@kenkaiiii/ggcoder 5.50.0 → 5.51.0

package/dist/app-sidecar.js

@@ -71,6 +71,8 @@ import { downscaleForPreview, shrinkToFit, validateVisionImage } from "./utils/i
 import { startServeMode } from "./modes/serve-mode.js";
 import { loadTelegramConfig, saveTelegramConfig, verifyBotToken } from "./core/telegram-config.js";
 import { loadServers, addServer, removeServer, getServer, parseMcpAddCommand, MCPClientManager, McpOAuthStore, createElicitationBridge, } from "./core/mcp/index.js";
+import { createAskUserBridge } from "./core/ask-user.js";
+import { createAskUserTool } from "./tools/ask-user.js";
 import { buildSnapshot, levelForXp, rankForLevel } from "./core/progress/ranks.js";
 import { loadProgress, peekProgress, updateProgress } from "./core/progress/store.js";
 import { awardPrompt, awardCommits } from "./core/progress/engine.js";
@@ -1297,6 +1299,16 @@ async function createSession(deps, opts) {
             server: prompt.server,
         }),
     });
+    // ── ask_user bridge ────────────────────────────────────────
+    // The `ask_user` tool parks the turn on a human answer. Same shape as the
+    // MCP bridge above: broadcast over SSE, resolved when the webview POSTs
+    // /ask/:id. Registered ONLY here — a TUI/headless/subagent run has nobody to
+    // answer, so the tool is absent there rather than hanging on a dead channel.
+    const asks = createAskUserBridge({
+        broadcast: (prompt) => broadcast("ask_user", prompt),
+        onTimeout: (prompt) => log("WARN", "app-sidecar", "ask_user timed out", { id: prompt.id }),
+    });
+    const askUserTool = createAskUserTool(asks.park);
     // The session file path to resume (passed by the daemon's POST /session);
     // empty/unset starts a fresh session.
     const resumeSessionPath = opts.sessionPath;
@@ -1322,7 +1334,11 @@ async function createSession(deps, opts) {
         session = createChatAgent(chatAgent, {
             ...baseSessionOptions,
             sessionsDir: paths.sessionsDir,
-            additionalTools: [...buildMemoryTools(memoryStore), ...buildJiwaTools(jiwaStore)],
+            additionalTools: [
+                askUserTool,
+                ...buildMemoryTools(memoryStore),
+                ...buildJiwaTools(jiwaStore),
+            ],
             getSystemPromptTail: () => `${memoryStore.renderForPrompt()}\n\n${jiwaStore.renderForPrompt()}`,
             onAgentChange: async (nextAgent) => {
                 chatAgent = nextAgent;
@@ -1339,6 +1355,7 @@ async function createSession(deps, opts) {
     else {
         session = new AgentSession({
             ...baseSessionOptions,
+            additionalTools: [askUserTool],
             // Plan mode belongs only to the coding agent.
             onEnterPlan: async (reason) => {
                 deactivateApprovedPlan();
@@ -2152,8 +2169,9 @@ async function createSession(deps, opts) {
         abort.abort();
         // An MCP tool call parked on user input is not cancelled by the signal —
         // the promise lives in the bridge. Release it, or the aborted turn's tool
-        // call never returns.
+        // call never returns. Same for a question parked on the user.
         elicitations.cancelAll();
+        asks.cancelAll();
         // Stop a run-all sweep and every async child through AgentSession's signal.
         taskRunAll = false;
         autopilotCancelled = true;
@@ -4480,6 +4498,50 @@ async function createSession(deps, opts) {
             });
             return;
         }
+        // Answer (or dismiss) an `ask_user` question band. The turn is blocked on
+        // this, so both paths must land: "answer" carries the picked values,
+        // "cancel" releases the tool call with no answer.
+        if (method === "POST" && url.startsWith("/ask/")) {
+            const id = decodeURIComponent(url.slice("/ask/".length));
+            void readBody(req, res).then((raw) => {
+                if (raw === null)
+                    return;
+                let result;
+                try {
+                    const parsed = JSON.parse(raw);
+                    if (parsed.action !== "answer" && parsed.action !== "cancel") {
+                        json(res, 400, { error: "action must be answer or cancel" });
+                        return;
+                    }
+                    if (parsed.action === "cancel") {
+                        result = { action: "cancel" };
+                    }
+                    else {
+                        // Only strings and string arrays are answers; anything else is a
+                        // malformed client, not a value to hand the model.
+                        const answers = {};
+                        for (const [key, value] of Object.entries(parsed.answers ?? {})) {
+                            if (typeof value === "string")
+                                answers[key] = value;
+                            else if (Array.isArray(value) && value.every((v) => typeof v === "string")) {
+                                answers[key] = value;
+                            }
+                        }
+                        result = { action: "answer", answers };
+                    }
+                }
+                catch {
+                    json(res, 400, { error: "invalid JSON body" });
+                    return;
+                }
+                if (!asks.settle(id, result)) {
+                    json(res, 409, { error: "no question is awaiting an answer" });
+                    return;
+                }
+                json(res, 200, { ok: true });
+            });
+            return;
+        }
         if (method === "POST" && url === "/auth/logout") {
             void readBody(req, res).then(async (raw) => {
                 if (raw === null)
@@ -4958,6 +5020,7 @@ async function createSession(deps, opts) {
     }
     async function dispose() {
         elicitations.cancelAll();
+        asks.cancelAll();
         tasksPollStopped = true;
         if (tasksPoll)
             clearTimeout(tasksPoll);