[Bug]: Getting error during cursor runs, `RetriableError: [canceled] http/2 stream closed with error code CANCEL (0x8)`

[aashishsingla567]

Before submitting

• I searched existing issues and did not find a duplicate.
• I included enough detail to reproduce or investigate the problem.

Area

apps/web

Steps to reproduce

In a long run it eventually gets this error

Expected behavior

Agent keeps running until work is done

Actual behavior

Error: RetriableError: [canceled] http/2 stream closed with error code CANCEL (0x8)

Impact

Blocks work completely

Version or commit

0.0.42 (719a76c)

Environment

macOs 26.6.1 (25G76)

Logs or stack traces

ProviderAdapterRequestError: Provider adapter request failed (cursor) for session/prompt: Cursor reported a transport failure.
    at Array.<anonymous> (file:///Applications/T3%20Code%20(Alpha).app/Contents/Resources/app.asar/apps/server/dist/bin.mjs:146304:98)
    at next (<anonymous>)
    at sendTurn (Alpha)
    at sendTurn (definition) (Alpha)
    at processTurnStartRequested (Alpha)
    at processTurnStartRequested (definition) (file:///Applications/T3%20Code%20(Alpha).app/Contents/Resources/app.asar/apps/server/dist/bin.mjs:203752:36)
    at processDomainEvent (file:///Applications/T3%20Code%20(Alpha).app/Contents/Resources/app.asar/apps/server/dist/bin.mjs:204127:46)
    at processDomainEvent (definition) (file:///Applications/T3%20Code%20(Alpha).app/Contents/Resources/app.asar/apps/server/dist/bin.mjs:204076:29) {
  [cause]: Error: Error: RetriableError: [canceled] http/2 stream closed with error code CANCEL (0x8)
      at causePrettyError (file:///Applications/T3%20Code%20(Alpha).app/Contents/Resources/app.asar/apps/server/dist/claudeHistoryWorker-CAn1PawV.mjs:9188:17)
}

Screenshots, recordings, or supporting files

No response

Workaround

No workaround, but starts working for a while again if you continue

[juliusmarminge]

Triage

Verdict: Valid bug. Keep open.
Not a duplicate of #7830. That issue was Cursor leaking transport dumps as assistant text and T3 marking the turn completed. #10337 already fails those turns. This report is the leftover: the run still dies mid-work and the user has to Continue.
Not a duplicate of #10480. That one is RetriableError: [internal] Failed to run step, exceeded max retries (agent-loop). #11365 stopped labeling that class as a transport failure. This diagnostic is [canceled] http/2 stream closed … CANCEL (0x8), which is the transport class.
Not already fixed on current main (53510d44e) or on the reporter’s 0.0.42 (719a76ca1). Same fail-the-turn path, no retry, no session recycle.

Same reporter already left this exact string on #10480 a few minutes before filing this.

Area on the form is wrong: this is the Cursor ACP adapter (apps/server), not apps/web. The web client is only showing the failed turn.

What happens

1. Cursor ACP finishes session/prompt with a normal end_turn, but the assistant text is only a transport dump:

Error: RetriableError: [canceled] http/2 stream closed with error code CANCEL (0x8)

HTTP/2 CANCEL (0x8) is a stream reset on a long-lived Cursor backend request. Cursor’s interactive agent retries these internally. ACP leaks them as agent_message_chunk plus a successful prompt result. Cursor has acknowledged that error-channel leak (forum). #7830 already listed HTTP/2 CANCEL / stream-reset as part of this class.

2. T3’s matcher treats a standalone Error: RetriableError: … that is not [internal] as a transport failure. This string matches:

const maxLineLength = 4096;
// Cursor also uses RetriableError for agent-loop failures; preserve those diagnostics.
const transportError =
  /^Error: (?:RetriableError: (?!\[internal\]).+|ConnectError: \[(?:unavailable|aborted|deadline_exceeded)\].*)$/;

3. After draining ACP events, sendTurn fails the turn. It does not retry and does not drop the session:

          yield* ctx.acp.drainEvents;
          const failure = ctx.assistantReply.failure;
          if (ctx.promptsInFlight === 1 && result.stopReason !== "cancelled" && failure) {
            return yield* new ProviderAdapterRequestError({
              provider: PROVIDER,
              method: "session/prompt",
              detail: "Cursor reported a transport failure.",
              cause: failure,
            });
          }

That is why the user sees a hard stop instead of a fake completed answer, and why Continue works for a while: the next prompt often succeeds until the next cancel. On a long run that already used tools, this is the expected current behavior, not a missed matcher.

Related (do not close as these)

Item	Why it does not close this
#7830 (closed)	Fail-the-turn only. Retry was explicitly left out of #10337
#10480 (open)	[internal] max-retries, not HTTP/2 CANCEL
#10337 (merged)	Detection + Failed status. Shipped in 0.0.42
#11365 (merged)	Carve-out for [internal] only
#11225 (open, conflicting)	Bounded retry when the failed attempt did no work. A long run that already ran tools still stops
#12337 (open)	Recycles the ACP session after this exact diagnostic so Continue is a fresh session/load. Still no replay

Suggested fix

Do not replay a long run that already used tools. #10337 was right to refuse that.

Two stacked workarounds, neither of which is on main yet:

1. Land the session recycle in fix(server): recycle Cursor sessions after transport failures #12337 so Continue does not reuse a dead HTTP/2 transport. That matches the reporter’s current workaround and uses this exact CANCEL (0x8) string in the regression test.
2. Keep fix(cursor): retry prompts that only returned a transport failure #11225 (or a rebased follow-up) for the no-work case only: first-prompt / pre-tool blips. It will not satisfy “agent keeps running until work is done” on a long run that already called tools.

A later “auto-Continue after recycle” (new turn, not a replay of the original prompt) is the piece that would match the expected behavior for mid-run cancels after tools. That is not in either open PR. Do not buffer-and-hide the leaked diagnostic; leave it visible.

Root cause stays upstream: Cursor ACP should return these as JSON-RPC errors, not assistant text.

Labels: bug upstream (remove needs-triage)