Houston v0.4.26

Houston 0.4.26

Models

• Claude Sonnet 5 runs with a full 1M context window. That is a full million
  tokens of context on every message, so long missions hold much more of their
  history.
• Fable 5 is in the model picker. Pick it per agent or per mission.

Now in your language

• The new-agent store speaks Spanish and Portuguese. The built-in agents and
  the model picker inside the store now follow your app language, so the whole
  store reads in Spanish or Portuguese.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a
  running app cleanly. If in doubt, remove /Applications/Houston.app and drag
  the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward
  automatically. The MSI is still not OS-code-signed, so Windows SmartScreen may
  warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install.
  Download the ARM64 MSI manually, uninstall the x64 build first, then install
  the ARM64 one.

Houston v0.4.25

Houston 0.4.25

New models

• Claude Sonnet 5. Anthropic's newest Sonnet is now in the chat model
  picker. It brings stronger agentic coding and tool use. Pick it per agent or
  per mission.
• More OpenAI Codex models. The Codex picker now lists three more models so
  you can match the model to the job:
  • GPT-5.4, a strong model for everyday coding.
  • GPT-5.4-Mini, small, fast, and cost-efficient for simpler tasks.
  • GPT-5.3-Codex-Spark, an ultra-fast coding model.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a
  running app cleanly. If in doubt, remove /Applications/Houston.app and drag
  the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward
  automatically. The MSI is still not OS-code-signed, so Windows SmartScreen may
  warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install.
  Download the ARM64 MSI manually, uninstall the x64 build first, then install
  the ARM64 one.

Houston v0.4.24

Houston 0.4.24

Added

• Easier routine scheduling. Weekly schedules are now a simple multi-day
  preset, and the schedule form uses a friendly clock picker instead of making
  you type time values by hand.
• Clearer context in chat. The context indicator is now a quieter hover ring,
  so you can see the signal when you need it without adding more noise to the
  chat screen.
• Sign in without leaving Houston. You can now sign in right inside the app
  with Google, a one-time email code, or your Microsoft account, instead of
  bouncing out to a browser to finish.
• Agent Settings in one place. The agent's settings tab now has a Settings
  section where you can rename an agent and reach its card actions, instead of
  hunting through a menu.
• Find a timezone by typing. The routines timezone control is now a
  searchable picker. Type a city or region instead of scrolling a long list.

Improved

• Less visual noise while Houston works. The blinking loading helmet is gone,
  mission logs start collapsed, and Houston surfaces only the live action unless
  you want more detail.
• More consistent cards. Chat, integration, and context cards now share the
  same shape and behavior, so actions feel more predictable across the app.
• Simpler effort control. The effort button now cycles through levels with an
  icon that matches the selected level.
• One timezone for routines. Routine schedules now use one account-wide
  timezone instead of per-routine overrides, which makes scheduled behavior
  easier to reason about.
• Houston opens ready to go. Once your agents finish loading, Houston selects
  one for you instead of leaving the screen empty.

Fixed

• Claude session limits are labeled correctly. If Claude hits its 5-hour
  session limit, Houston now shows a session-limit card instead of a misleading
  rate-limit message.
• OpenAI Codex usage limits are labeled correctly. When Codex runs out of its
  usage allowance, Houston now shows a clear quota card, including when it resets,
  instead of a generic error.
• Routines no longer disappear. A single routine with an unusual character
  used to make the whole list fail to load. Houston now recovers your routines and
  keeps them instead of clearing the list.
• Houston opens reliably after relaunching. A startup hang could leave Houston
  running with no window. The main window now appears normally.
• The model picker only lists models you can use. A model that was not
  available to select no longer appears in the chat model picker.
• App connections update immediately. When a connected app is already linked,
  Houston now flips Connect to connected instead of leaving the screen stale.
• Chat errors stay where they happened. An error no longer jumps to the bottom
  of the conversation and separates itself from the message it belongs to.
• Skill detail loading is clearer. Skill cards disable and show progress while
  their detail view is loading.
• Routines fire on time after your Mac sleeps. Scheduled routines could run
  late or be skipped if your Mac slept, overnight or with the lid closed. They
  now keep accurate time and catch up as soon as your Mac wakes.
• Fewer false errors from Codex. Brief reconnect blips while OpenAI Codex is
  working no longer flash up as errors.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a
  running app cleanly. If in doubt, remove /Applications/Houston.app and drag
  the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward
  automatically. The MSI is still not OS-code-signed, so Windows SmartScreen may
  warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install.
  Download the ARM64 MSI manually, uninstall the x64 build first, then install
  the ARM64 one.

Houston v0.4.23

Houston 0.4.23

A reliability release. Connecting apps no longer hangs, skills keep working
after they move or get renamed, and a few things that used to break now
recover on their own. Plus a quick way to act on a whole board column at once.
Drop-in on top of 0.4.22, no breaking changes.

Added

• Act on a whole column at once. Each board column header now has a menu
  with "Select all in column," so you can move or update every card in a stage
  without clicking them one by one.

Fixed

• Connecting an app no longer hangs. Signing in to a connected app could
  stall for over five minutes with no sign of life. It now finishes quickly or
  tells you clearly what to do, instead of freezing.
• More connection links just work. Some apps hand back a plain web address
  when you connect them. Houston now accepts that and carries on.
• Adding a skill from a pasted command or link. Paste a full command or a
  web address and Houston works out the right skill to add, and clearly refuses
  genuine nonsense instead of failing in a confusing way.
• Renamed or moved skills keep working. A skill that was renamed or moved
  used to quietly disappear. Houston now finds it by its folder, so it keeps
  showing up.
• A damaged scheduled-tasks list repairs itself. One bad entry used to break
  your whole list of scheduled tasks. Houston now fixes it and keeps the rest.
• A brief hiccup no longer drops your chat. A momentary blip between Houston
  and its engine could show "Load failed." It now retries quietly and recovers.
• Steadier first-run setup. Creating your default workspace on first launch
  is now safe to retry, so a hiccup during setup can't leave you stuck or
  duplicated.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a
  running app cleanly. If in doubt, remove /Applications/Houston.app and drag
  the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward
  automatically. The MSI is still not OS-code-signed, so Windows SmartScreen may
  warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install.
  Download the ARM64 MSI manually, uninstall the x64 build first, then install
  the ARM64 one.

Houston v0.4.22

Houston 0.4.22

A release about choice and recovery. Switch the AI behind a chat without starting over, give each scheduled task its own brain, and get clearer prompts when a provider needs you to reconnect. Drop-in on top of 0.4.21, no breaking changes.

Added

• Switch the AI mid-conversation. You can move a live chat to a different AI provider at any time without losing the thread. Houston carries your conversation over to the new provider: the full history when it fits, or a short summary (with your go-ahead) when it does not. Handy when one provider runs out of credit, or you just want a second opinion partway through.
• Each scheduled task can pick its own AI. Routines can now choose their own provider, model, and effort level instead of always inheriting the agent's default. Pin a faster, cheaper model for a routine check-in, or a higher-effort one for the heavy weekly job. Leave it untouched and it keeps following the agent.

Fixed

• Houston picks the AI you actually use. Agents with no provider set used to fall back to Claude, which failed if you only use OpenAI. Houston now falls back to your last-used or only connected provider, so agents from the Store, scheduled tasks, and quick sends all start on the right AI.
• A clear reconnect prompt for OpenAI. When OpenAI ends your login session on their side, the chat showed a red border but no way to fix it, and any hint vanished on reload. Now you get the same inline reconnect button Claude already had, and it sticks around until you reconnect.
• Clearer messages when Claude is rate-limited. A Claude "too many requests" response used to show up as an unknown error with a "Report bug" button, sometimes doubled. It now reads correctly as a temporary rate limit, shown just once.
• Your own message shows in the mission card. Starting a task from a skill used to show a raw behind-the-scenes marker instead of what you wrote. The mission card now shows your message.
• Tool steps no longer take over the chat. A long list of an agent's tool steps could expand and crowd out the conversation. That panel is now capped, so the chat stays readable.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending), so Windows SmartScreen may warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.

Houston v0.4.21

Houston 0.4.21

A reliability release. A more reliable Stop button, installed skills show up, and a few provider papercuts are gone. Drop-in on top of 0.4.20, no breaking changes.

Changed

• Latest Claude Code under the hood. Houston now bundles the newest version of Claude Code that powers your Claude agents, so they run on Anthropic's most recent fixes and improvements.

Fixed

• More reliable Stop button. The Stop button already worked, but in some cases an agent could keep going in the background, especially when it had started subagents or other helper tasks. Stop now reliably halts the agent and everything it started, even mid-thought or right after you send a message. While an agent is working, the send button also shows a clear stop icon, so you always know how to halt it.
• Agents with a lot of context start again on Windows. A busy agent that had built up a large amount of memory and notes could fail to start on Windows. That is fixed, so even your most-used agents launch normally.
• Installed skills show up. A skill you install now appears for your agent right away and stays in sync if the agent later updates it. This was most noticeable on Windows, where installed skills could stay hidden.
• The Connect prompt only shows where it belongs. A "Connect Claude" button used to appear in chats that do not use Claude, like an OpenAI chat, and stick around. Now a reconnect prompt only ever shows for the provider that chat actually uses.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending), so Windows SmartScreen may warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.

Houston v0.4.20

Houston 0.4.20

Claude Fable 5, Anthropic's most capable model, is now a pick for your agents. Plus a simpler way to set custom routine schedules and a couple of chat fixes. Drop-in on top of 0.4.19, no breaking changes.

Added

• Claude Fable 5. Fable 5 is Anthropic's most capable model, and you can now choose it for any agent from the model picker. It is the strongest option for hard, multi-step work. One thing to know about cost: Fable 5 uses about twice the credits of Opus 4.8 per run, so reach for it when a task really calls for it and keep Opus 4.8 or Sonnet 4.6 for everyday work.
• Simpler custom routine schedules. Setting a custom schedule is now a plain "Repeat every N minutes, hours, days, weeks, or months" picker instead of anything cron-shaped. Choose weeks and you get a day-of-week selector with Every day, Weekdays, and Weekends shortcuts. Choose months and you pick the day of the month. The plain-language summary updates as you go, so you always see exactly when the routine will run.
• Routines now speak Spanish and Portuguese. The Routines tab, the schedule builder, run history, and the plain-language schedule summaries are all translated, so routines read in your language from end to end.

Changed

• Clearer model descriptions. Every Claude model in the picker now has a refreshed one-line description, so the trade-off between speed, capability, and cost reads at a glance.

Fixed

• Links in chat are clickable. A plain web address an agent writes in chat now opens in your browser with a single click, no copy and paste.
• Codex no longer interrupts during a web search. Fixed an error that could break a Codex chat while it was searching the web.
• No more flashing Claude sign-in dialog on desktop. A sign-in dialog meant for the web and mobile apps used to flash on screen and dismiss itself when you connected Claude on desktop. It no longer appears there.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending), so Windows SmartScreen may warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.

Known limitations

• Fable 5 costs more credits. It uses roughly twice the credits of Opus 4.8 per run. The model picker flags this, but it is worth knowing before you switch every agent over.

Houston v0.4.19

Houston 0.4.19

More control over how your routines use chats, update notes in your own language, and a reliability pass so Houston opens cleanly and the right things take you to the right place.

Added

• Choose how each routine uses chats. When you set up a routine, pick whether every run keeps going in one ongoing chat or starts a fresh chat each time, so the history matches how you think about that task.
• Update notes in your language. The "update available" card now shows what is new in English, Spanish, or Portuguese, matching the language you use Houston in.

Changed

• Mission Control matches your boards exactly. Mission Control now uses the same cards and behavior as each agent's board, so what you see lines up everywhere.

Fixed

• Houston opens even when a workspace is slow to load. The app no longer gets stuck on a blank window at startup if one workspace takes a while to respond.
• Routine notifications take you to the right chat. Clicking a routine's "finished" notification now opens that routine's chat instead of a generic view.
• Smoother mission dragging. Dragging mission cards now shows the same cursor on every system and no longer underlines the card title mid-drag.
• Clearer "connect" prompt. The "Waiting for you to connect" note for an integration now appears at the end of the agent's message, where you are already looking.
• Problem reports catch more (behind the scenes). Some errors from Houston's screen were being dropped before they reached us. They now get reported so we can fix them faster. Nothing for you to do.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending), so Windows SmartScreen may warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.

Houston v0.4.18

Houston 0.4.18

New ways to organize your missions, clearer scheduling and integrations, and a reliability pass so problems actually get reported when something goes wrong.

Added

• Drag and drop missions between columns. Rearrange mission cards across your board columns by dragging them, so the board matches how you actually work.
• Friendlier schedule picker. Setting a custom schedule for a routine now uses a simple interval picker instead of raw cron-style entry.
• Search highlights in archived missions. When you search archived missions, the matching words are now highlighted so the result is easy to spot.

Changed

• Clearer integration cards. An integration that still needs you to sign in now says "Waiting for you to connect," so the next step is obvious.
• Formatted update notes. The "update available" dialog now renders these release notes with proper formatting instead of raw text.
• Clearer problem reports. When Houston hits an error, the follow-up message now says "report sent" with a short reference code. Tap Copy to grab it and send it our way so we can pin down exactly what happened.

Fixed

• Routines run on the day you picked. A weekly routine now fires on the correct day of the week instead of being off by a day.
• Mission Control matches your boards. The chats and missions shown in Mission Control now line up with what is on each agent's board.
• Routine editor stays correct when you switch agents. Opening the routine editor after switching agents no longer shows leftover settings from the previous agent.
• Archived mission search lines up. The archived-mission search now sits and behaves consistently with the rest of the board.
• Problem reports carry the real details (behind the scenes). We fixed our build pipeline so crash reports point at the actual place a problem happened instead of unreadable scrambled code, and so problems in Houston's background engine get reported too. Nothing for you to do.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending), so Windows SmartScreen may warn on a fresh install.
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.

Houston v0.4.17

Houston 0.4.17

Long conversations now keep themselves tidy on their own, your language choice sticks per workspace, and you can search inside archived missions, plus a few routine and connection fixes.

Added

• Conversations that keep going. When a chat gets close to full, Houston now compacts it automatically so the conversation can continue without losing the thread or making you start over.
• Your language stays put. The interface language you pick is now remembered for each workspace, so it stays the way you set it next time you open Houston.
• Search your archived missions. The Archived tab now has a search box, so you can quickly find a finished mission instead of scrolling.

Fixed

• One ongoing chat per routine. A scheduled routine now keeps a single conversation across its runs, instead of starting a brand new chat every time it runs.
• Custom schedules are kept. Editing a routine no longer resets a custom schedule back to Daily.
• Connected apps show the right state. A connected app like Gmail or Slack no longer gets stuck saying "Connecting." The live status and the reconnect button now work independently.

Before you upgrade

• Mac: quit Houston before installing. macOS does not always replace a running app cleanly. If in doubt, remove /Applications/Houston.app and drag the new copy in.
• Windows x64: auto-update from 0.4.7 or later pulls you forward automatically. The MSI is still not OS-code-signed (SignPath integration still pending).
• Windows ARM64: there is no auto-update path from an emulated x64 install. Download the ARM64 MSI manually, uninstall the x64 build first, then install the ARM64 one.