Skip to content

Retain complete paper-batch inputs before final projection #385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
witbrock merged 1 commit into from
Aug 16, 2026
Merged

Retain complete paper-batch inputs before final projection #385

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion ...flows/repo_seed_bundles/email_source_representation_convergence_workflow_seed_bundle.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"family_id": "email_source_representation_convergence_workflow_seed_bundle",
"managed_by": "email_source_representation_convergence_workflow_vontology_service",
"schema_version": "repo_seed_workflow_bundle.v1",
"seed_version": "16",
"seed_version": "17",
"source_tag": "JVNAUTOSCI-2635",
"supported_action_ids": [
"arxiv.inspect_existing_state",
Expand Down Expand Up @@ -537,6 +537,20 @@
],
"execution_mode": "deterministic",
"on_failure_state": "failed",
"reads_context_keys": [
"gmail_profile",
"effective_gmail_query",
"gmail_max_results",
"message_item_count",
"message_selected_item_count",
"message_unattempted_count",
"message_success_count",
"message_error_count",
"message_partial_success",
"message_final_state_counts",
"message_iteration_results",
"message_iteration_errors"
],
"state_id": "project_batch_result",
"static_input_bindings": [
[
Expand Down
45 changes: 30 additions & 15 deletions tests/backend/test_email_source_representation_convergence_bootstrap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -857,27 +857,42 @@ def test_parent_batch_result_is_lossless_across_durable_checkpoints() -> None:
)[mod.ZHAN_GMAIL_ARXIV_INGESTION_WORKFLOW_ID]
lossless_keys = _execution_required_checkpoint_context_keys(definition)
assert "batch_result" in lossless_keys
assert "message_iteration_results" in lossless_keys
assert "message_iteration_errors" in lossless_keys

batch_result = {
"schema_version": "gmail_arxiv_batch_result.v1",
"items": [
{
"index": index,
"source_item_id": f"gmail-message-{index + 1}",
"paper_concept_ids": [f"#V#paper_{index + 1}"],
"evidence": "x" * 200,
}
for index in range(100)
],
}
iteration_results = [
{
"index": index,
"source_item_id": f"gmail-message-{index + 1}",
"paper_concept_ids": [f"#V#paper_{index + 1}"],
"evidence": "x" * 200,
}
for index in range(100)
]
iteration_errors = [
{
"index": 99,
"source_item_id": "gmail-message-100",
"error": "file_copy_type_not_visible_to_actor",
"details": {"stage": "file_copy_typing", "retryable": True},
}
]
projected = project_workflow_context_for_checkpoint(
{"batch_result": batch_result},
{
"message_iteration_results": iteration_results,
"message_iteration_errors": iteration_errors,
},
max_value_bson_bytes=512,
max_total_bson_bytes=512,
lossless_keys=lossless_keys,
)

assert projected["batch_result"] == batch_result
assert len(projected["batch_result"]["items"]) == 100
assert projected["message_iteration_results"] == iteration_results
assert len(projected["message_iteration_results"]) == 100
assert projected["message_iteration_errors"] == iteration_errors
assert projected["message_iteration_errors"][0]["error"] == (
"file_copy_type_not_visible_to_actor"
)


def test_email_source_seed_routes_exact_message_unit_and_explicit_batch() -> None:
Expand Down
Loading