https://prefect.io logo
Join Slack
Powered by
<@ULVA73B9P> I have upgraded from `cloud-run:push`...
# marvin-ai
j
@Marvin I have upgraded from 
cloud-run:push
workpool to 
cloud-run-v2:push
workpool. The flow run executions start as intended but they give warning:
Copy code
Unable to check status of flow run: <HttpError 404 when requesting <https://run.googleapis.com/v2/projects/project-name/locations/europe-north1/jobs/prefect-dbt-run-24h-2025-10-06T09:50:09/executions/prefect-wakeful-dragon-2zmln?alt=json> returned "Resource 'prefect-wakeful-dragon-2zmln' of kind 'EXECUTION' in region 'europe-north1' in project 'project-name' with parent 'prefect-dbt-run-24h-2025-10-06T09:50:09' does not exist.". Details: "Resource 'prefect-wakeful-dragon-2zmln' of kind 'EXECUTION' in region 'europe-north1' in project 'project-name' with parent 'prefect-dbt-run-24h-2025-10-06T09:50:09' does not exist.">
I have confirmed the related job 
prefect-wakeful-dragon-2zmln
exists in Cloud Run job pool and it has a YAML spec starting with:
Copy code
apiVersion: <http://run.googleapis.com/v1|run.googleapis.com/v1>
kind: Execution
metadata:
  name: prefect-wakeful-dragon-2zmln
  namespace: '837612869087'
  selfLink: /apis/run.googleapis.com/v1/namespaces/837612869087/executions/prefect-wakeful-dragon-2zmln
  uid: 2a904416-a9d6-4e6c-a17a-638c75c777f8
  resourceVersion: AAZAen54gj0
  generation: 1
  creationTimestamp: '2025-10-06T09:49:16.645383Z'
It seems like the workpool is still generating v1 jobs even though I have set it to be v2. I have confirmed from Prefect UI that the workpool is indeed of type 
Cloud Run V2:push
. What could be the issue?
m
✅ thought for 354.2 seconds
Thanks for the detailed info — that warning and your snippet are super helpful. What’s going on - The polling URL in the warning is a Cloud Run v2 Jobs path: https://run.googleapis.com/v2/projects/.../locations/europe-north1/jobs/prefect-dbt-run-24h-2025-10-06T09:50:09/executions/prefect-wakeful-dragon-2zmln - The “parent” job name in that path is prefect-dbt-run-24h-2025-10-06T095009 which includes uppercase “T” and colons “:”. - Cloud Run Job names must be DNS-1035 compliant (lowercase letters, digits, and hyphens only). Uppercase letters and colons are not allowed. - Because the parent job name in the v2 path is not valid, the v2 API returns 404 with “parent ... does not exist”, which is the warning you’re seeing. This does not necessarily mean the worker created the job via v1; it means the name used for polling does not match a valid v2 job resource. Why you’re seeing an apiVersion: run.googleapis.com/v1 in the console - The Cloud Run console often renders resources under a v1-style CRD view. That display by itself isn’t proof of which API the worker used; the key issue here is that the v2 polling path is using an invalid parent job name. Most likely root cause - Your deployment’s run name template (or the job name in the work pool’s base job template) includes a timestamp like 2025-10-06T095009. The “T” and “:” make the name invalid for Cloud Run Jobs v2. The worker kicks off the execution successfully, but when Prefect later polls status via the v2 Jobs API using that unsanitized job name, it 404s. How to fix Pick one of these and re-run: 1) Use a DNS-safe run name template for the deployment - In the Prefect UI, open your Deployment → Settings → Run names, and choose a template that avoids invalid characters. - Safe example:
Copy code
{{ flow_run.id }}
or, if you prefer something readable:
Copy code
{{ deployment.name | lower }}-{{ flow_run.id }}
If you really want to keep a timestamp, make it safe:
Copy code
{{ deployment.name | lower }}-{{ scheduled_start_time | replace(':','-') | replace('T','-') | lower }}
2) Override the job name in the Cloud Run V2 work pool’s base job template - Open your Cloud Run V2:push work pool → Base job template. - Set the job name field to a DNS-safe template, e.g.:
Copy code
{{ flow_run.id }}
or
Copy code
{{ deployment.name | lower }}-{{ flow_run.id }}
- Save, then re-run. Also recommended - Update to the latest versions of 
prefect
and 
prefect-gcp
to pick up any recent fixes or improvements. - Our GCP worker guide is here: Prefect GCP worker guide If you’re still seeing the warning after switching to a DNS-safe name, please share: - Your 
prefect
and 
prefect-gcp
versions - The deployment run name template - The Cloud Run V2 work pool base job template (redact secrets) - A short snippet from the worker logs showing the “Creating Cloud Run job/execution” and the names it uses I can help pinpoint whether there’s a naming mismatch in polling or something else we need to tweak.
j
@Marvin: The name template is now 
f"dbt-run-24h-{datetime.now().strftime("%Y-%m-%d-%H-%M-%S")}"
so I removed the problematic characters. I'm still getting the same warnings on flow runs. I'm using:
Copy code
prefect==3.4.12
prefect-gcp==0.6.10
Here is the base job template:
Copy code
{
  "variables": {
    "type": "object",
    "required": [
      "credentials"
    ],
    "properties": {
      "cpu": {
        "type": "string",
        "title": "CPU",
        "default": "1000m",
        "pattern": "^(\\d*000)m$",
        "description": "The CPU to allocate to the Cloud Run job."
      },
      "env": {
        "type": "object",
        "title": "Environment Variables",
        "default": {
          "prefect_var_env": "test",
          "prefect_var_region": "europe-north1",
          "prefect_var_gcp_account_id": "project-name"
        },
        "description": "Environment variables to set when starting a flow run.",
        "additionalProperties": {
          "type": "string"
        }
      },
      "args": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "title": "Args",
        "description": "The arguments to pass to the Cloud Run Job V2's entrypoint command."
      },
      "name": {
        "type": "string",
        "title": "Name",
        "description": "Name given to created infrastructure."
      },
      "image": {
        "type": "string",
        "title": "Image Name",
        "default": "prefecthq/prefect:3.4.12-python3.12",
        "description": "The image to use for the Cloud Run job. If not provided the latest Prefect image will be used."
      },
      "labels": {
        "type": "object",
        "title": "Labels",
        "description": "Labels applied to created infrastructure.",
        "additionalProperties": {
          "type": "string"
        }
      },
      "memory": {
        "type": "string",
        "title": "Memory",
        "default": "512Mi",
        "example": "512Mi",
        "pattern": "^\\d+(?:G|Gi|M|Mi)$",
        "description": "The memory to allocate to the Cloud Run job along with the units, which could be: G, Gi, M, Mi."
      },
      "region": {
        "type": "string",
        "title": "Region",
        "default": "europe-north1",
        "example": "europe-north1",
        "description": "The region in which to run the Cloud Run job"
      },
      "command": {
        "type": "string",
        "title": "Command",
        "description": "The command to use when starting a flow run. In most cases, this should be left blank and the command will be automatically generated."
      },
      "timeout": {
        "type": "integer",
        "title": "Job Timeout",
        "default": 3600,
        "maximum": 86400,
        "description": "The length of time that Prefect will wait for a Cloud Run Job to complete before raising an exception (maximum of 86400 seconds, 1 day).",
        "exclusiveMinimum": 0
      },
      "keep_job": {
        "type": "boolean",
        "title": "Keep Job After Completion",
        "default": false,
        "description": "Keep the completed Cloud run job on Google Cloud Platform."
      },
      "credentials": {
        "anyOf": [
          {
            "$ref": "#/definitions/GcpCredentials"
          },
          {
            "$ref": "#/definitions/OidcGcpCredentials"
          }
        ],
        "title": "GCP Credentials",
        "default": {
          "$ref": {
            "block_document_id": "redacted-uuid-reference-id"
          }
        },
        "description": "The GCP Credentials used to initiate the Cloud Run Job. `service_account_info` is required."
      },
      "max_retries": {
        "type": "integer",
        "title": "Max Retries",
        "default": 0,
        "description": "The number of times to retry the Cloud Run job."
      },
      "launch_stage": {
        "enum": [
          "ALPHA",
          "BETA",
          "GA",
          "DEPRECATED",
          "EARLY_ACCESS",
          "PRELAUNCH",
          "UNIMPLEMENTED",
          "LAUNCH_TAG_UNSPECIFIED"
        ],
        "type": "string",
        "title": "Launch Stage",
        "default": "BETA",
        "description": "The launch stage of the Cloud Run Job V2. See <https://cloud.google.com/run/docs/about-features-categories> for additional details."
      },
      "env_from_secrets": {
        "type": "object",
        "title": "Environment Variables from Secrets",
        "example": {
          "ENV_VAR_NAME": {
            "secret": "SECRET_NAME",
            "version": "latest"
          }
        },
        "description": "Environment variables to set from GCP secrets when starting a flow run."
      },
      "vpc_connector_name": {
        "type": "string",
        "title": "VPC Connector Name",
        "description": "The name of the VPC connector to use for the Cloud Run job."
      },
      "service_account_name": {
        "type": "string",
        "title": "Service Account Name",
        "example": "<mailto:service-account@example.iam.gserviceaccount.com|service-account@example.iam.gserviceaccount.com>",
        "description": "The name of the service account to use for the task execution of Cloud Run Job. By default Cloud Run jobs run as the default Compute Engine Service Account. "
      }
    },
    "definitions": {
      "GcpCredentials": {
        "type": "object",
        "title": "GcpCredentials",
        "properties": {
          "project": {
            "type": "string",
            "title": "Project",
            "description": "The GCP project to use for the client."
          },
          "service_account_file": {
            "type": "string",
            "title": "Service Account File",
            "format": "path",
            "description": "Path to the service account JSON keyfile."
          },
          "service_account_info": {
            "type": "object",
            "title": "Service Account Info",
            "description": "The contents of the keyfile as a dict."
          }
        },
        "description": "Block used to manage authentication with GCP. Google authentication is handled via the `google.oauth2.\nSee Google's [Authentication documentation](<https://cloud.google.com/docs/authentication#service-accounts>)\nfor details on inference and recommended authentication patterns.",
        "secret_fields": [
          "service_account_info.*"
        ],
        "block_type_slug": "gcp-credentials",
        "block_schema_references": {}
      },
      "OidcGcpCredentials": {
        "type": "object",
        "title": "OidcGcpCredentials",
        "required": [
          "project",
          "workload_identity_audience",
          "service_account_email"
        ],
        "properties": {
          "project": {
            "type": "string",
            "title": "Project",
            "description": "The GCP project to use for the client."
          },
          "service_account_email": {
            "type": "string",
            "title": "Service Account Email",
            "description": "Service account email to impersonate (e.g., '<mailto:prefect-runner@my-project.iam.gserviceaccount.com|prefect-runner@my-project.iam.gserviceaccount.com>')"
          },
          "workload_identity_audience": {
            "type": "string",
            "title": "Workload Identity Audience",
            "description": "The audience URL from your workload identity provider."
          }
        },
        "description": "Block used to manage authentication with GCP using OIDC Workload Identity Federation."
      }
    },
    "description": "Default variables for the Cloud Run V2 Push Pool.\n\nThe schema for this class is used to populate the `variables` section of the\ndefault base job template."
  },
  "job_configuration": {
    "env": "{{ env }}",
    "name": "{{ name }}",
    "labels": "{{ labels }}",
    "region": "{{ region }}",
    "command": "{{ command }}",
    "timeout": "{{ timeout }}",
    "job_body": {
      "client": "prefect",
      "template": {
        "template": {
          "timeout": "{{ timeout }}",
          "vpcAccess": {
            "connector": "{{ vpc_connector_name }}"
          },
          "containers": [
            {
              "env": [],
              "args": "{{ args }}",
              "image": "{{ image }}",
              "command": "{{ command }}",
              "resources": {
                "limits": {
                  "cpu": "{{ cpu }}",
                  "memory": "{{ memory }}"
                }
              }
            }
          ],
          "maxRetries": "{{ max_retries }}",
          "serviceAccount": "{{ service_account_name }}"
        }
      },
      "launchStage": "{{ launch_stage }}"
    },
    "keep_job": "{{ keep_job }}",
    "credentials": "{{ credentials }}",
    "env_from_secrets": "{{ env_from_secrets }}"
  }
}
m
Your message was too long, here's your message at the allowed limit: The name template is now 
f dbt-run-24h-{datetime now() strftime( %Y-%m-%d-%H-%M-%S )}
so I removed the problematic characters I'm still getting the same warnings on flow runs I'm using
Copy code
prefect==3 4 12 prefect-gcp==0 6 10
Here is the base job template ```{ variables { type object required [ credentials ] properties { cpu { type string title CPU default 1000m pattern ^(\\d*000)m$ description The CPU to allocate to the Cloud Run job } env { type object title Environment Variables default { prefect_var_env test prefect_var_region europe-north1 prefect_var_gcp_account_id project-name } description Environment variables to set when starting a flow run additionalProperties { type string } } args { type array items { type string } title Args description The arguments to pass to the Cloud Run Job V2's entrypoint command } name { type string title Name description Name given to created infrastructure } image { type string title Image Name default prefecthq/prefect 3 4 12-python3 12 description The image to use for the Cloud Run job If not provided the latest Prefect image will be used } labels { type object title Labels description Labels applied to created infrastructure additionalProperties { type string } } memory { type string title Memory default 512Mi example 512Mi pattern ^\\d+(? G|Gi|M|Mi)$ description The memory to allocate to the Cloud Run job along with the units which could be G Gi M Mi } region { type string title Region default europe-north1 example europe-north1 description The region in which to run the Cloud Run job } command { type string title Command description The command to use when starting a flow run In most cases this should be left blank and the command will be automatically generated } timeout { type integer title Job Timeout default 3600 maximum 86400 description The length of time that Prefect will wait for a Cloud Run Job to complete before raising an exception (maximum of 86400 seconds 1 day) exclusiveMinimum 0 } keep_job { type boolean title Keep Job After Completion default false description Keep the completed Cloud run job on Google Cloud Platform } credentials { anyOf [ { $ref #/definitions/GcpCredentials } { $ref #/definitions/OidcGcpCredentials } ] title GCP Credentials default { $ref { block_document_id redacted-uuid-reference-id } } description The GCP Credentials used to initiate the Cloud Run Job 
service_account_info
is required } max_retries { type integer title Max Retries default 0 description The number of times to retry the Cloud Run job } launch_stage { enum [ ALPHA BETA GA DEPRECATED EARLY_ACCESS PRELAUNCH UNIMPLEMENTED LAUNCH_TAG_UNSPECIFIED ] type string title Launch Stage default BETA description The launch stage of the Cloud Run Job V2 See <https //cloud google com/run/docs/about-features-categories> for additional details } env_from_secrets { type object title Environment Variables from Secrets example { ENV_VAR_NAME { secret SECRET_NAME version latest } } description Environment variables to set from GCP secrets when starting a flow run } vpc_connector_name { type string title VPC Connector Name description The name of the VPC connector to use for the Cloud
j
@Marvin: The name template is now 
f"dbt-run-24h-{datetime.now().strftime("%Y-%m-%d-%H-%M-%S")}"
so I removed the problematic characters. I'm still getting the same warnings on flow runs. I'm using:
Copy code
prefect==3.4.12
prefect-gcp==0.6.10
m
✅ thought for 454.9 seconds
Thanks for the details. A couple things to clarify so I can pinpoint why you’re still seeing warnings: - What exact warning text are you getting, and where (worker logs, UI, both)? - Which worker are you running this on (Cloud Run v1/v2, GKE)? - Where are you setting the name: in the flow decorator (
flow_run_name=...
), in code at runtime, or as part of a deployment name pattern? Important context for Prefect 3.4.12 + prefect-gcp 0.6.10: - There is no `name_template`/`run_name_template` argument on 
.deploy()
. In Prefect 3, dynamic flow run names are set on the flow itself via the 
@flow
decorator’s 
flow_run_name
parameter. - GCP workers (Cloud Run/GKE) generate a job/resource name and will “slugify” it (lowercase, replace invalid characters, truncate) using 
prefect_gcp.utilities.slugify_name
. If the worker has to change the name, it logs a warning. - Those warnings can be triggered by ANY of the names used to compose the job name, not just your flow run name. In practice, underscores, spaces, uppercase, and long names in your deployment name or flow name commonly cause the warnings even when the run name looks clean. What to try/check 1) Ensure you’re setting the run name on the flow (and not expecting 
.deploy()
to do it):
Copy code
from datetime import datetime
from prefect import flow

@flow(flow_run_name=lambda: f"dbt-run-24h-{datetime.utcnow().strftime('%Y-%m-%d-%H-%M-%S')}")
def my_flow():
    ...
- Using a callable avoids any templating braces ending up in the final string and guarantees the final run name only includes the characters you return. 2) Check your other names that may be used in the worker’s job name: - Deployment name - Flow name (function name or 
@flow(name=...)
) - Work pool and work queue names Make sure they only use lowercase letters, numbers, and dashes and are reasonably short. Avoid underscores and spaces. Example:
Copy code
# Good
name="dbt-daily-run"

# Risky (triggers slugify + warning)
name="DBT Daily_Run"
3) Keep names short - The GCP worker will truncate names with 
slugify_name
(default max length is limited) and can warn when truncating/sanitizing. Keep names reasonably short to avoid truncation warnings. 4) Turn on debug to see what’s being sanitized - Run your worker with a higher log level to see the exact “before” and “after” name:
Copy code
export PREFECT_LOGGING_LEVEL=DEBUG
# then start your worker as usual
This will usually reveal whether it’s your deployment name, flow name, or run name being altered. Reference docs - GCP worker guide: prefect-gcp worker guide - Custom metadata and run names: Custom metadata and naming If you can share: - the exact warning text, - your worker type, - the flow decorator snippet (where you set 
flow_run_name
), - and your deployment name/work pool name, I can identify which name is triggering the warning and suggest a precise fix.
j
@Marvin: Ok, let me recap. I have upgraded from 
cloud-run:push
workpool to 
cloud-run-v2:push
workpool. The flow run executions start as intended but they give warning:
Copy code
Unable to check status of flow run: <HttpError 404 when requesting <https://run.googleapis.com/v2/projects/project-name/locations/europe-north1/jobs/prefect-dbt-run-24h-2025-10-07-06-49-54/executions/prefect-sceptical-ocelot-5mwsr?alt=json> returned "Resource 'prefect-sceptical-ocelot-5mwsr' of kind 'EXECUTION' in region 'europe-north1' in project 'project-name' with parent 'prefect-dbt-run-24h-2025-10-07-06-49-54' does not exist.".
I have confirmed the related job 
prefect-sceptical-ocelot-5mwsr
exists in Cloud Run job pool and executes without warnings in Cloud Run logs. So the warning only appears in Prefect UI when checking flow run logs. I'm using:
Copy code
prefect==3.4.12
prefect-gcp==0.6.10
m
✅ thought for 131.0 seconds
Thanks for the thorough recap — that helps. What your error shows - Prefect is polling Cloud Run v2 at: projects/project-name/locations/europe-north1/jobs/prefect-dbt-run-24h-2025-10-07-06-49-54/executions/prefect-sceptical-ocelot-5mwsr - Cloud Run replies 404 saying that execution name under that parent job does not exist. - You’re seeing that a job named prefect-sceptical-ocelot-5mwsr does exist and is running fine. This strongly suggests the job and execution names are being mixed up in the status polling for Cloud Run v2 push runs: the job actually created is prefect-sceptical-ocelot-5mwsr, while Prefect is trying to poll an execution with that name under a different job (prefect-dbt-run-24h-...), which explains the 404 even though the run executes successfully. Quick verification Run these to confirm which one is the real job vs execution: - List jobs
Copy code
gcloud run jobs list --region europe-north1 --project project-name
- Check executions under each suspected job
Copy code
gcloud run jobs executions list --job prefect-dbt-run-24h-2025-10-07-06-49-54 --region europe-north1 --project project-name
gcloud run jobs executions list --job prefect-sceptical-ocelot-5mwsr --region europe-north1 --project project-name
You should see executions under the sceptical-ocelot job, and none under the dbt-run job name. That will confirm the mismatch. Why this happens - In Cloud Run v2, a Job resource has Executions created under it when run. - With prefect-gcp 0.6.10 on push pools, there appears to be a mismatch in how the job name and execution identifier are recorded and later used to poll status. Your custom flow run name (prefect-dbt-run-24h-...) is being used where the job name should be, while the friendly slug (prefect-sceptical-ocelot-...) is used as the execution id — reversed compared to what Cloud Run expects. Recommended next steps - Try upgrading to the latest prefect-gcp and Prefect 3.x. There have been steady improvements to workers and status polling: - Prefect GCP worker guide: GCP worker guide - Prefect how-to on naming/metadata: Custom metadata and naming - As a temporary workaround, if you need to eliminate the warning immediately: - Consider switching back to the cloud-run:push pool until you can upgrade. - Or, set a consistent job name via your work pool’s default variables to ensure the actual Job name matches what Prefect is polling. If you have a “name” or “name_prefix” field for Cloud Run v2 jobs in your work pool default variables, try aligning it with your flow run name template (lowercase, dashes only, short). This may avoid the swapped-name condition. If you share a screenshot of your Cloud Run v2 pool’s default variables, I can suggest exact values. To help us get a precise fix If you can share: - The output of the gcloud commands above (just the names), - Your work pool type exactly (“cloud-run-v2:push”) and pool default variables (redact secrets), - Your flow decorator snippet where you set 
flow_run_name
, - The deployment name you’re using, I can reproduce and open a targeted bug with the prefect-gcp team. The runs are healthy; this is a polling/lookup issue that we should correct so the warning goes away.
j
@Marvin: I started a new run 
theta848-alphecca-quadrant
that was renamed automatically in the UI to 
dbt-run-24h-2025-10-07-08-19-00
. I run the debuggin gcloud commands and got:
Copy code
JOB                                 REGION         LAST RUN AT              CREATED                  CREATED BY
prefect-theta848-alphecca-quadrant  europe-north1  2025-10-07 08:18:02 UTC  2025-10-07 08:17:57 UTC  <mailto:service-prefect-cr-wp-test@sok-gdw-main-test.iam.gserviceaccount.com|service-prefect-cr-wp-test@sok-gdw-main-test.iam.gserviceaccount.com>
And when checking the executions under that name, I get:
Copy code
JOB                                 EXECUTION                                 REGION         RUNNING  COMPLETE  CREATED                  RUN BY
…  prefect-theta848-alphecca-quadrant  prefect-theta848-alphecca-quadrant-7n94g  europe-north1  1        0 / 1     2025-10-07 08:18:02 UTC  <mailto:service-prefect-cr-wp-test@sok-gdw-main-test.iam.gserviceaccount.com|service-prefect-cr-wp-test@sok-gdw-main-test.iam.gserviceaccount.com>
The error is now:
Copy code
Unable to check status of flow run: <HttpError 404 when requesting <https://run.googleapis.com/v2/projects/project-name/locations/europe-north1/jobs/prefect-dbt-run-24h-2025-10-07-08-19-00/executions/prefect-theta848-alphecca-quadrant-7n94g?alt=json> returned "Resource 'prefect-theta848-alphecca-quadrant-7n94g' of kind 'EXECUTION' in region 'europe-north1' in project 'project-name' with parent 'prefect-dbt-run-24h-2025-10-07-08-19-00' does not exist.".
Does that mean that the flow and execution names are mixed? How to fix this?
m
✅ thought for 109.4 seconds
Short answer: yes — Cloud Run v2 job/execution names are being mixed during status polling. What your gcloud output shows - Actual Cloud Run Job: 
prefect-theta848-alphecca-quadrant
- Actual Execution: 
prefect-theta848-alphecca-quadrant-7n94g
- Prefect is polling: parent Job 
prefect-dbt-run-24h-2025-10-07-08-19-00
with execution 
prefect-theta848-alphecca-quadrant-7n94g
So Prefect is using the current flow run name as the Cloud Run Job parent, but the worker created the Job under the original/default slug name. That explains the 404 even though the run is healthy. Why this is happening - In Cloud Run v2, executions are nested under a specific Job. - With CloudRun v2 push, there’s a mismatch between the name Prefect stores/uses for polling and the name actually used to create the Cloud Run Job when your flow run is renamed at start (e.g., via 
flow_run_name
). Workarounds to stop the warnings - Easiest: temporarily remove your custom 
flow_run_name
so the flow run keeps the default slug (e.g., 
theta848-alphecca-quadrant
). That should make the polled Job parent match the actual Job and eliminate the 404 warnings. - Alternatively, roll back to the 
cloud-run:push
work pool until a fix is available for v2. - If you rely on custom names, try updating to the latest Prefect 3.x and prefect-gcp versions; there have been ongoing worker/polling improvements. GCP worker guide: GCP worker guide. Custom metadata and naming: Custom metadata and naming. Next steps I can take - If you can confirm that removing 
flow_run_name
makes the warning disappear, I’ll summarize this as a reproducible bug and open a thread with the team. If you’re okay with it, I can also create a GitHub Discussion to track it publicly so others can follow the fix. - If you prefer to keep the custom run name, I can help you test a few worker variable tweaks — but given Cloud Run v2’s naming handling, the reliable immediate fix is to avoid renaming the flow run until the polling logic stores/uses the actual Job name created by the worker. Want me to file a summary for the Prefect team with your reproduction steps and the gcloud outputs you shared?
2 Views
Open in Slack
PreviousNext
Powered by