Repository navigation
API 404 error silently hangs session in 'thinking' state with no error recovery #38951
Description
Description
When the upstream API returns an HTTP 404 error (e.g., model not found, wrong endpoint path, or deleted model), OpenCode silently hangs in the "thinking..." state indefinitely. No error message is shown to the user, no timeout or retry mechanism kicks in, and the session becomes completely unresponsive. The only recovery is to kill the process or restart the app.
This is distinct from stream errors during active streaming (#32366) — the 404 happens at the initial API request before any stream starts, yet produces the same stuck-in-thinking symptom.
OpenCode version
1.17.13 (also observed on earlier versions)
Steps to reproduce
- Configure an OpenAI-compatible provider with an incorrect API endpoint (e.g.,
https://api.example.com/v1/chat/completionsthat returns 404) - Or use a model name that does not exist on the provider
- Send any message to start a session
- Observe: UI shows "thinking..." immediately but never transitions to either a response or an error state
- The session stays stuck indefinitely — no cancel button, no error toast, no timeout recovery
Expected behavior
- Show an error message when the API returns 404 (e.g., "Model not found" or "API endpoint unavailable")
- Transition out of "thinking" state — either auto-retry with fallback or surface the error and return to idle
- Client-side timeout to prevent indefinite stuck states when the API fails to respond properly
Additional context
The same class of issue has been reported for different error triggers:
- bug: UI stuck on 'thinking' indefinitely after stream error, no error displayed or state recovery #32366 — stuck on thinking after stream errors (socket close, empty errors)
- Silent failure: opencode provider returns 500 errors but client drops response without showing error #38644 — 500 errors silently dropped without user notification
- ACP session/prompt hangs indefinitely on model API error #33055 — ACP session/prompt hangs on model API error
This issue specifically covers the HTTP 404 trigger case, which may need a slightly different fix (the error occurs before stream initiation, so stream-level error handling does not apply).
Operating System
macOS (darwin arm64)
Terminal
N/A (primarily affects Desktop GUI and TUI modes)
Activity
UCASRMTG5D commentedon Jul 26, 2026
Root Cause Analysis
After investigating the code, I traced the exact path that causes the infinite "thinking" state.
The Flow
HeaderTimeoutError) or 404MessageV2.fromError()— for timeout errors it setsisRetryable: trueEffect.retry(SessionRetry.policy(...))retryable()— for retryable errors it returns a delay valueRETRY_MAX_DELAY_NO_HEADERS = 30_000ms, but the OMO fallback guard threshold isRETRY_MAX_SINGLE_DELAY_MS = 60_000msOMO_HAS_FALLBACK && wait > RETRY_MAX_SINGLE_DELAY_MSnever evaluates to true for timeout errorsEffect.retryretries indefinitely (every ~30s) because the schedule has no upper bound on attemptsRoot Cause Constants
packages/opencode/src/session/retry.ts:36The protection mechanism that was designed to yield to OMO fallback when retry delays get too long is effectively dead code because the no-headers delay cap (30s) never exceeds the activation threshold (60s).
The Fix
Lower
RETRY_MAX_SINGLE_DELAY_MSto matchRETRY_MAX_DELAY_NO_HEADERS(30_000) so that once the backoff hits its cap for no-headers errors, the OMO fallback guard activates and the error propagates toSession.Event.Error, allowing configured fallback chains to take over.I will open a PR with this fix shortly.
github-actions commentedon Sep 25, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.