Changelog — MAX
Read release notes and changes in the MAX CLI, including fixes and new capabilities.
See what changed in releases: new capabilities, fixes and changes that may affect your commands. Start with your installed version, then use the linked guide for the feature you want to try.
Notable changes to @wirecat/max-cli, one section per version, newest first. Versions follow Semantic Versioning; the command interface may still change before 1.0.0.
0.111.0 — 12.11.2026
What's new
- The run record keeps the sync progress. Each progress line of
messages syncis now also async.progressevent with counters, in any output format, somax <profile> runs show <run>shows what WireCat Desktop saw and when. - Part of a name in
from:andchat:.from:Ярослав*andchat:*Квестор*match part of a name, alias or @username, ignoring case and ё/е. If nobody matches the pattern, the answer isnot_foundwith the closest names. If more than 50 match, it isquery.too-large: make the pattern narrower. A number and an exact name work as before. If several people have exactly that name, the error now also suggests those whose name only contains it: for «Ярослав», also «Ярослав Орлов». - Part of a word in message text.
*договор*without a field finds «Договор», «ДОГОВОРЫ» and «переговоры», also in a large archive, insideAND,OR,NOTand together withchat:anddate:. It needs three letters in a row. - The start of a word searches where a whole word does.
счет*without a field now also finds the word in voice message transcripts, in text and in file names, andmatched_insays where exactly.
Changed — may break scripts
- Built on cli-core 0.642.0 (was 0.638.0). The store stays at version 66. Details in the cli-core changelog.
*часть*in message text is searched as written. Before,*мои*also found «мой», and*cafe*also found «café». Now only case and ё/е are ignored. What to consider: write the letter as it stands in the text, or search for the whole word (мой), which still finds all its forms.- Remote embeddings over plain http only on this computer.
--base-urlorembedding_base_urlwith anhttp://address on another machine is now refused withmodel.address-refused: the messages would travel over the network unencrypted. What to consider: usehttps://or run the model on this computer (localhost,127.0.0.1). A saved setting is still read, and other commands do not break. list:in message search is now refused. It is a mail field, and a query with it used to find nothing without saying why. Now the answer isquery.unsupported-fieldwith an explanation.- Test data is hidden from people lists. A person whose addresses are all test ones (
example.com,.testand similar) or were added as an example is no longer shown in any view,allincluded.
Fixed
messages sync --allshows progress inside a chat. MAX returns a chat 30 messages at a time with a pause of 5–10 seconds, and the progress line came out only when the chat was finished: on a large chat WireCat Desktop showed «Чат 1 из 36 · 0» for minutes. Now thefetchedcounter grows after each page, at most twice a second.- The password storage hint no longer sends you to cron. If the profile has signed in but the token cannot be read, the error and
max <profile> doctornow say that the storage is most likely locked: right after the computer starts, it opens when you log in to the system, and a scheduled run waits for that by itself. The advice aboutXDG_RUNTIME_DIRstays for cron and ssh. - Daily and one-time schedules wait out a MAX request to wait. If such a timer run gets
rate_limited, it waits as long as MAX asked, if that is no more than six hours, and tries again instead of being lost until the next day. What to consider: a schedule with--everyand a manual run still fail with an error at once. *слово*in text suggests a way out. If such a pattern goes through too many words, the error now suggestsслово*, which also finds the forms of the word.
0.110.0 — 11.11.2026
What's new
participants_countin search and statistics.participants_count<10finds messages in chats with fewer than ten people, sostats messages show -- 'kind:private OR (kind:group participants_count<10)'counts private conversations without large groups.
Changed — may break scripts
- Built on cli-core 0.638.0 (was 0.633.0) and cli-base 0.96.0 (was 0.93.0). On first open the store moves to version 66.
contacts unlinknow requires--from person:<uid>or--from person:me: the person the account is unlinked from. Without it the command refuses and says what to add. An account already recorded for another person does not move. Details in the cli-core changelog.
Fixed
- Setting the system clock back no longer stops sync for hours. If the computer's clock ran ahead and was corrected, max assumed MAX had asked it to wait and refused every sync, although it had not even contacted MAX. Now the wait is recalculated by the size of the shift, and the refusal no longer says that MAX asked to wait.
0.109.0 — 10.11.2026
What's new
muted:in search and statistics, from@wirecat/cli-core0.633.0.muted:falseleaves out chats where you turned off notifications, sostats messages show -- 'date>=30d muted:false'counts only what sync still reads.stats messages responsesandstats messages waitingunderstand it too.store import, from@wirecat/cli-core0.633.0. It loads made-up chats, people and messages from a file marked synthetic into a test store, for example the Desktop sandbox. It does not touch the owner's real store.
0.108.0 — 10.11.2026
Changed — may break scripts
- Built on cli-core 0.630.0 (was 0.624.0). On first open the store moves to version 63. Each person's view is kept with the person, and saving chat members does not touch the rows of those who stayed, so
people listin memo filters, counts and pages in SQL. Whoever wrote in a private chat or a small group now counts as the owner's person, no rule joins anyone to the owner, and a name matches in Cyrillic and Latin. A tool on an older cli-core that saves members erases the saved views, so max, tg and memo move together. What changed between the versions is in the cli-core changelog.
0.107.0 — 09.11.2026
Changed — may break scripts
- Built on cli-core 0.624.0 (was 0.618.0). On first open the store moves to version 61 (people's ties to the owner, additions only). What changed between the versions is in the cli-core changelog.
search messages --timeout 30ssearches for up to 29 seconds. Before, search stopped after 2 seconds however much time the run was given, and a correct query on a large store failed in WireCat Desktop. Without--timeoutthe limit stays 2 seconds, also for agents and MCP.schedule pause <имя>andschedule resume <имя>: the schedule is taken off the timer and kept, andschedule runstill runs it.--atcan be given several times:--at 08:30 --at 18:00.
0.106.0 — 09.11.2026
What's new
- A pull request writes its changelog lines to a separate file,
changes/<ветка>.md. Open pull requests no longer conflict in the "Unreleased" section.pnpm docs:checkchecks each such file, andbin/releasecollects them into the version's section. During the transition an entry under "Unreleased" also works.
Fixed
max serveexits when its version is outdated, and the service starts the new one. Once a minute it checks whether the shared store has moved to a format this version can no longer write, and whether a newer version of max is installed. If so, it writesserve.outdatedto the log and exits with code 3, and the systemd service (Restart=on-failure) starts the installed version. Why: before,servecould keep running on an old version and save nothing.- After
max store recover run, a normal sync loads again what may have been lost in the damage. Recovery marks as not loaded everything the chat held from one day before the last passed deep check. From cli-core 0.618.0 (was 0.616.0).
0.105.0 — 09.11.2026
What's new
max <профиль> account remove --keep-data|--delete-datasigns the profile out of MAX and erases it on this computer. The command ends the session on the MAX server, then deletes the token from the keyring and the profile files: the state, the socket and themax servelog, and with them what the shared layer keeps for the profile.--keep-datakeeps the messages in the store, and search finds them.--delete-datadeletes them too. Other profiles are not affected. Why: until nowsession endforgot only the token and left the rest of the profile behind. What to consider: whilemax serveruns for the profile, the command refuses, assession enddoes: firstmax <профиль> server stop. The bot token (bot:<профиль>) stays: a bot is a separate account. A run with moved folders forgets only its own copy and does not sign the owner out of MAX.
0.104.0 — 08.11.2026
Changed — may break scripts
maxopens a store that memo and other WireCat tools have already upgraded, and upgrades it to version 57 itself. A store at version 56 or later cannot be opened bymax0.103.0 and older or by any tool on cli-core older than 0.606.0: they ask you to update. What to consider: updatemax,tgand memo together (cli-core 0.606.0, 0.607.0).--offlineon a command that needs MAX answerspermission_error(offline.refused) with exit code 5. Before,chats inspect,chats events,chats folders …andupgradeansweredvalidation_errorwith code 2. What to consider: a script that expects code 2 there must expect 5 (cli-core 0.607.0).contacts contextandcontacts prepareread only accounts of the same sphere as the profile. A personal profile no longer shows a person's mail, messages, events and meetings from work accounts, and a work profile no longer shows them from personal ones. The answer has a newaccountsfield: each account read and its sphere (cli-core 0.605.0).- A name typed with «е» finds a chat or person with «ё». A name that used to match one chat or person may now match two (
АленаandАлёна). Thenmaxrefuses and names both, as with any ambiguous name (cli-core 0.601.0). - Search reads a query as plain words more often.
?at the end of a word is a question mark:счёт?finds «счёт». Text with a colon, a link, a bracket or an unclosed quote (встреча в 10:30) is searched as words, where search used to refuse (cli-core 0.602.0, 0.604.0).
Fixed
- A damaged store file stops writes and names
max store recover. Before, a command that got «database disk image is malformed» from SQLite failed withinternal_error. Now the answer isconfiguration_error(store.damaged), and the next commands that write refuse until a deep check or recovery passes. Reading works (cli-core 0.605.0). - People you separated are not joined again. A third contact with the same email address could join two people again after you had separated them (cli-core 0.605.0).
0.103.0 — 07.11.2026
Changed — may break scripts
max schedule agentandmax schedule commandtake--deliver-to <маршрут>instead of--to <маршрут>, andschedule listnames the fielddeliver_to(cli-core 0.600.0). Schedules saved with--todeliver the result as before.
Fixed
- Opening the store no longer drops the SQLite file's locks. The file used to be opened with truncation, which released the POSIX locks that other processes held, so two writes could overlap (cli-core 0.599.0).
max mcp serve --permission <ключ>=denynow also applies tomax's own commands. Before, the levels given to the MCP server did not reachmax's checks: an agent could runcontacts sync,messages transcribe,watchand themax botcommands (for example,bot comments send) under the profile's saved levels, and the request went to MAX. Now such a command getspermission_errorbefore it connects. What to consider: an agent run with such levels no longer goes through the sharedmax serve(it knows only the saved levels); it opens its own connection, as a run with--permissionin the terminal does.
0.102.0 — 05.11.2026
Fixed
max bot listandmax bot list --checkwork without a profile name again. In 0.101.0, on a computer without profiles they answered with the errorname a profile, and the only way to get the list of bots was to put any word first:max personal bot list. The command reads every bot on this computer, so it needs no profile, as intgandwa. What to consider: the othermax bot …commands still need a profile, andmaxdoes not pick one for you.
0.101.0 — 05.11.2026
Fixed
- A Bot API request and a file upload no longer keep a finished command in memory until the end of their time limit. The limit timer ran to the end even after MAX had answered, and held everything the command had loaded. A process that makes many requests in a row, such as
max bot mcpormax bot updates watch, grew with every request. The same is fixed for--timeoutof themax botcommands.
0.100.0 — 05.11.2026
What's new
max config migrateadds to the file every setting that is missing there, with its built-in value, and every write bymaxto the file does the same. All settings are visible and editable inconfig.json,serveandtranscribe_modelincluded, without the documentation. Your values, their order and unknown keys stay;config unsetdoes not write the removed setting back, and a plain read does not rewrite the file (cli-core 0.563.0).max config showshows the built-in value of each setting and what it does, and alsokeep_successful_runs_for_daysandruns_size_limit_mb, which were missing from the list.- From cli-core 0.563.0:
config repairfixes the JSON syntax of the settings file;stats messages responsesandstats messages waiting;tasks status,tasks reviewandtasks acknowledge. - From cli-core 0.564.0–0.566.0:
store chats statuscounts the chats the archive holds from the first message, in part, or not at all;stats tasks showtakes a query and counts the tasks opened and closed in a period (-- created>=30d);has:transcriptfinds voice messages with a transcript.
Changed — may break scripts
- A write to a task that was changed after you read it now ends with the code
conflict, exit 15, notconfiguration_error, exit 3. The reason is stilltask.stale(cli-core 0.567.0, cli-base 0.77.1). max account listno longer shows a bot as an account without a sign-in. A name that only a bot has is left out; a name that is both your account and a bot is markedbot: true(cli-core 0.567.0).- The new error code
conflict(exit code 15) is inmax commands --jsonand in the MCP tools' error schema (cli-base 0.77.1). It means a write was refused because what it changes was changed after the read. A write to a task from a stale copy returns it (see above). search allranks every source in one list, searches mail by meaning too, and finds records for a question written as a sentence (cli-core 0.564.0). Before, the hits of each source came one source after another, and a question found only the records that held all its words.
0.99.0 — 03.11.2026
What's new
wcat maxruns the program, andwcat --helpshows it. The package installs the commandwcat-maxnext tomax, andwcat-max --wcat-describeprints the program's name, version and description forwcat.
0.98.0 — 02.11.2026
What's new
projects evidenceandprojects statusread the linked chats by purpose:--purpose sales,workor--purpose all. Without the flag they take the default purposes (the built-in one iswork). A chat left out of the selection does not disappear silently: it is amissingrow with the purpose, the number of messages and the command that reads it (cli-core 0.553.0).projects evidence --include-proposedalso reads chats with people who are proposed for the project but not yet confirmed; everything they bring is markedproposed(cli-core 0.553.0).projects evidence --compactprints one line per finding, linked chat, skipped chat and member (cli-core 0.553.0).
Changed — may break scripts
- The JSON of
projects statushas a new fieldpurposes, and a chat skipped by purpose has the account, the chat id and the counts (cli-core 0.553.0).
0.97.0 — 02.11.2026
What's new
max servecatches up on what arrived while it was not running. 30 seconds after it connects, it reads the chats that have messages newer than the ones in the local copy when it started: no more than 7 days back, up to 500 messages per chat, and for at most 5 minutes. After more than a week of downtime, runmax <profile> messages sync --allonce (cli-core 0.552.0).server installenables the service, andservestarts at every login and after a reboot. To enable a service that an earliermaxinstalled, runmax <profile> server installagain;server statusshowsstarts_at_login. A service from a max source checkout is written but not enabled (cli-core 0.552.0).messages syncfollows history limits: by default it does not read a group of more than 50 people (history_group_members_max), reads a group 365 days back and a personal chat 1095 days back (history_group_days,history_dialog_days), and says what it skipped inlimited.--full-historyreads further for one run; to always read large groups, raise the setting. New messages are never lost (cli-core 0.551.0).max <profile> projects status <проект>shows where a project stands, from the local copy only (cli-core 0.551.0).--compactprints one line per item for an agent, from the same answer as--json(cli-core 0.550.0).messages listreads a window from both sides, offline too:'date>=2026-10-01 date<2026-10-20'reads forward from the start and stops at the end. Before, such a query was refused (cli-core 0.547.0).- A command that needs a chat or a message also takes the reference that other WireCat programs print (
msg:…,chat:…) (cli-core 0.546.0).
Changed — may break scripts
- A search that ran out of time ends with
timeoutand the reasonquery.time-limitafter about 2 seconds, not withvalidation_error/query.too-largeafter a long run. The query is valid; addchat:ordate:to search a smaller part of the copy (cli-core 0.552.0). - Text of the form
<вид>:<без пробелов>in place of a chat is read as a reference, and a reference to another account or messenger is refused with its own reason. A key after--is read as a key (cli-core 0.546.0).
Fixed
- A sync whose output was closed finishes its work. A closed pipe (EPIPE) used to cut it off (cli-core 0.552.0).
messages deletewithout a message number refuses before it connects (cli-core 0.551.0).page.nextofmessages listruns as written, and an "inclusive" start keeps a message sent at exactly that moment (cli-core 0.547.0).- If the keyring is locked,
max serveand a scheduled run try again instead of asking you to sign in again. A profile that had already signed in on this computer but could not read its token answeredauthentication_error(code 4). Theserveservice withRestartPreventExitStatus=4then did not restart until a manualserver start, and a timer that fired at boot before login lost its run for the whole day. Nowmax serveand a run under a timer (MAX_SCHEDULED) answerprovider_unavailable(code 12) with the reasoncredentials.unreachable: systemd restarts the service, andschedule exec(cli-core) repeats the run until a login opens the keyring. A command typed by hand answers as before.
0.96.0 — 02.11.2026
What's new
max <profile> messages download --offlinecopies a file that is already on this computer, without connecting;--attachment <n>picks one file of the message, and amsg:reference can be passed in place of the chat and the message (cli-core 0.532.0).- The first run of a new version updates the agent instructions that an old version installed. An outdated copy of
SKILL.md(Claude Code,~/.agents/skills, Hermes) is rewritten once, with one line on stderr; the command does not touch a copy that is missing, has no version, or is a link.MAX_NO_SKILL_REFRESH=1turns this off (cli-core 0.544.0).
Security
- An agent can no longer weaken permissions from its own shell.
max <profile> config set|unset permissions…run by an agent (Hermes, OpenClaw, Claude Code and others that mark their shell) can only make a level stricter, not weaker, and only the owner changesmcp.authorityandbot.api. So the read-only mode that the WireCat app sets holds even if a chat message talks the agent into runningconfig set. Change permissions in a terminal outside the agent (cli-core 0.544.0).
0.95.0 — 01.11.2026
What's new
projects evidence --jsongives a fetch command for each linked chat inlinked_chats[].sync_command: the same line as in the text, or null if the chat is fully loaded (cli-core 0.517.0).
Fixed
projects evidenceno longer writes "held from only" about a chat that reached its first message: now it is "held from its first message, behind since " or "with gaps". The progress ofmessages syncshows how far it got as a date ("back to "), not as a message key, which in MAX was a number of milliseconds (cli-core 0.517.0).
0.94.0 — 01.11.2026
What's new
max <profile> projects evidence <project>(projectsCommandfrom cli-core). Shows what this account's saved messages hold about a project: the name, key, other names, words, contacts, confirmed members and linked chats.--sync-first(off by default, not in MCP) first fetches the linked chats that the store does not hold back to--since-time, one at a time, within--sync-time(3 minutes for all of them). A chat that ran out of time stays partial, withmissingandnext. If a fetch fails (for example, it needs a runningserve), the chat is markedfailedwith a reason, and the read goes on. Access is closed by themessagespermission (cli-core 0.511.0).
Changed — may break scripts
- The MCP call log names the agent that made the call, not
max-mcp(cli-core 0.509.0): the name the client gave itself (clientInfo.name, for exampleclaude-code), else the agent that started the server, elsemax-mcp. A filter onmax-mcpdoes not find new calls. The name is the client's own words, a label only.
0.93.0 — 31.10.2026
What's new
messages sync --jsonwrites the sync progress to stderr (cli-core 0.507.0): one JSON line at a time, counts only, without ids or chat names. stdout still carries one answer.
Changed — may break scripts
search messages --discoversearches by meaning even when the query has-,NOT,OR, brackets, phrases orexact:(cli-core 0.506.0). Before, such a query ran only as a strict search. Now the words are still searched with the whole query (discovery.method: "lexical-strict"), and messages close in meaning to its words are added. Each message found by meaning, and each added reply or follow-up, matches every field of the query and holds none of the excluded words.
Fixed
- The description of
doctoris the same as in the other CLIs: "the state this installation is in, without connecting unless --online" (cli-core 0.507.0). Before, max replaced it with its own, and the summary differed from the shared one. search messages --discoverwith a narrow filter (chat:,date:) ranks by meaning the messages of the filter itself, if there are no more than 100 000 of them, not the 100 nearest in the whole archive, so the page fills up (cli-core 0.506.0).search messages --discoverworks with a database opened read-only (cli-core 0.506.0).- A long rebuild in one process no longer breaks a write in another with the error "database is locked" (cli-core 0.506.0).
- The fallback file for the token is now handled by cli-base 0.68.0, with no code of its own in max (cli-core 0.507.0). A token from the private file is read from there, and rotation leaves it there;
session startmoves it back to the keyring and deletes the copy in the file, as in 0.92.0. The warning about an unavailable keyring is still one per run.
0.92.0 — 31.10.2026
What's new
search messagessays how many messages match in all:page.total(cli-core 0.501.0).--jsonhas a newpage.total: { value, relation }in the shape of Elasticsearch'shits.total:eqis an exact number,gtemeans at least (counting stops at 10 000). In the terminal, below the results:showing 1–20 of 144.session start --credential-storage keyring|file. By default the token goes to the system password store, and if that is unavailable, to a file only you can read, with no questions and one warning.filepicks the file right away; we do not recommend it. A token from the file is read first, so a locked store is no longer touched for it; the next sign-in with the store moves the token back there. The answer says where the token went:credential_storage. Needs cli-core 0.503.0.
Changed — may break scripts
- max requires cli-base 0.67.0 (cli-core 0.501.0).
0.91.0 — 31.10.2026
What's new
messages list --offline,tasks agendaandsearch allsay when the local copy holds a chat only in part (cli-core 0.493.0). A chat not fetched back to its start, or never fetched, givesmeta.complete: false,missingandnextwith the stepmessages sync <чат>(first for the answer's window, if it has one). Intasks agendaeach row hascompletenessandheld, and in the text such a chat is marked[partial]or[never fetched]. The exit code stays 0.
Changed — may break scripts
search messages,search all,tasks agendaandmessages list --offlineanswermeta.complete: falseif a chat they read is held in the copy only in part (cli-core 0.493.0). Before, it wastrue, and the gap was visible only inmissingandnext. A script that tookmeta.completeas a sign that "no source failed" must read the reason inmissing. The exit code is still 0.- Follow-ups in
search messages --discover --jsoncome as a snippet of up to 240 characters, like the result itself:items[].follow_ups[].excerptinstead oftext(cli-core 0.496.0). In 0.90.0 a follow-up came as the whole message, and on a real archive one long message added 7 KB to an answer of five results.messages context <ref>shows the whole message. The terminal output did not change.
Fixed
search messages --discoverwith a quoted date and time no longer fails withquery.invalid-date(cli-core 0.496.0). The "22:00" fix in 0.90.0 replaced the colon between digits inside quotes too, sodate:["2026-08-21T21:30:00Z" TO "…"]with--discoverdid not work.search notesand the notes insearch allfollow the query's fields for what is found by meaning too (cli-core 0.496.0).date:todayortag:workwithout--exactreturned about 20 notes that matched none of the fields. Now only the query's words are searched by meaning, and every field and every excluded word (-draft) applies to all results.- For a Drive document,
date:and the shownupdated_atare one time, the time of the edit in Drive (cli-core 0.496.0). Before,date:read the time the copy changed, and of 20 results fordate>=30d, 16 showed an older date. - A run with moved folders can no longer erase the owner's sign-in from the keyring, and does not sign out of MAX (cli-base 0.65.5, WC-SECR-24). Before, only a run with
MAX_*_DIRcounted as moved; a run with a differentHOMEor XDG folder touched the realmax-clientry, andsession endin it erased that entry. Now such a run reads the owner's sign-in but does not change or delete it, and a new sign-in is written to a temporary entry.session endon the owner's sign-in ends nothing and answerskept: "owners-sign-in". bin/maxin a source checkout no longer copies tokens: the checkout reads the owner's sign-in, andscripts/seed-worktree.tsmoves only the profile's state.- max requires cli-base 0.65.5 and cli-core 0.496.0.
0.90.0 — 31.10.2026
What's new
max <профиль> search messages '<вопрос>' --discovershows follow-ups: later messages that may cancel or change what was found (cli-core 0.492.0). Up to two later messages are added to the first five results, from any chat the search reads, that share a rare word with it (its stem is in no more than three messages of the archive): this shows when a decision was later cancelled and the cancellation was not a reply. In--jsonthis isitems[].follow_ups, in the terminal the lineslater, shares a rare word. What to consider: follow-ups appear once the word stems are built.
Fixed
search messages --discoverno longer fails on a question with a time or a ratio ("before 22:00", "1:1") (cli-core 0.492.0). The colon between digits was read as a field filter, and the search ended with the errorquery.invalid-syntax.- Correction to 0.89.0: in that version, a write to the store also stopped failing with "database is locked" while another WireCat program writes to it (cli-core 0.485.0). The 0.89.0 entry does not say so.
- max requires cli-core 0.492.0 (cli-base stays at 0.65.0).
0.89.0 — 31.10.2026
What's new
contacts list notes:finds part of a word in any letter case, Cyrillic included (cli-core 0.490.0). Before,notes:КВАРТdid not find a note with the word «квартира»: case-insensitive matching worked only for Latin letters, and the search read every note. Now notes are searched through a three-character index and answer in milliseconds. What to consider: a query shorter than three characters is refused with the error «search needs at least three characters» (an empty query still selects nothing). The store is upgraded to version 40 the first time it is opened; notes saved earlier get the index in batches duringsearch notesorstore migrate, and until then the old method searches them. A build of another WireCat program with an old cli-core does not write the index into an already upgraded store, so update all WireCat programs at once.
Fixed
- Correction to 0.88.0: the contact card's fields are named
firstName,lastNameanduserId. The 0.88.0 entry about theCONTACTattachment calls themfirst_name,last_nameanduser_id; #874 renamed them, and the entry stayed as it was. - max requires cli-core 0.491.0 (cli-base stays at 0.65.0). 0.491.0 fixes only the mail sync, which max does not use.
0.88.0 — 31.10.2026
What's new
- A contact card in a message (
CONTACT) is read as a contact: the attachment hascontactwith the name,first_name,last_nameanduser_id. Before, such an attachment came only with the kindcontact, without a name. What to consider: MAX does not send the phone number in the card, so there is nophonefield.
Fixed
- A search by chat title and by contact name ignores letter case in any alphabet (cli-core 0.484.0). Before,
max <профиль> chats list 'title:СТАС*' --offlinedid not find the chat «Стас»: the local store compared case-insensitively only for Latin letters. Now it finds it;name:intags listworks the same way for chat titles and contact names. What to consider: the store is upgraded to version 38 the first time it is opened, with nothing for you to do. If an older build of another WireCat program opens the same store and renames something, the search by the new name works after the store is next opened by a new build. max --helpshowsgcalin the "Works with" list (cli-core 0.482.0). It is Google Calendar next to the other WireCat data;max setupoffers to install@wirecat/gcal-cli. If a script checks the text of the first screen, it has one more line.- max requires cli-core 0.484.0 (cli-base stays at 0.65.0).
0.87.0 — 30.10.2026
Fixed
- Personal chats in the local store get a title from the other person's name, and
max <профиль> chats list 'title:Стас*' --offlinefinds them. Before, a personal chat had no title in the store, and each sign-in to MAX erased whatchats listhad managed to write, so an offline search by title found no personal chat at all, and agents had to go through every chat. Now, after a sign-in, the title is taken from the other person's name (the same namecontactsshows), for personal chats written earlier too. What to consider: a personal chat whose other person is neither in the contacts nor among the members of chats stays without a title untilchats listruns with the network.
0.86.0 — 29.10.2026
Changed — may break scripts
max contacts infois replaced bymax contacts show(cli-core 0.477.0). It shows the whole contact, and the phone number is now printed in full, without a mask. What to do: in scripts, replacecontacts infowithcontacts show. The old form of the command no longer exists.- max requires cli-core 0.478.0 (cli-base stays at 0.65.0).
Fixed
sender_is_meininbox,review,search messagesandsearch all(cli-core 0.478.0). These answers did not mark your own messages; now they have the field, asmessages listdoes.
0.85.0 — 29.10.2026
Changed — may break scripts
max mcp servewithout a profile no longer serves every profile (cli-core 0.470.0). It exits with code 2 (validation_error) and lists the profiles on this computer. Name a profile as the first word (max work mcp serve), a list (max mcp serve --profiles work,personal) or all of them (--profiles all).--http,mcp server start|stop|status,mcp revokeandmcp configwork the same way. Who is affected: an MCP client entry from 0.83.0–0.84.0 withmax mcp serveand no profile stops starting — print it again withmax mcp config --profiles allor add the profile. Restart a background server of all profiles started by those versions withmax mcp server start --profiles all. The MCP Registry entry already runsmcp serve --profiles all, the Docker image the profileglama, anddoctor --onlinethe profile it checks.- Every message in the answers of
messages list,show,context, search andinboxhassender_is_me(cli-core 0.473.0). It is true for your own messages, including in MAX, where the owner has no sender id. A script that checks the answer against a strict copy of the schema will reject the new field. - max requires cli-core 0.473.0 (cli-base stays at 0.65.0).
max --helpnow also namesmailunder "Works with". - The agent skill is published on ClawHub as
wirecat-max. Install:openclaw skills install @wirecat/wirecat-max. Themax-clientry is no longer updated.max skill installstill writesskills/max-cli/.
0.84.0 — 27.10.2026
Changed — may break scripts
- cli-core 0.469.0 and cli-base 0.65.0. cli-core 0.469 accepts only cli-base 0.65, so both versions move together. cli-base 0.65 has the verbs
serveandrevoke, so their entries in the linter baseline are removed, and itscli-dev bundlefinds a server started with a flag beforemcp serve. Since cli-core 0.468, the MCP server offers a command that only loads data into the store through the read tool.
0.83.0 — 27.10.2026
Changed — may break scripts
- The MCP server starts with
max mcp serve, andmax mcponly shows help (cli-core 0.463.0). The same for a bot:max <бот> bot mcp serve. Browser-app logins are ended bymax mcp revokeinstead ofmax mcp --revoke. The entries thatmcp configandmcp addprint,mcp server start,doctor --online, the MCP Registry entry and the Docker image already runmcp serve. What to do: in your MCP client entry or script, replacemax <профиль> mcpwithmax <профиль> mcp serve, andmcp --revokewithmcp revoke. The old form of the command no longer exists. skill show,skill statusandskill installwith--jsonprint{ item, meta }(cli-core 0.462.0). The fields that were at the top level (name,content,written) are now insideitem. The Windows installer already reads the new shape.max account listshows whether a profile is signed in on this computer (signed_in), and search results of every kind name the fields an agent reads as data (untrusted). A script that checks the answer against an old strict copy of the schema will reject the new field (cli-core 0.464.0 and 0.466.0).- Every run is recorded by default, successful ones too (cli-core 0.467.0). Successful runs are kept 7 days (
keep_successful_runs_for_days), failed ones 30 (keep_runs_for_days); the runs folder stays underruns_size_limit_mb(200). With the defaultrecord_input, a successful send leaves the typed text in a local record with0600permissions for 7 days.record: falsenow keeps failed runs (before: nothing),record_input: falsehides what you typed everywhere, and--no-recordkeeps nothing.kept_because_failedis no longer set inrun.json. - max requires cli-core 0.467.0 and cli-base 0.64.0.
What's new
- A request in a run record is marked as network traffic and knows its attempt. Each frame of the personal protocol and each Bot API request in
events.jsonlgets"level": "wire"andtransport(max-wsorhttp). A Bot API request also getsattempt, and a retry after429or a failure getswait_ms, how long the client waited before it. Retries ofmessages sendwhile the file is not ready (attachment.not.ready) are numbered the same way. Needs the cli-core that records every run. max upgraderestarts the browser MCP server thatmax mcp server startstarted, on the same port, with the same address and limits (mcp_servers, old → new version); a server started by hand stays and is named. Agent sessions over stdio on the old version are listed (stale_sessions): restart them from the agent app. Works from the next upgrade on (cli-core 0.464.0).
Fixed
max mcp servewithout a profile marks the profiles that are not signed in. Before, every profile was listed, and an app could pick a profile without a login and get an error. Now the app's menu and the description show "— not signed in" for such a profile, bot-only profiles are not shown (a bot has its ownbot mcp serve), and a call for a profile without a login answers how to sign in:max <профиль> setupor from WireCat Desktop.- The login page of the browser MCP server explains that a code works for one login. After an app logs in, a new code appears in WireCat Desktop and in
max mcp server status(cli-core 0.466.0). - The max-cli skill no longer sends the agent to
search allandmessages sync --all. Search starts withsearch messages; notes and Drive only when the owner asks. If nothing is found, the agent says so and offers a limited download of one chat, and starts it only after the owner agrees. The same changes in the README and in docs (search, usage, index, troubleshooting).
0.82.0 — 27.10.2026
What's new
- With no session, the error also offers WireCat Desktop.
no session,has not logged in yetand an expired token now say: a command in the terminal or sign-in in WireCat Desktop (Tools → MAX → Manage). Over MCP, the agent is told not to ask for codes and passwords (cli-core 0.452.0; with it 0.451.0: meaning search on the native ONNX Runtime on Windows too). max mcpwithout a profile serves every profile, on stdio and with--http(cli-core 0.450.0). An AI app needs one connector for MAX, not one per profile. Each tool (max_tools_search,max_read,max_write) has a requiredprofilefield (every profile on this computer, with no default), and the agent is told to ask if you did not name the account. The call goes to that profile's ownmax <profile> mcp: it starts on the first call and closes after 10 idle minutes, so the profile's permissions, session and log apply as before.max mcp --revoke,max mcp configandmax mcp server start|stop|statuswork without a profile, with their own login.--public-urlaccepts a path,https://<name>.ts.net/max. The MCP Registry entry runsmax mcp.max <profile> mcpdid not change.
Changed — may break scripts
- max requires cli-base 0.63.0 (cli-core 0.450.0). Nothing max uses changed in it.
Fixed
- Every command spends less time getting ready (cli-base 0.62.0, cli-core 0.449.0). The check of shared commands describes each command once, not again for every group above it. In tg, a warmed-up
run(["--version"])got faster: 29 ms instead of 49. Why: the check took about 60% of each command's preparation. What to check: nothing; the check catches the same changes. - Meaning search and
--discoverrun on the native ONNX Runtime on Windows too (cli-core 0.451.0). Aftermax <профиль> models download, the text models and the reranker use the native library on Windows x64 and arm64, as already on Linux and macOS: 2–3 times faster than WebAssembly. The download takesonnxruntime.dllfrom the npm packageonnxruntime-node(113.5 MB, once, checked by sha256). Image models (CLIP, SigLIP2) also go through the native library where it is installed: about twice as fast. Results are the same.
0.81.0 — 26.10.2026
What's new
- Meaning search and
search messages --discoverreranking run 2–3 times faster on Linux and Apple Silicon Macs (cli-core 0.448.0). Models are now computed by the native ONNX Runtime library instead of WebAssembly: on one archive,--discoverwent from 4.6 to 3.2 s, with the same answers. The library (10–42 MB, an official Microsoft release, checked by sha256) is installed bymax <профиль> models download; search downloads nothing itself. What to check: on a machine already set up, the speed-up comes after the nextmodels download e5-smallormodels download mmarco. Windows, Intel Macs and Alpine still run on WebAssembly.
Fixed
--discoverreranking sees the found message itself, not only the one it replies to (cli-core 0.447.0). Before, the model read the original message first in full and cut the text at 512 tokens, so with a long original the reply fell out of its window. Now the first 300 characters of the original are taken.
0.80.0 — 26.10.2026
What's new
max <профиль> session start qr --json --answer-stdinsigns in without a terminal, for WireCat Desktop (cli-core 0.443.0). The MAX cloud password is asked as aneedsline on stderr ({"event":"needs","field":"password","secret":true,"prompt","hint"}), and the answer is read as one line from stdin;session start tokenasks for the token the same way. Without--answer-stdin, a run without a terminal still refuses, so an agent's shell never waits for a question. The answer is not printed and does not reach run records.max <профиль> mcp server start|stop|statuskeeps the HTTP MCP server in the background (cli-core 0.445.0).starttakes--public-url,--portand--permission, likemcp --http, and returns once the server listens;statusshows the port, address, one-time login code and the apps logged in;stopstops only its own server. WireCat Desktop starts and stops it from the Manage panel.max <профиль> tasks list claimed_by:<кто>shows the tasks that worker took (cli-core 0.441.0).claimed_by:*lists every claimed task,NOT claimed_by:*those nobody took; a pattern such asclaimed_by:claude-code:*works too. Only live claims count: an expired claim holds nothing.
Changed — may break scripts
--recordhelp says what a run record actually keeps. Before: "ids and timings, never message content", although since 0.79.0 the record keeps the command line as you typed it. Now: "with the command as typed and secrets hidden; record_input false leaves the typed words out". What to check: the text ofmax --helpanddocs/commands.mdchanges; a check that compares help will see the new line.
Fixed
- The browser-app login code of
mcp --httpis renewed when it expires (cli-core 0.445.0), not only after a wrong or late entry. The login page says the code is shown in WireCat Desktop or in the terminal. A secondmcp --httpfor the same profile now refuses to start. search messages --discoverwith reranking reads only the first 300 characters of the message the hit replies to (cli-core 0.447.0). Why: a long original message took the model's whole window, and it scored that message instead of the reply. What to check: the order of--discoverresults with a reranker model may change; the model does about 40% less work.
Security
- A run record hides more secrets by their shape, not only by the flag name (cli-core 0.440.0–0.444.0). Replaced with
[redacted]: tokens of known formats (GitHub, OpenAI and Anthropic, Slack, AWS, Google, Stripe, npm, Telegram bot token, JWT, PEM private key),BearerandBasic, the value after a "secret" name (password=…,пароль 1234,pin 1234,код 123456), long random strings and hex keys; other words stay. A phone number with "+" or 11–15 digits in a row is hidden wherever it was typed, message text included. What to check: a full commit hash and a positive id of 11–15 digits also become[redacted]; a number without "+" written in groups (8 912 345-67-89) is not recognised. - If the settings failed to load, a run record hides the typed words (cli-core 0.442.0). Before,
record_inputwas then treated as on, even if the settings saidrecord_input: false.
0.79.0 — 26.10.2026
What's new
max skill install --for hermesinstalls the skill for Hermes Agent, andmax skill statussays which copy Hermes reads (cli-base 0.59.0). The command adds~/.agents/skillsto Hermes'sskills.external_dirsthroughhermes config set, keeping folders already listed, and if that fails it copies the file into Hermes's home folder. If Hermes is not installed, the command fails withnot_foundand writes nothing. Plainmax skill installand--for allstill write only the copies for Claude Code and~/.agents/skills.skill status --jsonhashermesbesidetargets.- A run started by OpenClaw or Hermes Agent names that agent (cli-core 0.437.0). In
runs show, a command the OpenClaw agent ran hasagentset toopenclaw, plusfrom_chat: trueif a chat message started it; a Hermes run has its session, so a task Hermes took is held by one session. - New setting
record_input(cli-core 0.439.0).max personal config set record_input falsehides what you typed in run records;config setandconfig showshow it. - The
max-cliskill tells OpenClaw and ClawHub that it needs themaxprogram and how to install it (metadata.openclaw:requires.binsand the npm package@wirecat/max-cli). Ifmaxis not on PATH, OpenClaw marks the skill as not ready and offers to install the package. Claude Code and Codex do not read this block.
Changed — may break scripts
- A run record keeps the command line as you typed it (cli-core 0.439.0).
argvinrun.jsonand inruns shownow shows the chat name, the search query, the message text, where[redacted]used to be. Secrets are always hidden: values of flags such as--tokenand--password, a password in an address, a long string that looks like a key, the body ofbot api … --body, a phone number typed aftercontacts lookup. Why: the record should show exactly what was run. What to check:max personal config set record_input falserestores the old hiding for a profile,max config set record_input false --defaultsfor all of them; a script or check that expects only[redacted]inargvwill see the typed words.doctor reports createstill hides them in the report.
Security
- A first word that cannot be a profile does not reach the run record (cli-core 0.438.0). Before, such a run stored it as
profile, although it could be message text or a person's name. - An error that quotes
--token=…orpassword=…no longer keeps the value (cli-core 0.439.0).
Fixed
- The
max-cliskill no longer offers the agentnpx @wirecat/max-cliwhenmaxis not found. It runs the installedmaxby its full path:"$(npm prefix -g)/bin/max" personal doctoror"$(pnpm bin -g)/max" personal doctor. Why:npxdownloads code, and plugin catalogues may forbid that; usuallymaxis installed but not on the agent's PATH. Agents read the skill throughmax skill show.
0.78.0 — 26.10.2026
Fixed
maxpresents itself as the current MAX web client:appVersion26.10.7 and Chrome 154 (was 26.9.8 and Chrome 151, read on 25.09). MAX refuses client versions it no longer supports;max doctorshows the date 2026-10-26.npx skills add WireCatLabs/max-clioffers only themax-cliskill. Before, it also showed four skills for max developers (add-command,parity-audit,release,test-live): they were in.claude/skills, and skills.sh looks for skills there too. Now they are indocs/dev/skills.- A vector is deleted as soon as no text in the store uses it (cli-core 0.435.0). Before, vectors stayed after an image's picture changed, a meeting transcript's text changed, or a chat was cleared (
store clear --left, a chat merged into another).conversations embeddings clear --chatnow also removes the chat's message vectors, not only its conversations';conversations embed --chatcreates them again. What to check:store rebuilddeletes vectors left by earlier versions and reports their number inunused_vectors_dropped;store checkcounts them invectors.unused. - The installation has one copy of sherpa-onnx, not two (cli-core 0.433.0). In 0.77.0, max moved to sherpa-onnx 2.0 before cli-core, and the installation grew by about 15 MB; now cli-core is on 2.0 too. Commands and their output do not change.
Changed — may break scripts
- The shared store moves to version 34: CLIs on cli-core 0.433.0 and older can no longer open it (cli-core 0.434.0). Meaning search takes candidates from a sqlite-vec index in the store instead of going through every vector; the answer is the same as with the full scan. The first open of the store by this version builds the index over the vectors already saved, in short batches. Why: going through every vector gets slower with each message that has a vector. What to check: update together with max every CLI that reads the same store (tg, wa, memo, zm, drive); old ones will refuse it and ask to be updated. The extension is part of the installation (
@wirecat/cli-core-sqlite1.1.0); if it did not load, a command that needs the store fails withstore.vector-extension-missingorstore.vector-extension-failed; reinstall max.store checkshowsvector_indexesand failschecks.vector_indexeswhen the index disagrees with the vectors. max upgradehelp shows only the examplemax upgrade --check(cli-core 0.433.0). Why: themax upgradeexample without a flag, copied and run, upgraded the program at once. What to check: only this line changes in the output ofmax upgrade --helpandmax commands --json.- An Anthropic model gets the key in the
Authorization: Bearerheader, notX-Api-Key(cli-core 0.433.0,@anthropic-ai/sdk1.3). Why: that is how the new version of the Anthropic library sends the key. What to check: this affects onlymodels.<назначение>.base_urlwith theanthropicprovider, that is, your own gateway instead of Anthropic's address: such a gateway must read the key fromAuthorization.
What's new
search messages --discoverreorders the first 50 results with a reranker model once it is downloaded (max models download mmarco, 136 MB; cli-core 0.435.0). The model reads the question together with each result, its chat, author, date and the message it replies to; its score is blended with the search score, and the other results keep their order. Each reordered result hasdiscovery.reranker_score, andscorestays the search score. Without the model, the order is unchanged and the search says so: anot reranked: …note in the terminal,missing/next(models.download) in--jsonand MCP. Reordering gets 15 seconds on top of the word search; if it does not finish, the results stay without it. The new profile settingsearch_rerankerselectsbge-reranker-v2-m3(588 MB) or turns reordering off (off). Nothing is downloaded on its own, and no text leaves the computer.models listshows rerankers with the kindreranker.search allalso finds messages by meaning, once the e5-small model is downloaded and messages have vectors (cli-core 0.435.0). Word and meaning matches are merged into one list of messages, and each one'sfoundBysays which search found it. A query with NOT or with a filter inside OR and groups, as well as--exactand--backend server, searches by words only. Without the model or vectors,search allsearches by words as before and says why: amessages: meaning search not used: …note,missing/nextin--jsonand MCP.
0.77.0 — 25.10.2026
Changed — may break scripts
- Voice message recognition runs on sherpa-onnx 2.0, and the installation grew by about 15 MB. Before, max and cli-core used one copy of sherpa-onnx 1.13.8. Why: every dependency was updated to its latest version; 2.0 removes only the speech-synthesis parts, and recognition works as before. What to check: until cli-core moves to sherpa-onnx 2.0, the installation holds two copies of this package. Commands and their output do not change. The unused
string-widthandwrap-ansiare no longer installed with max; if your script loaded them from the max installation, install them separately. - A failed run of a
botcommand names the Bot API call where it happened. Inruns showandruns list,error.httpnow hasmethodandendpoint_templatebeside the HTTP status, for example{ "method": "GET", "endpoint_template": "/chats/:id", "status": 403 }; before, it had only the status. Why: a status alone does not show which of the command's calls failed. What to check: chat, user and message ids in the path are written as:id, a video token as:token, and query parameters do not enter the template, so real ids and tokens do not reach the record. Bot requests in--traceand in the run record have the same two fields, and the--traceline shows them after the operation name (← getMyInfo GET /me 200 …). A script that parses the--tracetext will see an extra column.
What's new
store reset --dry-runlists what a reset would empty and deletes nothing (cli-core 0.429.0): the store's files and their size, every data table with its row count, whether a backup comes first, and whether serve or another process holds the file.search messages --discoveralso finds messages close in meaning, once the e5-small model is downloaded andconversations rebuildhas given messages their own vectors (cli-core 0.432.0). Each result'sdiscovery.found_bysays which search found it. Until then, search runs by words as before and explains why. Nothing is downloaded, and no text leaves the computer.
Fixed
- A bare
--versionanswers before the program loads: the bin starts through@wirecat/cli-core/cli/start(cli-core 0.429.0).
0.76.0 — 25.10.2026
Fixed
- A failure in the middle of a command is now reported like any other error. Instead of a Node stack trace, it prints an
internal_error(command.crashed): one line in a terminal, a JSON error object otherwise; the exit code is still 1. Why: a stack trace tells a script nothing and can put text on the screen that does not belong there. What to check: if a script parsed the stack trace on stderr, have it read the error object.
What's new
max doctor --jsonlists every problem in the settings file inconfig.issues(cli-core 0.423.0). Each problem is{ kind, file, profile?, key?, line?, column?, what, fix? };kindisinvalid_json,unknown_setting,unknown_permission,missing_settingorinvalid_value. For invalid JSON,lineandcolumnshow where parsing stopped; for the rest,fixis aconfig unsetcommand that removes the key and runs as written. The setting's value is not included in the answer. With problems in the file,doctorstill answers and exits with code0; without a profile name it answers withprofile: null.config showworks with a file that has problems and names each one with the command that removes it.config unsetalso removes a key that no schema knows, including one at the root of the file (max config unset <key>).max skill statusandmax skill show --for claude|agents(cli-core 0.427.0).statussays whether the installed SKILL.md matches this version;show --forprints the installed copy.max store tables listlists the tables of the shared archive, andstore infoshows more about the file (cli-core 0.427.0).- A run record says who started it and what went wrong (cli-core 0.425.0).
run.json,runs list,runs showandsearch runsgaincli_command,argv(content and secrets are[redacted]),agentand, for a failed run,error.
Changed — may break scripts
npm install -gchooses the agent for the skill only fromMAX_INSTALL_AGENT.TG_INSTALL_AGENTis no longer read.- The
doctoranswer has aconfig.issueslist instead of theconfig.errorstring. If settings could not be resolved because of a profile lock, a flag or an environment variable, the message is insettings.error. - Old setting names are no longer recognized.
default_profile,analysis_provider,analysis_model,analysis_base_urlwith theMAX_ANALYSIS_*variables, and camelCase names (sendsPerHourand others) are unknown settings like any other: the command refuses and names theconfig unsetthat removes the key. The analysis model is set inmodels.analysis.provider,models.analysis.modelandmodels.analysis.base_url. messages syncandbot messages syncare checked under their own keysmessages.syncandbot.messages.sync(cli-core 0.421.0). A level onmessagesorbot.messagesstill applies to them, and a denial written directly onmessages.syncorbot.messages.syncnow stops the command. Bot commands check a read denial before connecting.- A saved permission key that no command checks stops both bot commands and
--dry-run. The error names the key and theconfig unsetthat removes it;config show,setandunsetwork so the file can be repaired. - Former command names get the ordinary "unknown command" answer, without a hint.
max personal search mailno longer names memo: mail is searched bymemo search mail. - A run without a named profile is recorded without
profile, not with"profile": "default"(cli-core 0.424.0). - In a run record, a failed command's stack starts with the package name and has no Node lines (cli-core 0.425.0). A stack line is
MaxClient.connect @wirecat/max-cli/client.js:1497, notclient.js:1497; there are no morenode:internallines. config setwritesconfig.jsonwith mode0600, not0644(cli-base 0.57.0). The file holds the owner's profiles, accounts and paths. A program that reads the settings as another user will not read them after the nextconfig set.
Security
max doctornamesconfig.jsonand its folder if other users can read them, and thechmodcommand that fixes it. In--jsonthis isfiles:{ checked, ok, problems: [{ path, mode, want }] }; the file should be0600, the folder0700. For each problem stderr gets a lineto make it private: chmod 600 '<path>';doctoritself does not change permissions. The folder is checked also whenMAX_CONFIG_DIRsets it. The block is present without a profile name and when settings did not resolve; it is also included in thedoctor reports createreport. On Windows permissions are not checked:filesis{ checked: false, reason }.
0.75.0 — 25.10.2026
What's new
Changed — may break scripts
- Old names of statistics and search permissions are no longer recognized. Previously the keys
messages.stats,chats.stats,tasks.stats,messages.search,conversations.searchandtopics.searchstopped the command with a hint on how to rename them; now such a key simply has no effect, and a denial saved under the old name no longer applies. Rename them tostats.messages.show,stats.chats.show,stats.tasks.show,search.messages,search.conversationsandsearch.topics. - The shared database moves to version 33 (cli-core 0.420.0). Once this version opens the database, a CLI on an older cli-core refuses to work with it and asks to be updated, so update all WireCat CLIs that share the database together.
0.74.0 — 25.10.2026
Changed — may break scripts
bot store fetchis nowbot messages sync; thebot storegroup is gone. The command does the same as the personalmessages sync, so it now has the same name;storeis the local database. The old name answers with a hint naming the new one. If your settings keeppermissions.bot.store.fetch, commands refuse to run until the key is renamed topermissions.bot.messages.sync.
0.73.0 — 25.10.2026
What's new
-
chats requests confirm|reject <chat> --allanswers every request to a channel at once. The number of requests is first checked against the profile's permissions and the hourly action limit, then one MAX request is sent. Use it only for a channel where every pending request should get the same answer. Selecting by--linkis not available: the current MAX interface does not report which link a request came through. -
Bot member, comment and allowed-recipient lists accept a field query. Member and comment identifiers are passed to the Bot API before the page limit is applied; the recipient list is filtered when read and does not change sending permissions. A comment also shows its string
idwhen the API provided it inbody.mid.
Fixed
-
watch --jsonlprintsitemrecords and a finalend. A source failure ends the stream with an incomplete summary;--jsonrefuses before subscribing. The allowed-recipient list uses the shared native query. -
Archiving no longer stops at a call event next to a file. The file is saved and its checksum verified; messages that contain only a call need no download.
-
The diagnostic report uses the shared WireCat module. The MAX format and technical event fields are kept; message content is excluded, and identifiers get labels inside the report.
-
A permission denial does not hide a command. The CLI and MCP catalogues keep the commands and show their current availability with the reason for the denial; a call still checks permissions. The bot's MCP also shows setup commands within the bot profile.
-
Changing settings uses the shared WireCat implementation.
config set|unsetkeeps its answer format, the MAX settings and the permission limits; the shared module checks and writes the file.
Changed — may break scripts
-
A second webhook address is added with
--append.--add <chat>remains the folder-change flag. An unknown chat membership and the webhook type list are now omitted instead ofnull. -
Shared command contracts cannot change silently.
commands info --jsonshows the source definitions, schemas, error reasons and explicit MAX differences. Contact events useat:andscope:instead of time and scope flags, and diagnostic records usestarted_at:.
Security
- Dependency resolution excludes vulnerable Vite versions. Production dependencies are checked for both the saved and a fresh resolution.
0.72.0 — 24.10.2026
Added
-
After login,
max servemakes more of the requests made by web.max.ru: direct-chat contacts' profile cards and online status, plus stories for the chat list, missing folder chats and the next chat-list page after first login. This reduces differences from the web client; MAX can still distinguish the tool. These are read requests whose responses are not displayed. Push notifications remain unsubscribed (network requests). -
The first ordinary terminal run of
maxasks three shared questions: search languages, installing other WireCat tools and whether changes are permitted. Choosing read-only limits all profiles, including MCP, even with a more specificallow. Agents, pipelines, JSON mode and CI are not prompted. Change answers throughmax setup.
Changed — may break scripts
-
Shared commands use canonical names; old names are removed (cli-core 0.406.0):
contacts profile→contacts info,contacts timeline→contacts events,contacts alias→contacts aliases,chats link→chats links,metadata refresh→metadata sync,store reindex→store rebuild,commands schema→commands info,stats messages counters refresh→stats messages counters sync,models text key→models keys,models audio list→models list kind:audio,doctor report→doctor reports show. Old commands refuse to run and name the replacement; hidden option aliases are also removed. Update scripts, schedules and saved MCP calls. An old permission path such aspermissions.metadata.refreshnow stops execution withconfiguration_errorand names the replacement. -
max <profile> watch --jsonemits{ "type": "item", "data": … }records and a final{ "type": "end" }(cli-core 0.400.0). Messages and events use snake_case fields and canonical message values with references. Normal stops and timeouts produce a completeend; source failure produces an incomplete one and an error code. Update readers of the previous raw lines. -
Run search is
max <profile> search runs(search runs), replacingruns search. Putstatus:,error_code:,operation:andprofile:in the query:search runs status:failed error_code:timeout. There is no alias; migrate saved MCP requests. -
Statistics select rows with query terms. Replace
--chatand--exactwithchat:andexact:; rankings usemessage_kind:andmin_messages:, discussions usemin_views:andmax_replies:, unanswered questions useolder_than:. Update CLI and MCP calls;--sourceand--timezoneremain options. -
Commands that change what future runs may do require
permissions.mcp.authority: alloworaskin MCP, defaultdeny:config set|unset,recipients add|remove|clear,replies …,schedule command|agent|remove,skill install,flood clear, model keys and similar operations. The agent cannot change this key throughconfig set. See what MCP does not offer. -
Archive maintenance, server control, model downloads and report creation are available through MCP. They have individual permission keys such as
store.backup,server.start,models.download,doctor.reports.create, defaultask. Check permissions when an agent should only read: MCP permits a requested write ataskwithout a confirmation form. -
Raw
bot apirequires explicitpermissions.bot.api: alloworaskfor an agent. The default isdeny; broaderbot: allowdoes not enable it. The agent cannot changemcporbot.apiin settings or replace the wholepermissionsobject; other individual keys may be changed whenmcp.authoritypermits it. In max these calls retain permission and recipient checks and journal writes. -
Read similar-task pairs through
tasks duplicates list [query...]. Thetasks duplicatesgroup no longer lists them. Migrate saved CLI and MCP calls to explicitlist. -
events listreturns ISO 8601 dates and string identifiers.starts_at,ends_at,deleted_at,created_at,updated_atare no longer millisecond numbers;idandevent_series_idare no longer numbers. Update JSON readers relying on the old types. -
doctor reports createchecks permissions before writing a file. Invalid configuration returns code 3 because write permission cannot be checked. Read the reason throughdoctorand fix the setting first. With valid configuration, safe report creation is also available underMAX_READ_ONLY.
Fixed
attachments downloadskips service events and inline keyboards. These attachments contain no file; previously a chat containing them stopped copying with code 13. Verify existing copies throughattachments check; downloading again preserves them.
0.71.0 — 23.10.2026
Added
-
Voice transcripts match word forms and speech-recognition distortions (cli-core 0.396.0).
max <profile> search messages риелторfinds both «риелтору» and «реелтора» in transcripts. A result found only through distortion hasmatch: "corrected"andcorrections. Numbers, phrases,exact:and written message text are not expanded. Text an agent saves for a voice message is also a transcript. The store migrates to version 29 on first run. -
More commands are available through MCP within profile permissions (cli-core 0.398.0):
config show,doctor report,runs list|show|path,store status|info|check|export|reindex,store jobs cancel|retry|clear,attachments move,attachments jobs status,commands schema,guide,skill show, model lists,replies status|test|consents show,schedule list,server status|logs; for bots,list,chats leave,chats admins add|remove,commands set|clear,webhooks list|set|delete. See what MCP does not offer for exclusions and reasons. These are the names used in this historical release. -
max <profile> review --offlineanswers from the local archive instead of refusing (cli-core 0.398.0). It shows only synchronized material and warns about missing data (missingin JSON). -
Verified file copies.
attachments download <dir>saves available files across chats with size and SHA-256;attachments check <dir>checks copies offline.attachments jobscontrols explicitly enabled daily Linux copies. Finished copies survive interruptions and message-history clearing.attachments move <dir> <archive-dir> --before-time <time>moves older images to another verified archive and records their new location for checking and avoiding repeat downloads. -
Saved voice-transcript search matches word forms and spellings distorted by speech recognition.
text:searches written text only;exact:disables expansion for that word.
Fixed
- Examples in
--helpcan be pasted and run:Example:includes thepersonalprofile (max personal review "date>2h") instead of failing with “name a profile” (cli-core 0.398.0). - Saved meeting searches are no longer displayed or removed by message-search commands.
- Command correction hints retain the chosen profile; help shows short descriptions and examples.
Changed — may break scripts
- In MCP arguments, message deletion accepts
message, chat export acceptschat, and task-duplicate operations accepttaskand, for a pair,other_task. Update saved requests usingmessages,chatsordup. CLI positional order is unchanged. - Reference commands
commandsandcommands schemareject--jsonl: use--jsonfor one document.
0.70.0 — 23.10.2026
Added
contacts prepare <person>prepares a conversation briefing from saved messages, tasks, facts and notes, with source links. It is shared with tg and wa and does not connect to MAX (cli-core 0.394.0).- Command help includes invocation examples from cli-core 0.394.0.
Changed — may break scripts
- Reading no longer marks chats read.
messages listno longer accepts--mark-read;inboxandreviewno longer accept--mark-reador--no-mark-read;catch_up_marks_readis no longer valid. Send a receipt explicitly withchats mark-read. - Unknown nested permission keys are rejected as configuration errors before connecting. Correct the misspelled key instead of relying on the former warning.
0.69.0 — 22.10.2026
Added
- Date-filtered JSON responses identify the timezone used to interpret the date and the UTC window (cli-core 0.385.0):
meta.timezonenames the zone when absent from the input;meta.windowgives UTCsinceanduntilboundaries. Applies tostats chats show,stats chats retention,stats messages unanswered,stats messages discussion,stats contacts responses,stats chats newcomers,contacts context,search conversations,runs search,messages sync,store export,replies test, and toinbox,review,chats events,chats members historywithtime:ordate:query terms. This makes the selected window visible. Fields are new and optional; existing fields stay unchanged.search conversationsnow interprets a date without a time in--timezonewhen supplied. - Chat JSON includes
muted_until(UTC end of muting) andmarked_unread(chat marked unread), from cli-core 0.382.0.
Changed — may break scripts
- Archive-based
inboxandreviewomit muted and archived chats (cli-core 0.382.0). The archive now stores these flags from MAX, bringing its results into line with MAX. Usechats listto find these chats if a script previously expected them in inbox results. - An unwritable store returns
permission_error, exit code 5, reasonstore.not-writable(cli-core 0.381.0), replacinginternal_errorwith “this is a bug”. Update scripts handling the former exit code.
Fixed
- Names copied with emoji find the chat or person (cli-core 0.381.0). A copied emoji can contain an invisible selector absent from a typed one; «Семья❤️» previously failed to find «Семья❤».
0.68.0 — 22.10.2026
Changed — may break scripts
- Dates or times without a zone in
--since-time,--until-time,--at-timeandchats mute --untiluse the computer's timezone; a date alone means local midnight (cli-core 0.379.0, cli-base 0.48.0). Previously2026-09-01meant UTC midnight. An explicit zone (…Z,+02:00) still wins; a command's--timezonetakes precedence over the computer zone. An upper date-only boundary includes the whole local day. This matches the owner's calendar day. Scripts expecting UTC must specify it, for example2026-09-01T00:00:00Z; JSON times remain UTC withZ. stats chats retentionandchats stats showinterpret--since-timeand--until-timein--timezone; retention's date-only upper bound includes the whole local day (cli-core 0.380.0).stats charts,contacts timelineand MCPstatsidentify the zone inmeta.timezoneand the UTC window inmeta.window.
Fixed
max watchdisplays message times in the computer's zone, announcing it astimes in <пояс>before the first message. Previously the zone was unnamed.--jsonllines are unchanged in this release.max doctorand login refusals after frequent attempts display times as2026-10-21 16:03 Europe/Madrid, replacing the easily misread UTC form2026-10-21T14:03:00.000Z.max doctor --jsonretains UTC.
0.67.0 — 21.10.2026
Fixed
- A locked or unavailable Linux keyring warns and falls back to a credentials file (cli-base 0.47.5). The keyring is read only through Secret Service. Previously a failure could silently save credentials in kernel memory, which disappears at logout or reboot.
0.66.0 — 20.10.2026
New
- The store keeps a chat's history (store version 25, cli-core 0.366.0). A change to a chat's id, title,
membership or visibility is written to
chat_revisionswith the old and new value; a read by the old id of a chat that got a new one finds it. The store moves to version 25 when first opened; nothing is sent.
Fixed
- A chat you left is found by any of its ids (cli-core 0.368.0):
store export,store status,messages thread,--chatandchat:in search, tags, tasks and the other reads of its saved history.chats trackandstore gaps planrefuse a left chat: "you left chat ". max guide catch-upand the first screen ofmax --helpquote the filter:max review 'date>1d' --unanswered 4h. Without quotes the shell read>as a redirect: it created a file named1d, andreviewran without the filter. On cli-core 0.370.0 the scenario check in the tests catches such characters outside quotes.- "Works with" spells memo's scenario title the same way as memo and the other tools: "One person across every tool", capitalised.
0.65.0 — 19.10.2026
New
store clear --leftnames the chats it deletes (cli-core 0.353.0–0.362.0). The refusal without--allow-dangerouslists the first 20 by id, title and message count; the new--dry-runshows them all inleftand deletes nothing; the answer after deletion carrieslefttoo.
Changed — may break scripts
- Without a terminal,
session start qrandsetupprint the QR code as text, and--qr-fileis gone. The owner logged in through a PNG that the agent opened in an image viewer — a separate window that is easy to lose. Now the code goes to stderr as plain text (█▀▄characters, no colour, readable on a dark theme), and the agent pastes it into the chat as a code block. With--jsonthe code is also a{"event":"qr","qr":{"text","expires_at","scan"}}line on stderr. In a terminal the code is drawn as before. A script with--qr-filenow gets an unknown-option error. How an agent logs in: sessions.md.
Fixed
- A chat the owner returned to no longer stays marked "left" (cli-core 0.352.0). An incomplete chat list and a
login remove that mark from the chats they name; "archived" and other states stay. Before, such a chat could
disappear from
max chats list, andstore clear --leftdeleted it with its messages. A full list still marks as "left" the chats missing from it.
0.64.0 — 19.10.2026
New
session start qr --qr-file <png>andsetup --qr-file <png>, as in tg and wa: the QR code is written to a PNG for the agent, without a terminal. The file is created with mode0600from the start and removed after login. QR login now goes throughloginQrfrom cli-core 0.347.0, one for all three CLIs.- The next step in
--jsonoutput and in an error carriesline— the whole command with the profile (cli-core 0.348.0):"line": "max personal mcp config"beside"command": "mcp config". A copied barecommandfailed with "name a profile".commandis unchanged; MCP answers have noline.
Changed — may break scripts
- A narrow terminal no longer opens the QR code in a browser. The code is not drawn, and
maxsays to widen the window or pass--qr-file. Why: QR login is now shared by tg, max and wa, and a browser that opens by itself could not be moved into cli-core for all three. MAX issues one code per run, so there is nothing to wait for in a narrow window: stop the command and run it again wider or with--qr-file. - Without a terminal,
session start qrandsetupanswer the same as tg and wa: "shows a QR code to scan — run it in a terminal, or pass --qr-file ".
Fixed
- The login step in
setupis called "Link this device" and no longer asks to scan a QR code before it is drawn. The line under the code itself says where to scan; in a narrow terminal, only the hint to widen it. - A narrow terminal no longer asks to scan a QR code that is not there (cli-core 0.350.0).
session start qrandsetupwrote "scan this code with the MAX app on your phone" before the code; if the code did not fit, only the hint to widen the window or pass--qr-filefollowed. Now the line "scan in the MAX app on your phone" comes after the drawn code or the--qr-filenote, and a narrow terminal shows only the hint. - Hints in errors and notes name the profile: "the store is behind this build —
max personal store migrate" instead ofmax store migrate, which failed with "name a profile" when copied. The same for the hint to download the speech model:max personal models audio download gigaam-v3.
0.63.0 — 19.10.2026
New
max --helpandmaxwith no command show a short first screen (cli-core 0.345.0): what max can do, the other WireCat tools and where to go next —max commands,max guide,max help options,max skill show. It no longer prints the full command list and all the global options.max guide— scenarios: which commands to run, in order, for a common task. Four scenarios:catch-up(go through what has piled up),find-what-was-said(find what someone wrote),agent-on-a-timer(a scheduled agent that cannot send) andpost-as-a-bot(write as a bot).max guide <имя>prints the steps,--jsonthe same as data. Thememo guide person-briefscenario is shown under "Works with".max help optionsprints the options of every command,max --help-allthe former full help.max commandswithout--jsonprints the commands by section (Read, Write, Organise, Automate, Set up), one line per command;max commands <путь>narrows it.- Each command's help ends with Returns, Next usually and Example lines, and the same lines are in the command reference.
Changed — may break scripts
npm install -gno longer installs the agent skill by itself. It silently wrote to~/.claude/skillsand~/.agents/skills, and npm hides the install script's output. Now the skill is installed bymax <профиль> setupormax skill install --for all;MAX_INSTALL_AGENT=all(or an agent name) at install time installs it right away, as before. The Windows installer passesallitself and behaves as before.max --helpno longer lists the commands and global options. A script that looked for them there needsmax --help-allormax help options.max commandswithout--jsonprints text, even into a pipe. It used to print the whole JSON document (hundreds of kilobytes); a script that parsed it needs to add--json.- A typo in an option of a list that takes a query is an unknown-option error (
unknown option '--limt' (Did you mean --limit?)), not a query word. A negation such as-kind:channelis still part of the query.
Fixed
inboxandreviewdeclare their output (cli-core 0.345.0):max commands schema inboxgives the fields of the message summary, and--json=<поля>with a name it does not have refuses with the list of fields instead of returning empty records.--briefand--fullno longer mention mail in max's help.- A typo in a profile name no longer creates a profile.
max typoprofile chats listrefused but left aprofiles/typoprofile.jsonfile, and then the "name a profile" error andmax completeofferedtypoprofileas a profile on this computer. Now the file appears only at login;session endfor such a name does not create it either. Files left by earlier typos can be deleted from~/.local/share/max-cli/profiles/. max <профиль> doctorwithout a token suggestsmax <профиль> setup, like the README and the "no session" error, notsession start.
Security
- The write ban takes effect before connecting to MAX (cli-core). Under
MAX_READ_ONLY=1or with thereadonlyordenylevel,messages send,messages edit,messages delete --for-everyone,reactions addand other writes first connected to MAX and only then were refused; with a broken login they exited with code10. Now it is code5with no connection, as the security page promises. The refusal stays insends listas a short line: the command key and the kind, and the chat only if its id was given. --dry-rununderMAX_READ_ONLYno longer answers "allowed" for a write that a real run would refuse.max mcpunderMAX_READ_ONLYdoes not offer writes to MAX, and calling such a command throughmax_writegets the ban's refusal, not "no such command".
0.62.0 — 18.10.2026
New
- Over
max mcpan agent gets every command the profile's levels allow (cli-core 0.341.0). The server used to offer 141 hand-written tools; now the tools are built from the commands themselves, and the agent has 181 commands, among themmessages sync,contacts sync,chats members fetch,chats tracking add/remove,contacts link/unlink,mentions confirm/reject/rebuild,conversations embed,images embed,tasks reject,contacts import,account privacy setandchats app. What the agent may not do is decided by the profile's levels: set the area toreadonlyordeny. The full list is pinned incontracts/mcp-catalogue.json. conversations rebuildbuilds again the conversations of chats that changed and computes their vectors with the model on this computer; it does not ask MAX, downloads no model and sends no text anywhere. It replaces the agent toolconversations_refresh.
Changed — may break scripts
max mcptool arguments are named as the command options, in snake_case:chat,limit,query,sync_firstand so on. An agent that remembered the old names needs to askmax_tools_searchagain.- An agent's
search messagesno longer takes the structuredastquery, only the query text, as on the command line. - An agent cannot mark read or act on the owner's behalf:
--mark-readonmessages list,inboxandreview,--as-ownerandmessages send --allow-any-fileare not offered to the agent, and thecatch_up_marks_readsetting does not apply to its runs. Its--newcheckpoints are separate from yours.
Fixed
max mcpanswers every call received before stdin closed, instead of exiting and dropping one still running.max bot mcpdoes not do this yet.max tasks --helpno longer promises thatserveopens tasks. The help said "review and serve add them". Now it says that tasks are opened byreview,inboxandmessages sync, andserveopens only requests from auto-reply rules. Why:servein MAX does not check questions and mentions as they arrive. Anyone who keptserverunning and waited for tasks saw an empty list until the nextreviewormessages sync. What to consider: the behaviour has not changed. An emptytasks listnow says the same (cli-core 0.341.0).max mcp --helpsuggestsclaude mcp add max -- max <profile> mcp(cli-core 0.341.0). The old hint without a profile always failed with "name a profile", and the agent got a server that did not work.- On Node 22, commands that open the store no longer print
ExperimentalWarning: SQLite is an experimental feature(cli-core 0.341.0). Agents took these two lines in stderr for an error. Other warnings are printed as before. tags removeby a tag alias removes it the same waytags addsets it (cli-core 0.341.0).- Startup is a little faster (cli-base 0.45.0): the vocabulary and rule tables are no longer parsed on every start, only when the server for the agent starts.
Security
attachments extract --output-dirrefuses key folders,max's own folders and the store folder (cli-core 0.341.0), as the agent tool already did.
0.61.0 — 18.10.2026
New
tasks agendashows what others owe you (cli-core 0.328.0): open tasks that someone else is doing, in a separate section and asassignedin--json, oldest first.- An agent can mute and unmute a chat (cli-core 0.338.0):
chats muteandchats unmuteare now among themax mcptools. Each is checked against its own key (chats.mute,chats.unmute); nobody in the chat is told. - Examples in the help for
account privacy show,account privacy set,chats mute,chats unmute,messages pin,messages unpin,metadata getandmetadata refresh(cli-core 0.336.0, 0.339.0).
Changed — may break scripts
bot messages send --reply-toaccepts only a MAX message id,mid.…, and so does an agent withreply_to. Any other value is refused before sending (exit code 2). It used to go to MAX as it was.bot messages show,edit,delete,pinandunpinalso accept onlymid.…, and so does an agent. Any other value is refused before the first request (exit code 2). Before,deletewith several ids deleted messages up to the first wrong one and only failed on it (not_found).- A command without a terminal that waits for a person gets 5 minutes, not 30 seconds (cli-core 0.328.0), for
example an agent's
session start.--timeoutandMAX_TIMEOUTstill decide when set. - A command path given as one argument is an error (cli-core 0.328.0):
max 'chats list' --helpused to print the general help with exit code 0; now it answersvalidation_errorand shows how to write it correctly. - An agent no longer sees
offlineonbot me,bot comments list,bot comments getandbot chats members list. These commands always ask MAX and refusedoffline; now the argument is not in the tool description (cli-core 0.335.0). conversations buildandconversations embedare marked as changing something outside this computer (cli-core 0.334.0, 0.336.0): with--analyzeand--providerthey send conversation text to an external service, andsearch conversationswith a remote model sends the query there. UnderMAX_READ_ONLYall three refuse before sending; a model on this computer or on a local server works as before. They do not run throughmax serve. Indocs/commands.mdthis mark now reads "outside this computer: in MAX or in an external service", not "in MAX".- Under
MAX_READ_ONLY,session start,session endandsetuprefuse before they start (exit code 5, "it cannot log in or out"), not from inside the command. - Under
MAX_READ_ONLY, local writes that delete or overwrite what you saved are refused (cli-core 0.336.0, 0.337.0):searches create,searches delete,searches clear,contacts alias set,contacts alias rm,contacts notes add,contacts notes edit,contacts notes remove,contacts link,contacts unlink,tags add,tags auto,tags remove,mentions confirm,mentions reject,attachments text set,chats tracking add,chats tracking remove,conversations links add,conversations links clear,conversations consents revoke,tasks rejectand their agent tools exit with code 5,permission_error. What the store rebuilds itself still works (images embed,mentions rebuild,conversations embed clear,store jobs …), as do sync,serveand task bookkeeping (tasks add,scan,closeand others). Under the lock,tasks closeonly proposes closing the task, and--as-owneris refused. - While MAX restricts the account, no write goes out (cli-core 0.334.0): a reaction, reading a chat, a quiet
pin, changing a title or profile are refused too (
permission_error); reading works. A ban with no end holds writes until you runflood clearordoctor --onlinefinds the account well; in--jsonsuch a ban hasuntil: null. - A send that did not get a file lock held by another process exits with code 9 (
timeout), not 1 (cli-core 0.338.0): nothing was sent, so it is safe to retry. The same forflood clear. upgrade --offlineexits with code 2 (cli-core 0.338.0):upgradeasks npm, so with--offline(and with--check) it now refuses instead of going to the network against the flag.- The agent tool
messages listno longer offerstopic:(cli-core 0.340.0): MAX has no topics, and such a condition is refused, as it already was on the command line.
Fixed
- A store that failed to open is closed (cli-core 0.332.0): on Windows the folder with such a file can be deleted.
doctor report createworks underMAX_READ_ONLYagain. cli-core 0.337.0 forbids under this lock any local write not marked as safe; the report only adds a new file, and now it is marked.- Another process's file lock no longer stops
max serve(cli-core 0.340.0): serve used to wait for it up to 5 seconds, and all commands through it and the keep-alive with MAX stalled for that time. - Two changes to the recipient list at once no longer undo each other (cli-core 0.338.0):
recipients add,removeandclearread and write the list under one lock. store gaps repair --backgroundruns its job instead of failing at once (cli-core 0.339.0).- Hints from
server status,server …and store maintenance name the profile:max <profile> session start, notmax session start(cli-core 0.339.0). upgrade --checkworks underMAX_READ_ONLY(cli-core 0.338.0): it only asks npm about a new version.- Model downloads do not go through
max serve(cli-core 0.336.0):models … downloadandimages models downloaddownload from the model server, not from MAX. - With serve running,
images embedreads images through its connection, as other reads do (cli-core 0.337.0). - A restriction or ban that stopped
watchorserveis remembered (cli-core 0.334.0): the next command waits, as after the same error in an ordinary command.
Security
session endno longer logs out of the account thatmax serveuses. If serve was started manually or by a service,session endused to log out of the same MAX session serve runs on and delete its token. Now the command refuses (exit code 2) and asks you to runmax <profile> server stopfirst. A serve started by another command it still stops itself.session start,session endandsetupnever run through serve (cli-core 0.333.0,logsInOrOut).chats.unmute: readonlynow stopschats unmute(cli-core 0.336.0). Before, unmuting was checked against thechats.mutekey, and its own key had no effect. A setting that has onlychats.muteworks as before untilchats.unmuteis set.
0.60.0 — 17.10.2026
Added
stats messages top --measure reactionsshows reactions by emoji (cli-core 0.324.0): next to the total —👍 4 · 😂 3(up to five emoji, then+N), and in--jsoneach row hasreactions: [{reaction, count}].max <profile> contacts link <person> me(cli-core 0.323.0): mark a contact as you, for an account of yours that the store does not recognise by itself, such aszoom:<id>.
Changed — may break scripts
max bot mcptools are now built from themax botcommands themselves (cli-core 0.325.0) and run through them. Arguments are named as the command's:messages sendandmessages edittakemd/htmlinstead offormat,messages deletea listmessages,search messagesquery,chats members removeperson. New:chats rules show,offlineon commands that read MAX, and the argumentspage,newest,notify,no_block,sync_first. A write at levelaskis allowed for the agent: there is nobody to answer the question.- Not offered to the agent:
session,setup,config,doctor report,bot uploads, and--allow-dangerousonbot comments deleteand onbot api. Only the owner still runs them.
Fixed
- Mentions find fewer false names (cli-core 0.323.0). A word from a contact's name counts on its own only as a first or last name; a contact named like a company ("Smart Agents") is found only by the whole name, and the polite «Ваш», «Вам», «Вас» never count. A saint's name in a place name ("Saint Michael's Bridge") and a city after «в»/«во» («во Владимире») are not names either.
- Your accounts are you (cli-core 0.323.0): an account's own identity is linked to you on the next sync, and your name in your messages no longer belongs to another person.
- An address keeps its city (cli-core 0.323.0): one street in two cities is two places; an address without a city still finds its place on that street.
- In a group tagged
watch-tasks, any member's reply closes a question (cli-core 0.325.0). A direct reply to the question (a reply with a quote) from anyone other than the asker closes the task marked "answered in the group". Before, only your reply closed it, and questions others had already answered stayed open. A message that does not reply to the question closes nothing. In one-to-one chats and untagged groups only your reply still counts.
After updating, re-read old messages once: max <profile> mentions rebuild person-name place.
Security
MAX_READ_ONLYnow refuses login and logout, writes as the bot and store changes:session start,session endandsetuprefuse withpermission_errorbefore connecting. So dobot api(every operation that changes something, andget-updates),bot comments send|edit|delete,bot chats members add,bot uploads put, andstore reset,restore,clear,migrate,repair,copies deleteanddecrypt. Before,session endunder this guard logged out of MAX and forgot the session, and these bot commands sent a request to MAX.store repair --dry-rununder the guard still shows what would be repaired.- A Bot API write that max does not know how to journal is refused with
configuration_errorinstead of going to MAX past the recipient list and the send journal. So an operation that a future Bot API schema update adds cannot slip past the checks. Onlyget-updatespasses without a journal: it sends nothing to anyone.
0.59.0 — 17.10.2026
Added
- A task has an assignee (cli-core 0.320.0):
tasks add --assignee,tasks plan --assigneeand theassignee:filter intasks list— a task can also be something someone owes you. A group taggedwatch-tasksgets a task for every unanswered question, whoever it was asked of.
Changed — may break scripts
- No default profile is chosen any more (cli-core 0.319.0). The
default_profilesetting is not read: if it is still in the settings file, a command without a profile name stops and suggests what to type. Name the profile as the first word —max <profile> …— or setMAX_PROFILE, and remove the old setting:max config unset default_profile.max config set default_profilenow refuses. - A profile named
defaultis an ordinary name.max default mcp confignames the MCP servermax-default, notmax; an entry written earlier works untilmcp setuprewrites it under the new name. tasks applyis nowtasks scan(cli-core 0.320.0). The MCP tool istasks_scan, the permission keytasks.scan. It works the same: it shows which tasks a chat's history would open and creates them only with--yes.- An agent can no longer delete a message for everyone (cli-core 0.321.0). The MCP tool
messages deletedoes not acceptfor_everyone: the argument is rejected as unknown. The owner still deletes for everyone withmax <profile> messages delete --for-everyone. mcp --permissiononly tightens permissions (cli-core 0.321.0). An override that would loosen the profile's level, such asmessages.send=allowfor a profile withreadonly, is refused at server startup, naming the key. To allow more, change the profile's permissions;--permission messages.send=denyand other narrowings work as before.
Fixed
- Denying an agent
chats members listnow takes effect (cli-core 0.321.0). Over MCP the command took its level from thechats.memberskey, and a denial onchats.members.listdid not reach it. tasks show HRB-12shows a project task (cli-core 0.320.0). Before, a task of a project rather than an account was reported as not found.- Tasks open only where something was asked of you (cli-core 0.317.0). In a one-to-one chat, as before, every unanswered question; in a group only a reply to your message and a mention of you; in a channel and Saved messages nothing. Before, any unanswered question in any chat became your task.
- Editing a message does not erase what the edit lacks (cli-core 0.317.0): the send time, reactions and service fields of the stored message stay as they were.
max bot mcptools respect the server's environment. Before, a call bypassed the variables the server was started with: for example, withMAX_READ_ONLY=1the bot still sent a message. Now a call over MCP behaves the same as the same command in a terminal.
0.58.0 — 17.10.2026
Security
-
Internal attachment data stays out of output, including the bot event stream (cli-core 0.315.0). Media keys and the token stay inside the client.
-
WhatsApp state files cannot be sent as attachments (cli-core 0.314.0). The guard checks default directories, environment overrides and symbolic links; ordinary neighboring files remain allowed.
Added
- Names and addresses can be reviewed as mentions (cli-core 0.311.0).
mentions rebuild person-nameandmentions rebuild placefind them in stored text;mentions placeslists confirmed addresses. tasks apply <chat...>lists tasks from selected stored history.--yescreates them with duplicate checks.
Changed — may break scripts
- The first sync opens no tasks from old messages by default (cli-core 0.311.0).
task_first_pass_per_chatenables their creation;tasks applylets you review selected chats separately. Later syncs continue processing new messages.
Fixed
max doctor report createwrites a report even when settings are invalid. Previously it stopped withconfiguration_error, leaving no report to share. The report now records the settings error instead of a profile check, naming the invalid setting without its value, and includes the last failed run.
0.57.0 — 17.10.2026
Added
-
Drive documents appear in shared local search (cli-core 0.301.0), with their Google URL and modification time.
--source drive:<профиль>selects an imported profile.chats documents list <чат>lists documents shared in stored messages without requesting MAX. -
The MCP server loads only when max runs as MCP (cli-core 0.300.0): other commands load about a tenth fewer files at startup.
-
A task card shows tasks pointing back to it (cli-core 0.304.0):
tasks showprintstask:<id> follow-up-of this task, while--jsonand MCP returnlinked_from. Previously only the new task showed the relation, not the closed task. -
max starts about a quarter faster after its first run. Compiled Node code is cached in the system temporary directory, configurable with
NODE_COMPILE_CACHE:max --helptakes about 0.42 seconds instead of 0.56.
Changed — may break scripts
- Settings errors fit on one line without repeating the value (cli-core 0.304.0): the first invalid field, reason and number of further errors, such as
config.json: profiles.default.limitt is an unknown setting (and 2 more problems). An old field (clientId) suggests its new name (rename it to client_id, cli-core 0.307.0). Previously errors listed every problem and accepted field and quoted the value, which could accidentally contain a token. search notesselects notes withsource:internalorsource:filein its query (cli-core 0.303.0). The--typeflag and thetypefield of MCPsearch_notesare removed. The name matches the note'ssourcefield.--source notes:<папка>still selects which accounts to read.- The daily update hint stays silent for
--timeout=5,--help=…and other arguments separated by=, as it does for--timeout 5. The check now comes from shared cli-core. - Commands unsupported by MAX are hidden (cli-core 0.299.0).
messages send,chats mark-readandpolls createhave no--topic, because MAX has no forum topics.messages listrejectstopic:;chats requests acceptanddeclinehave no--allor--link, so a person is always required. Previously these options were shown but refused. max doctorresponds even when settings are invalid. Previously it returnedconfiguration_errorand exit 3; it now returnsconfig: {error: …}, naming the invalid setting, and exits 0.doctoris used precisely when settings are broken. Scripts that checked its exit code for invalid settings must inspectconfig.errorinstead.
0.56.0 — 16.10.2026
Added
tasks rejectrefuses an agent's suggested task close, andtasks list close:suggestedfinds those tasks (cli-core 0.295.0).tasks agendashows the reasonclose-suggested; the owner confirms withtasks close <задача>, without needing--as. Shared-store settingstask_agent_close(onby default) andtask_agent_close_min(0.8) control agent closes;config showdisplays them.- A new task about one closed in the last 14 days becomes its follow-up (cli-core 0.295.0):
reviewandtasks addlink it to the closed task withfollow-up-of. The closed task stays closed and does not entertasks duplicates;tasks showdisplays the link. - 59 default task categories instead of 7, with up to 80 in the list (cli-core 0.295.0 and 0.296.0):
bills,health,travel,fitness,subscriptionsand more.tasks categoriesprints each meaning and its English, Russian and Spanish rule words. A store whose list was saved withconfig set task_categories.*keeps its own;config unset task_categoriesselects the new defaults. - Categories removed from the list remain visible (cli-core 0.296.0):
tasks categoriesnames them and counts their open/total tasks (unlistedin JSON);tasks agendanames categories still carried by open tasks (unlisted_categories). - Spanish task support (cli-core 0.296.0): an
es:trigger matches other forms of a word (pagues—pagar) for Spanish messages, and duplicate checks understand dates such asmañana,el viernes,15 de noviembre. - Duplicate checks run again after linking a message (cli-core 0.295.0): after
tasks link <задача> msg:…,tasks add --intoandtasks merge, similar tasks appear intasks duplicates; the response'sreviewfield counts them. The link remains, and nothing merges automatically. commands --jsonstates a command's lifetime (cli-base 0.38.0):serveandwatchhavelifetime—persistent, whilesetupandsession startareinteractive. Previously the program inferred them from their names.
Changed — may break callers
- An agent closes a task only with
--certainty <0..1>, and an uncertain close waits for the owner (cli-core 0.295.0).AI_AGENTorCLAUDECODEidentifies an agent;--as-ownercloses as the owner. An agent can be wrong, and closed tasks disappear from the owner's agenda. An agent'stasks closewithout--certaintyrefuses withtask.certainty-required; MCPtasks_closerequires the newcertaintyargument. Belowtask_agent_close_min(0.8 by default), or withtask_agent_close off, the answer hasstate: openandclose_suggestion, and the task stays open. tasks addno longer refuses when only closed tasks match (cli-core 0.295.0): it opens a new task withfollow-up-of(follow_up_ofin the answer). Exit code 2 still applies when an open task matches. A script expecting code 2 for a closed match now receives a new task.- Rules choose narrower categories: electricity bills become
billsinstead ofmoney, and a doctor becomeshealthinstead ofpersonal(cli-core 0.295.0 and 0.296.0). The original seven categories keep their names/meaning; stored tasks do not change. A filter such astasks agenda category:personalcatches fewer new tasks. Some words move to narrower categories:gymtofitness,restauranttofood,переездtomoving. - Duplicate checks read the task's underlying messages (cli-core 0.295.0): the source and five most recently linked messages. A rule-created task without its own text is compared by message words, so
tasks addcan refuse with code 2 where it previously opened a task. max mcpandmax <бот> bot mcpnow use the shared MCP server, liketg. Tools remainmax_read,max_tools_searchandmax_write.chats checkinmax_writeis replaced bychats moderate; thechats rulesalias is gone, leavingchats rules show.max bot mcpno longer accepts--allow-send,--allow-delete,--allow-moderate,--confirm-sendor--allow-dangerous. MAX and TG share the same tested behavior. These oldbot mcpflags previously enabled nothing; now they prevent startup with exit code 2 and “unknown option”. Remove them from application settings;max <бот> bot mcp configprints the replacement. Agents usingchats checkorchats rulesneed the new names.max mcp configno longer includes--yes: MCP writes ataskalready run without a question. Voice over MCP is downloaded, then transcribed on this computer, as intg.chats moderatereads its checkpoint only from the rules file; very old session checkpoints are no longer migrated.setup --jsonputs next commands in the envelope'snext, notitem.next. Theitem.nextobject withinstructions,chats,historyandskillbecomes two top-level read steps:skill showandchats list --limit 5. All commands put next steps in one place for agents. Scripts readingitem.nextmust readnext. History download and skill installation remain in human output only.chats mediareturns messages with the same shape as chat history. Voice is nowvoice, rather thanaudio, as inmessages list. MAX file/video IDs are inside the attachment'sprovider_ref(provider_ref.file_id,provider_ref.video_id), not at its top level. Previouslychats mediareturned MAX-specific attachments. Scripts that expectedaudiomust look forvoiceand readfile_id/video_idinsideprovider_ref;--type audiostill selects voice.max watchrenders messages through the same code asmessages list. Polls show the question, answers and vote counts. JSON and--jsonlstay unchanged. Human output may look slightly different from 0.55.0; scripts should use--jsonl.
Fixed
doctor report createalso labels reply-target message IDs and write-attempt IDs. Labels correlate records within one report and change for the next report.
Security
- Every write is checked in one shared guard, through the terminal,
max serveand MCP. Sends, edits, deletions, reactions, mark-read, forwarding, moderation and chat/contact/account changes share permission levels,MAX_READ_ONLY, recipient lists and the send journal. Writes visible to others (messages, forwards, edits, deletions, new groups and adding people) also share the hourly limit.denyandreadonlyrefuse writes. Atask, the terminal asks or waits for--yes(--allow-dangerousfor deletion);--jsonwithout a flag refuses. MCP writes ataskrun as before, governed by profile permissions, including server--permissionoverrides.MAX_READ_ONLY=1refuses any write, including MCP. Previously MCP checks used a separate MAX path; now that path is shared withtg. Terminal commands keep their behavior. To prevent an agent deleting or sending without you, set the action todenyorreadonly, rather thanask: these tools are not offered to the agent.
0.55.0 — 15.10.2026
Changed — may break scripts
- Flags of shared commands follow the shared vocabulary; the old names are no longer accepted (cli-core 0.288.0):
--budget→--max-pages;messages sync --estimate→--dry-run(max still rejects it: MAX message ids do not tell how many are missing);contacts context --refresh,bot contacts show --refreshandtags auto --refresh-metadata→--sync-first;search conversations --refresh→--catch-up;attachments show --if-sha256→--expected-fingerprint; inreplies edit,--chats,--not-chats,--people,--not-people→--allow-chats,--deny-chats,--allow-people,--deny-people(the rules file does not change);schedule --once→--at-time;bot chats moderate --no-ban→--no-block;chats mark-read --until→--until-id;tasks add|plan --check→--remind-time;tasks add --attach→--into;tasks claim --for→--lease;tasks agenda --due→--due-within;server logs --lines→--limit(-nstays); inchats start,--payload→--start, as inchats app;store export --to/--kind→--output-dir/--include. Why: in max, tg and the other WireCat CLIs one word means one thing, and an agent does not have to remember a flag name for each program. What to check: an old name ends the command with exit code 2 ("unknown option") before connecting to MAX — check scripts and schedules (schedule list). In MCP the argument is the new flag name in snake_case, for examplemax_pages,until_id,expected_fingerprint,output_dir,allow_chats,at_time. Insearch conversations, do not change--refreshto--sync-first: that flag already existed and first reads new messages from MAX, while the former search preparation is now--catch-up. tasks similaris nowtasks related, andtasks duplicates unsureistasks duplicates defer, without the old names. Why: the same shared vocabulary. What to check: in MCP, find the commandstasks relatedandtasks duplicates deferthroughmax_tools_search. The permission key istasks.duplicates.defer. The old keytasks.duplicates.unsurein the settings file now only warns in stderr and has no effect, so the command gets thetaskslevel: remove it withconfig unsetand give the same level to the keytasks.duplicates.defer. In the database the decision is still calledunsure.tasks agendaandtasks duplicatesfilter with query fields, not flags:tasks agenda --tag <имя>→tag:<имя>,--category <имя>→category:<имя>,--claimed→claimed:any(alsonone,mine,others; by default, as before, unclaimed and your own);tasks duplicates --unsure→decision:unsure(by defaultdecision:review). Why: the database filters the list, as with the other lists, not the program after reading. What to check: an OR or NOT that mixes task fields withchat_kind:is rejected (query.unsupported-placement). In MCP these commands takequeryinstead oftag,category,claimedandunsure.- Every
--jsonanswer is an envelope:itemfor one thing, oritems+pagefor a list, andmeta. Now the ones that returned a bare object answer this way too: the--dry-run --jsonpreview (underitem, snake_case keys:business_rules,action_invoked,write_reserved,messenger_contacted,configuration_read),mentions confirm|rejectandimages embed --json,max_tools_searchin MCP ({items, more}→{items, page, meta}) and the MCP resourcemax://chat/<id>(the chat and messages underitem), as well asbot me,bot api …(the Bot API answer is insideitemunchanged, an empty answer isnull),contacts sync,contacts lookup(displayName→display_name,lastMessagedAt→last_messaged_at),doctor report,doctor report create(sendTo→send_to) andsetup(chats.hasMore→chats.has_more). Why: an agent parses any answer the same way. What to check: read fields from.item; instead ofmore, usepage.has_more. - A damaged local copy of the messages is an error, not an empty copy (cli-core 0.286.0). Before, a command that
connects to MAX silently went on without it. The copy is skipped only if it does not exist, if the account is not
recorded yet, or if another process (
serve) holds it for more than 5 seconds. Why: an answer without the copy looked complete, although it lacked what was saved. What to check: such an error is a reason formax <профиль> store repair --dry-run.
Fixed
- The next-step hint includes the profile (cli-core 0.286.0): after
max personal …the→ …line also starts withmax personal, and pasted as is it works instead of asking to choose a profile.
Removed
- Opening the database no longer deletes the old
messages.dbfile and no longer says so in stderr (cli-core 0.286.0). If the file is left over from old versions, delete it yourself.
0.54.0 — 15.10.2026
What's new
- Tasks can be claimed, tagged and sorted into categories:
tasks claim <задача> [--for 30m],tasks release,tasks categories,tags add|remove --task,tasks agenda --claimed(cli-core 0.282.0). - Tasks that may be the same work (cli-core 0.285.0):
tasks similar <задача>scores similar tasks;tasks duplicates [--unsure]shows pairs found by rules,tasks merge <задача> --into <другая>merges them,tasks unmergeundoes a merge,tasks duplicates reject|unsuredecides a pair.tasks agendaaccepts--categoryand--tag, andconfig set task_categories.<имя>changes the list of categories for the whole store. - Mentions (cli-core 0.285.0):
mentions domainsshows the sites that links point to;mentions list --newshows what was found since the last look;mentions confirm|reject <id> --all-in-chatdecides a name in the whole chat.config set phone_countries es,rureads numbers written without+. - Database version 16: the mention rules read the text of notes and of saved documents, and one
mentions rebuildreads those saved earlier;mentions liststill shows only mentions in messages. The update adds only triggers, so an earlier version of max can still open the database.
Changed — may break scripts
- Settings are named only in snake_case (cli-core 0.283.0):
config setandconfig unsetno longer understand camelCase, and a camelCase key in the settings file counts as unknown. The shared store settings are nowsearch_stemmers.cyrillic,search_stemmers.latinandaccount_groups.<имя>. tasks addrequires--category <имя>from the list shown bytasks categories(money,documents,meetingand others); if nothing fits, use--category other.MAX_READ_ONLYnow also forbids writing in max: before, this variable did not reach the write check.tasks addrefuses if the task may be the same work as one that is open or was closed in the last 14 days (cli-core 0.285.0): exit 2, reasontask.duplicate-candidates, candidates indetails.candidates. Repeat with--attach <задача>to attach the message to it, or with--newto open a new one; through MCP,tasks addbehaves the same.phone:andvalue:also find a stored number that ends with the national digits of the one typed (8 or more; cli-core 0.285.0), so a number stored beforephone_countriesis found in any form. A Russian city number written in groups,(812) 000-00-01, is now stored as+78120000001, not as bare digits.max search mailis gone: memo searches mail (owner's decision of 14.10.2026, cli-core 0.285.0, cli-core#1121). MCP has nosearch_mail.max search allsearches messages and notes (and meetings, if--sourcenames them), but never mail;--only mailis rejected. Instead of "unknown command",max search mail …answers with a hint:mail is memo's: install @wirecat/cli-memo, then `memo search mail …`. Tasks, contact notes, tags,search notesandsearch allstay inmax.
Fixed
- A title with capital Cyrillic letters is found by a lowercase query (cli-core 0.285.0).
- Harmful HTML in an attachment no longer hangs reading (cli-core 0.285.0): a page made of unclosed tags or comments is read in time linear in its size.
Security
messages send --file, sending from MCP, and profile or group photos do not take files from places with credentials (cli-core 0.283.0) — the same list asbot uploads putsince 0.53.0: SSH and cloud keys,.netrc,.git-credentials, gh, docker and kube settings, Claude and Codex credentials, keyrings, browser profiles, password stores and WireCat app folders; on macOS and Windows without case. Before, they refused only.ssh,.gnupg,.aws,.envand similar, and max folders. If you need exactly such a file, use--allow-any-file.- The list of places a file is not sent from is now one for all WireCat apps: max takes it from cli-core and no longer keeps its own copy. If the file does not exist yet, links in the folders above it are also resolved.
- Under
MAX_READ_ONLY, you cannot change what would allow writing later (cli-core 0.281.0):schedule command|agent|remove,config set|unset,recipients add|remove|clear,flood clear,server install|uninstall,mcp setup,skill install,upgrade, model keys andbot authanswerpermission_error. A scheduled agent runs with this variable and could earlier schedule a send for later; now it cannot, and a schedule saved under it also runs read-only. Reading, sync, tasks and notes work as before.
Removed
- Compatibility code.
max mcpandmcp config|setup|doctorno longer accept--allow-send,--confirm-send,--allow-mark-read,--allow-delete,--allow-moderate,--allow-dangerousand--http-confirmation; set access withpermissions.messages download --outputis removed;--output-dirremains. The commandconfig migrateis gone. The settingsread_only,allowandmcp_toolsare removed: a file with them is not read; setpermissions.<ресурс> readonlyinstead.doctordoes not look for the old cache file (legacy_cache), andinboxno longer carries over the oldlastCheckAtmark. - Moving folders at startup (from
~/Libraryand into the WireCat folder): it is already done. - The old search language:
search messagesandsearches createno longer have--languageand--regex. Save again any saved search written in the old language. conversations embed --workers.
0.53.0 — 15.10.2026
What's new
config setandconfig unsetaccept camelCase setting names (cli-core 0.279.0):max <профиль> config set senderColors falsewritessender_colors, andmax <профиль> config set readOtherBots true --botwritesread_other_bots. Command paths afterpermissions.keep their spelling.
Fixed
max bot uploads putand uploads through the code API refuse files from credential, keyring and browser-profile folders, as other uploads do; names are compared without case on macOS and Windows.- A send MAX refused for rate limiting can be repeated: when
messages send,messages forwardorpolls createreceives a rate-limit refusal, the error'sretry.safeistrue: the message was not sent. If the limit arrives during a retry after a lost response, it remainsoutcome_unknownandretry.safe: false.
0.52.0 — 14.10.2026
What's new
- Sync continues where it stopped:
store jobs showshowsprogress, andmessages sync --allno longer trips over a chat that is already busy (cli-core 0.276.0). max watchno longer crashes with a stack trace if an event handler throws: the subscription ends with that error, and the connection to the server stays.- Files and videos are streamed from disk while they upload (cli-core 0.272.0).
max messages send --file,--photo, profile and group photos andmax botno longer read the whole file into memory before sending, and the refusal for files of 2 GiB or more is gone. A voice message is still read whole — its length and waveform are computed from it — up to 256 MiB. - Picture search:
max <профиль> images embedandmax <профиль> images models download|list. Turn it on withmax <профиль> config set picture_search true(off by default); theclip-b32model is downloaded once (about 155 MB), andimages embedcomputes a vector for each picture in the local store. Message search by words then returnspicturesnext to the matches. Why: to find a picture by what it shows. What to consider: picture queries are English only; the agent translates them itself. More in search.
Changed — may break scripts
max store export --format jsonlwrites the same records to files and folders as to the screen: snake_case,chat_id; a deletion line is{ "id", "chat_id", "deleted": true }(cli-core 0.276.0). What to consider: the new build does not append to a folder exported earlier; export to a new folder.max watch --jsonlwrites messages in the same shape asmessages list: snake_case, withref(chat_id,chat_title,sender_name).--eventslines are snake_case too:chat_id,message_id,user_id,up_to_time,unread_count. A person sees the same as before. What to consider: scripts that readchatIdtakechat_id.- A voice message without text goes into
missinginreview,inbox,messages listand MCP, so the agent sees that it still needs a transcript (cli-core 0.275.0). - A next step to a command that changes only this computer does not run on its own (cli-core 0.273.0):
the
server restartandstore reindexsteps carrysafe_to_auto_execute: false. mentions rebuildtakes the kind as an argument:max <профиль> mentions rebuild person-name, not--kind(cli-core 0.272.0).max doctor --json,session startandsession endanswer with a snake_case envelope:{item, meta}, keyslegacy_cache,keyring.moved_by_environment,session.state_file,revoked_on_server. A person still sees lines of text. What to consider: scripts that read these answers take the fields fromitem, in snake_case.max bot chats members list --cursorinstead of--marker, with no alias; the bot's MCP tool takescursortoo. The answer names the next step inpage.next. max's own commands (recipients,config,mcp,messages transcribe,bot comments,bot uploads) answer the same way as the shared ones: an end line for--jsonland hints on stderr.
0.51.0 — 14.10.2026
What's new
- Each
max watchhas its own queue. A slow watcher no longer holds up the others; the buffer is 64 MiB per watcher and 256 MiB in total,max serve --max-subscriber-buffer-bytesand--max-subscriber-total-buffer-byteschange them,0removes the limit. max mentions: phones, e-mail, links and Google documents from stored messages (cli-core 0.264.0, database version 7).mentions list kind:phone,mentions list domain:google.com; a word without a field is a value in any record,89001234567finds+79001234567.mentions show <id>shows the text around it. Messages stored earlier are read by a singlemax <профиль> mentions rebuild; new ones are read as they are written.max mentions confirm|reject, mentions in files and voice messages, search byphone:,email:,url:,domain:(cli-core 0.269.0, database version 11).mentions confirm <id> [person:<uid>|organization:<id>]records whose phone or address it is (organizations too),mentions reject <id>dismisses the value for good; the author of the record is the agent or the owner (--as-owner). Text from files and voice transcripts also yields mentions (fieldfile_textortranscript); ones stored earlier are read by a singlementions rebuild. Message search finds them byphone:"8 900 000-00-01",domain:docs.google.com,email:"[email protected]". Older builds read the database as before.
Changed — may break scripts
- Built on
@wirecat/cli-core0.269.0:contacts timelinepages like the other lists. A list cut by--limitanswerspage.has_more: true,page.cursorand apage.nextstep (--cursorcontinues with the same--scope,--since-timeand--until-time); it used to behas_more: falseandmeta.truncated.meta.truncatedstays for changes still waiting in the queue. The "cut at --limit" note on stderr is gone. What to update: scripts that readmeta.truncatedfromcontacts timelinereadpage.has_more. - Error keys are snake_case for
max bottoo, and for a send with no answer. The MAX refusal code for a bot is nowerror.details.max_code(it wasmaxCode);outcome_unknownon a message send returnssend_id(it wassendId). - On
@wirecat/cli-core0.270.0 and@wirecat/cli-base0.27.2. --json=<поля>replaces--fieldsand--agent-json; they are gone.--json=id,textkeeps these fields of each item. JSON in the CLI keeps text as it is; MCP answers still show invisible characters.tags list,tasks listandconversations listtake a query instead of filter flags.tags list tag:work type:chat,tags list sources:auto;tasks list state:open kind:promise chat:<id>;conversations list <чат> started_at>=7d. These lists no longer have--tag,--type,--source,--state,--chat,--before-timeand--since-time. The items are shared entities: a tag names what it is on astarget, a conversation returnsmessages_count,started_at,first_message.
Fixed
max serveno longer loses the login if it was closed just as MAX answered. The profile state and the refreshed token are saved before the check for closing: MAX has already counted this login, and the next run does not log in again.- A full shared
max watchbuffer disconnects whoever holds the most, not whoever is written to next. The refusal reacheswatchwith codeinvalid_responseand reasonoutput.too-large, notprovider_error. - The record of a failed run again keeps the MAX refusal code (
providerError, for exampleproto.payload). Since cli-core 0.263.0 it is read fromerror.details.provider_error, but max wroteproviderError, and the code was lost; the "already voted" poll check and the retry afternot.foundnow look at the new key too. MaxClientcalls a file of 2 GiB or more what it is, not "it cannot be read". A file by path insend({ files })and a group or profile photo are checked for size first: Node does not read a file of 2 GiB or more, and the error now says so.max <бот> bot chats members addtakes at most 100 people at a time. The MAX Bot API accepts up to 100 ids in one request; a longer list is now refused before the request, with a request to split it across several runs.
0.50.0 — 14.10.2026
Changed — may break scripts
- Built on
@wirecat/cli-core0.262.0 (the new name of@wirecat/cli-messaging, follows its 0.261.0; the parity command iscli-core-parity) and@wirecat/cli-base0.26.0. Keys in machine output are snake_case: inerror.details—operation_id,send_id,retry_after_ms; incommands --json—global_options,inherited_options,exit_codes,takes_valueandcontract: 1. The query tree in the MCP argumentastwriteslower_inclusive,upper_inclusiveandmust_not. - HTML files are read as main text (cli-core 0.262.0): menus, footers and banners are dropped; headings, lists,
tables and links stay. Text already stored for HTML attachments is read again on the next
attachments extractand changes.title:,site:,lang:,author:andkeyword:search notes and files.
Fixed
max config set defaultProfile <имя>andconfig unset defaultProfilework without naming a profile. Before, the command first required a profile and failed if there were several (cli-core 0.262.0).
0.49.0 — 13.10.2026
What's new
- Built on
@wirecat/cli-messaging0.259.0 and@wirecat/cli-base0.24.0. Thestore fetchcommand is now calledmessages sync(same arguments, options and JSON); the old name is hidden and deprecated. --debug: on a failure, the full record — cause and stack — follows the error: in a terminal after the✗line, otherwise as a second JSON line.runs listandruns searchread a per-day index and answer in milliseconds even across thousands of runs.
Changed — may break scripts
- The shared message archive and speech models move once to the WireCat folder,
~/.local/share/WireCat/(Windows:%LOCALAPPDATA%\WireCat\Data\), on the first run — from~/.local/share/cli-messaging/and~/.cache/cli-common/models/. The move overwrites nothing: if both places hold different copies,maxstops with exit code3and names both files.WIRECAT_STATE_DIRreplacesCLI_COMMON_CACHE_DIRand moves the whole folder. Updatetgandmemotogether withmax: an older CLI will create a new copy in the old place. Where the files are. - One error object:
{"error":{"code","reason","message","details"}}. What used to sit directly inerror—candidates,sendId,operationId,permission— is now inerror.details.reasonis a dotted identifier (output_limit→output.too-large,input_limit→input.too-large);retryableis present only if the failure itself set it, andactionsonly on failed items of a partial result. Code1is calledinternal_error(it wasgeneric_failure), and its message no longer carries the failure's own text —--debugshows it. Keys that are not in the shared cli-messaging list are dropped fromdetails:providerErrorstays only in the message text, and the IDs of messages thatmessages deletedid not delete are also listed in the message. runs showshows only what went wrong (failed responses, warnings, a crash) and addseventCount; all events with-v, as before.maxno longer picks a profile by itself. If no profile is named by the first word, byMAX_PROFILEor by thedefaultProfilesetting, a command that needs an account exits with code2and lists the profiles on this computer — even when there is only one. It used to work silently with thedefaultprofile. The first login is named too:max personal setup(any name instead ofpersonal); on a computer without profiles the error suggests exactly this command. Without a profile,--help,--version,commands,skill show,account listandconfig showstill work. Hints in errors now always name the profile (max default setup, notmax setup), andmax mcp configalways passes it to the server. Why: which account writes and reads is the owner's decision, made explicitly — otherwise an agent or a script could act from the wrong account. What to do: for everyone who used the unnameddefaultprofile,max chats listand scripts without a profile stop working. The error names the profiles; use one of three:max default chats list,export MAX_PROFILE=defaultin your shell profile, ormax config set defaultProfile default. MCP entries made withmax mcp config— recreate them with the same command. Profiles.
0.48.0 — 12.10.2026
What's new
-
--briefand--fullon any command.--briefkeeps a found message's reference, chat, time, author, excerpt and score;--fullreturns everything. -
max search allnames the author of each hit and how it was found (by words or by meaning). -
max schedule: a command or an agent on a schedule — through systemd (Linux), launchd (macOS) or Task Scheduler (Windows).max schedule command <имя> --every 2h -- messages list <чат>runs a max command; reading saves what was read to the store.max schedule agent <имя> claude "<задание>" --at 08:30starts an agent (claude or codex), at most once an hour. The agent runs withMAX_READ_ONLY=1and cannot send anything; its answer is inlatest.mdnext to the schedule, and a desktop notification says when it is ready.--once 2his a single run; after it the schedule removes itself.max schedule list,run,remove. -
max server installsuggests how to turn on the daily review of commitments, and turns nothing on by itself. -
MAX_READ_ONLY=1forbids the process from sending anything, overriding the configuration file and--permission.
Changed — may break scripts
max search messagesreturns an excerpt, not the whole text. Each hit hasexcerptinstead oftext: about 240 characters around the first query word; the whole text with--fullormax messages show <ссылка>. EmptyeditedAt,replyTo,forwardedFromandreactionsare no longer printed in machine output. A script that readtextfrom search results readsexcerptor adds--full.
0.47.0 — 11.10.2026
What's new
- Tasks get a plan, links and an agenda (shared store 0.247.0, version 4).
max tasks addtakes--title,--description,--dueand--check;max tasks plan <задача>changes them later,noneclears a date. The check date is when the agent should look at the task again; it is not a reminder: the owner gets nothing.max tasks linkattaches messages, chats, people, documents and links to a task;max tasks showshows the plan with its links.max tasks agenda, without message text, lists overdue and upcoming tasks, chats where the owner owes an answer (owed), where the owner waits for an answer (waiting), and chats whose last message is not saved yet (unsynced).max skill show follow-upsis a daily review for the agent: drafts only, it sends nothing. - Search understands comparisons with a colon.
date:>=2026-01-01(and:>,:<,:<=) is the same asdate>=2026-01-01; previously this gaveinvalid_syntax. A rejectedafter:orbefore:now suggests the replacement: forafter:2026-09-01the answer is to usedate>=2026-09-01.
Changed — may break scripts
- Shared store 0.247.0: meeting context records facts with the
fact.addaction;memory.addno longer accepts thefactkind. - Shared store 0.246.0 checks new tags before creating them. A similar name needs the owner's review; you can use the existing tag or its explicit alias. Existing records are kept; automatic name and alias matches are merged into one tag.
0.46.0 — 11.10.2026
Changed — may break scripts
- On macOS, max keeps its files where it does on Linux:
~/.config/max-cli,~/.local/share/max-cliand~/.cache/max-cliinstead of~/Library/…. The first run moves the old folders there, together with the shared store and speech models, and points the log of the installedmax serveragent to the new folder. Whilemax serveor the MCP server is running, max prints one warning, works with the old folders this time and tries again on the next run. Nothing changes on Linux and Windows. - max runs on
@wirecat/cli-messaging0.242.0: existing project and task keys are kept; new projects get short keys, and the shared store supports verifiable task dependencies. - max runs on
@wirecat/cli-messaging0.238.0; the archive is version 2. On first open the archive is upgraded: memory records of thefactkind become facts (what happened, kept apart from conclusions), and "assigned" links are copied into task assignments. Earlier max builds open the upgraded archive as before. - Mail for search by meaning is split into chunks per thread, not per message. Quotes, greetings and signatures are left out of the chunks. On the first indexing the old chunks are deleted and all mail is embedded again — once, and it takes time. The mail text itself and search by words do not change.
What's new
--sourceinsearch messages,search mailandsearch conversationsaccepts a list of accounts and groups:--source group:work,max:default,email:[email protected]. A group is saved withmax config set accountGroups.<имя> <список>and is visible to every app that works with the archive.max search conversationsfinds mailbox mail by words too, not only by meaning.
0.45.5 — 11.10.2026
Changed — may break scripts
- Joining a chat and importing contacts count toward
sendsPerHour. Joining counts as one action, importing — one per number;max contacts importsends numbers 10 per request. If the limit stopped an import halfway, the error says how many numbers went through, and importing again is safe.
What's new
max search all --backend archive|server|bothand--server-time— as insearch messages; this applies only to messages, mail and notes are searched locally. The default isboth.max search mail --account <адрес>searches the mail of one mailbox; without it, all of them.- Mail is searched by recipients, folder and subject (
to:,cc:,bcc:,mailbox:,subject:), and mail attachments by meaning.
Security
- Search no longer returns another account's messages.
search messages --backend serverwith--source allorin:allcould show someone else's message with the same chat and message IDs; searching a chat without an account is now rejected. From@wirecat/cli-messaging0.233.0.
0.45.4 — 11.10.2026
What's new
max search messageswithout a chat also asks the MAX server, like the search bar on web.max.ru: one request across all chats, one best match from each chat. What it finds is saved in the archive and checked against your query. With--chat, the server searches one chat, as before.--backend archivekeeps the archive only; with--json, such searches now have aserverblock.
Changed — may break scripts
max search messageswith words and no chat now connects to MAX (it used to answer from the archive only) and can wait for the server for up to 5 seconds. The same applies to search through MCP. To search only the archive, as before, add--backend archive(in MCP,backend: "archive").
Fixed
- Runs on
@wirecat/cli-messaging0.231.0, which brings cli-meetings 0.3.0 and the SQLite and ONNX 1.0.1 packages with a license file; nothing changes formax.
0.45.3 — 11.10.2026
Changed — may break scripts
- Archive search with
--discoverhandles questions such as “Can contractors connect to the project?”: the question mark no longer turns into a search pattern. Strict search and filters work as before. - Mail search and a linked person's conversations also read the separate mail storage, alongside the earlier import. Mail supports sender and thread filters. In search results, an email with the same reference is shown once.
0.45.2 — 11.10.2026
Changed — may break scripts
- A history fetch whose very first page fails with no hope of a retry exits with an error again
(exit code
2), as before 0.45.1. A wait that MAX asks for, and a failure after several pages, still give a partial result withcomplete: falseand code0.
Fixed
max store fetch --backgroundno longer stops after 30 seconds. The background task received the 30-second limit shared by commands and stopped after about a hundred messages. Now it runs to the end; an explicit--timeoutstill limits it.max store fetch --allwaits out a short pause that the chat list asks for (up to 5 minutes, as message pages already did), instead of ending at once withrate_limited.
Security
- The old
messages.dbis deleted when the store is opened at its default path (since 0.45.1): the unencrypted file used beforewirecat.db, with its-waland-shm. One line on stderr names it. The file stays whenMESSAGING_STOREis set, and while another process keeps it open.
0.45.1 — 11.10.2026
Fixed
- Package references, documentation and examples use the WireCat namespace.
- HTTP attachment downloads distinguish 429 from an ordinary network failure: they stop new files and expose the
Retry-Afterwait when supplied. A 413 response suggests reducing input, rather than raising a local budget.
Changed — may break scripts
- Independent file or history-page failures retain successful work and return
complete: false,batchorissuewith exit code0. Scripts must check completeness; partial download JSONL addsbatch_summary. Errors include recoveryactions. Resuming downloads retries failed checkpoint IDs. - Batches stop new requests after ten attempts when failures exceed 50%;
MESSAGING_BATCH_MAX_ERROR_PERCENTadjusts the percentage, with 100 disabling that percentage stop. Throttling and authentication failures stop earlier; writes with unknown outcomes are never automatically replayed.
What's new
- Set extraction and retained-file transfer size through
MESSAGING_ATTACHMENT_MAX_MIB(default 50). PDF previews now allow 4000 pixels per side and 8 MiB per page;MESSAGING_PDF_PREVIEW_MAX_PIXELSandMESSAGING_PDF_PREVIEW_MAX_MIBadjust those budgets. Larger values need more memory; external OCR and decompression budgets remain separate. max runs search, also theruns searchcommand in MCPmax_read, searches safe diagnostic records by text, status, error code and time without connecting to MAX.
0.45.0 — 11.10.2026
Changed — may break scripts
- The store prunes its growing logs on open, at most once a day: agent tool calls older than 90 days are deleted, and a handled bot update older than 30 days keeps its row but loses its payload. Upgrade tg-cli and cli-memo at the same time, as they share the store.
What's new
max store resetfor a store this build cannot migrate: it backs the store up beside itself, deletes it and starts an empty one. It asks first;--yesskips the question and--no-backupskips the copy.max search all --meetings [provider:account]also searches one meeting account's transcripts, chat and summaries;--max-meetings <n|all>sets how many meetings it looks through (100 by default).
Security
- The old
messages.dbis deleted when the store opens at its default path: the unencrypted file used beforewirecat.db, with its-waland-shm. One line on stderr names it. It is kept whenMESSAGING_STOREis set, and while another process still has it open. From@wirecat/cli-messaging0.222.0.
0.44.0 — 10.10.2026
Changed — may break scripts
- The local store is a new file,
wirecat.db, and starts empty. It sits beside the oldmessages.db, whichmaxleaves as it is: not read, not converted, not deleted. Runmax store fetch --allto bring messages back from MAX. What exists only on this computer — for example notes, aliases, tags, tasks and transcriptions — stays inmessages.db. The login stays. Upgrade tg-cli at the same time, or the two see different archives.
What's new
max contacts timeline <человек>, also over MCP as thecontacts timelinecommand ofmax_read: everything one person took part in, in every messenger linked to them, newest first, from the local store.--scope personal|work,--since-time,--until-timeand--limitnarrow it.
0.43.1 — 10.10.2026
Fixed
- Attachment downloads use ordinary HTTP(S) and the configured transport without separate DNS validation or local-address restrictions. This preserves compatibility with VPNs, proxies and private networks; support for any particular proxy depends on the transport.
- Local PDF text extraction and page previews no longer require splitting documents after 20 pages; the separate 30-second extraction timer is removed. Overall command cancellation and size limits remain.
- Local transcription of complete mono or stereo Ogg Opus recordings no longer refuses audio after 10 minutes. Longer recordings require more memory and time.
- Attachments in ordinary hidden working folders are available again. Known credential files, CLI folders and the message store remain protected.
- Markdown export preserves message formatting; MCP preserves original Unicode on writes while showing controls visibly in responses. Configured model gateways allow ordinary redirects.
- Upgrade and MCP setup on Windows accept ordinary relative PATH entries and nonstandard command-processor environments. The message store keeps its existing schema.
- The guide clarifies that search with
--discoverreads only the local archive. Ordinary search in one chat can also query the MAX server; discovery does not.
0.43.0 — 10.10.2026
What's new
- Message search with
--discoveror MCPdiscover: truefinds partial word matches and eligible direct replies in the local archive without model downloads. Strict search remains the default; missing terms help agents check the evidence.
Changed — may break scripts
- The project is now licensed under Apache 2.0. See
LICENSEfor the terms.
0.42.0 — 10.10.2026
Changed — may break scripts
- The package is
@wirecat/max-cliand its repository belongs to WireCatLabs. Use this package for installations and updates. - Deletion verifies the outcome by reading from the server. If MAX still returns a message or verification fails, the command reports
outcome_unknowninstead ofdeleted. Read the message before retrying; acknowledging the request does not prove deletion. - Local transcription accepts complete mono or stereo Ogg Opus recordings up to 10 minutes. Split longer recordings. PDF text extraction supports at most 20 pages and 30 seconds; split larger PDFs.
- MCP makes hidden Unicode controls visible in text results and write arguments, including converted formatting. Regional flags remain intact; ordinary CLI JSON preserves the original strings.
Fixed
- Attachment downloads through MCP exit without hanging. Local text extraction no longer blocks the connection needed to download a file.
messages deleteaccepts comma-separated IDs as well as separate arguments.- MCP guides describe profile permissions and approval in the agent app. The server shows no approval forms; obsolete unused form code was removed.
Security
- Directory extraction and retained-file transfer check file locations. Hidden files and folders, CLI-owned folders and the message store are refused, including symlink targets. MCP downloads also refuse those places; use a normal downloads folder.
- DOCX applies the office archive limits. Part count, expanded size and text-part size are checked before reading.
0.41.0 — 09.10.2026
Changed — may break scripts
- Everyone selected by the rules receives auto-responses until you limit the audience; there is no longer a separate list for
testers.max replies audience --reply listed --allow-people <id>leaves only selected people,--deny-peopleand--deny-chatsexclude some. Nothing is sent unlesspermissions.replies.sendisallow, and the new rule is disabled until you enable it. Previously, the answer only went to those who were both intestersand in the audience; the two lists were confused. The file, where there is stilltesters, responds to exactly the same people: they become allowed (if the audience was alreadylisted, only those whom it also allowed). Allowed chats in such a file are removed, otherwise any participant in these chats would receive a response; prohibitions remain. Withouttesters, the file will be overwritten the next time you edit viamax replies. max replies status --jsonno longer has thetestersfield; who can be answered is shown by countersaudience. Inmax replies testandserve, a sender outside the audience is skipped with the reason “not on the allow list” instead of “not a test account”.
Fixed
max mcp configtransfersMESSAGING_STOREandXDG_RUNTIME_DIRto the client configuration, astgdoes. A client running a server with a stripped-down environment on Linux did not reach the keychain and answered “no session,” but with its ownMESSAGING_STOREit looked in a different local archive. Runmax mcp configagain and replace the entry in the client settings.
0.40.0 — 09.10.2026
Changed — may break scripts
- The message store deletes the copies it kept for older versions (schema version 28, cli-messaging 0.212.0). Notes, contact notes, relationships, and entities recorded before the transition to the new notes are transferred one time to the new tables during the update. After it, the old max, tg and memo refuse to open the archive with the message “upgrade this tool” - update all three together.
0.39.0 — 09.10.2026
New
-
max attachments show --page 1returns a page of a retained PDF as PNG. A remote agent can read every page with its own vision and save the text for search. Requires the optionalunpdfand@napi-rs/canvas; it does not start an OCR API or write to the index by itself. If the MCP client shows only resource metadata, requestformat: base64and display the PNG with the agent's own tools. -
max search all "<words>"searches everything stored on this machine at once: MAX and Telegram messages, mail imported by memo, and notes. Each result states its kind: message, email or note.--only notes(ormessages,mail) narrows the search. -
max search mailandmax search notessearch one kind. Notes are found by words and, if a local text model is downloaded, by meaning;--type internal(written in memo) orfile(from the notes folder). -
max search messages --type voice(ortext,file) finds only messages of that kind.
Changed — may break scripts
-
Statistics
--answereraccepts stored names, aliases and @usernames. Resolution is local to the accounts of the selected history; ambiguous names return candidates. An unknown name now fails instead of producing a report for a fabricated ID with zero answers. Useperson:provider/account/idto explicitly select an unknown string ID. Responses addidentityKnown; an ID without observations getsfalseandstatus: unknown. Zero observed answers do not prove inactivity (statistics). -
Every search moved under
max search. The old commands are gone:Before Now max messages searchmax search messagesmax messages search --source emailmax search mailmax conversations searchmax search conversationsmax bot messages searchmax bot search messagesFor agents the tools moved the same way:
search messages,search conversationsand the newsearch all, which is the place to start. -
max search messagesno longer returns mail. A saved search within:emailnow asks formax search mail. -
Permissions with the old paths (
messages.search,conversations.search) stopmax searchuntilmax config migraterenames them, keeping their levels.
Fixed
- Join-request help names MAX limitations explicitly. It no longer offers
--allor--linkas available operations and no longer promises chronological order; the refusal checks remain.
0.38.1 — 08.10.2026
New
max chats requests list|accept|declinelists and processes channel join requests.--searchfilters by name. MAX provides no request time:requestedAtisnull.--linkand bulk--allare unsupported and rejected before the request.
Fixed
- The shared library is updated to 0.205.0 so MAX, Telegram and Memo use the same archive version. Note schema and links are unchanged.
0.38.0 — 08.10.2026
New
max store jobs list --state <state>shows only background jobs in that state:running,done,failed,cancelledordied.
Changed — may break scripts
-
Latin words use English and Spanish stems together. Previously, only Spanish, so the English forms of words (“budgets” → “budget”) were found worse. What to consider: after an update, the stem index is built anew on its own. A small archive - immediately upon opening, a large one - little by little:
max servecompletes it in the background,max store migrate- immediately. While the index is not ready, the search looks for exact forms of words and writes about this to stderr, and in JSONquery.stemming.appliedis equal tofalse. The index of the stems of the Latin text is approximately twice as large. If you specifiedsearchStemmers.latinyourself, your setting remains and is still applied bymax store reindex. Update alsotg: the old version, opening the rebuilt archive, responds to a stem search with “update the program” (archive). -
Person notes (
max contacts notes) appear in every profile that sees the person. Before they appeared only in the originating profile. Owner notes are stored separately from messages alongsidememonotes. Notes from multiple MAX profiles now appear together; aliases (contacts alias) remain account-specific.
Fixed
max chats joinno longer reports a join request as joining. If a channel approves who joins, the command only sends a request and now answersrequested: trueinstead of the channel card; whilemax serveis running, such a channel does not appear in the chat list until the request is accepted (groups).
0.37.0 — 08.10.2026
New
- Bot buttons:
messages listandmessages showdisplay numbered buttons beneath a bot's message:[1 Да] [2 Нет].max messages press <чат> <сообщение> <кнопка>selects by number or exact text; the bot sees who pressed. Only ordinary callback buttons are pressed. Phone and location sharing buttons are never pressed; other kinds explain the next step. Buttons appear in messages read from MAX and are absent from the local copy (usage). - Start a bot:
max chats start <бот> [--payload]acts like its Start button. It acceptshttps://max.ru/<бот>?start=…, including a bot you have never messaged; its chat appears in the list. Links to people are refused. Starting is a message from you and passes send checks. - Bot mini apps:
max chats app <бот> [--start]prints a signed-in app address. Keep it private;maxdoes not store it. max account listlists local profiles and their accounts without contacting MAX.max bot messages listalso displays keyboards in the bot's own messages.max watch --eventsdisplays read receipts and chat changes (shipped in 0.36.0 but omitted there):readcan be your own other device;chatreflects title, membership or departure changes. Marking unread is not a read event.
Changed — may break scripts
-
contacts profile:botappeared inflags-truefor the bot,falsefor the person. Previously,flagswas always empty. -
watch --events: the linechatcomes only when something has actually changed in the chat - name, description, participants, status, photo or owner. Previously, whenmax servewas running, it could arrive for every send.
Fixed
- A lost reply after starting a bot or pressing its button returns unknown outcome (
outcome_unknown, exit 14), rather than a safely retryable failure. No automatic retry occurs; check the bot's reply before repeating. The journal retains the unknown outcome. - Viewing a group by link through
max serveno longer adds a group you have not joined to your chat list (fixed in 0.36.0 but omitted there). - Bare
maxand command groups such asmax chatsdisplay help at a terminal rather than✗ (outputHelp). Scripts and--jsonget an error pointing tomax --help.
0.36.0 — 08.10.2026
New
- Files for remote agents:
attachments showtransfers retained bytes in bounded chunks with SHA256. MCP returns complete images or binary resources, with JSON/base64 fallback. Transfer calls no model and changes no index; the agent reads the file and saves its text (attachments). - The shared library update also adds folder reads with chat names,
metadata refresh --only-missing, background-job retry/cleanup, observed retention cohorts and counters with explicit freshness; unknown values remain distinct from zero.
Changed — may break scripts
max contacts profilefillsseenwith the last presence time oronlinewhen MAX supplies presence. A field that was previously empty can now contain a value (people).- Ranking and evidence JSON includes counter observations and freshness; evidence also supports retention-cohort selections. Check each counter's fields and selection kind before interpreting the result; unknown values or incomplete archives do not mean zero.
0.35.0 — 08.10.2026
New
max chats deleteandmax chats clearremove the chat or its messages only for this account. Other participants keep them. Without--allow-dangerous, the command asks; without a terminal it refuses.- Local attachment text reading: ODT, ODS, XLSX, PPTX, EPUB, BOM-marked UTF-16 and confidently detected legacy encodings. No model call; formulas are not evaluated and images remain for the agent. No extra packages for these formats; PDF/DOCX retain optional engines (attachments).
- Stored administrator reports: unanswered questions, selected people's response latency, known-join newcomer help and viewed channel posts with little discussion. Selections/evidence show source messages; missing history stays unknown, so a missing observed answer does not prove nobody answered (rankings).
- Stickers:
max stickers listandmax messages send --sticker <id>. List added sets, or use--set <id>for their sticker ids. Send one sticker without text/files. max chats muteandmax chats unmutechange only your notifications, indefinitely or with--until 8h.max account privacy setchanges--find-by-phone,--phone-number,--calls,--chat-invites(everyone, contacts, nobody) and--hide-online on|off; other settings stay. MAX only permits everyone/contacts for finding by phone;nobodyis refused.max chats mediareads photos, video, files, audio and links from MAX, with--typeand--before-id(usage).max calls listshows incoming/outgoing/missed calls and duration, newest first.max account privacy showshows who may find, see the number, call or add the account and whether online status is hidden; it uses the login response without another request.
0.34.0 — 08.10.2026
New
max chats update --photosets the photo of a group or channel (groups).max chats folders orderchanges the folder order. The mandatory “All chats” folder comes first, followed by the named folders, then the remaining folders in their previous order (usage).- Your own names and notes about people:
max contacts aliasandmax contacts notes. They stay on this computer and are not sent to MAX;contacts show --with-notesdisplays them andcontacts list --search-notessearches them (usage). - Automatic group and channel tags:
max metadata refreshandmax tags auto— based on names and descriptions, without reading messages; your tags remain untouched (search). max store fetch --alldownloads all chats — the last 90 days of each;--backgroundruns it in the background. Search reports how many messages and chats it checked and how many chats have not been downloaded or are behind;coverage.nextin JSON gives the agent the command to run before concluding that a message is absent.- Reply and discussion metrics use saved MAX reply links. Incomplete data leaves a link unknown instead of assuming one.
- The rankings guide explains metrics, scores, coverage, saved selections and evidence.
- New guides explain attachments, speech recognition and external model setup.
Changed — may break scripts
-
max session endlogs out of MAX rather than just forgetting the token here — liketg session end.revokedOnServeris nowtrue. If the token was copied from a web.max.ru tab, that tab is logged out too (sessions). -
max messages searchin one chat also searches the MAX server. With--chatorchat:and words, it searches both archive and server by default (--backend both), finding messages not yet downloaded. Server results are checked against the same query; each message has asource.--backend archivesearches only the archive;--server-timesets how long to wait for the server (5 seconds). Without a chat, only the archive is searched (search). What to consider: searching one chat can now connect to MAX;--backend archivekeeps it local.
Fixed
-
Ready-made MCP requests use the available
max_readandmax_write, replacing the old names of individual tools. Their searches checkcoverage.nextbefore concluding that a message is absent. -
Saved selections retain exclusive date boundaries when rerun, excluding messages exactly on a boundary. Unsupported folder operations are no longer offered to the agent through MCP.
-
max serve --timeoutshuts down the server. When time runs out, the connection, unfinished login and background tasks end; the process exits with the timeout code.
0.33.0 — 07.10.2026
New
max stats messages topandmax stats contacts toprank saved messages and their authors, and each entry’sevidenceshows which messages account for its ranking. All calculations use the local copy; nothing is sent to MAX.searches create --selectionsaves such a ranking as a search.
Changed — may break scripts
- Each profile now shares one request rate to MAX across all
maxprocesses. Previously, simultaneous commands, backgroundstore fetch,mcpandserveeach paused independently, collectively contacting MAX more often. They now share one allowance: 10 requests in a burst, then 20 per minute. Why: MAX blocks accounts for excessive requests, and parallel tasks multiplied them. What to consider: bulk downloads running in parallel take longer; a command that would wait more than 5 minutes for its turn exits immediately with code8. Change the rate withrequestsPerMinuteorMAX_REQUESTS_PER_MINUTE;0disables it. See limits.md for limits. max messages sendno longer has the--comment-tooption. It appeared in 0.32.0 with shared Telegram code, but in MAX it only failed with code 2. What to consider: a script passing--comment-tostill gets code 2, now with an unknown-option message.
0.32.0 — 07.10.2026
New
- Photos and scans in attachments can be processed in batches using a selected model. By default, the agent still reads them itself and saves text with
attachments text set. Batch processing usesattachments extract --ocrwith the model frommodels.ocrand--concurrency; recognized text enters the existingcontent:search. What to consider:--ocrsends files to the selected model provider, so it must be enabled explicitly. The cache accounts for both file and model; an API failure does not overwrite the agent’s text or the existing index.
Changed — may break scripts
max contacts profileshows a person’s previous names in the newaliasesfield. Previously, the local copy kept only the current name: a new name from a message or contact sync overwrote the old one. Why: someone who changed their name is easier to recognize by a previous name. What to consider: the--jsonresponse now includesaliases, a list of{ name, firstSeenAt, lastSeenAt, source }ordered from oldest to newest.source: messagesmeans a name from saved messages; it is approximate. The list stays empty until the copy has observed a name change.from:searches only the current name. People.max messages sendgained--comment-to, but it does not work in MAX: the command fails with code 2 and sends nothing. The option is shared with Telegram, where it posts a comment under a channel post. What to consider: MAX does not support comments under channel posts; do not use this option in scripts.
0.31.0 — 07.10.2026
New
-
Search preparation and archive repair. Text extraction through MCP,
attachments extract --from-dirandmessages download --extract; hash checks for changed files.store fetch --catch-upprepares the graph and installed local vectors within set limits; it is off by default.store gaps plan/repairand MCP show recorded interior gaps and explicitly download them using limits and jobs. Unknown edges and ambiguous pages do not count as a complete archive. -
Member lists of tracked groups are updated daily while MAX server runs.
chats members fetch --trackis available; tracking does not extend the server’s idle timeout. -
max setupis easier to read. Each step has a heading such as[1/4] This computer, with an indented account of what happened below it; questions and the QR code appear under their step, with blank lines around the code. The result is an aligned table whose first row gives the command to start with.--jsonoutput and its keys are unchanged;--quietstill hides the steps. -
Auto-reply templates use Liquid and separate
aiblocks.models.repliesselects the provider;replies consentsgrants consent for a profile and endpoint, with exclusions for individual chats. Ordinaryreplies testdoes not call a model;--aiexplicitly passes saved data. Old templates retain fallback text with a warning. Sending remains restricted bytestersandreplies.send; see the guide. -
max serveopens tasks from auto-reply rules. View them withmax tasks listor the MCP promptopen-tasks; creating a task sends nothing. -
Browser connections are documented for Windows, macOS and Linux. The guide distinguishes Tailscale from the server, provides PowerShell commands and explains temporary send permissions, connecting Codex web, running two messengers and stopping individual tunnels. Connection.
-
Settings, permissions and profiles have separate explanations. Guides start with everyday tasks, file locations and examples; the full reference remains available.
Changed — may break scripts
-
SDK 0.161.0 contract: headless mode, input/output and time limits, command schemas, field selection, previews and rules for retrying writes. Statistics use
stats <ресурс> <вид>without the old aliases. -
MCP uses three tools for search, read and write instead of a separate tool for each command; there are no server confirmation forms. Profile permissions and separate moderation rules remain in effect.
-
Settings are split into a short guide and a full reference; a user-facing CLI contract page and an agent skill check in CI have been added.
-
Statistics now use
stats messages show,stats chats showandstats tasks show. The old pathsmessages stats,chats stats,tasks statsare removed; update commands and exact permissions tostats.messages.show,stats.chats.show,stats.tasks.show. MCP tools are now namedmax_stats_messages_show,max_stats_chats_show,max_stats_tasks_show. -
Syntax errors return code 2 and a structured JSON error. Scripts expecting the previous code 1 or plain text must update their error handling.
-
The first settings load creates config.json. An existing file is not overwritten; environment variables and command options are not saved into it. config show can now create the file, and ordinary values show the defaults file as their source.
-
Word and phrase searches find word forms. Queries in scripts may return more messages. For the previous exact matching, use exact: or --exact; an explicit text: still searches word forms. The archive’s language settings determine matching.
Fixed
-
Search preparation respects the ban on writing links.
conversations.links: readonlyordenystops catch-up after downloading and during gap repair before connecting or starting a job. Explicit--no-catch-upstill permits ordinary history reads under profile rules. -
Person context finds direct conversations without recorded membership when the conversation ID matches the person ID; recent messages in both directions are available again.
-
MCP documentation uses current command paths and permissions without the removed confirmation forms.
-
When a write is interrupted, the original
outcome_unknown,operationIdand retry details returned by the command are preserved: the shared library is updated to 0.161.0. -
A command timeout during a Bot API write preserves an unknown outcome. The operation may have completed; check its state before retrying.
-
MAX MCP does not offer unsupported forum tools. Command search no longer offers editing and reordering Telegram topics.
0.30.0 — 06.10.2026
New
max stats charts --output activity.pngsaves a dark-theme PNG chart. SVG remains available; images are written only to new files. MCPmax_stats_chartswithformat: "png"returns an image together with JSON, without connecting to MAX or writing files. Withoutformat, MCP still returns JSON.- Auto-reply rules can be edited with
max replies add|edit|on|offandaudience. A new rule is off until explicitly enabled; changes are saved only locally, without sending messages. Auto-replies remain restricted to test accounts; thetesterslist is still set in the file. Auto-replies. max tasksshows what is waiting for your reply.max reviewmaintains a task in the local copy for an unanswered question or a message mentioning you, and closes it when you reply; these tasks are now visible.max tasks listshows them with a message link;max tasks add <сообщение> --type promiseadds what rules miss;max tasks close <задача> --as done|dismissedcloses a task permanently;max tasks statscounts them by chat. MCPmax_tasks_list,max_tasks_add,max_tasks_close,max_tasks_statsgive the agent the same capabilities. Everything stays on this machine; nothing goes to MAX. Writes requiretasks.addandtasks.closepermissions. What to consider: MCP has four more tools;max servedoes not yet open tasks in MAX. What is waiting for your reply.- Semantic search covers long messages in full. Before embedding, messages longer than about 1200 characters are split into overlapping chunks, so semantic search reads the whole message rather than just its beginning. Previously built chats are considered stale: rebuild them with
conversations buildorsearch --refresh(cli-messaging 0.153.0; the store moves to version 21, which older builds can still write). - MCP performs permitted writes from web clients without server forms.
--http-confirmation permissionsfollows permission levels:allowrequires no server form, whileaskrequires one. By default, a form remains mandatory for every write. Repeated--permission ключ=уровеньoverrides permissions only while the server runs, without changing settings. App confirmation is separate and is not checked by the server. What to consider: in this mode, the browser agent performs anything the profile permits atallow, including sending messages, without a form; check permissions before enabling it. Connection.
Fixed
- MCP member-tracking tool descriptions account for manual collection in MAX. They no longer promise daily list reads through
serveor offer the unavailablefetch --track. The group list and saved snapshots are still read from the local store.
0.29.0 — 06.10.2026
New
-
max chats tracking list|show|add|removemanages the groups tracked for member changes. Inspect saved member-count snapshots, add a group without fetching immediately, or remove it while keeping its history. Usemax chats members fetchto record members. MAXservedoes not yet fetch members daily: repeat collection manually or on your own schedule. -
Person profiles.
max contacts profile <человек>shows what MAX reports about a person: name, link, description, account creation time (registered, as reported by MAX), and whether they have their own photo. For each shared chat it shows their stored message count, first and last message. When MAX supplies a phone number, only its last four digits appear;--show-phonereveals it in full. One additional MAX request beyondcontacts show. MCP:max_contacts_profile. -
Rule-based replies, only to test accounts.
max serveanswers incoming messages using rules in<профиль>.replies.json, only for people listed intestersand only withpermissions.replies.send allow. Commands:max replies test,pause,resume,status. See docs/replies.md. -
max contacts context <человек> --chat <чат>(repeatable) returns their recent messages in each chat, with time and text for an agent to summarise.-vadds ids and links;--limitapplies per chat;--refreshfirst reads the chat's latest page from MAX. -
Uses cli-messaging 0.152.0.
-
max contacts check <человек>checks whether a person looks like a bot. It scores the profile and stored messages (no messages, a link as the first message, identical text in several chats), with a source for each reason. Public spammer lists cover Telegram only, so they are not queried for MAX.max chats members audit --deep <n>checks the first n members in the same way, one per second. -
max chats members fetchretains member snapshots;historyshows changes. History is available offline with--since-time.--budgetbounds a snapshot; departures are recorded only after a complete read. Daily tracking awaits support from MAX's background service. Working with members. -
max stats chartsplots chat statistics. The command returns a neutral JSON description;--outputsaves a dark SVG of messages, active authors, joins and departures by day or week. Missing dates remain gaps and incomplete data is labelled. Existing files are not overwritten. MCPmax_stats_chartsreturns the description from the local store; PNG will come separately. The new library adds about 61.6 MiB of unpacked files before deduplication and loads into the process only when an image is requested. Usage. -
Channel-post reactions are also retained by
max store fetch. MAX includes reaction counts with channel history;maxnow retains them, somax chats statscan rank channel posts by reactions without another request. -
max chats stats <чат>reports group or channel activity over a period. Messages, active authors, replies, reactions, top posts, questions and response times, joins and departures. It calculates from the local store and asks MAX for joins and departures. With incomplete stored history, figures are lower bounds and the command suggests astore fetchto fill the gaps. -
Search reads file text.
attachments extractretains TXT, DOCX and PDF text layers;content:searches it. DOCX/PDF require optionalmammoth/unpdf; an agent reads photos and scans and saves the result withattachments text set. By default it reads only downloaded files;--download --output-direxplicitly downloads them first. -
Refresh before searching and follow reply chains.
--sync-firstbounds fetching to five chats, 500 messages and 30 seconds; incomplete refresh does not hide local results.--threadadds a bounded reply graph with link provenance; without a graph it uses chronological context. -
Conversation search accepts strict filters and explicit account scope.
--filterlimits conversations before ranking; at least one message must match the entire filter.--sourceexplicitly widens scope. An agent can link messages entirely over MCP: thelink-conversationsinstructions, batches, storing links and rebuilding the graph. -
Configure embedding and analysis models independently per profile. Local vectors and your own agent remain the defaults. An external service receives text only when explicitly selected;
build --analyze --chatasks for consent and remembers it for the account, chat and service until revoked. -
Local tags:
max tags add,removeandlist. Tag a chat (--chat), person (--contact) or message (--message);tag:<метка>finds tagged messages. Tags stay in the local archive and never go to MAX. A tag is 1–32 Latin letters, digits or hyphens. The same actions are available to agents over MCP. See Message search. -
Saved searches:
max searchesand--saved.max searches create <имя> [запрос]saves a query with its options;max messages search --saved <имя>andmax messages stats --saved <имя>run it. Words added to--savednarrow the query; command-line options replace saved ones.searches list,show,history,deleteandclearinspect and clean saved searches and history. The query formessages searchis now optional when--savedis given. -
max contacts context <человек>shows what the archive knows about a person. Shared chats, the latest messages in both directions, recent messages and mentions. It reads the archive and marks nothing read.max contacts linkrecords that a MAX and a Telegram account belong to the same person, socontextincludes both;max contacts unlinkreverses it. Sincecontextreturns message text,permissions.messages: denyalso blocks it. -
max store repairrepairs archive structure without deleting data. It keeps a table with a different shape as a copy alongside the replacement and names it in the result.--dry-runpreviews changes without applying them.max store copies delete <имя>deletes one retained copy. See Archive. -
Search can use word stems when enabled.
max config set searchStemmers.cyrillic russianandsearchStemmers.latin spanish(orenglish) configure the whole archive, all profiles and both messengers. Runmax store reindexafterwards. -
max flood clearforgets remembered waits and lifts send holds. They appear inmax server status, in the newfloodfield. MAX does not yet report a wait duration, so this is empty for a personal MAX account. The login cooldown shown bymax doctorstill protects against frequent logins. There is deliberately no MCP tool: an agent must not lift a restriction. -
Three search guides. Message search covers everyday searches by words, people, dates, files, links and tags; topic search covers conversations, vectors and text sent to external models; query language is the reference.
Changed — may break scripts
-
Semantic search with local e5-small discards weak matches before combining them with word matches. Cosine similarity must exceed 0.80; word matches remain. Results may be shorter, and a result found by both methods may become a word-only match.
-
The archive gains attachment-text and analysis-consent tables. This is a local migration on first opening; old messages are retained. Back up a large archive before updating.
-
The archive now retains every successful
messages searchandmessages statsquery, from both CLI and MCP. It stores the query and options, never result messages, keeping the latest 1,000 runs. This powerssearches historyand--saved. If queries must not stay on disk, use--no-recordormax config set record false;max searches clearempties history and keeps saved searches. -
The archive migrates to a new schema on first use. It gains tables for tags, saved searches and word stems;
max store migratefinishes the stem index for existing messages. On large archives,store migrateandstore reindextake longer. The store is shared withtg; oldermaxandtgversions can still open it. -
max inbox,inbox --new,reviewandchats list --unread(including--searchand--kind) inspect all chats MAX returned at login, instead of the newest 200. Previously unread chats lower in the list were silently skipped. Each run still processes at most 20 chats, naming the rest inskipped N chats.partial: truenow means only that MAX did not return every chat at login. -
max chats listreportshasMore: trueon the last nonempty page when MAX returned an incomplete chat list. Previously the list appeared complete. Scripts paging untilhasMore: falsestop on the empty page. -
max messages listandmax store fetchno longer treat a short page as the start of a chat. MAX does not report whether older messages exist, and a page can be shorter than--limiteven in the middle of a conversation. After a short page,maxnow requests one older message: if it exists,hasMore: true; if not, this is the start of the chat. What to consider: this adds one MAX request per short page, andhasMoreis more oftentrue. -
max config setandconfig unsetacceptsearchStemmers.cyrillicandsearchStemmers.latin;config show --jsonexposes them in the newstoreSettingsfield. These settings live in the archive rather than the settings file, so--defaults,--personaland--botare refused; they cannot be changed underMAX_PROFILE_LOCK.
Fixed
-
Errors in reply-rule files no longer print fragments of those files in the service log.
-
max mcp --http: Claude and ChatGPT can now finish signing in. The login page made the browser submit its form with no origin, andmaxreplied “Origin not allowed”. Login now works (cli-messaging 0.152.0). -
A message locator from another account no longer opens a same-numbered message in the current account.
messages show/contextrefuses it; MCP acceptsoffline: truefor ordinary local context. -
Strict
text:/…/regex search matches words the same way as word search. Previouslytext:/Квартир.*/andtext:/счёт/missed stored words because of case and the letter ё.body:remains case-sensitive. -
Strict-search errors explain what to do.
~suggests--language legacyandслово*; a short prefix such asк*names the 10,000-word limit and asks for a longer prefix;index_not_readyreports index progress and the exactmax store migratecommand. -
MCP does not retain query history when recording is disabled. Previously
record: falsedisabled history only in the CLI.
0.28.0 — 04.10.2026
New
-
MCP
max_chats_statscounts group or channel activity from the local archive; joins and departures are not requested.max chats members auditshows signs of suspicious members without removing anyone. -
MCP
max_inboxandmax_reviewacceptkindsandnew, with per-chat points kept separately from the CLI. -
max messages statscounts messages from the local archive by chat, sender, day or hour. The query uses strict Lucene; without one, all saved messages of the current account are counted. No network is used;--source maxexplicitly includes other profiles. In an incomplete archive, the result stays a lower bound; checkcoverageandcompleteness. -
max mcp --http --public-url https://<имя>.ts.netopensmaxto ChatGPT and Claude in the browser. MCP tools are served on127.0.0.1behind your own tunnel, with their own login: the app needs a one-time code thatmaxprints in the terminal. Every change first asks through a form in the app. The login lasts 30 days;max mcp --revokeends all logins. docs/remote.md replaces the setup with a third-party proxy. -
Personal MCP uses the same set of schemas as Telegram: devices, contact lookup by phone number, folders, members, invite links, group settings, polls, local evidence and conversations. Telegram topics are not supported in MAX. The old names of the group check and rules are kept.
-
A confirmed scheduled send uses the time from the form, even if the answer arrived later.
Changed — may break scripts
-
coverage.inventoryCompletenow reflects receiving a full chat list, andlastSyncedAtthe oldest fetch in coverage;completenessentries containfetchedAt. An existing archive gets this information after the next full chat list and history fetch./catch-upacceptskindandmodeinstead ofsince. -
config set permissionsrejects unknown commands with code 2, including typos inside a whole object.config unsetlets you remove them; reading an existing file prints a warning and continues. -
MCP arguments now use shared names:
at_time,md,since_time,before_n,after_n,unanswered;send_idis now a string. Unknown arguments are rejected before anything runs. Update your calls using the schema fromtools/list. Formax_inboxandmax_review,all: trueincludes muted and archived chats; without it, only mentions of the owner remain.
Fixed
- Search and statistics show the actual coverage of the local archive and the time of the last fetch.
wordsReadyno longer promises a ready word index for searches that use only filters or regex.store fetchignores the start-of-history mark if older messages turn up in the archive. server statusreports the exit code of a normal service shutdown and the reason it stopped, without starting it again.
0.27.0 — 04.10.2026
New
-
Global npm installation sets up Windows PATH and the agent skill. Existing PATH entries are preserved and
maxbecomes available in new terminals. An already-running agent must refresh its environment. The skill installs before login;MAX_INSTALL_AGENT=nonedisables it. Local installation and npx do not change the user's environment. -
max commands messages search --jsondescribes one command;max commands messages --jsondescribes a group. Agents no longer need to read the entire tree before every task. Global options and exit codes remain included. Words aftercommandsspecify one path; inspect other groups in separate calls. Without a path, the command still returns the entire tree. -
max messages linkand MCPmax_messages_linkreturn a message locator from the local archive. The target is validated under the current account; another account's locator is refused. Personal MAX has no verified permalink format yet:urlisnulland the response includes the reason.--offlinedoes not connect to MAX. See messages.
Changed — may break scripts
-
CLI and MCP use
permissionswith levelsdeny,readonly,askandallow. Commands and agents share the same permissions. Most MCP writes are now available by default; deleting messages and ending other sessions require confirmation unless explicitallowapplies. For example,messages: readonlywithmessages.delete: allowpermits reading and deletion without a question while forbidding other message writes; other resources remain unrestricted. Check agent permissions before updating and setreadonlyordenyon the resources you want to restrict.--confirm-sendrequires a form before every write; JSON-modeaskrequires an explicit flag. -
config migrateconverts legacy access settings and moderation-rule levels.--dry-runpreviews changes without writing. Migration preserves effective permissions, MAX settings and saved group-check positions. Oncepermissionsexists,readOnly,allowandmcpToolscannot be changed. Legacy MCP flags--allow-send,--allow-mark-read,--allow-deleteand--allow-moderateare accepted with a warning but grant no permissions. The recipient list and hourly limit still apply. See configuration and MCP.
Fixed
- Concurrent local-archive initialization waits for a brief SQLite startup lock. Previously, journal configuration could encounter a busy database before the wait timeout was enabled and fail immediately. A long lock still produces an error. This change does not start downloading history.
0.26.0 — 03.10.2026
New
-
max skill show link-conversationsprints the shared conversation-linking skill. It works without a session; without a name, it still prints the main MAX skill. -
max messages evidencereturns a bounded packet from the local archive, with a locator, completeness information and continuation through--before-id. It does not connect to MAX.
Changed — may break scripts
-
Downloaded photos get their extension from the HTTP MIME type, such as
.webpfor WebP, rather than JPEG based on the attachment type. Original file names remain intact; no extra preliminary requests are made. -
max account showuses the shared account format with Telegram. JSON addsusername: null; existing MAX fields, phone masking and--show-phoneremain unchanged. -
max sends listrespects the configuredlimit, as Telegram does. Previously it always selected 20 attempts without a flag. JSONlimitreports the selected limit;items,pageandhasMoreremain.--limitoverrides the setting. -
max messages downloadsupports--all,--output-dirand--pause, as Telegram does. The directory is created automatically; repeating a full-chat download continues saved progress.--outputremains a compatible directory name. Single-message JSON now contains{items}without artificialpage,limitandhasMore; scripts should readitems. Voice files now havekind=voice, as in Telegram, instead ofaudio. Downloads stream with the existing address and size checks; voice files retain the 32 MiB limit.
Security
max contacts lookupdoes not echo a phone number mistakenly passed as an argument. It refuses before prompting or connecting; enter the number at the prompt or through stdin.
Fixed
-
messages list,inboxandreviewwith--transcribedownload the recording through the reading connection. Previously, a second login to MAX was opened. The recording is downloaded before the connection closes, and local recognition starts after it closes. Nothing is marked as read without an explicit--mark-read. -
review --unansweredtakes into account saved and new transcripts of voice questions. Previously, a question with empty text was dropped before transcription. The same fix applies in MCP; the original message text does not change, and unrecognized recordings leave the review incomplete. -
max chats showexplains differing member counts accurately. The list may exclude your account or be incomplete. The command reports both counts without claiming a download failure. JSON and the original member list remain intact. -
The
poll.already.votedrefusal explains how to change a vote. If the poll allows this, first runpolls vote <chat> <message> --retractin the same profile, then select the new answer. -
max messages download --timeoutalso closes the attachment's HTTP stream. Previously it could continue after the command timed out until a separate idle timeout. Adapter close now cancels its streams and removes the incomplete file.
0.25.0 — 03.10.2026
New
bot apiuses the same command builder and input validation as Telegram. Generators remain in cli-core; parameters, native responses and effective MAX permissions are preserved. The shared--store-token <profile>option is for operations returning credentials; other operations reject it.
Fixed
messages list,inboxandreviewwith--transcribedownload the recording through the reading connection. Previously, a second login to MAX was opened. The recording is downloaded before the connection closes, and local recognition starts after it closes. Nothing is marked as read without an explicit--mark-read.review --unansweredtakes into account saved and new transcripts of voice questions. Previously, a question with empty text was dropped before transcription. The same fix applies in MCP; the original message text does not change, and unrecognized recordings leave the review incomplete.
Changed — may break scripts
-
max models audio list --jsonaddsdirectory: the shared model directory used by MAX and Telegram. Model commands, directory selection and download verification are now shared; existing files, model order andtranscribeModelremain. Models do not need another download. JSONL still returns one model per line. -
--mduses MAX's own formatter for send/edit and captions: nested styles,__жирный__,++подчёркнутый++, links and code. Bots support emphasis, headings and quotes through safe HTML; the personal protocol explicitly refuses unverified types. Telegram has different syntax. Unknown wire types are no longer silently sent.
0.24.0 — 03.10.2026
New
max setupguides the first run for a personal account: it checks local directories, offers QR login, checks the account and up to five chats, and connects the selected agent skill. Repeating setup reuses an existing session. History is downloaded separately; setup does not start the background service. Help, installation and agent instructions explain next steps and Windows execution without PATH.max skill showis available before login.
Changed — may break scripts
-
max chats checkis replaced bymax chats moderate: shared rules and moderation with Telegram.--since-timeaccepts a time or30m/2h/1d, replacing the former--sincewith a message number; JSON is now{ chatId, rows }. Each run reads up to 1000 messages. Rule levels aredeny|readonly|ask|allow; oldforbidandflag|confirmare read asdenyandask. The saved check position moves from the session to the existing rules file, so the first run resumes there. CLI and personal MCP use the same position; MCP tool names and flags are preserved. Inchats events, joining via a link is calledjoin. -
max upgrade --jsonalways includesrestarted. In MAX this is an empty array: the server restart policy is unchanged. Version checks and no-update results use the same response shape as installation; previous fields remain. Scripts that validate the exact set of keys must account for the additional field. -
Local search uses a strict Lucene profile: parentheses, fields, date ranges and
--timezone, limited wildcards and regex. Prefix matching is explicit, asслово*; the previous typo-correcting search remains available with--language legacy. JSON reports coverage even without matches. The guide and skill explain migration; JavaScript--regexruns in a separate worker with size and time limits. -
max commands --jsonreturns the JSON contract version incontract. Value0matches Telegram CLI; previous reference fields remain. Scripts that compare the entire JSON against a saved string must account for the new field; reading individual fields requires no changes. -
Group reads use shared options and formats.
chats eventsaccepts--since-timeinstead of--sinceand--typeinstead of--event; the boundary is a time, rather than a message ID. Creation events are nowcreateinstead ofnew.chats members listshows a page with--limit,--pageand--all; add--allfor the previous scope. JSON no longer containschatIdorrolesKnown, but roles, registration dates and last-seen times remain in rows.chats inspectreturnsid,kind,title,username,participantsCount,descriptionandmemberinstead of a record with access, link and settings.memberandusernamearenullwhen MAX does not report them. These are shared MAX and Telegram reads; update scripts and filters. Warnings about incomplete member lists and unknown roles remain; no read marks messages as read. See groups. -
Group-management commands return shared JSON with
operationId.chats create,join,updateandlink resetput the record inchat;leavereturnschatId.members addnow hasaddedandnotAdded, whilemembers removehasremoved;adminscommands returnpersonId, and adding an admin also returnsrights. This is the shared MAX and Telegram operation format; scripts must update result parsing.link showkeeps its previous format. Titles and settings still change through two requests: if the title or description changed but the settings request did not complete, the command reportsoutcome_unknownand records a partial result in the journal. Readchats showbefore retrying. See group management. -
max account updateandmax account sessions endreturn the shared format withoperationId. Profile changes return{operationId, account}withid,name,username,phone; ending sessions returns{operationId, sessions}instead of an array. This is the shared MAX and Telegram operation format; scripts must read data fromaccountorsessions. A profile description is no longer returned after a change: useaccount show. Phone numbers remain masked;sessions endstill requires--others --yes. Profile photos now accept JPG, JPEG, PNG and WebP; convert GIF to one of these formats. See profile and sessions. -
max chats folders create|update|deletereturnsoperationIdalongside the result. Creating and updating return{operationId, folder}; deleting returns{operationId, folderId}, instead of the folder record itself. This is the shared MAX and Telegram operation format; scripts must read the record fromfolderand usefolderIdafter deletion.updatewithout--title,--addor--removenow refuses rather than rewriting the same folder. Listing folders keeps its previous format. See folders. -
max contacts add|remove|block|unblock|rename|importreturns the shared format withoperationId. Adding and renaming return{operationId, person}; deleting and blocking return{operationId, personId}; importing returns{operationId, sent, recognised}.recognisednow contains person records (id,name,username) returned by MAX, instead of phone numbers; if no records are returned, the list is empty.sentcounts file rows, including duplicate numbers. This is the shared MAX and Telegram operation format; scripts must update response parsing. A phone number rejected by MAX no longer reports the file row; malformed rows still report their number. See contacts. -
max cache clearis removed. All reads and name resolution use the shared local store;max store clear --left --allow-dangerousremoves data for departed chats. There is no command to erase the entire shared store. The old file is neither migrated nor opened;max doctorshows its path, and history can be fetched again withmax store fetch.
Fixed
-
max conversations embed statusestimates e5-small time more accurately. It uses the measured 31 chunks/s rather than 15; on the measured laptop, the previous estimate was twice as long. Actual time depends on the computer and text length. Three worker threads delivered a measured 1.04–1.1× speedup at substantial memory cost; thread allocation is unchanged. -
max_messages_searchthrough MCP retains archive coverage metadata and uses the same search parameters as CLI. Available parameters includelanguage,timezone, versionedast, chat names, andsource,newest,contextfilters. The default profile accepts single-character queries. Previously, some parameters were absent and responses lostquery,coverageandcompleteness; empty results did not explain local-store coverage. Previous response fields and the tool name remain unchanged. -
max runs list --limitsuggests increasing the limit when some records are not shown. The hint no longer suggests an unsupported--pageoption. Reading the list or an individual record does not create another run; the JSON list still containshasMore. -
chats showdisplays a saved group even if it is absent from the latest login delta. Previously, the read could fail with “chat not found”. Unknown settings and links now stay empty; reading changes nothing in the group. -
max messages transcribefinds a saved transcript by chat name when the model has not been downloaded. Previously, it looked for text using the entered name instead of the chat ID and suggested downloading the model again. The full name or an unambiguous fragment now returns saved text without downloading the recording or recognizing it again. See voice messages. -
On Windows, the generator uses Node instead of directly launching
.cmd; documentation checks recognize Windows paths. Unix-permission tests do not require them on Windows, where ACLs control access. -
max boterrors before an action starts follow the bot profile’s recording settings, even with--timeoutbefore the command. Previously, a global option beforebotcould cause personal-account settings to apply. When bot-profile recording is disabled, a command-parsing error no longer creates a record against that setting.
0.23.0 — 03.10.2026
New
-
max serveand chat-management commands save names and chats in shared local storage. The old profile cache is no longer opened. A complete chat list marks departed chats; an empty response preserves the previous list. -
Contact commands and shared read commands save data in shared local storage. Name resolution and
contacts syncno longer require the old profile cache; synchronization still returns counts only. Deleting the old file does not reset the sync position. Runmax contacts syncto fetch the complete list again. -
max mcpreleases its search model after 10 minutes without searches. Agentconversations_searchno longer holds about 1 GB throughout the session. The next search reloads the model in about a second (cli-messaging 0.110.0). -
Chat and person completion uses the selected account's shared store. The old cache is unnecessary. Tab still never connects to MAX; bot commands suggest chats from their local list.
-
max mcp setup codex|claude-codeandmax mcp doctoradd local MCP to the selected client and check startup and available tools. Installation requires--allow-writesif the profile offers writes; this approval changes no permissions and does not verify MAX login. -
max <бот> bot store fetch <чат>downloads history to the bot's local store, newest first, with resumable runs.--last,--since-time,--limit,--page-size,--pausework likemax store fetch. -
--yesfor any command approves a write prompt required by consent levelask;max account sessions end --others --yesworks as before.
Changed — may break scripts
-
messages send --topicandpolls create --topicclearly reject MAX destinations. This shared option addresses Telegram forum topics, unsupported by MAX. No message or poll is sent; ordinary calls without--topicare unchanged. -
max doctor --jsonreports the shared store instoreand the old file inlegacyCache. It no longer opens the old cache or checks its schema. Scripts readingcachemust switch tostore. Delete old files manually and fetch history withmax store fetch. -
MCP reads the shared message store. Search, contacts, chat resources and transcripts use
messages.dbunder the profile account. The old cache is no longer opened. Reading history saves searchable messages. Voice attachments havekind: "voice". Tool names and parameters are unchanged. -
inboxandreviewuse shared command and message formats. Replace--sincewith--since-time.review --unansweredaccepts durations (4h,1d), not a number of hours. JSON voice attachments usekind: "voice"instead of"audio".--allincludes muted and archived chats. The first inbox run migrates the previousinbox --newposition. Review pages backwards and returns at most 300 messages per chat, marking incomplete results. Update script commands and JSON checks. -
Personal-account transcripts are saved in shared storage.
messages transcribe,inbox,reviewand MCP use the same account-scoped text asmessages list. Old profile-cache transcripts are not migrated; an explicit--transcriberequest recreates them using a downloaded model. -
max <бот> bot people showbecomesmax <бот> bot contacts show, with MCP toolmax_bot_contacts_show. Together withbot messages search|between, these commands are shared withtg; options and responses are unchanged. -
max <бот> bot chats checkis nowmax <бот> bot chats moderate— sharing the name and command withtg.--sinceis now--since-time(still accepting2h,1d); the--jsonresponse is{ chatId, rows }instead of a list; the MCP tool ismax_bot_chats_moderate. Rules and the previous check position remain in the same files. Consent levelflagnow means the same asconfirm: ask you, or act with--allow-dangerous. -
max <бот> bot mcpgrants access according to bot profile settings, rather than flags. Without flags, agents can write unlessreadOnly: trueorallowrestricts them. Deletion uses a confirmation form;--allow-dangerousremoves it.--allow-send,--allow-deleteand--allow-moderateare accepted with warnings but grant nothing. SetreadOnly: trueto retain read-only access. The server is now shared withtg. -
max bot messages searchmatches words, best matches first, instead of substrings newest first; use--newestfor the old order. All words are required."фраза",-слово,а OR бand filtersfrom:,chat:,after:,before:,has:are supported; typos are corrected with a stderr notice. Words need not be quoted;--fromremains repeatable. Bot search does not supportin:; it searches its own copy and copies permitted byreadOtherBots.
Fixed
- Bot write rejections suggest a valid configuration command with
--bot. Read-only failures suggest disablingreadOnly; missingallowpermissions suggest adding the action while retaining existing permissions. Previously the hint named nonexistentbot config.
0.22.0 — 02.10.2026
Most personal-account commands are now shared with tg: identical options and --json responses, and one shared store. Many names changed; see “Changed — may break scripts”. The previous max cache is not migrated. After upgrading, run commands without --offline and download history again with max store fetch.
New
max conversations search "<запрос>"finds semantically related conversations in one or all chats. Downloadmax models text download e5-smallonce (135 MB, shared withtg), then usemax conversations embed --chat <чат>to calculate vectors locally.embed statusreports remaining work;embed cleardeletes vectors. With--provider openaiand your key (max models text key set openai), an external service computes vectors;embedfirst reports token count and cost and asks for approval.- Direct-chat
chats list --jsonincludesproviderMetadata.partnerId, identifying the other person. Shared commands use it because MAX chat IDs and participant IDs differ. max messages searchcan search other accounts in shared storage: queryin:max,in:personal,in:bots,in:allor use--source. Otherwise it searches the current account as before.max conversations build|list|showandmax messages linksfind group conversations locally from replies, mentions and message order without querying MAX.conversations batches status|nextandconversations links add|clearprovide agent batches and accept its responses.max server logs,max server install,max server uninstall, matching tg.installwrites a systemd (Linux) or launchd (macOS) service without starting it;max server startandstopthen use the service. Authentication rejection does not restart the service, avoiding repeated logins.max server start --idleandrestart --idleremain supported.max store statusreports per-chat message counts and complete downloaded ranges.store fetch --backgroundandstore jobs list|show|cancelmanage background downloads.store info|check|migrate|backup|restore|reindexmaintain the shared store.store clear --left --allow-dangerousdeletes departed chats and messages.max bot auth,max bot list,max bot chats list,max bot recipientsandmax bot sends listare shared with tg through cli-messaging, with identical responses and hints. Tokens, recipients and logs retain their locations.max cache clear --leftdeletes only departed chats and their messages from the profile cache.max messages search --regex— one regular expression across all saved text.messages show|context msg:…— a message from asearchlink, without a separate ID.max polls show <чат> <сообщение>reads a poll, answer IDs and vote counts without changing anything.max polls create --send-idsafely retries poll creation after a missing response without creating a second poll.max messages send --photo <путь>— send.jpg .png .webpas a photo, as in tg.--no-previewis also available onsend, but MAX does not support it and the command refuses.max skill installinstalls the agent skill with one command: in~/.claude/skills/max-cli/for Claude Code and in~/.agents/skills/max-cli/for Codex and Gemini CLI, with themaxversion number.--for claudeor--for agentsinstalls into just one directory.max skill showprints the same content as before.- The agent learns about the skill automatically. If
AI_AGENTorCLAUDECODEis set and the skill is missing or older thanmax, one line aboutmax skill installappears in stderr once a day. Nothing is added to stdout. Disable it withmax config set skillHint false --defaults. max mcpandmax bot mcpexposemax://skilland mention it in agent instructions.max messages deletereturnsoperationId, also found inmax sends list. MCPmax_messages_deletedoes too. Options are unchanged.- Every send-log record includes
operationId, grouping records for one send, edit, deletion or chat change. For a message send, it equalssendId. - Installation is about 16 MB smaller: the database layer is bundled instead of installed separately.
maxcommands are unchanged.
Changed — may break scripts
-
max messages searchmatches words, best results first. Use--newestfor the former newest-first order. Queries support"фраза",-слово,OR,from:,chat:,after:/before:andhas:. Typos are corrected with a stderr notice.--context <n>shows neighboring messages. JSON addsmatchandscore. -
max bot updates watchis nowmax bot watch, like in tg and the personalmax watch. Without--events, only new messages are printed; with--events, all events are printed, and each line names its event ({ "event": "message" | "edit" | "delete" | "callback" | "joined" | … }) instead of a raw MAX event.--timeoutends it normally with code0.watchis now allowed for read-only bot profiles: receiving events is reading. The resume marker is unchanged. -
bot webhooks listreturns{ url, types }, not MAX-specific fields.bot callbacks answer --textno longer reads stdin through-.bot commands,bot callbacksandbot webhooksare shared with tg.webhooks set --secret-stdinprompts only after permission checks. -
Node 22.16 or later is required, or Bun as before. If Linux Node uses an outdated system SQLite,
maxrestarts using bundled SQLite from@wirecat/cli-messaging-sqlitebefore reading or sending. Official Node builds and Bun need no change. -
max storeis shared between tg and max.store fetchwrites to shared storage and pages MAX as before: 30 messages, 5–10-second pauses, up to 40 pages per run. This gives both messengers one store and consistentmessages,conversationsandstorereads. The old cache is not migrated; refetch history. Also:store fetch --estimateis rejected for MAX because message IDs cannot count missing records.store fetch|export --sincebecomes--since-time, accepting time only, not message IDs.store fetch --max-pages <n>becomes--limit <сообщений>, default 1,200 or forty 30-message pages. Page size uses--page-size.store export --format mdbecomes--format markdown;jsonlis unchanged. Missing ranges are reported bystore statusrather than export stderr. Existing files are never overwritten.store fetchno longer prints a ready-made export command.- If two messages share a millisecond and a page boundary separates them,
store fetchcan rarely miss the earlier one.
-
max messages list|show|context|searchare shared tg and max commands.--offlineandsearchread from the shared local copy, the same one used by tg. Why: the same options and responses as tg, and one copy for reading. What to consider: message and chat reading tools inmax mcpstill read the old max copy, so an agent using MCP and a terminal command with--offlinemay give different answers. The copy starts filling on the first run without--offlineafter updating; the old max copy is not migrated into it, including transcripts of voice messages heard before updating. Also:- Voice attachments use
"kind": "voice", not"audio";inboxandreviewstill use"audio"in this release. messages list --beforeand--aftersplit into--before-id,--before-time,--after-id,--after-time;messages contextuses--before-n,--after-n. Old options produce unknown-option errors.messages list --before-idexcludes that message itself; with--offline, only--before-idworks, and only with a message ID from the local copy;messages list --transcribe --jsonno longer returnstranscribeProblem: the reason appears in stderr; with--offline,unheardis empty. Voice messages are downloaded through a separate connection — with--no-serve, this is a second MAX login;maxlooks for speech models in~/.cache/cli-common/models/audio, the same directory as tg; a model downloaded into~/.cache/max-cli/models/audiomust be downloaded again or moved;messages searchmatches words and prefixes (квартирfinds “квартира”), rather than arbitrary three-letter substrings.--chataccepts a stored chat title.
- Voice attachments use
-
max chats list|showandmax contacts list|showare shared tg and max commands. Their--offlinereads from the shared local copy, the same one used by tg. Why: the same options and responses as tg. What to consider: the copy starts filling on the first run without--offlineafter updating; the old max copy is not migrated into it, and until then--offlinereturnsnot_found. Also:chats list --search|--kind|--unreadwithout--offlinesearches the 200 most recent chats and writes to stderr if older chats existed; with--offline, it searches all saved chats;chats show --offlineomitsdescription,access,settings, available only from MAX.- Invalid
--kindvalues now report--kind is one of dialog, group, channel, saved. cache clearalso clears this account from shared storage;contacts syncfetches everything into it.
-
max messages send|edit|forwardare shared tg and max commands.--jsonresponses:sendreturns{sendId, operationId, message}(withscheduledForwhen using--at-time);forwardalso returns{sendId, operationId, message};editreturns{operationId, message}, instead of an unwrapped message. MCP toolsmax_messages_send,max_messages_editandmax_messages_forwardreturn the same shapes;max_messages_editno longer hasmarkdown, andmax_messages_forwardno longer hassend_id. Why: the same options and responses as tg, with an action ID matching the send log. What to consider: scripts reading the message from the response root must now readmessage.sendno longer accepts several--fileattachments for one message: one attachment from--fileand one from--photo. If a send with--at-timegets no response, the error recommendsmessages scheduledwithout naming a chat. -
max pollsis shared with tg.polls vote|close --jsonreturns{operationId, poll}, withpollshaped as{chatId, messageId, question, answers: [{id, text, voters, chosen}], closed, multiple, anonymous, voters}.polls createreturns{sendId, operationId, message}. MCPmax_polls_vote,max_polls_close,max_polls_creatematch.max_polls_createreplacesrevotewithsilent. -
--jsonresponses for reactions, pinning and marking read are shared with tg, and each includesoperationId, the ID of that action as in the send log:reactions add|remove:{operationId, chatId, messageId, reaction}, your reaction ornull; message counts remain available throughmessages list.messages pin|unpin:{operationId, chatId, messageId, pinned}, withpinnedastrueorfalse.chats mark-read:{operationId, chatId, until}, withnullmeaning through the latest message.
MCP
max_reactions_add,max_reactions_remove,max_messages_pin,max_messages_unpin,max_chats_mark_readmatch. -
max messages unpin <чат> <сообщение>now requires a message number, likepinand tg. MAX has one pinned message per chat; that message is unpinned regardless of the number supplied. MCP toolmax_messages_unpinalso requiresmessage. What to consider:messages unpin <чат>without a number fails — add any message number from that chat. -
max serve --detachandmax serve --stopare removed, replaced bymax server startandmax server stop.servehandles foreground work;max servercontrols background work. Update scripts and manually written services. -
max server status --jsonreturns the same fields as tg:byHandbecomesby(handmeans manually started,commandmeans started by a command,servermeansmax server start,unitmeans a service); added fields arelog,unitandstale(the server crashed and left a marker).max server start,stopandrestartrespond as in tg:{ started, by, pid, startedAt, log }and{ stopped, by, pid };socketis removed. -
max messages send --atis now--at-time, as in every tg and max command whose option accepts a time. Scripts using--atget an “unknown option” error — replace it with--at-time. MCP parameteratinmax_messages_sendis unchanged. -
--markdownis removed; use--mdinmessages send,messages editand everywhere markup is read. This name is used in all tg and max commands; scripts with--markdownget an “unknown option” error — replace it with--md. -
max sends list --jsonrenamescidtosendId, a string instead of a number, matchingoutcome_unknownand--send-id. Older records are displayed in the new format too. -
Run records (
--trace,--record,max runs show) use a shared tg and max format. An event’s send ID is calledsend, notcid; the MAX failure field isproviderError, notmaxError, in events,run.jsonand thedetailsof a--jsonerror. -
max botreturnsoutcome_unknown(code14) for write responses 502, 503 or 504, previouslyprovider_unavailable(code12). Gateway responses do not prove whether MAX executed the request; it may have succeeded. Scripts retrying code12could duplicate writes. For code14, check the result first. Reads still retry and returnprovider_unavailable. -
Bot commands use shared tg names; old names are removed.
max bot messages get <сообщение>→messages show <чат> <сообщение>;messages edit|deletealso take chat first.bot chats get→chats show;bot chats pin|unpin→messages pin|unpin <чат> <сообщение>.--format markdown|htmlbecomes--mdor--html.--typeis removed: use--photo,--voice, or--as-filefor video documents.chats actionacceptstyping,photo,video,voice,file. Sends and edits return{ operationId, message }. Deletion asks for approval;--allow-dangeroussupplies it. MCP names aremax_bot_chats_show,max_bot_messages_show,max_bot_messages_pin,max_bot_messages_unpin. -
max bot membersandmax bot adminsare nowmax bot chats membersandmax bot chats admins, as in tg.admins addtakes--canwith the values frommax chats admins add(read,members,admins,info,pin,link,edit,delete) instead of--permissions, and--titleinstead of--alias.--canhas no “calls” or “statistics” rights.admins listreturns{ id, name, username, role, rights, title }. MCP tools:max_bot_chats_members_list|add|remove,max_bot_chats_admins_list. -
Local-only changes are now classified as writes.
config set,unset,chats rules set,unset,recipients add,remove,clear, and botauth set,remove,chats rules set,unset,recipients add,remove,clearwrite configuration, rules, recipient lists or keyring entries, never MAX. The Command reference labels them “Changes data only on this computer”;max commandsshows them inwrites. Read-only filters usingmax commands --jsonnow exclude them.
Fixed
- Time-based
max store fetchno longer skips a boundary message and stops if MAX repeatedly returns the same page. max messages list --before-timeexcludes messages at the exact millisecond boundary: before means strictly earlier.max messages list --after-id(0.21.0:--after <id>) reports a next page when present, instead of always claiming none for forward reads.max messages send --voiceworks throughmax serve. Previously its waveform was lost, causing MAXproto.payload, code11. It already worked with--no-serve.max chats listandmax chats showremove departed chats on the next login returning a complete MAX chat list. Previously they remained with stale member counts. Messages remain untilmax cache clear --left.max servedetects departure only on its next full login.max serveno longer confuses responses after prolonged use. Two-byte request numbers wrap after 65,536 requests; pending numbers are now skipped to avoid assigning another request's response.
0.21.0 — 30.09.2026
Changed — may break scripts
Commands follow one naming rule: subject first, then action. Old names no longer work — max returns “unknown command” or “unknown option” with code 1 and does nothing.
max backup messages→max store fetch. Download starts immediately;--estimateonly calculates (previously downloading required--run). Each run still handles up to--max-pagespages, default 40, with the same pauses.--pauserequires a duration (5s,500ms); unitless numbers refuse.--sinceand--lastare optional: repeated runs otherwise reach the beginning, resuming where they stopped.max export messages→max store export.--cid→--send-idformessages sendandmessages forward.outcome_unknownusessendId; MCPmax_messages_sendandmax_messages_forwardrenamecidtosend_id.max chats read→max chats mark-read; MCPmax_chats_read→max_chats_mark_read.max chats settingsis removed.max chats showdisplayssettings,description,access;max chats link showstill displays invites. Change settings withmax chats update <чат> --all-can-pin on|offand other flags.max update→max upgrade, and the new-version notice now namesmax upgrade.max recipients off→max recipients clear, responseoff→cleared;max bot recipients off→max bot recipients clear.max account sessions end-others→max account sessions end --others; omitting--othersrefuses.
New
max completeappears inmax --help, making Tab setup discoverable.- Browser access guide: ChatGPT or Claude through a password-authenticated proxy and public Tailscale address without a domain. Based on documentation, not tested end to end.
0.20.0 — 30.09.2026
Changed — may break scripts
- The shared message store moves to version 6 (cli-messaging 0.49.0). The first
maxrun updatesmessages.db; after that,tgversions older than the one released that day refuse to open the file and ask you to update —npm install -g @wirecat/tg-cli@latest.maxcommands are unchanged. --all-botsrequires permission to read other bots. ConfigurereadOtherBotsinbotwithmax <имя> config set --bot readOtherBots true, or a profile list. Otherwise the command refuses with code5and an enabling command.- When a name matches several people, candidates are sorted by name, with unnamed people first; previously they followed cache order. The error text is unchanged.
New
--bots news,supportforbot messages search,bot people show,bot messages betweenreads only those profiles if permitted byreadOtherBots.bot messages searchalso supports--all-bots.bot mcpexposesall_botsandbotsfor these three tools only when cross-bot reads are allowed.- People are isolated per bot. A person seen by one bot is unavailable to another without
--all-botsor--bots. - Bot text search matches three-letter substrings inside words (
вартирfinds “квартиру”), like personal search in this release.
0.19.0 — 28.09.2026
Changed — may break scripts
- An agent using
max mcpcloses a poll only if the profile permitsedit. Previously,reactionwas enough. Why: closing edits the poll message, andmax polls closealways requirededit— the agent and a person had different permissions for the same action. What to consider: if the profile’sallowincludesreactionbut notedit, the agent no longer seesmax_polls_close; addeditto let it close polls. Ifallowis unset, nothing changes. See docs/mcp.md.
Fixed
max mcp --confirm-sendstarts when account changes are enabled only throughmcpTools. Previously, the flag also required one of--allow-*, or the server would not start. Why it matters: a server with onlymcpToolstherefore ran without a confirmation form — the agent could add and remove contacts, create groups and change the profile without asking you. What to consider: without--confirm-send, behavior is unchanged. Add the flag to the server startup command to see a form before every change.max <бот> bot messages search --limit Nreports when more matches exist. Previously, responses always hadhasMore: false, andlimitcame from settings rather than yourN. What to consider: a script or agent relying onhasMoreto continue searching stopped on the first page and missed matches. It now receiveshasMore: truewhen there are more thanNmatches.
0.18.1 — 28.09.2026
Fixed
max contacts renameappears immediately incontacts showand direct-chat titles. Previously names remained stale until backgroundmax servelogged in again because it ignored the returned contact. If still stale, the first 0.18.1 command replaces the old server.
0.18.0 — 28.09.2026
New
- Account-changing tools in
max mcp: add, remove, rename and block contacts; close your poll; join, leave and create groups; appoint and remove admins; change profile name and description. Previously MCP only read and sent messages. Only the owner enables them throughmcpTools, for examplemax config set mcpTools contacts,polls; agents cannot self-enable through flags. Every action passesreadOnly,allowand logging. See MCP guide. - Bot file uploads appear in
--traceand run records.bot messages send --fileandbot uploads putshow two lines with file type, size, HTTP status and duration. Upload URLs and filenames are never displayed or logged.
Fixed
max contacts renamenow renames contacts. Previously, MAX reported success but the name remained unchanged. Why: withoutlastName, MAX silently changes nothing.lastNameis now always sent (nullif no surname), as in the web client. What to consider: names “changed” through 0.17.x were not actually changed — rename them again.
0.17.1 — 28.09.2026
Fixed
- Invalid
--limit,--last,--max-pageserrors repeat your input formessages list,inbox,backup,sends listand bots.--limit abcpreviously reportedNaN; 0.17.0 fixed only paginated lists. runs listandsends listtruncated by--limitreporthasMore: true. Previously, responses hadhasMore: false, andlimitdiffered from the number requested. What to consider: scripts usinghasMoreto decide whether to keep reading previously stopped on the first page.- A contact you renamed appears under the name you chose, as in the MAX app. Previously,
maxshowed the person’s own name even if you renamed them withcontacts renameor in the app.
0.17.0 — 28.09.2026
Changed — may break scripts
- Every list in
--jsonis an object{items, page, limit, hasMore}, rather than an array. This now applies toaccount sessions list,chats members list,chats folders list,messages scheduled,messages download,messages context,models audio list,recipients list,sends list,runs list,chats check,chats eventsand all bot lists. Previously, some returned arrays, andchats eventsreturned{events, more}. Why: lists came in three different shapes, so scripts and agents had to remember each command’s shape. What to consider: scripts that read an array must now read.items. For a list without pages,pageis 1 andlimitis the number of returned rows.bot members listandbot admins listalso includemarker, and theiruser_idis now a string.bot messages getreturns the message itself, rather than a one-item array.--jsonland human-readable tables are unchanged. MCP follows the same format.
New
max doctorandmax config showrecognize bots. The profile list includes all profiles on this computer, marked as personal account, bot or both. Bot profiles were previously missing.doctorshows the bot token’s source (without the token itself), how many chats the bot has seen and where profile files are;doctor --onlineasks Bot API who owns the token. What to consider: for bot profiles,doctorand personal commands no longer suggestsession start; they name the appropriatemax <имя> bot …command.- MCP
max_statusandmax_bot_statusreport the server profile, token presence and enabled writes. Neither writes;max_statusnever logs into MAX. - Tab completion recognizes bots. For bot commands, it suggests chats the bot has seen rather than personal account chats; for the first word, it suggests all profiles, including bot profiles.
- Bot commands support diagnostics like personal commands.
max <имя> bot … --traceprints each request's operation, chat/message, HTTP status and duration.--recordsaves runs; failures save automatically. Read withmax runs list,max runs show. File uploads (--file) were not recorded until 0.18.0. - Separate
personalandbotsettings, each withdefaultsandprofiles.max config set --personal|--botwrites sections;max config show --botshows bot values and source keys such asconfig file: bot.profiles.test. More specific values win: section profile, profile, section defaults, globaldefaults. Old files retain behavior. See Configuration. - Optional bot hourly limits:
max <имя> config set --bot sendsPerHour 200. Bots remain unlimited by default. max config set defaultProfile <имя>chooses the implicit profile, previously alwaysdefault.- Profile photos, your own name for a contact, and blocking.
max account update --photo <файл>sets a new profile photo.max contacts rename <кто> <имя> [фамилия]gives a person a name only you see.max contacts block <кто>andunblockblock and unblock people, even those not in your contacts. What to consider: all use the same checks asaccount updateandcontacts add. In this version,contacts renamedid not actually change names — fixed in 0.18.0. - Channels:
max chats create <название> --channelcreates a private channel. Invite withmax chats link show; direct addition may be rejected by MAX. - Admin read and invite-link rights:
max chats admins add <чат> <кто> --can read,link. A bot withoutreadcannot read group messages. - Relative times for
--since,--before,--after:30m,2h,1d, as inmax review --since 1d, replacing the former exact-time requirement.
Fixed
- Your chat changes appear immediately. After
max chats update,chats settings,chats link reset,chats showandchats listpreviously showed old titles for minutes because MAX does not echo changes andmax serveignored the returned chat. It now applies it as it already did sent messages. max export messagesno longer warns about missing history before 1970-01-01 after a completebackup.- Errors in
--limitand--pagerepeat what you typed. Previously, an error for--limit abcreferred to the input asNaN. - Reset invite links in
chats inspectandchats joinreturn not found (not_found, code 6) instead of an opaque MAX opcode rejection. Update scripts expecting another code. max config showandmax doctoromit phantom<имя>.moderationprofiles, previously confused with moderation-rule files.- Subcommand errors name the unknown word rather than the profile. Previously,
max work bot auth statussaidworkwas read as a profile name, although the unknown word wasstatus. max config showdisplaystranscribeModel, previously omitted.
Removed
- Join requests:
max chats requests list|accept|decline,requests,consent.accept,consent.decline. MAX has public or invite-only groups without approval, so the commands promised nonexistent functionality. Old rule files remain readable; the next write removes obsolete fields. Calls tochats requestsreturn unknown-command errors.
0.16.0 — 27.09.2026
New
- Bot people and conversations:
max <имя> bot people show <кто>shows where someone posted and their direct chat;bot messages search --from <кто>finds posts by people;bot messages between <кто> <кто>finds chats where everyone posted. All data comes from this computer's seen messages;--all-botsreads all bot copies. - Bot group checks:
max <имя> bot chats check <чат>appliesbot chats rules show|set|unsetto messages and members, using joins saved bybot updates watch. Removed people cannot return through invites unless--no-banis used; Bot API cannot undo the ban. Account ages are unavailable, so those rules do not run. - Polls.
max messages listshows a poll as text: question, options with IDs in[скобках], votes and ✓ beside your choice.max polls vote <чат> <сообщение> <вариант>…votes,--retractretracts a vote,max polls closecloses your own poll, andmax polls createcreates one. MCP hasmax_polls_voteandmax_polls_create, only with--allow-send. What to consider:maxrejects anything the web client would reject — closed polls, too many options, or a second vote without permission to revote — without sending anything. web.max.ru does not display polls, andpolls createreminds you of this. max <имя> bot mcpconnects an agent to a bot, read-only by default in this release. Writes require--allow-send,--allow-delete,--allow-moderate, with--confirm-sendfor forms. Commands enforce recipients and logs; rule actions needing confirmation share one form. See Bot MCP.
Changed — may break scripts
- The
timeoutparameter ofmax bot api get-updatesnow uses--poll-timeout. Previously, the operation’s--timeoutnever reached MAX:--timeoutis the command’s overall deadline. What to consider: scripts passing--timeoutfor long polling must switch to--poll-timeout.
Fixed
- Automatically started
max serveis replaced on the first newer-version command, rather than rejecting new operations, such as voting, untilmax server stop. - A different build with the same version also replaces its server. A manually started server rejects unfamiliar operations with a
max server stophint. max bot api get-updates --limit …works. Previously, the operation’s--limitwas mistaken for amaxsetting and the command refused.
0.15.0 — 27.09.2026
New
max chats check <чат>checks messages and joins since the last run againstmax chats rules, then reports, deletes messages or removes members as allowed. Default is report-only;--dry-runonly plans, at most 10 actions per check. Deletion/removal uses normal safeguards. Join-request actions were only planned here, then removed in 0.17.0 because MAX has none. See Groups.- Agent moderation:
max mcp --allow-moderateexposesmax_chats_check;max_chats_events,max_chats_members,max_chats_rulesare always available read-only. Without the flag, checks are absent. Required approvals use one form. - Roles and invites:
max chats members listlabelsowner,admin,member;max chats link show <чат>shows invites. - Personal-account video and voice:
max messages send <чат> --file ролик.mp4sends in-chat video (.mp4 .mov .webm .mkv);max messages send <чат> --voice заметка.oggsends voice with waveform and duration. Use--as-filefor the old video-document behavior. Voice requires Ogg Opus; other formats receive anffmpegconversion hint. See Personal account guide. - Voice messages appear as text directly in the list.
max messages list <чат> --transcribeandmax inbox --transcribetranscribe the displayed voice messages on this computer; text appears under the message with a 🎤 icon, and in--jsonundertranscript. MCP usestranscribe: trueinmax_messages_listandmax_inbox. What to consider: previously transcribed messages show text even without the flag. Transcription requires a downloaded model. - More bot commands:
max <имя> bot messages send --file <путь>attaches images, video, audio or files;bot uploads putuploads only.bot members list|add|remove,bot admins list|add|removemanage membership;bot comments list|get|send|edit|deletehandles channel comments;bot callbacks answerhandles buttons;bot commands list|set|clearmanages menus;bot webhooks list|set|deletemanages webhooks. See Bots.webhooks setrejects another configured address because MAX delivers to both instead of replacing one. - Bot local storage: read, sent and received messages are saved.
max <имя> bot messages list <чат> --offlineandmessages get --offlineread without a network;bot messages search <текст>searches. Deletions performed by the bot or observed throughupdates watchremove local messages. Storage contains message text. max <имя> bot updates watchprints events until Ctrl-C and saves messages, resuming on the next run. It does not work with a webhook and consumes updates unavailable to other readers; use only when no other reader needs the bot.- Bot people:
max <имя> bot people show <кто>reports chats and latest direct messages;--refreshrefetches from MAX.bot messages search --from <кто>searches one author;bot messages between <кто> <кто> …finds shared conversations.--all-botssearches all copies; people accept ID,@usernameor name fragment.
Changed — may break scripts
max bot messages listprints older messages first, likemax messages list. Previously, new messages came first. Messages sent by the bot are now marked as its own. What to consider: scripts taking the first row as the newest message now get the oldest.
Fixed
max review --transcribecloses MAX before recognition: audio downloads first, then connection closure, then the model.max bot api edit-my-commands,subscribe,unsubscribe,get-upload-urlwork, rather than failing with “an account change without a known action”.- Bot sends to positive IDs without
user:suggestuser:<номер>, since the destination is probably a person. - Bot examples omit fabricated chat IDs and explain how to get real ones.
0.14.0 — 27.09.2026
New
max botuses the official Bot API.max bot auth setverifies and stores its token separately in the keyring. Profiles go first:max рабочий bot me.max bot meshows the bot;max bot api <operation>calls any of 33 operations with parameter flags and JSON bodies, generated from the official schema. IDs above 2^53 are strings; scripts must treat them accordingly.- Convenient bot commands.
max <имя> bot messages send <чат> <текст>sends to a chat by number, to a person asuser:<номер>, or by the title of a chat the bot has seen;edit,delete,listandgetare also available.max <имя> bot chats listshows chats the bot has seen, alongsidechats get|pin|unpin|leave|action.max bot listshows every name with a bot token. Why “has seen”: MAX has no bot chat list, somaxremembers chats itself. - Bot recipients and logs:
max <имя> bot recipients add|list|remove|off,max <имя> bot sends list. Every write, includingbot api, checks recipients. No hourly bot limit existed until 0.17.0. See Bots. - Group moderation: what is happening.
max review --unanswered [часы]shows group questions neither you nor admins have answered yet;max review --chat <чат>reviews one chat.max chats events <чат>shows who joined, left, was added or removed.max chats members list <чат>lists all group or channel members, with registration date and last seen.max chats rules show|set|unset <чат>manages group moderation rules in one file, likeconfig set.
Fixed
- MAX disconnections report the close code and reason.
0.13.0 — 26.09.2026
New
max reviewgathers commitments: all messages, including yours, in chats active since the prior review, or 3 days without--since.--transcribeprocesses audio; the response gives the next review boundary. Incomplete data is explicitly marked; do not treat it as complete (Review guide).- MCP
max_reviewand/revieworganize what you owe, await and need to clarify, checking work groups before declaring overdue items and drafting reminders. Reminders require approval (MCP prompts). max mcp configprints configuration for Claude Desktop, Cursor and other clients, with absolute paths for Windows and applications missing terminalPATH(Connection guide).max doctorchecks the installation: what runsmax, where it is installed, whether a new terminal will find it, whether the keyring and SQLite load, and whether a speech model is downloaded. What to consider: if the command reference is not onPATH,doctorprints a command to fix it — for PowerShell on Windows andexporton Linux and macOS. Ifmaxitself is not found, runnpx @wirecat/max-cli doctor(troubleshooting.md).max doctor --onlinechecks MAX connectivity: one login, one chat and MCP startup, without sending.max models audio downloadchecks the model after download. Missing-model errors explain its language and alternative models with sizes.
Changed — may break scripts
- MCP
max_messages_attachmentbecomesmax_messages_photo. Regrant client permission under the new name if previously saved. - Profiles cannot be named
review, now a command; rename existing profiles with that name.
Security
- Windows reports hide every spelling of the home path, where some usernames previously remained visible.
0.12.0 — 26.09.2026
New
- More MCP tools:
max_inboxfor updates in one call, replies and formatting, reactions, and photos visible directly to agents (Tools). - Claude Code
/catch-up,/reply,/findand chats through@(MCP prompts).
Fixed
max serveworks on Windows, using a named pipe instead of a file.- Long socket paths on macOS and Linux produce clear errors, instead of
EINVAL; long profile names orMAX_STATE_DIRcan cause this.
0.11.0 — 26.09.2026
New
max watch --eventsincludes edits, deletions and reactions, with aneventfield. Without the flag, output is unchanged (Live updates).- Problem reports go to GitHub rather than email.
max doctor report createprints a prepared issue link; attach its report file. Issues and attachments are public (Reporting problems). - Every failed command gets a run record, including invalid flags, preflight checks and non-network commands (
models,server,watch), previously only failures reaching MAX. Only command words are recorded, not arguments or message text (Diagnostics). max backup messages --runexplains storage and export. Messages are in local storage;max export messagescreates a file. Its ready-made command appears at the end and inexport.- Background
max serveenforces read-only, actions, recipients and hourly limits and logs sends.config settakes effect without restart. It does not start withMAX_TOKEN. - After login,
max serverequests the same data as a web.max.ru tab: folders, banners, call history, sticker sets and reactions. It also logs in again the same way: it sends MAX the previous login time and asks only for changed chats, rather than the whole list. Why: the lessmaxdiffers from the web client, the fewer reasons MAX has to notice it. What to consider: all of this is read-only; responses are neither displayed nor saved. One-off commands do not do this (security.md). - The background server survives a malformed incoming MAX message: it skips the message, writes one line about it and keeps running. Previously, such a message could stop the server.
Changed — may break scripts
-
Stronger agent safeguards:
max mcp --confirm-sendconfirms every write, including edits, forwards, pins, read receipts and deletion. Approval works once for 5 minutes.sendsPerHourincludes edits, notified pins and each added person. Scheduled messages count in their send hour. Simultaneous sends can no longer both pass the last available slot.- Group creation and additions with a recipient list require every person's direct chat on that list.
chats members addhides older history unless--history;--hide-historyis removed.MAX_PROFILE_LOCKfixes the profile.--fileprotects hidden files/directories andmaxdirectories unless--allow-any-file.
Hourly limits may be reached sooner. Remove
--hide-historyfrom scripts; intentional hidden-file sends need--allow-any-file.
Fixed
max watchno longer labels edits or deletions as new messages, despite MAX returning them in message-shaped events.- Exact titles no longer silently win over other partial matches. Both candidates are shown for ID selection, preventing irreversible wrong sends.
Security
- A token from
MAX_TOKENstays only there. If MAX issues a new session token,maxwrites it neither to the keyring nor to a file, and reports this in stderr.max doctornamescredentials.jsonif that file stores the token instead of the keyring. max session startmasks phone numbers, likemax account show. Ctrl-C at the token prompt returns130.- The background server does not give the token to commands asking it for login information: they do not need it and consult the keyring instead.
- Network limits: decompressed MAX frames are capped at 32 MiB. Connections and downloads have timeouts.
max messages downloadrequires HTTPS, rejects local-machine/network URLs even after redirects, and caps files at 4 GiB and transcription audio at 32 MiB. Message links are untrusted. - Local storage permissions: database,
-wal,-shmfiles use0600; directories0700. Existing permissions are corrected on opening. Reports replace chat/message IDs with labels. - Untrusted text uses one line with visible controls in feeds, tables, candidates, Markdown and
messages downloadpaths. Filenames lose control and text-direction characters; onlyhttpandhttpsbecome Markdown links. - Completion inserts only IDs, displaying names beside them because titles and
@имяcome from other people and must not become shell code. max cache clearwithout a profile respects the default andMAX_PROFILE.- Releases are stricter. Dependency versions are pinned exactly; the package is built from scratch before each packaging step, without test helpers; publishing is done in a separate step that neither installs nor runs dependencies.
0.10.0 — 25.09.2026
New
max doctor reportandmax doctor report createexplain report contents or create a content-free file with next steps. This release used email; 0.11.0 moved to GitHub (Reporting problems).max backup messages <чат> --since <дата> | --last <n>downloads more chat history into the local copy. What to consider: without--run, the command only shows an estimate and sends nothing. With--run, it pages backwards through 30 messages at a time with pauses, up to 40 pages per run, and resumes from the same position on the next run (usage.md).max doctorshows which MAX web-client versionmaxidentifies as, and warns if that version was read more than 60 days ago. Why: MAX may stop accepting an old client version (troubleshooting.md).max server start|stop|status|restartmanages the background server as a separate component, likemax session.statusshows whether the server runs, since when, its version and whether it is connected to MAX; it suggestsrestartwhen the server’s version is older thanmax.max serve --detachand--stopstill work (usage.md).- History reads send the same five fields as the web client, and login requests 15 chats from MAX, like a web.max.ru tab, then retrieves the rest in one request. Previously,
maxadded a field the web client does not send and requested 40 chats at a time. Why: the lessmaxdiffers from the web client, the fewer reasons MAX has to notice it. What to consider: the chat list is unchanged. Checked on a channel with unread messages: reading still marks nothing as read. - The device description comes from your computer: time zone, system language and operating system are specific to each installation, as in a browser. Previously, every
maxinstallation identified as the same Chrome on Linux in the Madrid time zone. max servesends one hidden-tab-style service event 20 seconds after login: chat list shown, with account ID and time, no content or titles. One-off commands do not send it (Network behavior).maxrejects overly long folder titles itself — no more than 20 characters, the limit MAX accepts. Previously, the request went to MAX and came back rejected.
Changed — may break scripts
- Excessive-login rejections no longer trigger more attempts. Code
8pauses a profile for 1 minute, 5 minutes, 30 minutes, 1 hour, 6 hours, then 1 day. The background server stops on any login rejection, previously retrying indefinitely each minute. Scripts receive code8until the stated time; wait (Troubleshooting).
Fixed
- An unavailable keyring is no longer mistaken for being logged out. If a profile has logged in on this computer but its token is not visible — for example, from cron —
maxandmax doctorsay the keyring is probably the cause. Previously they suggested logging in again. Why it matters: a new login in this case adds an unnecessary new device to the account (recipes.md). - Failed runs save without
--record, including MAX key (login.token), warning codes, crash location, runtime version and OS, never text. Background logs use timestamped JSON lines (Diagnostics). max chats read --untilmarks only through its message, rather than using current time and marking newer messages read.messages list --mark-readis fixed too; others may previously have seen receipts for unread messages.
0.9.0 — 25.09.2026
New
maxtalks to MAX like the web client: the same address, binary frames and compression as web.max.ru, and the same device description with updated app and browser versions. Previously,maxsent text frames in an old format. Why: the old format mademaxeasiest to distinguish from the web client. Also, voice and round video messages need a byte field the old format could not send. What to consider: commands and output are unchanged. Sending voice messages is planned for later versions. For now, MAX sends the entire chat list at each login rather than only changes: this works but adds traffic.- Automatically started
max serverestarts after updatingmax. Manually started servers remain old untilmax serve --stopand a restart.
0.8.0 — 25.09.2026
New
max messages transcribe <чат> <id>recognizes voice locally without uploading it.max models audio listshows language support;max models audio download <id>downloads and checksum-verifies. MCP:max_messages_transcribe(Voice transcription). Download is explicit and one-time; saved transcripts avoid both network and model on repeats.- One MAX connection per profile, shared by commands,
max mcp,max watchthroughmax serve, reducing logins and possible session termination.max session startstops, logs in and restarts it (Server guide). max serve --detachstarts in the background and returns once connected;max serve --stopstops it. Manual servers stop only with Ctrl-C or--stop;max session endleaves them running.- The
allowsetting defines what a profile can do.max work config set allow send,reactionlets the profile only send messages and react. There are twelve names, fromsendtosessions. What to consider: without a list, everything is allowed, as before. Forbidden actions fail with code5before connecting, and the error names a command to permit them. Inmax mcp, the agent does not see tools the profile does not permit (usage.md). max messages send … --at <время>schedules on MAX's server, even with the computer off. Accepts2026-09-25T09:00locally or30m,2h,1d.max messages scheduled <чат>lists the queue; MCP usesatinmax_messages_sendandmax_messages_scheduled. Cancellation is app-only (Scheduled sends).max chats read <чат>andmax messages list … --mark-readsend explicit visible read receipts. MCP needsmax mcp --allow-mark-read; normal reads remain invisible (Reading).max export messages <чат> --format jsonl|mdexports a conversation from the local copy to JSONL or Markdown, with--sinceand--output. It does not contact MAX. What to consider: the command reports missing local data in stderr. The file from--outputis accessible only to you (usage.md).max messages delete <чат> <id…> --allow-dangerousdeletes messages, up to 10 at a time. By default, only for you; with--for-everyone, for everyone in the chat. MCP usesmax mcp --allow-delete, only “for me”. What to consider: without--allow-dangerous, the command refuses. Each deleted message counts towardssendsPerHour(usage.md).
Fixed
- Updating
maxno longer erases history you have read. Previously, every new version changing the local-copy structure discarded all saved messages. Messages now migrate into the new copy. What to consider: this release itself changes the copy’s structure, and history is retained. Chats and people are fetched again on the next login, as before. - After server login rejection, commands wait 10 minutes before starting another server, rather than repeatedly triggering rejected logins.
max session startclears the wait. max watchsees messages sent bymaxitself, previously missing because MAX does not echo to the sending connection.- Simultaneous
maxcommands no longer lose login data in the local copy. Previously, two out of three simultaneous commands reported “the local record did not take this login” and failed to save chats, members and the sync marker. The second now waits for the first to finish writing.
Security
- Error text cannot control the terminal. Controls display as
\x1b, extending 0.7.0's protections because errors may quote user input or MAX responses.
0.7.0 — 24.09.2026
New
max reactions remove <чат> <id>removes your reaction.- Groups and channels under
max chats: view the link, join, leave, create a group, add and remove people, assign and remove an admin, rename, change settings, re-release the link. There were also applications for membership here - they were removed in 0.17.0, because they are not in MAX. What to consider: all this is seen by other people, and each action goes through the same checks as sending (groups and channels). max updateupdatesmaxwith the same package manager it was supplied with;--checkonly tells if there is a newer version. What to consider: once a day a person sees a line in the terminal about a new version; agent and script - never. Turns offupdateCheck: falsetodefaults(update).- Addition for Tab in zsh, bash, fish and PowerShell:
source <(max complete zsh). Offers commands, flags, their meanings, as well as chats and people from a local copy - without connecting to MAX (help formax complete). max mcp- the same profile for agents via MCP, for clients without a terminal (Claude Desktop, Cursor). Connection - MCP server. Things to consider: the server only reads until it is started with--allow-send; the shipment undergoes the same checks asmax messages send.max mcp --allow-send --confirm-sendshows the form before each submission: to which chat (name and id) and what. What to consider: nothing goes away without your “yes”; a client that cannot display forms receives an error (what can an agent do).max messages send … --file <путь>sends photos and files; several photos are sent in one message.
Security
- Other people’s text no longer controls the terminal. A message, sender name, chat title, filename or reaction containing control characters could erase a line and print over existing
maxoutput. These characters are now displayed as\x1bin feeds, tables, errors and Tab suggestions. What to consider: JSON is unchanged — it already escaped them.
0.6.0 — 24.09.2026
New
max commands --jsondescribes all commands, arguments, flags and exit codes in one response, withmutates: truefor MAX changes. Agents avoid per-command--help; it works without login and with broken configuration.max messages send … --reply-to <id>replies to a message.max messages send … --markdown(or--md) formats**жирный**,_курсив_,~~зачёркнутый~~and`код`. Without a flag, text stays literal.max reactions add <чат> <id> <эмодзи>sets a reaction, replacing yours.- Reactions are visible while reading:
messages list,showandcontextprint👍 3 🔥 1 (you: 🔥)under a message; JSON has areactionsfield. What to consider: this adds one read-only request per page. With--offline, reactions are absent (null) because they are not stored. - Send logs and optional recipients:
max sends listlogs attempts without content;max recipients add|remove|list|offrestricts chats, rejecting code7.readOnlyrejects5. See Security for scope and limitations. max session start qr | qr-chrome | sms | tokenlogs in without copying browser tokens.qrrenders in the terminal, or browser if narrow;qr-chromeandsmsopen web.max.ru in separate Chrome, Chromium, Edge or Brave windows. Without a method, import manually or by pipe as before.
Changed — may break scripts
- Sending has an hourly limit: 30 messages by default (
sendsPerHour). Above this limit,max messages sendfails with code8. Previously there was no limit. What to consider: scripts sending more must raisesendsPerHourin settings.
0.5.0 — 24.09.2026
New
max messages download <чат> <id> [--output <каталог>]saves photos, files, video and audio without overwriting existing files.max config set <настройка> <значение>andmax config unset <настройка>edit configuration, with--defaultsfor all profiles. Globaldefaultsapply where a profile has no override.max chats list --unreadfilters unread chats.max messages list <чат> --after <id|время>reads forwards after a message or time, with a--after <id самого нового>continuation hint.max chats show <чат>shows a chat/members;max contacts show <человек>accepts ID, @username or name fragment and shows shared chats. Ambiguity lists candidates instead of guessing.- New read operations in this release neither send nor mark read.
Fixed
--offlineworks. Previously, no command received the flag: reads still contacted MAX, andmax --offline messages sendsent a message. Reads now use saved data, while sending and downloading refuse with--offline. What to consider: if you ran--offline messages sendon 0.4.0 or earlier, the message was sent.- Settings-file errors are explained plainly: which setting is unknown, which settings exist and what values are accepted. Previously, they were validation-library messages.
- Run-log failures (
--record) no longer crash commands. A stderr warning, even with--quiet, leaves the normal result and exit code intact.
Security
- GitHub Actions publishes with npm provenance, allowing verification that the package was built from this repository.
0.4.0 — 23.09.2026
New
max messages show <чат> <id>reads one message;max messages context <чат> <id>uses--before,--afterfor context, marking◀or JSON"anchor": true. Missing messages return not found instead of neighbors.max skill showprints installed agent instructions:max skill show > ~/.claude/skills/max-cli/SKILL.md.max config showreports effective profile and source, configuration path/existence, all profiles including state-only ones, and every setting's flag/environment/file/default source.MAX_CONFIG_DIRand related overrides warn about alternate keyring entries.- Piped text:
echo "текст" | max messages send <чат>reads stdin when no text argument is supplied, avoidingps/history exposure and supporting newlines. --timeout <срок>limits the whole connection/login/request sequence, not a single response.max doctorreports token source without its value, login count/time, logged-in profiles, supported/cache schemas and keyring entry without contacting MAX. It works during failures; missing sessions are data, not errors.
Changed — may break scripts
- The
--queryflag for lists is renamed to--search. This change was already included in 0.3.0 but was missing from its release notes. What to consider: scripts using--queryget an error — replace it with--search.
Fixed
messages list --before <id>derives time from the ID without requiring an earlier read.- Group members use names instead of IDs, fetched once and saved, including reply/forward authors; previously only contacts had names.
- Releases finish tagging after publication, fixing two failures by bypassing npm cache and waiting up to three minutes.
0.3.0 — 22.09.2026
New
- Conversation feeds: day separators,
время авторand aligned, terminal-width text.выmeans your messages, unnamed authors use IDs.↳and↪show replies/forwards received in full and saved locally. -v,-vvadd message, sender, chat IDs and attachment URLs, then all known fields.--jsonlprovides one JSON object per line for streaming andjq.- Attachment links:
📎 photo,📎 photo ×3 1 2 3,📎 файл.pdf · 24 MB; JSON includesurl,width,height,title. Photo URLs open without login, so recipients can access them. senderColors: truegives each author a color; off by default.
Changed — may break scripts
-vnow means output verbosity; the version ismax -V.--traceenables request lines in stderr — this was previously--verbose. What to consider: scripts usingmax -vfor the version or--verbosefor tracing must switch to-Vand--trace.- List
--querybecomes--search, originally omitted from these notes. - The local copy moves to schema 4 and is rebuilt on first run. What to consider: history read in this version is not retained — you must read it again.
Fixed
- Ambiguous chat names return candidates with IDs, including JSON
candidates. - Cache warnings name the schema and next steps, rather than
Error. messages listcontinuation hints use--before <id>, not nonexistent--page.
0.2.0 — 22.09.2026
New
max messages send --silentrequests sends without notifications. Its actual effect was not observed in this release because doing so required messaging a real person.- The token is exchanged on first login. MAX responds to login with its own token, and
maxstores it in the keyring instead of the one pasted from the browser. This happens once.
Fixed
max session startchecks before saving, preventing typos from replacing valid tokens.- Profiles stay tied to their account. A different account's token is rejected with an explanation rather than running commands as someone else.
- Unknown-send-outcome hints name a real command, not nonexistent
max send. - Login messages are retained, previously discarded due to an incorrectly described response shape.
0.1.0 — 21.09.2026
The first shareable version.
New
- Seven commands against real MAX:
session start|end,account show,chats list,contacts list,messages list,messages send. - Profile - first word:
max personal chats list. Several accounts live nearby, each with its own token, its own state and its own local copy.MAX_PROFILEsets the same. - The token is stored in the operating system keychain, and not in a file or in the command argument. What to consider: you don’t have your own login by phone number yet -
max session starttakes a token from the official client. - Machine mode:
--jsonputs exactly one JSON value and nothing else on stdout; the same thing turns on itself when stdout is not a terminal. The error goes to stderr, stdout remains empty. You can branch by exit code - table in command reference. - Diagnostics without content:
--verboseshows a line per request,--recordputs them in the run directory for 30 days,max runs list|show|pathreads them back. By default, nothing is written. - Local copy: what you read is saved nearby;
--offlineanswers from it without connecting, andmax cache clearforgets it. - Settings in
~/.config/max-cli/config.json, with the order “flag → environment variable → file → built-in value”. A typo in a field name is an error with the field name, not a silent omission. - Two runtimes: Node 22+ and Bun 1.3+; the assembled command is executed under both in CI.
- Reading does not mark anything as read. “Get history” and “mark as read” are different protocol operations; the second is never sent, and this is checked by the test.
- Sending does not lie about the outcome. If the response did not arrive -
outcome_unknown(code14), and not “error” and not “sent”. What to consider: you can repeat such a sending only with the same--cid, otherwise the message may be sent twice. - The MAX protocol is unofficial and reverse engineered: it is not a Bot API. Things to consider: It may change without notice; then command will say this in one line to stderr, rather than crash silently.
- Not yet able to: log in using a phone number, work with attachments, reactions, edits, groups, stories and calls - text only. There will be no mass mailing: this is a tool for a personal account.