
       expect(argv).toContain('--session-id');
       expect(argv).toContain('--extension');
-      expect(argv).toContain('makelore-runtime-v4.mjs');
+      expect(argv).toContain('makelore-runtime-v5.mjs');
       expect(options.additionalArgs?.filter((argument) => argument === '--extension')).toHaveLength(1);
       expect(argv).not.toContain('PRIVATE MANAGED PROMPT');
       expect(argv).not.toContain('provider-secret-value');