# Per-run agent choice, chat rerun history, and smarter SSH tunnels

> 6 updates: Choose an agent and other run settings per run, See rerun history right in the chat panel, Ask the chat agent for test cases by creator or…

Source: https://qa.tech/changelog/2026-08-12

---
6 updates shipped on August 12, 2026.

In this release

1.  01[Choose an agent and other run settings per run](#2026-08-12-agent-per-run-and-plan-defaults)
2.  02[See rerun history right in the chat panel](#2026-08-12-chat-rerun-history)
3.  03[Ask the chat agent for test cases by creator or owner](#2026-08-12-chat-test-cases-by-creator)
4.  04[Preview Excel downloads during test runs](#2026-08-12-excel-download-preview)
5.  05[See review duration at a glance on the Pull Requests table](#2026-08-12-pull-requests-duration-column)
6.  06[More reliable SSH tunnel setup and testing](#2026-08-12-ssh-tunnel-domain-routing)

1.  Update 01 of 06
    
    ## Choose an agent and other run settings per run
    
    Set a default agent per test plan, and override device, environment or agent for a single run.
    
    [Test plan](https://docs.qa.tech/core-concepts/test-plans) Settings has a new Advanced section with an agent selector, so you can set a default [agent](https://docs.qa.tech/best-practices/creating-tests#choosing-an-ai-agent) per plan the same way you already set device presets and environments.
    
    "Run with Options" now pre-fills the plan's saved device, environment and agent instead of showing empty defaults, and only the fields you actually change are submitted as overrides – including when you ask the [chat agent](https://docs.qa.tech/core-concepts/ai-chat-assistant) to run something for one request only.
    
    [\# Direct link](#2026-08-12-agent-per-run-and-plan-defaults)
    
2.  Update 02 of 06
    
    ## See rerun history right in the chat panel
    
    Reruns from chat show a "↻ N" badge with each earlier attempt's result instead of overwriting what you were looking at.
    
    Click the badge next to a retried test to expand its earlier attempts, each with its result, duration and a link to that specific trace.
    
    When you retry only the failing tests, the ones you did not retry are now marked "Not in latest rerun" instead of looking like they are still in progress – a clearer picture of [test results](https://docs.qa.tech/core-concepts/tests-and-results) from [chat](https://docs.qa.tech/core-concepts/ai-chat-assistant).
    
    [\# Direct link](#2026-08-12-chat-rerun-history)
    
3.  Update 03 of 06
    
    ## Ask the chat agent for test cases by creator or owner
    
    The chat agent filters test cases by who created or owns them, instead of returning everyone's.
    
    Ask for the test cases a specific teammate created and the [chat agent](https://docs.qa.tech/core-concepts/ai-chat-assistant) resolves the name and filters accurately.
    
    Every test case result in chat now also shows who created it, who owns it and who last edited it, so [ownership](https://docs.qa.tech/core-concepts/ownership) is visible even without filtering.
    
    [\# Direct link](#2026-08-12-chat-test-cases-by-creator)
    
4.  Update 04 of 06
    
    ## Preview Excel downloads during test runs
    
    .xlsx and .xlsm files downloaded mid-test render as a table in the file preview, the same way PDFs and CSVs already do.
    
    Open a spreadsheet from a run's [file preview](https://docs.qa.tech/test-features/file-downloads) and see its contents as a table instead of just a filename.
    
    Workbooks with multiple sheets get a tab per sheet, and very large sheets show a truncation note rather than rendering blank.
    
    [\# Direct link](#2026-08-12-excel-download-preview)
    
5.  Update 05 of 06
    
    ## See review duration at a glance on the Pull Requests table
    
    A Duration column shows how long each review took, with a hover card for multi-round reviews.
    
    Open a project's Pull Requests table to see review runtime next to each entry.
    
    For pull requests with more than one review round, hovering the duration shows every round's time and commit SHA in one card – handy when you are tuning [PR reviews](https://qa.tech/product/pr-testing) for speed.
    
    [\# Direct link](#2026-08-12-pull-requests-duration-column)
    
6.  Update 06 of 06
    
    ## More reliable SSH tunnel setup and testing
    
    Test Connection checks the same network path your tests run on, and tunnels can route only the domains that need one.
    
    Under Settings → Network → [SSH Tunnel Proxy](https://docs.qa.tech/configuration/ssh-tunnel), "Test Connection" now runs through the same network egress your tests use and shows the outgoing IP, so you can confirm it matches your bastion's allowlist instead of guessing why a check passed or failed.
    
    The Advanced section also adds "Only Route These Domains": list the hostnames that need the tunnel and everything else – auth providers, support widgets, CDNs – goes direct, so a jump host that only allows one preview domain no longer breaks the rest of the page.
    
    [\# Direct link](#2026-08-12-ssh-tunnel-domain-routing)
    

## Your team moves fast. Can your testing keep up?

QA.tech agents test your product autonomously, so moving fast never means shipping broken. See how it works in a 30-minute demo.

[Get a demo](https://qa.tech/demo)

[QA.tech](https://qa.tech/)

SOC 2 Type 2 compliant

![Sensiba SOC 2 Type 2 compliant](https://qa.tech/assets/soc2-type2-badge-DPb1j9VX.png)

### Product

-   [Platform overview](https://qa.tech/product)
-   [AI QA Testing](https://qa.tech/ai-qa-testing)
-   [Web Testing](https://qa.tech/product/web-testing)
-   [Mobile Testing](https://qa.tech/product/mobile-testing)
-   [PR Testing](https://qa.tech/product/pr-testing)
-   [MCP](https://qa.tech/product/mcp)
-   [Use cases](https://qa.tech/use-cases)
-   [Changelog](https://qa.tech/changelog)

### Compare

-   [QA.tech vs Cypress](https://qa.tech/compare/qa-tech-vs-cypress)
-   [QA.tech vs Playwright](https://qa.tech/compare/qa-tech-vs-playwright)
-   [QA.tech vs Mabl](https://qa.tech/compare/qa-tech-vs-mabl)
-   [QA.tech vs QA Wolf](https://qa.tech/compare/qa-tech-vs-qa-wolf)
-   [AI vs Human QA](https://qa.tech/saas)

### Resources

-   [Docs](https://docs.qa.tech/)
-   [Blog](https://qa.tech/blog)
-   [Events](https://qa.tech/events)
-   [Pricing](https://qa.tech/pricing)
-   [Case Studies](https://qa.tech/case-studies)

### Company

-   [About](https://qa.tech/about-us)
-   [Partnerships](https://qa.tech/partnerships)
-   [Press](https://qa.tech/press)
-   [Contact Us](https://qa.tech/contact)
-   [Privacy Policy](https://qa.tech/privacy-policy)
-   [Terms of Service](https://trust.qa.tech/resources?s=mb9w4yjb03i3t8bjsq4jx3&name=main-agreement.pdf)
-   [Security & Compliance](https://trust.qa.tech/)

### Social

-   [](https://www.linkedin.com/company/qa-tech-ai/)
-   [](https://x.com/getqatech)
-   [](https://www.instagram.com/getqatech/)

© 2025 QA.tech. All rights reserved
