Models that actually read your files

Portail v2.6.26 shipped on 2026-10-14 as a patch release focused on models that actually read your files. Attaching a file to a chat works much better now, whichever model you pick. Long files used to stop after the first stretch of text, and the model had no way to see the rest, so it would answer about a 200-page PDF having read only the first few pages. Now the model sees the beginning, knows exactly which pages or lines it hasn't seen yet, and reads them on its own when your question needs them: it can jump to a page, open one sheet of a workbook, or search a long log for the line that matters. You can watch it happen: each read shows up above the reply, like "Reading report.pdf, pages 12–14". Spreadsheets arrive with their sheet names, column letters, row numbers and formulas, so you can ask what is in C7 or why the total in B12 is wrong and get a straight answer. PDFs are numbered by page. Scanned PDFs, which used to arrive empty, are now shown to image-capable models as pictures of the pages. Files Portail made for you earlier in a chat are no longer forgotten: ask it to change the script or the spreadsheet it just gave you and it edits the real file instead of rewriting it from memory. Spreadsheets it creates now hold real numbers and working formulas, and can have more than one sheet. You can also attach code and config files directly: Python, JavaScript, TypeScript, HTML, CSS, Java, Go, Rust, SQL, YAML, logs and more. And if you send an image to a model that can't see images, it now tells you to switch models instead of answering as if nothing was attached. 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: long files no longer stop at the first part: the model opens the pages, sheets or lines it needs, or searches the file, spreadsheets keep sheet names, cell addresses and formulas; scanned pdfs are read as page images by vision models, ask portail to change a file it made earlier in the chat and it edits that exact file, and attach code, config and log files directly (python, js/ts, html, css, java, go, sql, yaml and more). 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. v2.6.26 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.