Auto now chooses from the whole model catalogue
Auto mode used to pick from a short, hand-kept list of about fifteen models, so most of the catalogue never got a turn and new models had to be added by hand before Auto would use them. It now considers every chat model Portail offers. For each message it still decides how demanding the request is: small talk, an everyday question, a real question that has to be right, code, or hard multi-step work. Then it scores every model that fits. The score weighs the model's size class, whether it is the newest release in its own family, how well its price suits the job, whether it reasons, and who makes it. Quick questions go to small, fast models, code goes to code-capable ones, and hard problems go to the strongest models your plan includes. Older generations lose to their successors, so a newly released model starts winning the moment it appears in the catalogue. Auto still respects your plan, so Free and Pro are never routed to a flagship model. Images only go to models that can see them, and long conversations only go to models with enough room to hold them. The most expensive reasoning models stay manual-only, because Auto spends your credits without asking. You can still pick any model yourself from the picker, and the Auto badge still shows which one answered.
635 words
Auto weighs every chat model in the catalogue, not a short fixed list.
Newly added models can be chosen by Auto right away, without a manual update.
Quick questions go to small fast models, code to code-capable ones, hard problems to the strongest your plan includes.
Older generations lose to newer releases from the same family.
Free and Pro are still never routed to flagship models, and the priciest reasoning models stay manual-only.
Portail v2.7.3 shipped on 2026-10-23 as a patch release focused on auto now chooses from the whole model catalogue. Auto mode used to pick from a short, hand-kept list of about fifteen models, so most of the catalogue never got a turn and new models had to be added by hand before Auto would use them. It now considers every chat model Portail offers. For each message it still decides how demanding the request is: small talk, an everyday question, a real question that has to be right, code, or hard multi-step work. Then it scores every model that fits. The score weighs the model's size class, whether it is the newest release in its own family, how well its price suits the job, whether it reasons, and who makes it. Quick questions go to small, fast models, code goes to code-capable ones, and hard problems go to the strongest models your plan includes. Older generations lose to their successors, so a newly released model starts winning the moment it appears in the catalogue. Auto still respects your plan, so Free and Pro are never routed to a flagship model. Images only go to models that can see them, and long conversations only go to models with enough room to hold them. The most expensive reasoning models stay manual-only, because Auto spends your credits without asking. You can still pick any model yourself from the picker, and the Auto badge still shows which one answered. The work is recorded here because small releases are still product history. They change how people sign in, read responses, pay for access, share conversations, open files, or trust the system when something goes wrong.
The main changes were direct: auto weighs every chat model in the catalogue, not a short fixed list, newly added models can be chosen by auto right away, without a manual update, quick questions go to small fast models, code to code-capable ones, hard problems to the strongest your plan includes, older generations lose to newer releases from the same family, and free and pro are still never routed to flagship models, and the priciest reasoning models stay manual-only. That list is intentionally plain. It names what changed without turning the release into theatre. When a release fixes a build, a redirect, a storage path, or a UI edge case, the value is often that users stop noticing the problem. The archive keeps that invisible work visible enough for future debugging and for anyone checking whether Portail has cared about the details over time.
This version also fits into the wider Portail contract. One account, one chat history, and one model picker only work if the smaller pieces keep their promises. Authentication has to fail clearly. Billing has to count honestly. Uploads have to arrive in a form models can read. Admin tools have to show the operator what happened instead of hiding it behind a blank screen. v2.7.3 moved that contract forward in its own narrow lane.
The screenshots attached to this entry show the public release record as it now appears on portail.cc. For older releases, this archive was rebuilt from the git history, package version changes, release modal text, and commit subjects. That means the page is honest about its source: it documents the shipped change and preserves the record going forward, even when the exact old production screen cannot be recreated from a single saved image.
The practical result is simple. Someone landing on this page can see the version number, date, release tier, headline, highlights, and a real rendered screenshot of the archive page. Search engines can index the post through the canonical URL, sitemap entry, and structured data. Future releases now have a standard to meet before deploy, so the history should get cleaner from here instead of fuzzier.