@lazyingart/agintiflow 0.14.0 → 0.14.1

package/README.md

@@ -67,7 +67,7 @@ aginti
 aginti chat
 ```
 
-Inside chat, type normal requests such as `write a small Python CLI app with tests`. The default is Docker workspace mode with approved package installs, so coding, plotting, and LaTeX tasks can set up project-local tools without touching the host. Use `/help` for commands, `/login` or `/auth` to paste a provider key, `/instructions` to inspect `AGINTI.md`, `/latex on` for PDF work, `/docker off` only when you intentionally want host mode, `/sessions` to list project runs, and `/resume latest` or `/resume <session-id>` to continue work. Type `/` then Tab for command completion. `Ctrl+J` inserts a new line in the colored input panel, Enter sends, arrow keys move through wrapped multiline input, and `Ctrl+A`/`Ctrl+E` jump to the current line start/end. During an active run, Enter sends the draft as an ASAP pipe message (`→`) and Tab queues it for after the run (`↳`); ASAP messages are consumed first, Alt+Up edits the last piped message, and Shift+Left edits the last after-finish queued message. The input panel always shows the current `cwd` footer and a single live status row, so long goals and tool updates are compacted instead of flooding the transcript. Assistant responses start on a fresh line after the `aginti>` header with a colored response gutter and render common Markdown, including headings, inline code, bold text, lists, quotes, code fences, tables, and red/green patch diff lines. Resuming a session prints the full saved chat history with wrapped messages before the prompt. Esc or Ctrl+C stops the active run cleanly and prints the resume command.
+Inside chat, type normal requests such as `write a small Python CLI app with tests`. The default is Docker workspace mode with approved package installs, so coding, plotting, and LaTeX tasks can set up project-local tools without touching the host. Use `/help` for commands, `/login` or `/auth` to paste a provider key, `/instructions` to inspect `AGINTI.md`, `/latex on` for PDF work, `/docker off` only when you intentionally want host mode, `/sessions` to list project runs, and `/resume latest` or `/resume <session-id>` to continue work. Type `/` then Tab for command completion. `Ctrl+J` inserts a new line in the colored input panel, Enter sends, arrow keys move through wrapped multiline input, and `Ctrl+A`/`Ctrl+E` jump to the current line start/end. During an active run, Enter sends the draft as an ASAP pipe message (`→`) and Tab queues it for after the run (`↳`); ASAP messages are consumed before after-finish queued prompts, Alt+Up edits the last piped message, and Shift+Left edits the last after-finish queued message. Idle Esc is ignored so it does not disturb the input panel; during a run, Esc waits when `→` messages are pending and otherwise stops the run cleanly. Ctrl+C always stops and prints the resume command. The input panel always shows the current `cwd` footer and a single live status row, so long goals and tool updates are compacted instead of flooding the transcript. Assistant responses start on a fresh line after the `aginti>` header with a colored response gutter and render common Markdown, including headings, inline code, bold text, lists, quotes, code fences, tables, and red/green patch diff lines. Resuming a session prints the full saved chat history with wrapped messages before the prompt.
 
 `aginti init` creates `AGINTI.md` at the project root. This is the editable project-instruction file for both CLI and web runs, similar to `AGENTS.md` or project memory in other agents. Keep durable preferences, commands, and constraints there, but never secrets. You can edit it manually or ask in chat, for example: `update AGINTI.md to remember that this project uses pytest and npm run check`.
 

package/docs/agent-runtime-pipe.md

@@ -9,11 +9,11 @@ AgInTiFlow keeps CLI and web runs equivalent by using the project folder as the
 
 When a run is active, the web chat and `aginti queue <session-id> "..."` append messages to the inbox instead of trying to mutate the running process directly. The web API exposes `GET /api/sessions/:id/inbox`, `POST /api/sessions/:id/inbox`, `PATCH /api/sessions/:id/inbox/:itemId`, and `DELETE /api/sessions/:id/inbox/:itemId` so browser users can inspect, edit, or remove pending pipe messages before the runner consumes them. The runner drains the inbox at safe boundaries: before each model step and after tool execution. This mirrors the event-queue style used by mature agent UIs while keeping the backend decoupled from any specific frontend.
 
-The interactive CLI keeps the input panel visible while a run is working. Enter sends the current draft as an ASAP pipe message and displays it as `→`; the runner drains those messages before normal inbox items. Tab stores the draft as an after-finish queue item and displays it as `↳`; those prompts run only after the current run completes. Alt+Up moves the last pending `→` message back into the editor, and Shift+Left moves the last pending `↳` message back into the editor. The current command cwd is rendered below the input panel in both idle and running states.
+The interactive CLI keeps the input panel visible while a run is working. Enter sends the current draft as an ASAP pipe message and displays it as `→`; the runner drains those messages before normal inbox items and before after-finish queued prompts. Tab stores the draft as an after-finish queue item and displays it as `↳`; those prompts run only after the current run completes. Alt+Up moves the last pending `→` message back into the editor, and Shift+Left moves the last pending `↳` message back into the editor. Idle Esc is ignored so it does not redraw the prompt into the transcript. During a run, Esc waits when `→` pipe messages are still pending and stops the run only when no ASAP pipe message is pending; Ctrl+C always stops. The current command cwd is rendered below the input panel in both idle and running states.
 
 The web UI uses a related but browser-appropriate pattern. Enter sends and Shift+Enter adds a newline. `Pipe to run` writes an ASAP inbox item shared with CLI. `Queue after finish` keeps a browser-local next prompt and starts it after the current web-owned run finishes. Both lanes render in a pending panel with Edit and Remove buttons instead of terminal-only keybindings.
 
-Runs can be stopped without corrupting session state. The CLI listens for Esc or Ctrl+C during an active run, and the web UI exposes a Stop button plus Esc. Both paths send an abort signal, persist `session.stopped`, and leave the session resumable through `aginti resume <session-id>`.
+Runs can be stopped without corrupting session state. The CLI listens for Ctrl+C during an active run, and Esc stops only when no ASAP pipe message is waiting to be applied. The web UI exposes a Stop button plus Esc. Stop paths send an abort signal, persist `session.stopped`, and leave the session resumable through `aginti resume <session-id>`.
 
 Default execution is Docker workspace mode with package installs approved inside the sandbox. The project is mounted at `/workspace`; persistent agent toolchain folders are mounted at `/aginti-home`, `/aginti-cache`, and `/aginti-env` from `~/.agintiflow/docker/`. Python, conda, and other language-level environments should be installed under `/aginti-env` so they survive across runs. Apt/apk package changes are ephemeral unless the Docker image is rebuilt.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lazyingart/agintiflow",
-  "version": "0.14.0",
+  "version": "0.14.1",
   "type": "module",
   "description": "AgInTiFlow is a resumable Playwright website-control agent with OpenAI-compatible tool calling.",
   "license": "Apache-2.0",

package/scripts/smoke-cli-chat.js

@@ -4,7 +4,7 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 import { fileURLToPath } from "node:url";
-import { buildPromptLayout, stripMarkdown } from "../src/interactive-cli.js";
+import { buildPromptLayout, classifyEscapeAction, stripMarkdown } from "../src/interactive-cli.js";
 
 const repoRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
 const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "agintiflow-cli-chat-"));
@@ -112,6 +112,15 @@ try {
   if (!queuedText.includes("run   running · tool: apply_patch") || !queuedText.includes("→ apply this") || !queuedText.includes("↳ run this") || !queuedText.includes("cwd   /tmp/aginti-project")) {
     throw new Error("terminal prompt layout did not render live input queue and cwd footer");
   }
+  if (classifyEscapeAction({ active: false }) !== "noop") {
+    throw new Error("idle Esc should not redraw or clear the prompt");
+  }
+  if (classifyEscapeAction({ active: true, pendingAsap: [{ content: "apply now" }] }) !== "wait-for-asap") {
+    throw new Error("active Esc should wait when ASAP pipe messages are pending");
+  }
+  if (classifyEscapeAction({ active: true, pendingAsap: [] }) !== "abort") {
+    throw new Error("active Esc should abort when no ASAP pipe messages are pending");
+  }
 
   await runCli(["init"], "");
   const instructions = await fs.readFile(path.join(tempRoot, "AGINTI.md"), "utf8");
@@ -163,7 +172,7 @@ try {
       {
         ok: true,
         projectRoot: tempRoot,
-        checks: ["markdown-render", "markdown-table-no-duplicate", "patch-diff-render", "prompt-layout", "live-input-status-layout", "agent-response-gutter", "aginti-md", "instructions-command", "skills-command", "instructions-chat-edit", "interactive-chat", "mock-file-write", "run-status", "resume-latest", "resume-history-full"],
+        checks: ["markdown-render", "markdown-table-no-duplicate", "patch-diff-render", "prompt-layout", "escape-policy", "live-input-status-layout", "agent-response-gutter", "aginti-md", "instructions-command", "skills-command", "instructions-chat-edit", "interactive-chat", "mock-file-write", "run-status", "resume-latest", "resume-history-full"],
       },
       null,
       2

package/src/interactive-cli.js

@@ -501,7 +501,7 @@ function printHelp() {
       "Type / then Tab to autocomplete commands.",
       "While a run is active, Enter pipes a message into the current run (→), Tab queues it after finish (↳).",
       "Alt+Up edits the last piped message; Shift+Left edits the last queued message.",
-      "Esc or Ctrl+C stops gracefully and prints a resume command.",
+      "Esc is ignored while idle. During a run, Esc waits for pending → pipe messages or stops if none; Ctrl+C always stops.",
     ].join("\n")
   );
 }
@@ -793,6 +793,11 @@ function createAbortError(message = "Aborted with Ctrl+C") {
   return error;
 }
 
+export function classifyEscapeAction({ active = false, pendingAsap = [] } = {}) {
+  if (!active) return "noop";
+  return Array.isArray(pendingAsap) && pendingAsap.length > 0 ? "wait-for-asap" : "abort";
+}
+
 function readTtyPrompt(options = {}) {
   return new Promise((resolve, reject) => {
     emitKeypressEvents(input);
@@ -966,10 +971,7 @@ function readTtyPrompt(options = {}) {
         return;
       }
       if (key.name === "escape") {
-        buffer = "";
-        cursor = 0;
-        preferredColumn = null;
-        redraw();
+        if (classifyEscapeAction({ active: false }) === "noop") return;
         return;
       }
       if (key.ctrl || key.meta) return;
@@ -1192,6 +1194,13 @@ class LiveRunInput {
       return;
     }
     if (key.name === "escape") {
+      const action = classifyEscapeAction({ active: true, pendingAsap: this.pendingAsap });
+      if (action === "wait-for-asap") {
+        const count = this.pendingAsap.length;
+        this.setStatus(`running · waiting to apply ${count} asap pipe message${count === 1 ? "" : "s"}`);
+        this.redraw();
+        return;
+      }
       this.controller.abort(new Error("Interrupted by escape."));
       return;
     }