Link automation.action.* events to automation.triggered event

[tomerqodo]

Benchmark PR from agentic-review-benchmarks#2

[qodo-code-review]

Code Review by Qodo

🐞 Bugs (0) 📘 Rule violations (4) 📎 Requirement gaps (0)

1. triggers.py missing future annotations 📘 Rule violation ✓ Correctness

Description

• src/prefect/server/events/triggers.py contains type annotations (including PEP604 unions like
  UUID | None) but does not include from __future__ import annotations as the first import.
• This violates the repository rule for consistent forward-reference behavior and type-checking
  performance across src/ Python files.
• It can also create subtle typing/runtime differences compared to other modules that follow the
  required pattern.

Code

src/prefect/server/events/triggers.py[R439-456]

+    # Determine the primary state change event ID for linking action events back to
+    # the automation.triggered or automation.resolved event. Prefer Triggered over
+    # Resolved when both are present.
+    primary_state_change_event = state_change_events.get(
+        TriggerState.Triggered
+    ) or state_change_events.get(TriggerState.Resolved)
+    primary_state_change_event_id = (
+        primary_state_change_event.id if primary_state_change_event else None
+    )
+
+    # By default, all `automation.actions` are fired. Each tuple contains:
+    # (triggering_event, action, automation_triggered_event_id)
+    source_actions: List[
+        Tuple[Optional[ReceivedEvent], ServerActionTypes, UUID | None]
+    ] = [
+        (firing.triggering_event, action, primary_state_change_event_id)
+        for action in automation.actions
    ]

Evidence

The compliance rule requires from __future__ import annotations at the top of any src/ Python
file that uses type hints. The file uses annotated variables/types in the changed hunk, and the file
header shows the import is missing.

AGENTS.md
src/prefect/server/events/triggers.py[1-24]
src/prefect/server/events/triggers.py[439-456]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`src/prefect/server/events/triggers.py` uses type annotations but does not include `from __future__ import annotations` as the first import, violating the required typing convention for `src/`.

## Issue Context
The repository compliance rule mandates this import in any `src/` Python module that contains type annotations.

## Fix Focus Areas
- src/prefect/server/events/triggers.py[1-24]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

2. automation_triggered_event_id uses field_validator 📘 Rule violation ✓ Correctness

Description

• TriggeredAction enforces a cross-field constraint (automation_triggered_event_id depends on
  triggering_event) via @field_validator, which is not the approved approach for cross-field
  validation.
• This violates the requirement to use @model_validator for validations that depend on multiple
  fields.
• Keeping cross-field logic in a field validator can lead to order-dependent behavior and
  missed/incorrect validation during model construction.

Code

src/prefect/server/events/schemas/automations.py[R772-780]

+    @field_validator("automation_triggered_event_id")
+    @classmethod
+    def validate_automation_triggered_event_id(cls, v, info):
+        """Ensure automation_triggered_event_id is only set when triggering_event exists."""
+        if v is not None and info.data.get("triggering_event") is None:
+            raise ValueError(
+                "automation_triggered_event_id can only be set when triggering_event is provided"
+            )
+        return v

Evidence

The checklist explicitly requires cross-field validation to be implemented with @model_validator.
The added validator checks info.data.get("triggering_event"), meaning it depends on another field,
but is implemented as a @field_validator.

AGENTS.md
src/prefect/server/events/schemas/automations.py[763-780]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`TriggeredAction` performs cross-field validation using `@field_validator`, which violates the requirement to use `@model_validator` for logic that depends on multiple fields.

## Issue Context
The validator checks `triggering_event` while validating `automation_triggered_event_id`, which is cross-field validation.

## Fix Focus Areas
- src/prefect/server/events/schemas/automations.py[763-780]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

3. automation_triggered_event_id set with None triggering_event 📘 Rule violation ⛯ Reliability

Description

• act() always passes a non-null primary_state_change_event_id into
  TriggeredAction.automation_triggered_event_id even when triggering_event is None (e.g.,
  proactive triggers).
• With the newly added validation, this can raise ValueError and break action publishing instead
  of handling the None edge case gracefully.
• This violates the robustness requirement to explicitly handle null/empty edge cases at potential
  failure points.

Code

src/prefect/server/events/triggers.py[R449-456]

+    # By default, all `automation.actions` are fired. Each tuple contains:
+    # (triggering_event, action, automation_triggered_event_id)
+    source_actions: List[
+        Tuple[Optional[ReceivedEvent], ServerActionTypes, UUID | None]
+    ] = [
+        (firing.triggering_event, action, primary_state_change_event_id)
+        for action in automation.actions
    ]

Evidence

The act() change constructs tuples where the first element is Optional[ReceivedEvent] (can be
None) while the third element is the state-change event id (typically present). The new validator
rejects any non-null automation_triggered_event_id when triggering_event is absent, creating an
unhandled None edge case leading to a raised exception.

Rule 3: Generic: Robust Error Handling and Edge Case Management
src/prefect/server/events/triggers.py[449-456]
src/prefect/server/events/schemas/automations.py[772-780]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`act()` can construct `TriggeredAction` objects with `triggering_event=None` while still setting `automation_triggered_event_id`, which (with the new validator) raises an exception instead of gracefully handling this edge case.

## Issue Context
This can happen for proactive triggers where there is no external triggering event, but state-change events still exist.

## Fix Focus Areas
- src/prefect/server/events/triggers.py[439-489]
- src/prefect/server/events/schemas/automations.py[763-780]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

View more (1)

4. action.triggered missing related links 📘 Rule violation ✧ Quality

Description

• In the failure path, fail() builds related_resources including automation-triggered-event
  and triggering-event, but then emits the prefect.automation.action.triggered event with
  related=self._resulting_related_resources instead of the enriched related_resources.
• This prevents consumers from reliably tracing the full causal chain for failed actions at the
  moment the action was triggered, weakening audit/trace reconstruction.
• This violates the audit trail requirement to log critical actions with sufficient context to
  reconstruct events.

Code

src/prefect/server/events/actions.py[R199-205]

                    occurred=triggered_action.triggered,
                    event="prefect.automation.action.triggered",
                    resource=resource,
-                    related=related_resources,
+                    related=self._resulting_related_resources,
                    payload=action_details,
                    id=triggered_event_id,
                    follows=follows_id,

Evidence

The compliance rule requires audit records to include essential context to reconstruct what
happened. The code clearly constructs an enriched related_resources list, but the emitted
prefect.automation.action.triggered event does not use it, dropping the linking context needed for
tracing.

Rule 1: Generic: Comprehensive Audit Trails
src/prefect/server/events/actions.py[177-206]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
In `fail()`, the enriched `related_resources` is constructed but not used for the emitted `prefect.automation.action.triggered` event, dropping traceability context.

## Issue Context
This reduces audit/trace reconstruction quality for failed actions because the triggered event lacks the expected related links.

## Fix Focus Areas
- src/prefect/server/events/actions.py[177-206]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

ⓘ The new review experience is currently in Beta. Learn more

[qodo-code-review]

1. triggers.py missing future annotations 📘 Rule violation ✓ Correctness

• src/prefect/server/events/triggers.py contains type annotations (including PEP604 unions like
  UUID | None) but does not include from __future__ import annotations as the first import.
• This violates the repository rule for consistent forward-reference behavior and type-checking
  performance across src/ Python files.
• It can also create subtle typing/runtime differences compared to other modules that follow the
  required pattern.

Agent prompt

## Issue description
`src/prefect/server/events/triggers.py` uses type annotations but does not include `from __future__ import annotations` as the first import, violating the required typing convention for `src/`.

## Issue Context
The repository compliance rule mandates this import in any `src/` Python module that contains type annotations.

## Fix Focus Areas
- src/prefect/server/events/triggers.py[1-24]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

2. automation_triggered_event_id uses field_validator 📘 Rule violation ✓ Correctness

• TriggeredAction enforces a cross-field constraint (automation_triggered_event_id depends on
  triggering_event) via @field_validator, which is not the approved approach for cross-field
  validation.
• This violates the requirement to use @model_validator for validations that depend on multiple
  fields.
• Keeping cross-field logic in a field validator can lead to order-dependent behavior and
  missed/incorrect validation during model construction.

Agent prompt

## Issue description
`TriggeredAction` performs cross-field validation using `@field_validator`, which violates the requirement to use `@model_validator` for logic that depends on multiple fields.

## Issue Context
The validator checks `triggering_event` while validating `automation_triggered_event_id`, which is cross-field validation.

## Fix Focus Areas
- src/prefect/server/events/schemas/automations.py[763-780]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

3. automation_triggered_event_id set with none triggering_event 📘 Rule violation ⛯ Reliability

• act() always passes a non-null primary_state_change_event_id into
  TriggeredAction.automation_triggered_event_id even when triggering_event is None (e.g.,
  proactive triggers).
• With the newly added validation, this can raise ValueError and break action publishing instead
  of handling the None edge case gracefully.
• This violates the robustness requirement to explicitly handle null/empty edge cases at potential
  failure points.

Agent prompt

## Issue description
`act()` can construct `TriggeredAction` objects with `triggering_event=None` while still setting `automation_triggered_event_id`, which (with the new validator) raises an exception instead of gracefully handling this edge case.

## Issue Context
This can happen for proactive triggers where there is no external triggering event, but state-change events still exist.

## Fix Focus Areas
- src/prefect/server/events/triggers.py[439-489]
- src/prefect/server/events/schemas/automations.py[763-780]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[qodo-code-review]

4. action.triggered missing related links 📘 Rule violation ✧ Quality

• In the failure path, fail() builds related_resources including automation-triggered-event
  and triggering-event, but then emits the prefect.automation.action.triggered event with
  related=self._resulting_related_resources instead of the enriched related_resources.
• This prevents consumers from reliably tracing the full causal chain for failed actions at the
  moment the action was triggered, weakening audit/trace reconstruction.
• This violates the audit trail requirement to log critical actions with sufficient context to
  reconstruct events.

Agent prompt

## Issue description
In `fail()`, the enriched `related_resources` is constructed but not used for the emitted `prefect.automation.action.triggered` event, dropping traceability context.

## Issue Context
This reduces audit/trace reconstruction quality for failed actions because the triggered event lacks the expected related links.

## Fix Focus Areas
- src/prefect/server/events/actions.py[177-206]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools