[Bug]: First message with an image or skill fails with "provider could not start this turn" after a thread sits idle for a few hours
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 45/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- typescript
- Domain
- backend-api-design
Research direction
Start in the apps/server area named in the issue and trace how a thread resumes after sitting idle, focusing on first messages that include an image or skill reference. Compare that path with a plain-text first message and inspect the server logs or provider setup when available. Done when the affected first message starts normally after the idle period and retries are no longer needed.
Written by the indexing model from the issue text.
Description
Before submitting
- I searched existing issues and did not find a duplicate.
- I included enough detail to reproduce or investigate the problem.
Area
apps/server
Steps to reproduce
- Let a thread finish its turn.
- Leave that thread idle for a few hours while you keep working in other threads.
- Come back to it and send a first message that has an image attached or references a skill (e.g.
/unslop).
Expected behavior
The turn starts normally.
Actual behavior
The turn never starts and I get:
Provider error
The provider could not start this turn. Retry the turn; if it keeps failing, check the provider setup and server logs.
Retrying gives the same error. I also tried editing the message to replace /unslop with plain text "unslop skill", and that still failed, so it's not only the skill reference itself.
If I send the same message without the image or skill, it works. After that, images and skills work fine in that thread again.
Impact
Minor bug or occasional failure
Version or commit
0.1.10 nightly (build from around 2026-11-11)
Environment
macOS, desktop app, Claude Code provider
Logs or stack traces
Didn't grab server logs from the machine this happened on. I can try to capture them next time it reproduces.
Workaround
Send a plain-text message first, then send the one with the image or skill.
Possibly related: #20828 (same generic error with the underlying cause dropped).
- Dominant language
- TypeScript
- Stars
- 24.8k
- Forks
- 6.4k
- Avg merge
- 4h 16m
- Merged PRs (30d)
- 352
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from pingdotgg/t3code
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 1 day
All issues in pingdotgg/t3code
Similar issues
-
Autocomplete still accepts an option after becoming disabledPossibly taken @Xapollon430 claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 1/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
reduxjs/react-redux#2416 · 1 comment ·