[Bug]: Injected browser rule forbids falling back after preview_open succeeds, so agents stop and ask the user which browser to use
I maintainer di solito rispondono entro 1 giorno
Valutazione
- Difficoltà
- 2/5
- Tempo stimato
- 1-3 ore
- Idoneità per principianti
- 82/100
- Tipo di issue
- Bug
- Chiarezza
- Specificata chiaramente
- Stato di attività
- Attiva
- Stack tecnologico
- typescript
- Ambito
- backend
Direzione di ricerca
Inizia da apps/server/src/provider/T3OrchestrationInstructions.ts e leggi la regola del browser iniettata. Aggiornala per consentire un fallback allo strumento browser dopo ripetuti errori delle chiamate di anteprima, senza rimuovere la preferenza generale per gli strumenti di anteprima T3; il lavoro è completato quando gli agenti possono passare da uno strumento all’altro senza chiedere e segnalare l’errore di anteprima grezzo.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Filed by Claude (Opus 5.5, running inside T3 Code) on behalf of @janpilu, at their request. The investigation was done by agents on their machine. We reviewed the last week of our T3 threads.
Before submitting
- I searched existing issues and did not find a duplicate. The failures that set this off are tracked in #13540 (failover after a timeout), #16264 (a timed-out evaluate keeps running), #13990 (
sandboxed_renderer.bundle.jsfailed to run) and #15336 (errors reduced to "failed on client"). This report is about how agents react to those failures. It isn't about the failures themselves. - I included enough detail to reproduce or investigate the problem.
Area
apps/server (src/provider/T3OrchestrationInstructions.ts)
Summary
T3 injects this browser rule into every provider session:
Use an alternative browser system only when the T3 preview tools are absent, the user explicitly requests another browser, or
preview_openreturns an explicit unsupported/unavailable error.
None of the three conditions covers the common failure: preview_open works, then later preview calls keep failing. Examples are calls that time out, a tab that lands on chrome-error://chromewebdata/, recordingStop failed on client …, or a different client ID answering after the session moved to another host (#13540). In that state the agent may not use Playwright or any other browser unless the user "explicitly requests" it. So unattended agents stop and ask the user which browser to use.
The person being asked usually can't answer. Our verification agents asked four times in three days, with questions like "Close the extra client?" and "Leave only the development-machine client connected?". Their answers were "what does this mean" and "no idea what you are talking about". The same thing happened to a coworker on a different machine, because the rule is injected for everyone. A project's own AGENTS.md or skill text that allows Playwright doesn't help: agents read the injected developer instruction as taking priority, and project text doesn't count as the user explicitly asking.
Steps to reproduce
- Give an agent a task that requires browser verification. Allow "T3 preview tools or Playwright" in the project instructions, and don't mention a browser in the prompt.
- Make preview calls fail after a successful
preview_open. The simplest way is #13540 with two desktop clients connected:preview_evaluatewithnew Promise(() => {})times out, and later calls go to the other host. - Watch the agent.
Expected behavior
After a bounded number of failed preview calls (for example, two failures on the same step), the agent may switch to another browser tool. It says so and quotes the raw preview error, and it doesn't need to ask. Alternatively, the rule says plainly that project or skill instructions can authorise a fallback.
Actual behavior
The agent stops the turn and asks the user for permission to switch browsers. Unattended pipelines stall until someone answers a question they don't have the context for. In one case, on 2026-10-05, the agent asked to switch because it thought its recordings were frozen. They weren't: its own frame-sampling script was returning frame 0 for every timestamp. The same rule meant even a mistaken diagnosis ended up as a question to the user.
Suggested change
Add a fourth condition along these lines: "…or after preview calls on an already-open tab have failed twice for the same step (timeout, chrome-error://, a failed recording stop, or a different client answering). In that case, state the raw error and switch without asking." Keep the general preference for T3 preview tools as it is.
Impact
Major degradation or frequent failure. Our verification pipeline stalls with an unanswerable question every few runs. Until #13540 and #16264 ship, this rule is what turns their failures into blocked turns.
Version
Nightly 0.0.46-nightly.20261005.2667 (37de6cbde65c), macOS 26.6.2 arm64. The instruction text is in apps/server/src/provider/T3OrchestrationInstructions.ts. In the shipped bundle it's binCli-*.mjs.
- Lingua principale
- TypeScript
- Stelle
- 24.8k
- Fork
- 6.4k
- Merge medio
- 13h 9m
- PR unite (30g)
- 271
Preparare l'ambiente
Avvia il container di sviluppo del progetto nel browser, con il tuo account GitHub.
- Nessun Dockerfile né file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di pingdotgg/t3code
-
[Bug]: Side-by-side diff squeezes the "N unmodified lines" divider into the line-number columnApertabug via-triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 62/100
pingdotgg/t3code#17157 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: Local environment can't be turned back on once disabled (toggle hidden behind "No environment selected")Forse già presa Una pull request collegata a questa issue è aperta o già unita. Apertabug via-triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
pingdotgg/t3code#17013 · 1 commento · 1 reazione ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: T3 Connect doc says held webhooks are kept per environment, but the relay keeps one inbox per linkForse già presa Una pull request collegata a questa issue è aperta o già unita. Apertadocumentation via-triage
Difficoltà 1/5 1-3 ore Idoneità per principianti 83/100
pingdotgg/t3code#16995 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: T3 Connect doc gives the relay webhook path as /v1/hooks/:environmentId/..., but the relay routes on :endpointKeyForse già presa Una pull request collegata a questa issue è aperta o già unita. Apertadocumentation via-triage
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 88/100
pingdotgg/t3code#16988 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di pingdotgg/t3code
Issue simili
-
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 85/100
lukilabs/beautiful-mermaid#160 ·
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 66/100
rescript-lang/rescript-lang.org#1420 ·
I maintainer di solito rispondono entro 2 giorni
-
bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
chthollyphile/folia-major#520 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
databuddy-analytics/Databuddy#1106 ·
I maintainer di solito rispondono entro 1 giorno