Conversation
❌ Deploy Preview for antenna-preview failed. Why did it fail? →
|
❌ Deploy Preview for antenna-ssec failed. Why did it fail? →
|
📝 WalkthroughWalkthroughAdded processing status tracking for source images across database, API, and UI layers. Introduces queryset methods to annotate processed state, creates null detections for unprocessed images, and exposes processed image counts via API serialization and timeline visualizations. Changes
Sequence DiagramsequenceDiagram
participant Pipeline as ML Pipeline
participant SaveResults as save_results()
participant DB as Database<br/>(Models)
participant API as API Layer<br/>(Views/Serializers)
participant UI as Frontend UI
Pipeline->>SaveResults: Returns detection results
SaveResults->>SaveResults: Create null detections<br/>for unprocessed images
SaveResults->>DB: Save all detections<br/>(including null bbox)
DB->>DB: Annotate was_processed<br/>via Detection.Exists()
DB->>DB: Count processed images<br/>distinct by image
API->>DB: Query with annotations
DB-->>API: Return annotated data<br/>(was_processed, counts)
API->>API: Serialize processed_count,<br/>was_processed fields
API-->>UI: Expose in JSON responses
UI->>UI: Render activity plot<br/>with processed series
UI->>UI: Display processed counts<br/>in capture-set table
Estimated Code Review Effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly Related PRs
Suggested Reviewers
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
vanessavmac
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
ami/main/api/views.py (1)
378-439:⚠️ Potential issue | 🟠 MajorFix
was_processedfor empty intervals (and avoid stale values).Line 439 uses
imageafter the loop; for intervals with no captures (or events with zero captures) this either reuses the prior interval’s image or can crash. Accumulate during the loop and keep False when no captures.🐛 Suggested fix
@@ while image_index < len(source_images) and source_images[image_index]["timestamp"] <= interval_end: image = source_images[image_index] @@ if image["detections_count"] >= max(interval_data["detection_counts"]): interval_data["top_capture"] = SourceImage(pk=image["id"]) + interval_data["was_processed"] = interval_data["was_processed"] or image["was_processed"] image_index += 1 @@ - interval_data["was_processed"] = image["was_processed"] + # was_processed already accumulated; remain False when no captures
🤖 Fix all issues with AI agents
In `@ami/main/models.py`:
- Around line 1839-1841: Remove the redundant Q(bbox=None) in
get_detections_count() (keep Q(bbox__isnull=True) and the empty-list check
Q(bbox=[])) and then make update_detection_counts() use the same exclusion
filter as get_detections_count() so the cached detections_count is computed
consistently; specifically, update the counting logic in
update_detection_counts() to apply .exclude(Q(bbox__isnull=True) | Q(bbox=[]))
on self.detections before calling .count() so both methods return the same
value.
In `@ami/ml/models/pipeline.py`:
- Around line 882-888: The loop that assigns detector_algorithm_reference over
algorithms_known currently overwrites when multiple detection algorithms exist;
update the logic in the section that iterates algorithms_known to make selection
deterministic or to emit a null detection per detector: either pick one
deterministic algorithm (e.g., lowest key or sorted by name) and log/warn when
multiple AlgorithmTaskType.DETECTION entries are present, or instead create an
AlgorithmReference for each known_algorithm with task_type DETECTION (rather
than a single detector_algorithm_reference) so downstream checks use
per-detector null detections; modify the code around
detector_algorithm_reference, algorithms_known and AlgorithmReference
accordingly and add a warning using the existing logger when multiple detectors
are found.
- Around line 896-902: The appended null detection currently uses a naive
timestamp via datetime.datetime.now(); update the DetectionResponse creation
inside the null_detections_to_add.append call to use the timezone-aware now()
function (already imported and used elsewhere) instead of
datetime.datetime.now(), ensuring the timestamp field for DetectionResponse is
timezone-aware and consistent with other parts of the pipeline.
In `@ui/src/data-services/models/collection.ts`:
- Around line 93-101: Rename the getter numImagesProccessed to
numImagesProcessedLabel in the Collection model so the name is spelled correctly
and follows the "*Label" convention; update the getter implementation (currently
computing numProcessed, pct and returning the formatted string) to the new name,
then find and replace all usages (e.g., any occurrences of
item.numImagesProccessed such as in collection-columns.tsx) to
item.numImagesProcessedLabel, and update any type declarations/exports or tests
that reference the old symbol to the new one to ensure no unresolved references
remain.
In `@ui/src/pages/session-details/playback/activity-plot/activity-plot.tsx`:
- Around line 71-96: The "Was processed" trace currently maps wasProcessed→0/1
onto yaxis 'y2' (shared with detectionsMaxCount) so it becomes invisible when
detectionsMaxCount is large and the mapping is inverted; fix by either (A)
giving this trace its own y-axis (e.g., set yaxis: 'y3' and add a yaxis config
with fixed range [0,1]) and keep y as wasProcessed ? 0 : 1 but rename the trace
to "Not processed" (or add a clarifying comment about the inversion), or (B)
scale the y values to the detections axis by mapping y: timeline.map(t =>
t.numCaptures>0 ? (t.wasProcessed ? 0 : detectionsMaxCount) : 0) and keep the
name "Not processed" (or invert the boolean mapping and rename to "Was
processed" accordingly); update hover/customdata text to match the chosen
semantics.
🧹 Nitpick comments (3)
ui/src/data-services/models/timeline-tick.ts (1)
35-37: Consider adding a nullish fallback forwasProcessed, consistent with other getters.Other getters in this class (e.g.,
numDetections,numCaptures) use?? 0/?? falseto guard against missing server data. Ifwas_processedis absent from the API response (e.g., during rollout or with an older API version), this will returnundefinedinstead offalse.Suggested fix
get wasProcessed(): boolean { - return this._timelineTick.was_processed + return this._timelineTick.was_processed ?? false }ami/main/admin.py (1)
256-269: Reduce admin list N+1 by annotatingwas_processed.
get_was_processedin list_display can trigger a query per row. Consider annotating inget_querysetand reading the annotation in an admin method.♻️ Suggested adjustment
@@ def get_queryset(self, request: HttpRequest) -> QuerySet[Any]: - return super().get_queryset(request).select_related("event", "deployment", "deployment__data_source") + return ( + super() + .get_queryset(request) + .select_related("event", "deployment", "deployment__data_source") + .with_was_processed() + ) + + `@admin.display`(boolean=True, ordering="was_processed", description="Was processed") + def get_was_processed(self, obj: SourceImage) -> bool: + return getattr(obj, "was_processed", obj.get_was_processed())ami/main/models.py (1)
3725-3734: Samebbox=None/bbox__isnull=Trueredundancy as inget_detections_count.
~models.Q(images__detections__bbox__isnull=True)and~models.Q(images__detections__bbox=None)produce identical SQL. One can be removed for clarity.Simplify the filter
source_images_with_detections_count=models.Count( "images", filter=( models.Q(images__detections__isnull=False) & ~models.Q(images__detections__bbox__isnull=True) - & ~models.Q(images__detections__bbox=None) & ~models.Q(images__detections__bbox=[]) ), distinct=True, )
ami/ml/models/pipeline.py
Outdated
There was a problem hiding this comment.
Make detector selection deterministic (or create one null detection per detector).
If a pipeline has multiple detection algorithms, the loop currently overwrites the reference, which can make algorithm-specific processed checks unreliable. Consider selecting deterministically and warning, or emitting one null detection per detector.
🛠️ Example deterministic selection
- detector_algorithm_reference = None
- for known_algorithm in algorithms_known.values():
- if known_algorithm.task_type == AlgorithmTaskType.DETECTION:
- detector_algorithm_reference = AlgorithmReference(
- name=known_algorithm.name, key=known_algorithm.key
- )
+ detector_algorithms = [
+ algo for algo in algorithms_known.values() if algo.task_type == AlgorithmTaskType.DETECTION
+ ]
+ if len(detector_algorithms) > 1:
+ job_logger.warning(
+ "Multiple detection algorithms found; using the first for null detections."
+ )
+ detector_algorithm_reference = (
+ AlgorithmReference(name=detector_algorithms[0].name, key=detector_algorithms[0].key)
+ if detector_algorithms
+ else None
+ )📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| detector_algorithm_reference = None | |
| for known_algorithm in algorithms_known.values(): | |
| if known_algorithm.task_type == AlgorithmTaskType.DETECTION: | |
| detector_algorithm_reference = AlgorithmReference( | |
| name=known_algorithm.name, key=known_algorithm.key | |
| ) | |
| detector_algorithms = [ | |
| algo for algo in algorithms_known.values() if algo.task_type == AlgorithmTaskType.DETECTION | |
| ] | |
| if len(detector_algorithms) > 1: | |
| job_logger.warning( | |
| "Multiple detection algorithms found; using the first for null detections." | |
| ) | |
| detector_algorithm_reference = ( | |
| AlgorithmReference(name=detector_algorithms[0].name, key=detector_algorithms[0].key) | |
| if detector_algorithms | |
| else None | |
| ) |
🤖 Prompt for AI Agents
In `@ami/ml/models/pipeline.py` around lines 882 - 888, The loop that assigns
detector_algorithm_reference over algorithms_known currently overwrites when
multiple detection algorithms exist; update the logic in the section that
iterates algorithms_known to make selection deterministic or to emit a null
detection per detector: either pick one deterministic algorithm (e.g., lowest
key or sorted by name) and log/warn when multiple AlgorithmTaskType.DETECTION
entries are present, or instead create an AlgorithmReference for each
known_algorithm with task_type DETECTION (rather than a single
detector_algorithm_reference) so downstream checks use per-detector null
detections; modify the code around detector_algorithm_reference,
algorithms_known and AlgorithmReference accordingly and add a warning using the
existing logger when multiple detectors are found.
ami/ml/models/pipeline.py
Outdated
There was a problem hiding this comment.
this loop over known_algorithms doesn't need to happen per-image and could be pulled out. I.e, you could find the known_detection_algorithm before looping the images. Do pipelines allow more than one detection algorithm? If so then I agree with coderrabit comment below. If not you could assert here that only one detection algo is found.
There was a problem hiding this comment.
Do pipelines allow more than one detection algorithm?
I think at the moment we only have one detection algorithm per pipeline. But maybe @mihow could confirm and comment here?
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
ami/ml/models/pipeline.py (1)
939-944:⚠️ Potential issue | 🟠 MajorNull detections incorrectly create empty
Occurrencerecords.
create_and_update_occurrences_for_detectionsreceives the fulldetectionslist, which includes null Detection objects (wherebbox=None). For each null detection without a pre-existing occurrence, it bulk-creates anOccurrencewith event, deployment, and project set but no taxon or determination. These phantom occurrences are semantically wrong — a null detection means "no animal found" — and persist in theOccurrencetable. Some API endpoints filter out these empty occurrences (checkingdetermination__isnull=False), but the core queryset.valid()only excludes occurrences with zero detections, allowing these to inflate counts in certain views. Filter out null detections before creating occurrences:🛠️ Proposed fix in
save_results+ real_detections = [d for d in detections if d.bbox is not None] create_and_update_occurrences_for_detections( - detections=detections, + detections=real_detections, logger=job_logger, )🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@ami/ml/models/pipeline.py` around lines 939 - 944, The code passes the full detections list (including null detections with bbox=None) into create_and_update_occurrences_for_detections which creates empty Occurrence records; filter the detections before calling that function (e.g., in save_results) by keeping only detections where bbox is not None (or detection is truthy) and then call create_and_update_occurrences_for_detections with that filtered list so null detections are ignored and no phantom Occurrence rows are created.
🧹 Nitpick comments (1)
ui/src/data-services/models/capture-set.ts (1)
82-101:numImagesWithDetectionsLabelcan render"undefined (0%)"— worth aligning with the new pattern.The new
numImagesProcessedLabelcorrectly defaultsnumProcessedto0via?? 0, so it never emits the string"undefined". The adjacent, pre-existingnumImagesWithDetectionsLabelusesthis.numImagesWithDetections?.toLocaleString()without a fallback; whennumImagesWithDetectionsisundefined, the template literal produces the literal string"undefined (0%)"in the rendered cell.Since the new getter sets the correct precedent, consider aligning
numImagesWithDetectionsLabelfor consistency:♻️ Proposed alignment for numImagesWithDetectionsLabel
get numImagesWithDetectionsLabel(): string { + const numWithDetections = this.numImagesWithDetections ?? 0 const pct = - this.numImagesWithDetections && this.numImages - ? (this.numImagesWithDetections / this.numImages) * 100 + this.numImages && this.numImages > 0 + ? (numWithDetections / this.numImages) * 100 : 0 - return `${this.numImagesWithDetections?.toLocaleString()} (${pct.toFixed( - 0 - )}%)` + return `${numWithDetections.toLocaleString()} (${pct.toFixed(0)}%)` }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@ui/src/data-services/models/capture-set.ts` around lines 82 - 101, The getter numImagesWithDetectionsLabel can produce "undefined (0%)" because it calls this.numImagesWithDetections?.toLocaleString() without a fallback; update it to mirror numImagesProcessedLabel by defaulting numImagesWithDetections to 0 (use the nullish coalescing operator, e.g. const numWithDetections = this.numImagesWithDetections ?? 0), compute pct from numWithDetections and this.numImages, and use numWithDetections.toLocaleString() in the returned template so the label never renders "undefined".
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@ami/main/models.py`:
- Around line 3741-3744: Remove the redundant null-checks in the queryset: drop
the negated Q(models.Q(images__detections__bbox=None)) since
Q(...__bbox__isnull=True) and Q(...__bbox=None) are equivalent for JSONField,
and also remove the now-unnecessary models.Q(images__detections__isnull=False)
because excluding bbox IS NULL already guarantees a detection row; update the
queryset fragment that currently contains
models.Q(images__detections__isnull=False) &
~models.Q(images__detections__bbox__isnull=True) &
~models.Q(images__detections__bbox=None) &
~models.Q(images__detections__bbox=[]) to only keep the meaningful predicates
(e.g., ~models.Q(images__detections__bbox__isnull=True) and
~models.Q(images__detections__bbox=[])).
In `@ami/ml/models/pipeline.py`:
- Around line 917-924: filter_processed_images is incorrectly treating the null
placeholder detections (created by create_null_detections_for_undetected_images,
which use detections with bbox=None) as "unprocessed" because they have no
classifications; add a branch in filter_processed_images before the existing
classifications__isnull check that detects when existing_detections consists
only of null detections (e.g., all detections have bbox==None or an equivalent
null marker) and treat that case as "processed - no animal found" so the image
is skipped on subsequent runs; update any comments/tests to reflect that
null-only detection sets should not cause re-queuing.
- Around line 830-834: The int() casts on detection.source_image_id and
source_img.id can raise ValueError for non-numeric IDs; change the membership
check to use string comparison instead of int conversion by building
source_images_with_detections from str(detection.source_image_id) (iterating
results.detections) and comparing against str(source_img.id) when iterating
results.source_images (or otherwise guard the cast with a try/except and fall
back to string comparison) so comparisons are robust for UUIDs and other
non-integer IDs.
In `@ui/src/pages/project/capture-sets/capture-set-columns.tsx`:
- Around line 113-114: The renderCell parameter is typed as Collection but that
type isn't imported—replace the incorrect type with CaptureSet (i.e., change the
renderCell signature from item: Collection to item: CaptureSet) to match the
other renderCell entries and ensure CaptureSet is imported at the top of the
file so the BasicTableCell usage of item.numImagesProcessedLabel compiles.
---
Outside diff comments:
In `@ami/ml/models/pipeline.py`:
- Around line 939-944: The code passes the full detections list (including null
detections with bbox=None) into create_and_update_occurrences_for_detections
which creates empty Occurrence records; filter the detections before calling
that function (e.g., in save_results) by keeping only detections where bbox is
not None (or detection is truthy) and then call
create_and_update_occurrences_for_detections with that filtered list so null
detections are ignored and no phantom Occurrence rows are created.
---
Duplicate comments:
In `@ami/ml/models/pipeline.py`:
- Around line 835-840: The loop over algorithms_known silently lets the last
detection algorithm win; modify the logic in the block that sets
detector_algorithm_reference so that if a second AlgorithmTaskType.DETECTION is
encountered (i.e., detector_algorithm_reference is already set) you surface a
clear failure (raise a ValueError/RuntimeError or log+raise) instead of
overwriting; reference the symbols algorithms_known,
AlgorithmTaskType.DETECTION, detector_algorithm_reference, and
AlgorithmReference to implement the check and error with a descriptive message
listing conflicting algorithm names/keys.
---
Nitpick comments:
In `@ui/src/data-services/models/capture-set.ts`:
- Around line 82-101: The getter numImagesWithDetectionsLabel can produce
"undefined (0%)" because it calls this.numImagesWithDetections?.toLocaleString()
without a fallback; update it to mirror numImagesProcessedLabel by defaulting
numImagesWithDetections to 0 (use the nullish coalescing operator, e.g. const
numWithDetections = this.numImagesWithDetections ?? 0), compute pct from
numWithDetections and this.numImages, and use numWithDetections.toLocaleString()
in the returned template so the label never renders "undefined".
| models.Q(images__detections__isnull=False) | ||
| & ~models.Q(images__detections__bbox__isnull=True) | ||
| & ~models.Q(images__detections__bbox=None) | ||
| & ~models.Q(images__detections__bbox=[]) |
There was a problem hiding this comment.
~Q(images__detections__bbox=None) is redundant — same issue patched elsewhere in this PR.
In Django ORM, Q(bbox__isnull=True) and Q(bbox=None) are identical for JSONField: both emit bbox IS NULL. Lines 3742 and 3743 therefore negate the exact same SQL predicate, so the second negation is a no-op. The same redundancy was already corrected in get_detections_count() as part of this PR, but was carried over to this new method.
🛠️ Proposed fix
def with_source_images_with_detections_count(self):
return self.annotate(
source_images_with_detections_count=models.Count(
"images",
filter=(
- models.Q(images__detections__isnull=False)
- & ~models.Q(images__detections__bbox__isnull=True)
- & ~models.Q(images__detections__bbox=None)
- & ~models.Q(images__detections__bbox=[])
+ ~models.Q(images__detections__bbox__isnull=True)
+ & ~models.Q(images__detections__bbox=[])
),
distinct=True,
)
)Q(images__detections__isnull=False) is also redundant once ~Q(bbox__isnull=True) is in place (a non-null bbox already implies a detection row exists).
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ami/main/models.py` around lines 3741 - 3744, Remove the redundant
null-checks in the queryset: drop the negated
Q(models.Q(images__detections__bbox=None)) since Q(...__bbox__isnull=True) and
Q(...__bbox=None) are equivalent for JSONField, and also remove the
now-unnecessary models.Q(images__detections__isnull=False) because excluding
bbox IS NULL already guarantees a detection row; update the queryset fragment
that currently contains models.Q(images__detections__isnull=False) &
~models.Q(images__detections__bbox__isnull=True) &
~models.Q(images__detections__bbox=None) &
~models.Q(images__detections__bbox=[]) to only keep the meaningful predicates
(e.g., ~models.Q(images__detections__bbox__isnull=True) and
~models.Q(images__detections__bbox=[])).
| source_images_with_detections = {int(detection.source_image_id) for detection in results.detections} | ||
| null_detections_to_add = [] | ||
|
|
||
| for source_img in results.source_images: | ||
| if int(source_img.id) not in source_images_with_detections: |
There was a problem hiding this comment.
int() cast can raise ValueError on non-integer source image IDs.
Both int(detection.source_image_id) (line 830) and int(source_img.id) (line 834) will throw if the ID is ever non-numeric (e.g., UUID-based pipelines). The comparison should be done in string space to stay consistent with the schema types, or the cast should be guarded.
🛠️ Proposed fix — compare as strings
- source_images_with_detections = {int(detection.source_image_id) for detection in results.detections}
+ source_images_with_detections = {str(detection.source_image_id) for detection in results.detections}
for source_img in results.source_images:
- if int(source_img.id) not in source_images_with_detections:
+ if str(source_img.id) not in source_images_with_detections:📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| source_images_with_detections = {int(detection.source_image_id) for detection in results.detections} | |
| null_detections_to_add = [] | |
| for source_img in results.source_images: | |
| if int(source_img.id) not in source_images_with_detections: | |
| source_images_with_detections = {str(detection.source_image_id) for detection in results.detections} | |
| null_detections_to_add = [] | |
| for source_img in results.source_images: | |
| if str(source_img.id) not in source_images_with_detections: |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ami/ml/models/pipeline.py` around lines 830 - 834, The int() casts on
detection.source_image_id and source_img.id can raise ValueError for non-numeric
IDs; change the membership check to use string comparison instead of int
conversion by building source_images_with_detections from
str(detection.source_image_id) (iterating results.detections) and comparing
against str(source_img.id) when iterating results.source_images (or otherwise
guard the cast with a try/except and fall back to string comparison) so
comparisons are robust for UUIDs and other non-integer IDs.
| # Ensure all images have detections | ||
| # if not, add a NULL detection (empty bbox) to the results | ||
| null_detections = create_null_detections_for_undetected_images( | ||
| results=results, | ||
| algorithms_known=algorithms_known, | ||
| logger=job_logger, | ||
| ) | ||
| results.detections = results.detections + null_detections |
There was a problem hiding this comment.
Null detections will cause images to be re-queued on every subsequent pipeline run.
filter_processed_images (line 87) yields an image if any existing detection lacks classifications:
elif existing_detections.filter(classifications__isnull=True).exists():
yield imageA null detection (bbox=None) has no classifications, so this condition is always True for it. Every image that was processed and returned no detections will be re-sent on the next job run, defeating the deduplication logic. filter_processed_images needs a new branch before the classifications__isnull check to recognise null-only detections as "processed, no animal found — skip".
🛠️ Proposed fix in filter_processed_images (lines 81–115)
for image in images:
existing_detections = image.detections.filter(detection_algorithm__in=pipeline_algorithms)
+ real_detections = existing_detections.filter(bbox__isnull=False)
+ null_only = existing_detections.exists() and not real_detections.exists()
+
if not existing_detections.exists():
task_logger.debug(f"Image {image} needs processing: has no existing detections from pipeline's detector")
yield image
- elif existing_detections.filter(classifications__isnull=True).exists():
+ elif null_only:
+ task_logger.debug(f"Image {image} was processed with no detections (null detection exists), skipping")
+ continue
+ elif real_detections.filter(classifications__isnull=True).exists():
task_logger.debug(...)
yield image
else:
pipeline_algorithm_ids = set(classification_algorithms.values_list("id", flat=True))
- detection_algorithm_ids = set(existing_detections.values_list("classifications__algorithm_id", flat=True))
+ detection_algorithm_ids = set(real_detections.values_list("classifications__algorithm_id", flat=True))🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ami/ml/models/pipeline.py` around lines 917 - 924, filter_processed_images is
incorrectly treating the null placeholder detections (created by
create_null_detections_for_undetected_images, which use detections with
bbox=None) as "unprocessed" because they have no classifications; add a branch
in filter_processed_images before the existing classifications__isnull check
that detects when existing_detections consists only of null detections (e.g.,
all detections have bbox==None or an equivalent null marker) and treat that case
as "processed - no animal found" so the image is skipped on subsequent runs;
update any comments/tests to reflect that null-only detection sets should not
cause re-queuing.
| renderCell: (item: Collection) => ( | ||
| <BasicTableCell value={item.numImagesProcessedLabel} /> |
There was a problem hiding this comment.
Collection is not defined or imported — TypeScript compilation will fail.
Line 113 uses item: Collection as the renderCell parameter type, but Collection is never imported in this file. Every other renderCell in the same array uses item: CaptureSet. This is a copy-paste error that will produce a TypeScript compile error.
🐛 Proposed fix
- renderCell: (item: Collection) => (
+ renderCell: (item: CaptureSet) => (
<BasicTableCell value={item.numImagesProcessedLabel} />
),📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| renderCell: (item: Collection) => ( | |
| <BasicTableCell value={item.numImagesProcessedLabel} /> | |
| renderCell: (item: CaptureSet) => ( | |
| <BasicTableCell value={item.numImagesProcessedLabel} /> | |
| ), |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ui/src/pages/project/capture-sets/capture-set-columns.tsx` around lines 113 -
114, The renderCell parameter is typed as Collection but that type isn't
imported—replace the incorrect type with CaptureSet (i.e., change the renderCell
signature from item: Collection to item: CaptureSet) to match the other
renderCell entries and ensure CaptureSet is imported at the top of the file so
the BasicTableCell usage of item.numImagesProcessedLabel compiles.
2 participants
Summary
If a pipeline doesn't return detections but still successfully processed the image, it will have a "null" detection.
List of Changes
Related Issues
Closes #484
How to Test the Changes
docker compose run --rm django python manage.py test -k test_image_with_null_detection --failfast --pdbScreenshots
Example of non-null detection
Example of null detection
Example of no processing/detections
Deployment Notes
Include instructions if this PR requires specific steps for its deployment (database migrations, config changes, etc.)
Checklist
Summary by CodeRabbit
Release Notes
New Features
Bug Fixes