AgentCoreMemorySessionManager discards the two boto3 clients MemoryClient builds; boto_session and boto_client_config are not passed through
I maintainer di solito rispondono entro 1 giorno
Valutazione
- Difficoltà
- 2/5
- Tempo stimato
- 1-3 ore
- Idoneità per principianti
- 84/100
Direzione di ricerca
Inizia in src/bedrock_agentcore/memory/integrations/strands/session_manager.py, in AgentCoreMemorySessionManager.init, quindi esamina MemoryClient.init in memory/client.py:76-80. Esegui la riproduzione fornita per no-session e warm-session; il lavoro è completato quando MemoryClient usa la stessa sessione dei client di override, senza modifiche alla firma pubblica, e il comportamento segnalato relativo a timing e regione è corretto.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Describe the bug
AgentCoreMemorySessionManager.__init__ builds its MemoryClient without a boto3 session, then overwrites both clients MemoryClient just created with clients from a different session.
# src/bedrock_agentcore/memory/integrations/strands/session_manager.py, 1.23.1
self.memory_client = MemoryClient(region_name=region_name) # :151
session = boto_session or boto3.Session(region_name=region_name) # :152
...
self.memory_client.gmcp_client = session.client( # :195
"bedrock-agentcore-control", region_name=..., config=client_config
)
self.memory_client.gmdp_client = session.client( # :198
"bedrock-agentcore", region_name=..., config=client_config
)
MemoryClient.__init__ accepts boto3_session (memory/client.py:76-80) and would use it. Since it isn't passed, MemoryClient creates its own boto3.Session() and builds bedrock-agentcore-control and bedrock-agentcore clients from it. Lines 195 and 198 then replace both. Those two clients are built and thrown away on every instantiation.
botocore caches the parsed service model per boto3.Session, so a fresh session pays that load again every time.
boto_session and boto_client_config are both in the signature and documented in the docstring. Neither reaches MemoryClient.
Cost
We build a session manager per invoke, so this runs on every turn. We also pass a long-lived boto_session, which is what the parameter is for, and that's where this hurts most. The injected session only reaches the override clients. MemoryClient still cold-builds its own session, and that cold build is nearly all of the remaining time.
Medians over 10 iterations after a warm-up, from the script below:
| caller | as shipped | with the fix below |
|---|---|---|
passes boto_session (a long-lived session) |
42 ms | 3.3 ms |
passes no boto_session |
97 ms | 41 ms |
Five consecutive runs ranged 40.3 to 43.9 ms against 3.2 to 3.5 ms for the first row, and 95.3 to 98.9 ms against 39.9 to 44.1 ms for the second.
These are from an M-series laptop. On a warm AgentCore runtime the per-turn cost is in the same range, 37 to 51 ms. The first construction on a cold container is higher, because the service-model load and credential resolution happen then.
To Reproduce
import os, statistics, time
os.environ["AWS_CONFIG_FILE"] = "/dev/null"
os.environ["AWS_SHARED_CREDENTIALS_FILE"] = "/dev/null"
os.environ["AWS_ACCESS_KEY_ID"] = "AKIAIOSFODNN7EXAMPLE"
os.environ["AWS_SECRET_ACCESS_KEY"] = "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"
os.environ["AWS_EC2_METADATA_DISABLED"] = "true"
import boto3
from botocore.config import Config
from bedrock_agentcore.memory.client import MemoryClient
REGION = "us-west-2"
CFG = Config(user_agent_extra="strands-agents") # what :184-192 builds
def pair(s): # the :195/:198 overrides
s.client("bedrock-agentcore-control", region_name=REGION, config=CFG)
s.client("bedrock-agentcore", region_name=REGION, config=CFG)
# A long-lived session the caller passes as boto_session, primed once.
WARM = boto3.Session(region_name=REGION)
pair(WARM)
def no_session_shipped(): # boto_session=None, as shipped
MemoryClient(region_name=REGION)
pair(boto3.Session(region_name=REGION))
def no_session_fixed():
s = boto3.Session(region_name=REGION)
MemoryClient(region_name=REGION, boto3_session=s)
pair(s)
def warm_session_shipped(): # boto_session=WARM, as shipped
MemoryClient(region_name=REGION)
pair(WARM)
def warm_session_fixed():
MemoryClient(region_name=REGION, boto3_session=WARM)
pair(WARM)
for name, fn in (("no session, shipped", no_session_shipped),
("no session, fixed", no_session_fixed),
("warm session, shipped", warm_session_shipped),
("warm session, fixed", warm_session_fixed)):
fn() # warm-up
samples = []
for _ in range(10):
t0 = time.perf_counter(); fn()
samples.append((time.perf_counter() - t0) * 1000)
print(f"{name:22s} {statistics.median(samples):6.1f} ms")
Run it with no AWS profile set. It makes no network calls, so the dummy keys only stop botocore from searching for real ones.
Expected behavior
MemoryClient should be built from the same session the overrides use. Hoisting line 152 above line 151 and passing the session through is enough:
session = boto_session or boto3.Session(region_name=region_name)
self.memory_client = MemoryClient(region_name=region_name, boto3_session=session)
No public signature changes. Callers who pass boto_session get the 42 to 3.3 ms drop, and callers who don't still save the second service-model load.
Two related points:
-
boto_client_configcan't be forwarded the same way.MemoryClient.__init__takes onlyregion_name,integration_sourceandboto3_session, and builds its ownConfig(user_agent_extra=...)internally. Honouring the documentedboto_client_configmeans adding a parameter there. Until then, retry and timeout config can't be set on the memory client at all. -
With
region_name=Noneand aboto_sessionpinned to one region,MemoryClient.region_nameresolves from a fresh default session while the clients actually used come fromboto_session. The attribute can disagree with the region serving the calls. Passing the session fixes that too.
Happy to test a patch against our workload. I didn't open a PR because CONTRIBUTING.md says the repo isn't accepting external ones.
Environment
bedrock-agentcore1.23.1. Also present onmainat cc980d14, the most recent commit to touch this file.- boto3 1.43.101, botocore 1.43.101
- Python 3.13.13, macOS
- Also reproduces on 1.18.1
- Lingua principale
- Python
- Stelle
- 776
- Fork
- 153
- Merge medio
- 1g 8h
- PR unite (30g)
- 15
Preparare l'ambiente
- Nessun Dockerfile né file Docker Compose
- Nessun modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di aws/bedrock-agentcore-sdk-python
-
bug high-severity
Difficoltà 2/5 1-3 ore Idoneità per principianti 88/100
aws/bedrock-agentcore-sdk-python#698 ·
I maintainer di solito rispondono entro 1 giorno
-
bug high-severity
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
aws/bedrock-agentcore-sdk-python#680 ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug] update_message fails with parameter validation error when SessionMessage.message_id is a Strands positional integer indexForse già presa @citizen204 l’ha presa 100 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
aws/bedrock-agentcore-sdk-python#556 ·
I maintainer di solito rispondono entro 1 giorno
-
CodeInterpreter should not require a region argumentForse già presa @citizen204 l’ha presa 115 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
aws/bedrock-agentcore-sdk-python#511 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
aws/bedrock-agentcore-sdk-python#496 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di aws/bedrock-agentcore-sdk-python
Issue simili
-
bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 85/100
Deepak3699/Ai_Mentor#244 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
btclib-org/btclib-node#1880 ·
I maintainer di solito rispondono entro 1 giorno
-
CONTRIBUTING.md: say how ticketless bug fixes and feature PRs are handledForse già presa @khuisman l’ha presa oggi. Apertav0.9.2
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 84/100
khuisman/mcp-gee-sweet#941 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
pyjanitor-devs/pyjanitor#1758 ·
I maintainer di solito rispondono entro 1 giorno
-
bug ready for review
Difficoltà 2/5 1-3 ore Idoneità per principianti 86/100
odysseus-dev/odysseus#6641 ·
I maintainer di solito rispondono entro 1 giorno