agents_control 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7396050fbeeb69af3c8fd481608facce44bce68072dc043f03fa0bc34138de5b
+  data.tar.gz: '05597674bc05d4bb1142e1295c264f737caf7be5afee724616ec4e0673db3870'
+SHA512:
+  metadata.gz: efe615074ece6b5898eecaaa66fdc882c46d2b6a74c715b18768b347ab3af3ef180774930dc46d5648461a006b96059bd265c67f676e45ed2eadcc0017bc6ee2
+  data.tar.gz: 6137a2654888b576860d1a8463e5aff520ace959c687974e6bd20e3425ba40f98673391517c30dc7d1c54a58bbbbad070aa2253891d6553458f774354c9c6543

data/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Sapar Kurmanov
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

data/README.md

@@ -0,0 +1,282 @@
+# agents_control
+
+A remote for iTerm2 and its AI agents (Claude Code, Codex) from Telegram:
+tab list, commands, screen, new sessions. For Claude Code — also the
+agent's questions and permission requests: it stops, buttons show up in
+Telegram, you answer, the session unblocks.
+
+Everyone runs their own bot — the token lives in the Keychain or
+libsecret, never in files or in git. The daemon is invisible from
+outside: the port only binds to 127.0.0.1, there are no incoming connections.
+
+> **Status:** terminal control and Claude Code work in full. Codex
+> sessions are visible and controllable through the terminal (like any
+> tab), but without the question relay: its hooks don't give us
+> anything to hook into for that yet.
+
+## Platforms and requirements
+
+- **macOS** — terminal backend: iTerm2 (via AppleScript) or tmux;
+  secrets: Keychain; autostart: launchd.
+- **Linux** — terminal backend: tmux; secrets: libsecret; autostart: systemd.
+- **Windows is not supported.**
+- **Ruby 3.1+.** The only external dependency is `thor` (pure Ruby, no
+  C extensions) — installing it compiles nothing.
+
+On macOS, terminal control (sending commands, reading the screen,
+creating tabs) works through iTerm2 or tmux — Terminal.app isn't
+supported. Notifications about questions and permissions aren't tied to
+a terminal at all: their source is the agent's hooks, which work
+everywhere, including sessions with no terminal (a VS Code session, for
+instance), but for now only for Claude Code.
+
+## Why
+
+You need to run a command in a session, check the screen, or switch to
+a tab, and you're not at the computer — now you can do that from
+Telegram. If the session is Claude Code, there's a bonus too: the agent
+stops and waits for an answer — the question and its buttons arrive in
+Telegram, no need to go home just to say "continue."
+
+## How it works
+
+Hooks, not screen scraping. Claude Code itself calls agents_control
+when it stops — the hook waits for an answer and passes the decision
+back into the session. There's currently one adapter, for Claude Code;
+a new agent needs a file with the same interface. Codex didn't fit:
+its hooks only see shell commands and only understand `deny` — there's
+no "agent stopped" event to hook into at all.
+
+The terminal is iTerm2 or tmux, and each session picks its own backend.
+Terminalless sessions (VS Code) are visible and answer hooks too — they
+just have nothing to type into and nowhere to read a screen from.
+
+## Installation
+
+```sh
+git clone https://github.com/saparjohnick/agents_control
+cd agents_control
+bundle install
+```
+
+Or straight from Claude Code, as a plugin — the repo doubles as a marketplace:
+
+```
+/plugin marketplace add saparjohnick/agents_control
+/plugin install agents-control@agents-control
+```
+
+The plugin doesn't replace the install above — it's just a way to find
+the tool and get install instructions without leaving Claude Code.
+
+## Usage
+
+```sh
+agents_control          # opens the console and stays in the tab
+```
+
+The tool lives in a tab: while it's open, it listens to Telegram and
+receives agent events. Commands inside start with a slash, same as the bot's:
+
+```
+> /sessions          sessions with a live agent
+> /tabs              all terminal tabs
+> /away              intercept agent questions (before stepping out)
+> /settings          settings; /settings away — toggle
+> /doctor            check that everything is in place
+> /quit              quit
+```
+
+State icons: `⏳` working · `▸` at a shell prompt · `🖥` no terminal
+(VS Code) · `·` everything else.
+
+One-off commands exist too — `agents_control sessions`, `doctor`,
+`daemon` — but the normal way to run it is an open console.
+
+### Telegram
+
+Create a bot with [@BotFather](https://t.me/BotFather) and run the wizard:
+
+```sh
+agents_control setup    # asks for the token, waits for your /start
+agents_control           # after that, just open the console
+```
+
+The wizard catches your `chat_id` from your own message and adds it to
+the allowed list — no need to type in a long number by hand.
+
+Bot commands:
+
+| Command | What it does |
+|---|---|
+| `/agents` | sessions with a live agent |
+| `/tabs` | all terminal tabs |
+| `/screen N` | show a tab's screen |
+| `/focus N` | switch to a tab |
+| `/run N command` | run a command in a tab |
+| `/new [directory]` | create a tab |
+| `/away` | intercept agent questions |
+| `/status` | current status |
+
+The number `N` comes from the last list shown.
+
+This list also populates Telegram's own `/` command menu automatically
+— `setup` and every daemon start publish it via the Bot API, no manual
+BotFather step needed. If the menu still shows only `/start` after
+that, it's Telegram's client caching the old list, not a missing step
+on your end: close and reopen the chat, or restart the Telegram app,
+to force it to refresh.
+
+### Two modes
+
+While you're at the keyboard, intercepting agent questions is
+counterproductive: you'll answer in the terminal faster than you can
+reach for your phone, and a blocked hook keeps the dialog from ever
+appearing on screen. So there are two modes:
+
+- **present** (default) — questions are mirrored to Telegram but stay
+  in the terminal;
+- **away** (`/away`) — a question arrives with buttons and waits for a
+  reply; the agent stands by until you answer or time runs out.
+
+A question can also be answered by replying directly to the message —
+it goes to the right session, even with several tabs open.
+
+Silence is treated as a refusal. If nobody answered while you were
+out, the action doesn't happen, and the session just keeps waiting in the terminal.
+
+AskUserQuestion is the one exception to all of this: its answer never
+travels back through the hook at all, so there's nothing to block on —
+it always arrives with real buttons for each option, in both modes.
+Tapping one types that choice straight into the terminal, the same
+keystroke you'd type by hand. An open-ended option ("something else,"
+"explain what you mean") has no button — just reply to the message
+with your own words instead. With more than one question in a single
+batch, or several tabs sharing the same directory so the target pane
+is ambiguous, buttons are skipped in favor of a plain reply, since
+guessing at the terminal's exact sequencing there risks typing into
+the wrong place.
+
+A "continue" reply is sent automatically, but tool permissions aren't.
+These are two independent settings on purpose: merged into one, they'd
+produce an agent that approves itself everything while nobody's
+watching. A question that offers a choice ("rewrite it or leave it?")
+is never answered automatically, even if it contains the word "continue."
+
+### Hooks
+
+The daemon connects hooks on start and removes them on stop — otherwise
+the agent prints a warning about an unreachable address in every
+session. If the daemon crashed and the hooks are still there:
+
+```sh
+agents_control hooks          # check status
+agents_control hooks uninstall
+```
+
+Entries in `~/.claude/settings.json` are tagged, and other settings
+aren't touched: installing and removing return the file to exactly its original shape.
+
+## Rate-limit anchors
+
+A five-hour window starts at the minute of the first message and
+expires exactly three hundred minutes later. An anchor doesn't add a
+single extra token — it moves window boundaries to where they're
+convenient: the difference between "the window reset at 2:37pm,
+mid-work" and "windows at exactly 7am, noon, and 5pm."
+
+The ping uses a **cheap model**, and that's not economizing for its own
+sake. The five-hour window is shared across the account, but weekly
+limits are tracked per model family: an anchor on opus would spend the
+scarcest bucket for an effect haiku gives for free.
+
+Turned on in `/settings`. If you were working recently and a window is
+already open, the ping is skipped — the daemon sees every agent event
+and knows this without polling anything.
+
+On macOS, a 7am anchor won't fire if the laptop is asleep: `doctor`
+catches this and suggests `pmset repeat wakeorpoweron`.
+
+## Watchers
+
+Hooks see the agent's own decisions, but not everything: the CLI's own
+local menus (model switch, folder trust) and text on screen (a
+rate-limit message) aren't covered by hooks at all — these events never
+produce a single hook call. Two independent watchers handle them,
+working over the screen rather than over Claude Code. Both go through
+the full `Registry` — they see bare iTerm2 tabs and tmux panes alike.
+
+**CLI menus** (`terminal.watch_menus`, on by default, polled every 20
+seconds — `terminal.menu_poll_interval`). Notices the "❯ 1. … / 2. …"
+pattern Claude Code uses to draw any choice, and sends it to Telegram
+as buttons — pressing one types the option's number straight into the pane.
+
+**Limit reset** (`answers.auto_resume_after_limit`, on by default,
+polled once a minute — `terminal.rate_limit_poll_interval`). Notices a
+message like "resets 3pm (UTC)" / "resets Oct 9, 10am" and types the
+continuation itself once the time comes (with a minute of headroom).
+
+## Checking and autostart
+
+```sh
+agents_control doctor           # is everything in place
+agents_control service install  # autostart (launchd / systemd)
+```
+
+`doctor` checks **the environment the daemon will actually get**, not
+the current one: an interactive shell can show a different Ruby and a
+different PATH than the process a service manager launches separately
+— for instance, if a Ruby version manager puts a broken shim on PATH
+ahead of the working interpreter.
+
+That's why the service always starts via an absolute path to the
+interpreter, never through PATH.
+
+## Why a tab's title can't be trusted
+
+An agent sets a tab's title via an OSC sequence, and the title stays up
+after it exits — a tab with an agent icon isn't necessarily still
+running anything. That's why an agent's presence is confirmed by the
+process tree, and the title is only ever used as a label.
+
+## Security
+
+This tool lets you run commands on your machine from Telegram. That comes with some rules:
+
+- **There's no shared service.** Everyone sets up their own bot with
+  @BotFather and connects it with their own token — the daemon talks to
+  a bot only you own, not to any third-party infrastructure.
+- **The daemon's port only listens on `127.0.0.1`.** Reaching it from
+  outside the machine isn't just blocked by a password, it's physically
+  impossible. The daemon talks to Telegram itself via long polling —
+  outgoing connections only; no incoming port is opened for this either.
+- **An allowed `chat_id` list is required.** While it's empty, the bot
+  answers nobody, even if someone learns its name. The bot's token
+  isn't an access secret; the access secret is the chat_id filter.
+- **A leaked bot token is equivalent to remote code execution.**
+- The token is stored in the Keychain (macOS) or libsecret (Linux) —
+  the same place as website and Wi-Fi passwords — and never lands in
+  the config. There's deliberately no command-line argument for the
+  token: it would leak into `ps` and shell history.
+- This protects against leaks through git, config files, `ps`, and
+  shell history — not against malicious code already running as the
+  same user: like any CLI tool without its own signed `.app`, the
+  Keychain entry trusts the `security` utility itself, not
+  agents_control specifically, so any process on the same account that
+  knows the service name can read the token.
+- Auto-replying "continue" is on by default; automatic tool approval is
+  off. These are separate settings on purpose.
+
+## Development
+
+```sh
+rake test
+```
+
+Tests run on minitest, with external commands stubbed via
+`FakeExecutor` — neither iTerm2 nor tmux is needed to run them.
+Fixtures live in `test/fixtures.rb` — recorded output from real commands.
+
+## License
+
+Apache 2.0.

data/exe/agents_control

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require_relative "../lib/agents_control"
+
+AgentsControl::CLI.start(ARGV)

data/lib/agents_control/agents/base.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+module AgentsControl
+  module Agents
+    # The agent adapter contract.
+    #
+    # Deliberately tiny. The core is written for a weak agent — one with
+    # nothing but a process in a terminal. An agent with full hooks
+    # (Claude Code, Codex) just enriches the same events, without
+    # changing their shape.
+    #
+    # If adding a new agent requires changes outside its adapter, the
+    # registry, and the hook installer, the seam was drawn wrong.
+    class Base
+      class << self
+        # Name in the registry and in Session#agent.
+        def key = raise(NotImplementedError)
+
+        # Executable names, matched by process basename.
+        def binaries = []
+
+        # Whether this adapter can parse a hook payload of this shape.
+        def handles?(_payload) = false
+      end
+
+      def key = self.class.key
+
+      # What the adapter can do. The core checks this list, not the
+      # agent's name.
+      #
+      #   :push               — pushes events itself, no polling needed
+      #   :blocking_reply     — can wait for an answer and feed it back to the session
+      #   :structured_options — brings a ready-made list of answer choices
+      def capabilities = []
+
+      def supports?(capability) = capabilities.include?(capability)
+
+      # hook payload → Event, or nil if the event isn't interesting.
+      def to_event(_payload) = raise(NotImplementedError)
+
+      # Reply → the hook response body.
+      def to_response(_event, _reply) = raise(NotImplementedError)
+
+      # Register itself in the agent's config so events start arriving.
+      def install!(_url, secret: nil) = raise(NotImplementedError)
+
+      def uninstall! = raise(NotImplementedError)
+
+      def installed? = false
+    end
+  end
+end