fix(windows): restore LSP and TUI coverage

packages/lsp/lsp-local/src/connection.ts

@@ -8,7 +8,7 @@
  */
 
 import type { ChildProcessByStdio } from 'node:child_process'
-import { spawn } from 'node:child_process'
+import { spawn, spawnSync } from 'node:child_process'
 import type { Readable, Writable } from 'node:stream'
 import { setImmediate as yieldToEventLoop } from 'node:timers/promises'
 import { encodeMessage, MessageDecoder } from './framing.ts'
@@ -36,6 +36,105 @@ interface Pending {
   reject: (error: Error) => void
 }
 
+/**
+ * Write one JSON-RPC message to the child stdin.
+ * @param stdin - the spawned server stdin.
+ * @param message - the unencoded JSON-RPC message.
+ * @param done - callback that reports asynchronous stream settlement.
+ */
+export type ConnectionWriter = (
+  stdin: Writable,
+  message: unknown,
+  done: (error?: Error | null) => void,
+) => void
+
+/** Host operations used to signal a detached process tree. */
+export interface ProcessTreeOperations {
+  /** Signal a POSIX process group. */
+  readonly signal: (target: number, signal: NodeJS.Signals) => void
+  /** Signal the direct child when group/tree signalling is unavailable. */
+  readonly killChild: (signal: NodeJS.Signals) => void
+  /** Terminate a Windows process tree by root pid. */
+  readonly taskkill: (pid: number) => void
+}
+
+/** Narrow taskkill runner result used by the Windows process-tree adapter. */
+export interface TaskkillResult {
+  /** Process exit status, or null when spawning failed. */
+  readonly status: number | null
+  /** Spawn failure, when the executable could not run. */
+  readonly error?: Error
+}
+
+/** Invoke a command synchronously for the Windows taskkill adapter. */
+export type TaskkillRunner = (
+  command: string,
+  args: string[],
+  options: { stdio: 'ignore' },
+) => TaskkillResult
+
+/** Invoke the host process-signal primitive for a POSIX process group. */
+export type ProcessSignalRunner = (target: number, signal: NodeJS.Signals) => boolean
+
+const processSignalRunner: ProcessSignalRunner = process.kill.bind(process)
+
+const writeConnectionMessage: ConnectionWriter = (stdin, message, done) => {
+  stdin.write(encodeMessage(message), done)
+}
+
+/**
+ * Terminate one Windows process tree and wait for taskkill to finish.
+ * @param pid - root process id.
+ * @param run - command runner; tests inject results without requiring Windows.
+ */
+export function taskkillProcessTree(
+  pid: number,
+  run: TaskkillRunner = spawnSync,
+): void {
+  const result = run('taskkill', ['/PID', String(pid), '/T', '/F'], { stdio: 'ignore' })
+  if (result.error !== undefined) throw result.error
+  if (result.status !== 0) throw new Error(`taskkill exited with status ${String(result.status)}`)
+}
+
+/**
+ * Signal one POSIX process group through an injectable host primitive.
+ * @param target - negative process-group id.
+ * @param signal - requested signal.
+ * @param run - host signal runner; tests inject it without touching real processes.
+ */
+export function signalProcessGroup(
+  target: number,
+  signal: NodeJS.Signals,
+  run: ProcessSignalRunner = processSignalRunner,
+): void {
+  run(target, signal)
+}
+
+/**
+ * Signal a detached process tree with platform-correct semantics and a direct-child fallback.
+ * @param platform - host platform.
+ * @param pid - detached root process id.
+ * @param signal - requested termination signal.
+ * @param operations - host operations.
+ */
+export function signalProcessTree(
+  platform: NodeJS.Platform,
+  pid: number,
+  signal: NodeJS.Signals,
+  operations: ProcessTreeOperations,
+): void {
+  try {
+    if (platform === 'win32') operations.taskkill(pid)
+    else operations.signal(-pid, signal)
+  } catch {
+    try {
+      operations.killChild(signal)
+    } catch {
+      // The direct child already exited; teardown remains idempotent.
+    }
+  }
+}
+
 /** A live JSON-RPC endpoint bound to one child process. */
 export class LspConnection {
   private readonly child: ChildProcessByStdio<Writable, Readable, Readable>
@@ -50,14 +149,16 @@ export class LspConnection {
   /**
    * @param spec - how to launch the server and answer its config requests.
    * @param onServerRequest - answers a server→client request; rejects to send an error response.
+   * @param writer - message writer; tests inject callback failures without relying on OS pipe races.
    */
   constructor(
     private readonly spec: ConnectionSpec,
     private readonly onServerRequest: (method: string, params: unknown) => Promise<unknown>,
+    private readonly writer: ConnectionWriter = writeConnectionMessage,
   ) {
     this.decoder = new MessageDecoder(spec.maxMessageBytes)
-    // `detached` puts the server in its own process group so teardown can signal the WHOLE group
-    // (via `process.kill(-pid)`), reaching helper processes a language server spawns (e.g. tsserver).
+    // `detached` gives teardown a process-tree root: POSIX signals its negative process-group id,
+    // while Windows passes the root pid to taskkill /T so helpers such as tsserver cannot outlive it.
     this.child = spawn(spec.command, [...spec.args], {
       cwd: spec.cwd,
       env: spec.env,
@@ -94,6 +195,11 @@ export class LspConnection {
     return this.stderr.toString('utf8')
   }
 
+  /** Whether the transport has failed even if the child close event has not arrived yet. */
+  get failed(): boolean {
+    return this.closeReason !== undefined
+  }
+
   /**
    * Send a request and await its result.
    * @param method - the JSON-RPC method.
@@ -147,23 +253,23 @@ export class LspConnection {
     return this.nextId
   }
 
-  /** Send SIGTERM to the server's process group (idempotent-safe; a dead group ignores it). */
+  /** Request termination of the server's process tree. */
   terminate(): void {
-    this.signalGroup('SIGTERM')
+    this.signalTree('SIGTERM')
   }
 
-  /** Send SIGKILL to the server's process group. */
+  /** Force termination of the server's process tree. */
   kill(): void {
-    this.signalGroup('SIGKILL')
+    this.signalTree('SIGKILL')
   }
 
   /**
-   * Wait until the owned process group has no members.
+   * Wait until the owned process tree has exited.
    * @param signal - optional bound for the wait.
-   * @returns `true` when the group exited, or `false` when the signal aborted first.
+   * @returns `true` when the tree exited, or `false` when the signal aborted first.
    */
-  async waitForProcessGroupExit(signal?: AbortSignal): Promise<boolean> {
-    while (this.processGroupAlive()) {
+  async waitForProcessTreeExit(signal?: AbortSignal): Promise<boolean> {
+    while (this.processTreeAlive()) {
       if (signal?.aborted) return false
       await yieldToEventLoop()
     }
@@ -171,26 +277,21 @@ export class LspConnection {
   }
 
   /**
-   * Signal the whole process group (negative pid) so helper processes are reached; fall back to the
-   * direct child if the group send fails. Never throws — teardown races process exit.
+   * Signal the whole process tree so helper processes are reached; fall back to the direct child if
+   * tree signaling fails. Never throws because teardown races process exit.
    */
-  private signalGroup(sig: NodeJS.Signals): void {
+  private signalTree(sig: NodeJS.Signals): void {
     const pid = this.child.pid
     if (pid === undefined) return
-    try {
-      process.kill(-pid, sig)
-    } catch {
-      // The group is gone (already exited) or could not be signalled; try the direct child.
-      try {
-        this.child.kill(sig)
-      } catch {
-        // Already dead; nothing to signal.
-      }
-    }
+    signalProcessTree(process.platform, pid, sig, {
+      signal: signalProcessGroup,
+      killChild: this.child.kill.bind(this.child),
+      taskkill: taskkillProcessTree,
+    })
   }
 
-  /** Whether the detached process group still has at least one member. */
-  private processGroupAlive(): boolean {
+  /** Whether the detached tree's root or POSIX process group is still alive. */
+  private processTreeAlive(): boolean {
     const pid = this.child.pid
     /* v8 ignore next -- only an asynchronous spawn failure omits pid; its close path owns cleanup. */
     if (pid === undefined) return false
@@ -218,7 +319,7 @@ export class LspConnection {
       // A framing/JSON failure corrupts the stream position irrecoverably: fail the instance and
       // SIGKILL the whole group so helper processes don't outlive the leader.
       this.fail(asError(error))
-      this.signalGroup('SIGKILL')
+      this.signalTree('SIGKILL')
       return
     }
     for (const message of messages) this.dispatch(message)
@@ -293,7 +394,7 @@ export class LspConnection {
         reject(error)
       }
       try {
-        this.child.stdin.write(encodeMessage(message), done)
+        this.writer(this.child.stdin, message, done)
       /* v8 ignore start -- Node stream write failures are callback-delivered; this guards a
          nonconforming Writable implementation throwing synchronously. */
       } catch (error) {

packages/lsp/lsp-local/src/index.ts

@@ -2,9 +2,9 @@
  * Generic stdio language-server backend for `ctx.lsp`. One plugin instance configures a named table
  * of server commands and registers one isolated provider for each entry. Every provider lazily
  * single-flights one server process per canonical workspace realpath, serves transient-open queries
- * through it, and evicts a crashed process so a later query can replace it. Providers read sources
- * through Node APIs in the host namespace (not `ctx.fs`) and trust their configured servers — no
- * sandbox confinement.
+ * through it, and replaces a transport that dies between a pool liveness check and the next
+ * read-only query. Providers read sources through Node APIs in the host namespace (not `ctx.fs`)
+ * and trust their configured servers — no sandbox confinement.
  *
  * Namespace plugin (named exports, no default export). Lifecycle is effect-scoped: disposal
  * unregisters from `ctx.lsp` and tears down every live server.
@@ -227,6 +227,14 @@ class LocalLspProvider implements LspProvider {
       }
       try {
         return await instance.query(request, source, signal)
+      } catch (error) {
+        // A child can die after the pre-query liveness check but before or during the next write.
+        // Queries are read-only, so replace a newly failed transport once and retry transparently.
+        if (!instance.dead) throw error
+        this.evictIfCurrent(workspace, instance)
+        this.assertActive(signal)
+        instance = this.instanceFor(workspace)
+        return await instance.query(request, source, signal)
       } finally {
         // Drop a crashed slot only when it still owns this instance; a replacement must survive.
         if (instance.dead) this.evictIfCurrent(workspace, instance)

packages/lsp/lsp-local/src/instance.ts

@@ -17,7 +17,7 @@ import type {
 import { deadline } from '@deepseek-ai/dsh-timeout'
 import { abortable, abortError } from './abort.ts'
 import { LspConnection } from './connection.ts'
-import type { ConnectionSpec } from './connection.ts'
+import type { ConnectionSpec, ConnectionWriter } from './connection.ts'
 import type { HostSource } from './host.ts'
 import type { WireInitializeResult, WireServerCapabilities } from './protocol.ts'
 import {
@@ -58,9 +58,10 @@ export class LspInstance {
 
   /**
    * @param spec - the launch, initialize, and teardown parameters.
+   * @param writer - optional connection writer used by transport conformance tests.
    */
-  constructor(private readonly spec: InstanceSpec) {
-    this.connection = new LspConnection(spec, (method, params) => this.answerServerRequest(method, params))
+  constructor(private readonly spec: InstanceSpec, writer?: ConnectionWriter) {
+    this.connection = new LspConnection(spec, (method, params) => this.answerServerRequest(method, params), writer)
     this.ready = this.initialize()
     // A handshake rejection must not surface as an unhandled rejection before the first query awaits
     // it; queries attach the real handler.
@@ -70,7 +71,7 @@ export class LspInstance {
 
   /** Synchronous liveness check: true once the process has closed or the instance was disposed. */
   get dead(): boolean {
-    return this.processClosed || this.disposed
+    return this.processClosed || this.disposed || this.connection.failed
   }
 
   /**
@@ -272,7 +273,7 @@ export class LspInstance {
     try {
       await this.gracefulShutdown(shutdownDeadline.signal)
     } catch {
-      // Graceful shutdown failed or timed out; process-group cleanup below remains authoritative.
+      // Graceful shutdown failed or timed out; process-tree cleanup below remains authoritative.
     } finally {
       shutdownDeadline[Symbol.dispose]()
     }
@@ -286,20 +287,20 @@ export class LspInstance {
     await abortable(this.connection.closed, signal)
   }
 
-  /** SIGTERM the group, escalate after `killGraceMs`, then await leader and helper exit. */
+  /** Terminate the tree, escalate after `killGraceMs`, then await leader and helper exit. */
   private async forceTerminate(): Promise<void> {
     this.connection.terminate()
     const graceDeadline = deadline(undefined, this.spec.killGraceMs, 'LSP_KILL_GRACE')
-    let groupExited: boolean
+    let treeExited: boolean
     try {
-      groupExited = await this.connection.waitForProcessGroupExit(graceDeadline.signal)
+      treeExited = await this.connection.waitForProcessTreeExit(graceDeadline.signal)
     } finally {
       graceDeadline[Symbol.dispose]()
     }
-    if (!groupExited) this.connection.kill()
+    if (!treeExited) this.connection.kill()
     await Promise.all([
       this.connection.closed,
-      this.connection.waitForProcessGroupExit(),
+      this.connection.waitForProcessTreeExit(),
     ])
   }
 }