fix(read): avoid search focus for chat_id opens

MadKangYu · MadKangYu · commit 9114520b87c4 · 2026-05-27T14:37:06.000+09:00
chat_id lookups already come from the chat list registry, so prefer the visible chat-list row before falling back to KakaoTalk global search. Normalize KakaoTalk windows to a readable minimum size before scanning/opening so chat_id reads do not depend on a tiny or unrelated focused search window, while preserving existing larger windows and restoring the previous window position after automatic resizing.

Add an opt-in read --layout mode for operator-controlled placement. The default preserve mode keeps the current location, while left/right layout uses AX frame control against the current display bounds instead of Mission Control or Split View automation.

Constraint: KakaoTalk search fields can remain focused in unrelated small windows and fail AX focus verification.

Constraint: Automatic resizing must avoid shrinking user-sized windows or moving them to a surprising screen position unless the operator explicitly asks for layout.

Rejected: Only document FOCUS_FAIL recovery | leaves chat_id reads dependent on the same failing search path.

Rejected: Always use global search for chat_id | wastes the stronger identity from the chat list registry and keeps the focus failure mode.

Rejected: Drive Mission Control or Split View | too disruptive and not exposed as a stable public automation surface.

Rejected: Clamp every chat window to a fixed maximum by default | would shrink user-sized windows and create avoidable disruption.

Confidence: medium

Scope-risk: moderate

Tested: swift build; .build/debug/kmsg read --help; git diff --check

Not-tested: live read --chat-id completion; local debug binary previously hung in auth/window bootstrap before returning output. swift test unavailable because the package has no Tests target. Python tests unavailable because pytest is not installed.
diff --git a/Sources/kmsg/Accessibility/UIElement.swift b/Sources/kmsg/Accessibility/UIElement.swift
@@ -150,6 +150,27 @@ public final class UIElement: @unchecked Sendable {
         return CGRect(origin: pos, size: size)
     }
 
+    public func setPosition(_ point: CGPoint) throws {
+        var point = point
+        guard let value = AXValueCreate(.cgPoint, &point) else {
+            throw AccessibilityError.typeMismatch
+        }
+        try setAttribute(kAXPositionAttribute, value: value)
+    }
+
+    public func setSize(_ size: CGSize) throws {
+        var size = size
+        guard let value = AXValueCreate(.cgSize, &size) else {
+            throw AccessibilityError.typeMismatch
+        }
+        try setAttribute(kAXSizeAttribute, value: value)
+    }
+
+    public func setFrame(_ frame: CGRect) throws {
+        try setPosition(frame.origin)
+        try setSize(frame.size)
+    }
+
     // MARK: - Hierarchy
 
     public var parent: UIElement? {
diff --git a/Sources/kmsg/Commands/ReadCommand.swift b/Sources/kmsg/Commands/ReadCommand.swift
@@ -1,6 +1,8 @@
 import ArgumentParser
 import Foundation
 
+extension ChatWindowLayoutMode: ExpressibleByArgument {}
+
 struct ReadCommand: ParsableCommand {
     private struct ReadJSONResponse: Encodable {
         let chat: String
@@ -19,11 +21,20 @@ struct ReadCommand: ParsableCommand {
     static let configuration = CommandConfiguration(
         commandName: "read",
         abstract: "Read messages from a chat",
-        discussion: "When author is \"(me)\", the message was sent by you."
+        discussion: """
+            Use either:
+              kmsg read <chat>
+              kmsg read --chat-id <chat-id>
+
+            When author is "(me)", the message was sent by you.
+            """
     )
 
+    @Option(name: .long, help: "Read using a chat_id from 'kmsg chats'")
+    var chatID: String?
+
     @Argument(help: "Name of the chat to read from (partial match supported)")
-    var chat: String
+    var chat: String?
 
     @Option(name: .shortAndLong, help: "Maximum number of messages to show")
     var limit: Int = 20
@@ -46,9 +57,25 @@ struct ReadCommand: ParsableCommand {
     )
     var deepRecovery: Bool = false
 
+    @Option(name: .long, help: "Window layout before reading: preserve, left, or right")
+    var layout: ChatWindowLayoutMode = .preserve
+
     @Flag(name: .long, help: "Output in JSON format")
     var json: Bool = false
 
+    func validate() throws {
+        if let chatID, !chatID.isEmpty {
+            guard chat == nil else {
+                throw ValidationError("Chat name cannot be provided together with --chat-id.")
+            }
+            return
+        }
+
+        guard let chat, !chat.isEmpty else {
+            throw ValidationError("Chat name is required unless --chat-id is provided.")
+        }
+    }
+
     func run() throws {
         guard AccessibilityPermission.ensureGranted() else {
             AccessibilityPermission.printInstructions()
@@ -60,15 +87,24 @@ struct ReadCommand: ParsableCommand {
         let chatWindowResolver = ChatWindowResolver(
             kakao: kakao,
             runner: runner,
-            deepRecoveryEnabled: deepRecovery
+            deepRecoveryEnabled: deepRecovery,
+            layoutMode: layout
         )
         let transcriptReader = KakaoTalkTranscriptReader(kakao: kakao, runner: runner)
 
         let resolution: ChatWindowResolution
+        let requestedChat: String
         do {
-            resolution = try chatWindowResolver.resolve(query: chat)
+            if let chatID {
+                requestedChat = chatID
+                resolution = try chatWindowResolver.resolve(chatID: chatID)
+            } else {
+                let chat = chat ?? ""
+                requestedChat = chat
+                resolution = try chatWindowResolver.resolve(query: chat)
+            }
         } catch {
-            print("No chat window found for '\(chat)'")
+            print("No chat window found for '\(requestedChat)'")
             print("Reason: \(error)")
             print("\nAvailable windows:")
             for (index, window) in kakao.windows.enumerated() {
@@ -80,6 +116,11 @@ struct ReadCommand: ParsableCommand {
         let window = resolution.window
         if resolution.openedViaSearch {
             runner.log("read: opening chat via search")
+        } else if resolution.method == .openedViaChatList {
+            runner.log("read: opening chat via chat list")
+        }
+
+        if resolution.openedTransiently {
             if keepWindow {
                 runner.log("read: keep-window enabled; auto-opened window will be kept")
             } else {
@@ -90,16 +131,16 @@ struct ReadCommand: ParsableCommand {
         }
 
         defer {
-            if resolution.openedViaSearch && !keepWindow {
+            if resolution.openedTransiently && !keepWindow {
                 let resolvedTitle = window.title ?? ""
-                if !resolvedTitle.isEmpty && !resolvedTitle.localizedCaseInsensitiveContains(chat) {
+                if chatID == nil && !resolvedTitle.isEmpty && !resolvedTitle.localizedCaseInsensitiveContains(requestedChat) {
                     runner.log("read: skipped auto-close because resolved title '\(resolvedTitle)' did not match query")
                 } else if chatWindowResolver.closeWindow(window) {
                     runner.log("read: auto-opened chat window closed")
                 } else {
                     runner.log("read: failed to close auto-opened chat window")
                 }
-            } else if resolution.openedViaSearch && keepWindow {
+            } else if resolution.openedTransiently && keepWindow {
                 runner.log("read: auto-opened chat window kept by --keep-window")
             }
         }
@@ -108,7 +149,7 @@ struct ReadCommand: ParsableCommand {
         do {
             snapshot = try transcriptReader.readSnapshot(
                 from: window,
-                fallbackChatTitle: chat,
+                fallbackChatTitle: window.title ?? requestedChat,
                 limit: limit
             )
         } catch TranscriptReadError.transcriptContextUnavailable {
diff --git a/Sources/kmsg/Commands/SendCommand.swift b/Sources/kmsg/Commands/SendCommand.swift
@@ -129,22 +129,18 @@ struct SendCommand: ParsableCommand {
             runner.log("window strategy: focusedWindow -> mainWindow -> windows.first")
             let resolution: ChatWindowResolution
             if let chatID {
-                guard let record = ChatIdentityRegistryStore.shared.record(for: chatID) else {
-                    throw KakaoTalkError.elementNotFound("Unknown chat_id '\(chatID)'. Run 'kmsg chats' first to refresh the local registry.")
-                }
                 print("Looking for chat with \(targetDescription)...")
-                print("Resolved \(targetDescription) to '\(record.displayName)'.")
-                resolution = try chatWindowResolver.resolve(query: record.displayName)
-                if resolution.openedViaSearch {
-                    print("No existing chat window. Opening via search...")
+                resolution = try chatWindowResolver.resolve(chatID: chatID)
+                if resolution.openedTransiently {
+                    print("No existing chat window. Opening via chat list or search...")
                 } else {
                     print("Found existing chat window.")
                 }
             } else {
                 let recipient = recipient ?? ""
                 print("Looking for chat with \(targetDescription)...")
                 resolution = try chatWindowResolver.resolve(query: recipient)
-                if resolution.openedViaSearch {
+                if resolution.openedTransiently {
                     print("No existing chat window. Opening via search...")
                 } else {
                     print("Found existing chat window.")
diff --git a/Sources/kmsg/Commands/WatchCommand.swift b/Sources/kmsg/Commands/WatchCommand.swift
@@ -100,7 +100,7 @@ struct WatchCommand: ParsableCommand {
 
         var currentWindow = resolution.window
         var currentChatTitle = currentWindow.title ?? chat
-        var autoOpenedWindow: UIElement? = resolution.openedViaSearch ? currentWindow : nil
+        var autoOpenedWindow: UIElement? = resolution.openedTransiently ? currentWindow : nil
         var cachedContext: MessageTranscriptContext?
 
         defer {
@@ -224,7 +224,7 @@ struct WatchCommand: ParsableCommand {
         currentWindow = resolution.window
         currentChatTitle = currentWindow.title ?? chat
         cachedContext = nil
-        if resolution.openedViaSearch {
+        if resolution.openedTransiently {
             autoOpenedWindow = currentWindow
         }
         return try stabilizeBaseline(
diff --git a/Sources/kmsg/KakaoTalk/ChatWindowResolver.swift b/Sources/kmsg/KakaoTalk/ChatWindowResolver.swift
