temporal-spring-ai: a provider 429 fails the chat activity on the first attempt
Maintainer antworten meist innerhalb von 1 Tag
Dieses Issue hat noch niemand übernommen.
Bewertung
- Schwierigkeit
- 5/5
- Geschätzter Aufwand
- Über eine Woche
- Anfängerfreundlichkeit
- 38/100
Rechercherichtung
Start with ActivityChatModel.java:111-114 and the reported ProviderRateLimitRetryTest cases; the issue does not give the test's file path. Compare the activity's retry behavior with Spring AI's default handling of 429 and its inner retries. The issue describes possible approaches but leaves the policy to the team; done should address the reported 429 and 503 cases, including the Retry-After and insufficient_quota distinction.
Vom Indexierungsmodell aus dem Issue-Text verfasst.
Beschreibung
Expected Behavior
A rate-limited LLM call (HTTP 429) through ActivityChatModel is retried by Temporal with backoff. sdk-python's OpenAI Agents integration already treats 429 as retryable and passes the provider's retry delay through (temporalio/sdk-python#1796).
Actual Behavior
The activity fails on attempt 1 with RETRY_STATE_NON_RETRYABLE_FAILURE. Spring AI's default error handlers, both the plain builder default and the Boot auto-configured one, turn every 4xx, 429 included, into NonTransientAiException (RetryUtils in Spring AI 1.1.0), and ActivityChatModel puts that type in doNotRetry by default (ActivityChatModel.java:111-114).
A related interaction on 5xx: Spring AI's own RetryTemplate (10 attempts, backoff up to 3 minutes) runs inside the activity, so a persistent 503 can send up to 30 requests across Temporal's 3 attempts. The activity has a 2-minute start-to-close and no heartbeat, so a timed-out attempt can keep calling the provider while later attempts run. sdk-python turned off Botocore's inner retries for its default Strands Bedrock model for a similar reason (temporalio/sdk-python#1797).
Steps to Reproduce the Problem
- Point a real
OpenAiChatModelat a local stub that returns 429 withRetry-After: 7, register it withChatModelActivityImpl, and call it from a workflow throughActivityChatModel.forDefault(). - The stub sees one request; the workflow gets
ActivityFailurecaused byApplicationFailureof typeNonTransientAiException, attempt 1. - With a 503 stub and Spring AI's backoff shortened to milliseconds, the stub sees 30 requests.
I have this as a test (ProviderRateLimitRetryTest, five cases, including Boot-equivalent defaults and spring.ai.retry.on-http-codes=429). For a fix I'd rather not parse exception messages, but Spring AI's handlers throw NonTransientAiException with only a message, so the status survives only in the message and the headers are gone by the time the activity sees it. The OpenAI path could instead use a response error handler, scoped to the client Temporal calls, that keeps status, headers and the error body; the activity can then retry rate limits with Retry-After as the next delay and leave insufficient_quota 429s non-retryable, since backoff won't fix a billing limit. Whether the module should also turn off Spring AI's inner retry for calls it wraps seems like your team's call; I'll follow whichever direction you prefer.
Specifications
- Version: sdk-java main (be01e60a), Spring AI 1.1.0
- Platform: JDK 21, macOS
- Vorherrschende Sprache
- Java
- Sterne
- 433
- Forks
- 257
- Ø Merge
- 2 T. 18 Std.
- Gemergte PRs (30 T.)
- 24
Entwicklungsumgebung
- Kein Dockerfile und keine Docker-Compose-Datei
- Keine Pull-Request-Vorlage
- Beitragsleitfaden lesen
Erste Schritte
- Lesen Sie das ganze Issue und danach den Beitragsleitfaden des Projekts.
- Schreiben Sie ins Issue, dass Sie es übernehmen — das erspart doppelte Arbeit.
- Forken Sie das Repository und arbeiten Sie in einem Branch.
- Öffnen Sie einen Pull Request, der die Issue-Nummer nennt.
Mehr aus temporalio/sdk-java
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 78/100
temporalio/sdk-java#3134 ·
Maintainer antworten meist innerhalb von 1 Tag
-
enhancement
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 65/100
temporalio/sdk-java#1825 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 4/5 3-5 Tage Anfängerfreundlichkeit 55/100
temporalio/sdk-java#3132 ·
Maintainer antworten meist innerhalb von 1 Tag
-
enhancement
Schwierigkeit 4/5 3-5 Tage Anfängerfreundlichkeit 54/100
temporalio/sdk-java#3125 · 2 Kommentare ·
Maintainer antworten meist innerhalb von 1 Tag
-
enhancement
Schwierigkeit 3/5 1-2 Tage Anfängerfreundlichkeit 55/100
temporalio/sdk-java#3124 ·
Maintainer antworten meist innerhalb von 1 Tag
Alle Issues in temporalio/sdk-java
Ähnliche Issues
-
backend
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 76/100
bcgov/nr-forest-client#2524 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 67/100
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 1/5 Unter einer Stunde Anfängerfreundlichkeit 74/100
Maintainer antworten meist innerhalb von 1 Tag
-
team:Lumberjack
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 76/100
OpenLiberty/open-liberty#35998 ·
Maintainer antworten meist innerhalb von 1 Tag
-
[BUG] SQS SendMessageBatch accepts more than 10 entries instead of TooManyEntriesInBatchRequestEvtl. vergeben Ein verknüpfter Pull Request ist offen oder bereits gemergt. Offen
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 67/100
floci-io/floci#5319 · 1 Kommentar ·
Maintainer antworten meist innerhalb von 1 Tag