-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
Bug: Bedrock Converse Streaming silently aborts on long-context agent sessions (~6 min timeout, no retry, no fallback) #87876
Copy link
Copy link
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:fix-shape-clearClawSweeper found a clear likely implementation shape for this issue.ClawSweeper found a clear likely implementation shape for this issue.clawsweeper:queueable-fixClawSweeper marked this issue as an existing queue_fix_pr work candidate.ClawSweeper marked this issue as an existing queue_fix_pr work candidate.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.ClawSweeper found a high-confidence source-level issue reproduction.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:data-lossCan lose, corrupt, or silently drop user/session/config data.Can lose, corrupt, or silently drop user/session/config data.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.Very strong issue quality with high-confidence source-level or clear reproduction.no-staleExclude from stale automationExclude from stale automation
Description
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:fix-shape-clearClawSweeper found a clear likely implementation shape for this issue.ClawSweeper found a clear likely implementation shape for this issue.clawsweeper:queueable-fixClawSweeper marked this issue as an existing queue_fix_pr work candidate.ClawSweeper marked this issue as an existing queue_fix_pr work candidate.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.ClawSweeper found a high-confidence source-level issue reproduction.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:data-lossCan lose, corrupt, or silently drop user/session/config data.Can lose, corrupt, or silently drop user/session/config data.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.Very strong issue quality with high-confidence source-level or clear reproduction.no-staleExclude from stale automationExclude from stale automation
Type
Fields
Priority
None yet
Summary
Agent sessions using the
amazon-bedrockprovider abort silently after ~6 minutes when handling long-context prompts that require long streaming responses. The session dies with no retry, no fallback, and no transcript written — all work is lost.Environment
amazon-bedrock(Bedrock Converse Streaming API)amazon-bedrock/global.anthropic.claude-sonnet-4-6Reproduction
amazon-bedrock/global.anthropic.claude-sonnet-4-6as primary modelObserved behaviour
Session trajectory metadata after abort:
{ "status": "error", "aborted": true, "externalAbort": false, "timedOut": false, "idleTimedOut": false, "timedOutDuringCompaction": false, "timedOutDuringToolExecution": false, "promptError": "This operation was aborted" }2026-05-29T02:04:32Z2026-05-29T02:10:33Z(6 min 1 sec).jsonltranscript file never written (ENOENT) — no output savedexternalAbort: false— not killed externallytimedOut: false— did not hit the configured session timeoutpromptError: "This operation was aborted"— abort originated inside the Bedrock streaming callExpected behaviour
"This operation was aborted")Root cause hypothesis
The Bedrock Converse Streaming API appears to silently drop the connection after ~6 minutes on large payload requests. This is not surfaced as a named timeout error — it manifests as an internal abort in the bedrock-converse-stream adapter. The 6-minute window is suspiciously consistent and may correspond to an undocumented AWS streaming connection limit.
Impact
"This operation was aborted"with no actionable contextWorkaround
Provision
ANTHROPIC_API_KEYon the instance and useanthropic/claude-sonnet-4-6direct instead of Bedrock. No abort on the same prompt.Related
params.modelIdoverride ignored on Bedrock provider (separate bug, same provider layer)Reported by Haderach-Ram. Production instance, not a test environment.