5 OneChat is one AI agent in a single chat that never ends. A daemon owns
6 the agent and its files, and a terminal client and a Telegram bot talk
7 to it. It is in early development. Linux is supported.
13 OneChat keeps its data and its token file in one directory. It uses the
16 #. ``ONECHAT_DIR``, when it is set.
17 #. ``$XDG_DATA_HOME/onechat``, when ``XDG_DATA_HOME`` is an absolute
18 path. A relative value is ignored.
19 #. ``~/.local/share/onechat``. With no home directory, OneChat exits
22 OneChat creates the directory with mode 0700.
28 ``config.json`` in the data directory holds the settings. OneChat does
29 not create it. A missing file or field takes the default, and an unknown
35 "endpoint": "chatgpt",
36 "compactor": {"model": "gpt-6.1-sol", "effort": "high"}
40 ``chatgpt`` (the default) sends model calls to the ChatGPT backend
41 with the subscription login. ``api`` sends them to the OpenAI API
42 with the key in ``OPENAI_API_KEY``, which must then be set. With
43 ``chatgpt``, OneChat ignores ``OPENAI_API_KEY``.
46 The model and the reasoning effort of the summaries. The defaults are
47 ``gpt-6.1-sol`` and ``high``.
53 The ``chatgpt`` endpoint needs a login with a ChatGPT account:
59 The command shows a link and a code. Open the link on any device, enter
60 the code, and approve the login. Device code login must be allowed in
61 the ChatGPT security settings. OneChat writes the tokens to
62 ``auth.json`` in the data directory, with mode 0600, and refreshes them
63 before they expire. The file belongs to OneChat only. Do not share it
64 with the Codex CLI, because each program rotates the refresh token and
71 Start the daemon, and then the client in another terminal:
78 The daemon owns the root agent in ``agent/`` in the data directory and
79 listens on the Unix socket ``onechat.sock`` there. In the client, each
80 line is a message to the agent, the line ``/stop`` interrupts the
81 running turn, the line ``/stop NAME`` stops the subagent NAME, and
82 Ctrl-D ends the client. The client shows the replies, the tool calls,
83 and the first lines of each tool result as they happen. It also shows
84 each message that the user sends from another client, with the client as
85 a mark, such as ``[telegram] text``. When a subagent starts, the client
86 shows ``[NAME] started``, and it shows the whole report of the subagent,
87 which starts with ``[NAME]``, but not the tool calls of the subagent.
88 The daemon is the only process that uses the token file while it runs,
89 so ``onechat login`` and ``onechat probe`` refuse to start until it
92 The agent runs commands with bash as the user in its working directory,
93 with no sandbox. It has the rights of the user, also on the token file.
95 When the user asks for it, the agent starts subagents for long tasks.
96 Each subagent has a name, such as ``GreenOtter``, and runs in the
97 background while the agent answers other messages. It gets the view of
98 the agent and its task, and it runs its tools as the agent does, in
99 ``agent/subagents/NAME/work``. A task in a repository gives the path of
100 the repository. The steps of a subagent go to its own log in
101 ``agent/subagents/NAME``, not to the chat, and its final reply comes
102 back to the agent as one message that starts with ``[NAME]``. The agent
103 can send a subagent more messages: a running subagent reads them between
104 its tool calls, and a finished one goes on from its log, and its reply
105 comes back in the same way. When the user stops a subagent, the chat
106 gets a note, and the report of the subagent is logged, but it starts no
107 turn. Each model call of a subagent has the name in the ``agent`` field
108 of ``agent/usage.jsonl``.
110 ``agent/config.json`` holds the settings of the agent. The first start
111 writes it with the defaults and a random ID. Do not change the ID: the
112 prompt cache key comes from it.
118 "id": "0123456789abcdef0123456789abcdef",
119 "model": "gpt-6.1-sol",
121 "workdir": "/home/user"
124 ``workdir`` is an absolute path, and its default is the home directory.
125 ``agent/instructions.md`` holds the user's instructions: who they are,
126 how their files are organized, and how they want work done. The prompt
127 ends with them, and a change applies at the next call.
133 The daemon also connects the agent to a Telegram bot when
134 ``telegram.json`` exists in the data directory. It polls the Bot API for
135 new messages, so it needs no open port.
137 #. Make a bot with BotFather and keep its token.
139 #. Find your numeric Telegram user ID.
141 #. Write the token and the ID to ``telegram.json``, and give the file
142 mode 0600, because the token is a secret. The daemon refuses the file
145 #. Start the daemon, open a private chat with the bot, and write.
149 {"token": "123456:ABC-token-from-BotFather", "owner": 123456789}
151 The bot reads only the private chat of the owner and ignores all other
152 updates. Each text message goes to the agent as a user message, the line
153 ``/stop`` interrupts the running turn, and the line ``/stop NAME`` stops
154 the subagent NAME. The bot sends the replies in parts of at most 4096
155 characters, with their Markdown as Telegram formats: bold, italic,
156 strikethrough, code, code blocks, links, and headings as bold text. When
157 Telegram refuses the formats of a part, the bot sends the part again as
158 plain text. Each error goes as a short message in plain text. It shows
159 the typing action while a turn runs. It does not send the tool calls.
160 For a subagent it sends only ``[NAME] started`` and ``[NAME] finished``,
161 ``[NAME] stopped``, or ``[NAME] failed``, because the reply of the agent
162 carries the content of the report. It sends each message that the user
163 types in the terminal client, with the mark ``[terminal]``.
165 ``agent/telegram-offset.json`` holds the ID of the next update. The bot
166 moves it past an update only after the message is durable in the log, so
167 a restart of the daemon does not lose a message. A crash just after the
168 write of a message can make the message repeat once. A network failure
169 or a rate limit makes the bot wait and try again, and does not stop the
176 ``onechat probe LOG COUNT [BUILDS]`` measures the compactor on a log. It
177 appends the first COUNT messages of LOG, one JSON object ``{"kind",
178 "text"}`` on each line, to a new chat in ``probe/`` in the data
179 directory, and builds its tree with real model calls. The calls use the
180 quota of the account. The run stops at the first failed call, after 660
181 calls, or when the used percent of a quota window grows by more than 15
182 points. At the end it reports the calls per message, the cached share of
183 the input tokens, the retries, the line sizes, and the quota at the
184 first and the last call. BUILDS, from 1 to 8, limits the model calls at
187 A test writes a generated log of readable made-up messages:
191 ONECHAT_PROBE_LOG=probe.jsonl go test -run TestProbeLogHasTheSyntheticMix
197 Nix supplies the Go toolchain and all tools. Enter the development shell
204 Or enter it directly:
210 The shell sets ``ONECHAT_DIR`` to ``.devenv/onechat`` in the checkout,
211 unless it is already set. Development data goes there, and Git ignores
221 Format and check all files:
229 ``bin/check`` and ``nix build`` run a short replay of the synthetic log.
230 ``nix flake check`` also runs the full replay of 100,000 messages.